Related papers: ContextFlow: Context-Aware Flow Matching For Traje…

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…

Human trajectory forecasting is important for intelligent multimedia systems operating in visually complex environments, such as autonomous driving and crowd surveillance. Although Conditional Flow Matching (CFM) has shown strong ability in…

Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer…

Estimating the causal structure of observational data is a challenging combinatorial search problem that scales super-exponentially with graph size. Existing methods use continuous relaxations to make this problem computationally tractable…

Urban spatio-temporal flow prediction, encompassing traffic flows and crowd flows, is crucial for optimizing city infrastructure and managing traffic and emergency responses. Traditional approaches have relied on separate models tailored to…

Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still follow a static generative paradigm that directly maps historical observations to future…

Predicting future states of dynamic agents is a fundamental task in autonomous driving. An expressive representation for this purpose is Occupancy Flow Fields, which provide a scalable and unified format for modeling motion, spatial extent,…

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

Knowledge graph completion demands effective modeling of multifaceted semantic relationships between entities. Yet, prevailing methods, which rely on static scoring functions over learned embeddings, struggling to simultaneously capture…

Flow matching has recently emerged as a powerful alternative to diffusion models, providing a continuous-time formulation for generative modeling and representation learning. Yet, we show that this framework suffers from a fundamental…

Predicting the future occupancy states of the surrounding environment is a vital task for autonomous driving. However, current best-performing single-modality methods or multi-modality fusion perception methods are only able to predict…

Trajectory prediction and generation are crucial for autonomous robots in dynamic environments. While prior research has typically focused on either prediction or generation, our approach unifies these tasks to provide a versatile framework…

Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture…

During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and…

Whole-slide images (WSIs) present a fundamental challenge for computational pathology due to their extreme resolution, multi-scale heterogeneity, and the requirement for clinically reliable interpretation. Although recent pathology…

Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications. In recent years deep learning (DL) has been used to construct data-driven fluid-dynamic…

Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the…

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which…

We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…

Trajectory prediction has always been a challenging problem for autonomous driving, since it needs to infer the latent intention from the behaviors and interactions from traffic participants. This problem is intrinsically hard, because each…