Meta Research · 7 records

dateidtitleauthorsvenue↑
2026-07-302607.27180HumanCLAW: Can Vision-Language Models Act Through a Body?Siyao Li et al.arXiv73
2026-07-132607.09415Self-Guided Test-Time Training for Long-Context LLMsXinyu Zhu et al.arXiv12
2026-07-102607.08716Remember When It Matters: Proactive Memory Agent for Long-Horizon AgentsYifan Wu et al.arXiv13
2026-06-302606.29957SWE-Together: Evaluating Coding Agents in Interactive User SessionsYifan Wu et al.arXiv13
2026-06-112605.30861Distilling LLM Feedback for Lean Theorem ProvingGaetan Narozniak et al.arXiv3
2026-06-032606.01476OmniOPD: Logit-Free On-Policy Distillation via Speculative VerificationYuhang Zhou et al.arXiv7
2026-05-192605.18749WavFlow: Audio Generation in Waveform SpaceFeiyan Zhou et al.arXiv4