Jingyang Lin

jylins

·

https://jylin.me

jylins

AI & ML interests

vision-and-language

Recent Activity

liked a dataset 6 days ago

secemp9/arxiv-complete

updated a dataset 15 days ago

jylins/videomme-v2

published a dataset 15 days ago

jylins/perceptionbench

View all activity

Organizations

upvoted a paper 27 days ago

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Paper • 2608.29335 • Published about 1 month ago • 73

upvoted 3 papers 11 months ago

Scaling Long-Horizon LLM Agent via Context-Folding

Paper • 2510.11967 • Published Oct 13, 2025 • 8

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published Oct 28, 2025 • 105

FARMER: Flow AutoRegressive Transformer over Pixels

Paper • 2510.23588 • Published Oct 27, 2025 • 59

upvoted 3 papers over 1 year ago

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

Paper • 2504.07956 • Published Apr 10, 2025 • 46

Unleashing Hour-Scale Video Training for Long Video-Language Understanding

Paper • 2506.05332 • Published Jun 5, 2025 • 3

Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion

Paper • 2501.09019 • Published Jan 15, 2025 • 12