10 papers
VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection
Mengyang Zhao, Zhuolin He, Haiyang Yu +9
Few-shot visual anomaly detection is fundamentally a visual comparison task, requiring fine-grained inspection of a query against normal references. Many recent methods based on la…
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…
ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs
Xu Li, Yuxuan Liang, Yi Zheng +6
Large Vision-Language Models (LVLMs) face significant computational inefficiencies caused by the large number of visual tokens. Existing visual token pruning methods mainly focus o…
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi +18
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and unders…
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
Fan Shi, Bin Li, Xiangyang Xue
Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has b…
CoLa: Chinese Character Decomposition with Compositional Latent Components
Fan Shi, Haiyang Yu, Bin Li +1
Humans can decompose Chinese characters into compositional components and recombine them to recognize unseen characters. This reflects two cognitive principles: Compositionality, t…
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
Fan Shi, Bin Li, Xiangyang Xue
Endowing machines with abstract reasoning ability has been a long-term research topic in artificial intelligence. Raven's Progressive Matrix (RPM) is widely used to probe abstract…
Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems
Fan Shi, Bin Li, Xiangyang Xue
The abstract visual reasoning ability in human intelligence benefits discovering underlying rules in the novel environment. Raven's Progressive Matrix (RPM) is a classic test to re…
Compositional Law Parsing with Latent Random Functions
Fan Shi, Bin Li, Xiangyang Xue
Human cognition has compositionality. We understand a scene by decomposing the scene into different concepts (e.g., shape and position of an object) and learning the respective law…
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
Fan Shi, Bin Li, Xiangyang Xue
Abstract reasoning ability is fundamental to human intelligence. It enables humans to uncover relations among abstract concepts and further deduce implicit rules from the relations…