AI Research News Feeds for September 11th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Adversarial Attacks Against Automated Fact-Checking: A Survey
• Alternating Minimization Schemes for Computing Rate-Distortion-Perception Functions with $f$-Divergence Perception Constraints
• A Survey of World Models for Autonomous Driving
• Event Camera Meets Resource-Aware Mobile Computing: Abstraction, Algorithm, Acceleration, Application
• D\'ej\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
• Bias in the Loop: How Humans Evaluate AI-Generated Suggestions
• A transport approach to the cutoff phenomenon
• On the Sample Complexity of Set Membership Estimation for Linear Systems with Disturbances Bounded by Convex Sets
• Identification and Estimation of Simultaneous Equation Models Using Higher-Order Cumulant Restrictions
• RewardDance: Reward Scaling in Visual Generation
• SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video
• Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
• Physics-Guided Rectified Flow for Low-light RAW Image Enhancement
• Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
• CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretraining
• X-Part: high fidelity and structure coherent shape decomposition
• SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation
• Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning
• Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
• Vision Transformer with Sparse Scan Prior
• Have Large Vision-Language Models Mastered Art History?
• A Chinese Continuous Sign Language Dataset Based on Complex Environments
• ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions
• GloFinder: AI-empowered QuPath Plugin for WSI-level Glomerular Detection, Visualization, and Curation
• TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition
• F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration
• GNF: Gaussian Neural Fields for Multidimensional Signal Representation and Reconstruction
• Towards properties of adversarial image perturbations
• CamC2V: Context-aware Controllable Video Generation
• Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learning
• GenFlow: Interactive Modular System for Image Generation
• InsFusion: Rethink Instance-level LiDAR-Camera Fusion for 3D Object Detection
• Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
• VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
• Beyond Distribution Shifts: Adaptive Hyperspectral Image Classification at Test Time
• First-order State Space Model for Lightweight Image Super-resolution
• Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data
• Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
• HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
• ViewSparsifier: Killing Redundancy in Multi-View Plant Phenotyping
• Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
• Improving Greenland Bed Topography Mapping with Uncertainty-Aware Graph Learning on Sparse Radar Data
• EfficientIML: Efficient High-Resolution Image Manipulation Localization
• CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging
• AdsQA: Towards Advertisement Video Understanding
• LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation
• FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
• Multi-Modal Robust Enhancement for Coastal Water Segmentation: A Systematic HSV-Guided Framework
• Computational Imaging for Enhanced Computer Vision
• BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
• CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
• ArgoTweak: Towards Self-Updating HD Maps through Structured Priors
• Quantifying Accuracy of an Event-Based Star Tracker via Earth's Rotation
• Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matching
• GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
• DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts
• Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
• An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Cities
• Two Stage Context Learning with Large Language Models for Multimodal Stance Detection on Climate Change
• Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection
• Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing
• GTA-Crime: A Synthetic Dataset and Generation Framework for Fatal Violence Detection with Adversarial Snippet-Level Domain Adaptation
• Symmetry Interactive Transformer with CNN Framework for Diagnosis of Alzheimer's Disease Using Structural MRI
• EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning
• Hyperspectral Mamba for Hyperspectral Object Tracking
• Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features
• Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration
• Dual-Thresholding Heatmaps to Cluster Proposals for Weakly Supervised Object Detection
• An Open Benchmark Dataset for GeoAI Foundation Models for Oil Palm Mapping in Indonesia
• SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
• Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference
• AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs
• SciGPT: A Large Language Model for Scientific Literature Understanding and Knowledge Discovery
• No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models
• Culturally transmitted color categories in LLMs reflect a learning bias toward efficient compression
• MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder and LLM Fusion
• Verbalized Algorithms
• Towards Knowledge-Aware Document Systems: Modeling Semantic Coverage Relations via Answerability Detection
• CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework
• Acquiescence Bias in Large Language Models
• Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text
• Too Helpful, Too Harmless, Too Honest or Just Right?
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models
• LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge
• Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
• Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
• Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
• Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora
• Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles
• Baba Is AI: Break the Rules to Beat the Benchmark
• TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
• MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision
• REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction
• Maximizing Information in Domain-Invariant Representation Improves Transfer Learning
• Damped Proximal Augmented Lagrangian Method for weakly-Convex Problems with Convex Constraints
• A single-loop SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization
• Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operators
• Reward function compression facilitates goal-dependent reinforcement learning
• Gaussian Process Regression -- Neural Network Hybrid with Optimized Redundant Coordinates
• Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
• Calibrating Transformers via Sparse Gaussian Processes
• Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
• MDDM: A Molecular Dynamics Diffusion Model to Predict Particle Self-Assembly
• Investigating Compositional Reasoning in Time Series Foundation Models
• Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
• Task-based Loss Functions in Computer Vision: A Comprehensive Review
• Training Deep Morphological Neural Networks as Universal Approximators
• Data-driven generative simulation of SDEs using diffusion models
• ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System
• PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
• Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
• ADHDeepNet From Raw EEG to Diagnosis: Improving ADHD Diagnosis through Temporal-Spatial Processing, Adaptive Attention Mechanisms, and Explainability in Raw EEG Signals
• A Survey of TinyML Applications in Beekeeping for Hive Monitoring and Management
• STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery
• Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
• Forecasting Generative Amplification
• SCA-LLM: Spectral-Attentive Channel Prediction with Large Language Models in MIMO-OFDM
• Bias after Prompting: Persistent Discrimination in Large Language Models
• Generative Quasi-Continuum Modeling of Confined Fluids at the Nanoscale
• RepViT-CXR: A Channel Replication Strategy for Vision Transformers in Chest X-ray Tuberculosis and Pneumonia Classification
• LLM-Guided Ans\"atze Design for Quantum Circuit Born Machines in Financial Generative Modeling
• LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations
• Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
• Compressing CNN models for resource-constrained systems by channel and layer pruning
• Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
• Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation
• The Domain Mixed Unit: A New Neural Arithmetic Layer
• Selective Induction Heads: How Transformers Select Causal Structures In Context
• ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
• Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
• Adaptive Rainfall Forecasting from Multiple Geographical Models Using Matrix Profile and Ensemble Learning
• EvolKV: Evolutionary KV Cache Compression for LLM Inference
• Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
• Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
• An Interpretable Deep Learning Model for General Insurance Pricing
• SHAining on Process Mining: Explaining Event Log Characteristics Impact on Algorithms
• Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
• Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
• Towards Interpretable Deep Neural Networks for Tabular Data
• Generative Data Refinement: Just Ask for Better Data
• Replicable Reinforcement Learning with Linear Function Approximation
• Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping
• Stopping Criteria for Value Iteration on Concurrent Stochastic Reachability and Safety Games
• Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations
• From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense Against DoS Attacks in UAV Swarm Networks
• VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents
• A Nonlinear Low-rank Representation Model with Convolutional Neural Network for Imputing Water Quality Data
• Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
• CyberRAG: An Agentic RAG cyber attack classification and reporting tool
• Comprehensive Evaluation of Prototype Neural Networks
• Hammer and Anvil: A Principled Defense Against Backdoors in Federated Learning
• In-Context Learning Enhanced Credibility Transformer
• MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs
• FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models
• A Transformer approach for Electricity Price Forecasting
• Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study
• QR-VC: Leveraging Quantization Residuals for Linear Disentanglement in Zero-Shot Voice Conversion
• Traffic-Rule-Compliant Trajectory Repair via Satisfiability Modulo Theories and Reachability Analysis
• Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
• CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning
• MPO: Boosting LLM Agents with Meta Plan Optimization
• To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging
• LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
• VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making
• A decision-theoretic approach to dealing with uncertainty in quantum mechanics
• Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
• TerraMind: Large-Scale Generative Multimodality for Earth Observation
• CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
• Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
• Prior Prompt Engineering for Reinforcement Fine-Tuning
• Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
• Explainability of CNN Based Classification Models for Acoustic Signal
• X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
• Learning Turbulent Flows with Generative Models: Super-resolution, Forecasting, and Sparse Flow Reconstruction
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
• Using AI to Optimize Patient Transfer and Resource Utilization During Mass-Casualty Incidents: A Simulation Platform
• An End-to-End Deep Learning Framework for Arsenicosis Diagnosis Using Mobile-Captured Skin Images
• PianoVAM: A Multimodal Piano Performance Dataset
• Scaling Truth: The Confidence Paradox in AI Fact-Checking
• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
• A Survey of Reinforcement Learning for Large Reasoning Models
• Associative Knowledge Graphs for Efficient Sequence Storage and Retrieval
• Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research
• PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
• Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
• Toward Subtrait-Level Model Explainability in Automated Writing Evaluation
• <think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
• An Iterative LLM Framework for SIBT utilizing RAG-based Adaptive Weight Optimization
• Spherical Brownian Bridge Diffusion Models for Conditional Cortical Thickness Forecasting
• Prompt-Driven Image Analysis with Multimodal Generative AI: Detection, Segmentation, Inpainting, and Interpretation
• Send to which account? Evaluation of an LLM-based Scambaiting System
• HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
• Variational Rank Reduction Autoencoders for Generative
• Agents of Discovery
• Interpretability as Alignment: Making Internal Understanding a Design Principle
• Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications
• Classification of 24-hour movement behaviors from wrist-worn accelerometer data: from handcrafted features to deep learning techniques
• UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation
• Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
• Performance Assessment Strategies for Generative AI Applications in Healthcare
• APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
• Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography
• From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital
• Diffusion-Guided Multi-Arm Motion Planning
• Quadrotor Navigation using Reinforcement Learning with Privileged Information
• XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols
• Accelerating AI Development with Cyber Arenas
• Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units
• Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization
• Combined-distance-based score function of cognitive fuzzy sets and its application in lung cancer pain evaluation
• A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving
• Segment Transformer: AI-Generated Music Detection via Music Structural Analysis
• Game-Theoretic Resilience Framework for Cyber-Physical Microgrids using Multi-Agent Reinforcement Learning
• Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing
• Retrieval-Augmented VLMs for Multimodal Melanoma Diagnosis
• EnvX: Agentize Everything with Agentic AI
• Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI
• Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
• Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
• Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
• No-Knowledge Alarms for Misaligned LLMs-as-Judges
• Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference
• The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems
• Narrative-Guided Reinforcement Learning: A Platform for Studying Language Model Influence on Decision Making
• ToDMA: Large Model-Driven Token-Domain Multiple Access for Semantic Communications
• Expert-Guided Explainable Few-Shot Learning for Medical Image Diagnosis
• A New Dataset and Benchmark for Grounding Multimodal Misinformation
• The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
• Measuring and mitigating overreliance is necessary for building human-compatible AI
• Validation of a CT-brain analysis tool for measuring global cortical atrophy in older patient cohorts
• MVPBench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
• NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment