5 papers
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
Han Li, Xinyu Peng, Yaoming Wang +7
We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our fr…
Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Feilong Tang, Chengzhi Liu, Zhongxing Xu +9
Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations…
ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos
Haolin Yang, Feilong Tang, Ming Hu +8
Video diffusion models (VDMs) facilitate the generation of high-quality videos, with current research predominantly concentrated on scaling efforts during training through improvem…
PG-SAM: Prior-Guided SAM with Medical for Multi-organ Segmentation
Yiheng Zhong, Zihong Luo, Chengzhi Liu +7
Segment Anything Model (SAM) demonstrates powerful zero-shot capabilities; however, its accuracy and robustness significantly decrease when applied to medical image segmentation. E…
OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining
Ming Hu, Kun Yuan, Yaling Shen +17
Surgical practice involves complex visual interpretation, procedural skills, and advanced medical knowledge, making surgical vision-language pretraining (VLP) particularly challeng…