Related papers: EC-Diffuser: Multi-Object Manipulation via Entity-…
Behavioral cloning (BC) provides a straightforward solution to offline RL by mimicking offline trajectories via supervised learning. Recent advances (Chen et al., 2021; Janner et al., 2021; Emmons et al., 2021) have shown that by…
Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function,…
Learning from humans is challenging because people are imperfect teachers. When everyday humans show the robot a new task they want it to perform, humans inevitably make errors (e.g., inputting noisy actions) and provide suboptimal examples…
Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…
Imitation learning empowers artificial agents to mimic behavior by learning from demonstrations. Recently, diffusion models, which have the ability to model high-dimensional and multimodal distributions, have shown impressive performance on…
There has been substantial progress in humanoid robots, with new skills continuously being taught, ranging from navigation to manipulation. While these abilities may seem impressive, the teaching methods often remain inefficient. To enhance…
A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…
With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…
As one of the basic tasks of computer vision, object detection has been widely used in many intelligent applications. However, object detection algorithms are usually heavyweight in computation, hindering their implementations on…
Learning based multi-robot path planning methods struggle to scale or generalize to changes, particularly variations in the number of robots during deployment. Most existing methods are trained on a fixed number of robots and may tolerate a…
Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid…
Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion…
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 uses a single pre-training stage to address both…
In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly,…
A key challenge with procedure planning in instructional videos lies in how to handle a large decision space consisting of a multitude of action types that belong to various tasks. To understand real-world video content, an AI agent must…
Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for…
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for…
Humans can recognize the same actions despite large context and viewpoint variations, such as differences between species (walking in spiders vs. horses), viewpoints (egocentric vs. third-person), and contexts (real life vs movies). Current…
Long-horizon contact-rich manipulation has long been a challenging problem, as it requires reasoning over both discrete contact modes and continuous object motion. We introduce Implicit Contact Diffuser (ICD), a diffusion-based model that…
Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics, yet it suffers from a fundamental limitation: in high-dimensional generative…