Han Lu's picture

3 1

Han Lu

SJTULH

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs

liked a dataset about 1 month ago

nex-agi/agent-sft

authored a paper 3 months ago

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

View all activity

Organizations

authored 2 papers 3 months ago

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Paper • 2510.13554 • Published Oct 15, 2025 • 57

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony

Paper • 2510.11345 • Published Oct 13, 2025 • 17