huggingface3d agoDeepSeek-V4: a million-token context that agents can actually useRead on huggingface →
huggingface5d agoHow to Ground a Korean AI Agent in Real Demographics with Synthetic PersonasRead on huggingface →
huggingfaceApr 17NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid RobotsRead on huggingface →
huggingfaceApr 16Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational AgentsRead on huggingface →
huggingfaceApr 16Training and Finetuning Multimodal Embedding & Reranker Models with Sentence TransformersRead on huggingface →
huggingfaceApr 9Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUsRead on huggingface →
huggingfaceApr 9Multimodal Embedding & Reranker Models with Sentence TransformersRead on huggingface →
huggingfaceMar 31Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise DocumentsRead on huggingface →
huggingfaceMar 10Keep the Tokens Flowing: Lessons from 16 Open-Source RL LibrariesRead on huggingface →
huggingfaceMar 10Keep the Tokens Flowing: Lessons from 16 Open-Source RL LibrariesRead on huggingface →
huggingfaceMar 9Granite 4.0 1B Speech: Compact, Multilingual, and Built for the EdgeRead on huggingface →
huggingfaceMar 9Ulysses Sequence Parallelism: Training with Million-Token ContextsRead on huggingface →
huggingfaceMar 9Ulysses Sequence Parallelism: Training with Million-Token ContextsRead on huggingface →
huggingfaceMar 5Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device OptimizationsRead on huggingface →
huggingfaceMar 5Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device OptimizationsRead on huggingface →
huggingfaceMar 5Introducing Modular Diffusers - Composable Building Blocks for Diffusion PipelinesRead on huggingface →
huggingfaceMar 5Introducing Modular Diffusers - Composable Building Blocks for Diffusion PipelinesRead on huggingface →
huggingfaceFeb 20GGML and llama.cpp join HF to ensure the long-term progress of Local AIRead on huggingface →
huggingfaceFeb 20GGML and llama.cpp join HF to ensure the long-term progress of Local AIRead on huggingface →
huggingfaceFeb 18IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MASTRead on huggingface →
huggingfaceFeb 18IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MASTRead on huggingface →
huggingfaceFeb 12OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World EnvironmentsRead on huggingface →
huggingfaceFeb 12OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World EnvironmentsRead on huggingface →
huggingfaceFeb 4Community Evals: Because we're done trusting black-box leaderboards over the communityRead on huggingface →
huggingfaceFeb 4Community Evals: Because we're done trusting black-box leaderboards over the communityRead on huggingface →
huggingfaceFeb 3The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+Read on huggingface →
huggingfaceFeb 3The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+Read on huggingface →
huggingfaceFeb 3Training Design for Text-to-Image Models: Lessons from AblationsRead on huggingface →
huggingfaceFeb 3Training Design for Text-to-Image Models: Lessons from AblationsRead on huggingface →
huggingfaceJan 29Introducing Daggr: Chain apps programmatically, inspect visuallyRead on huggingface →
huggingfaceJan 29Introducing Daggr: Chain apps programmatically, inspect visuallyRead on huggingface →
huggingfaceJan 27Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeekRead on huggingface →
huggingfaceJan 27Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeekRead on huggingface →
huggingfaceJan 27Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMsRead on huggingface →
huggingfaceJan 27Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMsRead on huggingface →
huggingfaceJan 27Unlocking Agentic RL Training for GPT-OSS: A Practical RetrospectiveRead on huggingface →
huggingfaceJan 27Unlocking Agentic RL Training for GPT-OSS: A Practical RetrospectiveRead on huggingface →
huggingfaceJan 21AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial RealityRead on huggingface →
huggingfaceJan 21AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial RealityRead on huggingface →
huggingfaceJan 20Introducing Waypoint-1: Real-time interactive video diffusion from OverworldRead on huggingface →
huggingfaceJan 20Introducing Waypoint-1: Real-time interactive video diffusion from OverworldRead on huggingface →
huggingfaceJan 5Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid ArchitectureRead on huggingface →