Metis Collection Metis persistent-memory model family based on Qwen3.5, including 4B, 9B, and 27B parameter scales. • 4 items • Updated 8 days ago • 7
Skywork-Unipic3 Collection Unified Multi-Image Composition with Sequence Modeling • 9 items • Updated Mar 2 • 13
view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 22 days ago • 58
TIPSv2 Collection TIPSv2 foundational vision-language models. Webpage: https://gdm-tipsv2.github.io/ • 9 items • Updated 17 days ago • 41
view article Article Hugging Face and Cerebras bring Gemma 4 to real-time voice AI +2 A-Mahla, andito, lvwerra, vyassaurabh • Jul 1 • 93
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs Paper • 2606.06574 • Published Jun 4 • 25
view article Article How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent nvidia • Jun 4 • 75
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World Paper • 2605.26086 • Published May 25 • 25
ResearchMath-14K: Scaling Research-Level Mathematics via Agents Paper • 2605.28003 • Published May 27 • 50
MolmoAct2 Models Collection Collection of the base models for MolmoAct2 • 6 items • Updated May 5 • 23
MolmoAct2 Finetuned Models Collection Collection of the fine-tuned models for MolmoAct2 • 7 items • Updated May 14 • 12
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 356
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation Paper • 2605.27366 • Published May 26 • 30
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory Paper • 2605.15128 • Published May 14 • 65
view article Article Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality ibm-granite • May 14 • 33