Lune

Profiles2020-2026

Min Zhang

Soochow University

87Papers
66Last author
154Unique co-authors
0First author
0Solo

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

Recent papers87

  1. FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable ReasoningAuthor 5 of 5ICLR 2026 · 7 citations
  2. Re2: Unlocking LLM Reasoning via Reinforcement Learning with Re-solvingAuthor 7 of 7ICLR 2026 · 7 citations
  3. Revisiting Long-context Modeling from Context Denoising PerspectiveAuthor 6 of 6ICLR 2026 · 5 citations
  4. When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient ReasoningAuthor 7 of 7ACL 2026 · 3 citations
  5. Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse DomainsAuthor 7 of 8ACL 2026
  6. DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-RewardAuthor 9 of 9ACL 2026
  7. When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math ReasoningAuthor 8 of 8ACL Findings 2026
  8. Generative Reward Modeling via Synthetic Criteria Preference LearningAuthor 6 of 6ACL 2025 · 8 citations
  9. ALW: Adaptive Layer-Wise contrastive decoding enhancing reasoning ability in Large Language ModelsAuthor 5 of 5ACL Findings 2025 · 1 citation
  10. Revealing and Mitigating the Local Pattern Shortcuts of MambaAuthor 5 of 5ACL Findings 2025 · 1 citation
  11. A Training-free LLM-based Approach to General Chinese Character Error CorrectionAuthor 5 of 5ACL 2025
  12. A³: Automatic Alignment Framework for Attributed Text GenerationAuthor 5 of 5ACL 2025
  13. Accurate KV Cache Quantization with Outlier Tokens TracingAuthor 9 of 9ACL 2025
  14. An Empirical Study of Iterative Refinements for Non-autoregressive TranslationAuthor 6 of 6ACL 2025
  15. An Evaluation Resource for Grounding Translation ErrorsAuthor 8 of 8EMNLP Findings 2025
  16. Basic Reading DistillationAuthor 5 of 5ACL 2025
  17. Beware of Calibration Data for Pruning Large Language ModelsAuthor 8 of 8ICLR 2025
  18. DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling CheckAuthor 5 of 9ACL 2025
  19. From Awareness to Adaptability: Enhancing Tool Utilization for Scientific ReasoningAuthor 7 of 7ACL Findings 2025
  20. MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain AgentsAuthor 6 of 6EMNLP Findings 2025
  21. Revealing and Mitigating Over-Attention in Knowledge EditingAuthor 6 of 6ICLR 2025
  22. Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language ModelsAuthor 5 of 5ACL 2025
  23. From Role-Play to Drama-Interaction: An LLM SolutionAuthor 6 of 6ACL Findings 2024 · 20 citations
  24. Rethinking Negative Instances for Generative Named Entity RecognitionAuthor 6 of 6ACL Findings 2024 · 19 citations
  25. Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question AnsweringAuthor 7 of 7EMNLP Findings 2024 · 17 citations
  26. Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian OptimizationAuthor 9 of 9EMNLP Findings 2024 · 4 citations
  27. Demonstration Augmentation for Zero-shot In-context LearningAuthor 6 of 6ACL Findings 2024 · 4 citations
  28. DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware TranslatorsAuthor 4 of 6EMNLP 2024 · 4 citations
  29. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language ModelsAuthor 8 of 8EMNLP 2024 · 2 citations
  30. Are Bert Family Good Instruction Followers? A Study on Their Potential And LimitationsAuthor 8 of 8ICLR 2024 · 2 citations

Showing the 30 most recent indexed papers.

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