English
Related papers

Related papers: Gradient Inversion Transcript: Leveraging Robust G…

200 papers

Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose…

Machine Learning · Computer Science 2026-01-12 Saad Mokssit , Ouassim Karrakchou , Alejandro Mousist , Mounir Ghogho

In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Yuan Zhang , Jiacheng Jiang , Guoqing Ma , Zhiying Lu , Haoyang Huang , Jianlong Yuan , Nan Duan , Daxin Jiang

Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024)…

Artificial Intelligence · Computer Science 2024-10-23 Zhiwei Deng , Tao Li , Yang Li

Federated learning (FL) allows multiple entities to train a shared model collaboratively. Its core, privacy-preserving principle is that participants only exchange model updates, such as gradients, and never their raw, sensitive data. This…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Md Fazle Rasul , Alanood Alqobaisi , Bruhadeshwar Bezawada , Indrakshi Ray

Deep learning models have achieved state-of-the-art performances in various domains, while they are vulnerable to the inputs with well-crafted but small perturbations, which are named after adversarial examples (AEs). Among many strategies…

Computer Vision and Pattern Recognition · Computer Science 2023-10-11 Huihui Gong

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Jiafeng Wang , Zhaoyu Chen , Kaixun Jiang , Dingkang Yang , Lingyi Hong , Pinxue Guo , Haijing Guo , Wenqiang Zhang

Training generative adversarial networks (GAN) in a distributed fashion is a promising technology since it is contributed to training GAN on a massive of data efficiently in real-world applications. However, GAN is known to be difficult to…

Machine Learning · Computer Science 2020-10-27 Xiaojun Chen , Shu Yang , Li Shen , Xuanrong Pang

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style…

Recently, parallel text generation has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its generation quality, they still need the help of an…

Computation and Language · Computer Science 2022-04-06 Yu Bao , Hao Zhou , Shujian Huang , Dongqi Wang , Lihua Qian , Xinyu Dai , Jiajun Chen , Lei Li

Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to gradient inversion attacks (GIAs), which allow adversaries to reconstruct private training data…

Computation and Language · Computer Science 2026-02-19 Xinguo Feng , Zhongkui Ma , Zihan Wang , Alsharif Abuadbba , Guangdong Bai

In recent years, distributed optimization is proven to be an effective approach to accelerate training of large scale machine learning models such as deep neural networks. With the increasing computation power of GPUs, the bottleneck of…

Machine Learning · Computer Science 2021-09-14 Xiangyi Chen , Xiaoyun Li , Ping Li

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Machine Learning · Computer Science 2026-02-26 Ningyuan Yang , Weihua Du , Weiwei Sun , Sean Welleck , Yiming Yang

Building subsurface velocity models is essential to our goals in utilizing seismic data for Earth discovery and exploration, as well as monitoring. With the dawn of machine learning, these velocity models (or, more precisely, their…

Geophysics · Physics 2024-08-20 Randy Harsuko , Shijun Cheng , Tariq Alkhalifah

Federated learning frameworks have been regarded as a promising approach to break the dilemma between demands on privacy and the promise of learning from large collections of distributed data. Many such frameworks only ask collaborators to…

Machine Learning · Computer Science 2021-03-17 Junyi Zhu , Matthew Blaschko

Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm…

Cryptography and Security · Computer Science 2024-10-08 Junjie Chu , Zeyang Sha , Michael Backes , Yang Zhang

Federated Learning (FL) is designed to prevent data leakage through collaborative model training without centralized data storage. However, it remains vulnerable to gradient reconstruction attacks that recover original training data from…

Machine Learning · Computer Science 2024-11-07 Yuxiao Chen , Gamze Gürsoy , Qi Lei

One of the key advantages of Federated Learning (FL) is its ability to collaboratively train a Machine Learning (ML) model while keeping clients' data on-site. However, this can create a false sense of security. Despite not sharing private…

Cryptography and Security · Computer Science 2026-05-26 Vincenzo Carletti , Pasquale Foggia , Carlo Mazzocca , Giuseppe Parrella , Mario Vento

This article introduces GIT-Net, a deep neural network architecture for approximating Partial Differential Equation (PDE) operators, inspired by integral transform operators. GIT-NET harnesses the fact that differential operators commonly…

Machine Learning · Statistics 2023-12-06 Chao Wang , Alexandre Hoang Thiery

Gaining a deeper understanding of the thickness and variability of internal ice layers in Radar imagery is essential in monitoring the snow accumulation, better evaluating ice dynamics processes, and minimizing uncertainties in climate…

Machine Learning · Computer Science 2025-07-11 Zesheng Liu , Maryam Rahnemoonfar