Factor-Aware Predictive Learning enables video diffusion transformers to leverage multimodal language model representations ...
A Blog post by NVIDIA on Hugging Face ...
We ask what a policy learns from its harness and what survives when the harness changes. Under KL-regularized control, we ...
Hy-Nomas is a video world model that uses causal attention and structured captions to follow multi-turn text and camera ...
Rollback improves robot policies by using world models to rewind to past decisions, explore counterfactual actions, and ...
VibeVideoBench evaluates multimodal agents that generate videos via code, finding that top systems meet core requirements on ...
CREDIT improves language model self-attribution of external information via counterfactual training, reducing false ...
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, ...
StreamVibe introduces a benchmark, streaming vision-language model, and hierarchical memory harness to enable proactive, ...
Reinforcement learning improves reasoning accuracy without requiring a specific wait marker, which originates from training ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results