Lune

Profiles2025-2026

Sirui Han

The Hong Kong University of Science and Technology

21Papers
3Last author
25Unique co-authors
1First author
0Solo

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

Recent papers21

  1. BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary CodebookAuthor 9 of 10ACL 2026 · 5 citations
  2. SafeMT: Multi-turn Safety for Multimodal Language ModelsAuthor 10 of 11ACL 2026 · 4 citations
  3. Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning ModelsAuthor 7 of 9ACL 2026 · 3 citations
  4. Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic VerificationAuthor 11 of 11ICML 2026 · 3 citations
  5. Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI CollaborationAuthor 1 of 6CHI 2026 · 3 citations
  6. IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM InferenceAuthor 9 of 9ICML 2026 · 2 citations
  7. Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingAuthor 7 of 8AAAI 2026 · 2 citations
  8. What, Whether and How? Unveiling Process Reward Models for Thinking with Images ReasoningAuthor 8 of 8AAAI 2026 · 2 citations
  9. ContextLens: Modeling Imperfect Privacy and Safety Context for Legal ComplianceAuthor 8 of 9ACL 2026
  10. Modeling the Brain’s Grammar: ROI-Guided fMRI Pretraining for Transferable and Interpretable Vision DecodingAuthor 5 of 6CVPR 2026
  11. Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model MergingAuthor 8 of 9AAAI 2026
  12. Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News DetectionAuthor 8 of 9ACL 2026
  13. QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training-Inference MismatchAuthor 11 of 12ACL Findings 2026
  14. Automate Strategy Finding with LLM in Quant InvestmentAuthor 9 of 10EMNLP Findings 2025 · 10 citations
  15. Out-of-Distribution Detection via LLM-Guided Outlier Generation for Text-attributed GraphAuthor 5 of 6ACL Findings 2025 · 4 citations
  16. SafeLawBench: Towards Safe Alignment of Large Language ModelsAuthor 9 of 10ACL Findings 2025 · 4 citations
  17. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement LearningAuthor 6 of 11EMNLP 2025 · 1 citation
  18. Efficient Fine-Tuning of Large Models Via Nested Low-Rank AdaptationAuthor 9 of 10ICCV 2025 · 1 citation
  19. Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem ProvingAuthor 9 of 10EMNLP 2025 · 1 citation
  20. AIRA: Activation-Informed Low-Rank Adaptation for Large ModelsAuthor 6 of 7ICCV 2025
  21. PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal ComplianceAuthor 6 of 10ACL 2025
Dusk over the sea between two cliffs drawn in fine vertical lines