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

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

Object detectors often suffer a decrease in performance due to the large domain gap between the training data (source domain) and real-world data (target domain). Diffusion-based generative models have shown remarkable abilities in…

Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend…

The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but…

This paper's primary objective is to develop a robust generalist perception model capable of addressing multiple tasks under constraints of computational resources and limited training data. We leverage text-to-image diffusion models…

In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of…

The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

Learning priors on trajectory distributions can help accelerate robot motion planning optimization. Given previously successful plans, learning trajectory generative models as priors for a new planning problem is highly desirable. Prior…

Self-supervised learning (SSL), especially contrastive methods, has raised attraction recently as it learns effective transferable representations without semantic annotations. A common practice for self-supervised pre-training is to use as…

Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of…

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes…

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…

Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile…

Redundant manipulators, with their higher Degrees of Freedom (DoFs), offer enhanced kinematic performance and versatility, making them suitable for applications like manufacturing, surgical robotics, and human-robot collaboration. However,…