arxiv:2506.05426
Zican Hu
huzican
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 9 hours ago
WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
upvoted
a
paper
22 days ago
Speed Always Wins: A Survey on Efficient Architectures for Large
Language Models
authored
a paper
about 1 month ago
Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents
via Offline Hierarchical Reinforcement Learning
Organizations
None yet
models
0
None public yet
datasets
0
None public yet