Wei Lin's picture

10 7 5

Wei Lin

wlin21at

·

https://wlin-at.github.io/

wlin-at

AI & ML interests

None yet

Recent Activity

upvoted a paper 7 days ago

PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies

commented on a paper 7 days ago

PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies

upvoted a paper 18 days ago

TTRV: Test-Time Reinforcement Learning for Vision Language Models

View all activity

Organizations

authored 2 papers about 1 year ago

GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models

Paper • 2410.06154 • Published Oct 8, 2024 • 16

LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content

Paper • 2410.10783 • Published Oct 14, 2024 • 27

authored 2 papers about 2 years ago

MATE: Masked Autoencoders are Online 3D Test-Time Learners

Paper • 2211.11432 • Published Nov 21, 2022

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge

Paper • 2303.08914 • Published Mar 15, 2023