PPaperPicks

Dawei Yin

Baidu, Beijing, China

109 papers at tracked venues · 72 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Accurate and Efficient Personalized Query Rewriting in Baidu Search
  2. AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
  3. Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models
  4. Agentic-R: Learning to Retrieve for Agentic Search
  5. An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision
  6. Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
  7. DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search
  8. DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
  9. Efficient Thought Space Exploration Through Strategic Intervention
  10. LLM-Based Listwise Reranking Under the Effect of Positional Bias
  11. MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
  12. Model Editing for New Document Integration in Generative Information Retrieval
  13. Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search
  14. RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
  15. ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
  16. Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning
  17. Reinforced Efficient Reasoning via Semantically Diverse Exploration
  18. Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory
  19. Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
  20. Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
  21. VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
  22. Advancing Temporal Sensitive Question Answering through Progressive Multi-Step Reflection
  23. AgentIR: 2nd Workshop on Agent-based Information Retrieval
  24. CLUE: Using Large Language Models for Judging Document Usefulness in Web Search Evaluation
  25. CTR-Guided Generative Query Suggestion in Conversational Search
  26. CoRanking: Collaborative Ranking with Small and Large Ranking Agents
  27. DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
  28. Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
  29. Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
  30. Enhancing Retrieval-Augmented Generation via Evidence Tree Search
  31. Exploring Preference-Guided Diffusion Model for Cross-Domain Recommendation
  32. FULTR: A Large-Scale Fusion Learning to Rank Dataset and Its Application for Satisfaction-Oriented Ranking
  33. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
  34. Generative Retrieval for Book Search
  35. Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
  36. Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
  37. Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
  38. InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
  39. Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
  40. Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
  41. LLMs + Persona-Plug = Personalized LLMs
  42. Large Language Model for E-Commerce Workshop
  43. Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search
  44. M2oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search
  45. MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification
  46. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
  47. MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
  48. Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
  49. Multi-Agent Proactive Information Seeking with Adaptive LLM Orchestration for Non-Factoid Question Answering
  50. Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search
  51. PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
  52. Proactive Guidance of Multi-Turn Conversation in Industrial Search
  53. RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction
  54. RankElectra: Semi-supervised Pre-training of Learning-to-Rank Electra for Web-scale Search
  55. RankExpert: A Mixture of Textual-and-Behavioral Experts for Multi-Objective Learning-to-Rank in Web Search
  56. Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
  57. Replication and Exploration of Generative Retrieval over Dynamic Corpora
  58. Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  59. Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models
  60. TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
  61. Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization
  62. The 2nd Workshop on Large Language Models for E-Commerce
  63. The Mirage of Model Editing: Revisiting Evaluation in the Wild
  64. Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
  65. TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
  66. Towards S²-Challenges Underlying LLM-Based Augmentation for Personalized News Recommendation
  67. Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance
  68. Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation
  69. Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation
  70. A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
  71. A Survey of Large Language Models for Graphs
  72. A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  73. ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator
  74. AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
  75. AgentIR: 1st Workshop on Agent-based Information Retrieval
  76. Cross-model Control: Improving Multiple Large Language Models in One-time Training
  77. Exploring Memorization in Fine-tuned Language Models
  78. FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding
  79. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
  80. GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation
  81. GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract)
  82. Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
  83. GraphGPT: Graph Instruction Tuning for Large Language Models
  84. HiGPT: Heterogeneous Graph Language Model
  85. Hyperbolic Contrastive Learning for Cross-Domain Recommendation
  86. KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
  87. Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
  88. LLMRec: Large Language Models with Graph Augmentation for Recommendation
  89. LT2R: Learning to Online Learning to Rank for Web Search
  90. Large Language Models for Graphs: Progresses and Directions
  91. Learning to Use Tools via Cooperative and Interactive Agents
  92. MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
  93. MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
  94. MPGraf: a Modular and Pre-trained Graphformer for Learning to Rank at Web-scale (Extended Abstract)
  95. PSP: Pre-training and Structure Prompt Tuning for Graph Neural Networks
  96. Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
  97. Representation Learning with Large Language Models for Recommendation
  98. Text-Video Retrieval via Multi-Modal Hypergraph Networks
  99. The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
  100. The Fall of ROME: Understanding the Collapse of LLMs in Model Editing
  101. The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
  102. Towards Completeness-Oriented Tool Retrieval for Large Language Models
  103. Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
  104. UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle
  105. Unbiased Learning-to-Rank Needs Unconfounded Propensity Estimation
  106. Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback
  107. UrbanGPT: Spatio-Temporal Large Language Models
  108. VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization
  109. Whole Page Unbiased Learning to Rank