PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents Paper • 2608.26530 • Published 15 days ago • 35
ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion Paper • 2607.20417 • Published Jul 22 • 10
From Pixels to States: Rethinking Interactive World Models as Game Engines Paper • 2607.14076 • Published Jul 15 • 37
anorim/bertweetbr-fusion-2-regmean-a0.9-bestcross-hatebr-hspt-olidbr-toldbr-tupy-v5 0.1B • Updated Jul 16 • 1
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published Jul 7 • 79
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published Jun 19 • 76
RepSelect: Robust LLM Unlearning via Representation Selectivity Paper • 2606.17168 • Published Jun 15 • 5
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks Paper • 2606.12344 • Published Jun 10 • 72