Yin Li

Rethinking Chain-of-Thought Reasoning for Videos

arXiv 2025

LETS Forecast: Learning Embedology for Time Series Forecasting

arXiv 2025

Learning to Inference Adaptively for Multimodal Large Language Models

ICCV 2025

PAVE: Patching and Adapting Video Large Language Models

CVPR 2025 1

SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation

arXiv 2025

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

ICCV 2025

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

arXiv 2024

Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations

CVPR 2023 1

Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers

ICCV 2023 1

Cosmology with one galaxy?

arXiv 2022

RegionCLIP: Region-based Language-Image Pretraining

CVPR 2022 1

Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention

arXiv 2021

The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations

arXiv 2020

ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles

arXiv 2020

Yiwu Zhong

Daniel Anglés-Alcázar

David N. Spergel

Francisco Villaescusa-Navarro

Khoi Duc Nguyen

LiWei Wang

Saurabh Bagchi

Shy Genel

Somali Chaterji

Valentina La Torre