Cosmos-Reason2 Collection Cosmos Reason 2 is an open, customizable, reasoning vision language model (VLM) for physical AI and robotics • 14 items • Updated 4 days ago • 6
Nemotron-Cascade Collection Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models • 17 items • Updated 6 days ago • 39
qqWen-Series Collection Based off the Qwen-2.5 Series - model finetuned for the Q programming language. • 12 items • Updated Oct 22 • 11
view article Article I Built a RAG System That Listens to Live BBC News and Answers Questions About "What Happened 10 Minutes Ago" 20 days ago • 13
PaCoRe Collection Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning • 3 items • Updated 20 days ago • 8
UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving Paper • 2512.09864 • Published 19 days ago • 10
Ultra Quantization Hybrid Model. Collection These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 6 items • Updated 4 days ago • 1
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization Paper • 2511.15705 • Published Nov 19 • 92
DeepSeek-R1-ReDistill Collection Re-distilled DeepSeek R1 models • 4 items • Updated Jan 30 • 15
Inference Optimized Checkpoints (with Model Optimizer) Collection A collection of generative models quantized and optimized for inference with Model Optimizer. • 46 items • Updated 6 days ago • 66
view article Article Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips Sep 24 • 9
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds Paper • 2511.08892 • Published Nov 12 • 201