NYC Computer Vision Day 2026

NYC Computer Vision Day is an invite-only event that aims to be an informal day where the computer vision community from NYC and surroundings can share ideas and meet. A primary focus is visibility for graduate students and early career researchers.

Date: Monday, April 27
Time: 10AM - 6:15PM (breakfast available at 9:30AM)
Location: NYU Kimmel Center  (Map)
Organizer: David Fouhey

Attendance Information: There is a strict guest list. If you are not a confirmed guest, you will not be admitted to the event. There are no exceptions.

photo of Washington Square Park

Schedule

☕ Casual Conversations and Coffee: 9:30AM — 10:00AM

Doors will open at 9:30AM to give time to get settled in with some coffee.




Morning Session (E&L Auditorium): 10:00AM — 12:00PM
⚡ Lightning Talk Session 1
  1. Young Kyung Kim, Princeton: Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
  2. Rundong Luo, Cornell: ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
  3. Gene Chou, Cornell: CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
  4. Jordan Lin, Columbia: Vista4D: Video Reshooting with 4D Point Clouds
  5. Derong Jin, UMD: SonoWorld: From One Image to a 3D Audio-Visual Scene
  6. Hao Phung, Cornell: Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
  7. Alexandros Graikos, Stony Brook: Fast Constrained Sampling in Pre-Trained Diffusion Models
  8. Nick Huang, Brown: R3GAN2: Activation Magnitude Control Lets GANs Scale Efficiently
  9. Giancarlo Pereira, NYU: NeLU3D: Neural Inverse Structured Light without Modeling the Projector
  10. Yiming Dou, Cornell: Tactile-Augmented Radiance Fields
  11. Irene Kim, Stony Brook: Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimation
  12. Alexander Raistrick, Princeton: ProcFunc: A Framework for Compositional Procedural Generation
  13. Jeffrey Gu, Princeton: Separating Signal from Noise: A Self-Distillation Approach for Amortized Heterogeneous Cryo-EM Reconstruction




💎 Keynote 1: Aleksander Hołyński

Assistant Professor, Columbia University & Staff Research Scientist, Google DeepMind




🥪 Lunch and 🪧 Poster Session 1 (Rosenthal Pavilion): 12:00PM — 2:00PM

We'll have posters and ample time for casual conversation.

Each attending PI will be given a 24” (high) × 36” (wide) posterboard in one session. This can be used as the PI sees fit: for instance, a single larger poster or multiple smaller posters. You can find the assignments here.





Afternoon Session (E&L Auditorium): 2:00PM — 4:30PM
⚡ Lightning Talk Session 2
  1. Yixuan Wang, Columbia: Interactive World Simulator for Robot Policy Training and Evaluation
  2. Xiang Li, Stony Brook: Motion World Models for Robot Control
  3. Zilai Zeng, Brown: Self-Improving Loops for Visual Robotic Planning
  4. Junbang Liang, Columbia: Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
  5. Aileen Liao, Penn: VLM-Focus: Task-Relevant Scene Reduction for Planning and Control in Clutter
  6. Eadom Dessalene, UMD: FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
  7. Levi Burner, UMD: Embodied Visuomotor Representation
  8. Ying Wang, NYU: Temporal Straightening for Latent Planning
  9. Tianjiao Ding, Penn: Sparse Latent Concept Geometry for Steering Foundation Model




💎 Keynote 2: Paola Cascante-Bonilla

Assistant Professor, Stony Brook University





Brief Break




⚡ Lightning Talk Session 3
  1. Zekun Li, Brown: LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
  2. Hazel (Heejeong) Nam, Brown: Causal-JEPA: Learning World Models through Object-Level Latent Interventions
  3. Kaleb S. Newman, Princeton: Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
  4. Protyay Dey, Buffalo: Inference-Time Answer Correction and Topology Adaptation for SLM Multi-Agent Reasoning Systems
  5. Wenxuan Li, Johns Hopkins: The AI That Sees Cancer Coming
  6. Yuyang Ji, Drexel: From 3D Pose to Prose: Biomechanics-Grounded Vision-Language Coaching
  7. Chris Liu, NYU: Finch: Pareto Efficient EEG Foundation Model Family for Brain Computer Interface
  8. Yifan Wang, Stony Brook: From Noise to Neural Signals: Continuous Flow Matching for EEG Generation
  9. Bilal Abdulrahman, CUNY: Beyond Pedestrian Flow: Evaluating Urban Sidewalk Friction and Accessibility via Efficient State Space Models
  10. Peter Michael, Cornell: Noise-Coded Illumination


🪧 Poster Session 2 (Rosenthal Pavilion): 4:30PM — 6:15PM

We'll have posters and ample time for casual conversation.

Each attending PI will be given a 24” (high) × 36” (wide) posterboard in one session. This can be used as the PI sees fit: for instance, a single larger poster or multiple smaller posters. You can find the assignments here.


Host Information

NYC Computer Vision Day 2026 would not be possible without the generous support of the NYU Tandon School of Engineering.