Paper page - Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
… To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. …
Search
Paper page - Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
… View arXiv page View PDF Add to collection Community We're excited to share Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures ! …
Paper page - Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
… View arXiv page View PDF Project page GitHub 1 Add to collection Community Large-scale instruction tuning hits two walls: heterogeneous tasks produce conflicting gradients negative transfer , and joint training needs constant gradient sync across a tightly-coupled cluster. …
Share your open ML datasets on Hugging Face Hub!
… Even guidance on independently publishing our story in a way that aligns with Hugging Face's community values would be invaluable. We're committed to the same principles of open science and community engagement that make the Hub special. …
Easily Build and Share ROCm Kernels with Hugging Face
… You can find the documentation for Apple Silicon Metal here: https://github.com/huggingface/kernel-builder/blob/main/docs/metal.md And here’s an example of a kernel built for Metal: https://huggingface.co/kernels-community/gpt-oss-metal-kernels
Paper page - Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
… View arXiv page View PDF GitHub 1 Add to collection Community Published in IEEE Access, Vol. …
Paper page - PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
… View arXiv page View PDF Project page GitHub 21 Add to collection Community Welcome Wow! …
Paper page - AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
… View arXiv page View PDF Add to collection Community Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. …
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
… Great news for the Local AI community. …
Paper page - MinT: Managed Infrastructure for Training and Serving Millions of LLMs
… For more details about supported models, please visit: https://mint-doc.macaron.im/en/community/get-started/supported-models In addition, MinT also supports model families such as GLM-5.1, MiniMax, and OpenPI. …