AI Research News Feeds for November 5th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• 3D Point Cloud Object Detection on Edge Devices for Split Computing
• A Kullback-Leibler divergence method for input-system-state identification
• HAGI++: Head-Assisted Gaze Imputation and Generation
• SigmaCollab: An Application-Driven Dataset for Physically Situated Collaboration
• Resource-efficient Automatic Refinement of Segmentations via Weak Supervision from Light Feedback
• An unscented Kalman filter method for real time input-parameter-state estimation
• Robust Identity Perceptual Watermark Against Deepfake Face Swapping
• Training Convolutional Neural Networks with the Forward-Forward algorithm
• Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection
• Mobile Robotic Multi-View Photometric Stereo
• Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal
• RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
• 3DBonsai: Structure-Aware Bonsai Modeling Using Conditioned 3D Gaussian Splatting
• FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks
• Breaking Down Monocular Ambiguity: Exploiting Temporal Evolution for 3D Lane Detection
• GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
• GeoSDF: Plane Geometry Diagram Synthesis via Signed Distance Field
• Crucial-Diff: A Unified Diffusion Model for Crucial Image and Annotation Synthesis in Data-scarce Scenarios
• Light Future: Multimodal Action Frame Prediction via InstructPix2Pix
• A Practical Investigation of Spatially-Controlled Image Generation with Transformers
• Label tree semantic losses for rich multi-class medical image segmentation
• Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
• Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imaging
• The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs
• Large Language Models are Unreliable for Cyber Threat Intelligence
• Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
• Repetitions are not all alike: distinct mechanisms sustain repetition in language models
• Evolutionary Machine Learning meets Self-Supervised Learning: a comprehensive survey
• NMCSE: Noise-Robust Multi-Modal Coupling Signal Estimation Method via Optimal Transport for Cardiovascular Disease Detection
• OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data
• Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport
• DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging
• Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
• MediQ-GAN: Quantum-Inspired GAN for High Resolution Medical Image Generation
• Weakly Supervised Object Segmentation by Background Conditional Divergence
• AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
• Multi-Personality Generation of LLMs at Decoding-time
• Rethinking LLM Human Simulation: When a Graph is What You Need
• IG-Pruning: Input-Guided Block Pruning for Large Language Models
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw
• LiveSecBench: A Dynamic and Culturally-Relevant AI Safety Benchmark for LLMs in Chinese Context
• AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
• Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance
• Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas
• Smart-Hiring: An Explainable end-to-end Pipeline for CV Information Extraction and Job Matching
• The Analysis of Lexical Errors in Machine Translation from English into Romanian
• Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
• CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency
• The Realignment Problem: When Right becomes Wrong in LLMs
• Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis, Solution, and Interpretation
• PragExTra: A Multilingual Corpus of Pragmatic Explicitation in Translation
• AI Diffusion in Low Resource Language Countries
• Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
• Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
• Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities
• SciDaSynth: Interactive Structured Data Extraction from Scientific Literature with Large Language Model
• Complete asymptotic type-token relationship for growing complex systems with inverse power-law count rankings
• Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences
• InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance
• An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM
• SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
• Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions
• Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
• CoCoVa: Chain of Continuous Vision-Language Thought for Latent Space Reasoning
• DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
• UniChange: Unifying Change Detection with Multimodal Large Language Model
• The Collaboration Gap
• CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
• VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
• How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes
• Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs
• On Extending Direct Preference Optimization to Accommodate Ties
• I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
• ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
• Composing or Not Composing? Towards Distributional Construction Grammars
• The exponential distribution of the order of demonstrative, numeral, adjective and noun
• Mixture of Routers
• TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance
• Identifying Aspects in Peer Reviews
• Rethinking the Relationship between the Power Law and Hierarchical Structures
• Beyond the Link: Assessing LLMs' ability to Classify Political Content across Global Media
• ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
• Visual Program Distillation with Template-Based Augmentation
• Understanding and Optimizing Agentic Workflows via Shapley value
• SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
• iFlyBot-VLA Technical Report
• Challenging DINOv3 Foundation Model under Low Inter-Class Variability: A Case Study on Fetal Brain Ultrasound
• Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users
• Locally-Supervised Global Image Restoration
• Towards Selection of Large Multimodal Models as Engines for Burned-in Protected Health Information Detection in Medical Images
• StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities
• Text-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis
• Markerless Augmented Reality Registration for Surgical Guidance: A Multi-Anatomy Clinical Accuracy Study
• From Instance Segmentation to 3D Growth Trajectory Reconstruction in Planktonic Foraminifera
• Fast Measuring Pavement Crack Width by Cascading Principal Component Analysis
• Autobiasing Event Cameras for Flickering Mitigation
• Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models
• MM-UNet: Morph Mamba U-shaped Convolutional Networks for Retinal Vessel Segmentation
• Language-Enhanced Generative Modeling for PET Synthesis from MRI and Blood Biomarkers
• Object-Centric 3D Gaussian Splatting for Strawberry Plant Reconstruction and Phenotyping
• Estimation of Segmental Longitudinal Strain in Transesophageal Echocardiography by Deep Learning
• Can Foundation Models Revolutionize Mobile AR Sparse Sensing?
• Collaborative Attention and Consistent-Guided Fusion of MRI and PET for Alzheimer's Disease Diagnosis
• Monocular absolute depth estimation from endoscopy via domain-invariant feature learning and latent consistency
• Medical Report Generation: A Hierarchical Task Structure-Based Cross-Modal Causal Intervention Framework
• Are Euler angles a useful rotation parameterisation for pose estimation with Normalizing Flows?
• Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization
• GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection
• M3PD Dataset: Dual-view Photoplethysmography (PPG) Using Front-and-rear Cameras of Smartphones in Lab and Clinical Settings
• RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning
• A Novel Grouping-Based Hybrid Color Correction Algorithm for Color Point Clouds
• Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
• IllumFlow: Illumination-Adaptive Low-Light Enhancement via Conditional Rectified Flow and Retinex Decomposition
• ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension
• Synthetic Crop-Weed Image Generation and its Impact on Model Generalization
• From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics
• KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image
• MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer
• OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control
• Object Detection as an Optional Basis: A Graph Matching Network for Cross-View UAV Localization
• Adapting General-Purpose Foundation Models for X-ray Ptychography in Low-Data Regimes
• ESA: Energy-Based Shot Assembly Optimization for Automatic Video Editing
• Keeping it Local, Tiny and Real: Automated Report Generation on Edge Computing Devices for Mechatronic-Based Cognitive Systems
• LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization
• Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data
• The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic
• Seeing Across Time and Views: Multi-Temporal Cross-View Learning for Robust Video Person Re-Identification
• A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
• Zero-Shot Multi-Animal Tracking in the Wild
• Robust Face Liveness Detection for Biometric Authentication using Single Image
• Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
• Differentiable Hierarchical Visual Tokenization
• Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification
• VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
• LLEXICORP: End-user Explainability of Convolutional Neural Networks
• Dynamic Reflections: Probing Video Representations with Text Alignment
• PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing
• When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
• AI-Generated Image Detection: An Empirical Study and Future Research Directions
• PLUTO-4: Frontier Pathology Foundation Models
• Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
• Opto-Electronic Convolutional Neural Network Design Via Direct Kernel Optimization
• A Step Toward World Models: A Survey on Robotic Manipulation
• High-Resolution Magnetic Particle Imaging System Matrix Recovery Using a Vision Transformer with Residual Feature Network
• Enhancing Federated Learning Privacy with QUBO
• Can LLMs subtract numbers?
• Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning
• TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
• Assessing win strength in MLB win prediction models
• GeoCrossBench: Cross-Band Generalization for Remote Sensing
• In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
• Learning phases with Quantum Monte Carlo simulation cell
• Condition-Invariant fMRI Decoding of Speech Intelligibility with Deep State Space Model
• BondBERT: What we learn when assigning sentiment in the bond market
• CytoNet: A Foundation Model for the Human Cerebral Cortex
• Learned Cost Model for Placement on Reconfigurable Dataflow Hardware
• Effectiveness of High-Dimensional Distance Metrics on Solar Flare Time Series
• Affordable EEG, Actionable Insights: An Open Dataset and Evaluation Framework for Epilepsy Patient Stratification
• Mirror-Neuron Patterns in AI Alignment
• LGCC: Enhancing Flow Matching Based Text-Guided Image Editing with Local Gaussian Coupling and Context Consistency
• EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
• Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models
• Improving Bayesian inference in PTA data analysis: importance nested sampling with Normalizing Flows
• Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis II: Noise and SGWB inference through parameter decorrelation
• Stability of mixed-state phases under weak decoherence
• SEAL - A Symmetry EncourAging Loss for High Energy Physics
• Solving cold start in news recommendations: a RippleNet-based system for large scale media outlet
• Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications
• Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
• Optimizing Attention on GPUs by Exploiting GPU Architectural NUMA Effects
• DoFlow: Causal Generative Flows for Interventional and Counterfactual Time-Series Prediction
• Near Optimal Convergence to Coarse Correlated Equilibrium in General-Sum Markov Games
• ScenicProver: A Framework for Compositional Probabilistic Verification of Learning-Enabled Systems
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs
• PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks
• Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning
• Training Proactive and Personalized LLM Agents
• Optimizing Multi-Lane Intersection Performance in Mixed Autonomy Environments
• Structural Plasticity as Active Inference: A Biologically-Inspired Architecture for Homeostatic Control
• Demo: Statistically Significant Results On Biases and Errors of LLMs Do Not Guarantee Generalizable Results
• From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models
• Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
• Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
• An Automated Framework for Strategy Discovery, Retrieval, and Evolution in LLM Jailbreak Attacks
• Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation
• A new class of Markov random fields enabling lightweight sampling
• AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
• Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds
• MammoClean: Toward Reproducible and Bias-Aware AI in Mammography through Dataset Harmonization
• Arithmetic Circuits and Neural Networks for Regular Matroids
• An Adaptive Sampling Framework for Detecting Localized Concept Drift under Label Scarcity
• Learning CNF formulas from uniform random solutions in the local lemma regime
• Many-vs-Many Missile Guidance via Virtual Targets
• Agentic AI for Mobile Network RAN Management and Optimization
• Forecasting Future Anatomies: Longitudianl Brain Mri-to-Mri Prediction
• RIS-Assisted 3D Spherical Splatting for Object Composition Visualization using Detection Transformers
• TAUE: Training-free Noise Transplant and Cultivation Diffusion Model
• Redundancy Maximization as a Principle of Associative Memory Learning
• Verifying LLM Inference to Prevent Model Weight Exfiltration
• The stability of shallow neural networks on spheres: A sharp spectral analysis
• Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks
• RL-Aided Cognitive ISAC: Robust Detection and Sensing-Communication Trade-offs
• Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes
• Optimizing Kernel Discrepancies via Subset Selection
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning
• DANIEL: A Distributed and Scalable Approach for Global Representation Learning with EHR Applications
• Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
• Accelerated Frank-Wolfe Algorithms: Complementarity Conditions and Sparsity
• TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System
• Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything
• Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)
• Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
• Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
• Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
• Improving Uncertainty Estimation through Semantically Diverse Language Generation
• RASPNet: A Benchmark Dataset for Radar Adaptive Signal Processing Applications
• Feature compression is the root cause of adversarial fragility in neural network classifiers
• Link Prediction with Untrained Message Passing Layers
• Network Anomaly Traffic Detection via Multi-view Feature Fusion
• Lower-dimensional projections of cellular expression improves cell type classification from single-cell RNA sequencing
• Constrained Optimal Fuel Consumption of HEVs under Observational Noise
• Multiscale spatiotemporal heterogeneity analysis of bike-sharing system's self-loop phenomenon: Evidence from Shanghai
• MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
• LoLaFL: Low-Latency Federated Learning via Forward-only Propagation
• LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency
• UFGraphFR: Graph Federation Recommendation System based on User Text description features
• Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders
• Personalized Interpolation: Achieving Efficient Conversion Estimation with Flexible Optimization Windows
• Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
• Training Language Models to Reason Efficiently
• Universal Sequence Preconditioning
• Position: Bridge the Gaps between Machine Unlearning and AI Regulation
• Remasking Discrete Diffusion Models with Inference-Time Scaling
• Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization
• Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic
• Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
• Emergence and scaling laws in SGD learning of shallow neural networks
• AI-driven software for automated quantification of skeletal metastases and treatment response evaluation using Whole-Body Diffusion-Weighted MRI (WB-DWI) in Advanced Prostate Cancer
• Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
• Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
• Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning
• DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
• Strategic Classification with Non-Linear Classifiers
• From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
• Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit
• Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
• End-to-End Probabilistic Framework for Learning with Hard Constraints
• ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search
• Two-Player Zero-Sum Games with Bandit Feedback
• Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
• Modeling Hierarchical Spaces: A Review and Unified Framework for Surrogate-Based Architecture Design
• Aggregation of Published Non-Uniform Axial Power Data for Phase II of the OECD/NEA AI/ML Critical Heat Flux Benchmark
• Relational Causal Discovery with Latent Confounders
• Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate
• Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number
• A Compositional Kernel Model for Feature Learning
• Expertise and confidence explain how social influence evolves along intellective tasks
• Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates
• Testing with Non-identically Distributed Samples
• Cross-modal Diffusion Modelling for Super-resolved Spatial Transcriptomics
• Tracking solutions of time-varying variational inequalities
• Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey
• Language-Agnostic Modeling of Source Reliability on Wikipedia
• Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach
• Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
• Astromer 2
• Bayesian Optimization by Kernel Regression and Density-based Exploration
• Image Super-Resolution with Guarantees via Conformalized Generative Models
• Gradient GA: Gradient Genetic Algorithm for Drug Molecular Design
• Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms
• Towards efficient quantum algorithms for diffusion probabilistic models
• Rethinking Video Super-Resolution: Towards Diffusion-Based Methods without Motion Alignment
• FORTALESA: Fault-Tolerant Reconfigurable Systolic Array for DNN Inference
• Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?
• Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework
• MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
• Efficient Vector Symbolic Architectures from Histogram Recovery
• A Detailed Study on LLM Biases Concerning Corporate Social Responsibility and Green Supply Chains
• SmartMLOps Studio: Design of an LLM-Integrated IDE with Automated MLOps Pipelines for Model Development and Monitoring
• Trove: A Flexible Toolkit for Dense Retrieval
• Learning Complementary Policies for Human-AI Teams
• Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
• The Digital Ecosystem of Beliefs: does evolution favour AI over humans?
• Survey Transfer Learning: Recycling Data with Silicon Responses
• The Limits of AI Explainability: An Algorithmic Information Theory Approach
• LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
• CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
• Limits of Safe AI Deployment: Differentiating Oversight and Control
• Agentic Large Language Models for Conceptual Systems Engineering and Design
• Prevailing Research Areas for Music AI in the Era of Foundation Models
• FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMs
• Runtime Analysis of Evolutionary Algorithms for Multi-party Multi-objective Optimization
• Generative AI and Empirical Software Engineering: A Paradigm Shift
• HCT-QA: A Benchmark for Question Answering on Human-Centric Tables
• Memory Assisted LLM for Personalized Recommendation System
• In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledge
• Balancing Caregiving and Self-Care: Exploring Mental Health Needs of Alzheimer's and Dementia Caregivers
• PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
• A Collectivist, Economic Perspective on AI
• H-NeiFi: Non-Invasive and Consensus-Efficient Multi-Agent Opinion Guidance
• CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
• Retrieval-Augmented Multimodal Depression Detection
• The Eigenvalues Entropy as a Classifier Evaluation Measure
• Variational Geometry-aware Neural Network based Method for Solving High-dimensional Diffeomorphic Mapping Problems
• Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
• Neural Green's Functions
• DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
• Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model
• Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models
• Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
• Q-Sat AI: Machine Learning-Based Decision Support for Data Saturation in Qualitative Studies
• Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
• The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
• Learning a Distance for the Clustering of Patients with Amyotrophic Lateral Sclerosis
• COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy
• Interpretable Heart Disease Prediction via a Weighted Ensemble Model: A Large-Scale Study with SHAP and Surrogate Decision Trees
• EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory
• NeuroClean: A Generalized Machine-Learning Approach to Neural Time-Series Conditioning
• Bulk-boundary decomposition of neural networks
• TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
• Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
• Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance
• RobustFSM: Submodular Maximization in Federated Setting with Malicious Clients
• Predicting Microbial Interactions Using Graph Neural Networks
• Quantum-Enhanced Generative Models for Rare Event Prediction
• Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants
• Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
• A Dual-Use Framework for Clinical Gait Analysis: Attention-Based Sensor Optimization and Automated Dataset Auditing
• Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems
• Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models
• Energy Loss Functions for Physical Systems
• LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS
• Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling
• Uncertainty Guided Online Ensemble for Non-stationary Data Streams in Fusion Science
• Geometric Data Valuation via Leverage Scores
• Measuring the Intrinsic Dimension of Earth Representations
• Matrix Sensing with Kernel Optimal Loss: Robustness and Optimization Landscape
• Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits
• QuPCG: Quantum Convolutional Neural Network for Detecting Abnormal Patterns in PCG Signals
• Disentangling Causal Substructures for Interpretable and Generalizable Drug Synergy Prediction
• CFL: On the Use of Characteristic Function Loss for Domain Alignment in Machine Learning
• ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts
• Tackling Incomplete Data in Air Quality Prediction: A Bayesian Deep Learning Framework for Uncertainty Quantification
• OmniField: Conditioned Neural Fields for Robust Multimodal Spatiotemporal Learning
• Learning Interactive World Model for Object-Centric Reinforcement Learning
• Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
• Neural network initialization with nonlinear characteristics and information on spectral bias
• Probabilistic Graph Cuts
• Gradient-Variation Online Adaptivity for Accelerated Optimization with H\"older Smoothness
• Reinforcement learning based data assimilation for unknown state model
• Federated Quantum Kernel Learning for Anomaly Detection in Multivariate IoT Time-Series
• FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error
• The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
• Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning
• RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
• Learning A Universal Crime Predictor with Knowledge-guided Hypernetworks
• Reducing normalizing flow complexity for MCMC preconditioning
• Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition
• Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments
• LUMA-RAG: Lifelong Multimodal Agents with Provably Stable Streaming Alignment
• H-Infinity Filter Enhanced CNN-LSTM for Arrhythmia Detection from Heart Sound Recordings
• A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control
• Improving Unlearning with Model Updates Probably Aligned with Gradients
• Accounting for Underspecification in Statistical Claims of Model Superiority
• SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization
• NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers
• BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring
• Variational Geometric Information Bottleneck: Learning the Shape of Understanding
• An End-to-End Learning Approach for Solving Capacitated Location-Routing Problems
• Causal Graph Neural Networks for Healthcare
• Rawlsian many-to-one matching with non-linear utility
• Theoretical Guarantees for Causal Discovery on Large Random Graphs
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
• Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization
• Directional-Clamp PPO
• A Large Language Model for Corporate Credit Scoring
• Neural Network Interoperability Across Platforms
• A Non-Adversarial Approach to Idempotent Generative Modelling
• Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning
• Natural-gas storage modelling by deep reinforcement learning
• Apriel-H1: Towards Efficient Enterprise Reasoning Models
• Nesterov-Accelerated Robust Federated Learning Over Byzantine Adversaries
• In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
• Scalable Evaluation and Neural Models for Compositional Generalization
• Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
• Does Interpretability of Knowledge Tracing Models Support Teacher Decision Making?
• Calibration improves detection of mislabeled examples
• ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
• From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos
• VecComp: Vector Computing via MIMO Digital Over-the-Air Computation
• STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation
• Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
• GEPOC Parameters -- Open Source Parametrisation and Validation for Austria, Version 2.0
• Engineering.ai: A Platform for Teams of AI Engineers in Computational Design
• Incremental Selection of Most-Filtering Conjectures and Proofs of the Selected Conjectures
• Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities
• A Multimodal Framework for Depression Detection during Covid-19 via Harvesting Social Media: A Novel Dataset and Method
• GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
• Reimagining Safety Alignment with An Image
• Efficient Generation of Binary Magic Squares
• PreferThinker: Reasoning-based Personalized Image Preference Assessment
• Lifted Successor Generation in Numeric Planning
• Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
• Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence
• How Focused Are LLMs? A Quantitative Study via Repetitive Deterministic Prediction Tasks
• Count-Based Approaches Remain Strong: A Benchmark Against Transformer and LLM Pipelines on Structured EHR
• Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?
• AI for pRedicting Exacerbations in KIDs with aSthma (AIRE-KIDS)
• Knowledge Elicitation with Large Language Models for Interpretable Cancer Stage Identification from Pathology Reports
• Efficient Test-Time Retrieval Augmented Generation
• Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Models
• DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models
• MiRAGE: Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble Fusion
• QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
• Graph Neural Network-Based Semi-Supervised Open-Set Fault Diagnosis for Marine Machinery Systems
• llmSHAP: A Principled Approach to LLM Explainability
• OmniFuser: Adaptive Multimodal Fusion for Service-Oriented Predictive Maintenance
• Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework
• Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing
• Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
• Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering
• Modulation of temporal decision-making in a deep reinforcement learning agent under the dual-task paradigm
• Robust Multimodal Sentiment Analysis via Double Information Bottleneck
• From Passive to Proactive: A Multi-Agent System with Dynamic Task Orchestration for Intelligent Medical Pre-Consultation
• TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
• Analyzing Sustainability Messaging in Large-Scale Corporate Social Media
• ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks
• IVGAE-TAMA-BO: A novel temporal dynamic variational graph model for link prediction in global food trade networks with momentum structural memory and Bayesian optimization
• Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
• A Two Level Neural Approach Combining Off-Chip Prediction with Adaptive Prefetch Filtering
• Sorting by Strip Swaps is NP-Hard
• STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
• Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World
• RailEstate: An Interactive System for Metro Linked Property Trends
• Adding New Capability in Existing Scientific Application with LLM Assistance
• Digital Twin based Automatic Reconfiguration of Robotic Systems in Smart Environments
• Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System
• Artificial Intelligence in Elementary STEM Education: A Systematic Review of Current Applications and Future Challenges
• Real-DRL: Teach and Learn in Reality
• Inferring multiple helper Dafny assertions with LLMs
• End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection
• What a diff makes: automating code migration with large language models
• Effectiveness of LLMs in Temporal User Profiling for Recommendation
• Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
• Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
• Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits
• Emotion Detection in Speech Using Lightweight and Transformer-Based Models: A Comparative and Ablation Study
• Quantum Machine Unlearning: Foundations, Mechanisms, and Taxonomy
• Human-AI Programming Role Optimization: Developing a Personality-Driven Self-Determination Framework
• LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026
• DRIP: Defending Prompt Injection via De-instruction Training and Residual Fusion Model Architecture
• Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models
• A Multimodal Dataset for Indoor Radio Mapping with 3D Point Clouds and RSSI
• HIP-LLM: A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models
• On Improvisation and Open-Endedness: Insights for Experiential AI
• EPARA: Parallelizing Categorized AI Inference in Edge Clouds
• AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
• More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
• Lessons Learned from the Use of Generative AI in Engineering and Quality Assurance of a WEB System for Healthcare
• ShadowLogic: Backdoors in Any Whitebox LLM
• A Voice-Enabled Virtual Patient System for Interactive Training in Standardized Clinical Assessment
• FeNN-DMA: A RISC-V SoC for SNN acceleration
• EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference
• Quantifying truth and authenticity in AI-assisted candidate evaluation: A multi-domain pilot analysis
• Towards Ultra-Low Latency: Binarized Neural Network Architectures for In-Vehicle Network Intrusion Detection
• CodeClash: Benchmarking Goal-Oriented Software Engineering
• Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
• Fast Stochastic Greedy Algorithm for $k$-Submodular Cover Problem
• Dynamic Logic of Trust-Based Beliefs
• Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
• Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations
• HAFixAgent: History-Aware Automated Program Repair Agent
• AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
• A High-Throughput Spiking Neural Network Processor Enabling Synaptic Delay Emulation
• Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs
• Influence-aware Causal Autoencoder Network for Node Importance Ranking in Complex Networks
• Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
• Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
• Exploringand Unleashing the Power of Large Language Models in CI/CD Configuration Translation
• AI for Requirements Engineering: Industry adoption and Practitioner perspectives
• Embodied Cognition Augmented End2End Autonomous Driving
• Beyond Permissions: Investigating Mobile Personalization with Simulated Personas
• The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project
• AI Literacy in UAE Libraries: Assessing Competencies, Training Needs, and Ethical Considerations for the Digital Age
• FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths
• MO-SeGMan: Rearrangement Planning Framework for Multi Objective Sequential and Guided Manipulation in Constrained Environments
• Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models
• The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity
• Spin-Adapted Neural Network Wavefunctions in Real Space
• Student Engagement in AI Assisted Complex Problem Solving: A Pilot Study of Human AI Rubik's Cube Collaboration
• Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks
• SM-based Semantics for Answer Set Programs Containing Conditional Literals and Arithmetic
• Context-Guided Decompilation: A Step Towards Re-executability
• GenDexHand: Generative Simulation for Dexterous Hands