Lin Zihan

thomas-hill's activity

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

upvoted a paper about 13 hours ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published 4 days ago • 240

upvoted a paper about 16 hours ago

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published 11 days ago • 460

upvoted 2 papers 2 days ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 5 days ago • 272

Synthetic Sandbox for Training Machine Learning Engineering Agents

Paper • 2604.04872 • Published 7 days ago • 14

upvoted a paper 7 days ago

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published 16 days ago • 347

upvoted 2 papers 11 days ago

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Paper • 2603.24414 • Published 18 days ago • 182

CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence

Paper • 2603.28032 • Published 14 days ago • 339

upvoted a paper 12 days ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published 23 days ago • 330

upvoted a paper 24 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 26 days ago • 367

upvoted a paper about 1 month ago

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published Mar 3 • 193