pith. sign in

Sirui Han

Identifiers

  • name variant Sirui Han 0.60 · backfill

Papers (13)

  1. RW-TTT: Batched Serving for Request-Owned Test-Time Training State cs.LG · 2026 · author #6
  2. IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference cs.CL · 2026 · author #8
  3. KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning cs.AI · 2026 · author #7
  4. NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation cs.AI · 2026 · author #11
  5. ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution cs.RO · 2026 · author #6
  6. When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models cs.CV · 2026 · author #5
  7. ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance cs.CL · 2026 · author #8
  8. Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs cs.LG · 2026 · author #10
  9. QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch cs.LG · 2026 · author #11
  10. TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation cs.RO · 2026 · author #12
  11. Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning cs.CV · 2026 · author #7
  12. When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning cs.AI · 2025 · author #7
  13. BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook cs.LG · 2025 · author #9

Mentions

  • 2605.28053 #6 · arxiv_oai · confidence 0.70 Sirui Han
  • 2605.25475 #8 · arxiv_oai · confidence 0.70 Sirui Han
  • 2602.09023 #12 · arxiv_oai · confidence 0.70 Sirui Han
  • 2604.17375 #5 · backfill · confidence 0.70 Sirui Han

Frequent Coauthors