5 papers
Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
Bowen Wen, Shaurya Dewan, Stan Birchfield
Stereo foundation models achieve strong zero-shot generalization but remain computationally prohibitive for real-time applications. Efficient stereo architectures, on the other han…
Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
Andrew F. Luo, Jacob Yeung, Rushikesh Zawar +4
We introduce BrainSAIL, a method for linking neural selectivity with spatially distributed semantic visual concepts in natural scenes. BrainSAIL leverages recent advances in large-…
StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic Images
Rushikesh Zawar, Shaurya Dewan, Andrew F. Luo +3
Understanding the semantics of visual scenes is a fundamental challenge in Computer Vision. A key aspect of this challenge is that objects sharing similar semantic meanings or func…
DiffusionPID: Interpreting Diffusion via Partial Information Decomposition
Rushikesh Zawar, Shaurya Dewan, Prakanshul Saxena +3
Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex vis…
Curiosity & Entropy Driven Unsupervised RL in Multiple Environments
Shaurya Dewan, Anisha Jain, Zoe LaLena +1
The authors of 'Unsupervised Reinforcement Learning in Multiple environments' propose a method, alpha-MEPOL, to tackle unsupervised RL across multiple environments. They pre-train…