Lemeng Wu

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

arXiv 2026

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

arXiv 2026

EdgeTAM: On-Device Track Anything Model

CVPR 2025 1

Steepest Descent Density Control for Compact 3D Gaussian Splatting

CVPR 2025 1

Efficient Track Anything

ICCV 2025

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

arXiv 2024

Longhorn: State Space Models are Amortized Online Learners

arXiv 2024

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

CVPR 2024 1

Fast Point Cloud Generation with Straight Flows

CVPR 2023 1

Raghuraman Krishnamoorthi

Vikas Chandra

Yunyang Xiong

Chenchen Zhu

Chong Zhou

Saksham Suri

Zechun Liu

Balakrishnan Varadarajan

Bilge Soran

Dilin Wang