相关论文: DeLeaker: Dynamic Inference-Time Reweighting For S…

Expressive neural text-to-speech (TTS) systems incorporate a style encoder to learn a latent embedding as the style information. However, this embedding process may encode redundant textual information. This phenomenon is called content…

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive…

The text to medical image (T2MedI) with latent diffusion model has great potential to alleviate the scarcity of medical imaging data and explore the underlying appearance distribution of lesions in a specific patient status description.…

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers…

Robust model-editing techniques are essential for deploying large language models (LLMs) in practical applications, as they enable cost-effective ways to deal with challenges such as privacy breaches, bias mitigation and misinformation…

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while…

Diffusion models have recently been investigated as powerful generative solvers for image dehazing, owing to their remarkable capability to model the data distribution. However, the massive computational burden imposed by the retraining of…

Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with implicit sexual prompts. Unlike explicit harmful prompts,…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…

Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on…

Deep learning-based semantic communication (SemCom) has emerged as a promising paradigm for next-generation wireless networks, offering superior transmission efficiency by extracting and conveying task-relevant semantic latent…

The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…

Diffusion models excel at image restoration via probabilistic modeling of forward noise addition and reverse denoising, and their ability to handle complex noise while preserving fine details makes them well-suited for Low-Light Image…

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

As AI models grow larger, the demand for accountability and interpretability has become increasingly critical for understanding their decision-making processes. Concept Bottleneck Models (CBMs) have gained attention for enhancing…