相关论文: SCOPE: Intrinsic Semantic Space Control for Mitiga…

Large Language Models (LLMs) represent valuable intellectual property (IP), reflecting significant investments in training data, compute, and expertise. Deploying these models on partially trusted or insecure devices introduces substantial…

Automatic indentation of source code is fundamentally a simple matter of parsing the code and then applying language- and style-specific rules about relative indentation of the various constructs. Yet, in practice, full parsing is not…

Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks. However, the vast potential and remarkable capabilities of LLMs also raise new security and privacy concerns if they are…

Sparse coding (SC) is attracting more and more attention due to its comprehensive theoretical studies and its excellent performance in many signal processing applications. However, most existing sparse coding algorithms are nonconvex and…

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Task-oriented semantic parsing models typically have high resource requirements: to support new ontologies (i.e., intents and slots), practitioners crowdsource thousands of samples for supervised fine-tuning. Partly, this is due to the…

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…

Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplored for 3D point clouds. Existing methods suffer from catastrophic forgetting or…

Sparse coding is a class of unsupervised methods for learning a sparse representation of the input data in the form of a linear combination of a dictionary and a sparse code. This learning framework has led to state-of-the-art results in…

We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we…

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving…

As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often fail to address the technical complexities of digital data…

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…