AI Research News Feeds for September 18th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Large Language Models for Information Retrieval: A Survey
• Physics-informed, boundary-constrained Gaussian process regression for the reconstruction of fluid flow fields
• Field of View Enhanced Signal Dependent Binauralization with Mixture of Experts Framework for Continuous Source Motion
• Imputation-Powered Inference
• Holdout cross-validation for large non-Gaussian covariance matrix estimation using Weingarten calculus
• Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification
• Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
• Effort-Optimized, Accuracy-Driven Labelling and Validation of Test Inputs for DL Systems: A Mixed-Integer Linear Programming Approach
• Synthesis and Perceptual Scaling of High Resolution Naturalistic Images Using Stable Diffusion
• Scattering approach to diffusion quantifies axonal damage in brain injury
• Robust Shape Regularity Criteria for Superpixel Evaluation
• SCALP: Superpixels with Contour Adherence using Linear Path
• PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimation
• GROOD: GRadient-Aware Out-of-Distribution Detection
• Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks
• Brain age identification from diffusion MRI synergistically predicts neurodegenerative disease
• Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data
• UniPLV: Towards Label-Efficient Open-World 3D Scene Understanding by Regional Visual Language Supervision
• Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images
• Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions
• CROP: Contextual Region-Oriented Visual Token Pruning
• GenExam: A Multidisciplinary Text-to-Image Exam
• 3D Reconstruction of Coronary Vessel Trees from Biplanar X-Ray Images Using a Geometric Approach
• Autonomous Reporting of Normal Chest X-rays by Artificial Intelligence in the United Kingdom. Can We Take the Human Out of the Loop?
• Semantic 3D Reconstructions with SLAM for Central Airway Obstruction
• Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT
• Object Pose Estimation through Dexterous Touch
• Rest2Visual: Predicting Visually Evoked fMRI from Resting-State Scans
• InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap
• MetricNet: Recovering Metric Scale in Generative Navigation Policies
• MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping
• Texture-Aware Superpixel Segmentation
• Superpixel-based Color Transfer
• Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
• VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement
• AD-DINOv3: Enhancing DINOv3 for Zero-Shot Anomaly Detection with Anomaly-Aware Calibration
• Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
• CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Experts
• Generative AI for Misalignment-Resistant Virtual Staining to Accelerate Histopathology Workflows
• Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection
• MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
• An Exploratory Study on Abstract Images and Visual Representations Learned from Them
• BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
• Cin\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark
• Distractor-Aware Memory-Based Visual Object Tracking
• Invisible Yet Detected: PelFANet with Attention-Guided Anatomical Fusion for Pelvic Fracture Diagnosis
• EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View
• White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation
• Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
• Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
• Noise-Level Diffusion Guidance: Well Begun is Half Done
• Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation
• Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environments
• SAIL-VL2 Technical Report
• PROFUSEme: PROstate Cancer Biochemical Recurrence Prediction via FUSEd Multi-modal Embeddings
• Task-Aware Image Signal Processor for Advanced Visual Perception
• NDLPNet: A Location-Aware Nighttime Deraining Network and a Real-World Benchmark Dataset
• VocSegMRI: Multimodal Learning for Precise Vocal Tract Segmentation in Real-time MRI
• Generative Image Coding with Diffusion Prior
• AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
• Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization
• CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
• SWA-PF: Semantic-Weighted Adaptive Particle Filter for Memory-Efficient 4-DoF UAV Localization in GNSS-Denied Environments
• Masked Feature Modeling Enhances Adaptive Segmentation
• Data-Efficient Spectral Classification of Hyperspectral Data Using MiniROCKET and HDC-MiniROCKET
• Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
• EDITS: Enhancing Dataset Distillation with Implicit Textual Semantics
• Federated Learning for Deforestation Detection: A Distributed Approach with Satellite Imagery
• Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction
• FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras
• Taylor-Series Expanded Kolmogorov-Arnold Network for Medical Imaging Classification
• StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models
• UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
• Improving Generalized Visual Grounding with Instance-aware Joint Learning
• Cross-modal Full-mode Fine-grained Alignment for Text-to-Image Person Retrieval
• Controllable-Continuous Color Editing in Diffusion Model via Color Mapping
• Iterative Prompt Refinement for Safer Text-to-Image Generation
• Semantic-Enhanced Cross-Modal Place Recognition for Robust Robot Localization
• Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
• MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes
• LivePyxel: Accelerating image annotations with a Python-integrated webcam live streaming
• DEFT-VTON: Efficient Virtual Try-On with Consistent Generalised H-Transform
• Adversarial Appearance Learning in Augmented Cityscapes for Pedestrian Recognition in Autonomous Driving
• FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation
• Multimodal Hate Detection Using Dual-Stream Graph Neural Networks
• MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM
• A Generalization of CLAP from 3D Localization to Image Processing, A Connection With RANSAC & Hough Transforms
• SAMIR, an efficient registration framework via robust feature learning from SAM
• An Attention-Based Denoising Framework for Personality Detection in Social Media Texts
• KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction
• Research on Expressway Congestion Warning Technology Based on YOLOv11-DIoU and GRU-Attention
• Parking Space Ground Truth Test Automation by Artificial Intelligence Using Convolutional Neural Networks
• Real-Time Detection and Tracking of Foreign Object Intrusions in Power Systems via Feature-Based Edge Intelligence
• SCRum-9: Multilingual Stance Classification over Rumours on Social Media
• Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
• FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging
• A Culturally-diverse Multilingual Multimodal Video Benchmark & Model
• Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers
• MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
• KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models
• Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
• LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
• Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics
• What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs
• ClonEval: An Open Voice Cloning Benchmark
• CAMEO: Collection of Multilingual Emotional Speech Corpora
• From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
• Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
• An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
• CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI
• Annotating Satellite Images of Forests with Keywords from a Specialized Corpus in the Context of Change Detection
• Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
• Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection
• Enhancing Time Awareness in Generative Recommendation
• A TRRIP Down Memory Lane: Temperature-Based Re-Reference Interval Prediction For Instruction Caching
• When Avatars Have Personality: Effects on Engagement and Communication in Immersive Medical Training
• GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing
• NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities
• Contextual modulation of language comprehension in a dynamic neural model of lexical meaning
• Findings of the Third Automatic Minuting (AutoMin) Challenge
• Large Language Models Discriminate Against Speakers of German Dialects
• Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs
• Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
• Early Stopping Chain-of-thoughts in Large Language Models
• Audio-Based Crowd-Sourced Evaluation of Machine Translation Quality
• Enhancing Multi-Agent Debate System Performance via Confidence Expression
• Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
• CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset
• AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
• Framing Migration: A Computational Analysis of UK Parliamentary Discourse
• Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs
• Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning
• Overview of Dialog System Evaluation Track: Dimensionality, Language, Culture and Safety at DSTC 12
• Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives?
• Integrating Text and Time-Series into (Large) Language Models to Predict Medical Outcomes
• DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning
• Implementing a Logical Inference System for Japanese Comparatives
• Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages
• Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
• Zero-Knowledge Proofs in Sublinear Space
• Soft Graph Transformer for MIMO Detection
• CoVariance Filters and Neural Networks over Hilbert Spaces
• Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learning
• Learning Multimodal Attention for Manipulating Deformable Objects with Changing States
• Backdoor Attacks on Transformers for Tabular Data: An Empirical Study
• Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs
• Global Search for Optimal Low Thrust Spacecraft Trajectories using Diffusion Models and the Indirect Method
• Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
• Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
• Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
• Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
• Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
• Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain
• Predicting O-GlcNAcylation Sites in Mammalian Proteins with Transformers and RNNs Trained with a New Loss Function
• Data-Efficient Sleep Staging with Synthetic Time Series Pretraining
• Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
• DRDT3: Diffusion-Refined Decision Test-Time Training Model
• Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning
• Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients
• BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
• Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning
• Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation
• SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
• Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
• Artificial neural networks ensemble methodology to predict significant wave height
• Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics
• NIRVANA: Structured pruning reimagined for large language models compression
• Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
• LLM Chatbot-Creation Approaches
• Maximizing UAV Cellular Connectivity with Reinforcement Learning for BVLoS Path Planning
• A novel approach of day-ahead cooling load prediction and optimal control for ice-based thermal energy storage (TES) system in commercial buildings
• Valuation of Exotic Options and Counterparty Games Based on Conditional Diffusion
• A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction
• TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates
• APFEx: Adaptive Pareto Front Explorer for Intersectional Fairness
• eXtended Physics Informed Neural Network Method for Fracture Mechanics Problems
• Deep Learning-Driven Peptide Classification in Biological Nanopores
• Online Bayesian Risk-Averse Reinforcement Learning
• Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques
• Breaking the Cycle of Incarceration With Targeted Mental Health Outreach: A Case Study in Machine Learning for Public Policy
• TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
• Multimodal signal fusion for stress detection using deep neural networks: a novel approach for converting 1D signals to unified 2D images
• LLM-I: LLMs are Naturally Interleaved Multimodal Creators
• Sequential Data Augmentation for Generative Recommendation
• Controllable Pareto Trade-off between Fairness and Accuracy
• RF-LSCM: Pushing Radiance Fields to Multi-Domain Localized Statistical Channel Modeling for Cellular Network Optimization
• A Conformal Prediction Framework for Uncertainty Quantification in Physics-Informed Neural Networks
• ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
• Floating-Body Hydrodynamic Neural Networks
• Hybrid Quantum-Classical Neural Networks for Few-Shot Credit Risk Assessment
• An End-to-End Differentiable, Graph Neural Network-Embedded Pore Network Model for Permeability Prediction
• An Analysis of Optimizer Choice on Energy Efficiency and Performance in Neural Network Training
• Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection
• Privacy-Aware In-Context Learning for Large Language Models
• Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation
• Direct Video-Based Spatiotemporal Deep Learning for Cattle Lameness Detection
• Evolution Meets Diffusion: Efficient Neural Architecture Generation
• Using LLMs in Generating Design Rationale for Software Architecture Decisions
• Defending against Indirect Prompt Injection by Instruction Detection
• Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data
• Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies
• EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
• LLM-ABBA: Understanding time series via symbolic approximation
• Beyond checkmate: exploring the creative chokepoints in AI text
• A Deep Learning Pipeline for Solid Waste Detection in Remote Sensing Images
• Gemstones: A Model Suite for Multi-Faceted Scaling Laws
• Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon
• A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare
• CoPL: Collaborative Preference Learning for Personalizing LLMs
• CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
• COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing
• Conformal Temporal Logic Planning using Large Language Models
• Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
• Self-adaptive weights based on balanced residual decay rate for physics-informed neural networks and deep operator networks
• Towards Unified and Adaptive Cross-Domain Collaborative Filtering via Graph Signal Processing
• xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
• DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing
• TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning
• Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs
• Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
• A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
• Language models' activations linearly encode training-order recency
• Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
• Designing AI-Agents with Personalities: A Psychometric Approach
• Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation
• Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
• Large Language Models' Reasoning Stalls: An Investigation into the Capabilities of Frontier Models
• An Empirical Study on Failures in Automated Issue Solving
• LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology
• Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
• MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
• You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
• Prompt2Auto: From Motion Prompt to Automated Control via Geometry-Invariant One-Shot Gaussian Process Learning
• Comprehensive Evaluation of CNN-Based Audio Tagging Models on Resource-Constrained Devices
• Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
• Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
• Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation
• Towards a Physics Foundation Model
• Understanding the Process of Human-AI Value Alignment
• Masked Diffusion Models as Energy Minimization
• Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification
• FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
• Do Large Language Models Understand Word Senses?
• Ensemble of Pre-Trained Models for Long-Tailed Trajectory Prediction
• DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models
• Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation
• AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation
• Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations
• CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion
• DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
• Automated Triaging and Transfer Learning of Incident Learning Safety Reports Using Large Language Representational Models
• Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
• BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
• GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?
• Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
• DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring
• ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors
• Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation
• TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning
• Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents
• Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
• Secure, Scalable and Privacy Aware Data Strategy in Cloud
• DeepLogit: A sequentially constrained explainable deep learning modeling approach for transport policy analysis
• Uncovering AI Governance Themes in EU Policies using BERTopic and Thematic Analysis
• Landcover classification and change detection using remote sensing and machine learning: a case study of Western Fiji
• A Domain Knowledge Informed Approach for Anomaly Detection of Electric Vehicle Interior Sounds
• The Intercepted Self: How Generative AI Challenges the Dynamics of the Relational Self
• TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models
• The threat of analytic flexibility in using large language models to simulate human data: A call to attention
• EdiVal-Agent: An Object-Centric Framework for Automated, Scalable, Fine-Grained Evaluation of Multi-Turn Editing
• Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
• An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software
• Prompt2DAG: A Modular Methodology for LLM-Based Data Enrichment Pipeline Generation
• Reproducible workflow for online AI in digital health
• Joint data imputation and mechanistic modelling for simulating heart-brain interactions in incomplete datasets
• Prognosis of COVID-19 using Artificial Intelligence: A Systematic Review and Meta-analysis
• Dual Actor DDPG for Airborne STAR-RIS Assisted Communications
• Explainable AI-Enhanced Supervisory Control for High-Precision Spacecraft Formation
• Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
• Real World Robotic Exploration using Deep Neural Networks Trained in Photorealistic Reconstructed Environments
• Accuracy Paradox in Large Language Models: Regulating Hallucination Risks in Generative AI
• Evaluating undergraduate mathematics examinations in the era of generative AI: a curriculum-level case study
• The Provenance Problem: LLMs and the Breakdown of Citation Norms
• Generative AI Pipeline for Interactive Prompt-driven 2D-to-3D Vascular Reconstruction for Fontan Geometries from Contrast-Enhanced X-Ray Fluoroscopy Imaging
• $Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation
• The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs
• SteeringControl: Holistic Evaluation of Alignment Steering in LLMs
• AI Agents with Human-Like Collaborative Tools: Adaptive Strategies for Enhanced Problem-Solving
• Programmable Cognitive Bias in Social Agents
• See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
• InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management
• MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
• An Exhaustive DPLL Approach to Model Counting over Integer Linear Constraints with Simplification Techniques
• Exploring Major Transitions in the Evolution of Biological Cognition With Artificial Neural Networks
• Evaluation Awareness Scales Predictably in Open-Weights Large Language Models
• FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
• Position: AI Safety Must Embrace an Antifragile Perspective
• Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
• Agentic UAVs: LLM-Driven Autonomy with Integrated Tool-Calling and Cognitive Reasoning