Search: “concepts”

Exemplar Partitioning for Mechanistic Interpretability

arXiv:2605.14347v1 Announce Type: new Abstract: We introduce Exemplar Partitioning (EP), an unsupervised method for constructing interpretable feature dictionaries from large language model activation

Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI

DGX agent

arXiv:2605.14665v1 Announce Type: new Abstract: Legal reasoning is not semantic similarity search. A court judgment encodes constrained symbolic reasoning: precedent propagation, procedural state tran

hardwarearxiv-cs-ai

15 May 2026

GenExam: A Multidisciplinary Text-to-Image Exam

model-releasesarxiv-cs-cv

arXiv:2509.14232v5 Announce Type: replace Abstract: Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style bench

Kolmogorov-Arnold Chemical Reaction Neural Networks for learning pressure-dependent kinetic rate laws

arXiv:2511.07686v2 Announce Type: replace-cross Abstract: Chemical Reaction Neural Networks (CRNNs) have emerged as an interpretable machine learning framework for discovering reaction kinetics direct

Metis AI: The Overlooked Middle Zone Between AI-Native and World-Movers

arXiv:2605.14407v1 Announce Type: new Abstract: The dominant discourse on AI limitations frames the boundary of AI capability as a divide between digital tasks (where AI excels) and physical tasks (wh

researcharxiv-cs-ai

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models

arXiv:2605.15071v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work ident

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands

arXiv:2605.15164v1 Announce Type: cross Abstract: This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI govern

Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

arXiv:2605.14561v1 Announce Type: new Abstract: Prompt engineering is crucial for effective interaction with generative artificial intelligence systems, yet existing optimisation methods often operate

tutorialsarxiv-cs-ai

Hardware

Synthetic Sociality: How Generative Models Privatize the Social Fabric

arXiv:2605.14090v1 Announce Type: cross Abstract: We put forth a critical theoretical framework for analyzing generative models both descriptively and normatively. Our thesis is that generative models

hardwarearxiv-cs-lg

The Evaluation Trap: Benchmark Design as Theoretical Commitment

arXiv:2605.14167v1 Announce Type: new Abstract: Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments

Training ML Models with Predictable Failures

arXiv:2605.15134v1 Announce Type: new Abstract: Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely l

safetyarxiv-cs-lg

What Do EEG Foundation Models Capture from Human Brain Signals?

arXiv:2605.11410v2 Announce Type: replace Abstract: Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, e.g., band power, connectivity, complexit

tutorialsarxiv-cs-ai

An Agentic LLM-Based Framework for Population-Scale Mental Health Screening

arXiv:2605.13046v1 Announce Type: new Abstract: Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from ele

agentsarxiv-cs-ai

Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables

arXiv:2605.13383v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) perform computations on graphs by routing the signal between graph regions using a graph shift operator or a message passin

Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform'

arXiv:2605.13642v1 Announce Type: cross Abstract: Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without cl

tutorialsarxiv-cs-lg

Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling

arXiv:2605.13337v1 Announce Type: cross Abstract: Security Information and Event Management (SIEM) systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule

Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2

arXiv:2605.12968v1 Announce Type: cross Abstract: Do large language models internally encode ontological relations in a formally verifiable algebraic structure? We introduce Algebraic Ontology Project

Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems

arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analy

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning

arXiv:2605.13612v1 Announce Type: new Abstract: Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We

tutorialsarxiv-cs-lg

Multi-Agent Systems in Emergency Departments: Validation Study on a ED Digital Twin

arXiv:2605.13345v1 Announce Type: new Abstract: Emergency departments (ED) face challenges in patient care and resource management. We propose to explore optimization strategies in a realistic and fle

agentsarxiv-cs-ai

Tools

Mythos has cracked MacOS. It took five days.

Mythos, a security researcher or team, successfully exploited macOS security vulnerabilities in a five-day timeframe, demonstrating the relative speed at which determined actors can compromise Apple's

toolsboris-cherny--x

Neural Surrogate Forward Modelling For Electrocardiology Without Explicit Intracellular Conductivity Tensor

arXiv:2605.13366v1 Announce Type: new Abstract: Accurate forward modelling is essential for non-invasive cardiac electrophysiology, particularly in atrial fibrillation, where electrical activation is

researcharxiv-cs-cv

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior…

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter de

tutorialsandrew-ng--x

Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory

arXiv:2605.13370v1 Announce Type: new Abstract: For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for la

Revealing Interpretable Failure Modes of VLMs

arXiv:2605.12674v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to general

Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic

arXiv:2605.12651v1 Announce Type: new Abstract: Runtime monitoring of autonomous systems traditionally relies on mapping continuous sensor observations to discrete logical propositions defined over lo

safetyarxiv-cs-lg

Semantic knowledge guides innovation and drives cultural evolution

arXiv:2510.12837v3 Announce Type: replace-cross Abstract: Cultural evolution allows ideas and technologies to accumulate across generations, reaching their most complex and open-ended form in humans.

agentsarxiv-cs-ai

SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking

arXiv:2601.19667v2 Announce Type: replace-cross Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in

Unweighted ranking for value-based decision making with uncertainty

arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern

A Composite Activation Function for Learning Stable Binary Representations

arXiv:2605.11558v1 Announce Type: new Abstract: Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations ha

ASD-Bench: A Four-Axis Comprehensive Benchmark of AI Models for Autism Spectrum Disorder

arXiv:2605.11091v1 Announce Type: new Abstract: Automated ASD screening tools remain limited by single-architecture evaluations, axis-restricted assessment, and near-exclusive focus on adult cohorts,

Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification

arXiv:2605.11460v1 Announce Type: new Abstract: System identification (SysID) is critical for modeling dynamical systems from experimental data, yet traditional approaches often fail to capture nonlin

Cooperative Robotics Reinforced by Collective Perception for Traffic Moderation

arXiv:2605.11972v1 Announce Type: new Abstract: Collisions at non-line-of-sight (NLOS) intersections remain a major safety concern because drivers have limited visibility of approaching traffic. V2X b

safetyarxiv-cs-ro

Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsals

arXiv:2605.11463v1 Announce Type: new Abstract: Learning and representing the subjectivities of agents has become a challenging but crucial problem in the trajectory prediction task. Such subjectiviti

agentsarxiv-cs-cv

Local Ai

FAME: Feature Activation Map Explanation on Image Classification and Face Recognition

arXiv:2605.12017v1 Announce Type: new Abstract: Deep Learning has revolutionized machine learning, reaching unprecedented levels of accuracy, but at the cost of reduced interpretability. Especially in

local-aiarxiv-cs-cv

Tools

increasing levels of autonomy: /skill: preset prompts /plan: human-refined inputs /goal: AI-evaluated outputs

This post outlines a framework for progressively automating AI workflows through three levels of increasing autonomy: using preset prompts for consistency, refining inputs with human judgment to impro

toolsswyx--x

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering

arXiv:2605.12361v1 Announce Type: new Abstract: Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain dis

Applications

Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction

arXiv:2503.09051v2 Announce Type: replace Abstract: We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reco

applicationsarxiv-cs-lg

Online Continual Learning with Dynamic Label Hierarchies

arXiv:2605.11742v1 Announce Type: new Abstract: Online Continual Learning (OCL) aims to learn from endless nonext{-}stationary data streams, yet most existing methods assume a flat label space and ove

tutorialsarxiv-cs-lg

Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering

arXiv:2605.12313v1 Announce Type: new Abstract: Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple s

PresentAgent-2: Towards Generalist Multimodal Presentation Agents

arXiv:2605.11363v1 Announce Type: cross Abstract: Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal med

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

arXiv:2605.11887v1 Announce Type: new Abstract: Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, li

RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking

arXiv:2605.12059v1 Announce Type: cross Abstract: Computational thinking (CT) is increasingly promoted as a core literacy, yet learners and teachers face challenges in connecting abstract program logi

agentsarxiv-cs-ro

Robustness Certificates for Neural Networks against Adversarial Attacks

arXiv:2512.20865v2 Announce Type: replace Abstract: The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that

safetyarxiv-cs-lg

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

arXiv:2605.11919v1 Announce Type: new Abstract: Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node

Stationary MMD Points

arXiv:2505.20754v3 Announce Type: replace-cross Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integratio

The power of LLMs on your data, more than two orders of magnitude faster and cheaper

model-releasesgoogle-cloud-ai

Databases have introduced new AI-powered SQL functions which take natural language instructions as input and are evaluated using LLMs. They leverage the power of LLMs to answer new kinds of queries: W

What Does It Mean for a Medical AI System to Be Right?

model-releasesarxiv-cs-cv

arXiv:2605.11963v1 Announce Type: new Abstract: This paper examines what it means for a medical AI system to be right by grounding the question in a specific clinical context: the automatic classifica