Senqiao Yang

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20

Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process…

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Xinjie Zhang, Peng Zhang, Shicheng Zheng +21

Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to…

Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention

Wenhu Zhang, Yiming Wu, Huanyu Wang +6

Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling…

Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learning

Bozhao Li, Shaocong Wu, Tong Shao +4

Recent advances in open-vocabulary object detection focus primarily on two aspects: scaling up datasets and leveraging contrastive learning to align language and vision modalities.…

Multimodal Dataset Distillation via Phased Teacher Models

Shengbin Guo, Hang Zhao, Senqiao Yang +5

Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, exi…

VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis

Meng Chu, Senqiao Yang, Haoxuan Che +8

Generative models can now produce photorealistic imagery, yet they still struggle with the long, multi-goal prompts that professional designers issue. To expose this gap and better…

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Senqiao Yang, Junyi Li, Xin Lai +3

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. How…

Mitigating Object Hallucinations via Sentence-Level Early Intervention

Shangpin Peng, Senqiao Yang, Li Jiang +1

Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs…

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Tianyuan Qu, Longxiang Tang, Bohao Peng +3

The rise of Large Vision-Language Models (LVLMs) has significantly advanced video understanding. However, efficiently processing long videos remains a challenge due to the ``Sampli…

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Zhisheng Zhong, Chengyao Wang, Yuqi Liu +12

As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, prev…

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Senqiao Yang, Yukang Chen, Zhuotao Tian +4

Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raisin…

Typicalness-Aware Learning for Failure Detection

Yijun Liu, Jiequan Cui, Zhuotao Tian +4

Deep neural networks (DNNs) often suffer from the overconfidence issue, where incorrect predictions are made with high confidence scores, hindering the applications in critical sys…