Lune

Profiles2023-2026

Yaojie Lu

Chinese Academy of Sciences

39Papers
0Last author
73Unique co-authors
0First author
0Solo

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

Recent papers39

  1. DeepRAG: Thinking to Retrieve Step by Step for Large Language ModelsAuthor 5 of 9ICLR 2026 · 30 citations
  2. Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language ModelsAuthor 3 of 9ICLR 2026 · 10 citations
  3. Coupled Variational Reinforcement Learning for Language Model General ReasoningAuthor 8 of 9ICML 2026 · 1 citation
  4. PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register IndexingAuthor 4 of 8ACL 2026 · 1 citation
  5. Across Programming Language Silos: A Study on Cross-Lingual Retrieval-Augmented Code GenerationAuthor 5 of 9ACL Findings 2026
  6. All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGAuthor 8 of 12ACL 2026
  7. DeepPresenter: Environment-Grounded Reflection for Agentic Presentation GenerationAuthor 7 of 10ACL Findings 2026
  8. EmbedAgent: Benchmarking Large Language Models in Embedded System DevelopmentAuthor 5 of 8ICSE 2026
  9. Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile ReasoningAuthor 4 of 8ACL Findings 2026
  10. On the Editability of Delta Parameters in Post-Trained ModelsAuthor 6 of 8ACL Findings 2026
  11. Towards Multimodal Large Language Models with Both Training and Inference EfficiencyAuthor 3 of 7ICML 2026
  12. CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and ExecutionAuthor 3 of 9ACL 2025 · 26 citations
  13. DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code GenerationAuthor 3 of 7AAAI 2025 · 25 citations
  14. DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point ThinkingAuthor 5 of 9ACL 2025 · 13 citations
  15. READoc: A Unified Benchmark for Realistic Document Structured ExtractionAuthor 3 of 10ACL Findings 2025 · 6 citations
  16. Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought CriticAuthor 7 of 10ACL Findings 2025 · 4 citations
  17. On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination MitigationAuthor 6 of 11ACL Findings 2025 · 3 citations
  18. PPTAgent: Generating and Evaluating Presentations Beyond Text-to-SlidesAuthor 8 of 11EMNLP 2025 · 3 citations
  19. Sparse Latents Steer Retrieval-Augmented GenerationAuthor 7 of 10ACL 2025 · 2 citations
  20. Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from ScratchAuthor 4 of 12ACL 2025 · 1 citation
  21. ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from ScratchAuthor 6 of 10EMNLP 2025
  22. From Informal to Formal - Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal ProofsAuthor 2 of 12ACL 2025
  23. Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?Author 3 of 10ICLR 2025
  24. ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective LayersAuthor 5 of 9ICCV 2025
  25. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information StructurizationAuthor 5 of 10ICLR 2025
  26. Teach Small Models to Reason by Curriculum DistillationAuthor 2 of 5EMNLP 2025
  27. The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward ModelsAuthor 5 of 8ICML 2025
  28. The Linguistic Connectivities Within Large Language ModelsAuthor 5 of 10ACL Findings 2025
  29. Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based RetrofittingAuthor 4 of 7AAAI 2024 · 127 citations
  30. Self-Retrieval: End-to-End Information Retrieval with One Large Language ModelAuthor 5 of 13NeurIPS 2024 · 14 citations

Showing the 30 most recent indexed papers.

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