6 papers · 1 filter
Counterfactual Attention Policy Distillation for Temporal Video Grounding
Shaobo Ju, Haiyang Yu, Xuecheng Wu +6
Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, which is however often limited by…
ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers
Ruiliang Zhou, Xuecheng Wu, Kang He +6
While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing s…
HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs
Zijian Zhang, Xuecheng Wu, Danlei Huang +3
Driven by the rapid progress in vision-language models (VLMs), the responsible behavior of large-scale multimodal models has become a prominent research area, particularly focusing…
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han, Haotian Fan, Fangyuan Kong +112
This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoratio…
ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations
Xuecheng Wu, Jiaxing Liu, Danlei Huang +8
Visual-Interleaved Chain-of-Thought (VI-CoT) enables Multi-modal Large Language Models (MLLMs) to continually update their understanding and decision space based on step-wise inter…
TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
Zijian Zhang, Xuhui Zheng, Xuecheng Wu +2
While text-to-image (T2I) generation models have achieved remarkable progress in recent years, existing evaluation methodologies for vision-language alignment still struggle with t…