Postdoc @ Stanford CS. Previously: PhD at Brown University. Interested in Neurosymbolic methods that generate / analyze visual data (especially 3D shapes).
Heading to #SIGGRAPH next month?
Come spend Sunday afternoon with us at the Lines & Minds workshop!🧠🎨
With this wonderful group of speakers, we'll explore how visual abstraction connects art, psychology, and computer graphics.
Hope to see you there!
https://t.co/dZaoDPv5Zt
Self-consistency works great for language tasks like math and coding, but what about motions?
Our new work at #CVPR2026 extends self-consistency to trajectories in motion graphics animations. Instead of "binning" text answers, we cluster motion paths using geometric transformations (rigid, similarity, affine, etc) to identify groups of consistent trajectories for more accurate path generation and verification.
Project: https://t.co/HBjtBprIzk
Come chat with me at 11:45am MDT in Exhibit Hall F to learn more!
#SelfConsistency #MotionGraphics #GenerativeAI #Animation
Really liked this paper from Brown and Adobe about turning meshes into SuperFrustum primitives. That's the right way to do 3D reconstruction in my opinion, ready for interaction, simulation or editing. #CVPR2026 https://t.co/k2arwx6GuF
@YVinker is talking at 4pm on "What Makes a Visual Idea? Decomposing and Recombining Visual Concepts with Generative Models"
Join us for our last keynote at the Visual Concepts workshop @CVPR (room 501)!
#CVPR2026
The Visual Concepts Workshop is coming soon to @CVPR 2026!
Join us on June 4 for an exciting discussion on all aspects of visual concepts: from discovery and reasoning, to controllable generation, robotics, and more!
Hope to see you in Denver! #CVPR
The Visual Concepts Workshop is coming soon to @CVPR 2026!
Join us on June 4 for an exciting discussion on all aspects of visual concepts: from discovery and reasoning, to controllable generation, robotics, and more!
Hope to see you in Denver! #CVPR
The workshop on Visual Concept is starting in 1 hour in room 501!
Niloy Mitra will be giving the first keynote: "Capturing and Anticipating 4D Dynamics" at 9:05am
Hope to see you there!
@CVPR#CVPR2026
The Visual Concepts Workshop is coming soon to @CVPR 2026!
Join us on June 4 for an exciting discussion on all aspects of visual concepts: from discovery and reasoning, to controllable generation, robotics, and more!
Hope to see you in Denver! #CVPR
How do you make AI-generated 3D shapes editable? Break them into smart building blocks. Our #CVPR2026 Oral SuperFit converts 3D shapes into compact, editable primitive assemblies with SuperFrustum, an 8-parameter primitive that spans cubes, cones & more. https://t.co/7bqiVSISM9 #3D
The Visual Concepts Workshop is coming soon to @CVPR 2026!
Join us on June 4 for an exciting discussion on all aspects of visual concepts: from discovery and reasoning, to controllable generation, robotics, and more!
Hope to see you in Denver! #CVPR
Submit to the Visual Concepts Workshop @CVPR 2026!
We welcome work on learning compact, structured representations of the visual world across domains/applications: vision, learning, robotics, and cognitive science.
Submission deadline: 4/1
See you in Denver! #CVPR2026
Excited to share the 3rd Workshop on Visual Concepts at @CVPR 2026! Call for papers is now open till April 1. We welcome submissions on the following topics. See our website for more info: https://t.co/hfHrdxiGsS
Join us in Denver!
#CVPR2026
BVC Seminar will host @ItaiLang this Friday at 12pm Eastern! Catch his talk, "Clicks and Prompts: Intuitive Interactive Segmentation and Local Editing of 3D Shapes" live on YouTube!
The submission deadline for the Workshop on Visual Concepts @CVPR is extended to April 15. #CVPR2025
As visual generative and perception modeling rapidly evolve, it's a great time to join us (and an incredible speaker lineup!) for discussions.
More info: https://t.co/maMVGRxeYK
Excited to bring back the 2nd Workshop on Visual Concepts at @CVPR 2025, this time with a call for papers!
We welcome submissions on the following topics. See our website for more info:
https://t.co/gk0NgYAcEx
Join us & a fantastic lineup of speakers in Tennessee!
I'll be presenting our work on visual program synthesis with networks that learn to edit programs at #Neurips2024 during the Thursday morning poster session (#1401).
If you're around and want to chat, please stop by or reach out!
Paper: https://t.co/YRSiPwFZaa
Code: https://t.co/h7762wbvvg
Video: https://t.co/7ahVAYfYgm
Thanks to my wonderful collaborators and looking forward to visiting Vancouver for NeurIPS next month!
(12/N)
Paper: https://t.co/YRSiPwFZaa
Code: https://t.co/h7762wbvvg
Video: https://t.co/7ahVAYfYgm
Thanks to my wonderful collaborators and looking forward to visiting Vancouver for NeurIPS next month!
(12/N)
We compare reconstruction performance between our joint paradigm and using only a one-shot network while varying time spent on inference. We find that the performance gap between these paradigms is more pronounced when more time is spent searching for programs.
(9/N)
Looking forward, we’re excited about the potential impact of this framing for other program synthesis tasks.
Moving past the ‘one-shot’ paradigm might be necessary if we want to build systems that can automatically author complex pieces of code.
(11/N)