English
Related papers

Related papers: Improved Training Technique for Shortcut Models

200 papers

Standard gradient descent methods yield point estimates with no measure of confidence. This limitation is acute in overparameterized and low-data regimes, where models have many parameters relative to available data and can easily overfit.…

Machine Learning · Computer Science 2025-08-22 Carlos Stein Brito

Learning harmful shortcuts such as spurious correlations and biases prevents deep neural networks from learning the meaningful and useful representations, thus jeopardizing the generalizability and interpretability of the learned…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Chong Ma , Lin Zhao , Yuzhong Chen , Lu Zhang , Zhenxiang Xiao , Haixing Dai , David Liu , Zihao Wu , Zhengliang Liu , Sheng Wang , Jiaxing Gao , Changhe Li , Xi Jiang , Tuo Zhang , Qian Wang , Dinggang Shen , Dajiang Zhu , Tianming Liu

We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…

The rapid advancement of generative models has made real and synthetic images increasingly indistinguishable. Although extensive efforts have been devoted to detecting AI-generated images, out-of-distribution generalization remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Ziqiang Li , Jiazhen Yan , Fan Wang , Kai Zeng , Zhangjie Fu

Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior belief, we show that generative models alone are not…

Machine Learning · Computer Science 2022-11-29 Wanqian Yang , Polina Kirichenko , Micah Goldblum , Andrew Gordon Wilson

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Yasong Dai , Zeeshan Hayder , David Ahmedt-Aristizabal , Hongdong Li

Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Tiankai Hang , Shuyang Gu , Chen Li , Jianmin Bao , Dong Chen , Han Hu , Xin Geng , Baining Guo

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…

We consider scenarios where a very accurate (often small) predictive model using restricted features is available when training a full-featured (often larger) model. This restricted model may be thought of as side-information'', and can…

Machine Learning · Computer Science 2025-04-10 Usama Muneeb , Mesrob I. Ohannessian

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

Machine Learning · Computer Science 2025-10-27 Myunsoo Kim , Donghyeon Ki , Seong-Woong Shim , Byung-Jun Lee

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Machine Learning · Computer Science 2025-05-13 Xiaotian Lin , Yanlin Qi , Yizhang Zhu , Themis Palpanas , Chengliang Chai , Nan Tang , Yuyu Luo

Continuous-time Consistency Models (CMs) promise efficient few-step generation but face significant challenges with training instability. We argue this instability stems from a fundamental conflict: Training the network exclusively on a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Yansong Peng , Kai Zhu , Yu Liu , Pingyu Wu , Hebei Li , Xiaoyan Sun , Feng Wu

Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the performance of modern vision models, undermining both their…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Rajeev Ranjan Dwivedi , Ankur Kumar , Vinod K Kurmi

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Zhaowen Li , Yousong Zhu , Zhiyang Chen , Wei Li , Chaoyang Zhao , Rui Zhao , Ming Tang , Jinqiao Wang

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Liang Chen , Shuai Bai , Wenhao Chai , Weichu Xie , Haozhe Zhao , Leon Vinci , Junyang Lin , Baobao Chang

Flow map models such as Consistency Models (CM) and Mean Flow (MF) enable few-step generation by learning the long jump of the ODE solution of diffusion models, yet training remains unstable, sensitive to hyperparameters, and costly.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Zheyuan Hu , Chieh-Hsin Lai , Yuki Mitsufuji , Stefano Ermon

Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reliably as design complexity increases. Existing fine-tuning…

Machine Learning · Computer Science 2026-03-31 Giorgio Giannone , Anna Clare Doris , Amin Heyrani Nobari , Kai Xu , Akash Srivastava , Faez Ahmed

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Wei Chow , Juncheng Li , Qifan Yu , Kaihang Pan , Hao Fei , Zhiqi Ge , Shuai Yang , Siliang Tang , Hanwang Zhang , Qianru Sun

As deep learning models continue to scale, the growing computational demands have amplified the need for effective coreset selection techniques. Coreset selection aims to accelerate training by identifying small, representative subsets of…

Machine Learning · Computer Science 2025-11-24 Wei-Kai Chang , Rajiv Khanna

Multimodal learning integrates diverse modalities but suffers from modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing methods predominantly rely on static modulation or…

Machine Learning · Computer Science 2026-02-11 Zhaocheng Liu , Zhiwen Yu , Xiaoqing Liu