相关论文: TARO: Temporal Adversarial Rectification Optimizat…

Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for language models is particularly challenging because token-space…

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often…

Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However,…

Diffusion models have emerged as a key pillar of foundation models in visual domains. One of their critical applications is to universally solve different downstream inverse tasks via a single diffusion prior without re-training for each…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature…

The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on…

Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those…

Fault detection is essential in complex industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. With the growing availability of condition monitoring data, data-driven…

Achieving robust generalization against unseen attacks remains a challenge in Audio Deepfake Detection (ADD), driven by the rapid evolution of generative models. To address this, we propose a framework centered on hard sample…

Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates…

Adversarial evasion attacks pose significant threats to graph learning, with lines of studies that have improved the robustness of Graph Neural Networks (GNNs). However, existing works rely on priors about clean graphs or attacking…

Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we…

Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts models to generalize to corrupted data during testing,…

Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions can lock the network into a brittle structure that is…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

Deep models are highly susceptible to adversarial attacks. Such attacks are carefully crafted imperceptible noises that can fool the network and can cause severe consequences when deployed. To encounter them, the model requires training…

The proliferation and ubiquity of temporal data across many disciplines has sparked interest for similarity, classification and clustering methods specifically designed to handle time series data. A core issue when dealing with time series…

Synthetic Aperture Radar (SAR) provides all-weather, high-resolution imaging capabilities, but its unique imaging mechanism often requires expert interpretation, limiting its widespread applicability. Translating SAR images into more easily…

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancement results in severe…