papers

Publications (13)

cs.CV2024

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

Ruyi Xu, Yuan Yao, Zonghao Guo +7

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions,…

cs.CV2025

Qwen3-VL Technical Report

Shuai Bai, Yuxuan Cai, Ruizhe Chen +61

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively…

cs.CV2022

On the Integration of Self-Attention and Convolution

Xuran Pan, Chunjiang Ge, Rui Lu +4

Convolution and self-attention are two powerful techniques for representation learning, and they are usually considered as two peer approaches that are distinct from each other. In…

cs.CV2024

Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment

Jiayi Guo, Junhao Zhao, Chaoqun Du +6

Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt…

cs.CV2025

OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

Yifei Li, Junbo Niu, Ziyang Miao +12

Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline…

cs.CV2025

Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation

Shukang Yin, Chaoyou Fu, Sirui Zhao +7

Recent years have seen the success of Multimodal Large Language Models (MLLMs) in the domain of vision understanding. The success of these models can largely be attributed to the d…

cs.CV2022

Domain Adaptation via Prompt Learning

Chunjiang Ge, Rui Huang, Mixue Xie +4

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approach…

cs.LG2024

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

Kai Yang, Jian Tao, Jiafei Lyu +6

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns…

cs.CV2024

Demystify Mamba in Vision: A Linear Attention Perspective

Dongchen Han, Ziyi Wang, Zhuofan Xia +7

Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision…

cs.CV2026

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Xiang An, Yin Xie, Feilong Tang +27

We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of mu…

cs.CV2025

Cross-Modal Adapter for Vision-Language Retrieval

Haojun Jiang, Jianke Zhang, Rui Huang +4

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained…

cs.CV2025

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models

Junbo Niu, Yuanhong Zheng, Ziyang Miao +8

Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, l…

cs.CV2024

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

Chunjiang Ge, Sijie Cheng, Ziming Wang +6

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadrat…