Kangrui Wang

JamesK2W's activity

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

upvoted a paper about 16 hours ago

Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models

Paper • 2506.18945 • Published 3 days ago • 25

upvoted a paper 29 days ago

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Paper • 2504.20073 • Published Apr 24 • 11

authored a paper 4 months ago

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Paper • 2502.09560 • Published Feb 13 • 36

upvoted a paper 4 months ago

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Paper • 2502.09560 • Published Feb 13 • 36

upvoted a paper 8 months ago

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

Paper • 2410.07166 • Published Oct 9, 2024 • 3