arXiv preprints from January 1, 2026 through July 20, 2026 — 21:06:40 EST
Understanding relationships between attention heads is essential for interpreting the internal structure of Transformers, yet existing metrics do not capture this structure well. We focus on the subspaces spanned by attention-head weight matrices and quantify head-to-head relationships using the Projection Kernel (PK), a...
In the field of artificial intelligence, real parameter single objective optimization is an important direction. Both the Differential Evolution (DE) and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) demonstrate good performance for real parameter single objective optimization. Nevertheless, there exist other types of...
We analyze polarization-adjusted convolutional codes using the algebraic representation of polar and Reed-Muller codes. We define a large class of codes, called generalized polynomial polar codes which include PAC codes and Reverse PAC codes. We derive structural properties of generalized polynomial polar codes, such as duality,...
Virtualization-based binary obfuscation is widely adopted to protect software intellectual property, yet existing approaches leave exception-handling (EH) metadata unprotected to preserve ABI compatibility. This exposed metadata leaks rich structural information, such as stack layouts, control-flow boundaries, and object lifetimes,...
In this paper, we analyze the periodic transmission masks for MASked Modulation (MASM) in half-duplex integrated sensing and communication (ISAC), and derive their closed-form expected range-Doppler response $\mathbb{E}\{r(k,l,ν)\}$. We show that range sidelobes ($k\neq l$) are Doppler-invariant, extending the range-sidelobe...
AI-powered coding assistants are rapidly becoming fixtures in professional IDEs, yet their sustained influence on everyday development remains poorly understood. Prior research has focused on short-term use or self-reported perceptions, leaving open questions about how sustained AI use reshapes actual daily coding practices in the...
When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons. Standard evaluation conflates these by testing only matched conditions (e.g., English dilemma with English...
We introduce the sum channel, a new channel model motivated by applications in distributed storage and DNA data storage. In the error-free case, it takes as input an $\ell$-row binary matrix and outputs an $(\ell+1)$-row matrix whose first $\ell$ rows equal the input and whose last row is their parity (sum) row. We construct a...
We present NoReGeo, a novel benchmark designed to evaluate the intrinsic geometric understanding of large language models (LLMs) without relying on reasoning or algebraic computation. Unlike existing benchmarks that primarily assess models' proficiency in reasoning-based geometry-where solutions are derived using algebraic...
Current in-IDE AI coding tools typically rely on time-consuming manual prompting and context management, whereas proactive alternatives that anticipate developer needs without explicit invocation remain underexplored. Understanding when humans are receptive to such proactive AI assistance during their daily work remains an open...
Sharpness-Aware Minimization (SAM) aims to improve generalization by minimizing a worst-case perturbed loss over a small neighborhood of model parameters. However, during training, its optimization behavior does not always align with theoretical expectations, since both sharp and flat regions may yield a small perturbed loss. In such...
Access to mental healthcare is increasingly strained by workforce shortages and rising demand, motivating the development of intelligent systems that can support mental healthcare experts. We introduce coTherapist, a unified framework utilizing a small language model to emulate core therapeutic competencies through domain-specific...
Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to complete solution breakdown. Current LLM routing methods assign entire queries to one model, treating all reasoning steps as equal. We propose TRIM (Targeted routing in multi-step reasoning tasks),...
Imagine sitting in a presentation, trying to follow the speaker while simultaneously scanning the slides for relevant information. While the entire slide is visible, identifying the relevant regions can be challenging. As you focus on one part of the slide, the speaker moves on to a new sentence, leaving you scrambling to catch up...
Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational depth by iterating shared layers--can bridge this gap by utilizing their iterative nature as a...
Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood. We analyze DP-SGD in the $f$-differential privacy framework, which characterizes privacy via hypothesis-testing trade-off...
AI writing assistants can reduce effort and improve fluency, but they may also weaken writers' sense of authorship. We study this tension with an ownership-aware co-writing editor that offers on-demand, sentence-level suggestions and tests two common design choices: persona-based coaching and style personalization. In an online study...
This work addresses the challenge of safe and efficient mobile robot navigation in complex dynamic environments with concave moving obstacles. Reactive safe controllers like Control Barrier Functions (CBFs) design obstacle avoidance strategies based only on the current states of the obstacles, risking future collisions. To alleviate...
Understanding complex parameter dependencies is critical for effective configuration and maintenance of software systems across diverse domains - from Computer-Aided Engineering (CAE) to cloud infrastructure and database management. However, legacy tabular interfaces create a major bottleneck: engineers cannot easily comprehend how...
Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown that LLMs often generate logically inconsistent reasoning steps even when their final answers are correct. These...
Multimodal Large Language Models (MLLMs) struggle with complex video QA benchmarks like HD-EPIC VQA due to ambiguous queries/options, poor long-range temporal reasoning, and non-standardized outputs. We propose a framework integrating query/choice pre-processing, domain-specific Qwen2.5-VL fine-tuning, a novel Temporal...
Origami-inspired structures with rigid panels now span thick, kirigami, and multi-sheet realizations, making unified kinematic analysis essential. Yet a general method that consolidates their loop constraints has been lacking. We present an automated approach that generates the Pfaffian constraint matrix for arbitrary rigid foldable...
People who stutter (PWS) face systemic exclusion in today's voice-driven society, where access to voice assistants, authentication systems, and remote work tools increasingly depends on fluent speech. Current automatic speech recognition (ASR) systems, trained predominantly on fluent speech, fail to serve millions of PWS worldwide. We...
A new transformation is underway in software engineering, driven by the rapid adoption of generative AI in development workflows. Similar to how version control systems once automated manual coordination, AI tools are now beginning to automate many aspects of programming. For embedded software engineering organizations, however, this...
In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) systems have attempted to address this complexity with a blunt tool: linearization. We convert rich, multidimensional tables into simple...