PPaperPicks

Rui Yan

Peking University, Center for Data Science, Beijing, China

66 papers at tracked venues · 50 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Data Pollination: An Emergent Ecological Process Driving AI Population Evolution
  2. DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
  3. From 1, 000, 000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
  4. From Style to Story: A Curriculum Learning Approach for Imitative Novel Generation
  5. StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
  6. Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers
  7. When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
  8. 2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
  9. 3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling
  10. Autonomy-of-Experts Models
  11. Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
  12. BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking
  13. CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback
  14. DNASpeech: A Contextualized and Situated Text-to-Speech Dataset with Dialogues, Narratives and Actions
  15. Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
  16. GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework
  17. Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey
  18. Language Models "Grok" to Copy
  19. LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
  20. Luoling: An Immersive Cross-Modal Interactive Poem Creation Factory through Multi-Agent Collaboration
  21. MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
  22. MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions
  23. MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting
  24. More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
  25. PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead
  26. PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
  27. SAGraph: A Large-Scale Social Graph Dataset with Comprehensive Context for Influencer Selection in Marketing
  28. Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
  29. The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents
  30. The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News
  31. Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement
  32. Towards Effective and Efficient Continual Pre-training of Large Language Models
  33. Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts
  34. Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
  35. "In-Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
  36. An Analysis and Mitigation of the Reversal Curse
  37. Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
  38. BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning
  39. Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking
  40. Bridging the Space Gap: Unifying Geometry Knowledge Graph Embedding with Optimal Transport
  41. CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
  42. CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation
  43. Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference
  44. CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment
  45. DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy
  46. Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
  47. Empathetic Response Generation with Relation-aware Commonsense Knowledge
  48. Enhancing Job Recommendation through LLM-Based Generative Adversarial Networks
  49. Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors
  50. Flexible and Adaptable Summarization via Expertise Separation
  51. Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
  52. From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News
  53. From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
  54. Graph-Structured Speculative Decoding
  55. Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
  56. Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
  57. Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
  58. Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules
  59. Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
  60. Re-creation of Creations: A New Paradigm for Lyric-to-Melody Generation
  61. SCALE: Synergized Collaboration of Asymmetric Language Translation Engines
  62. StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  63. The Reasonableness Behind Unreasonable Translation Capability of Large Language Model
  64. Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search
  65. What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation
  66. Your Career Path Matters in Person-Job Fit