Arrow Research search

Author name cluster

Tong Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

26 papers
2 author rows

Possible papers

26

TIST Journal 2026 Journal Article

Learning Causality-Aware Exploration with Transformers for Goal-Oriented Navigation

  • Ruoyu Wang
  • Tong Yu
  • Mingjie Li
  • Yuanjiang Cao
  • Yao Liu
  • Lina Yao

Navigation is a fundamental task in the research of Embodied AI, and recent advances in machine learning algorithms have garnered growing interest in developing versatile Embodied AI systems. However, current research in this domain reveals opportunities for improvement. First, the direct application of RNNs and Transformers often overlooks the distinct characteristics of navigation tasks compared to traditional sequential data modeling. These methods are inherently designed to capture long-term dependencies, which are relatively weak in navigation scenarios, potentially limiting their performance in such tasks. Second, the reliance on task-specific configurations, such as pre-trained modules and dataset-specific logic, compromises the generalizability of these methods. We address these constraints by initially exploring the unique differences between Navigation tasks and other sequential data tasks through the lens of Causality, presenting a causal framework to elucidate the inadequacies of conventional sequential methods for Navigation. By leveraging this causal perspective, we propose Causality-Aware Transformer (CAT) Networks for Navigation, featuring a Causal Understanding Module to enhance the model’s Environmental Understanding capability. Meanwhile, our method is devoid of task-specific inductive biases and can be trained in an End-to-End manner, which enhances the method’s generalizability across various contexts. Empirical evaluations demonstrate that our methodology consistently surpasses benchmark performances across a spectrum of settings, tasks, and simulation environments, specifically, in Object Navigation within RoboTHOR, Objective Navigation, Point Navigation in Habitat, and R2R Navigation. Extensive ablation studies reveal that the performance gains can be attributed to the Causal Understanding Module, which demonstrates effectiveness and efficiency in both Reinforcement Learning and Supervised Learning settings. Additionally, further analysis highlights the robustness of our method, demonstrating its capacity to consistently perform well across diverse experimental settings and varying conditions. This robustness underscores the adaptability and generalizability of our approach, reinforcing its potential for application across a wide range of tasks.

Details DOI

AAAI Conference 2026 Conference Paper

VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use

  • Zhehao Zhang
  • Ryan A. Rossi
  • Tong Yu
  • Franck Dernoncourt
  • Ruiyi Zhang
  • Jiuxiang Gu
  • Sungchul Kim
  • Xiang Chen

While vision-language models (VLMs) have demonstrated remarkable performance across various tasks combining textual and visual information, they continue to struggle with fine-grained visual perception tasks that require detailed pixel-level analysis. Effectively eliciting comprehensive reasoning from VLMs on such intricate visual elements remains an open challenge. In this paper, we present VipAct, an agent framework that enhances VLMs by integrating multi-agent collaboration and vision expert models, enabling more precise visual understanding and comprehensive reasoning. VipAct consists of an orchestrator agent, which manages task requirement analysis, planning, and coordination, along with specialized agents that handle specific tasks such as image captioning and vision expert models that provide high-precision perceptual information. This multi-agent approach allows VLMs to better perform fine-grained visual perception tasks by synergizing planning, reasoning, and tool use. We evaluate VipAct on benchmarks featuring a diverse set of visual perception tasks, with experimental results demonstrating significant performance improvements over state-of-the-art baselines across all tasks. Furthermore, comprehensive ablation studies reveal the critical role of multi-agent collaboration in eliciting more detailed System-2 reasoning and highlight the importance of image input for task planning. Additionally, our error analysis identifies patterns of VLMs' inherent limitations in visual perception, providing insights into potential future improvements. VipAct offers a flexible and extensible framework, paving the way for more advanced visual perception systems across various real-world applications.

PDF Details DOI

AAMAS Conference 2025 Conference Paper

Adaptive Offline Data Replay in Offline-to-Online Reinforcement Learning

  • Xu Liu
  • Tong Yu
  • Shuai Li

Offline-to-online reinforcement learning combines the advantages of offline data utilization with online exploration to enhance sample efficiency and performance. A primary challenge lies in managing the distribution shift between offline and online data, which significantly impacts training effectiveness. Existing methods often employ fixed mixing ratios for data replay, but these require taskspecific tuning and may fail to generalize across different environments. To address this, we introduce a metric that evaluates policy quality relative to offline and online data, and propose a banditbased strategy to adjust the mixing ratio adaptively, optimizing policy quality during training. Experiments across diverse environments demonstrate that our approach outperforms static methods, offering robust adaptability and minimizing manual tuning.

PDF

TMLR Journal 2025 Journal Article

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

  • Leitian Tao
  • Xiang Chen
  • Tong Yu
  • Tung Mai
  • Ryan A. Rossi
  • Yixuan Li
  • Saayan Mitra

Large Language Models (LLMs) have revolutionized code generation but are require significant resources and tend to over-generalize, limiting their task-specific efficiency. Fine-tuning smaller, open-source LLMs is a cost-effective alternative, yet standard supervised approaches rely solely on correct examples, overlooking valuable insights from failures. We introduce CodeLutra, a new framework that leverages both correct and incorrect code attempts. Instead of purely instructing with correct solutions, CodeLutra uses iterative preference-based refinement, comparing successful and failed outputs to better approximate desired results. This process narrows the performance gap with state-of-the-art, larger models, without requiring massive datasets or auxiliary models. For example, on a challenging data science coding task, using only 500 samples improved Llama-3-8B’s accuracy from 28.2% to 48.6%, approaching GPT-4’s level. By capitalizing on both successes and mistakes, \textsc{CodeLutra} offers a scalable, efficient path to high-quality code generation, making smaller open-source models more competitive with leading closed-source alternatives.

PDF Details

NeurIPS Conference 2025 Conference Paper

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

  • Hongtao Huang
  • Chengkai Huang
  • Junda Wu
  • Tong Yu
  • Julian McAuley
  • Lina Yao

Forecasting multi-step user behavior trajectories requires reasoning over structured preferences across future actions, a challenge overlooked by traditional sequential recommendation. This problem is critical for applications such as personalized commerce and adaptive content delivery, where anticipating a user’s complete action sequence enhances both satisfaction and business outcomes. We identify an essential limitation of existing paradigms: their inability to capture global, listwise dependencies among sequence items. To address this, we formulate User Behavior Trajectory Prediction (UBTP) as a new task setting that explicitly models longterm user preferences. We introduce Listwise Preference Diffusion Optimization (LPDO), a diffusion-based training framework that directly optimizes structured preferences over entire item sequences. LPDO incorporates a Plackett–Luce supervision signal and derives a tight variational lower bound aligned with listwise ranking likelihoods, enabling coherent preference generation across denoising steps and overcoming the independent-token assumption of prior diffusion methods. To rigorously evaluate multi-step prediction quality, we propose the task-specific metric: Sequential Match (SeqMatch), which measures exact trajectory agreement, and adopt Perplexity (PPL), which assesses probabilistic fidelity. Extensive experiments on real-world user behavior benchmarks demonstrate that LPDO consistently outperforms state-of-the-art baselines, establishing a new benchmark for structured preference learning with diffusion models.

PDF Details

AAAI Conference 2025 Conference Paper

Numerical Pruning for Efficient Autoregressive Models

  • Xuan Shen
  • Zhao Song
  • Yufa Zhou
  • Bo Chen
  • Jing Liu
  • Ruiyi Zhang
  • Ryan A. Rossi
  • Hao Tan

Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.

PDF Details DOI

TMLR Journal 2025 Journal Article

Personalization of Large Language Models: A Survey

  • Zhehao Zhang
  • Ryan A. Rossi
  • Branislav Kveton
  • Yijia Shao
  • Diyi Yang
  • Hamed Zamani
  • Franck Dernoncourt
  • Joe Barrow

Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we bridge the gap between these two separate main directions for the first time by introducing a taxonomy for personalized LLM usage and summarizing the key differences and challenges. We provide a formalization of the foundations of personalized LLMs that consolidates and expands notions of personalization of LLMs, defining and discussing novel facets of personalization, usage, and desiderata of personalized LLMs. We then unify the literature across these diverse fields and usage scenarios by proposing systematic taxonomies for the granularity of personalization, personalization techniques, datasets, evaluation methods, and applications of personalized LLMs. Finally, we highlight challenges and important open problems that remain to be addressed. By unifying and surveying recent research using the proposed taxonomies, we aim to provide a clear guide to the existing literature and different facets of personalization in LLMs, empowering both researchers and practitioners.

PDF Details

NeurIPS Conference 2024 Conference Paper

Calibrating Reasoning in Language Models with Internal Consistency

  • Zhihui Xie
  • Jizhou Guo
  • Tong Yu
  • Shuai Li

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious mistakes and contradictions, raising doubts about their ability to robustly process and utilize generated rationales. In this work, we investigate reasoning in LLMs through the lens of internal representations, focusing on how these representations are influenced by generated rationales. Our preliminary analysis reveals that while generated rationales improve answer accuracy, inconsistencies emerge between the model’s internal representations in middle layers and those in final layers, potentially undermining the reliability of their reasoning processes. To address this, we propose internal consistency as a measure of the model’s confidence by examining the agreement of latent predictions decoded from intermediate layers. Extensive empirical studies across different models and datasets demonstrate that internal consistency effectively distinguishes between correct and incorrect reasoning paths. Motivated by this, we propose a new approach to calibrate reasoning by up-weighting reasoning paths with high internal consistency, resulting in a significant boost in reasoning performance. Further analysis uncovers distinct patterns in attention and feed-forward modules across layers, providing insights into the emergence of internal inconsistency. In summary, our results demonstrate the potential of using internal representations for self-evaluation of LLMs.

PDF Details DOI

EAAI Journal 2024 Journal Article

Human-like mechanism deep learning model for longitudinal motion control of autonomous vehicles

  • Zhenhai Gao
  • Tong Yu
  • Fei Gao
  • Rui Zhao
  • Tianjun Sun

Artificial intelligence (AI) plays a critical role in the prediction, planning, and control of autonomous vehicle. The original motion control methods are increasing in accuracy, but their control style markedly differs from that of human drivers. This not only degrades the passenger's ride experience but also brings unfamiliarity to other drivers, leading to safety hazards. Moreover, some of the methods are a direct application of AI techniques without any specific enhancements tailored for vehicle control. This both fails to fully utilize the potential of AI and reduces interpretability. To address these issues, in this paper, deep learning methods are integrated with driver control mechanisms to propose a human-like neural network for vehicle longitudinal dynamics estimation and control (HNN). First, the process of driver estimation and control of vehicle dynamics is proposed and described in mathematical language. Subsequently, the HNN composed of three sub-networks is presented. The three sub-networks correspond to the three sub-processes of the driver's mechanism, which makes the proposed HNN method more applicable to vehicle dynamics control and more interpretable in specific engineering domains. The effectiveness of the HNN method is verified on a real-world dataset. The results demonstrate that the HNN not only enhances vehicle human-like control but also surpasses baselines in terms of control style consistency and convergence rate.

Details DOI

JMLR Journal 2024 Journal Article

Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model

  • Rashmi Ranjan Bhuyan
  • Adel Javanmard
  • Sungchul Kim
  • Gourab Mukherjee
  • Ryan A. Rossi
  • Tong Yu
  • Handong Zhao

We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments. We consider a dynamic model with the consumers’ preferences as well as price sensitivity varying over time. Building on the well-known finding that consumers sharing similar characteristics act in similar ways, we consider a global shrinkage structure, which assumes that the consumers’ preferences across the different segments can be well approximated by a spatial autoregressive (SAR) model. In such a streamed longitudinal setup, we measure the performance of a dynamic pricing policy via regret, which is the expected revenue loss compared to a clairvoyant that knows the sequence of model parameters in advance. We propose a pricing policy based on penalized stochastic gradient descent (PSGD) and explicitly characterize its regret as functions of time, the temporal variability in the model parameters as well as the strength of the auto-correlation network structure spanning the varied customer segments. Our regret analysis results not only demonstrate asymptotic optimality of the proposed policy but also show that for policy planning it is essential to incorporate available structural information as policies based on unshrunken models are highly sub-optimal in the aforementioned set-up. We conduct simulation experiments across a wide range of regimes as well as real-world networks based studies and report encouraging performance for our proposed method. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

NeurIPS Conference 2024 Conference Paper

The Closeness of In-Context Learning and Weight Shifting for Softmax Regression

  • Shuai Li
  • Zhao Song
  • Yu Xia
  • Tong Yu
  • Tianyi Zhou

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit. In-context learning is one of the celebrated abilities of recent LLMs. Without further parameter updates, Transformers can learn to predict based on few in-context examples. However, the reason why Transformers becomes in-context learners is not well understood. Recently, in-context learning has been studied from a mathematical perspective with simplified linear self-attention without softmax unit. Based on a linear regression formulation $\min_x\| Ax - b \|_2$, existing works show linear Transformers' capability of learning linear functions in context. The capability of Transformers with softmax unit approaching full Transformers, however, remains unexplored. In this work, we study the in-context learning based on a softmax regression formulation $\min_{x} \| \langle \exp(Ax), {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2$. We show the upper bounds of the data transformations induced by a single self-attention layer with softmax unit and by gradient-descent on a $\ell_2$ regression loss for softmax prediction function. Our theoretical results imply that when training self-attention-only Transformers for fundamental regression tasks, the models learned by gradient-descent and Transformers show great similarity.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Causal Discovery in Semi-Stationary Time Series

  • Shanyun Gao
  • Raghavendra Addanki
  • Tong Yu
  • Ryan Rossi
  • Murat Kocaoglu

Discovering causal relations from observational time series without making the stationary assumption is a significant challenge. In practice, this challenge is common in many areas, such as retail sales, transportation systems, and medical science. Here, we consider this problem for a class of non-stationary time series. The structural causal model (SCM) of this type of time series, called the semi-stationary time series, exhibits that a finite number of different causal mechanisms occur sequentially and periodically across time. This model holds considerable practical utility because it can represent periodicity, including common occurrences such as seasonality and diurnal variation. We propose a constraint-based, non-parametric algorithm for discovering causal relations in this setting. The resulting algorithm, PCMCI$_{\Omega}$, can capture the alternating and recurring changes in the causal mechanisms and then identify the underlying causal graph with conditional independence (CI) tests. We show that this algorithm is sound in identifying causal relations on discrete time series. We validate the algorithm with extensive experiments on continuous and discrete simulated data. We also apply our algorithm to a real-world climate dataset.

PDF Details

ICLR Conference 2023 Conference Paper

ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length

  • Ruslan Khalitov
  • Tong Yu
  • Lei Cheng
  • Zhirong Yang

Sequential data naturally have different lengths in many domains, with some very long sequences. As an important modeling tool, neural attention should capture long-range interaction in such sequences. However, most existing neural attention models admit only short sequences, or they have to employ chunking or padding to enforce a constant input length. Here we propose a simple neural network building block called ChordMixer which can model the attention for long sequences with variable lengths. Each ChordMixer block consists of a position-wise rotation layer without learnable parameters and an element-wise MLP layer. Repeatedly applying such blocks forms an effective network backbone that mixes the input signals towards the learning targets. We have tested ChordMixer on the synthetic adding problem, long document classification, and DNA sequence-based taxonomy classification. The experiment results show that our method substantially outperforms other neural attention models.

Details

NeurIPS Conference 2023 Conference Paper

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

  • Junda Wu
  • Tong Yu
  • Rui Wang
  • Zhao Song
  • Ruiyi Zhang
  • Handong Zhao
  • Chaochao Lu
  • Shuai Li

Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We have also empirically observed that conventional prompt tuning methods cannot encode and learn sufficient task-relevant information from prompt tokens. In this work, we develop an information-theoretic framework that formulates soft prompt tuning as maximizing the mutual information between prompts and other model parameters (or encoded representations). This novel view helps us to develop a more efficient, accurate and robust soft prompt tuning method, InfoPrompt. With this framework, we develop two novel mutual information based loss functions, to (i) explore proper prompt initialization for the downstream tasks and learn sufficient task-relevant information from prompt tokens and (ii) encourage the output representation from the pretrained language model to be more aware of the task-relevant information captured in the learnt prompts. Extensive experiments validate that InfoPrompt can significantly accelerate the convergence of the prompt tuning and outperform traditional prompt tuning methods. Finally, we provide a formal theoretical result to show that a gradient descent type algorithm can be used to train our mutual information loss.

PDF Details

NeurIPS Conference 2023 Conference Paper

Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels

  • Jian Chen
  • Ruiyi Zhang
  • Tong Yu
  • Rohan Sharma
  • Zhiqiang Xu
  • Tong Sun
  • Changyou Chen

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, i. e. , labels are generated by gradually refining an initial random guess. This new perspective immediately enables existing powerful diffusion models to seamlessly learn the stochastic generative process. Once the generative uncertainty is modeled, we can perform classification inference using maximum likelihood estimation of labels. To mitigate the impact of noisy labels, we propose the L abel- R etrieval- A ugmented (LRA) diffusion model, which leverages neighbor consistency to effectively construct pseudo-clean labels for diffusion training. Our model is flexible and general, allowing easy incorporation of different types of conditional information, e. g. , use of pre-trained models, to further boost model performance. Extensive experiments are conducted for evaluation. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets. Remarkably, by incorporating conditional information from the powerful CLIP model, our method can boost the current SOTA accuracy by 10-20 absolute points in many cases. Code is available: https: //anonymous. 4open. science/r/LRA-diffusion-5F2F

PDF Details

NeurIPS Conference 2023 Conference Paper

Online Corrupted User Detection and Regret Minimization

  • Zhiyong Wang
  • Jize Xie
  • Tong Yu
  • Shuai Li
  • John C. S. Lui

In real-world online web systems, multiple users usually arrive sequentially into the system. For applications like click fraud and fake reviews, some users can maliciously perform corrupted (disrupted) behaviors to trick the system. Therefore, it is crucial to design efficient online learning algorithms to robustly learn from potentially corrupted user behaviors and accurately identify the corrupted users in an online manner. Existing works propose bandit algorithms robust to adversarial corruption. However, these algorithms are designed for a single user, and cannot leverage the implicit social relations among multiple users for more efficient learning. Moreover, none of them consider how to detect corrupted users online in the multiple-user scenario. In this paper, we present an important online learning problem named LOCUD to learn and utilize unknown user relations from disrupted behaviors to speed up learning, and identify the corrupted users in an online setting. To robustly learn and utilize the unknown relations among potentially corrupted users, we propose a novel bandit algorithm RCLUB-WCU. To detect the corrupted users, we devise a novel online detection algorithm OCCUD based on RCLUB-WCU's inferred user relations. We prove a regret upper bound for RCLUB-WCU, which asymptotically matches the lower bound with respect to $T$ up to logarithmic factors, and matches the state-of-the-art results in degenerate cases. We also give a theoretical guarantee for the detection accuracy of OCCUD. With extensive experiments, our methods achieve superior performance over previous bandit algorithms and high corrupted user detection accuracy.

PDF Details

AAAI Conference 2023 Conference Paper

Reinforced Approximate Exploratory Data Analysis

  • Shaddy Garg
  • Subrata Mitra
  • Tong Yu
  • Yash Gadhia
  • Arjun Kashettiwar

Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results. Data processing systems often execute the queries on samples to produce results with low latency. Different downsampling strategy preserves different statistics of the data and have different magnitude of latency reductions. The optimum choice of sampling strategy often depends on the particular context of the analysis flow and the hidden intent of the analyst. In this paper, we are the first to consider the impact of sampling in interactive data exploration settings as they introduce approximation errors. We propose a Deep Reinforcement Learning (DRL) based framework which can optimize the sample selection in order to keep the analysis and insight generation flow intact. Evaluations with real datasets show that our technique can preserve the original insight generation flow while improving the interaction latency, compared to baseline methods.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Text-Based Interactive Recommendation via Offline Reinforcement Learning

  • Ruiyi Zhang
  • Tong Yu
  • Yilin Shen
  • Hongxia Jin

Interactive recommendation with natural-language feedback can provide richer user feedback and has demonstrated advantages over traditional recommender systems. However, the classical online paradigm involves iteratively collecting experience via interaction with users, which is expensive and risky. We consider an offline interactive recommendation to exploit arbitrary experience collected by multiple unknown policies. A direct application of policy learning with such fixed experience suffers from the distribution shift. To tackle this issue, we develop a behavior-agnostic off-policy correction framework to make offline interactive recommendation possible. Specifically, we leverage the conservative Q-function to perform off-policy evaluation, which enables learning effective policies from fixed datasets without further interactions. Empirical results on the simulator derived from real-world datasets demonstrate the effectiveness of our proposed offline training framework.

PDF Details

AAAI Conference 2022 Conference Paper

TiGAN: Text-Based Interactive Image Generation and Manipulation

  • Yufan Zhou
  • Ruiyi Zhang
  • Jiuxiang Gu
  • Chris Tensmeyer
  • Tong Yu
  • Changyou Chen
  • Jinhui Xu
  • Tong Sun

Using natural-language feedback to guide image generation and manipulation can greatly lower the required efforts and skills. This topic has received increased attention in recent years through refinement of Generative Adversarial Networks (GANs); however, most existing works are limited to singleround interaction, which is not reflective of real world interactive image editing workflows. Furthermore, previous works dealing with multi-round scenarios are limited to predefined feedback sequences, which is also impractical. In this paper, we propose a novel framework for Text-based interactive image generation and manipulation (TiGAN) that responds to users’ natural-language feedback. TiGAN utilizes the powerful pre-trained CLIP model to understand users’ naturallanguage feedback and exploits contrastive learning for a better text-to-image mapping. To maintain the image consistency during interactions, TiGAN generates intermediate feature vectors aligned with the feedback and selectively feeds these vectors to our proposed generative model. Empirical results on several datasets show that TiGAN improves both interaction efficiency and image quality while better avoids undesirable image manipulation during interactions.

PDF Details

AAAI Conference 2020 Conference Paper

Towards Hands-Free Visual Dialog Interactive Recommendation

  • Tong Yu
  • Yilin Shen
  • Hongxia Jin

With the recent advances of multimodal interactive recommendations, the users are able to express their preference by natural language feedback to the item images, to find the desired items. However, the existing systems either retrieve only one item or require the user to specify (e. g. , by click or touch) the commented items from a list of recommendations in each user interaction. As a result, the users are not hands-free and the recommendations may be impractical. We propose a hands-free visual dialog recommender system to interactively recommend a list of items. At each time, the system shows a list of items with visual appearance. The user can comment on the list in natural language, to describe the desired features they further want. With these multimodal data, the system chooses another list of items to recommend. To understand the user preference from these multimodal data, we develop neural network models which identify the described items among the list and further predict the desired attributes. To achieve efficient interactive recommendations, we leverage the inferred user preference and further develop a novel bandit algorithm. Specifically, to avoid the system exploring more than needed, the desired attributes are utilized to reduce the exploration space. More importantly, to achieve sample efficient learning in this hands-free setting, we derive additional samples from the user’s relative preference expressed in natural language and design a pairwise logistic loss in bandit learning. Our bandit model is jointly updated by the pairwise logistic loss on the additional samples derived from natural language feedback and the traditional logistic loss. The empirical results show that the probability of finding the desired items by our system is about 3 times as high as that by the traditional interactive recommenders, after a few user interactions.

PDF Details

NeurIPS Conference 2019 Conference Paper

Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning

  • Ruiyi Zhang
  • Tong Yu
  • Yilin Shen
  • Hongxia Jin
  • Changyou Chen

Text-based interactive recommendation provides richer user preferences and has demonstrated advantages over traditional interactive recommender systems. However, recommendations can easily violate preferences of users from their past natural-language feedback, since the recommender needs to explore new items for further improvement. To alleviate this issue, we propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference, which is incorporated into the standard RL objective of maximizing expected cumulative future rewards. Our proposed framework is general and is further extended to the task of constrained text generation. Empirical results show that the proposed method yields consistent improvement relative to standard RL methods.

PDF Details

AAAI Conference 2018 Conference Paper

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models

  • Bing Liu
  • Tong Yu
  • Ian Lane
  • Ole Mengshoel

Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on of- fline supervised learning using a large set of context-response pairs. In this paper, we focus on online learning of response selection in retrieval-based dialog systems. We propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection. A bidirectional LSTM is used to produce the distributed representations of dialog context and responses, which serve as the input to a contextual bandit. In learning the bandit, we propose a customized Thompson sampling method that is applied to a polynomial feature space in approximating the reward. Experimental results on the Ubuntu Dialogue Corpus demonstrate significant performance gains of the proposed method over conventional linear contextual bandits. Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.

PDF Details

AIIM Journal 2017 Journal Article

Knowledge graph for TCM health preservation: Design, construction, and applications

  • Tong Yu
  • Jinghua Li
  • Qi Yu
  • Ye Tian
  • Xiaofeng Shun
  • Lili Xu
  • Ling Zhu
  • Hongjie Gao

Traditional Chinese Medicine (TCM) is one of the important non-material cultural heritages of the Chinese nation. It is an important development strategy of Chinese medicine to collect, analyzes, and manages the knowledge assets of TCM health care. As a novel and massive knowledge management technology, knowledge graph provides an ideal technical means to solve the problem of “Knowledge Island” in the field of traditional Chinese medicine. In this study, we construct a large-scale knowledge graph, which integrates terms, documents, databases and other knowledge resources. This knowledge graph can facilitate various knowledge services such as knowledge visualization, knowledge retrieval, and knowledge recommendation, and helps the sharing, interpretation, and utilization of TCM health care knowledge.

Details DOI

IJCAI Conference 2016 Conference Paper

Markov Chain Analysis of Noise and Restart in Stochastic Local Search

  • Ole J. Mengshoel
  • Youssef Ahres
  • Tong Yu

Stochastic local search (SLS) algorithms have proven to be very competitive in solving hard computational problems. This paper investigates the foundations of SLS algorithms. We develop a simple SLS algorithm, MarkovSLS, with three search operators: greedy, noise, and restart. The search operators are controlled by probability parameters, leading to soft (probabilistic) rather than hard (deterministic) restarts. We consider two special cases of the MarkovSLS algorithm: SoftSLS and AdaptiveSLS. In SoftSLS, the probability parameters are fixed, enabling analysis using standard homogeneous Markov chains. We study the interaction between the restart and noise parameters in SoftSLS, and optimize them analytically in addition to the traditional empirical approach. Experimentally, we investigate the dependency of SoftSLS's performance on its noise and restart parameters, validating the analytical results. AdaptiveSLS dynamically adjusts its noise and restart parameters during search. Experimentally, on synthetic and feature selection problems, we compare AdaptiveSLS with other algorithms including an analytically optimized version of SoftSLS, and find that it performs well while not requiring prior knowledge of the search space.

PDF Details

JMLR Journal 2015 Journal Article

Combination of Feature Engineering and Ranking Models for Paper-Author Identification in KDD Cup 2013

  • Chun-Liang Li
  • Yu-Chuan Su
  • Ting-Wei Lin
  • Cheng-Hao Tsai
  • Wei-Cheng Chang
  • Kuan-Hao Huang
  • Tzu-Ming Kuo
  • Shan-Wei Lin

This paper describes the winning solution of team National Taiwan University for track 1 of KDD Cup 2013. The track 1 in KDD Cup 2013 considers the paper-author identification problem, which is to identify whether a paper is truly written by an author. First, we conduct feature engineering to transform the various types of provided text information into 97 features. Second, we train classification and ranking models using these features. Last, we combine our individual models to boost the performance by using results on the internal validation set and the official Valid set. Some effective post-processing techniques have also been proposed. Our solution achieves 0.98259 MAP score and ranks the first place on the private leaderboard of the Test set. [abs] [ pdf ][ bib ] &copy JMLR 2015. ( edit, beta )

PDF Details

JMLR Journal 2014 Journal Article

Effective String Processing and Matching for Author Disambiguation

  • Wei-Sheng Chin
  • Yong Zhuang
  • Yu-Chin Juan
  • Felix Wu
  • Hsiao-Yu Tung
  • Tong Yu
  • Jui-Pin Wang
  • Cheng-Xia Chang

Track 2 of KDD Cup 2013 aims at determining duplicated authors in a data set from Microsoft Academic Search. This type of problems appears in many large-scale applications that compile information from different sources. This paper describes our solution developed at National Taiwan University to win the first prize of the competition. We propose an effective name matching framework and realize two implementations. An important strategy in our approach is to consider Chinese and non-Chinese names separately because of their different naming conventions. Post-processing including merging results of two predictions further boosts the performance. Our approach achieves F1-score 0.99202 on the private leader board, while 0.99195 on the public leader board. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

PDF Details
v2026.09.13