Zihan Gao's picture

Open to Work

Zihan Gao

Papercold

·

AI & ML interests

Robotics Manipulation/Data Generation

Recent Activity

upvoted a paper 1 day ago

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

upvoted a paper 4 days ago

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

liked a model 4 days ago

nvidia/Cosmos3-Super

View all activity

Organizations

upvoted a paper 1 day ago

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Paper • 2606.13681 • Published 3 days ago • 118

upvoted a paper 4 days ago

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Paper • 2606.10572 • Published 4 days ago • 15

upvoted a collection 4 months ago

XVLA

X-VLA is a soft-prompted Transformer for cross-embodiment robot learning • 6 items • Updated Dec 4, 2025 • 13

upvoted a collection 5 months ago

Pi0.5

π₀₅ base models from Physical Intelligence • 5 items • Updated Mar 4 • 12

upvoted a paper 7 months ago

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

Paper • 2511.06411 • Published Nov 9, 2025 • 18