Thomas ROBINSON

thomasmk30's activity

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

upvoted a paper about 17 hours ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 2 days ago • 113

upvoted a paper about 18 hours ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 2 days ago • 47

upvoted a paper 1 day ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 5 days ago • 159

upvoted a paper 6 days ago

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Paper • 2608.11924 • Published 7 days ago • 282

upvoted 3 papers 7 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 8 days ago • 178

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 10 days ago • 210

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Paper • 2608.07468 • Published 12 days ago • 105

upvoted a paper 8 days ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 9 days ago • 334

upvoted a paper 12 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 12 days ago • 242

upvoted a paper 15 days ago

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Paper • 2607.29677 • Published 19 days ago • 24

upvoted 2 papers 16 days ago

Mental World Modeling

Paper • 2607.27201 • Published 21 days ago • 106

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published 20 days ago • 116

upvoted 3 papers 19 days ago

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 21 days ago • 271

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 20 days ago • 306

DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation

Paper • 2607.26811 • Published 21 days ago • 92

upvoted 2 papers 21 days ago

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published 22 days ago • 156

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Paper • 2607.21655 • Published 28 days ago • 193

upvoted a paper 26 days ago

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 27 days ago • 154

upvoted 2 papers 28 days ago

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published 28 days ago • 311

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published about 1 month ago • 198