arXiv:2603.24343v1 Announce Type: cross Abstract: Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large language models (LLMs) further demonstrates the benefits of scaling model parameters, but also highlights one bottleneck […]
A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English
arXiv:2603.24549v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the mainstream accents represented in training data. This study investigates ASR bias through a sociolinguistic analysis of Newcastle English, a regional variety […]
Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
arXiv:2505.16950v4 Announce Type: replace-cross Abstract: Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space “thinking” chains of thought. A growing line of work pushes extra computation into the model’s latent space, which we term Auxiliary Latent-Space Computation (ALSC). Existing ALSC methods largely fall into three […]
The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
arXiv:2603.24124v1 Announce Type: cross Abstract: RLHF-aligned language models exhibit response homogenization: on TruthfulQA (n=790), 40-79% of questions produce a single semantic cluster across 10 i.i.d. samples. On affected questions, sampling-based uncertainty methods have zero discriminative power (AUROC=0.500), while free token entropy retains signal (0.603). This alignment tax is task-dependent: on GSM8K (n=500), token entropy achieves […]
Upper Entropy for 2-Monotone Lower Probabilities
arXiv:2603.23558v1 Announce Type: cross Abstract: Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifying prediction uncertainties to perform active learning or OOD detection. Within credal approaches that consider modeling uncertainty as probability sets, upper entropy plays a central role as an uncertainty measure. This paper is devoted to the […]
Assessment Design in the AI Era: A Method for Identifying Items Functioning Differentially for Humans and Chatbots
arXiv:2603.23682v1 Announce Type: cross Abstract: The rapid adoption of large language models (LLMs) in education raises profound challenges for assessment design. To adapt assessments to the presence of LLM-based tools, it is crucial to characterize the strengths and weaknesses of LLMs in a generalizable, valid and reliable manner. However, current LLM evaluations often rely on […]
Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities
arXiv:2603.24318v1 Announce Type: cross Abstract: State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because they utilize auxiliary modules for low-level motion planning and control. Motion planning remains challenging due to the high dimensionality of the robot’s configuration space and the […]
Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
arXiv:2603.23064v2 Announce Type: replace-cross Abstract: We identify a critical security vulnerability in mainstream Claw personal AI agents: untrusted content encountered during heartbeat-driven background execution can silently pollute agent memory and subsequently influence user-facing behavior without the user’s awareness. This vulnerability arises from an architectural design shared across the Claw ecosystem: heartbeat background execution runs in […]
Comparative analysis of dual-form networks for live land monitoring using multi-modal satellite image time series
arXiv:2603.24109v1 Announce Type: cross Abstract: Multi-modal Satellite Image Time Series (SITS) analysis faces significant computational challenges for live land monitoring applications. While Transformer architectures excel at capturing temporal dependencies and fusing multi-modal data, their quadratic computational complexity and the need to reprocess entire sequences for each new acquisition limit their deployment for regular, large-area monitoring. […]
Enhancing Jailbreak Attacks on LLMs via Persona Prompts
arXiv:2507.22171v3 Announce Type: replace-cross Abstract: Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM safety. Previous jailbreak approaches have mainly focused on direct manipulations of harmful intent, with limited attention to […]
Explainable embeddings with Distance Explainer
arXiv:2505.15516v2 Announce Type: replace-cross Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance […]
SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
arXiv:2510.15259v3 Announce Type: replace Abstract: Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-free setting, large language model (LLM)-based agents face severe efficiency bottlenecks: limited to local visual experiences, they make myopic decisions and rely on inefficient trial-and-error, hindering both […]