Related papers: Diffusion-Based Imitation Learning for Social Pose…

The increasing labor shortage and aging population underline the need for assistive robots to support human care recipients. To enable safe and responsive assistance, robots require accurate human motion prediction in physical interaction…

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze…

Social agents both internalize collective norms and reshape them through creative action, yet computational models have not captured this bidirectional process within a unified framework. We propose a multi-agent simulation model grounded…

Realistic driving simulation requires that NPCs not only mimic natural driving behaviors but also react to the behavior of other simulated agents. Recent developments in diffusion-based scenario generation focus on creating diverse and…

A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning,…

Modeling realistic pedestrian trajectories requires accounting for both social interactions and environmental context, yet most existing approaches largely emphasize social dynamics. We propose \textbf{EnvSocial-Diff}: a diffusion-based…

Anticipating future actions is inherently uncertain. Given an observed video segment containing ongoing actions, multiple subsequent actions can plausibly follow. This uncertainty becomes even larger when predicting far into the future.…

Generating a photorealistic image with intended human pose is a promising yet challenging research topic for many applications such as smart photo editing, movie making, virtual try-on, and fashion display. In this paper, we present a novel…

Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant…

Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to…

Perception is essential for the active interaction of physical agents with the external environment. The integration of multiple sensory modalities, such as touch and vision, enhances this perceptual process, creating a more comprehensive…

Diffusion-based generative modeling has been achieving state-of-the-art results on various generation tasks. Most diffusion models, however, are limited to a single-generation modeling. Can we generalize diffusion models with the ability of…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

Recent advances in imitation learning, particularly using generative modelling techniques like diffusion, have enabled policies to capture complex multi-modal action distributions. However, these methods often require large datasets and…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…

Diffusion policies are conditional diffusion models that learn robot action distributions conditioned on the robot and environment state. They have recently shown to outperform both deterministic and alternative action distribution learning…

Deep generative models produce data according to a learned representation, e.g. diffusion models, through a process of approximation computing possible samples. Approximation can be understood as reconstruction and the large datasets used…

Generating high-quality whole-body human object interaction motion sequences is becoming increasingly important in various fields such as animation, VR/AR, and robotics. The main challenge of this task lies in determining the level of…

Conversational scenarios are very common in real-world settings, yet existing co-speech motion synthesis approaches often fall short in these contexts, where one person's audio and gestures will influence the other's responses.…

Grasping is a fundamental skill in robotics with diverse applications across medical, industrial, and domestic domains. However, current approaches for predicting valid grasps are often tailored to specific grippers, limiting their…