Related papers: TIGFlow-GRPO: Trajectory Forecasting via Interacti…
Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward…
Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing methods relying on rigid spatial masks or localized attention often struggle with the…
We present TraceFlow, a novel framework for high-fidelity rendering of dynamic specular scenes by addressing two key challenges: precise reflection direction estimation and physically accurate reflection modeling. To achieve this, we…
Multi-agent interacting systems are prevalent in the world, from pure physical systems to complicated social dynamic systems. In many applications, effective understanding of the situation and accurate trajectory prediction of interactive…
Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches…
Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps…
Flow-based frame interpolation methods ensure motion stability through estimated intermediate flow but often introduce severe artifacts in complex motion regions. Recent generative approaches, boosted by large-scale pre-trained video…
While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this…
Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…
This paper proposes a graph-based approach to representing spatio-temporal trajectory data that allows an effective visualization and characterization of city-wide traffic dynamics. With the advance of sensor, mobile, and Internet of Things…
Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting…
Effective trajectory generation is essential for reliable on-board spacecraft autonomy. Among other approaches, learning-based warm-starting represents an appealing paradigm for solving the trajectory generation problem, effectively…
A representation gap exists between grasp synthesis for rigid and soft grippers. Anygrasp [1] and many other grasp synthesis methods are designed for rigid parallel grippers, and adapting them to soft grippers often fails to capture their…
Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement…
Flow matching is a scalable generative framework for characterizing continuous normalizing flows with wide-range applications. However, current state-of-the-art methods are not well-suited for modeling dynamical systems, as they construct…
Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…
Motivated by the problem of pursuit-evasion, we present a motion planning framework that combines energy-based diffusion models with artificial potential fields for robust real time trajectory generation in complex environments. Our…
Predicting the future behavior of human road users is an important aspect for the development of risk-aware autonomous vehicles. While many models have been developed towards this end, effectively capturing and predicting the variability…
Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently…
The importance of mobile phone GPS trajectory data is widely recognized across many fields, yet the use of real data is often hindered by privacy concerns, limited accessibility, and high acquisition costs. As a result, generating…