HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals Paper • 2609.04444 • Published 11 days ago • 5
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 12 days ago • 546
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Paper • 2609.00188 • Published 14 days ago • 53
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs Paper • 2607.25669 • Published Jul 28 • 9
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 254
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published May 28 • 152