Xiangtai Li's picture

Xiangtai Li

LXT

·

https://lxtgh.github.io/

AI & ML interests

Computer Vision, Multi-Modal Understanding, Generative AI

Recent Activity

updated a model 4 days ago

ByteDance/Sa2VA-4B

new activity 4 days ago

ByteDance/Sa2VA-4B:Update README.md

new activity 4 days ago

ByteDance/Sa2VA-4B:Dependency conflicts

View all activity

Organizations

LXT's activity

upvoted a paper 10 days ago

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published 11 days ago • 40

upvoted 4 papers about 1 month ago

Multimodal Latent Language Modeling with Next-Token Diffusion

Paper • 2412.08635 • Published Dec 11, 2024 • 44

EMOv2: Pushing 5M Vision Model Frontier

Paper • 2412.06674 • Published Dec 9, 2024 • 13

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Paper • 2412.07589 • Published Dec 10, 2024 • 45

HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing

Paper • 2412.04280 • Published Dec 5, 2024 • 13

upvoted 3 papers 3 months ago

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Paper • 2410.13848 • Published Oct 17, 2024 • 32

Movie Gen: A Cast of Media Foundation Models

Paper • 2410.13720 • Published Oct 17, 2024 • 91

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10, 2024 • 50

upvoted a paper 6 months ago

Video Diffusion Alignment via Reward Gradients

Paper • 2407.08737 • Published Jul 11, 2024 • 48

upvoted 5 papers 7 months ago

Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language

Paper • 2406.20085 • Published Jun 28, 2024 • 11

Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Paper • 2406.19369 • Published Jun 27, 2024 • 2

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27, 2024 • 53

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning

Paper • 2406.17770 • Published Jun 25, 2024 • 19

MotionBooth: Motion-Aware Customized Text-to-Video Generation

Paper • 2406.17758 • Published Jun 25, 2024 • 19

upvoted a paper 9 months ago

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

Paper • 2401.10226 • Published Jan 18, 2024 • 1

upvoted a paper over 1 year ago

MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation

Paper • 2309.13042 • Published Sep 22, 2023 • 9