Saksham Suri

Efficient Universal Perception Encoder

arXiv 2026

UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders

arXiv 2026

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

arXiv 2026

Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory

arXiv 2026

Small Vision-Language Models are Smart Compressors for Long Video Understanding

arXiv 2026

EdgeTAM: On-Device Track Anything Model

CVPR 2025 1

Efficient Track Anything

ICCV 2025

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

larp-tokenizing-videos-with-a-learned

Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization

arXiv 2023

Teaching Matters: Investigating the Role of Supervision in Vision Transformers

CVPR 2023 1

Towards Discovery and Attribution of Open-world GAN Generated Images

ICCV 2021 10

Abhinav Shrivastava

Chenchen Zhu

Raghuraman Krishnamoorthi

Vikas Chandra

Yunyang Xiong

Chong Zhou

Lemeng Wu

Wei Wen

Zechun Liu

Balakrishnan Varadarajan