Archives AI News

Memorization Sinks: Isolating Memorization during LLM Training

arXiv:2507.09937v2 Announce Type: replace-cross Abstract: Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have shown limited success so…

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

arXiv:2503.05179v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs, leading to increased…

zELO: ELO-inspired Training Method for Rerankers and Embedding Models

arXiv:2509.12541v1 Announce Type: new Abstract: We introduce a novel training methodology named zELO, which optimizes retrieval performance via the analysis that ranking tasks are statically equivalent to a Thurstone model. Based on the zELO method, we use unsupervised data in…

Adversarial Prompt Distillation for Vision-Language Models

arXiv:2411.15244v3 Announce Type: replace-cross Abstract: Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like autonomous driving and medical diagnosis. One…

A Dimensionality-Reduced XAI Framework for Roundabout Crash Severity Insights

arXiv:2509.12524v1 Announce Type: new Abstract: Roundabouts reduce severe crashes, yet risk patterns vary by conditions. This study analyzes 2017-2021 Ohio roundabout crashes using a two-step, explainable workflow. Cluster Correspondence Analysis (CCA) identifies co-occurring factors and yields four crash patterns. A…

Physical Complexity of a Cognitive Artifact

arXiv:2509.12495v1 Announce Type: new Abstract: Cognitive science and theoretical computer science both seek to classify and explain the difficulty of tasks. Mechanisms of intelligence are those that reduce task difficulty. Here we map concepts from the computational complexity of a…

HARMONIC: A Content-Centric Cognitive Robotic Architecture

arXiv:2509.13279v1 Announce Type: cross Abstract: This paper introduces HARMONIC, a cognitive-robotic architecture designed for robots in human-robotic teams. HARMONIC supports semantic perception interpretation, human-like decision-making, and intentional language communication. It addresses the issues of safety and quality of results; aims…

Empowering Clinical Trial Design through AI: A Randomized Evaluation of PowerGPT

arXiv:2509.12471v1 Announce Type: new Abstract: Sample size calculations for power analysis are critical for clinical research and trial design, yet their complexity and reliance on statistical expertise create barriers for many researchers. We introduce PowerGPT, an AI-powered system integrating large…

A Design Co-Pilot for Task-Tailored Manipulators

arXiv:2509.13077v1 Announce Type: cross Abstract: Although robotic manipulators are used in an ever-growing range of applications, robot manufacturers typically follow a “one-fits-all” philosophy, employing identical manipulators in various settings. This often leads to suboptimal performance, as general-purpose designs fail to…

Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

arXiv:2509.12464v1 Announce Type: new Abstract: Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater performance…