8 papers · 1 filter
UltraLBM-UNet: Ultralight Bidirectional Mamba-based Model for Skin Lesion Segmentation
Linxuan Fan, Juntao Jiang, Weixuan Liu +4
Skin lesion segmentation is a crucial step in dermatology for guiding clinical decision-making. However, existing methods for accurate, robust, and resource-efficient lesion analys…
OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
Haoyang He, Jie Wang, Jiangning Zhang +5
The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain…
LLM-Oriented Token-Adaptive Knowledge Distillation
Xurong Xie, Zhucun Xue, Jiafu Wu +5
Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are mi…
IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
Yinan Chen, Jiangning Zhang, Teng Hu +7
Instruction-guided video editing has emerged as a rapidly advancing research direction, offering new opportunities for intuitive content transformation while also posing significan…
Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
Xinlei Yu, Chengming Xu, Guibin Zhang +8
Multi-Agent System (MAS) powered by Visual Language Models (VLMs) enables challenging tasks but suffers from a novel failure term, multi-agent visual hallucination snowballing, whe…
UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
Zhucun Xue, Jiangning Zhang, Teng Hu +8
The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for vide…
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
Zhucun Xue, Jiangning Zhang, Xurong Xie +4
Multimodal Large Language Models (MLLMs) perform well in video understanding but degrade on long videos due to fixed-length context and weak long-term dependency modeling. Retrieva…
MARRS: Masked Autoregressive Unit-based Reaction Synthesis
Yabiao Wang, Shuo Wang, Jiangning Zhang +3
This work aims at a challenging task: human action-reaction synthesis, i.e., generating human reactions conditioned on the action sequence of another person. Currently, autoregress…