PPaperPicks

Shuaiqiang Wang

64 papers at tracked venues · 40 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. Beyond Step Pruning: Information Theory Based Step-level Optimization for Self-Refining Large Language Models
  5. DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
  6. Efficient Thought Space Exploration Through Strategic Intervention
  7. LLM-Based Listwise Reranking Under the Effect of Positional Bias
  8. MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
  9. Model Editing for New Document Integration in Generative Information Retrieval
  10. Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search
  11. Reinforced Efficient Reasoning via Semantically Diverse Exploration
  12. Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory
  13. Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
  14. Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
  15. VPN: Visual Prompt Navigation
  16. VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
  17. Advancing Temporal Sensitive Question Answering through Progressive Multi-Step Reflection
  18. CLUE: Using Large Language Models for Judging Document Usefulness in Web Search Evaluation
  19. CTR-Guided Generative Query Suggestion in Conversational Search
  20. CoRanking: Collaborative Ranking with Small and Large Ranking Agents
  21. DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
  22. Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
  23. Enhancing Retrieval-Augmented Generation via Evidence Tree Search
  24. FULTR: A Large-Scale Fusion Learning to Rank Dataset and Its Application for Satisfaction-Oriented Ranking
  25. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
  26. Generative Retrieval for Book Search
  27. Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
  28. Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
  29. LLMs + Persona-Plug = Personalized LLMs
  30. Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search
  31. M2oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search
  32. MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
  33. Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
  34. Multi-Agent Proactive Information Seeking with Adaptive LLM Orchestration for Non-Factoid Question Answering
  35. PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
  36. Proactive Guidance of Multi-Turn Conversation in Industrial Search
  37. RankElectra: Semi-supervised Pre-training of Learning-to-Rank Electra for Web-scale Search
  38. RankExpert: A Mixture of Textual-and-Behavioral Experts for Multi-Objective Learning-to-Rank in Web Search
  39. Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
  40. Replication and Exploration of Generative Retrieval over Dynamic Corpora
  41. Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  42. Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models
  43. TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
  44. Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization
  45. Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation
  46. Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes
  47. A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
  48. AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
  49. Cross-model Control: Improving Multiple Large Language Models in One-time Training
  50. Exploring Memorization in Fine-tuned Language Models
  51. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
  52. GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract)
  53. HetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awareness
  54. Hyperbolic Contrastive Learning for Cross-Domain Recommendation
  55. KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
  56. Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
  57. LT2R: Learning to Online Learning to Rank for Web Search
  58. MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
  59. MPGraf: a Modular and Pre-trained Graphformer for Learning to Rank at Web-scale (Extended Abstract)
  60. PSP: Pre-training and Structure Prompt Tuning for Graph Neural Networks
  61. The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
  62. Towards Completeness-Oriented Tool Retrieval for Large Language Models
  63. Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
  64. Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback