AI Research News Feeds for September 10th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Signal-Based Malware Classification Using 1D CNNs
• Missing Fine Details in Images: Last Seen in High Frequencies
• Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media
• VMGNet: A Low Computational Complexity Robotic Grasping Network Based on VMamba with Multi-Scale Feature Fusion
• PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map
• BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video
• GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions
• Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving
• IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Rendering
• Nonparametric Envelopes for Flexible Response Reduction
• Bayesian Pliable Lasso with Horseshoe Prior for Interaction Effects in GLMs with Missing Responses
• Physics-informed low-rank neural operators with application to parametric elliptic PDEs
• Feature Understanding and Sparsity Enhancement via 2-Layered kernel machines (2L-FUSE)
• Expected Signature Kernels for L\'evy Rough Paths
• Counterfactual Cocycles: A Framework for Robust and Coherent Counterfactual Transports
• Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation
• Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots
• Evaluation of Alignment-Regularity Characteristics in Deformable Image Registration
• Large-scale Pre-training for Grounded Video Caption Generation
• A Decade of Wheat Mapping for Lebanon
• RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning
• SAMba-UNet: SAM2-Mamba UNet for Cardiac MRI in Medical Robotic Perception
• PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessment
• SPACE-iT: Spatial-Aware Curriculum Exploration and Feedback-Driven Adaptive Augmentation for Vision Transformer Distillation
• Interpretable Text-Guided Image Clustering via Iterative Search
• Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars
• Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
• HieraRS: A Hierarchical Segmentation Paradigm for Remote Sensing Enabling Multi-Granularity Interpretation and Cross-Domain Transfer
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model
• D-LEAF: Localizing and Correcting Hallucinations in Multimodal LLMs via Layer-to-head Attention Diagnostics
• Object-level Correlation for Few-Shot Segmentation
• ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion
• Dynamic Scene 3D Reconstruction of an Uncooperative Resident Space Object
• Feature Space Analysis by Guided Diffusion Model
• One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
• Visual Representation Alignment for Multimodal Large Language Models
• A smart fridge with AI-enabled food computing
• Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials
• Understanding Ice Crystal Habit Diversity with Self-Supervised Learning
• A Challenging Benchmark of Anime Style Recognition
• SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance
• TractGraphFormer: Anatomically Informed Hybrid Graph CNN-Transformer Network for Interpretable Sex and Age Prediction from Diffusion MRI Tractography
• MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning
• InteractPro: A Unified Framework for Motion-Aware Image Composition
• Self Supervised Networks for Learning Latent Space Representations of Human Body Scans and Motions
• OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations
• Decoupled Sparse Priors Guided Diffusion Compression Model for Point Clouds
• Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection
• Detect Changes like Humans: Incorporating Semantic Priors for Improved Change Detection
• DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation
• In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
• XOCT: Enhancing OCT to OCTA Translation via Cross-Dimensional Supervised Multi-Scale Feature Learning
• ANYPORTAL: Zero-Shot Consistent Video Background Replacement
• LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors
• DiGS: Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learning
• MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection
• Universal Few-Shot Spatial Control for Diffusion Models
• TextlessRAG: End-to-End Visual Document RAG by Speech Without Text
• PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
• Temporal Image Forensics: A Review and Critical Evaluation
• Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
• Data-Efficient Fine-Tuning of Vision-Language Models for Diagnosis of Alzheimer's Disease
• Self-Supervised Cross-Encoder for Neurodegenerative Disease Diagnosis
• Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity
• Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection
• EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration
• SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compression
• HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting
• RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis
• Faster, Self-Supervised Super-Resolution for Anisotropic Multi-View MRI Using a Sparse Coordinate Loss
• Understanding Museum Exhibits using Vision-Language Reasoning
• Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection
• FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
• Geospatial Foundational Embedder: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025)
• K-Syn: K-space Data Synthesis in Ultra Low-data Regimes
• Enhancing Classification of Streaming Data with Image Distillation
• Faster VGGT with Block-Sparse Global Attention
• Detection and Recovery of Adversarial Slow-Pose Drift in Offloaded Visual-Inertial Odometry
• Realism to Deception: Investigating Deepfake Detectors Against Face Enhancement
• G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
• Parse Graph-Based Visual-Language Interaction for Human Pose Estimation
• Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
• Are Humans as Brittle as Large Language Models?
• From Detection to Mitigation: Addressing Gender Bias in Chinese Texts via Efficient Tuning and Voting-Based Rebalancing
• Biased Tales: Cultural and Topic Bias in Generating Children's Stories
• SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
• Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
• VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality
• Neurocognitive Modeling for Text Generation: Deep Learning Architecture for EEG Data
• GLEAM: Learning to Match and Explain in Cross-View Geo-Localization
• Visual-TableQA: Open-Domain Benchmark for Reasoning over Table Images
• UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
• Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference
• M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis
• MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering
• When Large Language Models Meet Speech: A Survey on Integration Approaches
• Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation
• Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
• A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP
• FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain
• Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects
• Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMs
• Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation
• GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
• Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders
• MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations
• The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
• Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector
• Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation
• PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions
• The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering
• LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction
• AIxcellent Vibes at GermEval 2025 Shared Task on Candy Speech Detection: Improving Model Performance by Span-Level Training
• Understanding Stigmatizing Language Lexicons: A Comparative Analysis in Clinical Contexts
• From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation
• VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
• MaLei at MultiClinSUM: Summarisation of Clinical Documents using Perspective-Aware Iterative Self-Prompting with LLMs
• MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
• M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models
• Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
• SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP
• Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE Distillation and Diffusion Probabilistic Feedback
• Prepared for the Worst: A Learning-Based Adversarial Attack for Resilience Analysis of the ICP Algorithm
• JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
• Improving the Estimation of Lifetime Effects in A/B Testing via Treatment Locality
• Explainable Metrics for the Assessment of Neurodegenerative Diseases through Handwriting Analysis
• PnP-Flow: Plug-and-Play Image Restoration with Flow Matching
• Generalizable Humanoid Manipulation with 3D Diffusion Policies
• A Data-Free Analytical Quantization Scheme for Deep Learning Models
• Improved Physics-informed neural networks loss function regularization with a variance-based term
• Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models
• Matrix Completion in Group Testing: Bounds and Simulations
• MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
• FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
• Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models
• SemCAFE: When Named Entities make the Difference Assessing Web Source Reliability through Entity-level Analytics
• Analytic theory of dropout regularization
• Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular Optimization
• Learning to Upsample and Upmix Audio in the Latent Domain
• MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
• Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters
• Active Learning of Piecewise Gaussian Process Surrogates
• FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning
• Efficient Methods for Non-stationary Online Learning
• On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
• CoMMIT: Coordinated Multimodal Instruction Tuning
• BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery
• Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift
• When Do Neural Networks Learn World Models?
• Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
• SynLlama: Generating Synthesizable Molecules and Their Analogs with Large Language Models
• Highly Efficient Direct Analytics on Semantic-aware Time Series Data Compression
• M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
• Scalable Autoregressive 3D Molecule Generation
• Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization
• Equivariant U-Shaped Neural Operators for the Cahn-Hilliard Phase-Field Model
• Bootstrapping Task Spaces for Self-Improvement
• Time-Varying Graph Learning with Constraints on Graph Temporal Variation
• Challenging Bug Prediction and Repair Models with Synthetic Bugs
• LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade
• Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Space
• Identifying Neural Signatures from fMRI using Hybrid Principal Components Regression
• Causal Attention with Lookahead Keys
• Instance-level Performance Prediction for Long-form Generation Tasks
• Reinforcement learning for online hyperparameter tuning in convex quadratic programming
• Synthetic Data Generation with Lorenzetti for Time Series Anomaly Detection in High-Energy Physics Calorimeters
• MedicalPatchNet: A Patch-Based Self-Explainable AI Architecture for Chest X-ray Classification
• RINO: Renormalization Group Invariance with No Labels
• Asynchronous Gossip Algorithms for Rank-Based Statistical Methods
• Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription
• Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
• Nearest Neighbor Projection Removal Adversarial Training
• CAViAR: Critic-Augmented Video Agentic Reasoning
• Building causation links in stochastic nonlinear systems from data
• Toward Quantum Utility in Finance: A Robust Data-Driven Algorithm for Asset Clustering
• Quantum Computing for Large-scale Network Optimization: Opportunities and Challenges
• Decentralized Online Riemannian Optimization Beyond Hadamard Manifolds
• Nuclear Data Adjustment for Nonlinear Applications in the OECD/NEA WPNCS SG14 Benchmark -- A Bayesian Inverse UQ-based Approach for Data Assimilation
• Smart Fast Finish: Preventing Overdelivery via Daily Budget Pacing at DoorDash
• Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees
• RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
• Bio-KGvec2go: Serving up-to-date Dynamic Biomedical Knowledge Graph Embeddings
• One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
• Customizing the Inductive Biases of Softmax Attention using Structured Matrices
• Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence
• Toric geometry of ReLU neural networks
• DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
• veScale: Consistent and Efficient Tensor Programming with Eager-Mode SPMD
• Private Queries with Sigma-Counting
• Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRI
• TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion
• A Quantum Bagging Algorithm with Unsupervised Base Learners for Label Corrupted Datasets
• PUUMA (Placental patch and whole-Uterus dual-branch U-Mamba-based Architecture): Functional MRI Prediction of Gestational Age at Birth and Preterm Risk
• SAM$^{*}$: Task-Adaptive SAM with Physics-Guided Rewards
• End-to-End Efficiency in Keyword Spotting: A System-Level Approach for Embedded Microcontrollers
• Sequentially Auditing Differential Privacy
• ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression
• NestGNN: A Graph Neural Network Framework Generalizing the Nested Logit Model for Travel Mode Choice
• Avoiding Over-Personalization with Rule-Guided Knowledge Graph Adaptation for LLM Recommendations
• Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
• Dimensionally Reduced Open-World Clustering: DROWCULA
• Predicting person-level injury severity using crash narratives: A balanced approach with roadway classification and natural language process techniques
• Addressing the Cold-Start Problem for Personalized Combination Drug Screening
• Leveraging Support Vector Regression for Outcome Prediction in Personalized Ultra-fractionated Stereotactic Adaptive Radiotherapy
• A Survey of Graph Neural Networks for Drug Discovery: Recent Developments and Challenges
• Feasibility of In-Ear Single-Channel ExG for Wearable Sleep~Monitoring in Real-World Settings
• A Modular Algorithm for Non-Stationary Online Convex-Concave Optimization
• IP-Basis PINNs: Efficient Multi-Query Inverse Parameter Estimation
• GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning
• Learning Generalized Hamiltonian Dynamics with Stability from Noisy Trajectory Data
• CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation
• FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learning
• EfficientNet in Digital Twin-based Cardiac Arrest Prediction and Analysis
• EMORF-II: Adaptive EM-based Outlier-Robust Filtering with Correlated Measurement Noise
• Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks
• RoseCDL: Robust and Scalable Convolutional Dictionary Learning for Rare-event Detection
• uGMM-NN: Univariate Gaussian Mixture Model Neural Network
• Homogenization with Guaranteed Bounds via Primal-Dual Physically Informed Neural Networks
• K2-Think: A Parameter-Efficient Reasoning System
• Graph-based Integrated Gradients for Explaining Graph Neural Networks
• FUnc-SNE: A flexible, Fast, and Unconstrained algorithm for neighbour embeddings
• IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missing
• MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
• GRADA: Graph-based Reranking against Adversarial Documents Attack
• Overflow Prevention Enhances Long-Context Recurrent LLMs
• Visuospatial Cognitive Assistant
• Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts
• Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
• SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
• Multi-output Classification using a Cross-talk Architecture for Compound Fault Diagnosis of Motors in Partially Labeled Condition
• Localizing Persona Representations in LLMs
• Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
• HueManity: Probing Fine-Grained Visual Perception in MLLMs
• From Images to Insights: Explainable Biodiversity Monitoring with Plain Language Habitat Explanations
• Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
• A Kriging-HDMR-based surrogate model with sample pool-free active learning strategy for reliability analysis
• Machine Generalize Learning in Agent-Based Models: Going Beyond Surrogate Models for Calibration in ABMs
• Recursive State Inference for Linear PASFA
• Benchmarking Vision Transformers and CNNs for Thermal Photovoltaic Fault Detection with Explainable AI Validation
• Of Graphs and Tables: Zero-Shot Node Classification with Tabular Foundation Models
• PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
• Fed-REACT: Federated Representation Learning for Heterogeneous and Evolving Data
• Predicting effect of novel treatments using molecular pathways and real-world data
• CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge
• Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning
• TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
• Automatically Detecting Online Deceptive Patterns
• TrojanRobot: Physical-world Backdoor Attacks Against VLM-based Robotic Manipulation
• Cardiverse: Harnessing LLMs for Novel Card Game Prototyping
• VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification
• Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention
• DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation
• Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution
• The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
• Audio-centric Video Understanding Benchmark without Text Shortcut
• Enhancing Traffic Incident Response through Sub-Second Temporal Localization with HybridMamba
• Llama-Nemotron: Efficient Reasoning Models
• Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?
• Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices
• OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
• Multimodal Contrastive Pretraining of CBCT and IOS for Enhanced Tooth Segmentation
• GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models
• Accelerating Local AI on Consumer GPUs: A Hardware-Aware Dynamic Strategy for YOLOv10s
• Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation
• ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation
• Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
• ACE and Diverse Generalization via Selective Disagreement
• Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
• Self-Emotion-Mediated Exploration in Artificial Intelligence Mirrors: Findings from Cognitive Psychology
• Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
• COMMA: A Communicative Multimodal Multi-Agent Benchmark
• Visualizing Thought: Conceptual Diagrams Enable Robust Combinatorial Planning in LMMs
• Automatic Reward Shaping from Confounded Offline Data
• GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
• Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
• MedGellan: LLM-Generated Medical Guidance to Support Physicians
• Attention Maps in 3D Shape Classification for Dental Stage Estimation with Class Node Graph Attention Networks
• BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment
• Can SSD-Mamba2 Unlock Reinforcement Learning for End-to-End Motion Control?
• Transformer-Based Approach to Optimal Sensor Placement for Structural Health Monitoring of Probe Cards
• Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniques
• From Classical Data to Quantum Advantage -- Quantum Policy Evaluation on Quantum Hardware
• Variational Quantum Circuits in Offline Contextual Bandit Problems
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Enhancing Online Learning by Integrating Biosensors and Multimodal Learning Analytics for Detecting and Predicting Student Behavior: A Review
• Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
• What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects
• Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning
• XSRD-Net: EXplainable Stroke Relapse Detection
• Individual utilities of life satisfaction reveal inequality aversion unrelated to political alignment
• Enhanced SegNet with Integrated Grad-CAM for Interpretable Retinal Layer Segmentation in OCT Images
• Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
• Small Open Models Achieve Near Parity with Large Models in Low Resource Literary Translation at a Fraction of the Cost
• Deep Learning-Based Burned Area Mapping Using Bi-Temporal Siamese Networks and AlphaEarth Foundation Datasets
• Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
• Uncovering Scaling Laws for Large Language Models via Inverse Problems
• Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents
• Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions
• Toward Lifelong-Sustainable Electronic-Photonic AI Systems via Extreme Efficiency, Reconfigurability, and Robustness
• Benchmarking Universal Interatomic Potentials on Zeolite Structures
• The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
• Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions
• Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
• DepthVision: Robust Vision-Language Understanding through GAN-Based LiDAR-to-RGB Synthesis
• HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention
• Fine-Tuning Vision-Language Models for Visual Navigation Assistance
• Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognition
• Astra: A Multi-Agent System for GPU Kernel Performance Optimization
• ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval
• Water Demand Forecasting of District Metered Areas through Learned Consumer Representations
• EHWGesture -- A dataset for multimodal understanding of clinical gestures
• Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data
• FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
• HU-based Foreground Masking for 3D Medical Masked Image Modeling
• Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
• $\Delta L$ Normalization: Rethink Loss Aggregation in RLVR
• Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference
• A multi-strategy improved gazelle optimization algorithm for solving numerical optimization and engineering applications
• XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning
• Explaining How Quantization Disparately Skews a Model
• A transformer-based generative model for planetary systems
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning
• Benchmarking Information Retrieval Models on Complex Retrieval Tasks
• Datasets for Navigating Sensitive Topics in Recommendation Systems
• Breast Cancer Detection in Thermographic Images via Diffusion-Based Augmentation and Nonlinear Feature Fusion
• ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers
• Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
• zkUnlearner: A Zero-Knowledge Framework for Verifiable Unlearning with Multi-Granularity and Forgery-Resistance
• Reconstruction Alignment Improves Unified Multimodal Models
• Basis Vector Metric: A Method for Robust Open-Ended State Change Detection
• Does This Look Familiar to You? Knowledge Analysis via Model Internal Representations
• MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models
• Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation
• DEPF: A UAV Multispectral Object Detector with Dual-Domain Enhancement and Priority-Guided Mamba Fusion
• General Demographic Foundation Models for Enhancing Predictive Performance Across Diseases
• Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms
• SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
• Random Forest Stratified K-Fold Cross Validation on SYN DoS Attack SD-IoV
• An efficient deep reinforcement learning environment for flexible job-shop scheduling
• MEGS$^{2}$: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning
• Preventing Another Tessa: Modular Safety Middleware For Health-Adjacent AI Assistants
• 1 bit is all we need: binary normalized neural networks
• Contradictions
• Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
• The Impact of Artificial Intelligence on Traditional Art Forms: A Disruption or Enhancement
• A Minimalist Bayesian Framework for Stochastic Optimization
• A Maslow-Inspired Hierarchy of Engagement with AI Model
• Methodological Insights into Structural Causal Modelling and Uncertainty-Aware Forecasting for Economic Indicators
• Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
• Automated Evaluation of Gender Bias Across 13 Large Multimodal Models
• Lookup multivariate Kolmogorov-Arnold Networks
• Riemannian Batch Normalization: A Gyro Approach
• SVGauge: Towards Human-Aligned Evaluation for SVG Generation
• SoK: Security and Privacy of AI Agents for Blockchain
• Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study
• Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Models
• Measuring Uncertainty in Transformer Circuits with Effective Information Consistency
• DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge
• Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans
• Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings
• Cross-field SNR Analysis and Tensor Channel Estimation for Multi-UAV Near-field Communications
• Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities
• Association of Timing and Duration of Moderate-to-Vigorous Physical Activity with Cognitive Function and Brain Aging: A Population-Based Study Using the UK Biobank
• Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach
• Individualized and Interpretable Sleep Forecasting via a Two-Stage Adaptive Spatial-Temporal Model
• GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
• A Knowledge-Guided Cross-Modal Feature Fusion Model for Local Traffic Demand Prediction
• Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification
• Exploring Over-stationarization in Deep Learning-based Bus/Tram Arrival Time Prediction: Analysis and Non-stationary Effect Recovery
• RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use
• CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention
• FediLoRA: Heterogeneous LoRA for Federated Multimodal Fine-tuning under Missing Modalities
• CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis
• FusWay: Multimodal hybrid fusion approach. Application to Railway Defect Detection
• Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detection
• The Protocol Genome A Self Supervised Learning Framework from DICOM Headers
• Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
• Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories
• ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code
• Computational Concept of the Psyche
• Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Models
• Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity
• Autonomous Code Evolution Meets NP-Completeness
• Language Self-Play For Data-Free Training
• SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection
• Towards explainable decision support using hybrid neural models for logistic terminal automation
• Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
• Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment
• DeepGraphLog for Layered Neurosymbolic AI
• Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
• FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support
• RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning
• BDPM: A Machine Learning-Based Feature Extractor for Parkinson's Disease Classification via Gut Microbiota Analysis
• The Carbon Footprint Wizard: A Knowledge-Augmented AI Interface for Streamlining Food Carbon Footprint Analysis
• Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
• Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
• SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs
• CP-Model-Zoo: A Natural Language Query System for Constraint Programming Models
• HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?
• Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare
• Estimating forest carbon stocks from high-resolution remote sensing imagery by reducing domain shift with style transfer
• VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving
• Renewable Energy Sources Selection Analysis with the Maximizing Deviation Method
• From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
• Statistical Methods in Generative AI
• Instruction Agent: Enhancing Agent with Expert Demonstration
• Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis
• Autoencoder-Based Denoising of Muscle Artifacts in ECG to Preserve Skin Nerve Activity (SKNA) for Cognitive Stress Detection
• PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning
• That's So FETCH: Fashioning Ensemble Techniques for LLM Classification in Civil Legal Intake and Referral
• A Hybrid CNN-LSTM Deep Learning Model for Intrusion Detection in Smart Grid
• BlendedNet: A Blended Wing Body Aircraft Dataset and Surrogate Model for Aerodynamic Predictions
• OmniAcc: Personalized Accessibility Assistant Using Generative AI
• HealthSLM-Bench: Benchmarking Small Language Models for Mobile and Wearable Healthcare Monitoring