…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…
…All members share the same per-example gradient direction, differing only by a scalar amplification P_{θ^{-q}} that reweights each instance independently of the learning rate. This amplification is the mechanism…
…python -m mlx_vlm.generate --model mlx-community/SmolVLM2-500M-Video-Instruct-mlx --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg --prompt "Can you describe this image?" ====================================== test…
…A design choice shared by nearly all such methods, however, has gone unquestioned: the teacher always sees the full reference reasoning. We argue that this default itself is part of the problem…
…On five tasks under a shared GPT-5.5 backbone, AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction that reduces lower-wall Cf RMSE against DNS by 7.89% on…
…Thank you again for sharing this work with the community! Hi @ sseymens Thank you for your comments. I can help to reply your question about MOE on policy part. Yeah, forcing old…
…To support open-world generalization , we build a large-scale standardized data pipeline that converts heterogeneous robot, human, simulation, and real-world scan data into a shared affordance schema with language, masks…
…View arXiv page View PDF Project page GitHub 41 Add to collection Community Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle…
…On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from…
…The release contains 105 tasks spanning controlled business services and local workspace repair, and evaluates 13 frontier models under a shared public pass rule. Experiments reveal that reliable workflow automation remains far…