Yi Ren

EAAI Journal 2026 Journal Article

Quantum-inspired neural networks with stochastic dynamics for multimodal sentiment analysis and sarcasm detection

• Kehuan Yan
• Peichao Lai
• Xianghan Zheng
• Yang Yang
• Yi Ren
• Tuyatsetseg Badarch
• Yiwei Chen

EAAI Journal 2025 Journal Article

Adaptive Coordinated Motion Planning for lower limb exoskeleton robots with a robotic walker

• Chaobin Zou
• Yi Ren
• Rui Huang
• Xinhao Zhang
• Jingting Zhang
• Zhinan Peng
• Hong Cheng

NeurIPS Conference 2025 Conference Paper

ASGO: Adaptive Structured Gradient Optimization

• Kang An
• Yuxing Liu
• Rui Pan
• Yi Ren
• Shiqian Ma
• Donald Goldfarb
• Tong Zhang

Training deep neural networks (DNNs) is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than simple vectors. Under this structural representation, it has been widely observed that gradients are low-rank and Hessians are approximately block-wise diagonal. These structured properties are crucial for designing efficient optimization algorithms but may not be utilized by current popular optimizers like Adam. In this paper, we present a novel optimization algorithm ASGO that capitalizes on these properties by employing a preconditioner that is adaptively updated using structured gradients. By fine-grained theoretical analysis, ASGO is proven to achieve superior convergence rates compared to existing structured gradient methods. Based on the convergence theory, we further demonstrate that ASGO can benefit from the low-rank and block-wise diagonal properties. We also discuss practical modifications of ASGO and empirically verify the effectiveness of the algorithm on language model tasks.

ICLR Conference 2025 Conference Paper

Learning Dynamics of LLM Finetuning

• Yi Ren
• Danica J. Sutherland

Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning dynamics of large language models during different types of finetuning, by analyzing the step-wise decomposition of how influence accumulates among different potential responses. Our framework allows a uniform interpretation of many interesting observations about the training of popular algorithms for both instruction tuning and preference tuning. In particular, we propose a hypothetical explanation of why specific types of hallucination are strengthened after finetuning, e.g., the model might use phrases or facts in the response for question B to answer question A, or the model might keep repeating similar simple phrases when generating responses. We also extend our framework and highlight a unique ``squeezing effect'' to explain a previously observed phenomenon in off-policy direct preference optimization (DPO), where running DPO for too long makes even the desired outputs less likely. This framework also provides insights into where the benefits of on-policy DPO and other variants come from. The analysis not only provides a novel perspective of understanding LLM's finetuning but also inspires a simple, effective method to improve alignment performance.

NeurIPS Conference 2025 Conference Paper

On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization

• wenlong deng
• Yi Ren
• Muchen Li
• Danica J. Sutherland
• Xiaoxiao Li
• Christos Thrampoulidis

Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a widely used algorithm in recent systems. Despite GRPO's widespread adoption, we identify a previously unrecognized phenomenon we term Lazy Likelihood Displacement (LLD), wherein the likelihood of correct responses marginally increases or even decreases during training. This behavior mirrors a recently discovered misalignment issue in Direct Preference Optimization (DPO), attributed to the influence of negative gradients. We provide a theoretical analysis of GRPO’s learning dynamic, identifying the source of LLD as the naive penalization of all tokens in incorrect responses with the same strength. To address this, we develop a method called NTHR, which downweights penalties on tokens contributing to the LLD. Unlike prior DPO-based approaches, NTHR takes advantage of GRPO’s group-based structure, using correct responses as anchors to identify influential tokens. Experiments on math reasoning benchmarks demonstrate that NTHR effectively mitigates LLD, yielding consistent performance gains across models ranging from 0. 5B to 3B parameters.

ICRA Conference 2025 Conference Paper

Physics-Informed Split Koopman Operators for Data-Efficient Soft Robotic Simulation

• Eron Ristich
• Lei Zhang
• Yi Ren
• Jiefeng Sun

Koopman operator theory provides a powerful data-driven technique for modeling nonlinear dynamical systems in a linear framework, in comparison to computationally expensive and highly nonlinear physics-based simulations. However, Koopman operator-based models for soft robots are very high dimensional and require considerable amounts of data to properly resolve. Inspired by physics-informed techniques from machine learning, we present a novel physics-informed Koopman operator identification method that improves simulation accuracy for small dataset sizes. Through Strang splitting, the method takes advantage of both continuous and discrete Koopman operator approximation to obtain information both from trajectory and phase space data. The method is validated on a tendon-driven soft robotic arm, showing orders of magnitude improvement over standard methods in terms of the shape error. We envision this method can significantly reduce the data requirement of Koopman operators for systems with partially known physical models, and thus reduce the cost of obtaining data. More info: https://sunrobotics.lab.asu.edu/blog/2024/ristich-icra-2025/

IROS Conference 2025 Conference Paper

Successor Features for Transfer in Alternating Markov Games

• Sunny Amatya
• Yi Ren
• Zhe Xu 0005
• Wenlong Zhang

This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a "jump start" for agents when facing new tasks with varying reward structures. However, knowledge transfer in games typically relies on value and equilibrium transfers, which heavily depends on the similarity between tasks. This reliance can lead to failures when the tasks differ significantly. To address this issue, this paper presents an application of successor features to games and presents a novel algorithm called Game Generalized Policy Improvement (GGPI), designed to address Markov games in multi-agent reinforcement learning. The proposed algorithm enables the transfer of learning values and policies across games. An upper bound of the errors for transfer is derived as a function the similarity of the task. Through experiments with a turn-based pursuer-evader game, we demonstrate that the GGPI algorithm can generate high-reward interactions and one-shot policy transfer. When further tested in a wider set of initial conditions, the GGPI algorithm achieves higher success rates with improved path efficiency compared to those of the baseline algorithms.

JBHI Journal 2025 Journal Article

Taming Unleashed Large Language Models With Blockchain for Massive Personalized Reliable Healthcare

• Lianshan Sun
• Diandong Liu
• Maoxue Wang
• Yongyi Han
• Yanqing Zhang
• Biwei Zhou
• Yi Ren
• Peng Zhu

The digital health field's pursuit of massive, personalized healthcare continuously faces constraints from doctors' resources and capacity limitations. Recently, the emergence of large language models (LLMs), with their remarkable comprehension and processing abilities, has revolutionized digital health and enhanced massive, personalized healthcare. Although these LLMs have achieved significant advancements, they have also introduced inevitable hallucinations, which impact patient safety when used in massive applications. To address these challenges, this study proposes a digital hospital for a massive, personalized, reliable healthcare service named the Chat Chain-Brain-based Doctor (CHATCBD). In addition, this study transforms the LLM-based diagnostic process into a digital hospital architecture, designs a controllable AI agents framework, and develops a self-audit mechanism to enhance their reliability. The proposed CHATCBD uses blockchain technology to decentralize external regulation of the LLMs' personalized diagnoses. It introduces a blockchain-based personalized routing management mechanism to improve patient-centered decision-making and designs a blockchain-based audit framework based on a proposed mathematical model that ensures both the professionalism and honesty of audits, serving as a safety net for addressing LLM hallucinations. The results of extensive experiments conducted on 13 datasets from multiple perspectives demonstrate that the proposed CHATCBD system can significantly enhance the capabilities of LLMs in personalized healthcare.

TMLR Journal 2024 Journal Article

AdaFlood: Adaptive Flood Regularization

• Wonho Bae
• Yi Ren
• Mohamed Osama Ahmed
• Frederick Tung
• Danica J. Sutherland
• Gabriel L. Oliveira

Although neural networks are conventionally optimized towards zero training loss, it has been recently learned that targeting a non-zero training loss threshold, referred to as a flood level, often enables better test time generalization. Current approaches, however, apply the same constant flood level to all training samples, which inherently assumes all the samples have the same difficulty. We present AdaFlood, a novel flood regularization method that adapts the flood level of each training sample according to the difficulty of the sample. Intuitively, since training samples are not equal in difficulty, the target training loss should be conditioned on the instance. Experiments on datasets covering four diverse input modalities -- text, images, asynchronous event sequences, and tabular -- demonstrate the versatility of AdaFlood across data domains and noise levels.

AAAI Conference 2024 Conference Paper

AMD: Autoregressive Motion Diffusion

• Bo Han
• Hao Peng
• Minjing Dong
• Yi Ren
• Yixuan Shen
• Chang Xu

Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple motion patterns, they encounter difficulties when dealing with long prompts or complex motions. The challenges are two-fold: 1) the scarcity of human motion-captured data for long prompts and complex motions. 2) the high diversity of human motions in the temporal domain and the substantial divergence of distributions from conditional modalities, leading to a many-to-many mapping problem when generating motion with complex and long texts. In this work, we address these gaps by 1) elaborating the first dataset pairing long textual descriptions and 3D complex motions (HumanLong3D), and 2) proposing an autoregressive motion diffusion model (AMD). Specifically, AMD integrates the text prompt at the current timestep with the text prompt and action sequences at the previous timestep as conditional information to predict the current action sequences in an iterative manner. Furthermore, we present its generalization for X-to-Motion with “No Modality Left Behind”, enabling for the first time the generation of high-definition and high-fidelity human motions based on user-defined modality input.

AAAI Conference 2024 System Paper

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

• Rongjie Huang
• Mingze Li
• Dongchao Yang
• Jiatong Shi
• Xuankai Chang
• Zhenhui Ye
• Yuning Wu
• Zhiqing Hong

Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spoken dialogue. With an increasing demand to evaluate multi-modal LLMs of human intention understanding and cooperation with foundation models, we outline the principles and processes and test AudioGPT in terms of consistency, capability, and robustness. Experimental results demonstrate the capabilities of AudioGPT in solving 16 AI tasks with speech, music, sound, and talking head understanding and generation in multi-round dialogues, which empower humans to create rich and diverse audio content with unprecedented ease. Code can be found in https://github.com/AIGC-Audio/AudioGPT

NeurIPS Conference 2024 Conference Paper

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective

• Yi Ren
• Shangmin Guo
• Linlu Qiu
• Bailin Wang
• Danica J. Sutherland

With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round on-policy self-improving methods allow LLMs to generate new examples for training subsequent models. At the same time, multi-agent LLM systems, involving automated interactions among agents, are also increasing in prominence. Thus, in both short and long terms, LLMs may actively engage in an evolutionary process. We draw parallels between the behavior of LLMs and the evolution of human culture, as the latter has been extensively studied by cognitive scientists for decades. Our approach involves leveraging Iterated Learning (IL), a Bayesian framework that elucidates how subtle biases are magnified during human cultural evolution, to explain some behaviors of LLMs. This paper outlines key characteristics of agents' behavior in the Bayesian-IL framework, including predictions that are supported by experimental verification with various LLMs. This theoretical framework could help to more effectively predict and guide the evolution of LLMs in desired directions.

AAAI Conference 2024 Conference Paper

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling

• Rui Liu
• Yifan Hu
• Yi Ren
• Xiang Yin
• Haizhou Li

Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not thoroughly investigated the emotional expressiveness problems due to the scarcity of emotional conversational datasets and the difficulty of stateful emotion modeling. In this paper, we propose a novel emotional CSS model, termed ECSS, that includes two main components: 1) to enhance emotion understanding, we introduce a heterogeneous graph-based emotional context modeling mechanism, which takes the multi-source dialogue history as input to model the dialogue context and learn the emotion cues from the context; 2) to achieve emotion rendering, we employ a contrastive learning-based emotion renderer module to infer the accurate emotion style for the target utterance. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity, and annotate additional emotional information on the existing conversational dataset (DailyTalk). Both objective and subjective evaluations suggest that our model outperforms the baseline models in understanding and rendering emotions. These evaluations also underscore the importance of comprehensive emotional annotations. Code and audio samples can be found at: https://github.com/walker-hyf/ECSS.

IJCAI Conference 2024 Conference Paper

Hacking Task Confounder in Meta-Learning

• Jingyao Wang
• Yi Ren
• Zeen Song
• Jianqi Zhang
• Changwen Zheng
• Wenwen Qiang

Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization performance. However, our experiments reveal an unexpected result: there is negative knowledge transfer between tasks, affecting generalization performance. To explain this phenomenon, we conduct Structural Causal Models (SCMs) for causal analysis. Our investigation uncovers the presence of spurious correlations between task-specific causal factors and labels in meta-learning. Furthermore, the confounding factors differ across different batches. We refer to these confounding factors as ``Task Confounders". Based on these findings, we propose a plug-and-play Meta-learning Causal Representation Learner (MetaCRL) to eliminate task confounders. It encodes decoupled generating factors from multiple tasks and utilizes an invariant-based bi-level optimization mechanism to ensure their causality for meta-learning. Extensive experiments on various benchmark datasets demonstrate that our work achieves state-of-the-art (SOTA) performance. The code is provided in https: //github. com/WangJingyao07/MetaCRL.

ICLR Conference 2024 Conference Paper

lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning

• Shangmin Guo
• Yi Ren
• Stefano V. Albrecht
• Kenny Smith

Although much research has been done on proposing new models or loss functions to improve the generalisation of artificial neural networks (ANNs), less attention has been directed to the impact of the training data on generalisation. In this work, we start from approximating the interaction between samples, i.e. how learning one sample would modify the model's prediction on other samples. Through analysing the terms involved in weight updates in supervised learning, we find that labels influence the interaction between samples. Therefore, we propose the labelled pseudo Neural Tangent Kernel (lpNTK) which takes label information into consideration when measuring the interactions between samples. We first prove that lpNTK asymptotically converges to the empirical neural tangent kernel in terms of the Frobenius norm under certain assumptions. Secondly, we illustrate how lpNTK helps to understand learning phenomena identified in previous work, specifically the learning difficulty of samples and forgetting events during learning. Moreover, we also show that using lpNTK to identify and remove poisoning training samples does not hurt the generalisation performance of ANNs.

NeurIPS Conference 2024 Conference Paper

MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes

• Zhenhui Ye
• Tianyun Zhong
• Yi Ren
• Ziyue Jiang
• Jiawei Huang
• Rongjie Huang
• Jinglin Liu
• JinZheng He

Talking face generation (TFG) aims to animate a target identity's face to create realistic talking videos. Personalized TFG is a variant that emphasizes the perceptual identity similarity of the synthesized result (from the perspective of appearance and talking style). While previous works typically solve this problem by learning an individual neural radiance field (NeRF) for each identity to implicitly store its static and dynamic information, we find it inefficient and non-generalized due to the per-identity-per-training framework and the limited training data. To this end, we propose MimicTalk, the first attempt that exploits the rich knowledge from a NeRF-based person-agnostic generic model for improving the efficiency and robustness of personalized TFG. To be specific, (1) we first come up with a person-agnostic 3D TFG model as the base model and propose to adapt it into a specific identity; (2) we propose a static-dynamic-hybrid adaptation pipeline to help the model learn the personalized static appearance and facial dynamic features; (3) To generate the facial motion of the personalized talking style, we propose an in-context stylized audio-to-motion model that mimics the implicit talking style provided in the reference video without information loss by an explicit style representation. The adaptation process to an unseen identity can be performed in 15 minutes, which is 47 times faster than previous person-dependent methods. Experiments show that our MimicTalk surpasses previous baselines regarding video quality, efficiency, and expressiveness. Video samples are available at https: //mimictalk. github. io.

IROS Conference 2024 Conference Paper

ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition

• Weidong Xie
• Lun Luo
• Nanfei Ye
• Yi Ren
• Shaoyi Du
• Minhang Wang
• Jintao Xu 0001
• Rui Ai 0001

Place recognition is an important task for robots and autonomous cars to localize themselves and close loops in pre-built maps. While single-modal sensor-based methods have shown satisfactory performance, cross-modal place recognition that retrieving images from a point-cloud database remains a challenging problem. Current cross-modal methods transform images into 3D points using depth estimation for modality conversion, which are usually computationally intensive and need expensive labeled data for depth supervision. In this work, we introduce a fast and lightweight framework to encode images and point clouds into place-distinctive descriptors. We propose an effective Field of View (FoV) transformation module to convert point clouds into an analogous modality as images. This module eliminates the necessity for depth estimation and helps subsequent modules achieve real-time performance. We further design a non-negative factorization-based encoder to extract mutually consistent semantic features between point clouds and images. This encoder yields more distinctive global descriptors for retrieval. Experimental results on the KITTI dataset show that our proposed methods achieve state-of-the-art performance while running in real time. Additional evaluation on the HAOMO dataset covering a 17 km trajectory further shows the practical generalization capabilities. We have released the implementation of our methods as open source at: https://github.com/haomo-ai/ModaLink.git.

ICML Conference 2024 Conference Paper

State-Constrained Zero-Sum Differential Games with One-Sided Information

• Mukesh Ghimire
• Lei Zhang
• Zhe Xu 0005
• Yi Ren

We study zero-sum differential games with state constraints and one-sided information, where the informed player (Player 1) has a categorical payoff type unknown to the uninformed player (Player 2). The goal of Player 1 is to minimize his payoff without violating the constraints, while that of Player 2 is to violate the state constraints if possible, or to maximize the payoff otherwise. One example of the game is a man-to-man matchup in football. Without state constraints, Cardaliaguet (2007) showed that the value of such a game exists and is convex to the common belief of players. Our theoretical contribution is an extension of this result to games with state constraints and the derivation of the primal and dual subdynamic principles necessary for computing behavioral strategies. Different from existing works that are concerned about the scalability of no-regret learning in games with discrete dynamics, our study reveals the underlying structure of strategies for belief manipulation resulting from information asymmetry and state constraints. This structure will be necessary for scalable learning on games with continuous actions and long time windows. We use a simplified football game to demonstrate the utility of this work, where we reveal player positions and belief states in which the attacker should (or should not) play specific random deceptive moves to take advantage of information asymmetry, and compute how the defender should respond.

ICRA Conference 2023 Conference Paper

Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games

• Lei Zhang
• Mukesh Ghimire
• Wenlong Zhang
• Zhe Xu 0005
• Yi Ren

Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs (HJI) PDEs. Self-supervised learning has been used to approximate solutions of such PDEs while circumventing the curse of dimensionality. However, this method fails to learn discontinuous PDE solutions due to its sampling nature, leading to poor safety performance of the resulting controllers in robotics applications when player rewards are discontinuous. This paper investigates two potential solutions to this problem: a hybrid method that leverages both supervised Nash equilibria and the HJI PDE, and a value-hardening method where a sequence of HJIs are solved with a gradually hardening reward. We compare these solutions using the resulting generalization and safety performance in two vehicle interaction simulation studies with 5D and 9D state spaces, respectively. Results show that with informative supervision (e. g. , collision and near-collision demonstrations) and the low cost of self-supervised learning, the hybrid method achieves better safety performance than the supervised, self-supervised, and value hardening approaches on equal computational budget. Value hardening fails to generalize in the higher-dimensional case without informative supervision. Lastly, we show that the neural activation function needs to be continuously differentiable for learning PDEs and its choice can be case dependent.

ICML Conference 2023 Conference Paper

Attributing Image Generative Models using Latent Fingerprints

• Guangyu Nie
• Changhoon Kim
• Yezhou Yang
• Yi Ren

Generative models have enabled the creation of contents that are indistinguishable from those taken from nature. Open-source development of such models raised concerns about the risks of their misuse for malicious purposes. One potential risk mitigation strategy is to attribute generative models via fingerprinting. Current fingerprinting methods exhibit a significant tradeoff between robust attribution accuracy and generation quality while lacking design principles to improve this tradeoff. This paper investigates the use of latent semantic dimensions as fingerprints, from where we can analyze the effects of design variables, including the choice of fingerprinting dimensions, strength, and capacity, on the accuracy-quality tradeoff. Compared with previous SOTA, our method requires minimum computation and is more applicable to large-scale models. We use StyleGAN2 and the latent diffusion model to demonstrate the efficacy of our method.

ICML Conference 2023 Conference Paper

FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning

• Congyu Qiao
• Ning Xu 0009
• Jiaqi Lv
• Yi Ren
• Xin Geng 0001

To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguation, i. e. , identification of the correct label in the candidate label set, adopted in most PLL methods. However, this assumption is impractical as no one could guarantee the existence of the correct label in the candidate label set under real-world scenarios. Therefore, Unreliable Partial Label Learning (UPLL) is investigated where the correct label of each example may not exist in the candidate label set. In this paper, we propose a fusion framework of refinement and disambiguation named FREDIS to handle the UPLL problem. Specifically, with theoretical guarantees, not only does disambiguation move incorrect labels from candidate labels to non-candidate labels but also refinement, an opposite procedure, moves correct labels from non-candidate labels to candidate labels. Besides, we prove that the classifier trained by our framework could eventually approximate the Bayes optimal classifier. Extensive experiments on widely used benchmark datasets validate the effectiveness of our proposed framework.

ICLR Conference 2023 Conference Paper

How to prepare your task head for finetuning

• Yi Ren
• Shangmin Guo
• Wonho Bae
• Danica J. Sutherland

In the era of deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually different. Although there exist many different designs for finetuning, a full understanding of when and why these algorithms work has been elusive. We analyze how the choice of task head controls feature adaptation and hence influences the downstream performance. By decomposing the feature's learning dynamics, we find the key aspect is the training accuracy and loss at the beginning of finetuning, which determines the "energy" available for the feature's adaptation. We identify a significant trend in the effect of changes in this initial energy on the resulting features after finetuning. Specifically, as the energy increases, the Euclidean and cosine distances between the resulting and original features increase, while their dot product (and the resulting features’ norm) first increases and then decreases. Inspired by this, we give several practical principles that lead to better downstream performance. We analytically prove this trend in an overparamterized linear setting and verify its applicability to different experimental settings.

NeurIPS Conference 2023 Conference Paper

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

• Yi Ren
• Samuel Lavoie
• Michael Galkin
• Danica J. Sutherland
• Aaron C. Courville

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process, "iterated learning, " to help explain how human language developed this ability; the theory rests on simultaneous pressures towards compressibility (when an ignorant agent learns from an informed one) and expressivity (when it uses the representation for downstream tasks). Inspired by this process, we propose to improve the compositional generalization of deep networks by using iterated learning on models with simplicial embeddings, which can approximately discretize representations. This approach is further motivated by an analysis of compositionality based on Kolmogorov complexity. We show that this combination of changes improves compositional generalization over other approaches, demonstrating these improvements both on vision tasks with well-understood latent factors and on real molecular graph prediction tasks where the latent structure is unknown.

NeurIPS Conference 2023 Conference Paper

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

• Pengfei Wei
• Lingdong Kong
• Xinghua Qu
• Yi Ren
• Zhiqiang Xu
• Jing Jiang
• Xiang Yin

Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through disentanglement. Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information. A Transfer Sequential VAE (TranSVAE) framework is then developed to model such generation. To better serve for adaptation, we propose several objectives to constrain the latent factors. With these constraints, the spatial divergence can be readily removed by disentangling the static domain-specific information out, and the temporal divergence is further reduced from both frame- and video-levels through adversarial learning. Extensive experiments on the UCF-HMDB, Jester, and Epic-Kitchens datasets verify the effectiveness and superiority of TranSVAE compared with several state-of-the-art approaches.

ICLR Conference 2022 Conference Paper

Better Supervisory Signals by Observing Learning Paths

• Yi Ren
• Shangmin Guo
• Danica J. Sutherland

Better-supervised models might have better performance. In this paper, we first clarify what makes for good supervision for a classification problem, and then explain two existing label refining methods, label smoothing and knowledge distillation, in terms of our proposed criterion. To further answer why and how better supervision emerges, we observe the learning path, i.e., the trajectory of the model's predictions during training, for each training sample. We find that the model can spontaneously refine "bad" labels through a "zig-zag" learning path, which occurs on both toy and real datasets. Observing the learning path not only provides a new perspective for understanding knowledge distillation, overfitting, and learning dynamics, but also reveals that the supervisory signal of a teacher network can be very unstable near the best points in training on real tasks. Inspired by this, we propose a new knowledge distillation scheme, Filter-KD, which improves downstream classification performance in various settings.

NeurIPS Conference 2022 Conference Paper

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

• Ziyue Jiang
• Zhe Su
• Zhou Zhao
• Qian Yang
• Yi Ren
• Jinglin Liu
• 振辉 叶

Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts from language experts, making it difficult to extend high-quality neural TTS systems to out-of-domain daily conversations and countless languages worldwide. This paper tackles the polyphone disambiguation problem from a concise and novel perspective: we propose Dict-TTS, a semantic-aware generative text-to-speech model with an online website dictionary (the existing prior information in the natural language). Specifically, we design a semantics-to-pronunciation attention (S2PA) module to match the semantic patterns between the input text sequence and the prior semantics in the dictionary and obtain the corresponding pronunciations; The S2PA module can be easily trained with the end-to-end TTS model without any annotated phoneme labels. Experimental results in three languages show that our model outperforms several strong baseline models in terms of pronunciation accuracy and improves the prosody modeling of TTS systems. Further extensive analyses demonstrate that each design in Dict-TTS is effective. The code is available at https: //github. com/Zain-Jiang/Dict-TTS.

AAAI Conference 2022 Conference Paper

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

• Jinglin Liu
• Chengxi Li
• Yi Ren
• Feiyang Chen
• Zhou Zhao

Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e. g. , melspectrogram) given a music score. Previous singing acoustic models adopt a simple loss (e. g. , L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from over-smoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. DiffSinger is a parameterized Markov chain that iteratively converts the noise into mel-spectrogram conditioned on the music score. By implicitly optimizing variational bound, DiffSinger can be stably trained and generate realistic outputs. To further improve the voice quality and speed up inference, we introduce a shallow diffusion mechanism to make better use of the prior knowledge learned by the simple loss. Specifically, DiffSinger starts generation at a shallow step smaller than the total number of diffusion steps, according to the intersection of the diffusion trajectories of the ground-truth mel-spectrogram and the one predicted by a simple mel-spectrogram decoder. Besides, we propose boundary prediction methods to locate the intersection and determine the shallow step adaptively. The evaluations conducted on a Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work. Extensional experiments also prove the generalization of our methods on text-to-speech task (DiffSpeech). Audio samples: https: //diffsinger. github. io. Codes: https: //github. com/ MoonInTheRiver/DiffSinger.

IJCAI Conference 2022 Conference Paper

EditSinger: Zero-Shot Text-Based Singing Voice Editing System with Diverse Prosody Modeling

• Lichao Zhang
• Zhou Zhao
• Yi Ren
• Liqun Deng

Zero-shot text-based singing editing enables singing voice modification based on the given edited lyrics without any additional data from the target singer. However, due to the different demands, challenges occur when applying existing speech editing methods to singing voice editing task, mainly including the lack of systematic consideration concerning prosody in insertion and deletion, as well as the trade-off between the naturalness of pronunciation and the preservation of prosody in replacement. In this paper we propose EditSinger, which is a novel singing voice editing model with specially designed diverse prosody modules to overcome the challenges above. Specifically, 1) a general masked variance adaptor is introduced for the comprehensive prosody modeling of the inserted lyrics and the transition of deletion boundary; and 2) we further design a fusion pitch predictor for replacement. By disentangling the reference pitch and fusing the predicted pronunciation, the edited pitch can be reconstructed, which could ensure a natural pronunciation while preserving the prosody of the original audio. In addition, to the best of our knowledge, it is the first zero-shot text-based singing voice editing system. Our experiments conducted on the OpenSinger prove that EditSinger can synthesize high-quality edited singing voices with natural prosody according to the corresponding operations.

ICLR Conference 2022 Conference Paper

Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability

• Shangmin Guo
• Yi Ren
• Kory Wallace Mathewson
• Simon Kirby
• Stefano V. Albrecht
• Kenny Smith

Researchers are using deep learning models to explore the emergence of language in various language games, where agents interact and develop an emergent language to solve tasks. We focus on the factors that determine the expressivity of emergent languages, which reflects the amount of information about input spaces those languages are capable of encoding. We measure the expressivity of emergent languages based on the generalisation performance across different games, and demonstrate that the expressivity of emergent languages is a trade-off between the complexity and unpredictability of the context those languages emerged from. Another contribution of this work is the discovery of message type collapse, i.e. the number of unique messages is lower than that of inputs. We also show that using the contrastive loss proposed by Chen et al. (2020) can alleviate this problem.

IJCAI Conference 2022 Conference Paper

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

• Rongjie Huang
• Max W. Y. Lam
• Jun Wang
• Dan Su
• Dong Yu
• Yi Ren
• Zhou Zhao

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e. g. , Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4. 28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at https: //FastDiff. github. io/.

AAAI Conference 2022 Conference Paper

Flow-Based Unconstrained Lip to Speech Generation

• JinZheng He
• Zhou Zhao
• Yi Ren
• Jinglin Liu
• Baoxing Huai
• Nicholas Yuan

Unconstrained lip-to-speech aims to generate corresponding speeches based on silent facial videos with no restriction to head pose or vocabulary. It is desirable to generate intelligible and natural speech with a fast speed in unconstrained settings. Currently, to handle the more complicated scenarios, most existing methods adopt the autoregressive architecture, which is optimized with the MSE loss. Although these methods have achieved promising performance, they are prone to bring issues including high inference latency and melspectrogram over-smoothness. To tackle these problems, we propose a novel flow-based non-autoregressive lip-to-speech model (GlowLTS) to break autoregressive constraints and achieve faster inference. Concretely, we adopt a flow-based decoder which is optimized by maximizing the likelihood of the training data and is capable of more natural and fast speech generation. Moreover, we devise a condition module to improve the intelligibility of generated speech. We demonstrate the superiority of our proposed method through objective and subjective evaluation on Lip2Wav-Chemistry- Lectures and Lip2Wav-Chess-Analysis datasets. Our demo video can be found at https: //glowlts. github. io/.

NeurIPS Conference 2022 Conference Paper

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

• Rongjie Huang
• Yi Ren
• Jinglin Liu
• Chenye Cui
• Zhou Zhao

Style transfer for out-of-domain (OOD) speech synthesis aims to generate speech samples with unseen style (e. g. , speaker identity, emotion, and prosody) derived from an acoustic reference, while facing the following challenges: 1) The highly dynamic style features in expressive voice are difficult to model and transfer; and 2) the TTS models should be robust enough to handle diverse OOD conditions that differ from the source data. This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice. GenerSpeech decomposes the speech variation into the style-agnostic and style-specific parts by introducing two components: 1) a multi-level style adaptor to efficiently model a large range of style conditions, including global speaker and emotion characteristics, and the local (utterance, phoneme, and word-level) fine-grained prosodic representations; and 2) a generalizable content adaptor with Mix-Style Layer Normalization to eliminate style information in the linguistic content representation and thus improve model generalization. Our evaluations on zero-shot style transfer demonstrate that GenerSpeech surpasses the state-of-the-art models in terms of audio quality and style similarity. The extension studies to adaptive style transfer further show that GenerSpeech performs robustly in the few-shot data setting. Audio samples are available at \url{https: //GenerSpeech. github. io/}.

NeurIPS Conference 2022 Conference Paper

M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus

• Lichao Zhang
• Ruiqi Li
• Shoutong Wang
• Liqun Deng
• Jinglin Liu
• Yi Ren
• JinZheng He
• Rongjie Huang

The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Multi-singer Mandarin singing collection with elaborately annotated Musical scores as well as its benchmarks. Specifically, 1) we construct and release a large high-quality Chinese singing voice corpus, which is recorded by 20 professional singers, covering 700 Chinese pop songs as well as all the four SATB types (i. e. , soprano, alto, tenor, and bass); 2) we take extensive efforts to manually compose the musical scores for each recorded song, which are necessary to the study of the prosody modeling for SVS. 3) To facilitate the use and demonstrate the quality of M4Singer, we conduct four different benchmark experiments: score-based SVS, controllable singing voice (CSV), singing voice conversion (SVC) and automatic music transcription (AMT).

AAAI Conference 2022 Conference Paper

Parallel and High-Fidelity Text-to-Lip Generation

• Jinglin Liu
• Zhiying Zhu
• Yi Ren
• Wencan Huang
• Baoxing Huai
• Nicholas Yuan
• Zhou Zhao

As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in text-to-lip (T2L) generation. T2L is a challenging task and existing end-to-end works depend on the attention mechanism and autoregressive (AR) decoding manner. However, the AR decoding manner generates current lip frame conditioned on frames generated previously, which inherently hinders the inference speed, and also has a detrimental effect on the quality of generated lip frames due to error propagation. This encourages the research of parallel T2L generation. In this work, we propose a parallel decoding model for fast and high-fidelity text-to-lip generation (ParaLip). Specifically, we predict the duration of the encoded linguistic features and model the target lip frames conditioned on the encoded linguistic features with their duration in a non-autoregressive manner. Furthermore, we incorporate the structural similarity index loss and adversarial learning to improve perceptual quality of generated lip frames and alleviate the blurry prediction problem. Extensive experiments conducted on GRID and TCD-TIMIT datasets demonstrate the superiority of proposed methods.

IJCAI Conference 2022 Conference Paper

SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech

• Zhenhui Ye
• Zhou Zhao
• Yi Ren
• Fei Wu

The recent progress in non-autoregressive text-to-speech (NAR-TTS) has made fast and high-quality speech synthesis possible. However, current NAR-TTS models usually use phoneme sequence as input and thus cannot understand the tree-structured syntactic information of the input sequence, which hurts the prosody modeling. To this end, we propose SyntaSpeech, a syntax-aware and light-weight NAR-TTS model, which integrates tree-structured syntactic information into the prosody modeling modules in PortaSpeech. Specifically, 1) We build a syntactic graph based on the dependency tree of the input sentence, then process the text encoding with a syntactic graph encoder to extract the syntactic information. 2) We incorporate the extracted syntactic encoding with PortaSpeech to improve the prosody prediction. 3) We introduce a multi-length discriminator to replace the flow-based post-net in PortaSpeech, which simplifies the training pipeline and improves the inference speed, while keeping the naturalness of the generated audio. Experiments on three datasets not only show that the tree-structured syntactic information grants SyntaSpeech the ability to synthesize better audio with expressive prosody, but also demonstrate the generalization ability of SyntaSpeech to adapt to multiple languages and multi-speaker text-to-speech. Ablation studies demonstrate the necessity of each component in SyntaSpeech. Source code and audio samples are available at https: //syntaspeech. github. io.

ICRA Conference 2022 Conference Paper

Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns

• Prasanth Buddareddygari
• Travis Zhang
• Yezhou Yang
• Yi Ren

Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous driving. Threat models for these demonstrations are limited to (1) targeted attacks through real-time manipulation of the agent's observation, and (2) untargeted attacks through manipulation of the physical environment. The former assumes full access to the agent's states/observations at all times, while the latter has no control over attack outcomes. This paper investigates the feasibility of targeted attacks through visually learned patterns placed on physical objects in the environment, a threat model that combines the practicality and effectiveness of the existing ones. Through analysis, we demonstrate that a pre-trained policy can be hijacked within a time window, e. g. , performing an unintended self-parking, when an adversarial object is present. To enable the attack, we adopt an assumption that the dynamics of both the environment and the agent can be learned by the attacker. Lastly, we empirically show the effectiveness of the proposed attack on different driving scenarios, perform a location robustness test, and study the tradeoff between the attack strength and its effectiveness Code is available at https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD

IROS Conference 2022 Conference Paper

Toward Global Sensing Quality Maximization: A Configuration Optimization Scheme for Camera Networks

• Xuechao Zhang
• Xuda Ding
• Yi Ren
• Yu Zheng 0001
• Chongrong Fang
• Jianping He 0001

The performance of a camera network monitoring a set of targets depends crucially on the configuration of the cameras. In this paper, we investigate the reconfiguration strategy for the parameterized camera network model, with which the sensing qualities of the multiple targets can be optimized globally and simultaneously. We first propose to use the number of pixels occupied by a unit-length object in image as a metric of the sensing quality of the object, which is determined by the parameters of the camera, such as intrinsic, extrinsic, and distortional coefficients. Then, we form a single quantity that measures the sensing quality of the targets by the camera network. This quantity further serves as the objective function of our optimization problem to obtain the optimal camera configuration. We verify the effectiveness of our approach through extensive simulations and experiments, and the results reveal its improved performance on the AprilTag detection tasks. Codes and related utilities for this work are open-sourced and available at https://github.com/sszxc/MultiCam-Simulation.

ICLR Conference 2021 Conference Paper

Decentralized Attribution of Generative Models

• Changhoon Kim
• Yi Ren
• Yezhou Yang

Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated. Existing studies showed empirical feasibility of attribution through a centralized classifier trained on all existing user-end models. However, this approach is not scalable in a reality where the number of models ever grows. Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model. Each binary classifier is parameterized by a user-specific key and distinguishes its associated model distribution from the authentic data distribution. We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets. We also examine the trade-off between generation quality and robustness of attribution against adversarial post-processes.

IJCAI Conference 2021 Conference Paper

FedSpeech: Federated Text-to-Speech with Continual Learning

• Ziyue Jiang
• Yi Ren
• Ming Lei
• Zhou Zhao

Federated learning enables collaborative training of machine learning models under strict privacy restrictions and federated text-to-speech aims to synthesize natural speech of multiple users with a few audio training samples stored in their devices locally. However, federated text-to-speech faces several challenges: very few training samples from each speaker are available, training samples are all stored in local device of each user, and global model is vulnerable to various attacks. In this paper, we propose a novel federated learning architecture based on continual learning approaches to overcome the difficulties above. Specifically, 1) we use gradual pruning masks to isolate parameters for preserving speakers' tones; 2) we apply selective masks for effectively reusing knowledge from tasks; 3) a private speaker embedding is introduced to keep users' privacy. Experiments on a reduced VCTK dataset demonstrate the effectiveness of FedSpeech: it nearly matches multi-task training in terms of multi-speaker speech quality; moreover, it sufficiently retains the speakers' tones and even outperforms the multi-task training in the speaker similarity experiment.

NeurIPS Conference 2021 Conference Paper

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

• Yi Ren
• Jinglin Liu
• Zhou Zhao

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e. g. , prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. Specifically, 1) to model both the prosody and mel-spectrogram details accurately, we adopt a lightweight VAE with an enhanced prior followed by a flow-based post-net with strong conditional inputs as the main architecture. 2) To further compress the model size and memory footprint, we introduce the grouped parameter sharing mechanism to the affine coupling layers in the post-net. 3) To improve the expressiveness of synthesized speech and reduce the dependency on accurate fine-grained alignment between text and speech, we propose a linguistic encoder with mixture alignment combining hard word-level alignment and soft phoneme-level alignment, which explicitly extracts word-level semantic information. Experimental results show that PortaSpeech outperforms other TTS models in both voice quality and prosody modeling in terms of subjective and objective evaluation metrics, and shows only a slight performance degradation when reducing the model parameters to 6. 7M (about 4x model size and 3x runtime memory compression ratio compared with FastSpeech 2). Our extensive ablation studies demonstrate that each design in PortaSpeech is effective.

AAAI Conference 2021 Conference Paper

SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint

• Zhonghao Sheng
• Kaitao Song
• Xu Tan
• Yi Ren
• Wei Ye
• Shikun Zhang
• Tao Qin

Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-tomelody generation and melody-to-lyric generation are two important tasks, both of which usually suffer from the following challenges: 1) the paired lyric and melody data are limited, which affects the generation quality of the two tasks, considering a lot of paired training data are needed due to the weak correlation between lyric and melody; 2) Strict alignments are required between lyric and melody, which relies on specific alignment modeling. In this paper, we propose SongMASS to address the above challenges, which leverages masked sequence to sequence (MASS) pre-training and attention based alignment modeling for lyric-to-melody and melody-to-lyric generation. Specifically, 1) we extend the original sentence-level MASS pre-training to song level to better capture long contextual information in music, and use a separate encoder and decoder for each modality (lyric or melody); 2) we leverage sentence-level attention mask and token-level attention constraint during training to enhance the alignment between lyric and melody. During inference, we use a dynamic programming strategy to obtain the alignment between each word/syllable in lyric and note in melody. We pre-train SongMASS on unpaired lyric and melody datasets, and both objective and subjective evaluations demonstrate that SongMASS generates lyric and melody with significantly better quality than the baseline method.

NeurIPS Conference 2021 Conference Paper

Tensor Normal Training for Deep Learning Models

• Yi Ren
• Donald Goldfarb

Despite the predominant use of first-order methods for training deep learning models, second-order methods, and in particular, natural gradient methods, remain of interest because of their potential for accelerating training through the use of curvature information. Several methods with non-diagonal preconditioning matrices, including KFAC, Shampoo, and K-BFGS, have been proposed and shown to be effective. Based on the so-called tensor normal (TN) distribution, we propose and analyze a brand new approximate natural gradient method, Tensor Normal Training (TNT), which like Shampoo, only requires knowledge of the shape of the training parameters. By approximating the probabilistically based Fisher matrix, as opposed to the empirical Fisher matrix, our method uses the block-wise covariance of the sampling based gradient as the pre-conditioning matrix. Moreover, the assumption that the sampling-based (tensor) gradient follows a TN distribution, ensures that its covariance has a Kronecker separable structure, which leads to a tractable approximation to the Fisher matrix. Consequently, TNT's memory requirements and per-iteration computational costs are only slightly higher than those for first-order methods. In our experiments, TNT exhibited superior optimization performance to state-of-the-art first-order methods, and comparable optimization performance to the state-of-the-art second-order methods KFAC and Shampoo. Moreover, TNT demonstrated its ability to generalize as well as first-order methods, while using fewer epochs.

AAAI Conference 2021 Conference Paper

UWSpeech: Speech to Speech Translation for Unwritten Languages

• Chen Zhang
• Xu Tan
• Yi Ren
• Tao Qin
• Kejun Zhang
• Tie-Yan Liu

Existing speech to speech translation systems heavily rely on the text of target language: they usually translate source language either to target text and then synthesize target speech from text, or directly to target speech with target text for auxiliary training. However, those methods cannot be applied to unwritten target languages, which have no written text or phoneme available. In this paper, we develop a translation system for unwritten languages, named as UWSpeech, which converts target unwritten speech into discrete tokens with a converter, and then translates source-language speech into target discrete tokens with a translator, and finally synthesizes target speech from target discrete tokens with an inverter. We propose a method called XL-VAE, which enhances vector quantized variational autoencoder (VQ-VAE) with cross-lingual (XL) speech recognition, to train the converter and inverter of UWSpeech jointly. Experiments on Fisher Spanish-English conversation translation dataset show that UWSpeech outperforms direct translation and VQ-VAE baseline by about 16 and 10 BLEU points respectively, which demonstrate the advantages and potentials of UWSpeech.

ICRA Conference 2021 Conference Paper

When Shall I Be Empathetic? The Utility of Empathetic Parameter Estimation in Multi-Agent Interactions

• Yi Chen
• Lei Zhang
• Tanner Merry
• Sunny Amatya
• Wenlong Zhang
• Yi Ren

Human-robot interactions (HRI) can be modeled as differential games with incomplete information, where each agent holds private reward parameters. Due to the open challenge in finding perfect Bayesian equilibria of such games, existing studies often decouple the belief and physical dynamics by iterating between belief update and motion planning. Importantly, the robot’s reward parameters are often assumed to be known to the humans, in order to simplify the computation. We show in this paper that under this simplification, the robot performs non-empathetic belief update about the humans’ parameters, which causes high safety risks in uncontrolled intersection scenarios. In contrast, we propose a model for empathetic belief update, where the agent updates the joint probabilities of all agents’ parameter combinations. The update uses a neural network that approximates the Nash equilibrial action-values of agents. We compare empathetic and non-empathetic belief update methods on a two-vehicle uncontrolled intersection case with short reaction time. Results show that when both agents are unknowingly aggressive (or non-aggressive), empathy is necessary for avoiding collisions when agents have false believes about each others’ parameters. This paper demonstrates the importance of acknowledging the incomplete-information nature of HRI.

ICLR Conference 2020 Conference Paper

Compositional languages emerge in a neural iterated learning model

• Yi Ren
• Shangmin Guo
• Matthieu Labeau
• Shay B. Cohen
• Simon Kirby

The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality is indeed a natural property of language, we may expect it to appear in communication protocols that are created by neural agents via grounded language learning. Inspired by the iterated learning framework, which simulates the process of language evolution, we propose an effective neural iterated learning algorithm that, when applied to interacting neural agents, facilitates the emergence of a more structured type of language. Indeed, these languages provide specific advantages to neural agents during training, which translates as a larger posterior probability, which is then incrementally amplified via the iterated learning procedure. Our experiments confirm our analysis, and also demonstrate that the emerged languages largely improve the generalization of the neural agent communication.

NeurIPS Conference 2020 Conference Paper

Practical Quasi-Newton Methods for Training Deep Neural Networks

• Donald Goldfarb
• Yi Ren
• Achraf Bahamou

We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). In DNN training, the number of variables and components of the gradient n is often of the order of tens of millions and the Hessian has n^2 elements. Consequently, computing and storing a full n times n BFGS approximation or storing a modest number of (step, change in gradient) vector pairs for use in an L-BFGS implementation is out of the question. In our proposed methods, we approximate the Hessian by a block-diagonal matrix and use the structure of the gradient and Hessian to further approximate these blocks, each of which corresponds to a layer, as the Kronecker product of two much smaller matrices. This is analogous to the approach in KFAC, which computes a Kronecker-factored block diagonal approximation to the Fisher matrix in a stochastic natural gradient method. Because the indefinite and highly variable nature of the Hessian in a DNN, we also propose a new damping approach to keep the upper as well as the lower bounds of the BFGS and L-BFGS approximations bounded. In tests on autoencoder feed-forward network models with either nine or thirteen layers applied to three datasets, our methods outperformed or performed comparably to KFAC and state-of-the-art first-order stochastic methods.

IJCAI Conference 2020 Conference Paper

Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation

• Jinglin Liu
• Yi Ren
• Xu Tan
• Chen Zhang
• Tao Qin
• Zhou Zhao
• Tie-Yan Liu

Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share model structure and AT is an easier task than NAT due to the explicit dependency on previous target-side tokens, a natural idea is to gradually shift the model training from the easier AT task to the harder NAT task. To smooth the shift from AT training to NAT training, in this paper, we introduce semi-autoregressive translation (SAT) as intermediate tasks. SAT contains a hyperparameter k, and each k value defines a SAT task with different degrees of parallelism. Specially, SAT covers AT and NAT as its special cases: it reduces to AT when k=1 and to NAT when k=N (N is the length of target sentence). We design curriculum schedules to gradually shift k from 1 to N, with different pacing functions and number of tasks trained at the same time. We called our method as task-level curriculum learning for NAT (TCL-NAT). Experiments on IWSLT14 De-En, IWSLT16 En-De, WMT14 En-De and De-En datasets show that TCL-NAT achieves significant accuracy improvements over previous NAT baselines and reduces the performance gap between NAT and AT models to 1-2 BLEU points, demonstrating the effectiveness of our proposed method.

NeurIPS Conference 2019 Conference Paper

FastSpeech: Fast, Robust and Controllable Text to Speech

• Yi Ren
• Yangjun Ruan
• Xu Tan
• Tao Qin
• Sheng Zhao
• Zhou Zhao
• Tie-Yan Liu

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e. g. , Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i. e. , some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

ICRA Conference 2019 Conference Paper

How Shall I Drive? Interaction Modeling and Motion Planning towards Empathetic and Socially-Graceful Driving

• Yi Ren
• Steven Elliott
• Yiwei Wang 0002
• Yezhou Yang
• Wenlong Zhang

While intelligence of autonomous vehicles (AVs) has significantly advanced in recent years, accidents involving AVs suggest that these autonomous systems lack gracefulness in driving when interacting with human drivers. In the setting of a two-player game, we propose model predictive control based on social gracefulness, which is measured by the discrepancy between the actions taken by the AV and those that could have been taken in favor of the human driver. We define social awareness as the ability of an agent to infer such favorable actions based on knowledge about the other agent's intent, and further show that empathy, i. e. , the ability to understand others' intent by simultaneously inferring others' understanding of the agent's self intent, is critical to successful intent inference. Lastly, through an intersection case, we show that the proposed gracefulness objective allows an AV to learn more sophisticated behavior, such as passive-aggressive motions that gently force the other agent to yield.

ICRA Conference 2017 Conference Paper

Mechanical specialization of robotic limbs

• Nathan M. Cahill
• Yi Ren
• Thomas Sugar

In this paper we introduce a design framework that permits task-specific complex geometries in robotic limbs with the minimal power consumption. Additionally we present a optimal gear ratio selection algorithm with realistic constraints, which we use as a subroutine within the geometry optimization. As a case study we optimize the a spatial, hybrid parallel-serial robotic limb structure with a large set of geometric parameters. Optimal design with respect to this mechanism produces three locally optimal families of designs. These are analyzed rigorously and a best design was chosen. A prototype has been constructed from the chosen design family, proving that the approach is practical. This serves as evidence that the design optimization method is an effective tool to minimize the electrical cost of a given task, and thus specialize the design.

IJCAI Conference 2017 Conference Paper

Sense Beauty by Label Distribution Learning

• Yi Ren
• Xin Geng

Beauty is always an attractive topic in the human society, not only artists and psychologists, but also scientists have been searching for an answer -- what is beautiful. This paper presents an approach to learning the human sense toward facial beauty. Different from previous study, the human sense is represented by a label distribution, which covers the full range of beauty ratings and indicates the degree to which each beauty rating describes the face. The motivation is that the human sense of beauty is generally quite subjective, thus it might be inappropriate to represent it with a single scalar, as most previous work does. Therefore, we propose a method called Beauty Distribution Transformation(BDT) to covert the k-wise ratings to label distributions and propose a learning method called Structural Label Distribution Learning(SLDL) based on structural Support Vector Machine to learn the human sense of facial beauty.