中文
相关论文

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

200 篇论文

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

计算与语言 · 计算机科学 2024-06-26 Zihan Liao , Hang Yu , Jianguo Li , Jun Wang , Wei Zhang

Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Gen Li , Yang Xiao , Jie Ji , Kaiyuan Deng , Bo Hui , Linke Guo , Xiaolong Ma

Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse…

计算与语言 · 计算机科学 2026-03-18 Xiaobing Sun , Perry Lam , Shaohua Li , Zizhou Wang , Rick Siow Mong Goh , Yong Liu , Liangli Zhen

Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…

计算机视觉与模式识别 · 计算机科学 2025-05-01 Xingxi Yin , Zhi Li , Jingfeng Zhang , Chenglin Li , Yin Zhang

While recent text-to-image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, their performance significantly degrades when confronted with long, detail-intensive prompts required in professional…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Qirui Jiao , Daoyuan Chen , Yilun Huang , Xika Lin , Ying Shen , Yaliang Li

With the rapid advancement of Multi-modal Large Language Models (MLLMs), MLLM-based Image Quality Assessment (IQA) methods have shown promising performance in linguistic quality description. However, current methods still fall short in…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Zhiyuan You , Xin Cai , Jinjin Gu , Tianfan Xue , Chao Dong

Modern text-to-image (T2I) models amplify harmful societal biases, challenging their ethical deployment. We introduce an inference-time method that reliably mitigates social bias while keeping prompt semantics and visual context…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Venkatesh Thirugnana Sambandham , Torsten Schön

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a…

机器学习 · 计算机科学 2025-07-31 Mohammad Abdul Hafeez Khan , Yash Jain , Siddhartha Bhattacharyya , Vibhav Vineet

Investigative journalism in recent years is confronted with two major challenges: 1) vast amounts of unstructured data originating from large text collections such as leaks or answers to Freedom of Information requests, and 2) multi-lingual…

计算与语言 · 计算机科学 2018-07-17 Gregor Wiedemann , Seid Muhie Yimam , Chris Biemann

Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable…

计算机视觉与模式识别 · 计算机科学 2024-04-12 Yanbing Zhang , Mengping Yang , Qin Zhou , Zhe Wang

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

计算与语言 · 计算机科学 2026-03-09 Schrasing Tong , Eliott Zemour , Jessica Lu , Rawisara Lohanimit , Lalana Kagal

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

计算与语言 · 计算机科学 2025-12-09 Sebastian Sztwiertnia , Felix Friedrich , Kristian Kersting , Patrick Schramowski , Björn Deiseroth

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing and reasoning over diverse modalities, but their advanced abilities also raise significant privacy concerns, particularly regarding Personally…

密码学与安全 · 计算机科学 2025-10-01 Boyang Zhang , Istemi Ekin Akkus , Ruichuan Chen , Alice Dethise , Klaus Satzke , Ivica Rimac , Yang Zhang

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Yang Zhang , Teoh Tze Tzun , Lim Wei Hern , Tiviatis Sim , Kenji Kawaguchi

Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tuning using low-rank adaptations (LoRA), which enables efficient…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Geonhui Jang , Jin-Hwa Kim , Yong-Hyun Park , Junho Kim , Gayoung Lee , Yonghyun Jeong

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

计算与语言 · 计算机科学 2025-03-12 Gleb Kuzmin , Neemesh Yadav , Ivan Smirnov , Timothy Baldwin , Artem Shelmanov

Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Chuanming Tang , Kai Wang , Joost van de Weijer

Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Wenhao Luo , Zhangyi Shen , Ye Yao , Feng Ding , Guopu Zhu , Weizhi Meng

Recent advancements in diffusion models have introduced fast sampling methods that can effectively produce high-quality images in just one or a few denoising steps. Interestingly, when these are distilled from existing diffusion models,…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Rinon Gal , Or Lichter , Elad Richardson , Or Patashnik , Amit H. Bermano , Gal Chechik , Daniel Cohen-Or

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become…

计算机视觉与模式识别 · 计算机科学 2024-11-15 Chutian Meng , Fan Ma , Jiaxu Miao , Chi Zhang , Yi Yang , Yueting Zhuang
‹ 上一页 1 8 9 10 下一页 ›