7 papers
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
Dingyu Yao, Junhao Zhou, Chenxu Yang +12
Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor, an expression flickers across a video call, or a product a viewer wants flashes b…
AdaCodec: A Predictive Visual Code for Video MLLMs
Haowen Hou, Zhen Huang, Zheming Liang +8
Video is temporally redundant: adjacent frames usually share most objects, background, and layout. Yet existing video multimodal large language models (video MLLMs) usually encode…
SEMAG: Self-Evolutionary Multi-Agent Code Generation
Yulin Peng, Haowen Hou, Xinxin Zhu +2
Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, whic…
SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding
Nianbo Zeng, Haowen Hou, Fei Richard Yu +2
Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast sca…
RWKV-UI: UI Understanding with Enhanced Perception and Reasoning
Jiaxi Yang, Haowen Hou
Existing Visual Language Modelsoften struggle with information loss and limited reasoning abilities when handling high-resolution web interfaces that combine complex visual, textua…
VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
Haowen Hou, Peigen Zeng, Fei Ma +1
Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurr…