Related papers: Mean Mode Screaming: Mean--Variance Split Residual…
While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy…
Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel object classes in medical images using only minimal annotated examples, addressing the critical challenges of data scarcity and domain shifts prevalent in medical imaging.…
Adversarial patches are physically realizable localized noise, which are able to hijack Vision Transformers (ViT) self-attention, pulling focus toward a small, high-contrast region and corrupting the class token to force confident…
Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring…
A splitting of the fundamental optical modes in micro/nano-cavities comprising semiconductor heterostructures is commonly observed. Given that this splitting plays an important role for the light-matter interaction and hence quantum…
Diffusion models (DMs) are a powerful generative framework that have attracted significant attention in recent years. However, the high computational cost of training DMs limits their practical applications. In this paper, we start with a…
Pre-trained text-to-image (T2I) diffusion models have shown strong potential for real-world image super-resolution (Real-ISR), owing to their noise-started generation process that enables realistic texture synthesis and captures the…
Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to…
Significant progress has been witnessed in learning-based Multi-view Stereo (MVS) under supervised and unsupervised settings. To combine their respective merits in accuracy and completeness, meantime reducing the demand for expensive…
Distributed systems frequently encounter consistency violation faults (cvfs), where nodes operate on outdated or inaccurate data, adversely affecting convergence and overall system performance. This study presents a machine learning-based…
It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability…
Distributed machine learning (ML) training has become a necessity with the prevalence of billion to trillion-parameter-scale models. While prior work has improved training efficiency from the ML perspective at the application layer, it…
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI),…
MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or…
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…
Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce…
Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an…
Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video…
Diffusion models exhibit remarkable generative capability, but their high latency limits practical deployment. Many studies have attempted to reduce sampling steps to accelerate inference. Among them, MeanFlow has attracted considerable…