Thomas ROBINSON

thomasmk30's activity

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

upvoted 2 papers about 17 hours ago

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 3 days ago • 120

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 3 days ago • 107

upvoted a paper 2 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 3 days ago • 170

upvoted a paper 3 days ago

WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation

Paper • 2608.24479 • Published 4 days ago • 134

upvoted a paper 8 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 9 days ago • 265

upvoted 2 papers 9 days ago

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Paper • 2608.13558 • Published 16 days ago • 91

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

Paper • 2608.18565 • Published 10 days ago • 116

upvoted a paper 10 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 15 days ago • 168

upvoted 2 papers 11 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 12 days ago • 339

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

Paper • 2608.16072 • Published 12 days ago • 150

upvoted a paper 12 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 15 days ago • 170

upvoted a paper 16 days ago

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

Paper • 2608.11924 • Published 17 days ago • 289

upvoted 2 papers 17 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 18 days ago • 187

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 20 days ago • 218

upvoted 2 papers 18 days ago

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

Paper • 2608.07468 • Published 22 days ago • 107

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

Paper • 2608.09819 • Published 19 days ago • 342

upvoted a paper 22 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 22 days ago • 249

upvoted a paper 25 days ago

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Paper • 2607.29677 • Published 29 days ago • 24

upvoted 2 papers 26 days ago

Mental World Modeling

Paper • 2607.27201 • Published Jul 29 • 108

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

Paper • 2607.28261 • Published about 1 month ago • 116