相关论文: Methodologies for Quantifying (Re-)randomization S…

In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers…

Characterization of experimental systems is an essential step in developing and improving quantum hardware. A collection of protocols known as Randomized Benchmarking (RB) was developed in the past decade, which provides an efficient way to…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

In recent RAG approaches, rerankers play a pivotal role in refining retrieval accuracy with the ability of revealing logical relations for each pair of query and text. However, existing rerankers are required to repeatedly encode the query…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Recently, post-training quantization (PTQ) has driven much attention to produce efficient neural networks without long-time retraining. Despite its low cost, current PTQ works tend to fail under the extremely low-bit setting. In this study,…

Large language models (LLMs) are increasingly used for automated code refactoring tasks. Although these models can quickly refactor code, the quality may exhibit inconsistencies and unpredictable behavior. In this article, we systematically…

Reliability, longevity, availability, and deadline guarantees are the four most important metrics to measure the QoS of long-running safety-critical real-time applications. Software aging is one of the major factors that impact the safety…

Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing…

Randomized exponential backoff is a widely deployed technique for coordinating access to a shared resource. A good backoff protocol should, arguably, satisfy three natural properties: (i) it should provide constant throughput, wasting as…

Time-Optimal Path Parameterization (TOPP) is a well-studied problem in robotics and has a wide range of applications. There are two main families of methods to address TOPP: Numerical Integration (NI) and Convex Optimization (CO). NI-based…

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…

Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First (RAF), a…

A device-independent randomness expansion protocol aims to take an initial random seed and generate a longer one without relying on details of how the devices operate for security. A large amount of work to date has focussed on a particular…

As experimental platforms for quantum information processing continue to mature, characterization of the quality of unitary gates that can be applied to their quantum bits (qubits) becomes essential. Eventually, the quality must be…

When fine-tuning language models on new tasks, catastrophic forgetting -- performance degradation on previously-learned tasks -- is a ubiquitous problem. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA address this through…

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have…