When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Paper • 2609.20511 • Published Sep 17 • 143
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published Sep 2 • 121
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 522
SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models Paper • 2608.29974 • Published Aug 30 • 4
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published Aug 31 • 119
Demystifying Agent Skills: Why They Work-Until They Don't Paper • 2608.14036 • Published Aug 14 • 168
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Paper • 2608.11924 • Published Aug 12 • 300
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues Paper • 2607.26178 • Published Jul 28 • 12
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting Paper • 2607.28261 • Published Jul 30 • 114