相关论文: TemporalFlowViz: Parameter-Aware Visual Analytics …

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems…

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve…

Data collection and analysis in the field is critical for operations in domains such as environmental science and public safety. However, field workers currently face data- and platform-oriented issues in efficient data collection and…

We study the question of how visual analysis can support the comparison of spatio-temporal ensemble data of liquid and gas flow in porous media. To this end, we focus on a case study, in which nine different research groups concurrently…

Software fuzzing is a strong testing technique that has become the de facto approach for automated software testing and software vulnerability detection in the industry. The random nature of fuzzing makes monitoring and understanding the…

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analysis, and multi-turn conversation. However, their scalability…

Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporally coherent events rather than isolated frames. Current approaches are limited to static…

This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…

Generating high-quality time series data has emerged as a critical research topic due to its broad utility in supporting downstream time series mining tasks. A major challenge lies in modeling the intrinsic stochasticity of temporal…

We consider the task of semi-supervised video object segmentation (VOS). Our approach mitigates shortcomings in previous VOS work by addressing detail preservation and temporal consistency using visual warping. In contrast to prior work…

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

Biomedical researchers face increasing challenges in navigating millions of publications in diverse domains. Traditional search engines typically return articles as ranked text lists, offering little support for global exploration or…

The paper presents a review of modern methods in the registration, processing, and analysis of dynamic processes in liquids, gases, plasmas, multiphase media, which are realized in researches and technology. The review author observes both…

Molecular Dynamics (MD) simulations are ubiquitous in cutting-edge physio-chemical research. They provide critical insights into how a physical system evolves over time given a model of interatomic interactions. Understanding a system's…

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Understanding long-context visual information remains a fundamental challenge for vision-language models, particularly in agentic tasks such as GUI control and web navigation. While web pages and GUI environments are inherently structured…

Topic models are statistical tools that allow their users to gain qualitative and quantitative insights into the contents of textual corpora without the need for close reading. They can be applied in a wide range of settings from discourse…

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…

Scalar features in time-dependent fluid flow are traditionally visualized using 3D representation, and their topology changes over time are often conveyed with abstract graphs. Using such techniques, however, the structural details of…

Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or…