Tianyi Liu

JBHI Journal 2026 Journal Article

MedMAP: Promoting Incomplete Multi-Modal Brain Tumor Segmentation With Alignment

• Tianyi Liu
• Zhaorui Tan
• Muyin Chen
• Xi Yang
• Haochuan Jiang
• Kaizhu Huang

Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents a more difficult scenario. To cope with this challenge, Knowledge Distillation, Domain Adaption, and Shared Latent Space have emerged as commonly promising strategies. However, recent efforts to address the missing modality problem in brain tumor segmentation typically overlook the modality gaps and thus fail to learn important invariant feature representations across different modalities. Such drawback consequently leads to limited performance for missing modality models. To ameliorate these problems, pre-trained models are used in natural visual segmentation tasks to minimize the gaps. However, promising pre-trained models are difficult to obtain in the brain tumor segmentation task due to the lack of sufficient data. Along this line, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor as the substitution of the pre-trained model. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce models with narrowed modality gaps. Models with our alignment paradigm show their superior performance on both BraTS2018, BraTS2020 and Brain Metastasis datasets.

AAAI Conference 2026 Conference Paper

RSPlace: Rotation Sensing Macro Placement via Bidirectional Tree Expansion

• Tianyi Liu
• Yaxin Xu
• Lin Geng
• Ningzhong Liu
• Han Sun
• Yu Wang

Macro placement is a crucial subproblem of chip design, focusing on determining the locations of numerous macros while minimizing multiple metrics. In recent years, reinforcement learning (RL) has gained traction as a favorable technique to improve placement performance. However, existing RL-based placers ignore the orientation of macros, resulting in the state space constrained to two-dimensional discrete coordinates and greatly restricting the exploration opportunities. To address this issue, we propose a novel macro placement method, RSPlace, which guides the bidirectional expansion of the global search tree to offer the RL agent more exploration opportunities, incorporating rotation into the RL-based macro placement solution for the first time. RSPlace intelligently determines the optimal rotation angle to maximize placement benefits by leveraging rotation sensing and placement perturbations. Extensive experiments demonstrate that taking the macro orientation into account substantially broadens the feasible locations and effectively reduces the half-perimeter wirelength (HPWL), thus ensuring that our approach significantly improves the optimization effect compared to the state-of-the-art method.

JBHI Journal 2026 Journal Article

USRMamba: Adaptive Routing-Guided State Space Model for Ultrasound Super-Resolution

• Tao Wang
• Zihan Zhou
• Chufeng Jin
• Tianyi Liu
• Baike Shi
• Guangquan Zhou
• Rongjun Ge
• Jean-Louis Coatrieux

In ultrasound (US) imaging, resolution degradation caused by the acoustic diffraction limit and transducer array density can significantly reduce image quality, which have negative impacts on clinical diagnosis. Super-resolution (SR) reconstruction is a more flexible and cost-effective measure compared to system upgrades. However, the complexity and diversity of tissue acoustic properties make it difficult to establish a unified model for US image SR reconstruction. In this context, this paper pioneers a revolutionary Mamba-based single US image SR method, referred to as USRMamba. Firstly, a simple and efficient Enhanced Transform Combine Module (ETCM) is designed for shallow feature extraction, which achieves multi-scale decoupling through Laplacian sharpening and wavelet transform to solve the interference of high-frequency information loss and speckle noise in US images; More importantly, an Adaptive Top-k Prompt Module (ATPM) is proposed, whose core is to generate semantic prompts through an adaptive routing-guided strategy to suppress the interference of fuzzy region labels caused by attenuation on detail reconstruction. In addition, a Frequency Channel Attention Module (FCAM) is developed, forming a modeling strategy of “frequency-spatial domain reconstruction” in parallel with ATPM, further optimizing the fidelity for US images SR reconstruction. Qualitative and quantitative experiments demonstrate that USRMamba exhibits superior performance on several US datasets. Especially with scale factor ×2, the proposed method has an average PSNR 1. 31dB higher than state-of-the-art (SOTA) methods.

ECAI Conference 2025 Conference Paper

IBS-Net: Advancing Implicit Boundary-Aware Segmentation for Diaphragm Ultrasound Analysis

• Baike Shi
• Yikang He
• Chenlong Miao
• Wenbo Huang
• Tao Wang 0107
• Tianyi Liu
• Hui Tang
• Jianmin Dong

Accurate automated measurement of diaphragmatic thickness in ultrasound imaging is a critical challenging task for respiratory function assessment, primarily due to difficulties in precise fascial identification. And ultrasound visualization of the diaphragm is characterized by unique challenges, including discontinuous and blurred boundary delineations caused by imaging artifacts, as well as interference and influence from adjacent muscular reverberations. These problems are further compounded by subjects’ pose variations during image acquisition. To address these challenges, we introduce IBS-Net, an innovative triple-branch interactive segmentation network that synergistically combines boundary regression with auxiliary task learning to optimize feature representation in segmentation task. Moreover, Our framework incorporates two innovative module: an Adaptive Fusion Module (AFM) that enables multi-scale hierarchical feature refinement for precise boundary characterization, and a Cross Interactive Module (CIM) that employs parallel-encoded feature extraction to simultaneously achieve accurate fascial localization while preserving structural topology. These complementary mechanisms effectively resolve spatial feature inconsistencies, facilitating robust multi-level feature integration. Comprehensive experimental results demonstrate that IBS-Net achieves statistically significant improvements of 8. 9% in Dice similarity coefficient and 8. 05% in Jaccard index compared to conventional methods. Moreover, to verify the effectiveness of the proposed method, we extended it to other publicly available BUSI dataset for experimentation. The results demonstrate that our method is competitive in terms of both accuracy and completeness in the identification of fuzzy boundaries in ultrasound images.

ICLR Conference 2024 Conference Paper

LEMON: Lossless model expansion

• Yite Wang
• Jiahao Su
• Hanlin Lu
• Cong Xie
• Tianyi Liu
• Jianbo Yuan
• Haibin Lin
• Ruoyu Sun 0001

Scaling of deep neural networks, especially Transformers, is pivotal for their surging performance and has further led to the emergence of sophisticated reasoning capabilities in foundation models. Such scaling generally requires training large models from scratch with random initialization, failing to leverage the knowledge acquired by their smaller counterparts, which are already resource-intensive to obtain. To tackle this inefficiency, we present $\textbf{L}$ossl$\textbf{E}$ss $\textbf{MO}$del Expansio$\textbf{N}$ (LEMON), a recipe to initialize scaled models using the weights of their smaller but pre-trained counterparts. This is followed by model training with an optimized learning rate scheduler tailored explicitly for the scaled models, substantially reducing the training time compared to training from scratch. Notably, LEMON is versatile, ensuring compatibility with various network structures, including models like Vision Transformers and BERT. Our empirical results demonstrate that LEMON reduces computational costs by 56.7\% for Vision Transformers and 33.2\% for BERT when compared to training from scratch.

ICLR Conference 2024 Conference Paper

Let Models Speak Ciphers: Multiagent Debate through Embeddings

• Chau Pham 0001
• Boyi Liu 0001
• Yingxiang Yang
• Zhengyu Chen 0001
• Tianyi Liu
• Jianbo Yuan
• Bryan A. Plummer
• Zhaoran Wang 0001

Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs. Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary. In this paper, we introduce a communication regime named CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. Specifically, we remove the token sampling step from LLMs and let them communicate their beliefs across the vocabulary through the expectation of the raw transformer output embeddings. Remarkably, by deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights, outperforming the state-of-the-art LLM debate methods using natural language by 0.5-5.0% across five reasoning tasks and multiple open-source LLMs of varying sizes. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs. We anticipate that CIPHER will inspire further exploration for the design of interactions within LLM agent systems, offering a new direction that could significantly influence future developments in the field.

YNICL Journal 2024 Journal Article

Unveiling MRI markers for Parkinson’s Disease: GABAergic dysfunction and cortical changes

• Yuan Tian
• Sijia Geng
• Tianyi Liu
• Qi Wang
• Jianxiu Lian
• Liangjie Lin
• Jiayu Li
• Tao Gong

NeurIPS Conference 2023 Conference Paper

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

• Tianyi Liu
• Kejun Wu
• Yi Wang
• Wenyang Liu
• Kim-Hui Yap
• Lap-Pui Chau

The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communication (e. g. , telepresence, live streaming, and internet video) and multimedia forensics. To address this, we introduce the bitstream-corrupted video (BSCV) benchmark, the first benchmark dataset with more than 28, 000 video clips, which can be used for bitstream-corrupted video recovery in the real world. The BSCV is a collection of 1) a proposed three-parameter corruption model for video bitstream, 2) a large-scale dataset containing rich error patterns, multiple corruption levels, and flexible dataset branches, and 3) a new video recovery framework that serves as a benchmark. We evaluate state-of-the-art video inpainting methods on the BSCV dataset, demonstrating existing approaches' limitations and our framework's advantages in solving the bitstream-corrupted video recovery problem. The benchmark and dataset are released at https: //github. com/LIUTIGHE/BSCV-Dataset.

ICML Conference 2023 Conference Paper

Machine Learning Force Fields with Data Cost Aware Training

• Alexander Bukharin
• Tianyi Liu
• Shengjie Wang 0001
• Simiao Zuo
• Weihao Gao
• Wen Yan
• Tuo Zhao

Machine learning force fields (MLFF) have been proposed to accelerate molecular dynamics (MD) simulation, which finds widespread applications in chemistry and biomedical research. Even for the most data-efficient MLFFs, reaching chemical accuracy can require hundreds of frames of force and energy labels generated by expensive quantum mechanical algorithms, which may scale as $O(n^3)$ to $O(n^7)$, with $n$ proportional to the number of basis functions. To address this issue, we propose a multi-stage computational framework – ASTEROID, which lowers the data cost of MLFFs by leveraging a combination of cheap inaccurate data and expensive accurate data. The motivation behind ASTEROID is that inaccurate data, though incurring large bias, can help capture the sophisticated structures of the underlying force field. Therefore, we first train a MLFF model on a large amount of inaccurate training data, employing a bias-aware loss function to prevent the model from overfitting the potential bias of this data. We then fine-tune the obtained model using a small amount of accurate training data, which preserves the knowledge learned from the inaccurate training data while significantly improving the model’s accuracy. Moreover, we propose a variant of ASTEROID based on score matching for the setting where the inaccurate training data are unlabeled. Extensive experiments on MD datasets and downstream tasks validate the efficacy of ASTEROID. Our code and data are available at https: //github. com/abukharin3/asteroid.

ICML Conference 2023 Conference Paper

Taxonomy-Structured Domain Adaptation

• Tianyi Liu
• Zihao Xu 0001
• Hao He 0011
• Guang-Yuan Hao
• Guang-He Lee
• Hao Wang 0014

Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nuanced domain relationships in the real world. In this work, we tackle a generalization with taxonomy-structured domains, which formalizes domains with nested, hierarchical similarity structures such as animal species and product catalogs. We build on the classic adversarial framework and introduce a novel taxonomist, which competes with the adversarial discriminator to preserve the taxonomy information. The equilibrium recovers the classic adversarial domain adaptation’s solution if given a non-informative domain taxonomy (e. g. , a flat taxonomy where all leaf nodes connect to the root node) while yielding non-trivial results with other taxonomies. Empirically, our method achieves state-of-the-art performance on both synthetic and real-world datasets with successful adaptation.

UAI Conference 2022 Conference Paper

Differentially private multi-party data release for linear regression

• Ruihan Wu
• Xin Yang 0017
• Yuanshun Yao
• Jiankai Sun
• Tianyi Liu
• Kilian Q. Weinberger
• Chong Wang 0002

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focused on scenarios where a single party owns all the data. In this paper we focus on the multi-party setting, where different stakeholders own disjoint sets of attributes belonging to the same group of data subjects. Within the context of linear regression that allow all parties to train models on the complete data without the ability to infer private attributes or identities of individuals, we start with directly applying Gaussian mechanism and show it has the small eigenvalue problem. We further propose our novel method and prove it asymptotically converges to the optimal (non-private) solutions with increasing dataset size. We substantiate the theoretical results through experiments on both artificial and real-world datasets.

ICML Conference 2022 Conference Paper

Fourier Learning with Cyclical Data

• Yingxiang Yang
• Zhihan Xiong
• Tianyi Liu
• Taiqing Wang
• Chong Wang

Many machine learning models for online applications, such as recommender systems, are often trained on data with cyclical properties. These data sequentially arrive from a time-varying distribution that is periodic in time. Existing algorithms either use streaming learning to track a time-varying set of optimal model parameters, yielding a dynamic regret that scales linearly in time; or partition the data of each cycle into multiple segments and train a separate model for each—a pluralistic approach that is computationally and storage-wise expensive. In this paper, we have designed a novel approach to overcome the aforementioned shortcomings. Our method, named "Fourier learning", encodes the periodicity into the model representation using a partial Fourier sequence, and trains the coefficient functions modeled by neural networks. Particularly, we design a Fourier multi-layer perceptron (F-MLP) that can be trained on streaming data with stochastic gradient descent (streaming-SGD), and we derive its convergence guarantees. We demonstrate Fourier learning’s better performance with extensive experiments on synthetic and public datasets, as well as on a large-scale recommender system that is updated in real-time, and trained with tens of millions of samples per day.

UAI Conference 2022 Conference Paper

PathFlow: A normalizing flow generator that finds transition paths

• Tianyi Liu
• Weihao Gao
• Zhirui Wang
• Chong Wang 0002

Sampling from a Boltzmann distribution to calculate important macro statistics is one of the central tasks in the study of large atomic and molecular systems. Recently, a one-shot configuration sampler, the Boltzmann generator [Noé et al. , 2019], is introduced. Though a Boltzmann generator can directly generate independent metastable states, it lacks the ability to find transition pathways and describe the whole transition process. In this paper, we propose PathFlow that can function as a one-shot generator as well as a transition pathfinder. More specifically, a normalizing flow model is constructed to map the base distribution and linear interpolated path in the latent space to the Boltzmann distribution and a minimum (free) energy path in the configuration space simultaneously. PathFlow can be trained by standard gradient-based optimizers using the proposed gradient estimator with a theoretical guarantee. PathFlow, validated with the extensively studied examples including a synthetic Müller potential and Alanine dipeptide, shows a remarkable performance.

ICLR Conference 2020 Conference Paper

On Computation and Generalization of Generative Adversarial Imitation Learning

• Minshuo Chen
• Yizhou Wang 0006
• Tianyi Liu
• Zhuoran Yang
• Xingguo Li
• Zhaoran Wang 0001
• Tuo Zhao

Generative Adversarial Imitation Learning (GAIL) is a powerful and practical approach for learning sequential decision-making policies. Different from Reinforcement Learning (RL), GAIL takes advantage of demonstration data by experts (e.g., human), and learns both the policy and reward function of the unknown environment. Despite the significant empirical progresses, the theory behind GAIL is still largely unknown. The major difficulty comes from the underlying temporal dependency of the demonstration data and the minimax computational formulation of GAIL without convex-concave structure. To bridge such a gap between theory and practice, this paper investigates the theoretical properties of GAIL. Specifically, we show: (1) For GAIL with general reward parameterization, the generalization can be guaranteed as long as the class of the reward functions is properly controlled; (2) For GAIL, where the reward is parameterized as a reproducing kernel function, GAIL can be efficiently solved by stochastic first order optimization algorithms, which attain sublinear convergence to a stationary solution. To the best of our knowledge, these are the first results on statistical and computational guarantees of imitation learning with reward/policy function ap- proximation. Numerical experiments are provided to support our analysis.

ICML Conference 2019 Conference Paper

Toward Understanding the Importance of Noise in Training Neural Networks

• Mo Zhou
• Tianyi Liu
• Yan Li 0074
• Dachao Lin
• Enlu Zhou
• Tuo Zhao

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of deep neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem through training a simple two-layer convolutional neural network model. Although training such a network requires to solve a non-convex optimization problem with a spurious local optimum and a global optimum, we prove that a perturbed gradient descent algorithm in conjunction with noise annealing is guaranteed to converge to a global optimum in polynomial time with arbitrary initialization. This implies that the noise enables the algorithm to efficiently escape from the spurious local optimum. Numerical experiments are provided to support our theory.

NeurIPS Conference 2019 Conference Paper

Towards Understanding the Importance of Shortcut Connections in Residual Networks

• Tianyi Liu
• Minshuo Chen
• Mo Zhou
• Simon Du
• Enlu Zhou
• Tuo Zhao

Residual Network (ResNet) is undoubtedly a milestone in deep learning. ResNet is equipped with shortcut connections between layers, and exhibits efficient training using simple first order algorithms. Despite of the great empirical success, the reason behind is far from being well understood. In this paper, we study a two-layer non-overlapping convolutional ResNet. Training such a network requires solving a non-convex optimization problem with a spurious local optimum. We show, however, that gradient descent combined with proper normalization, avoids being trapped by the spurious local optimum, and converges to a global optimum in polynomial time, when the weight of the first layer is initialized at 0, and that of the second layer is initialized arbitrarily in a ball. Numerical experiments are provided to support our theory.

NeurIPS Conference 2018 Conference Paper

Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization

• Tianyi Liu
• Shiyang Li
• Jianping Shi
• Enlu Zhou
• Tuo Zhao

Asynchronous momentum stochastic gradient descent algorithms (Async-MSGD) have been widely used in distributed machine learning, e. g. , training large collaborative filtering systems and deep neural networks. Due to current technical limit, however, establishing convergence properties of Async-MSGD for these highly complicated nonoconvex problems is generally infeasible. Therefore, we propose to analyze the algorithm through a simpler but nontrivial nonconvex problems --- streaming PCA. This allows us to make progress toward understanding Aync-MSGD and gaining new insights for more general problems. Specifically, by exploiting the diffusion approximation of stochastic optimization, we establish the asymptotic rate of convergence of Async-MSGD for streaming PCA. Our results indicate a fundamental tradeoff between asynchrony and momentum: To ensure convergence and acceleration through asynchrony, we have to reduce the momentum (compared with Sync-MSGD). To the best of our knowledge, this is the first theoretical attempt on understanding Async-MSGD for distributed nonconvex stochastic optimization. Numerical experiments on both streaming PCA and training deep neural networks are provided to support our findings for Async-MSGD.