Related papers: Investigation of Factorized Optical Flows as Mid-L…
Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal…
Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle…
Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices,…
Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition. In this work, a variety of optical flow…
Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate robot actions. This design allows training the planner on action-free or even non-robot data sources (e.g.,…
Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger trainable…
This paper presents a general-purpose formulation of a large class of discrete-time planning problems, with hybrid state and control-spaces, as factored transition systems. Factoring allows state transitions to be described as the…
We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant…
Generative Flow Networks (GFlowNets), a new family of probabilistic samplers, have recently emerged as a promising framework for learning stochastic policies that generate high-quality and diverse objects proportionally to their rewards.…
The field of general-purpose robotics has recently embraced powerful probabilistic diffusion-based models to learn the complex embodiment behaviours. However, existing models often come with significant trade-offs, namely high computational…
We introduce a neural network architecture and a learning algorithm to produce factorized symbolic representations. We propose to learn these concepts by observing consecutive frames, letting all the components of the hidden representation…
Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are…
Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance…
Planning in realistic environments requires searching in large planning spaces. Affordances are a powerful concept to simplify this search, because they model what actions can be successful in a given situation. However, the classical…
Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which estimate the average velocity between timesteps, mitigate this…
This paper presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments. Existing methods typically rely solely on…
This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task. It promotes the…
This paper introduces a representative-based approach for distributed learning that transforms multiple raw data points into a virtual representation. Unlike traditional distributed learning methods such as Federated Learning, which do not…
Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a…
Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data heterogeneity is one of the core challenges in federated learning, which could severely degrade the convergence rate and…