Ruihan Yang

rhyang2021's activity

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

upvoted a paper 14 days ago

WideSeek: Advancing Wide Research via Multi-Agent Scaling

Paper • 2602.02636 • Published 21 days ago • 15

upvoted a paper 17 days ago

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning

Paper • 2601.21037 • Published 26 days ago • 15

upvoted a paper 20 days ago

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published 21 days ago • 238

upvoted a paper about 2 months ago

Confidence Estimation for LLMs in Multi-turn Interactions

Paper • 2601.02179 • Published Jan 5 • 17

liked a dataset 4 months ago

rhyang2021/UNCLE

Viewer • Updated Oct 9, 2025 • 1.07k • 147 • 1

updated a dataset 5 months ago

rhyang2021/UNCLE

Viewer • Updated Oct 9, 2025 • 1.07k • 147 • 1

published a dataset 5 months ago

rhyang2021/UNCLE

Viewer • Updated Oct 9, 2025 • 1.07k • 147 • 1

upvoted a paper 5 months ago

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Paper • 2509.22638 • Published Sep 26, 2025 • 70

upvoted a paper 6 months ago

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

Paper • 2509.06501 • Published Sep 8, 2025 • 82

liked a model 6 months ago

Alibaba-NLP/WebDancer-32B

Text Generation • Updated Jun 26, 2025 • 53 • • 57

liked a model 8 months ago

MASWorks/MAS-GPT-32B

Text Generation • 33B • Updated Jul 14, 2025 • 7 • 4

upvoted 4 papers 8 months ago

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Paper • 2502.08235 • Published Feb 12, 2025 • 59

Group-in-Group Policy Optimization for LLM Agent Training

Paper • 2505.10978 • Published May 16, 2025 • 20

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14, 2025 • 333

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Paper • 2506.13585 • Published Jun 16, 2025 • 273

upvoted a collection 8 months ago

MiniMax-M1

Collection

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated 10 days ago • 118

upvoted 4 papers 9 months ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9, 2025 • 263

ATLaS: Agent Tuning via Learning Critical Steps

Paper • 2503.02197 • Published Mar 4, 2025 • 9

Is Extending Modality The Right Path Towards Omni-Modality?

Paper • 2506.01872 • Published Jun 2, 2025 • 24

Think on your Feet: Adaptive Thinking via Reinforcement Learning for Social Agents

Paper • 2505.02156 • Published May 4, 2025 • 18