arXiv AI
Jul 3
XSearch: Explainable Code Search via Concept-to-Code Alignment
arXiv:2605. 16046v2 Announce Type: replace-cross Abstract: Semantic code search has been widely adopted in both academia and industry.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv Machine Learning
Jul 3
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
arXiv Machine Learning
Jul 3
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
arXiv:2607. 01278v1 Announce Type: new Abstract: The research proposes a multilayer Q-matrix-embedded neural network for cognitive diagnosis (M-QCDNet), which integrates the structural interpretability of cognitive diagnostic models (CDMs) with the deep learning neural network (NN).
arXiv Machine Learning
Jul 3
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
arXiv:2607. 01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints.
arXiv Machine Learning
Jul 3
From Approximation to Emergence: A Theory of Deep Learning
arXiv:2607. 01311v1 Announce Type: new Abstract: Deep learning has outgrown any single mathematical explanation.
arXiv Machine Learning
Jul 3
Geometry-Aware R-Structured Kolmogorov-Arnold Networks
arXiv:2607. 01449v1 Announce Type: new Abstract: We propose a novel hybrid neural architecture, the Geometry-aware R-Structured Kolmogorov-Arnold Network (GRS-KAN), which integrates V.
arXiv AI
Jul 3
Psychological Imagination Networks Show Cross-Population Centrality and Clustering Alignment in Humans That Large Language Models Fail to Replicate
arXiv:2510. 04391v5 Announce Type: replace Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown.
arXiv AI
Jul 3
Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias
arXiv:2607. 01973v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied in medical tasks such as pathology description, report generation, and visual question answering.
arXiv AI
Jul 3
Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing
arXiv:2607. 01690v1 Announce Type: new Abstract: Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core claims, an effect known as Negation Neglect.
arXiv AI
Jul 3
Mirror Illusion Art
arXiv:2607. 02015v1 Announce Type: cross Abstract: Mirror Illusion Art is a novel reflection-conditioned 3D illusion where one object yields two target appearances (front and mirror).
arXiv Machine Learning
Jul 3
Transformer Geometry Observatory TGO-II: Representational Similarity Observatory
arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.
arXiv AI
Jul 3
Safety Targeted Embedding Exploit via Refinement
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
arXiv AI
Jul 3
X-LogSMask: Expand Transformer for Graph-Structured Data
arXiv:2607. 01553v1 Announce Type: cross Abstract: Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale.
arXiv AI
Jul 3
Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
arXiv:2607. 01457v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication.
arXiv AI
Jul 3
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
arXiv:2607. 01982v1 Announce Type: cross Abstract: Using molecular large language models (LLMs) as a unified framework for understanding molecular structures and functions is emerging as a new trend in tasks such as molecular design and drug discovery.
arXiv AI
Jul 3
RadiomicNet: A Hybrid Radiomics-Guided Lightweight Architecture for Interpretable Medical Image Segmentation
arXiv:2607. 02185v1 Announce Type: cross Abstract: Deep learning has achieved remarkable performance in medical image segmentation, yet it suffers from critical limitations: mathematical intractability, substantial parameter requirements, and lack of clinical interpretability.
arXiv AI
Jul 3
Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
arXiv:2607. 01799v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and inferring a sparse code $\mathbf{x}\in\mathbb{R}^n$ from $\mathbf{h}\approx\mathbf{W}\mathbf{x}$.
arXiv AI
Jul 3
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
arXiv:2607. 01336v1 Announce Type: cross Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately capture physical observables that they have never been explicitly optimized for?
arXiv AI
Jul 3
Generative AI and Federated Learning for Intrusion Detection Systems: A Survey
arXiv:2607. 01305v1 Announce Type: cross Abstract: Intrusion Detection Systems (IDSs) are essential for monitoring network traffic and identifying malicious activities in modern cyber-physical, Internet of Things (IoT), enterprise, and distributed network environments.
arXiv AI
Jul 3
Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification
arXiv:2607. 01272v1 Announce Type: cross Abstract: Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware.