5 papers · 1 filter
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6
Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thin…
Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysis
Weiyi Wu, Xinwen Xu, Chongyang Gao +3
Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is hindered by immense data size and…
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering
Xingjian Diao, Weiyi Wu, Keyi Kong +5
Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous…
Learning Musical Representations for Music Performance Question Answering
Xingjian Diao, Chunhui Zhang, Tingxuan Wu +4
Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals th…
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
Xingjian Diao, Chunhui Zhang, Weiyi Wu +5
Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models fa…