arXiv preprints from January 1, 2026 through September 22, 2026 — 02:28:07 EST
We investigate intelligent personal assistants (IPAs) accessibility for deaf and hard of hearing (DHH) people who can use their voice in everyday communication. The inability of IPAs to understand diverse accents including deaf speech renders them largely inaccessible to non-signing and speaking DHH individuals. Using an Echo Show, we...
Why do even the most powerful 7B-parameter embedding models struggle with simple retrieval tasks that the decades old BM25 handles with ease? Recent theory suggests that this happens because of a dimensionality bottleneck. This occurs when we force infinite linguistic nuances into small, fixed-length learned vectors. We developed...
Early and accurate classification of Alzheimers disease (AD) from brain MRI scans is essential for timely clinical intervention and improved patient outcomes. This study presents a comprehensive comparative analysis of five CNN architectures (EfficientNetB0, ResNet50, DenseNet201, MobileNetV3, VGG16), five Transformer-based models...
When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content through AI transmission chains, we find three consistent patterns. The first is convergence, where...
Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose improves crowded pose estimation without sacrificing performance on standard scenes. Building on this,...
Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias. In such datasets, language instructions are highly...
AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why many of them fail to be merged. In this paper, we conduct...
This work investigates the performance of Large Language Models (LLMs) in generating ABAP code. Despite successful applications of generative AI in many programming languages, there are hardly any systematic analyses of ABAP code generation to date. The aim of the study is to empirically analyze to what extent various LLMs can...
While large language models (LLMs) are increasingly used to summarize long documents, this trend poses significant challenges in the legal domain, where the factual accuracy of deposition summaries is crucial. Nugget-based methods have been shown to be extremely helpful for the automated evaluation of summarization approaches. In this...
We propose the integration of staged metaprogramming into a session-typed message passing functional language. We build on a model of contextual modal type theory with multi-level contexts, where contextual values, closing arbitrary terms over a series of variables, may be boxed and transmitted in messages. Once received, one such...
Reflexive Thematic Analysis (RTA) is a critical method for generating deep interpretive insights. Yet its core tenets, including researcher reflexivity, tangible analytical evolution, and productive disagreement, are often poorly supported by software tools that prioritize speed and consensus over interpretive depth. To address this...
The unification of neural and symbolic approaches to artificial intelligence remains a central open challenge. In this work, we introduce a tensor network formalism, which captures sparsity principles originating in the different approaches in tensor decompositions. In particular, we describe a basis encoding scheme for functions and...
Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown promise in disentangling latent representations, existing SAE-based methods for diffusion model understanding rely on unsupervised approaches that fail to...
Egocentric video action recognition under domain shifts remains challenging due to large intra-class spatio-temporal variability, long-tailed feature distributions, and strong correlations between actions and environments. Existing benchmarks for egocentric domain generalization often conflate covariate shifts with concept shifts,...
Large Language Models (LLMs) like ChatGPT offer potential support for autistic people, but this potential requires understanding the implicit perspectives these models might carry, including their biases and assumptions about autism. Moving beyond single-agent prompting, we utilized LLM-based multi-agent systems to investigate complex...
We propose a novel way to evaluate sycophancy of LLMs in a direct and neutral way, mitigating various forms of uncontrolled bias, noise, or manipulative language, deliberately injected to prompts in prior works. A key novelty in our approach is the use of LLM-as-a-judge, evaluation of sycophancy as a zero-sum game in a bet setting....
The evolution of digital manufacturing requires intelligent Question Answering (QA) systems that can seamlessly integrate and analyze complex multi-modal data, such as text, images, formulas, and tables. Conventional Retrieval Augmented Generation (RAG) methods often fall short in handling this complexity, resulting in subpar...
Scientific research metadata is vital to ensure the validity, reusability, and cost-effectiveness of research efforts. The MEDFORD metadata language was previously introduced to simplify the process of writing and maintaining metadata for non-programmers. However, barriers to entry and usability remain, including limited automatic...
Radiance field-based rendering methods have attracted significant interest from the computer vision and computer graphics communities. They enable high-fidelity rendering with complex real-world lighting effects, but at the cost of high rendering time. 3D Gaussian Splatting solves this issue with a rasterisation-based approach for...
Large Language Models (LLMs) generate fluent answers but can struggle with trustworthy, domain-specific reasoning. We evaluate whether domain knowledge graphs (KGs) improve Retrieval-Augmented Generation (RAG) for healthcare by constructing three PubMed-derived graphs: $\mathbb{G}_1$ (T2DM), $\mathbb{G}_2$ (Alzheimer's disease), and...
We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system summarizes behavior windows as behavioral archetypes and activates archetype-based scoring only when an in-support confidence signal exceeds a validation-calibrated threshold,...
Motivated by applications in computable analysis, we study fixpoints of certain endofunctors over categories of containers. More specifically, we focus on fibred endofunctors over the fibrewise opposite of the codomain fibration that can be themselves be represented by families of polynomial endofunctors. In this setting, we show how...
We present a scalable framework for cross-embodiment humanoid robot control by learning a shared latent representation that unifies motion across humans and diverse humanoid platforms, including single-arm, dual-arm, and legged humanoid robots. Our method proceeds in two stages: first, we construct a decoupled latent space that...
We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, and training directly on such heterogeneous data often yields suboptimal models. We propose a dataset-model...
VIBETENSOR is an open-source research system software stack for deep learning, generated by LLM-powered coding agents under high-level human guidance. In this paper, "fully generated" refers to code provenance: implementation changes were produced and applied as agent-proposed diffs; validation relied on agent-run builds, tests, and...