Related papers: CURE: Controlled Unlearning for Robust Embeddings …

Pretrained models like CLIP have demonstrated impressive zero-shot classification capabilities across diverse visual domains, spanning natural images, artistic renderings, and abstract representations. However, real-world applications often…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Reinforcement learning post-training has improved the reasoning ability of large language models, but often produces unnecessarily long, repetitive, or semantically opaque reasoning traces. Existing efficient reasoning methods mainly…

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

In recent years, a significant number of high-quality pretrained models have emerged, greatly impacting Natural Language Understanding (NLU), Natural Language Generation (NLG), and Text Representation tasks. Traditionally, these models are…

Deployed text-to-image diffusion models increasingly require post-hoc concept unlearning for copyright claims, artist opt-outs, safety updates, and protected-content mitigation without full retraining. A central challenge is erase-retain…

Data augmentation is a crucial component in unsupervised contrastive learning (CL). It determines how positive samples are defined and, ultimately, the quality of the learned representation. In this work, we open the door to new…

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Text-to-Image diffusion models can produce undesirable content that necessitates concept erasure. However, existing methods struggle with under-erasure, leaving residual traces of targeted concepts, or over-erasure, mistakenly eliminating…

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…

Deep Learning (DL) models to analyze source code have shown immense promise during the past few years. More recently, self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE…

Classic approaches to content moderation typically apply a rule-based heuristic approach to flag content. While rules are easily customizable and intuitive for humans to interpret, they are inherently fragile and lack the flexibility or…

Growing concerns regarding algorithmic fairness have led to a surge in methodologies to mitigate algorithmic bias. However, such methodologies largely assume that observed labels in training data are correct. This is problematic because…

In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when…

While large language models (LLMs) have shown to perform well on monolingual mathematical and commonsense reasoning, they remain unreliable for multilingual medical reasoning applications, hindering their deployment in multilingual…