6 papers
CAD: Conflict-Aware Decoding to Mitigate Cross-Modal Hallucinations in Omnimodal Large Language Models
Yuchen Deng, Chang Sun, Hai-Tao Zheng +2
Omnimodal large language models (Omni-LLMs) integrate audio, video, and text, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predicti…
OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
Yuchen Deng, Zidang Cai, Hai-Tao Zheng +3
Omnimodal large language models (Omni-LLMs) show strong capability in audio-video understanding, but their practical deployment remains limited by high inference cost of long video…
AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units
Xinzi Cao, Jianyang Zhai, Pengfei Li +17
To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full pote…
Beyond Boundary Frames: Talking-Head Inbetweening via Context-Aware Motion Modeling
Yuchen Deng, Hai-Tao Zheng, Jie Wang +3
Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we study talking-head inbetweening,…
Multimodal Quantitative Language for Generative Recommendation
Jianyang Zhai, Zi-Feng Mai, Chang-Dong Wang +4
Generative recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. Most existing methods attempt to leverage prio…
Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion
Quanmin Liang, Zhilin Huang, Xiawu Zheng +4
Current Event Stream Super-Resolution (ESR) methods overlook the redundant and complementary information present in positive and negative events within the event stream, employing…