Related papers: CRAFT: Video Diffusion for Bimanual Robot Data Gen…
LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data,…
Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either provide imprecise camera control from text prompts or rely on labor-intensive manual…
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation,…
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified…
Robust generalization in robotic manipulation is crucial for robots to adapt flexibly to diverse environments. Existing methods usually improve generalization by scaling data and networks, but model tasks independently and overlook…
Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…
Navigation by scent is a capability in robotic systems that is rising in demand. However, current methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects due to limitations in olfactory…
Decentralized multi-robot motion planning requires each robot to generate collision-free trajectories from local observations, without global sensing or reliable communication. However, most existing planners, whether classical or…
Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal coherence, and motion accuracy. A key reason for these…
Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…
Learning robot manipulation from human videos is appealing due to the scale and diversity of human demonstrations, but transferring such demonstrations to executable robot behavior remains challenging. Prior work either relies on robot data…
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to…
Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, guiding diffusion models on graphs under arbitrary reward…
This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the…
Automated 3D scene generation is pivotal for applications spanning virtual reality, digital content creation, and Embodied AI. While computer graphics prioritizes aesthetic layouts, vision and robotics demand scenes that mirror real-world…
Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in…
Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…
Swarm robotic trajectory planning faces challenges in computational efficiency, scalability, and safety, particularly in complex, obstacle-dense environments. To address these issues, we propose SwarmDiff, a hierarchical and scalable…
Recent advances in offline Reinforcement Learning (RL) have proven that effective policy learning can benefit from imposing conservative constraints on pre-collected datasets. However, such static datasets often exhibit distribution bias,…
There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…