shiyang li

flashlizard

·

FlashLizard

AI & ML interests

None yet

Recent Activity

upvoted a paper about 8 hours ago

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

upvoted a paper about 2 months ago

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

upvoted a paper 2 months ago

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

View all activity

Organizations

None yet

flashlizard 's datasets

None public yet