5 papers
AnyView: Synthesizing Any Novel View in Dynamic Scenes
Basile Van Hoorick, Dian Chen, Shun Iwase +7
Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world…
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
TRI LBM Team, Jose Barreiros, Andrew Beaulieu +79
Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently…
Understanding Complexity in VideoQA via Visual Program Generation
Cristobal Eyzaguirre, Igor Vasiljevic, Achal Dave +5
We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design…
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis +56
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…
Should VLMs be Pre-trained with Image Data?
Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre +8
Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capabil…