| HF | vLLM V0 to V1: Correctness Before Corrections in RLโ | May 6, 2026 |
| HF | Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agentsโ | Apr 28, 2026 |
| HF | DeepSeek-V4: a million-token context that agents can actually useโ | Apr 24, 2026 |
| HF | QIMMA ููู
ูุฉ โฐ: A Quality-First Arabic LLM Leaderboardโ | Apr 21, 2026 |
| HF | How to Ground a Korean AI Agent in Real Demographics with Synthetic Personasโ | Apr 21, 2026 |
| HF | ALTKโEvolve: OnโtheโJob Learning for AI Agentsโ | Apr 8, 2026 |
| HF | Welcome Gemma 4: Frontier multimodal intelligence on deviceโ | Apr 2, 2026 |
| HF | Holo3: Breaking the Computer Use Frontierโ | Apr 1, 2026 |
| HF | Liberate your OpenClawโ | Mar 27, 2026 |
| HF | Build a Domain-Specific Embedding Model in Under a Dayโ | Mar 20, 2026 |
| HF | What's New in Mellea 0.4.0 + Granite Libraries Releaseโ | Mar 20, 2026 |
| HF | **Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding**โ | Mar 19, 2026 |
| HF | Beyond Semantic Similarity: Introducing NVIDIA NeMo Retrieverโs Generalizable Agentic Retrieval Pipelineโ | Mar 13, 2026 |
| HF | How NVIDIA Builds Open Data for AIโ | Mar 10, 2026 |
| HF | GGML and llama.cpp join HF to ensure the long-term progress of Local AIโ | Feb 20, 2026 |
| HF | NVIDIA Nemotron 2 Nano 9B Japanese: ๆฅๆฌใฎใฝใใชใณAIใๆฏใใๆๅ
็ซฏๅฐ่ฆๆจก่จ่ชใขใใซโ | Feb 17, 2026 |
| HF | OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environmentsโ | Feb 12, 2026 |
| HF | Introducing SyGra Studioโ | Feb 5, 2026 |
| HF | Nemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3โs Top Modelโ | Feb 4, 2026 |
| HF | Community Evals: Because we're done trusting black-box leaderboards over the communityโ | Feb 4, 2026 |
| HF | H Company's new Holo2 model takes the lead in UI Localizationโ | Feb 3, 2026 |
| HF | The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+โ | Feb 3, 2026 |