Related papers: Curiosity-Diffuser: Curiosity Guide Diffusion Mode…
Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound over time which can potentially lead to failure. Some…
Classifier guidance is intended to steer a diffusion process such that a given classifier reliably recognizes the generated data point as a certain class. However, most classifier guidance approaches are restricted to robust classifiers,…
Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem…
Proper quantification and propagation of uncertainties in computational simulations are of critical importance. This issue is especially challenging for CFD applications. A particular obstacle for uncertainty quantifications in CFD problems…
Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees…
Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enjoyed great success recently, a full theoretical…
We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action…
Diffusion models have emerged as powerful generative tools for modeling complex data distributions, yet their purely data-driven nature limits applicability in practical engineering and scientific problems where physical laws need to be…
Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their continuous latent dynamics make discrete constraints -- e.g., the output should be a JSON file…
Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…
World models have recently gained prominence for action-conditioned visual prediction in complex environments. However, relying on only a few recent observations causes them to lose long-term context. Consequently, within a few steps, the…
Despite the remarkable progress in generative modelling, current diffusion models lack a quantitative approach to assess image quality. To address this limitation, we propose to estimate the pixel-wise aleatoric uncertainty during the…
Recent work has framed decision-making as a sequence modeling problem using generative models such as diffusion models. Although promising, these approaches often overlook latent factors that exhibit evolving dynamics, elements that are…
Human-in-the-loop (HitL) robot deployment has gained significant attention in both academia and industry as a semi-autonomous paradigm that enables human operators to intervene and adjust robot behaviors at deployment time, improving…
Diffusion policies excel at visuomotor control but often fail catastrophically under severe out-of-distribution (OOD) disturbances, such as unexpected object displacements or visual corruptions. To address this vulnerability, we introduce…
Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Existing model-based curiosity methods look to approximate…
The spread of new ideas, behaviors or technologies has been extensively studied using epidemic models. Here we consider a model of diffusion where the individuals' behavior is the result of a strategic choice. We study a simple coordination…
Diffusion models have become popular for policy learning in robotics due to their ability to capture high-dimensional and multimodal distributions. However, diffusion policies are stochastic and typically trained offline, limiting their…
Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed. We trace this consistency to a simple linear effect: the shared Gaussian statistics across…
Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in robotics research, where they are used for generating robot…