Related papers: TemporalFlowViz: Parameter-Aware Visual Analytics …
Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…
Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models…
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…
Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this fundamental limitation by formalizing the…
Simulation ensembles are a common tool in physics for understanding how a model outcome depends on input parameters. We analyze an active particle system, where each particle can use energy from its surroundings to propel itself. A…
Understanding and tuning the performance of extreme-scale parallel computing systems demands a streaming approach due to the computational cost of applying offline algorithms to vast amounts of performance log data. Analyzing large…
Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale…
Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric…
Many Vision-Language-Action (VLA) models are built upon an internal world model trained via next-frame prediction ``$v_t \rightarrow v_{t+1}$''. However, this paradigm attempts to predict the future frame's appearance directly, without…
Temporal graphs are commonly used to represent complex systems and track the evolution of their constituents over time. Visualizing these graphs is crucial as it allows one to quickly identify anomalies, trends, patterns, and other…
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…
Fluid prediction is a long-standing challenge due to the intrinsic high-dimensional non-linear dynamics. Previous methods usually utilize the non-linear modeling capability of deep models to directly estimate velocity fields for future…
Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we…
Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly on global image understanding, struggling to simulate…
Understanding temporal dynamics in medical imaging is crucial for applications such as disease progression modeling, treatment planning and anatomical development tracking. However, most deep learning methods either consider only single…
Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…
Significant progress has been made on the model development for simulating turbulent reacting flows. As a consequence, we are currently in a position where key-physical aspects of fairly complex combustion processes are well understood at a…
Current visualization research has identified the potential of more immersive settings for data exploration, leveraging VR and AR technologies. To explore how a traditional visualization system could be adapted into an immersive framework,…
Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…
Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. During model selection and debugging, data scientists need to…