zichuan lin

zichuan-lin's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 25 days ago

SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

Paper • 2512.02631 • Published 28 days ago • 8

authored 5 papers 26 days ago

Pretraining in Deep Reinforcement Learning: A Survey

Paper • 2211.03959 • Published Nov 8, 2022 • 1

A Survey on Transformers in Reinforcement Learning

Paper • 2301.03044 • Published Jan 8, 2023

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

Paper • 2511.15248 • Published Nov 19 • 6

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition

Paper • 2512.03794 • Published 27 days ago • 3

Future-conditioned Unsupervised Pretraining for Decision Transformer

Paper • 2305.16683 • Published May 26, 2023