Generate Images with Claude and Hugging Face
…Tools like this could really change how teams design, iterate, or even co-create content together. This comment has been hidden It seems something was changed, because out of the box, i…
Search
Paper page - Step-level Optimization for Efficient Computer-use Agents
…many steps are routine and can be handled reliably by smaller, cheaper policies, while errors tend to concentrate at a relatively small number of high-risk moments. Across computer-use benchmarks, these…
Paper page - Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control
…Theoretically, we relate per-step entropy change to the advantage distribution under minimal assumptions. This explains the behavior of existing RL and entropy-preserving methods. Entrocraft also enables a systematic study of…
Paper page - FrameSkip: Learning from Fewer but More Informative Frames in VLA Training
…Bin Yu , Shijie Lian , , , , , , , , , Abstract FrameSkip is a data-layer frame selection method that improves VLA policy training by prioritizing high-importance frames based on action variation and visual-coherence metrics. AI…
Paper page - MolmoAct2: Action Reasoning Models for Real-world Deployment
…Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable…
Paper page - Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility
…Jungsuk Oh , , , , Abstract SPEED is a phase-asymmetric KV-visibility policy that reduces long-context inference costs in decoder-only language models by processing prompt tokens in lower layers during prefill while…
Paper page - Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
…On-Policy Self-Distillation for Long-Context Language Models (2026) A Survey of On-Policy Distillation for Large Language Models (2026) TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models (2026…
Paper page - ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
…We first model localized support interactions as Intervention Units (IUs), which capture state--action--outcome dynamics between seeker states, support interventions, and post-response emotional changes. Based on IUs extracted from both…
Paper page - Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages
…We argue this framing is wrong in mechanism but partially correct in conclusion, and that the correction matters for both theory and policy. Agents are not labor; they are a production technology…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.