Related papers: Autoregressive Meta-Actions for Unified Controllab…

This paper addresses navigation in crowded environments by integrating goal-conditioned generative models with Sampling-based Model Predictive Control (SMPC). We introduce goal-conditioned autoregressive models to generate crowd behaviors,…

Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass marginal prediction. However, many applications…

Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously…

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely…

Recent progress in controllable image generation and editing is largely driven by diffusion-based methods. Although diffusion models perform exceptionally well in specific tasks with tailored designs, establishing a unified model is still…

Text-to-motion generation has attracted increasing attention in the research community recently, with potential applications in animation, virtual reality, robotics, and human-computer interaction. Diffusion and autoregressive models are…

Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses…

Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically translate into control: models may infer objects, relations, or knowledge cues but fail to…

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…

Generative modeling offers a promising solution to data scarcity and privacy challenges in time series analysis. However, the structural complexity of time series, characterized by multi-scale temporal patterns and heterogeneous components,…

Planning with generative models has emerged as an effective decision-making paradigm across a wide range of domains, including reinforcement learning and autonomous navigation. While continuous replanning at each timestep might seem…

Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often…

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured…

Trajectory generation and prediction are two interwoven tasks that play important roles in planner evaluation and decision making for intelligent vehicles. Most existing methods focus on one of the two and are optimized to directly output…

Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction…

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…

Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a…

We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refreshable vision-language prefixes. In contrast to existing Vision-Language-Action (VLA) models and…

Character animation in real-world scenarios necessitates a variety of constraints, such as trajectories, key-frames, interactions, etc. Existing methodologies typically treat single or a finite set of these constraint(s) as separate control…

Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrained trajectory prediction focus on structured constraints by…