Autoregressive (AR) video diffusion models generate streaming video of arbitrary length by conditioning each new chunk of frames on those already generated. However, they suffer from exposure bias, where a model trained on clean context must continue from its own imperfect outputs, and errors compound until quality col...
Wen-Qing Wang, Joonghyuk Shin, Jonathan Tremblay et al.· 0 citations
General-purpose robot manipulation policies learn short-horizon skills effectively, but degrade rapidly on long-horizon tasks. Existing benchmarks cannot isolate failures because task horizon is either too short or entangled with scene and object variations. We propose LADDER, a long-horizon robot manipulation benchmar...
Petko Petkov, Giuliano Albanese, Nikolay Nikolov et al.· 1 citation
Vision-language models (VLMs) have shown promising spatial reasoning capabilities from static visual inputs, where the evidence needed to answer a question is available in the provided views. However, in cluttered environments, answer-relevant evidence may be occluded rather than absent: an object may lie beneath a pil...
This work develops PROBE, a framework for benchmarking and finetuning VLM agents on cluttered tabletop scenes, and designs PROBE-Agent, a finetuning recipe to distill successful trajectories from a powerful teacher foundation model to a smaller open-weight model using a mixed data recipe that encourages manipulation-ef...
Vineet Bhat, Si-Yi Chen, Alex Zook et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
