10 papers
Dynamic Hub-and-Spoke Memory for Streaming Video Understanding
Xinru Jiang, Lin Zhao, Xi Xiao +7
Streaming video understanding requires answering questions at arbitrary times over a continuously growing visual stream. The central challenge is to compactly remember long-range h…
Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
Rahul Chowdhury, Timothy A Rupprecht, Senhao Cao +5
Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs display in-co…
Memory-Bounded Continuation of Greedy Sampling for Continual Anomaly Detection
Yoon Gyo Jung, Jaewoo Park, Kuan-Chuan Peng +2
Greedy sampling produces a compact yet representative summary of normal data, which is essential for reliable anomaly detection that relies on measuring distance from normality. Fo…
OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization
Sakib Reza, Gauri Jagatap, Mohsen Moghaddam +2
Temporal Action Localization (TAL) typically relies on segment annotations or offline access to full videos, limiting scalability and online use. We introduce Point-Supervised Onli…
Memory-Distilled Selection for Noise-Robust Anomaly Detection
Sirojbek Safarov, Jaewoo Park, Yoon Gyo Jung +4
Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfectly clean training sets is…
HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
Lin Zhao, Xinru Jiang, Xi Xiao +7
Dataset distillation often prioritizes global semantic proximity when creating small surrogate datasets for original large-scale ones. However, object semantics are inherently hier…
Grounding Multimodal Large Language Models with Quantitative Skin Attributes: A Retrieval Study
Max Torop, Masih Eskandar, Nicholas Kurtansky +6
Artificial Intelligence models have demonstrated significant success in diagnosing skin diseases, including cancer, showing the potential to assist clinicians in their analysis. Ho…
REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding
Sakib Reza, Xiyun Song, Heather Yu +3
Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Rece…
TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
Yoon Gyo Jung, Jaewoo Park, Jaeho Yoon +4
We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class dis…
HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization
Sakib Reza, Yuexi Zhang, Mohsen Moghaddam +1
Online video understanding often relies on individual frames, leading to frame-by-frame predictions. Recent advancements such as Online Temporal Action Localization (OnTAL), extend…