AI Research News Feeds for September 8th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• 3D Densification for Multi-Map Monocular VSLAM in Endoscopy
• Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
• Histo-Miner: Deep Learning based Tissue Features Extraction Pipeline from H&E Whole Slide Images of Cutaneous Squamous Cell Carcinoma
• Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach
• High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion model
• Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception
• Colorectal Cancer Tumor Grade Segmentation in Digital Histopathology Images: From Giga to Mini Challenge
• Beyond the Linear Separability Ceiling: Aligning Representations in VLMs
• Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
• Automatic segmentation of Organs at Risk in Head and Neck cancer patients from CT and MRI scans
• Multimodal LLM Guided Exploration and Active Mapping using Fisher Information
• A biologically inspired separable learning vision model for real-time traffic object perception in Dark
• Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition
• LUIVITON: Learned Universal Interoperable VIrtual Try-ON
• Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction
• GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting
• Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
• Semi-supervised Deep Transfer for Regression without Domain Alignment
• SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
• SL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
• FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
• STADI: Fine-Grained Step-Patch Diffusion Parallelism for Heterogeneous GPUs
• AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representations
• Histogram Driven Amplitude Embedding for Qubit Efficient Quantum Image Compression
• Multi-modal Uncertainty Robust Tree Cover Segmentation For High-Resolution Remote Sensing Images
• Towards an Accurate and Effective Robot Vision (The Problem of Topological Localization for Mobile Robots)
• VLSM-Ensemble: Ensembling CLIP-based Vision-Language Models for Enhanced Medical Image Segmentation
• Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
• Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs
• PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking
• HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation
• DirectorLLM for Human-Centric Video Generation
• Disentangled Clothed Avatar Generation with Layered Representation
• ActiveGAMER: Active GAussian Mapping through Efficient Rendering
• Facial Emotion Recognition does not detect feeling unsafe in automated driving
• PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting
• Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model
• Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
• DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models
• WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human
• Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning
• UAV-Based Intelligent Traffic Surveillance System: Real-Time Vehicle Detection, Classification, Tracking, and Behavioral Analysis
• Guideline-Consistent Segmentation via Multi-Agent Refinement
• Domain Adaptation for Different Sensor Configurations in 3D Object Detection
• CD-Mamba: Cloud detection with long-range spatial dependency modeling
• Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation
• WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
• Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
• Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
• Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
• TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
• Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
• CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
• Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning
• UniView: Enhancing Novel View Synthesis From A Single Image By Unifying Reference Features
• Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
• Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
• Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study
• Uniform Information Density and Syntactic Reduction: Revisiting $\textit{that}$-Mentioning in English Complement Clauses
• Elucidating the Design Space of Decay in Linear Attention
• Labelling Data with Unknown References
• WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
• Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media
• Non-Termination Proving: 100 Million LoC and Beyond
• Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval
• Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
• LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
• What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis
• Assessing the Sensitivity and Alignment of FOL Closeness Metrics
• Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
• All That Glitters is Not Novel: Plagiarism in AI Generated Research
• Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
• StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings
• Can LLMs Simulate Personas with Reversed Performance? A Benchmark for Counterfactual Instruction Following
• ViClaim: A Multilingual Multilabel Dataset for Automatic Claim Detection in Videos
• Text2Cypher Across Languages: Evaluating and Finetuning LLMs
• Yesterday's News: Benchmarking Multi-Dimensional Out-of-Distribution Generalization of Misinformation Detection Models
• Hunyuan-MT Technical Report
• Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
• ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models
• Combine Virtual Reality and Machine-Learning to Identify the Presence of Dyslexia: A Cross-Linguistic Approach
• Artificially Fluent: Swahili AI Performance Benchmarks Between English-Trained and Natively-Trained Datasets
• Advancing SLM Tool-Use Capability using Reinforcement Learning
• Hierarchical Section Matching Prediction (HSMP) BERT for Fine-Grained Extraction of Structured Data from Hebrew Free-Text Radiology Reports in Crohn's Disease
• Using LLMs to create analytical datasets: A case study of reconstructing the historical memory of Colombia
• Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects
• AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs
• Why Language Models Hallucinate
• OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse Topics
• Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
• Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
• Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
• Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs
• Analyzing Finnish Inflectional Classes through Discriminative Lexicon and Deep Learning Models
• AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding
• Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?
• Using LLMs for Multilingual Clinical Entity Linking to ICD-10
• L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
• ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
• Masked Diffusion Language Models with Frequency-Informed Training
• Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
• PRIM: Towards Practical In-Image Multilingual Machine Translation
• Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework
• INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance
• Mentalic Net: Development of RAG-based Conversational AI and Evaluation Framework for Mental Health Support
• Do MLLMs Really Understand the Charts?
• Predicting Failures of LLMs to Link Biomedical Ontology Terms to Identifiers Evidence Across Models and Ontologies
• From Post To Personality: Harnessing LLMs for MBTI Prediction in Social Media
• An End-to-End System for Culturally-Attuned Driving Feedback using a Dual-Component NLG Engine
• Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models
• ALF: Advertiser Large Foundation Model for Multi-Modal Advertiser Understanding
• Scalable Unit Harmonization in Medical Informatics via Bayesian-Optimized Retrieval and Transformer-Based Re-ranking
• A Deep Learning Framework for Two-Dimensional, Multi-Frequency Propagation Factor Estimation
• The dynamic interplay between in-context and in-weight learning in humans and neural networks
• Assumption-Lean Post-Integrated Inference with Surrogate Control Outcomes
• CRANE: Reasoning with constrained LLM generation
• Barrier Certificates for Unknown Systems with Latent States and Polynomial Dynamics using Bayesian Inference
• Graph Transformer-Based Flood Susceptibility Mapping: Application to the French Riviera and Railway Infrastructure Under Climate Change
• RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language
• SynGen-Vision: Synthetic Data Generation for training industrial vision models
• Classification of kinetic-related injury in hospital triage data using NLP
• MAIA: An Inpainting-Based Approach for Music Adversarial Attacks
• Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
• Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
• Dynamical Learning in Deep Asymmetric Recurrent Neural Networks
• QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
• Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
• Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
• Symbolic Graphics Programming with Large Language Models
• Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense
• Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
• Towards Generative Ray Path Sampling for Faster Point-to-Point Ray Tracing
• Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
• Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL
• Should We Always Train Models on Fine-Grained Classes?
• Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
• Deep Learning-Enhanced for Amine Emission Monitoring and Performance Analysis in Industrial Carbon Capture Plants
• Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
• Learning to accelerate distributed ADMM using graph neural networks
• Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
• Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning
• Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis
• Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
• Scaling behavior of large language models in emotional safety classification across sizes and tasks
• Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
• Inferring the Graph Structure of Images for Graph Neural Networks
• Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems
• Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
• Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
• Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
• Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
• Any-Step Density Ratio Estimation via Interval-Annealed Secant Alignment
• Q-SafeML: Safety Assessment of Quantum Machine Learning via Quantum Distance Metrics
• Flexible inference of learning rules from de novo learning data using neural networks
• Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition
• Echoes Before Collapse: Deep Learning Detection of Flickering in Complex Systems
• CPEP: Contrastive Pose-EMG Pre-training Enhances Gesture Generalization on EMG Signals
• Natural Spectral Fusion: p-Exponent Cyclic Scheduling and Early Decision-Boundary Alignment in First-Order Optimization
• An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning
• Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
• A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection
• Ontology-Aligned Embeddings for Data-Driven Labour Market Analytics
• Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
• Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks
• Depth-Aware Initialization for Stable and Efficient Neural Network Training
• MultiSurv: A Multimodal Deep Survival Framework for Prostrate and Bladder Cancer
• Net2Brain: A Toolbox to compare artificial vision models with human brain responses
• Demystifying Chains, Trees, and Graphs of Thoughts
• AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
• From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks
• PersonaGym: Evaluating Persona Agents and LLMs
• HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
• The Information Security Awareness of Large Language Models
• Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofing
• PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
• Revealing higher-order neural representations of uncertainty with the Noise Estimation through Reinforcement-based Diffusion (NERD) model
• RailGoerl24: G\"orlitz Rail Test Center CV Dataset 2024
• AutoPDL: Automatic Prompt Optimization for LLM Agents
• TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
• First Steps Towards Overhearing LLM Agents: A Case Study With Dungeons & Dragons Gameplay
• AI-Assisted Rapid Crystal Structure Generation Towards a Target Local Environment
• BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields
• Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification
• Food safety trends across Europe: insights from the 392-million-entry CompreHensive European Food Safety (CHEFS) database
• AI Agents for Web Testing: A Case Study in the Wild
• Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
• RapidGNN: Energy and Communication-Efficient Distributed Training on Large-Scale Graph Neural Networks
• HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models
• CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
• Uncertain but Useful: Leveraging CNN Variability into Data Augmentation
• Recomposer: Event-roll-guided generative audio editing
• Scaling Performance of Large Language Model Pretraining
• SpikingBrain Technical Report: Spiking Brain-inspired Large Models
• Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
• MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts
• Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
• Neural Network Verification with PyRAT
• Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
• ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding
• Translating Federated Learning Algorithms in Python into CSP Processes Using ChatGPT
• Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
• Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
• Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
• A Study of Large Language Models for Patient Information Extraction: Model Architecture, Fine-Tuning Strategy, and Multi-task Instruction Tuning
• FloodVision: Urban Flood Depth Estimation Using Foundation Vision-Language Models and Domain Knowledge Graph
• The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
• VARMA-Enhanced Transformer for Time Series Forecasting
• Enhancing Diversity in Large Language Models via Determinantal Point Processes
• Graph Unlearning: Efficient Node Removal in Graph Neural Networks
• Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
• AI-Driven Fronthaul Link Compression in Wireless Communication Systems: Review and Method Design
• Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
• REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts
• A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routing
• Artificial intelligence for representing and characterizing quantum systems
• DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation
• High-Resolution Global Land Surface Temperature Retrieval via a Coupled Mechanism-Machine Learning Framework
• LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration
• Pointing-Guided Target Estimation via Transformer-Based Attention
• GenAI-based test case generation and execution in SDV platform
• Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
• Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations
• DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
• Understanding Reinforcement Learning for Model Training, and future directions with GRAPE
• VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
• Behavioral Fingerprinting of Large Language Models
• Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENs
• From Silent Signals to Natural Language: A Dual-Stage Transformer-LLM Approach
• Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
• Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation
• In-Context Policy Adaptation via Cross-Domain Skill Diffusion
• Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
• Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
• Toward Faithfulness-guided Ensemble Interpretation of Neural Network
• Sample-efficient Integration of New Modalities into Large Language Models
• Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control
• Schema Inference for Tabular Data Repositories Using Large Language Models
• Scaling Environments for Organoid Intelligence with LLM-Automated Design and Plasticity-Based Evaluation
• Comparative Analysis of Transformer Models in Disaster Tweet Classification for Public Safety
• Interpreting Transformer Architectures as Implicit Multinomial Regression
• Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
• ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs
• Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving
• KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
• LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
• MLP-SRGAN: A Single-Dimension Super Resolution GAN using MLP-Mixer
• Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection
• Benchmarking GPT-5 for biomedical natural language processing
• Multiscale Graph Neural Network for Turbulent Flow-Thermal Prediction Around a Complex-Shaped Pin-Fin
• Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
• Emotionally-Aware Agents for Dispute Resolution
• Enhancing LLM Efficiency: Targeted Pruning for Prefill-Decode Disaggregation in Inference
• Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study
• Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
• MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification
• SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings
• Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
• ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
• Training Text-to-Molecule Models with Context-Aware Tokenization
• No Clustering, No Routing: How Transformers Actually Process Rare Tokens
• Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments
• Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
• DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
• ASCENDgpt: A Phenotype-Aware Transformer Model for Cardiovascular Risk Prediction from Electronic Health Records
• Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition
• Refining Transcripts With TV Subtitles by Prompt-Based Weakly Supervised Training of ASR
• Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
• The Ethical Compass of the Machine: Evaluating Large Language Models for Decision Support in Construction Project Management
• Maestro: Joint Graph & Config Optimization for Reliable AI Agents
• An Approach to Grounding AI Model Evaluations in Human-derived Criteria
• What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking
• TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models
• Cloning a Conversational Voice AI Agent from Call\,Recording Datasets for Telesales
• OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
• Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents