TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 13 days ago • 166
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models Paper • 2607.08770 • Published 23 days ago • 37
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
Agent Skills Should Go Beyond Text: The Case for Visual Skills Paper • 2606.01414 • Published May 31 • 10
blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated-exl3-5.0bpw Text Generation • 3B • Updated May 31 • 11 • 1
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published May 19 • 191
Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning Paper • 2605.14040 • Published May 13 • 5
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks Paper • 2605.19147 • Published May 18 • 3