…View arXiv page View PDF Project page Add to collection Community We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full…
…View arXiv page View PDF Project page GitHub 82.2k Add to collection Community https://arxiv.org/pdf/2606.03264
…Abstract Reinforcement learning for large language model agents focuses on coordinating team behaviors through orchestration traces that capture spawning, delegation, communication, aggregation, and stopping decisions, identifying key technical axes in reward design…
…View arXiv page View PDF Project page GitHub 145 Add to collection Community An efficient transfer paradigm enabling high-quality, end-to-end pixel-space diffusion with minimal computational overhead (even on…
…View arXiv page View PDF Add to collection Community No dataset linking this paper Cite arxiv.org/abs/2605.09810 in a dataset README.md to link it from this page. No…
…View arXiv page View PDF Add to collection Community paper: https://arxiv.org/pdf/2606.03348 github: https://github.com/thu-coai/Syncred-Bench data: https://huggingface.co/datasets/thu-coai/Syncred…
…View arXiv page View PDF Project page GitHub 23 Add to collection Community Get this paper in your agent: hf papers read 2605.12492 Don't have the latest CLI? curl -LsSf…
…View arXiv page View PDF Project page GitHub 223 Add to collection Community Get this paper in your agent: hf papers read 2606.03985 Don't have the latest CLI? curl -LsSf…
…View arXiv page View PDF GitHub 61 Add to collection Community Qwen-Image-VAE-2.0 Technical Report
…We propose semantic motion anchors , natural-language abstractions of gesture motion capturing physical form and communicative intent . Our method discretizes 3D gestures into body-hand motion primitives , verbalizes them into structured descriptions…