We ask what a policy learns from its harness and what survives when the harness changes. Under KL-regularized control, we ...
VibeVideoBench evaluates multimodal agents that generate videos via code, finding that top systems meet core requirements on ...
Hy-Nomas is a video world model that uses causal attention and structured captions to follow multi-turn text and camera ...
ThinkWorld improves robotic generalization by representing actions as dynamics chains and using world imagination to learn ...
Prox replaces calibrated thresholds with top-k channel selection and a weight-derived reader to accelerate Mixture-of-Experts ...
A world model predicts machine learning program outcomes to enable affordable test-time scaling for AI research agents, ...
Rollback improves robot policies by using world models to rewind to past decisions, explore counterfactual actions, and ...
CREDIT improves language model self-attribution of external information via counterfactual training, reducing false ...
Factor-Aware Predictive Learning enables video diffusion transformers to leverage multimodal language model representations ...
A Blog post by NVIDIA on Hugging Face ...
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.
Download qwen3.5_9b_int8_convrot.safetensors from Winnougan/Qwen-3.5-INT8-Convrot-Comfy: direct link, hf CLI and curl. Xet efficiently stores Large Files inside Git, intelligently splitting files into ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results