Related papers: Task-Agnostic Pre-training and Task-Guided Fine-tu…

We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment,…

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…

Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…

Task planning for embodied AI has been one of the most challenging problems where the community does not meet a consensus in terms of formulation. In this paper, we aim to tackle this problem with a unified framework consisting of an…

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning…

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

Learning to navigate in dynamic and complex open-world environments is a critical yet challenging capability for autonomous robots. Existing approaches often rely on cascaded modular frameworks, which require extensive hyperparameter tuning…

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…

Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation. Preference optimization (PO) is a prominent and growing area of research that aims to align these…

Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs,…

Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks requiring multiple…

Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a single episode. While diffusion-based planners enable flexible trajectory generation,…

This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize…

Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc…

Recent studies demonstrate that diffusion planners benefit from sparse-step planning over single-step planning. Training models to skip steps in their trajectories helps capture long-term dependencies without additional memory or…