Related papers: Bidirectional Decoding: Improving Action Chunking …
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for…
Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three phases. First, a…
Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but…
Robots that can operate autonomously in a human living environment are necessary to have the ability to handle various tasks flexibly. One crucial element is coordinated bimanual movements that enable functions that are difficult to perform…
For reliable deployment of deep-learning systems, out-of-distribution (OOD) detection is indispensable. In the real world, where test-time inputs often arrive as streaming mixtures of in-distribution (ID) and OOD samples under evolving…
The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts…
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…
Imitation learning offers a promising framework for enabling robots to acquire diverse skills from human users. However, most imitation learning algorithms assume access to high-quality demonstrations an unrealistic expectation when…
Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.…
Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. When performing demonstrations, experts are not always consistent and might…
Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…
Production AI systems often operate with incomplete, conflicting, or insufficient evidence. Forced classifiers collapse such cases into action labels, while generative systems can produce outputs that are difficult to interpret as auditable…
We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on…
Exploring the bridge between historical and future motion behaviors remains a central challenge in human motion prediction. While most existing methods incorporate a reconstruction task as an auxiliary task into the decoder, thereby…
We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…
Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by…
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…
This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The…
Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial role when learning an…
Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs),…