Lune

Profiles2022-2026

Rui Wang

Shanghai Jiao Tong University

35Papers
18Last author
39Unique co-authors
0First author
0Solo

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

Recent papers35

  1. DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing ReasoningAuthor 12 of 15ICLR 2026 · 271 citations
  2. Proximal Supervised Fine-TuningAuthor 3 of 6ICLR 2026 · 13 citations
  3. MrRoPE: Mixed-radix Rotary Position EmbeddingAuthor 5 of 5ICLR 2026 · 3 citations
  4. Hybrid Policy Distillation for LLMsAuthor 3 of 4ICML 2026 · 2 citations
  5. ML-Embed: Inclusive and Efficient Embeddings for a Multilingual WorldAuthor 5 of 5ICML 2026
  6. RepoDistill: Distilling Repository Knowledge through Compression-Aware Budget Allocation and Policy OptimizationAuthor 5 of 7ACL Findings 2026
  7. Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early DecodingAuthor 7 of 7NeurIPS 2025 · 66 citations
  8. GALLa: Graph Aligned Large Language Models for Improved Source Code UnderstandingAuthor 6 of 6ACL 2025 · 11 citations
  9. Enhancing Machine Translation with Self-Supervised Preference DataAuthor 5 of 5ACL 2025 · 7 citations
  10. Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-AgentAuthor 5 of 5ACL Findings 2025 · 1 citation
  11. Do Large Language Models Truly Understand Geometric Structures?Author 4 of 4ICLR 2025
  12. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning ModelsAuthor 11 of 14ICML 2025
  13. Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form GenerationAuthor 6 of 7EMNLP 2025
  14. Latent Space Chain-of-Embedding Enables Output-free LLM Self-EvaluationAuthor 5 of 5ICLR 2025
  15. RaSA: Rank-Sharing Low-Rank AdaptationAuthor 10 of 10ICLR 2025
  16. Structure Trumps Size: Rethinking Data Quality for LLM ReasoningAuthor 3 of 4EMNLP Findings 2025
  17. Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of TranslationeseAuthor 8 of 9EMNLP 2025
  18. Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned ModelAuthor 5 of 5ICLR 2025
  19. R-Judge: Benchmarking Safety Risk Awareness for LLM AgentsAuthor 11 of 12EMNLP Findings 2024 · 46 citations
  20. Embedding Trajectory for Out-of-Distribution Detection in Mathematical ReasoningAuthor 6 of 8NeurIPS 2024 · 23 citations
  21. Improving Open-Ended Text Generation via Adaptive DecodingAuthor 5 of 5ICML 2024 · 21 citations
  22. Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language ModelsAuthor 8 of 8ACL 2024 · 17 citations
  23. Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement MethodAuthor 7 of 7ACL Findings 2024 · 8 citations
  24. Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuningAuthor 6 of 7EMNLP Findings 2024 · 6 citations
  25. Unsupervised Sign Language Translation and GenerationAuthor 5 of 9ACL Findings 2024 · 6 citations
  26. AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization PreferenceAuthor 3 of 5EMNLP Findings 2024 · 2 citations
  27. MELA: Multilingual Evaluation of Linguistic AcceptabilityAuthor 5 of 6ACL 2024
  28. Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought MethodAuthor 3 of 3ACL 2023 · 39 citations
  29. Rethinking Translation Memory Augmented Neural Machine TranslationAuthor 6 of 6ACL Findings 2023 · 7 citations
  30. DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine ReadingAuthor 6 of 6EMNLP Findings 2023 · 4 citations

Showing the 30 most recent indexed papers.

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