arXiv cs.AI / cs.LG / cs.CL·4d agoCliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents#context-compaction#coding-agents#test-time-scalingAI research1
Hugging Face daily papers·11d agoSample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling#batching#benchmarking#gpu-energy
arXiv cs.AI / cs.LG / cs.CL·15d agoDynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model#diffusion-models#foundation-models#masked-diffusionAI research1
Hugging Face daily papers·16d agoDynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model#masked-diffusion#open-x-embodiment#robotics1
