Related papers: Inferring Invariants with Quantifier Alternations:…
The safety alignment of Language Models (LMs) is a critical concern, yet their integrity can be challenged by direct parameter manipulation attacks, such as those potentially induced by fault injection. As LMs are increasingly deployed…
Despite the crucial need for formal safety and security verification of programs, discovering loop invariants remains a significant challenge. Static analysis is a primary technique for inferring loop invariants but often relies on…
We present a novel view of nonlinear manifold learning using derivative-free optimization techniques. Specifically, we propose an extension of the classical multi-dimensional scaling (MDS) method, where instead of performing gradient…
Zoned neutral atom architectures are emerging as a promising platform for large-scale quantum computing. Their growing scale, however, creates a critical need for efficient and automated compilation solutions. Yet, existing methods fail to…
Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for…
Passage retrieval is a fundamental task in many information systems, such as web search and question answering, where both efficiency and effectiveness are critical concerns. In recent years, neural retrievers based on pre-trained language…
Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output length. In this work, we investigate a distinct attack…
The rapidly growing ecosystem of Large Language Models (LLMs) makes it increasingly challenging to manage and utilize the vast and dynamic pool of models effectively. We propose LOCUS, a method that produces low-dimensional vector…
Parameter inference for dynamical models of (bio)physical systems remains a challenging problem. Intractable gradients, high-dimensional spaces, and non-linear model functions are typically problematic without large computational budgets. A…
The explosive growth of easily-accessible unlabeled data has lead to growing interest in active learning, a paradigm in which data-hungry learning algorithms adaptively select informative examples in order to lower prohibitively expensive…
The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a promising solution by strategically retaining $N$ elements…
Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a…
Recent studies have made remarkable progress in histopathology classification. Based on current successes, contemporary works proposed to further upgrade the model towards a more generalizable and robust direction through incrementally…
Quantum search has emerged as one of the most promising fields in quantum computing. State-of-the-art quantum search algorithms enable the search for specific elements in a distribution by monotonically increasing the density of these…
Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable…
We introduce an efficient combination of polyhedral analysis and predicate partitioning. Template polyhedral analysis abstracts numerical variables inside a program by one polyhedron per control location, with a priori fixed directions for…
Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful…
Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order logic queries is exponential in the number of existential…
Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference…
To address three important issues involved in latent variable models (LVMs), including capturing infrequent patterns, achieving small-sized but expressive models and alleviating overfitting, several studies have been devoted to…