Tao Gui

Venues

Frequent coauthors

Papers

1. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
   ACL 2026 ·

   Jie Yang

   DBLP profile ↗ORCID search ↗
2. AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
   ACL 2026 ·

   Zhiheng Xi

   DBLP profile ↗ORCID search ↗
3. AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
   WWW 2026 ·

   Zhiheng Xi

   DBLP profile ↗ORCID search ↗
4. AgentV-RL: Scaling Reward Modeling with Agentic Verifier
   ACL 2026 ·

   Jiazheng Zhang

   DBLP profile ↗ORCID search ↗
5. Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training
   ACL 2026 ·

   Changhao Jiang

   DBLP profile ↗ORCID search ↗
6. Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
   ACL 2026 ·

   Xin Guo

   DBLP profile ↗ORCID search ↗
7. DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data
   ACL 2026 ·

   Shaofan Liu

   DBLP profile ↗ORCID search ↗
8. Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
   ACL 2026 ·

   Junzhe Wang

   DBLP profile ↗ORCID search ↗
9. Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
   ACL 2026 ·

   Junjie Ye

   DBLP profile ↗ORCID search ↗
10. FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
    ACL 2026 ·

    Caishuang Huang

    DBLP profile ↗ORCID search ↗
11. From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling
    ACL 2026 ·

    Yifei Cao

    DBLP profile ↗ORCID search ↗
12. LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
    ACL 2026 ·

    Ming Zhang

    DBLP profile ↗ORCID search ↗
13. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
    ACL 2026 ·

    Hengyuan Zhang

    DBLP profile ↗ORCID search ↗
14. MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention Across Vision-Language Models
    AAAI 2026 ·

    Xiaoran Fan

    DBLP profile ↗ORCID search ↗
15. MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
    ACL 2026 ·

    Jiahang Lin

    DBLP profile ↗ORCID search ↗
16. MetaAct-RL: Training Language Models for Reasoning Through Meta-Action-Based Reinforcement Learning
    AAAI 2026 ·

    Zhiheng Xi

    DBLP profile ↗ORCID search ↗
17. MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
    ACL 2026 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
18. Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control
    ACL 2026 ·

    Changhao Jiang

    DBLP profile ↗ORCID search ↗
19. OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
    ACL 2026 ·

    Deming Ding

    DBLP profile ↗ORCID search ↗
20. Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
    ACL 2026 ·

    Binghai Wang

    DBLP profile ↗ORCID search ↗
21. VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
    ACL 2026 ·

    Dingwei Zhu

    DBLP profile ↗ORCID search ↗
22. What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
    AAAI 2026 ·

    Xiaoran Fan

    DBLP profile ↗ORCID search ↗
23. Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
    ACL 2026 ·

    Yuming Yang

    DBLP profile ↗ORCID search ↗
24. AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments
    ACL 2025 ·

    Zhiheng Xi

    DBLP profile ↗ORCID search ↗
25. Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning
    AAAI 2025 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
26. Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
    EMNLP 2025 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
27. BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
    NeurIPS 2025 ·

    Zhiheng Xi

    DBLP profile ↗ORCID search ↗
28. Better Process Supervision with Bi-directional Rewarding Signals
    ACL 2025 ·

    Wenxiang Chen

    DBLP profile ↗ORCID search ↗
29. CritiQ: Mining Data Quality Criteria from Human Preferences
    ACL 2025 ·

    Honglin Guo

    DBLP profile ↗ORCID search ↗
30. Distill Visual Chart Reasoning Ability from LLMs to MLLMs
    EMNLP 2025 ·

    Wei He

    DBLP profile ↗ORCID search ↗
31. EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
    NeurIPS 2025 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
32. Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety
    EMNLP 2025 ·

    Chenhao Huang

    DBLP profile ↗ORCID search ↗
33. Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
    ICLR 2025 ·

    Shuo Li

    DBLP profile ↗ORCID search ↗
34. INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
    NeurIPS 2025 ·

    Wujian Peng

    DBLP profile ↗ORCID search ↗
35. LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation
    EMNLP 2025 ·

    Ming Zhang

    DBLP profile ↗ORCID search ↗
36. LoRACoE: Improving Large Language Model via Composition-based LoRA Expert
    EMNLP 2025 ·

    Guanyu Li

    DBLP profile ↗ORCID search ↗
37. Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling
    ACL 2025 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
38. Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric
    ACL 2025 ·

    Yuming Yang

    DBLP profile ↗ORCID search ↗
39. Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
    EMNLP 2025 ·

    Shuo Li

    DBLP profile ↗ORCID search ↗
40. Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
    NAACL 2025 ·

    Yiwen Ding

    DBLP profile ↗ORCID search ↗
41. Multi-Programming Language Sandbox for LLMs
    ACL 2025 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
42. PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts
    ACL 2025 ·

    Ming Zhang

    DBLP profile ↗ORCID search ↗
43. Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
    EMNLP 2025 ·

    Senjie Jin

    DBLP profile ↗ORCID search ↗
44. Pre-Trained Policy Discriminators are General Reward Models
    NeurIPS 2025 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
45. RMB: Comprehensively benchmarking reward models in LLM alignment
    ICLR 2025 ·

    Enyu Zhou

    DBLP profile ↗ORCID search ↗
46. SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models
    CVPR 2025 ·

    Yongting Zhang

    DBLP profile ↗ORCID search ↗
47. TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
    EMNLP 2025 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
48. ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
    ACL 2025 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
49. Toward Optimal LLM Alignments Using Two-Player Games
    EMNLP 2025 ·

    Rui Zheng

    DBLP profile ↗ORCID search ↗
50. Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
    ACL 2025 ·

    Tao Ji

    DBLP profile ↗ORCID search ↗
51. Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
    NeurIPS 2025 ·

    Jun Zhao

    DBLP profile ↗ORCID search ↗
52. UniPaint: Unified Space-Time Video Inpainting via Mixture-of-Experts
    ICCV 2025 ·

    Zhen Wan

    DBLP profile ↗ORCID search ↗
53. AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
    ACL 2024 ·

    Jun Zhan

    DBLP profile ↗ORCID search ↗
54. Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
    ACL 2024 ·

    Ting Wu

    DBLP profile ↗ORCID search ↗
55. Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning
    EMNLP 2024 ·

    Lu Chen

    DBLP profile ↗ORCID search ↗
56. Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
    ICLR 2024 ·

    Rui Zheng

    DBLP profile ↗ORCID search ↗
57. LLMEval: A Preliminary Study on How to Evaluate Large Language Models
    AAAI 2024 ·

    Yue Zhang

    DBLP profile ↗ORCID search ↗
58. LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration
    EMNLP 2024 ·

    Jun Zhao

    DBLP profile ↗ORCID search ↗
59. Length Generalization of Causal Transformers without Position Encoding
    ACL 2024 ·

    Jie Wang

    DBLP profile ↗ORCID search ↗
60. LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
    ACL 2024 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
61. LongHeads: Multi-Head Attention is Secretly a Long Context Processor
    EMNLP 2024 ·

    Yi Lu

    DBLP profile ↗ORCID search ↗
62. Making Harmful Behaviors Unlearnable for Large Language Models
    ACL 2024 ·

    Xin Zhou

    DBLP profile ↗ORCID search ↗
63. Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
    EMNLP 2024 ·

    Chong Zhang

    DBLP profile ↗ORCID search ↗
64. Navigating the OverKill in Large Language Models
    ACL 2024 ·

    Chenyu Shi

    DBLP profile ↗ORCID search ↗
65. P4: Plug-and-Play Discrete Prompting for Large Language Models Personalization
    ACL 2024 ·

    Yuansen Zhang

    DBLP profile ↗ORCID search ↗
66. PDF-to-Tree: Parsing PDF Text Blocks into a Tree
    EMNLP 2024 ·

    Yue Zhang

    DBLP profile ↗ORCID search ↗
67. Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation
    ACL 2024 ·

    Yikun Wang

    DBLP profile ↗ORCID search ↗
68. Reward Modeling Requires Automatic Adjustment Based on Data Quality
    EMNLP 2024 ·

    Binghai Wang

    DBLP profile ↗ORCID search ↗
69. RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
    EMNLP 2024 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
70. Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
    NAACL 2024 ·

    Wei He

    DBLP profile ↗ORCID search ↗
71. StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback
    ACL 2024 ·

    Shihan Dou

    DBLP profile ↗ORCID search ↗
72. ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
    ACL 2024 ·

    Junjie Ye

    DBLP profile ↗ORCID search ↗
73. Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
    ICML 2024 ·

    Zhiheng Xi

    DBLP profile ↗ORCID search ↗
74. TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
    EMNLP 2024 ·

    Ming Zhang

    DBLP profile ↗ORCID search ↗
75. Unveiling Linguistic Regions in Large Language Models
    ACL 2024 ·

    Zhihao Zhang

    DBLP profile ↗ORCID search ↗
76. Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
    EMNLP 2024 ·

    Xin Zhou

    DBLP profile ↗ORCID search ↗