Lune

Profiles2020-2026

Wei Ye

Peking University

55Papers
15Last author
59Unique co-authors
1First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers55

  1. TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate ThemAuthor 13 of 14ICLR 2026 · 29 citations
  2. OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use AgentsAuthor 9 of 10ICLR 2026 · 24 citations
  3. Retrieval as Generation: A Unified Framework with Self-Triggered Information PlanningAuthor 5 of 5ACL 2026 · 8 citations
  4. Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGAuthor 6 of 6AAAI 2026 · 5 citations
  5. Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment PerspectiveAuthor 8 of 8AAAI 2026 · 5 citations
  6. Instruction Data Selection via Answer DivergenceAuthor 4 of 4ACL 2026 · 4 citations
  7. Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-FutureAuthor 11 of 12ICML 2026 · 3 citations
  8. ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive SkewnessAuthor 6 of 6AAAI 2026
  9. AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering AgentsAuthor 4 of 5ISSTA 2026
  10. Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented GenerationAuthor 6 of 6SIGIR 2026
  11. Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented GenerationAuthor 5 of 5SIGIR 2026
  12. Data Selection for Multi-turn Dialogue Instruction TuningAuthor 3 of 3ACL Findings 2026
  13. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal ModelsAuthor 5 of 5ICML 2026
  14. LeLoRA: Learnable Low-Rank Adaptation of Large Language ModelsAuthor 4 of 5ACL 2026
  15. Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic FrameworkAuthor 4 of 4CVPR Findings 2026
  16. SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment GenerationAuthor 8 of 9FSE 2026
  17. Tailoring the Training: Difficulty-Aware Learning Strategy Allocation for Large Language ModelsAuthor 8 of 9ICML 2026
  18. What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?Author 9 of 9ICML 2026
  19. VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-ThoughtAuthor 3 of 9NeurIPS 2025 · 56 citations
  20. Queries Are Not Alone: Clustering Text Embeddings for Video SearchAuthor 4 of 4SIGIR 2025 · 8 citations
  21. SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse AutoencodersAuthor 7 of 7NeurIPS 2025 · 6 citations
  22. Boosting Resilience of Large Language Models through Causality-Driven Robust OptimizationAuthor 6 of 8NeurIPS 2025 · 5 citations
  23. Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security PerspectiveAuthor 5 of 5ACL 2025 · 4 citations
  24. All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image DenoisingAuthor 3 of 8CVPR 2025
  25. HaDeMiF: Hallucination Detection and Mitigation in Large Language ModelsAuthor 4 of 5ICLR 2025
  26. MPL: Multiple Programming Languages with Large Language Models for Information ExtractionAuthor 3 of 7ACL Findings 2025
  27. Reasoning Through Execution: Unifying Process and Outcome Rewards for Code GenerationAuthor 7 of 8ICML 2025
  28. SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference OptimizationAuthor 4 of 9CVPR 2025
  29. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationAuthor 12 of 14ICLR 2024 · 368 citations
  30. AutoSurvey: Large Language Models Can Automatically Write SurveysAuthor 11 of 13NeurIPS 2024 · 151 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines