Related papers: Attribution-Guided Masking for Robust Cross-Domain…

We present an explainable, bias-aware generative framework that unifies cross-modal attention fusion, Grad-CAM++ attribution, and a Reveal-to-Revise feedback loop within a single training paradigm. The architecture couples a conditional…

Unsupervised domain adaption has been widely adopted in tasks with scarce annotated data. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the…

Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be leveraged as a critic and enable generators to distill…

AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization…

Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model…

Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style invariance is usually underappreciated and put on the shelf. In…

The performance of speech emotion recognition is affected by the differences in data distributions between train (source domain) and test (target domain) sets used to build and evaluate the models. This is a common problem, as multiple…

Despite the frequent use of agent-based models (ABMs) for studying social phenomena, parameter estimation remains a challenge, often relying on costly simulation-based heuristics. This work uses variational inference to estimate the…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

Deep neural networks have achieved strong performance in genomic sequence classification; however, relating their predictions to biologically meaningful sequence patterns remains challenging. In this work, we present AttnGen, an…

Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important…

Cross-domain sentiment classification has been a hot spot these years, which aims to learn a reliable classifier using labeled data from a source domain and evaluate it on a target domain. In this vein, most approaches utilized domain…

Feature attribution methods (FAs), such as gradients and attention, are widely employed approaches to derive the importance of all input features to the model predictions. Existing work in natural language processing has mostly focused on…

Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy…

With the widespread adoption of pre-trained Large Language Models (LLM), there exists a high demand for task-specific test sets to benchmark their performance in domains such as healthcare and biomedicine. However, the cost of labeling test…

Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-invariant representations. However, prior approaches often…

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive models for generative modeling of discrete data. However, existing work in this area has been hindered by unnecessarily complex model formulations and…

In recent years, machine learning has achieved impressive results across different application areas. However, machine learning algorithms do not necessarily perform well on a new domain with a different distribution than its training set.…

Generative recommendation (GR) with semantic IDs (SIDs) has emerged as a promising alternative to traditional recommendation approaches due to its performance gains, capitalization on semantic information provided through language model…