Related papers: GUDA: Counterfactual Group-wise Training Data Attr…

Robust Unsupervised Domain Adaptation (RoUDA) aims to achieve not only clean but also robust cross-domain knowledge transfer from a labeled source domain to an unlabeled target domain. A number of works have been conducted by directly…

The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and leak sensitive source-domain specific information in the target…

To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting…

Generative art using Diffusion models has achieved remarkable performance in image generation and text-to-image tasks. However, the increasing demand for training data in generative art raises significant concerns about copyright…

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of…

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the…

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…

The problem of learning from positive and unlabeled data (A.K.A. PU learning) has been studied in a binary (i.e., positive versus negative) classification setting, where the input data consist of (1) observations from the positive class and…

Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data converge to suboptimal joint behaviours because they cannot…

Recent diffusion-based generative models achieve remarkable results by training on massive datasets, yet this practice raises concerns about memorization and copyright infringement. A proposed remedy is to train exclusively on noisy data…

Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reliably erased, while others persist despite the same…

Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLMs generate text by…

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective,…

Guided or controlled data generation with diffusion models\blfootnote{Partial preliminary results of this work appeared in International Conference on Machine Learning 2025 \citep{li2025provable}.} has become a cornerstone of modern…

Recent advances in diffusion-based generative models have shown incredible promise for zero shot image-to-image translation and editing. Most of these approaches work by combining or replacing network-specific features used in the…

Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in…

Contemporary sequential recommendation methods are becoming more complex, shifting from classification to a diffusion-guided generative paradigm. However, the quality of guidance in the form of user information is often compromised by…

Source-free domain adaptation is a crucial machine learning topic, as it contains numerous applications in the real world, particularly with respect to data privacy. Existing approaches predominantly focus on Euclidean data, such as images…

Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data,…