PPaperPicks

Maosong Sun

Tsinghua University, Department of Computer Science and Technology, Beijing, China

116 papers at tracked venues · 91 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-6011-6115 ↗Google Scholar ↗

Venues

ACL ×58EMNLP ×18ICLR ×13NeurIPS ×8CVPR ×4NAACL ×4AAAI ×3ICML ×3IJCAI ×2ACM MM ×1CIKM ×1SIGIR ×1

Frequent coauthors

Shuzheng Si
DBLP profile ↗ORCID search ↗
×5
Weize Chen
DBLP profile ↗ORCID search ↗
×5
Kangyang Luo
DBLP profile ↗ORCID search ↗
×3
Chen Qian
DBLP profile ↗ORCID search ↗
×3
Xuanle Zhao
DBLP profile ↗ORCID search ↗
×2
Pengcheng Huang
DBLP profile ↗ORCID search ↗
×2
Zhenghao Liu
DBLP profile ↗ORCID search ↗
×2
Xingyu Shen
DBLP profile ↗ORCID search ↗
×2
Zhu Liu
DBLP profile ↗ORCID search ↗
×2
Shangda Wu
DBLP profile ↗ORCID search ↗
×2
Yingli Shen
DBLP profile ↗ORCID search ↗
×2
Weilin Zhao
DBLP profile ↗ORCID search ↗
×2

Papers

  1. A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Task
    ACL 2026 ·
    Shuzheng Si
    DBLP profile ↗ORCID search ↗
  2. AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
    ACL 2026 ·
    Xuanle Zhao
    DBLP profile ↗ORCID search ↗
  3. AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
    ACL 2026 ·
    ShangZhan Li
    DBLP profile ↗ORCID search ↗
  4. CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
    ACL 2026 ·
    Dingling Xu
    DBLP profile ↗ORCID search ↗
  5. Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
    ACL 2026 ·
    Shaohua Duan
    DBLP profile ↗ORCID search ↗
  6. EchoMLLM: Incentivizing Echocardiographic Video Understanding with Keyframe Grounding and Report Generation
    ACL 2026 ·
    Heyu Huang
    DBLP profile ↗ORCID search ↗
  7. Empirical Analysis of Decoding Biases in Masked Diffusion Models
    ACL 2026 ·
    Pengcheng Huang
    DBLP profile ↗ORCID search ↗
  8. Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
    ACL 2026 ·
    Zhuoyang Wu
    DBLP profile ↗ORCID search ↗
  9. FaithLens: Detecting and Explaining Faithfulness Hallucination
    ACL 2026 ·
    Shuzheng Si
    DBLP profile ↗ORCID search ↗
  10. From Scaffolding to Assimilation: Progressive Structural Internalization for Format-Constrained Creative Text Generation
    ACL 2026 ·
    Wenhao Li
    DBLP profile ↗ORCID search ↗
  11. IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
    AAAI 2026 ·
    Yuzhuo Bai
    DBLP profile ↗ORCID search ↗
  12. ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
    ACL 2026 ·
    Kangyang Luo
    DBLP profile ↗ORCID search ↗
  13. LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid
    AAAI 2026 ·
    Yipeng Zhang
    DBLP profile ↗ORCID search ↗
  14. Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
    ACL 2026 ·
    Zhenghao Liu
    DBLP profile ↗ORCID search ↗
  15. MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints
    ACL 2026 ·
    Kangyang Luo
    DBLP profile ↗ORCID search ↗
  16. MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
    ACL 2026 ·
    Haidong Xin
    DBLP profile ↗ORCID search ↗
  17. Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
    SIGIR 2026 ·
    Chunyi Peng
    DBLP profile ↗ORCID search ↗
  18. Musical Score Understanding Benchmark: Evaluating Large Language Models' Comprehension of Complete Musical Scores
    ACL 2026 ·
    Congren Dai
    DBLP profile ↗ORCID search ↗
  19. RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
    ACL 2026 ·
    Bingxian Wu
    DBLP profile ↗ORCID search ↗
  20. Revealing the Attention Floating Mechanism in Masked Diffusion Models
    ACL 2026 ·
    Xin Dai
    DBLP profile ↗ORCID search ↗
  21. StateX: Enhancing RNN Recall via Post-training State Expansion
    ACL 2026 ·
    Xingyu Shen
    DBLP profile ↗ORCID search ↗
  22. Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
    AAAI 2026 ·
    Shuzheng Si
    DBLP profile ↗ORCID search ↗
  23. UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
    ACL 2026 ·
    Yifan Ji
    DBLP profile ↗ORCID search ↗
  24. A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
    ICLR 2025 ·
    Kairong Luo
    DBLP profile ↗ORCID search ↗
  25. A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Case Study of Supplementary Adverbs
    NAACL 2025 ·
    Zhu Liu
    DBLP profile ↗ORCID search ↗
  26. A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
    NeurIPS 2025 ·
    Xiaoang Xu
    DBLP profile ↗ORCID search ↗
  27. APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
    ACL 2025 ·
    Yuxiang Huang
    DBLP profile ↗ORCID search ↗
  28. AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
    CVPR 2025 ·
    Yiyang Du
    DBLP profile ↗ORCID search ↗
  29. Advancing LLM Reasoning Generalists with Preference Trees
    ICLR 2025 ·
    Lifan Yuan
    DBLP profile ↗ORCID search ↗
  30. AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
    EMNLP 2025 ·
    Zhong Zhang
    DBLP profile ↗ORCID search ↗
  31. AgentRM: Enhancing Agent Generalization with Reward Modeling
    ACL 2025 ·
    Yu Xia
    DBLP profile ↗ORCID search ↗
  32. Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
    ACL 2025 ·
    Shuzheng Si
    DBLP profile ↗ORCID search ↗
  33. AutoClean: LLMs Can Prepare Their Training Corpus
    NAACL 2025 ·
    Xingyu Shen
    DBLP profile ↗ORCID search ↗
  34. Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
    ACM MM 2025 ·
    Zhenghao Liu
    DBLP profile ↗ORCID search ↗
  35. CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models
    NAACL 2025 ·
    Shangda Wu
    DBLP profile ↗ORCID search ↗
  36. CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages
    ACL 2025 ·
    Shangda Wu
    DBLP profile ↗ORCID search ↗
  37. ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
    ACL 2025 ·
    Xuanle Zhao
    DBLP profile ↗ORCID search ↗
  38. ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
    EMNLP 2025 ·
    Hao Chen
    DBLP profile ↗ORCID search ↗
  39. Cost-Optimal Grouped-Query Attention for Long-Context Modeling
    EMNLP 2025 ·
    Yingfa Chen
    DBLP profile ↗ORCID search ↗
  40. DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
    NeurIPS 2025 ·
    Yingli Shen
    DBLP profile ↗ORCID search ↗
  41. DeepNote: Note-Centric Deep Retrieval-Augmented Generation
    EMNLP 2025 ·
    Ruobing Wang
    DBLP profile ↗ORCID search ↗
  42. Document Segmentation Matters for Retrieval-Augmented Generation
    ACL 2025 ·
    Zhitong Wang
    DBLP profile ↗ORCID search ↗
  43. Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub
    ACL 2025 ·
    Bohan Lyu
    DBLP profile ↗ORCID search ↗
  44. FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
    ACL 2025 ·
    Weilin Zhao
    DBLP profile ↗ORCID search ↗
  45. From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
    EMNLP 2025 ·
    Yingli Shen
    DBLP profile ↗ORCID search ↗
  46. Fusing Highly Specialized Language Models for Comprehensive Expertise
    ACL 2025 ·
    Ning Ding
    DBLP profile ↗ORCID search ↗
  47. GATEAU: Selecting Influential Samples for Long Context Alignment
    EMNLP 2025 ·
    Shuzheng Si
    DBLP profile ↗ORCID search ↗
  48. GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion
    ACL 2025 ·
    Kangyang Luo
    DBLP profile ↗ORCID search ↗
  49. GUICourse: From General Vision Language Model to Versatile GUI Agent
    ACL 2025 ·
    Wentong Chen
    DBLP profile ↗ORCID search ↗
  50. Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
    ICLR 2025 ·
    Weize Chen
    DBLP profile ↗ORCID search ↗
  51. Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
    ACL 2025 ·
    Shuliang Liu
    DBLP profile ↗ORCID search ↗
  52. KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases
    EMNLP 2025 ·
    Zheni Zeng
    DBLP profile ↗ORCID search ↗
  53. LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
    EMNLP 2025 ·
    Yu Chao
    DBLP profile ↗ORCID search ↗
  54. LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models
    ACL 2025 ·
    Zihan Zhou
    DBLP profile ↗ORCID search ↗
  55. Learning to Generate Structured Output with Schema Reinforcement Learning
    ACL 2025 ·
    Yaxi Lu
    DBLP profile ↗ORCID search ↗
  56. Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
    EMNLP 2025 ·
    Haozhe Zhao
    DBLP profile ↗ORCID search ↗
  57. Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
    ACL 2025 ·
    You Li
    DBLP profile ↗ORCID search ↗
  58. Multi-Agent Collaboration via Evolving Orchestration
    NeurIPS 2025 ·
    Yufan Dang
    DBLP profile ↗ORCID search ↗
  59. NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
    IJCAI 2025 ·
    Yashan Wang
    DBLP profile ↗ORCID search ↗
  60. On LLM-Based Scientific Inductive Reasoning Beyond Equations
    EMNLP 2025 ·
    Brian S. Lin
    DBLP profile ↗ORCID search ↗
  61. Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
    ACL 2025 ·
    Weize Chen
    DBLP profile ↗ORCID search ↗
  62. ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
    NeurIPS 2025 ·
    Pengcheng Huang
    DBLP profile ↗ORCID search ↗
  63. PersLLM: A Personified Training Approach for Large Language Models
    EMNLP 2025 ·
    Zheni Zeng
    DBLP profile ↗ORCID search ↗
  64. Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
    ICLR 2025 ·
    Yaxi Lu
    DBLP profile ↗ORCID search ↗
  65. RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
    ICLR 2025 ·
    Xinze Li
    DBLP profile ↗ORCID search ↗
  66. RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
    ACL 2025 ·
    Kunlun Zhu
    DBLP profile ↗ORCID search ↗
  67. RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
    CVPR 2025 ·
    Tianyu Yu
    DBLP profile ↗ORCID search ↗
  68. Rational Decision-Making Agent with Learning Internal Utility Judgment
    ICLR 2025 ·
    Yining Ye
    DBLP profile ↗ORCID search ↗
  69. Scaling Large Language Model-based Multi-Agent Collaboration
    ICLR 2025 ·
    Chen Qian
    DBLP profile ↗ORCID search ↗
  70. Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training
    NAACL 2025 ·
    Sun Ao
    DBLP profile ↗ORCID search ↗
  71. Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
    ICML 2025 ·
    Yuqi Luo
    DBLP profile ↗ORCID search ↗
  72. The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
    NeurIPS 2025 ·
    Weize Chen
    DBLP profile ↗ORCID search ↗
  73. The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
    ACL 2025 ·
    Bingxiang He
    DBLP profile ↗ORCID search ↗
  74. TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
    ACL 2025 ·
    Jianling Li
    DBLP profile ↗ORCID search ↗
  75. Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs' Value Evaluation
    ACL 2025 ·
    Jing Yao
    DBLP profile ↗ORCID search ↗
  76. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
    ICLR 2025 ·
    Shi Yu
    DBLP profile ↗ORCID search ↗
  77. WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
    ICLR 2025 ·
    Shengda Fan
    DBLP profile ↗ORCID search ↗
  78. XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?
    CVPR 2025 ·
    Fengxiang Wang
    DBLP profile ↗ORCID search ↗
  79. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
    ICLR 2024 ·
    Weize Chen
    DBLP profile ↗ORCID search ↗
  80. Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
    EMNLP 2024 ·
    Weize Chen
    DBLP profile ↗ORCID search ↗
  81. Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
    EMNLP 2024 ·
    Xinrong Zhang
    DBLP profile ↗ORCID search ↗
  82. Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion
    ACL 2024 ·
    Ziyue Wang
    DBLP profile ↗ORCID search ↗
  83. CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models
    ACL 2024 ·
    Fuwen Luo
    DBLP profile ↗ORCID search ↗
  84. Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
    NeurIPS 2024 ·
    Xin Li
    DBLP profile ↗ORCID search ↗
  85. ChatDev: Communicative Agents for Software Development
    ACL 2024 ·
    Chen Qian
    DBLP profile ↗ORCID search ↗
  86. Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
    EMNLP 2024 ·
    Yiju Guo
    DBLP profile ↗ORCID search ↗
  87. DebugBench: Evaluating Debugging Capability of Large Language Models
    ACL 2024 ·
    Runchu Tian
    DBLP profile ↗ORCID search ↗
  88. DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models
    EMNLP 2024 ·
    Ranchi Zhao
    DBLP profile ↗ORCID search ↗
  89. Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
    NeurIPS 2024 ·
    Bowen Ping
    DBLP profile ↗ORCID search ↗
  90. Empowering Private Tutoring by Chaining Large Language Models
    CIKM 2024 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  91. Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs
    EMNLP 2024 ·
    Cheng Gao
    DBLP profile ↗ORCID search ↗
  92. Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
    ACL 2024 ·
    Yuanchi Zhang
    DBLP profile ↗ORCID search ↗
  93. Experiential Co-Learning of Software-Developing Agents
    ACL 2024 ·
    Chen Qian
    DBLP profile ↗ORCID search ↗
  94. Exploring the Benefit of Activation Sparsity in Pre-training
    ICML 2024 ·
    Zhengyan Zhang
    DBLP profile ↗ORCID search ↗
  95. Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics
    ACL 2024 ·
    Zhu Liu
    DBLP profile ↗ORCID search ↗
  96. FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection
    ACL 2024 ·
    Yufei Huang
    DBLP profile ↗ORCID search ↗
  97. InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
    NeurIPS 2024 ·
    Chaojun Xiao
    DBLP profile ↗ORCID search ↗
  98. LEGENT: Open Platform for Embodied Agents
    ACL 2024 ·
    Zhili Cheng
    DBLP profile ↗ORCID search ↗
  99. Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
    ICLR 2024 ·
    Jinyi Hu
    DBLP profile ↗ORCID search ↗
  100. LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
    ACL 2024 ·
    Hanqing Wang
    DBLP profile ↗ORCID search ↗
  101. MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
    ACL 2024 ·
    Zhiyu Yang
    DBLP profile ↗ORCID search ↗
  102. Model Composition for Multimodal Large Language Models
    ACL 2024 ·
    Chi Chen
    DBLP profile ↗ORCID search ↗
  103. OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
    ACL 2024 ·
    Chaoqun He
    DBLP profile ↗ORCID search ↗
  104. On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
    IJCAI 2024 ·
    Xinpeng Wang
    DBLP profile ↗ORCID search ↗
  105. Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
    EMNLP 2024 ·
    Weilin Zhao
    DBLP profile ↗ORCID search ↗
  106. Predicting Emergent Abilities with Infinite Resolution Evaluation
    ICLR 2024 ·
    Shengding Hu
    DBLP profile ↗ORCID search ↗
  107. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-Grained Correctional Human Feedback
    CVPR 2024 ·
    Tianyu Yu
    DBLP profile ↗ORCID search ↗
  108. Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
    ACL 2024 ·
    Xiaolong Wang
    DBLP profile ↗ORCID search ↗
  109. RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation
    EMNLP 2024 ·
    Qinyu Luo
    DBLP profile ↗ORCID search ↗
  110. StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
    ACL 2024 ·
    Zhicheng Guo
    DBLP profile ↗ORCID search ↗
  111. Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
    ACL 2024 ·
    Cheng Qian
    DBLP profile ↗ORCID search ↗
  112. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
    ICLR 2024 ·
    Yujia Qin
    DBLP profile ↗ORCID search ↗
  113. ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
    ICML 2024 ·
    Ganqu Cui
    DBLP profile ↗ORCID search ↗
  114. UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs
    ACL 2024 ·
    Chaoqun He
    DBLP profile ↗ORCID search ↗
  115. UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
    ACL 2024 ·
    Haoyu Wang
    DBLP profile ↗ORCID search ↗
  116. ınftyBench: Extending Long Context Evaluation Beyond 100K Tokens
    ACL 2024 ·
    Xinrong Zhang
    DBLP profile ↗ORCID search ↗