We introduce EEG Autoclean Vision Language AI (ICVision) a first-of-its-kind system that emulates expert-level EEG ICA component classification through AI-agent vision and natural language reasoning. Unlike conventional classifiers such as ICLabel, which rely on handcrafted features, ICVision directly interprets ICA dashboard visualizations topography, time series, power spectra, and ERP plots, using a multimodal large language model (GPT-4 Vision). This allows the AI to see and explain EEG components the way trained neurologists do, making it the first scientific implementation of AI-agent visual cognition in neurophysiology. ICVision classifies each component into one of six canonical categories (brain, eye, heart, muscle, channel noise, and other noise), returning both a confidence score and a human-like explanation. Evaluated on 3,168 ICA components from 124 EEG datasets, ICVision achieved k = 0.677 agreement with expert consensus, surpassing MNE ICLabel, while also preserving clinically relevant brain signals in ambiguous cases. Over 97% of its outputs were rated as interpretable and actionable by expert reviewers. As a core module of the open-source EEG Autoclean platform, ICVision signals a paradigm shift in scientific AI, where models do not just classify, but see, reason, and communicate. It opens the door to globally scalable, explainable, and reproducible EEG workflows, marking the emergence of AI agents capable of expert-level visual decision-making in brain science and beyond.

Most AI benchmarks saturate within years or even months after they are introduced, making it hard to study long-run trends in AI capabilities. To address this challenge, we build a statistical framework that stitches benchmarks together, putting model capabilities and benchmark difficulties on a single numerical scale. This acts as a "Rosetta Stone", allowing us to compare models across a wide range of abilities and time, even if they are not evaluated on the same benchmarks. Moreover, this works without assuming how capabilities evolve across time or with training compute. We demonstrate three applications of this framework. First, we use it to measure the speed of AI progress over time, and to forecast future AI capabilities. Second, we estimate the rate of improvements in algorithmic efficiency, finding estimates that are higher, but broadly consistent with prior work. Finally, we find that our approach can be used to detect rapid accelerations in AI progress.

Large Language Models (LLMs) have attracted significant attention for classification tasks, offering a flexible alternative to trusted classical machine learning models like LightGBM through zero-shot prompting. However, their reliability for structured tabular data remains unclear, particularly in high-stakes applications like financial risk assessment. Our study systematically evaluates LLMs and generates their SHAP values on financial classification tasks. Our analysis shows a divergence between LLMs self-explanation of feature impact and their SHAP values, as well as notable differences between LLMs and LightGBM SHAP values. These findings highlight the limitations of LLMs as standalone classifiers for structured financial modeling, but also instill optimism that improved explainability mechanisms coupled with few-shot prompting will make LLMs usable in risk-sensitive domains.

Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language models on this problem remain scarce. In this work, we present the first comprehensive evaluation of five state-of-the-art large language models on assembly-to-source translation. We assess model performance using a diverse set of metrics capturing lexical similarity (BLEU, ROUGE, and METEOR), semantic alignment (BERTScore), fluency (Perplexity), and efficiency (time prediction). Our results reveal clear trade-offs: while certain models excel in text similarity metrics, others demonstrate lower perplexity or faster inference times. We further provide qualitative analyses of typical model successes and failure cases, highlighting challenges such as control flow recovery and identifier reconstruction. Taken together, our benchmark offers actionable insights into the strengths and limitations of current large language models for program translation, establishing a foundation for future research in combining accuracy with efficiency for real-world applications.

Graph neural networks (GNNs) have shown promise in hardware security by learning structural motifs from netlist graphs. However, this reliance on motifs makes GNNs vulnerable to adversarial netlist rewrites; even small-scale edits can mislead GNN predictions. Existing adversarial approaches, ranging from synthesis-recipe perturbations to gate transformations, come with high design overheads. We present NetDeTox, an automated end-to-end framework that orchestrates large language models (LLMs) with reinforcement learning (RL) in a systematic manner, enabling focused local rewriting. The RL agent identifies netlist components critical for GNN-based reasoning, while the LLM devises rewriting plans to diversify motifs that preserve functionality. Iterative feedback between the RL and LLM stages refines adversarial rewritings to limit overheads. Compared to the SOTA work AttackGNN, NetDeTox successfully degrades the effectiveness of all security schemes with fewer rewrites and substantially lower area overheads (reductions of 54.50% for GNN-RE, 25.44% for GNN4IP, and 41.04% for OMLA, respectively). For GNN4IP, ours can even optimize/reduce the original benchmarks' area, in particular for larger circuits, demonstrating the practicality and scalability of NetDeTox.

This work examines how three different image-based methods, VGG16, ViT-B/16, and CoAtNet-Tiny, perform in identifying depression, schizophrenia, and healthy controls using daily actigraphy records. Wrist-worn activity signals from the Psykose and Depresjon datasets were converted into 30 48 images and evaluated through a three-fold subject-wise split. Although all methods fitted the training data well, their behaviour on unseen data differed. VGG16 improved steadily but often settled at lower accuracy. ViT-B/16 reached strong results in some runs, but its performance shifted noticeably from fold to fold. CoAtNet-Tiny stood out as the most reliable, recording the highest average accuracy and the most stable curves across folds. It also produced the strongest precision, recall, and F1-scores, particularly for the underrepresented depression and schizophrenia classes. Overall, the findings indicate that CoAtNet-Tiny performed most consistently on the actigraphy images, while VGG16 and ViT-B/16 yielded mixed results. These observations suggest that certain hybrid designs may be especially suited for mental-health work that relies on actigraphy-derived images. I. Introduction Mental health disorders such as depression and schizophrenia constitute a significant and growing global health challenge, with profound impacts on individuals, families, and healthcare systems worldwide. According to the World Health Organization, depression affects over 280 million people.

Autonomous robots are increasingly deployed in dynamic and unstructured environments, where they must plan and execute complex tasks under uncertainty. Classical planning approaches, typically modeled in PDDL and solved with heuristic search, provide a principled foundation for task planning (Edelkamp and Schr odl, 2011; Geffner and Bonet, 2013). However, these methods rely on explicit domain models that enumerate preconditions and effects of actions. In practice, such models often omit implicit commonsense knowledge, for example, that a container must be upright before pouring, or that water must be boiled before making tea. The absence of such knowledge can lead to plans that are logically correct but physically invalid. Cognitive robotics research seeks to bridge symbolic reasoning with robot perception and control (Ghallab et al., 2004). While significant progress has been made in integrating planning with motion control and execution, robots still lack the ability to autonomously infer commonsense constraints that humans consider obvious. Large Language Models (LLMs), trained on massive corpora of human knowledge, present a promising avenue for addressing this gap. LLMs can generate likely preconditions, subgoals, and contextual constraints from natural language task descriptions, potentially enriching classical planning models. 1

Self-evaluation is increasingly central to language model training, underpinning techniques from Constitutional AI to self-refinement. We investigate whether coupling self-evaluation to reward signals creates incentives for wireheading, where agents manipulate the measurement process rather than optimizing the task. We first formalize conditions under which reward-channel control strictly dominates task-focused behavior in partially observable Markov decision processes (POMDPs). We then test these predictions empirically across two models (Llama-3.1-8B and Mistral-7B) and three tasks. We find that when self-grades determine rewards, models exhibit substantial grade inflation without corresponding accuracy gains, particularly on ambiguous tasks like summarization. While decoupling self-grades from the reward signal mitigates this inflation, models may still display lesser (but significant) overconfidence. Our results suggest that within current model scales, separating evaluation from reward removes immediate wireheading incentives. However, we caution that strictly decoupling rewards may not suffice for situationally aware models, which could learn to inflate grades for instrumental reasons (such as influencing deployment decisions) even absent direct reward coupling.

Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric measures across a wide set of text embedding models and datasets. We find a high degree of redundancy among these measures and observe that individual metrics often fail to sufficiently differentiate embedding spaces. Building on these insights, we introduce Unified Topological Signatures (UTS), a holistic framework for characterizing embedding spaces. We show that UTS can predict model-specific properties and reveal similarities driven by model architecture. Further, we demonstrate the utility of our method by linking topological structure to ranking effectiveness and accurately predicting document retrievability. We find that a holistic, multi-attribute perspective is essential to understanding and leveraging the geometry of text embeddings.

Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generation but remain confined to single-node execution. We propose DSD, a distributed speculative decoding framework that extends SD to multi-device deployments through coordinated draft-target execution. Given the lack of prior work on simulating this paradigm, we first introduce DSD-Sim, a discrete-event simulator that captures network, batching, and scheduling dynamics. Building on insights from DSD-Sim, we further design an Adaptive Window Control (AWC) policy that dynamically adjusts speculation window size to optimize throughput. Experiments across diverse workloads show that DSD achieves up to 1.1x speedup and 9.7% higher throughput over existing SD baselines, enabling agile and scalable LLM serving across edge and cloud.