1 citations · 1 across the 9 of their papers we have counts for
9 papers
LookThere! Sparse Vision by Reinforced Selection
Sreehari Rammohan, Yousef Yassin, Anthony Fuller +3
Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive computation methods accelerat…
Robot Critics that Sweat the Small Stuff
Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan +3
Large vision-language models contain several priors about the world and object interactions, making them useful critics during inference to steer robot policies towards success. Ho…
: Smaller Self-Supervised ViTs Localize Better than Larger Ones
Sreehari Rammohan, Huy Ha, Carl Vondrick
Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention map…
New York Smells: A Large Multimodal Dataset for Olfaction
Ege Ozguroglu, Junbang Liang, Ruoshi Liu +6
While olfaction is central to how animals perceive the world, this rich chemical sensory modality remains largely inaccessible to machines. One key bottleneck is the lack of divers…
Video Generators are Robot Policies
Junbang Liang, Pavel Tokmakov, Ruoshi Liu +4
Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or b…
Self-Improving Autonomous Underwater Manipulation
Ruoshi Liu, Huy Ha, Mengxue Hou +2
Underwater robotic manipulation faces significant challenges due to complex fluid dynamics and unstructured environments, causing most manipulation systems to rely heavily on human…
Differentiable Robot Rendering
Ruoshi Liu, Alper Canberk, Shuran Song +1
Vision foundation models trained on massive amounts of visual data have shown unprecedented reasoning and planning skills in open-world settings. A key challenge in applying them t…
EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images
Alper Canberk, Maksym Bondarenko, Ege Ozguroglu +2
Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often f…
Controlling the World by Sleight of Hand
Sruthi Sudhakar, Ruoshi Liu, Basile Van Hoorick +2
Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action. While generativ…