6 papers
PRISM: Polynomial Representations for Interaction-Structured Motor Control
Seung Hyun Lee, Stella X. Yu
Robot policies are typically MLPs mapping observations to actions. Yet robot observations are physical variables, and many action-relevant cues arise not from individual variables…
Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
Byeongju Woo, Zilin Wang, Byeonghyun Pak +2
Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidenc…
SHED Light on Segmentation for Dense Prediction
Seung Hyun Lee, Sangwoo Mo, Stella X. Yu
Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes exhibit strong structure, existing methods…
Normalize Filters! Classical Wisdom for Deep Vision
Gustavo Perez, Stella X. Yu
Classical image filters, such as those for averaging or differencing, are carefully normalized to ensure consistency, interpretability, and to avoid artifacts like intensity shifts…
Next-Embedding Prediction Makes Strong Vision Learners
Sihan Xu, Ziqiao Ma, Wenhao Chai +5
Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training mode…
Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
Yan Xu, Yixing Wang, Stella X. Yu
Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, no…