AI Research News Feeds for August 29th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• TGOSPA Metric Parameters Selection and Evaluation for Visual Multi-object Tracking
• A multimodal dataset for understanding the impact of mobile phones on remote online virtual education
• SMARTe-VR: Student Monitoring and Adaptive Response Technology for e-Learning in Virtual Reality
• HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation
• Pixel Motion as Universal Representation for Robot Control
• TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
• Latent Factor Point Processes for Patient Representation in Electronic Health Records
• Extreme Learning Machine for the Characterization of Anomalous Diffusion from Single Trajectories (AnDi-ELM)
• Bounds in Wasserstein Distance for Locally Stationary Processes
• A Metropolis-Adjusted Langevin Algorithm for Sampling Jeffreys Prior
• OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
• First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge
• LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty
• A Machine Learning Approach to Volumetric Computations of Solid Pulmonary Nodules
• Efficient and Privacy-Protecting Background Removal for 2D Video Streaming using iPhone 15 Pro Max LiDAR
• Federated Learning for Large Models in Medical Imaging: A Comprehensive Review
• Prediction of Distant Metastasis for Head and Neck Cancer Patients Using Multi-Modal Tumor and Peritumoral Feature Fusion Network
• GENRE-CMR: Generalizable Deep Learning for Diverse Multi-Domain Cardiac MRI Reconstruction
• Efficient Fine-Tuning of DINOv3 Pretrained on Natural Images for Atypical Mitotic Figure Classification in MIDOG 2025
• VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
• ZIM: Zero-Shot Image Matting for Anything
• CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs
• T-Stars-Poster: A Framework for Product-Centric Advertising Image Design
• Language-to-Space Programming for Training-Free 3D Visual Grounding
• L2RW+: A Comprehensive Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
• WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
• GeoTexBuild: 3D Building Model Generation from Map Footprints
• RSRNav: Reasoning Spatial Relationship for Image-Goal Navigation
• When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
• Leadership Assessment in Pediatric Intensive Care Unit Team Training
• Robust ID-Specific Face Restoration via Alignment Learning
• A multi-task neural network for atypical mitosis recognition under domain shift
• MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
• CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
• Multi-View 3D Point Tracking
• Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
• Adapting Foundation Model for Dental Caries Detection with Dual-View Co-Training
• FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning
• Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
• PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification
• PathMR: Multimodal Visual Reasoning for Interpretable Pathology Diagnosis
• Deep Learning Framework for Early Detection of Pancreatic Cancer Using Multi-Modal Medical Imaging Analysis
• Understanding and evaluating computer vision models through the lens of counterfactuals
• To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software
• Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation
• Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement
• COMETH: Convex Optimization for Multiview Estimation and Tracking of Humans
• Olive Tree Satellite Image Segmentation Based On SAM and Multi-Phase Refinement
• E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
• DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
• Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation
• POSE: Phased One-Step Adversarial Equilibrium for Video Diffusion Models
• Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
• Mitosis detection in domain shift scenarios: a Mamba-based approach
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
• IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection
• Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent
• DCFS: Continual Test-Time Adaptation via Dual Consistency of Feature and Sample
• Adam SLAM - the last mile of camera calibration with 3DGS
• Learning What is Worth Learning: Active and Sequential Domain Adaptation for Multi-modal Gross Tumor Volume Segmentation
• Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection
• Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset
• Domain Adaptation Techniques for Natural and Medical Image Classification
• Contrastive Learning through Auxiliary Branch for Video Object Detection
• GLaRE: A Graph-based Landmark Region Embedding Network for Emotion Recognition
• FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models
• UTA-Sign: Unsupervised Thermal Video Augmentation via Event-Assisted Traffic Signage Sketching
• Disruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
• Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion
• Optimization-Based Calibration for Intravascular Ultrasound Volume Reconstruction
• Physics Informed Generative Models for Magnetic Field Images
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
• EmoCAST: Emotional Talking Portrait via Emotive Text Description
• Mask-Guided Multi-Channel SwinUNETR Framework for Robust MRI Classification
• AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Images
• CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
• "Humor, Art, or Misinformation?": A Multimodal Dataset for Intent-Aware Synthetic Image Detection
• Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network
• CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Network
• Mix, Align, Distil: Reliable Cross-Domain Atypical Mitosis Classification
• Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning
• Relative Drawing Identification Complexity is Invariant to Modality in Vision-Language Models
• SDiFL: Stable Diffusion-Driven Framework for Image Forgery Localization
• Enhancing Automatic Modulation Recognition With a Reconstruction-Driven Vision Transformer Under Limited Labels
• InfinityHuman: Towards Long-Term Audio-Driven Human
• Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos
• ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems
• Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)
• MedFoundationHub: A Lightweight and Secure Toolkit for Deploying Medical Vision Language Foundation Models
• Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction
• Audio-Guided Visual Editing with Complex Multi-Modal Prompts
• More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning
• Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection
• MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection
• A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection
• Re-Densification Meets Cross-Scale Propagation: Real-Time Compression of LiDAR Point Clouds
• Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
• Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation
• Towards Inclusive Communication: A Unified LLM-Based Framework for Sign Language, Lip Movements, and Audio Understanding
• Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
• STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment
• Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
• An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs
• Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm
• A Unified Theory of Language
• Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
• Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
• Improving Alignment in LVLMs with Debiased Self-Judgment
• Leveraging Large Language Models for Generating Research Topic Ontologies: A Multi-Disciplinary Study
• Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
• ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
• LGDE: Local Graph-based Dictionary Expansion
• Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
• Explaining word embeddings with perfect fidelity: Case study in research impact prediction
• Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
• Improving the quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics
• Are formal and functional linguistic mechanisms dissociated in language models?
• SaRoHead: Detecting Satire in a Multi-Domain Romanian News Headline Dataset
• Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
• DART: Distilling Autoregressive Reasoning to Silent Thought
• Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
• Integrating SystemC TLM into FMI 3.0 Co-Simulations with an Open-Source Approach
• Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities
• Joint Enhancement of Relational Reasoning for Long-Context LLMs
• CAPE: Context-Aware Personality Evaluation Framework for Large Language Models
• UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools
• KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
• CAMB: A comprehensive industrial LLM benchmark on civil aviation maintenance
• Searching the Title of Practical Work of the Informatics Engineering Bachelor Program with the Case Base Reasoning Method
• MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
• Prediction of mortality and resource utilization in critical care: a deep learning approach using multimodal electronic health records with natural language processing techniques
• ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety
• SciTopic: Enhancing Topic Discovery in Scientific Literature through Advanced LLM
• Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search
• KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling
• Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning
• Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
• rStar2-Agent: Agentic Reasoning Technical Report
• Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees
• Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets
• GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
• Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessions
• GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction
• MSRS: Evaluating Multi-Source Retrieval-Augmented Generation
• The Uneven Impact of Post-Training Quantization in Machine Translation
• SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
• How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\tau$-bench
• Transformers Meet In-Context Learning: A Universal Approximation Theory
• Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models
• Prediction of Local Failure after Stereotactic Radiotherapy in Melanoma Brain Metastases Using Ensemble Learning on Clinical, Dosimetric, and Radiomic Data
• Improving Fine-Grained Control via Aggregation of Multiple Diffusion Models
• ADAGE: Active Defenses Against GNN Extraction
• Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
• Molecular Machine Learning in Chemical Process Design
• Studying Effective String Theory using deep generative models
• OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
• Efficient Large-Scale Cross-Domain Sequential Recommendation with Dynamic State Representations
• FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
• Unlearning Concepts from Text-to-Video Diffusion Models
• LASE: Learned Adjacency Spectral Embeddings
• CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting
• Gradual Domain Adaptation for Graph Learning
• Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schr\"odinger Equation
• Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification
• Phase Transitions between Accuracy Regimes in L2 regularized Deep Neural Networks
• VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
• Physics-Constrained Machine Learning for Chemical Engineering
• Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach
• Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
• cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
• Practical Physical Layer Authentication for Mobile Scenarios Using a Synthetic Dataset Enhanced Deep Learning Approach
• Turning Tabular Foundation Models into Graph Foundation Models
• Evaluating LLMs on microservice-based applications: how complex is your specification?
• Spatio-Temporal Pruning for Compressed Spiking Large Language Models
• MicroLad: 2D-to-3D Microstructure Reconstruction and Generation via Latent Diffusion and Score Distillation
• Grounding Multimodal Large Language Models with Quantitative Skin Attributes: A Retrieval Study
• Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
• ELIXIR: Efficient and LIghtweight model for eXplaIning Recommendations
• CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference
• Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Setting
• QTMRL: An Agent for Quantitative Trading Decision-Making Based on Multi-Indicator Guided Reinforcement Learning
• Enhancing Corpus Callosum Segmentation in Fetal MRI via Pathology-Informed Domain Randomization
• BiListing: Modality Alignment for Listings
• Rethinking Transformer Connectivity: TLinFormer, A Path to Exact, Full Context-Aware Linear Attention
• Structure-aware Hypergraph Transformer for Diagnosis Prediction in Electronic Health Records
• Khiops: An End-to-End, Frugal AutoML and XAI Machine Learning Solution for Large, Multi-Table Databases
• Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
• What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture
• Generalizable AI Model for Indoor Temperature Forecasting Across Sub-Saharan Africa
• A Systematic Review on the Generative AI Applications in Human Medical Genomics
• FORGE: Foundational Optimization Representations from Graph Embeddings
• Dynamic Synthetic Controls vs. Panel-Aware Double Machine Learning for Geo-Level Marketing Impact Estimation
• Adaptive Segmentation of EEG for Machine Learning Applications
• DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
• Developing a Multi-Modal Machine Learning Model For Predicting Performance of Automotive Hood Frames
• NetGPT: Generative Pretrained Transformer for Network Traffic
• Network Formation and Dynamics Among Multi-LLMs
• Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
• SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking
• FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
• Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language
• Application of AI to formal methods - an analysis of current trends
• RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
• Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models
• ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation
• A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing
• Safe and Efficient Social Navigation through Explainable Safety Regions Based on Topological Features
• Improving Quantization with Post-Training Model Expansion
• Program Semantic Inequivalence Game with Large Language Models
• A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems (Changes are marked)
• Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models
• Entropy-Memorization Law: Evaluating Memorization Difficulty of Data in LLMs
• Evaluating Compositional Generalisation in VLMs and Diffusion Models
• Exploring Machine Learning and Language Models for Multimodal Depression Detection
• Uncertainty Aware-Predictive Control Barrier Functions: Safer Human Robot Interaction through Probabilistic Motion Forecasting
• Multi-Agent Penetration Testing AI for the Web
• JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
• AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning
• Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant
• Research Challenges in Relational Database Management Systems for LLM Queries
• ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
• WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations
• ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts
• Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
• ChainReaction! Structured Approach with Causal Chains as Intermediate Representations for Improved and Explainable Causal Video Question Answering
• Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
• Understanding, Protecting, and Augmenting Human Cognition with Generative AI: A Synthesis of the CHI 2025 Tools for Thought Workshop
• FakeParts: a New Family of AI-Generated DeepFakes
• OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models
• Prompt-to-Product: Generative Assembly via Bimanual Manipulation
• OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
• Possible Principles for Aligned Structure Learning Agents
• Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground
• Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
• BridgeShield: Enhancing Security for Cross-chain Bridge Applications via Heterogeneous Graph Mining
• SPGrasp: Spatiotemporal Prompt-driven Grasp Synthesis in Dynamic Scenes
• MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning
• Adaptive Federated Distillation for Multi-Domain Non-IID Textual Data
• AI and Agile Software Development: A Research Roadmap from the XP2025 Workshop
• Towards Mechanistic Defenses Against Typographic Attacks in CLIP
• MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
• Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement
• ArtFace: Towards Historical Portrait Face Identification via Model Adaptation
• Task Allocation for Autonomous Machines using Computational Intelligence and Deep Reinforcement Learning
• MobileCLIP2: Improving Multi-Modal Reinforced Training
• Generative Annotation for ASR Named Entity Correction
• EEGDM: Learning EEG Representation with Latent Diffusion Model
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
• Provable Benefits of In-Tool Learning for Large Language Models
• SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer
• Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
• Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
• Safer Skin Lesion Classification with Global Class Activation Probability Map Evaluation and SafeML
• Collaborating with GenAI: Incentives and Replacements
• Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models
• A Novel Framework for Automated Explain Vision Model Using Vision-Language Models
• Validating Generative Agent-Based Models for Logistics and Supply Chain Management Research
• The Mathematician's Assistant: Integrating AI into Research Practice
• MedNet-PVS: A MedNeXt-Based Deep Learning Model for Automated Segmentation of Perivascular Spaces
• SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization
• How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
• Network-Level Prompt and Trait Leakage in Local Research Agents
• Objective Value Change and Shape-Based Accelerated Optimization for the Neural Network Approximation
• Beacon: Post-Training Quantization with Integrated Grid Selection
• Surveying the Operational Cybersecurity and Supply Chain Threat Landscape when Developing and Deploying AI Systems
• GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs
• Multi-View Graph Convolution Network for Internal Talent Recommendation Based on Enterprise Emails
• Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
• Boosting Skeleton-Driven SMT Solver Fuzzing by Leveraging LLM to Produce Formula Generators
• Graph-R1: Unleashing LLM Reasoning with NP-Hard Graph Problems
• Ultra-Low-Latency Spiking Neural Networks with Temporal-Dependent Integrate-and-Fire Neuron Model for Objects Detection
• Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction
• TF-TransUNet1D: Time-Frequency Guided Transformer U-Net for Robust ECG Denoising in Digital Twin
• DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding
• On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
• Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Aware Unlearning with Proxy Constraint
• Evaluating Differentially Private Generation of Domain-Specific Text
• Do Students Rely on AI? Analysis of Student-ChatGPT Conversations from a Field Study
• AI reasoning effort mirrors human decision time on content moderation tasks
• AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
• Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
• AWorld: Orchestrating the Training Recipe for Agentic AI
• Governable AI: Provable Safety Under Extreme Threat Models
• Enhancing Health Fact-Checking with LLM-Generated Synthetic Data
• Human-AI Collaborative Bot Detection in MMORPGs
• Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science
• Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings
• Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control
• A Graph-Based Test-Harness for LLM Evaluation
• Efficient Neuro-Symbolic Learning of Constraints and Objective
• ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery
• Can LLMs Identify Tax Abuse?
• A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning Approach
• Deep Reinforcement Learning for Optimal Asset Allocation Using DDPG with TiDE
• Flexible metadata harvesting for ecology using large language models
• Is Artificial Intelligence Reshaping the Landscape of the International Academic Community of Geosciences?
• Particle swarm optimization for online sparse streaming feature selection under uncertainty
• Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms
• Artificial Intelligence for CRISPR Guide RNA Design: Explainable Models and Off-Target Safety
• Data-Efficient Point Cloud Semantic Segmentation Pipeline for Unimproved Roads
• Navigating the EU AI Act: Foreseeable Challenges in Qualifying Deep Learning-Based Automated Inspections of Class III Medical Devices
• RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI
• Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
• AI Propaganda factories with language models
• ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
• QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
• IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
• AI-AI Esthetic Collaboration with Explicit Semiotic Awareness and Emergent Grammar Development