Granite 4.2 Language Models Collection Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 3 items • Updated about 14 hours ago • 17
Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts Paper • 2608.20061 • Published 6 days ago • 42
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published 12 days ago • 277
view article Article State of Open Models: Summer 2026 Observations +1 AdinaY, multimodalart, irenesolaiman • 12 days ago • 154
NVFP4 Collection Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 11 items • Updated 6 days ago • 66
view article Article Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model CohereLabs • 14 days ago • 38
LTX-2.5 Collection LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs • 4 items • Updated 14 days ago • 51
NVIDIA Nemotron v3 Collection Open, Production-ready Enterprise Models • 33 items • Updated 11 days ago • 363
Muse Glimmer Collection Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated 16 days ago • 103
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Paper • 2608.05102 • Published 21 days ago • 66
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published 20 days ago • 62
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing Paper • 2608.02711 • Published 22 days ago • 91
Xiaomi-Robotics-1 Collection Scaling Vision-Language-Action Models with 100K+ Hours of Real-World Data • 4 items • Updated 29 days ago • 23
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory Paper • 2607.27919 • Published 27 days ago • 59
J.O.S.I.E-2 Collection The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 22 items • Updated 19 days ago • 11