Nemotron-Terminal Collection We are releasing Nemotron-Terminal models and training datasets. • 7 items • Updated 2 days ago • 18
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data Paper • 2405.14333 • Published May 23, 2024 • 44
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 7 days ago • 465
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback Paper • 2511.01678 • Published Nov 3, 2025 • 38
Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors Paper • 2508.08896 • Published Aug 12, 2025 • 12
High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting Paper • 2510.10637 • Published Oct 12, 2025 • 15
Scaling Language-Centric Omnimodal Representation Learning Paper • 2510.11693 • Published Oct 13, 2025 • 104
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity Paper • 2510.23603 • Published Oct 27, 2025 • 25
Gemma 3 - Reasoning/Thinking Models (incl uncensored) Collection Fine tunes (most uncensored) of Gemma3s to add reasoning/thinking. Increases output and image processing quality and general model metrics. • 25 items • Updated about 18 hours ago • 14
OpenAI-GPT 20B, 37B ,120B: Neo, reg, uncensored, ablit. Collection OpenAi's model in various sizes and formats, including NEO Imatrix, DI, Tri Matrix, Uncensored, Albiterated, and Brainstorm 20x (37B). • 14 items • Updated 18 days ago • 14