ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published 5 days ago • 290
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 2 days ago • 256
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Paper • 2609.11115 • Published 6 days ago • 185
DataFlex-RL: An Evaluation Platform for RLVR Data Policies Paper • 2609.06107 • Published 11 days ago • 109
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models Paper • 2609.12641 • Published 5 days ago • 70
Dr. Claw: An AI Scientist Workspace for Vibe Research Paper • 2609.00365 • Published 16 days ago • 182
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published 14 days ago • 122
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 15 days ago • 268
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 21 days ago • 196