Bin Xiao

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

arXiv 2026

Baichuan-Omni-1.5 Technical Report

arXiv 2025

Mobius: Text to Seamless Looping Video Generation via Latent Shift

arXiv 2025

Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration

arXiv 2025

Efficient Modulation for Vision Networks

arXiv 2024

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

CVPR 2025 1

CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training

arXiv 2024

Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge

arXiv 2024

TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance

ICCV 2023 1

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

CVPR 2024 1

Baichuan 2: Open Large-scale Language Models

arXiv 2023

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

arXiv 2023

DaViT: Dual Attention Vision Transformers

arXiv 2022

CvT: Introducing Convolutions to Vision Transformers

ICCV 2021 10

Lite-HRNet: A Lightweight High-Resolution Network

CVPR 2021 1

Dynamic Head: Unifying Object Detection Heads with Attentions

CVPR 2021 1

Florence: A New Foundation Model for Computer Vision

arXiv 2021

Deep High-Resolution Representation Learning for Human Pose Estimation

deep-high-resolution-representation-learning-1

Lu Yuan

Xiyang Dai

Lei Zhang

Mengchen Liu

Fan Yang

Haiping Wu

Haoze Sun

Jianwei Yang

Jingdong Wang

Lei Su