Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,617 papers.
5 Oct 2026
World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert.
8 Oct 2026
Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and action-conditioned dynamics before adding a control policy or solver.
16 Oct 2026
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control.
15 Oct 2026
We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plus, RoboTwin Clean2Rand and RoboCasa365, it is outperformed only by models about twice its size.
16 Sep 2026
Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labeled robot videos directly supervise control but are costly and limited in diversity, whereas egocentric human videos…