DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotationby Xiaobin Hu, Xu Peng, Donghao Luo, Xiaozhong Ji,…
Non-autoregressive Sequence-to-Sequence Vision-Language Modelsby Kunyu Shi, Qi Dong, Luis Goncalves, Zhuowen Tu, Stefano SoattoFirst submitted…
GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Featuresby Yunzhuo Sun, Yifang Xu,…
MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Modelby Chunyi Li, Guo Lu,…
A Self-supervised Pressure Map human keypoint Detection Approch: Optimizing Generalization and Computational Efficiency Across Datasetsby…
Anchor-based Large Language Modelsby Jianhui Pang, Fanghua Ye, Derek Fai Wong, Xin He, Wanshun Chen,…
Alirector: Alignment-Enhanced Chinese Grammatical Error Correctorby Haihui Yang, Xiaojun QuanFirst submitted to arxiv on: 7…
StableMask: Refining Causal Masking in Decoder-only Transformerby Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao,…
SpeechComposer: Unifying Multiple Speech Tasks with Prompt Compositionby Yihan Wu, Soumi Maiti, Yifan Peng, Wangyou…
BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT pretrainingby Wen Liang, Youzhi…