8 papers
Unifying Language-Action Understanding and Generation for Autonomous Driving
Xinyang Wang, Qian Liu, Wenjie Ding +7
Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about…
Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion
Sen Zhang, Jianguo Wei, Wenhuan Lu +6
The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in si…
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
Guangzhi Sun, Yixuan Li, Xiaodong Wu +4
Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhance…
Audio-centric Video Understanding Benchmark without Text Shortcut
Yudong Yang, Jimin Zhuang, Guangzhi Sun +7
Audio often serves as an auxiliary modality in video understanding tasks of audio-visual large language models (LLMs), merely assisting in the comprehension of visual information.…
video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models
Changli Tang, Yixuan Li, Yudong Yang +5
We present video-SALMONN 2, a family of audio-visual large language models that set new state-of-the-art (SOTA) results in video description and question answering (QA). Our core c…
Improving LLM Video Understanding with 16 Frames Per Second
Yixuan Li, Changli Tang, Jimin Zhuang +5
Human vision is dynamic and continuous. However, in video understanding with multimodal large language models (LLMs), existing methods primarily rely on static features extracted f…