PPaperPicks

Ji-Rong Wen

Renmin University of China, Beijing, China

132 papers at tracked venues · 94 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Analyzing and Mitigating Object Hallucination: A Training Bias Perspective
  2. Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models
  3. Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
  4. DeepAgent: A General Reasoning Agent with Scalable Toolsets
  5. EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
  6. Evaluating the Factuality of Large Language Models Using Multiple Plug-and-Play Fact Sources
  7. Experience-Driven Reflective Co-Evolution of Prompts and Heuristics for Autonomous Algorithm Design
  8. From Search to Ask to Act: The Evolution of Information Access in the Age of Large Models and Agents
    SIGIR 2026 · Ji-Rong Wen
  9. GenCI: Generative Modeling of User Interest Shift via Cohort-based Intent Learning for CTR Prediction
  10. Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
  11. HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches
  12. L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention
  13. LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation
  14. LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
  15. Learning to Retrieve from Agent Trajectories
  16. RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection
  17. Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement
  18. Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning
  19. Toward Generalized Web Agent Training: A Deep Dive into Entropy-Balanced Reinforcement Learning
  20. Universal Item Tokenization for Transferable Generative Recommendation
  21. Web Sitemap Knowledge Can Enhance Autonomous Browsing
  22. Addressing Personalized Bias for Unbiased Learning to Rank
  23. Autonomous Reasoning-Retrieval for Large Language Model Based Recommendation
  24. BordaRAG: Resolving Knowledge Conflict in Retrieval-Augmented Generation via Borda Voting Process
  25. Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation
  26. CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmented Generation
  27. CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds
  28. Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction
  29. DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
  30. DIVAgent: A Diversified Search Agent that Mimics the Human Search Process
  31. Dense Retrieval for Aggregated Search
  32. Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation
  33. Enhancing LLM Text Detection with Retrieved Contexts and Logits Distribution Consistency
  34. Enhancing Reward Models for High-Quality Image Generation: Beyond Text-Image Alignment
  35. Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation
  36. Evolving Graph-Based Context Modeling for Multi-Turn Conversational Retrieval-Augmented Generation
  37. Exploring the Design Space of Visual Context Representation in Video MLLMs
  38. Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop
  39. Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
  40. FairDiverse: A Comprehensive Toolkit for Fairness- and Diversity-aware Information Retrieval
  41. FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research
  42. FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
  43. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
  44. GenSim: A General Social Simulation Platform with Large Language Model based Agents
  45. HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
  46. ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
  47. Improving Retrospective Language Agents via Joint Policy Gradient Optimization
  48. Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
  49. Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study
  50. Irrational Complex Rotations Empower Low-bit Optimizers
  51. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
  52. KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
  53. LLM-Empowered Creator Simulation for Long-Term Evaluation of Recommender Systems Under Information Asymmetry
  54. Large Language Diffusion Models
  55. Less is More: High-value Data Selection for Visual Instruction Tuning
  56. MMATH: A Multilingual Benchmark for Mathematical Reasoning
  57. Masked Diffusion Models as Energy Minimization
  58. MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
  59. Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
  60. MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
  61. MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
  62. NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search
  63. Neuro-Symbolic Query Compiler
  64. Neuron based Personality Trait Induction in Large Language Models
  65. OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
  66. One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models
  67. Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
  68. Progressive Multimodal Reasoning via Active Retrieval
  69. RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation
  70. Regulatory DNA Sequence Design with Reinforcement Learning
  71. Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User
  72. Self-Calibrated Listwise Reranking with Large Language Models
  73. SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
  74. Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
  75. Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  76. Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework
  77. Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
  78. Test-Time Alignment with State Space Model for Tracking User Interest Shifts in Sequential Recommendation
  79. Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
  80. Toward Verifiable Instruction-Following Alignment for Retrieval Augmented Generation
  81. Towards Effective and Efficient Continual Pre-training of Large Language Models
  82. TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System
  83. Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
  84. Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
  85. Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing
  86. Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers
  87. ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
  88. WebThinker: Empowering Large Reasoning Models with Deep Research Capability
  89. YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model
  90. Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
  91. AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems
  92. An Analysis and Mitigation of the Reversal Curse
  93. AuriSRec: Adversarial User Intention Learning in Sequential Recommendation
  94. BASES: Large-scale Web Search User Simulation with Large Language Model based Agents
  95. Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
  96. CL4DIV: A Contrastive Learning Framework for Search Result Diversification
  97. Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model
  98. Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
  99. Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time
  100. DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy
  101. Dynamic Prompt Optimizing for Text-to-Image Generation
  102. EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention
  103. Exploring Context Window of Large Language Models via Decomposed Positional Vectors
  104. INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
  105. Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
  106. Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
  107. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
  108. LLMBox: A Comprehensive Library for Large Language Models
  109. Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
  110. Large Language Model Powered Agents for Information Retrieval
  111. Large Language Model Powered Agents in the Web
  112. Large Language Model-based Human-Agent Collaboration for Complex Task Solving
  113. Learning Dynamic Multi-attribute Interest for Personalized Product Search
  114. Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
  115. Modeling User Attention in Music Recommendation
  116. Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment
  117. Optimizing Probabilistic Box Embeddings with Distance Measures
  118. P2C2Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
  119. Promoting Two-sided Fairness with Adaptive Weights for Providers and Customers in Recommendation
  120. REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering
  121. Reflective Multi-Agent Collaboration based on Large Language Models
  122. Rotative Factorization Machines
  123. Scaling Law of Large Sequential Recommendation Models
  124. Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector
  125. Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs
  126. StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  127. The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
  128. Towards Completeness-Oriented Tool Retrieval for Large Language Models
  129. Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
  130. Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
  131. Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models
  132. Your Career Path Matters in Person-Job Fit