Related papers: VADF: Vision-Adaptive Diffusion Policy Framework f…

Watch-time prediction is a central regression task in short-video recommender systems, where labels are highly long-tailed and residual errors vary systematically across observed watch-time regions. In practice, a model may appear globally…

Deep neural networks (DNNs) remain challenged by distribution shifts in complex open-world domains like automated driving (AD): Robustness against yet unknown novel objects (semantic shift) or styles like lighting conditions (covariate…

Video Generation Models (VGMs) have become powerful backbones for Vision-Language-Action (VLA) models, leveraging large-scale pretraining for robust dynamics modeling. However, current methods underutilize their distribution modeling…

In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection. Based on only normal knowledge, visual anomaly detection has wide applications in…

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in maximizing rewards, they often suffer from…

Active distribution networks (ADNs) incorporating massive photovoltaic (PV) devices encounter challenges of rapid voltage fluctuations and potential violations. Due to the fluctuation and intermittency of PV generation, the state gap,…

Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical,…

While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images.…

In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Dual-arm cooperative manipulation holds great promise for tackling complex real-world tasks that demand seamless coordination and adaptive dynamics. Despite substantial progress in learning-based motion planning, most approaches struggle to…

Solving high-dimensional PDE-governed inverse problems is often challenging due to complex non-Gaussian posterior distributions, expensive forward model evaluations, and misspecified prior information. To address these issues, we propose a…

Efficient deployment of Deep Neural Networks (DNNs), such as Large Language Models (LLMs), on tensor accelerators is essential for maximizing computational efficiency in modern AI systems. However, achieving this is challenging due to the…

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…

Diffusion-based visuomotor policies excel at modeling action distributions but are inference-inefficient, since recursively denoising from noise to policy requires many steps and heavy UNet backbones, which hinders deployment on…

Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing…