Raghuraman Krishnamoorthi

Efficient Universal Perception Encoder

arXiv 2026

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

arXiv 2026

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

arXiv 2026

EdgeTAM: On-Device Track Anything Model

CVPR 2025 1

Efficient Track Anything

ICCV 2025

Agent-as-a-Judge: Evaluate Agents with Agents

arXiv 2024

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

arXiv 2024

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

arXiv 2024

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

arXiv 2023

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

CVPR 2024 1

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

arXiv 2023

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

arXiv 2023

Binary and Ternary Natural Language Generation

arXiv 2023

Fast Point Cloud Generation with Straight Flows

CVPR 2023 1

Vikas Chandra

Yunyang Xiong

Zechun Liu

Chenchen Zhu

Lemeng Wu

Changsheng Zhao

Saksham Suri

Chong Zhou

Ernie Chang

Jun Chen