…View arXiv page View PDF Project page Add to collection Community FINAL Bench introduces a new evaluation paradigm for LLMs: functional metacognitive reasoning — not just "can the model solve it," but "does…
…However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill…
…View arXiv page View PDF GitHub 1 Add to collection Community We believe this work provides a step toward bridging ICL from pattern matching to in-context test time learning with two…
…View arXiv page View PDF Project page GitHub 116 Add to collection Community that gated attention trick to curb attention sink in a single, concatenated vision+text transformer is the most interesting…
…View arXiv page View PDF Add to collection Community Sharing our paper "The First Token Knows: Single-Decode Confidence for Hallucination Detection" . A single greedy decode captures almost all the hallucination-detection…
…View arXiv page View PDF Project page GitHub 34 Add to collection Community While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training…
…A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals…
…View arXiv page View PDF GitHub 889 Add to collection Community We're in the middle of a skill/agent explosion — everyone is packaging capabilities as reusable modules. But medical research skills…
…to collection Community ExoActor provides a scalable approach to modeling interaction-rich humanoid behaviors, potentially opening a new avenue for generative models to advance general-purpose humanoid intelligence. Feedback is very welcome…
…https://be2rlab.github.io/radio_vipe View arXiv page View PDF Project page GitHub 125 Add to collection Community We present RADIO-ViPE (Reduce All Domains Into One — Video Pose Engine), an…