Related papers: Differentiable Faithfulness Alignment for Cross-Mo…

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Domain adaptive object detection (DAOD) aims to generalize an object detector trained on labeled source-domain data to a target domain without annotations, the core principle of which is \emph{source-target feature alignment}. Typically,…

In this work, we introduce DeepDFA, a novel approach to identifying Deterministic Finite Automata (DFAs) from traces, harnessing a differentiable yet discrete model. Inspired by both the probabilistic relaxation of DFAs and Recurrent Neural…

By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels. Many existing UDA algorithms suffer from directly using raw…

Federated learning allows multiple clients to collaboratively train a model without exchanging their data, thus preserving data privacy. Unfortunately, it suffers significant performance degradation due to heterogeneous data at clients.…

The purpose of this paper is to formally specify a flow devoted to the design of Differential Power Analysis (DPA) resistant QDI asynchronous circuits. The paper first proposes a formal modeling of the electrical signature of QDI…

Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…

Recent years have witnessed the remarkable performance of diffusion models in various vision tasks. However, for image restoration that aims to recover clear images with sharper details from given degraded observations, diffusion-based…

Although deep learning and end-to-end models have been widely used and shown superiority in automatic speech recognition (ASR) and text-to-speech (TTS) synthesis, state-of-the-art forced alignment (FA) models are still based on hidden…

Large language models (LLMs) have demonstrated strong performance on formal language tasks, yet whether this reflects genuine symbolic reasoning or pattern matching on familiar constructions remains unclear. We introduce a benchmark for…

Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks tend to craft…

Large language models (LLMs) offer a promising way to simulate human survey responses, potentially reducing the cost of large-scale data collection. However, existing zero-shot methods suffer from prompt sensitivity and low accuracy, while…

Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more accurate and contextually rich responses. To improve the…

Channel state information (CSI) at transmitter is crucial for massive MIMO downlink systems to achieve high spectrum and energy efficiency. Existing works have provided deep learning architectures for CSI feedback and recovery at the…

Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot centralize it due to regulatory, proprietary, or…

Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…

Transformer-based neural decoders have emerged as a promising approach to error correction coding, combining data-driven adaptability with efficient modeling of long-range dependencies. This paper presents a novel decoder architecture that…

Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogeneous pretrained large language models (LLMs). To address this…

Approximate density functional theory (DFT) has become indispensable owing to its cost-accuracy trade-off in comparison to more computationally demanding but accurate correlated wavefunction theory. To date, however, no single density…

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most…