Related papers: Data Leakage and Redundancy in the LIT-PCBA Benchm…

Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…

We present a parallel algorithm and scalable implementation for genome analysis, specifically the problem of finding overlaps and alignments for data from "third generation" long read sequencers. While long sequences of DNA offer enormous…

The adoption of Large Language Models (LLMs) in scientific writing promises efficiency but risks introducing informational entropy. While "hallucinated papers" are a known artifact, the systematic degradation of valid citation chains…

The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are rigorously benchmarked, the data fueling them remains a black…

Federated learning (FL) enables workers to learn a model collaboratively by using their local data, with the help of a parameter server (PS) for global model aggregation. The high communication cost for periodic model updates and the…

In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level…

The quality of training data has a huge impact on the efficiency, accuracy and complexity of machine learning tasks. Various tools and techniques are available that assess data quality with respect to general cleaning and profiling checks.…

In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing…

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model…

While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood. Existing robustness benchmarks mainly focus on single modalities, making them…

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

The increasing complexity of algorithms for analyzing medical data, including de-identification tasks, raises the possibility that complex algorithms are learning not just the general representation of the problem, but specifics of given…

Large Language Models (LLMs) are increasingly trusted to perform automated code review and static analysis at scale, supporting tasks such as vulnerability detection, summarization, and refactoring. In this paper, we identify and exploit a…

Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. However, they are known to suffer from information leakage,…

Behavioral models are the key enablers for behavioral analysis of Software Product Lines (SPL), including testing and model checking. Active model learning comes to the rescue when family behavioral models are non-existent or outdated. A…

Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work, we…

Deep learning-based models are utilized to achieve state-of-the-art performance for recommendation systems. A key challenge for these models is to work with millions of categorical classes or tokens. The standard approach is to learn…

The Physics Lab Inventory of Critical Thinking (PLIC) measures three components of students' critical thinking in physics labs: evaluating data, evaluating methods, and proposing next steps. Prior work has analyzed these components in…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…