Factor-Aware Predictive Learning enables video diffusion transformers to leverage multimodal language model representations ...
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 ...
ThinkWorld improves robotic generalization by representing actions as dynamics chains and using world imagination to learn ...
CREDIT improves language model self-attribution of external information via counterfactual training, reducing false ...
VibeVideoBench evaluates multimodal agents that generate videos via code, finding that top systems meet core requirements on ...
Prox replaces calibrated thresholds with top-k channel selection and a weight-derived reader to accelerate Mixture-of-Experts ...
StreamVibe introduces a benchmark, streaming vision-language model, and hierarchical memory harness to enable proactive, ...
A world model predicts machine learning program outcomes to enable affordable test-time scaling for AI research agents, ...
Reinforcement learning improves reasoning accuracy without requiring a specific wait marker, which originates from training ...
Quant-Arena benchmarks end-to-end quantitative research by evaluating whether language models can build trading strategies on ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results