AI Research News Feeds for September 1st, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement
• Retrieval-Augmented Machine Translation with Unstructured Knowledge
• DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
• DDaTR: Dynamic Difference-aware Temporal Residual Network for Longitudinal Radiology Report Generation
• TrueGL: A Truthful, Reliable, and Unified Engine for Grounded Learning in Full-Stack Search
• Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
• Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
• Bringing Attention to CAD: Boundary Representation Learning via Transformer
• Visual Imitation Enables Contextual Humanoid Control
• Explicit Residual-Based Scalable Image Coding for Humans and Machines
• mmFlux: Crowd Flow Analytics with Commodity mmWave MIMO Radar
• Discovering Heterogeneous Treatment Effects in Regression Discontinuity Designs
• Mixed membership estimation for categorical data with weighted responses
• ARGS: Advanced Regularization on Aligning Gaussians over the Surface
• The Rosario Dataset v2: Multimodal Dataset for Agricultural Robotics
• From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China
• ALow-Cost Real-Time Framework for Industrial Action Recognition Using Foundation Models
• JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model
• Maximising Kidney Glomeruli Segmentation using Minimal Labels via Self-Supervision
• CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization
• Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration
• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
• PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation
• Computer-Aided Design of Personalized Occlusal Positioning Splints Using Multimodal 3D Data
• Saliency-Guided Training for Fingerprint Presentation Attack Detection
• InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization
• Gaussian is All You Need: A Unified Framework for Solving Inverse Problems via Diffusion Posterior Sampling
• Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
• One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist
• Federated Fine-tuning of SAM-Med3D for MRI-based Dementia Classification
• Multi-Method Ensemble for Out-of-Distribution Detection
• Adversarial Patch Attack for Ship Detection via Localized Augmentation
• Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation
• HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones
• ECHO: Ego-Centric modeling of Human-Object interactions
• How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images
• Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging
• Integrating Pathology and CT Imaging for Personalized Recurrence Risk Prediction in Renal Cancer
• Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation
• Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models
• Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
• FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
• Learning from Silence and Noise for Visual Sound Source Localization
• UItron: Foundational GUI Agent with Advanced Perception and Planning
• What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos
• A Multi-Stage Fine-Tuning and Ensembling Strategy for Pancreatic Tumor Segmentation in Diagnostic and Therapeutic MRI
• VoCap: Video Object Captioning and Segmentation from Any Prompt
• DriveQA: Passing the Driving Knowledge Test
• ScanMove: Motion Prediction and Transfer for Unregistered Body Meshes
• Mini Autonomous Car Driving based on 3D Convolutional Neural Networks
• Inducing Programmatic Skills for Agentic Tasks
• Testing Conviction: An Argumentative Framework for Measuring LLM Political Stability
• 2COOOL: 2nd Workshop on the Challenge Of Out-Of-Label Hazards in Autonomous Driving
• Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment
• ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
• Video-LLMs with Temporal Visual Screening
• ROBUST-MIPS: A Combined Skeletal Pose and Instance Segmentation Dataset for Laparoscopic Surgical Instruments
• GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regions
• SYNBUILD-3D: A large, multi-modal, and semantically rich synthetic dataset of 3D building models at Level of Detail 4
• Radially Distorted Homographies, Revisited
• GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
• Lightweight MRI-Based Automated Segmentation of Pancreatic Cancer with Auto3DSeg
• Reverse Imaging for Wide-spectrum Generalization of Cardiac MRI Segmentation
• PHD: Personalized 3D Human Body Fitting with Point Diffusion
• Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
• Print2Volume: Generating Synthetic OCT-based 3D Fingerprint Volume from 2D Fingerprint Image
• GLENDA: Gynecologic Laparoscopy Endometriosis Dataset
• Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation
• Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
• Trees as Gaussians: Large-Scale Individual Tree Mapping
• Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcasting
• Granite Embedding R2 Models
• How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
• Can Multimodal LLMs Solve the Basic Perception Problems of Percept-V?
• Do Self-Supervised Speech Models Exhibit the Critical Period Effects in Language Acquisition?
• Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework
• Discovering Semantic Subdimensions through Disentangled Conceptual Representations
• Beyond the Surface: Probing the Ideological Depth of Large Language Models
• Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks
• Is this chart lying to me? Automating the detection of misleading visualizations
• Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
• Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses
• CrossTL: A Universal Programming Language Translator with Unified Intermediate Representation
• From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics
• Morae: Proactively Pausing UI Agents for User Choices
• E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
• Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer
• Strategic resource allocation in memory encoding: An efficiency principle shaping language processing
• Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery
• Revealing Fine-Grained Values and Opinions in Large Language Models
• BrainGPT: Unleashing the Potential of EEG Generalist Foundation Model by Autoregressive Pre-training
• Control of Rayleigh-B\'enard Convection: Effectiveness of Reinforcement Learning in the Turbulent Regime
• From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
• L3Cube-MahaEmotions: A Marathi Emotion Recognition Dataset with Synthetic Annotations using CoTR prompting and Large Language Models
• Interpretation of Deep Learning Model in Embryo Selection for In Vitro Fertilization (IVF) Treatment
• SatDINO: A Deep Dive into Self-Supervised Pretraining for Remote Sensing
• Standardized Multi-Layer Tissue Maps for Enhanced Artificial Intelligence Integration and Search in Large-Scale Whole Slide Image Archives
• Adaptive generative moment matching networks for improved learning of dependence structures
• Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localisation Using Reinforcement Learning
• Surface Stability Modeling with Universal Machine Learning Interatomic Potentials: A Comprehensive Cleavage Energy Benchmarking Study
• A Soft Inducement Framework for Incentive-Aided Steering of No-Regret Players
• Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations
• Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms
• Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation
• Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
• Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
• SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative Decoding
• On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning
• Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
• BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
• Rethinking Layer-wise Model Merging through Chain of Merges
• Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning
• Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
• Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control
• Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
• Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification
• OASIS: Harnessing Diffusion Adversarial Network for Ocean Salinity Imputation using Sparse Drifter Trajectories
• Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
• UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
• QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models
• Achieving Hilbert-Schmidt Independence Under R\'enyi Differential Privacy for Fair and Private Data Generation
• ImmunoAI: Accelerated Antibody Discovery Using Gradient-Boosted Machine Learning with Thermodynamic-Hydrodynamic Descriptors and 3D Geometric Interface Topology
• Advanced Deep Learning Techniques for Classifying Dental Conditions Using Panoramic X-Ray Images
• Synthetic CVs To Build and Test Fairness-Aware Hiring Tools
• Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting
• Weighted Support Points from Random Measures: An Interpretable Alternative for Generative Modeling
• Faster Inference of Cell Complexes from Flows via Matrix Factorization
• BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models
• Single Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement
• Adaptive LLM Routing under Budget Constraints
• Model-Task Alignment Drives Distinct RL Outcomes
• RelP: Faithful and Efficient Circuit Discovery via Relevance Patching
• CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams
• Detecting Domain Shifts in Myoelectric Activations: Challenges and Opportunities in Stream Learning
• Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
• AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture
• QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges
• Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation
• COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty
• Guiding a diffusion model using sliding windows
• ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
• Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts
• LLM Test Generation via Iterative Hybrid Program Analysis
• FROG: Fair Removal on Graphs
• Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysis
• DeepTrans: Deep Reasoning Translation via Reinforcement Learning
• SAGA: A Security Architecture for Governing AI Agentic Systems
• MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness
• Towards Embodiment Scaling Laws in Robot Locomotion
• FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models
• Beyond Frequency: The Role of Redundancy in Large Language Model Memorization
• Complete Gaussian Splats from a Single Image with Denoising Diffusion Models
• What Data is Really Necessary? A Feasibility Study of Inference Data Minimization for Recommender Systems
• EZ-Sort: Efficient Pairwise Comparison via Zero-Shot CLIP-Based Pre-Ordering and Human-in-the-Loop Sorting
• Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
• Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
• Harnessing IoT and Generative AI for Weather-Adaptive Learning in Climate Resilience Education
• Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
• OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
• Developer Insights into Designing AI-Based Computer Perception Tools
• Neural Network Acceleration on MPSoC board: Integrating SLAC's SNL, Rogue Software and Auto-SNL
• Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight
• MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Prediction
• DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers
• Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
• Transforming Wearable Data into Personal Health Insights using Large Language Model Agents
• A Financial Brain Scan of the LLM
• Efficient Code Embeddings from Code Generation Models
• BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
• MyGO: Memory Yielding Generative Offline-consolidation for Lifelong Learning Systems
• Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models
• Stairway to Fairness: Connecting Group and Individual Fairness
• DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
• Adaptive Heavy-Tailed Stochastic Gradient Descent
• EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure
• Challenges and Applications of Large Language Models: A Comparison of GPT and DeepSeek family of models
• RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation
• Iterative Inference in a Chess-Playing Neural Network
• zkLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
• Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models
• The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
• MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
• Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction
• Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
• Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI
• Spatiotemporal EEG-Based Emotion Recognition Using SAM Ratings from Serious Games with Hybrid Deep Learning
• Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models
• Learning to Generate Unit Test via Adversarial Reinforcement Learning
• An Explainable, Attention-Enhanced, Bidirectional Long Short-Term Memory Neural Network for Joint 48-Hour Forecasting of Temperature, Irradiance, and Relative Humidity
• Automating the Deep Space Network Data Systems; A Case Study in Adaptive Anomaly Detection through Agentic AI
• EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
• R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
• HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection
• A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
• WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration
• Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
• Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
• BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
• Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization
• Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
• Generalizable Object Re-Identification via Visual In-Context Prompting
• Quantum Machine Learning for Optimizing Entanglement Distribution in Quantum Sensor Circuits
• Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits
• Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
• Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding
• Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs
• MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems
• Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
• AI Compute Architecture and Evolution Trends
• MMSearch-Plus: A Simple Yet Challenging Benchmark for Multimodal Browsing Agents
• HealthProcessAI: A Technical Framework and Proof-of-Concept for LLM-Enhanced Healthcare Process Mining
• Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study
• Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
• Orientability of Causal Relations in Time Series using Summary Causal Graphs and Faithful Distributions
• Tree-Guided Diffusion Planner
• Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
• QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning
• Pep2Prob Benchmark: Predicting Fragment Ion Probability for MS$^2$-based Proteomics
• Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation
• TrInk: Ink Generation with Transformer Network
• Safe-Control: A Safety Patch for Mitigating Unsafe Content in Text-to-Image Generation Models