1 15 35

Xinlong Wang

xinlongwang

https://xloong.wang/

WXinlong

AI & ML interests

computer vision, foundation model

Recent Activity

authored a paper 10 days ago

Autoregressive Video Generation without Vector Quantization

liked a Space 10 days ago

BAAI/nova-d48w1024-osp480

upvoted a collection 10 days ago

NOVA

View all activity

Organizations

xinlongwang's activity

upvoted a collection 10 days ago

NOVA

Collection

NOVA: Autoregressive Video Generation without Vector Quantization • 6 items • Updated 9 days ago • 4

upvoted a paper 10 days ago

Autoregressive Video Generation without Vector Quantization

Paper • 2412.14169 • Published 12 days ago • 13

upvoted a paper 20 days ago

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Paper • 2412.06699 • Published 21 days ago • 11

upvoted a paper 3 months ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27 • 93

upvoted a collection 3 months ago

Emu3

Collection

Emu3: Next-Token Prediction is All You Need • 5 items • Updated 9 days ago • 66

upvoted a paper 5 months ago

Diffusion Feedback Helps CLIP See Better

Paper • 2407.20171 • Published Jul 29 • 36

upvoted 2 papers 6 months ago

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Paper • 2407.08303 • Published Jul 11 • 17

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17 • 50

upvoted a paper 11 months ago

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6 • 25

upvoted a paper 12 months ago

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Paper • 2401.09417 • Published Jan 17 • 59

upvoted 4 papers about 1 year ago

upvoted a paper over 1 year ago

Generative Pretraining in Multimodality

Paper • 2307.05222 • Published Jul 11, 2023 • 21