AI Research News Feeds for August 27th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Estimating oil recovery factor using machine learning: Applications of XGBoost classification
• Lightweight posterior construction for gravitational-wave catalogs with the Kolmogorov-Arnold network
• How many samples are needed to train a deep neural network?
• Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal
• Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data
• FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual Localization
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields
• ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration
• Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
• StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
• Survey on Monocular Metric Depth Estimation
• Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance
• PromptGAR: Flexible Promptive Group Activity Recognition
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
• LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification
• ForgetMe: Evaluating Selective Forgetting in Generative Models
• WMKA-Net: A Weighted Multi-Kernel Attention Network for Retinal Vessel Segmentation
• PhysioSync: Temporal and Cross-Modal Contrastive Learning Inspired by Physiological Synchronization for EEG-Based Emotion Recognition
• RAFT: Robust Augmentation of FeaTures for Image Segmentation
• MonoCoP: Chain-of-Prediction for Monocular 3D Object Detection
• Generative Data Augmentation for Object Point Cloud Segmentation
• Egocentric Human-Object Interaction Detection: A New Benchmark and Method
• Prompt-based Dynamic Token Pruning for Efficient Segmentation of Medical Images
• OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding
• Confidence-driven Gradient Modulation for Multimodal Human Activity Recognition: A Dynamic Contrastive Dual-Path Learning Approach
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
• Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention
• MOSformer: Momentum encoder-based inter-slice fusion transformer for medical image segmentation
• TimeFlow: Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis
• Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze Information and Motion Bottlenecks
• Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization
• Objective Task-based Evaluation of Quantitative Medical Imaging Methods: Emerging Frameworks and Future Directions
• TRAN-D: 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update
• Handcrafted vs. Deep Radiomics vs. Fusion vs. Deep Learning: A Comprehensive Review of Machine Learning -Based Cancer Outcome Prediction in PET and SPECT Imaging
• Style4D-Bench: A Benchmark Suite for 4D Stylization
• Articulate3D: Zero-Shot Text-Driven 3D Object Posing
• VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
• Impact of Target and Tool Visualization on Depth Perception and Usability in Optical See-Through AR
• Controllable Single-shot Animation Blending with Temporal Conditioning
• SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis
• Enhancing Video-Based Robot Failure Detection Using Task Knowledge
• A Closer Look at Edema Area Segmentation in SD-OCT Images Using Adversarial Framework
• Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
• Quantum-Circuit-Based Visual Fractal Image Generation in Qiskit and Analytics
• PanoHair: Detailed Hair Strand Synthesis on Volumetric Heads
• Enhanced UAV Path Planning Using the Tangent Intersection Guidance (TIG) Algorithm
• Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Data
• Time Series Analysis of Spiking Neural Systems via Transfer Entropy and Directed Persistent Homology
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
• SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain
• Hierarchical Spatio-temporal Segmentation Network for Ejection Fraction Estimation in Echocardiography Videos
• Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency
• A Novel Deep Hybrid Framework with Ensemble-Based Feature Optimization for Robust Real-Time Human Activity Recognition
• ColorGS: High-fidelity Surgical Scene Reconstruction with Colored Gaussian Splatting
• Class-wise Flooding Regularization for Imbalanced Image Classification
• Flatness-aware Curriculum Learning via Adversarial Difficulty
• Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vectorized Drawings
• Rethinking Human-Object Interaction Evaluation for both Vision-Language Models and HOI-Specific Methods
• Design, Implementation and Evaluation of a Real-Time Remote Photoplethysmography (rPPG) Acquisition System for Non-Invasive Vital Sign Monitoring
• Robust and Label-Efficient Deep Waste Detection
• Embedding Font Impression Word Tags Based on Co-occurrence
• Deep Pre-trained Time Series Features for Tree Species Classification in the Dutch Forest Inventory
• Automated Classification of Normal and Atypical Mitotic Figures Using ConvNeXt V2: MIDOG 2025 Track 2
• Boosting Micro-Expression Analysis via Prior-Guided Video-Level Regression
• Quantitative Outcome-Oriented Assessment of Microsurgical Anastomosis
• Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
• Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
• DQEN: Dual Query Enhancement Network for DETR-based HOI Detection
• Event-Enriched Image Analysis Grand Challenge at ACM Multimedia 2025
• Preliminary Study on Space Utilization and Emergent Behaviors of Group vs. Single Pedestrians in Real-World Trajectories
• Generative AI in Map-Making: A Technical Exploration and Its Implications for Cartographers
• Can we make NeRF-based visual localization privacy-preserving?
• Enhancing Document VQA Models via Retrieval-Augmented Generation
• Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone
• MicroDetect-Net (MDN): Leveraging Deep Learning to Detect Microplastics in Clam Blood, a Step Towards Human Blood Analysis
• ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval
• VibES: Induced Vibration for Persistent Event-Based Sensing
• Dual Enhancement on 3D Vision-Language Perception for Monocular 3D Visual Grounding
• Beyond flattening: a geometrically principled positional encoding for vision transformers with Weierstrass elliptic functions
• SoccerNet 2025 Challenges Results
• FastMesh:Efficient Artistic Mesh Generation via Component Decoupling
• All-in-One Slider for Attribute Manipulation in Diffusion Models
• OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation
• Automated Feature Tracking for Real-Time Kinematic Analysis and Shape Estimation of Carbon Nanotube Growth
• Autoregressive Universal Video Segmentation Model
• HateDebias: On the Diversity and Variability of Hate Speech Debiasing
• Recognizing Limits: Investigating Infeasibility in Large Language Models
• Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models
• Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge
• Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications
• Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence
• Improving Multilingual Language Models by Aligning Representations through Steering
• Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
• Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
• ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction
• Subjective Perspectives within Learned Representations Predict High-Impact Innovation
• Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment
• VAGUE: Visual Contexts Clarify Ambiguous Expressions
• Evolutionary Automata and Deep Evolutionary Computation
• Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication
• SERES: Semantic-aware neural reconstruction from sparse views
• FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses
• Securing Face and Fingerprint Templates in Humanitarian Biometric Systems
• Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?
• LPLC: A Dataset for License Plate Legibility Classification
• VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results
• DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
• Adaptive Visual Navigation Assistant in 3D RPGs
• Wan-S2V: Audio-Driven Cinematic Video Generation
• Decouple, Reorganize, and Fuse: A Multimodal Framework for Cancer Survival Prediction
• OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward
• Semantic Attractors and the Emergence of Meaning: Towards a Teleological Model of AGI
• Not All Visitors are Bilingual: A Measurement Study of the Multilingual Web from an Accessibility Perspective
• Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
• Integral Transformer: Denoising Attention, Not Too Much Not Too Little
• Integrating gender inclusivity into large language models via instruction tuning
• COMET-poly: Machine Translation Metric Grounded in Other Candidates
• The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
• A New NMT Model for Translating Clinical Texts from English to Spanish
• Thinking Before You Speak: A Proactive Test-time Scaling Approach
• Emotion Omni: Enabling Empathetic Speech Response Generation through Large Language Models
• Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning
• Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
• Filtering for Creativity: Adaptive Prompting for Multilingual Riddle Generation in LLMs
• EMMM, Explain Me My Model! Explainable Machine Generated Text Detection in Dialogues
• Chronological Passage Assembling in RAG framework for Temporal Question Answering
• ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
• Controllable Conversational Theme Detection Track at DSTC 12
• LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination
• LLM-based Contrastive Self-Supervised AMR Learning with Masked Graph Autoencoders for Fake News Detection
• Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
• Empowering Computing Education Researchers Through LLM-Assisted Content Analysis
• Affective Polarization across European Parliaments
• MovieCORE: COgnitive REasoning in Movies
• "Where does it hurt?" - Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues
• It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
• Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index
• Beyond the Black Box: Integrating Lexical and Semantic Methods in Quantitative Discourse Analysis with BERTopic
• Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
• Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning
• Evaluating the Evaluators: Are readability metrics good measures of readability?
• Designing across domains with declarative thinking: Insights from the 96-Eyes ptychographic imager project
• UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
• Beyond the Textual: Generating Coherent Visual Options for MCQs
• The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
• A Survey on Data Selection for LLM Instruction Tuning
• KNN and K-means in Gini Prametric Spaces
• Keep your distance: learning dispersed embeddings on $\mathbb{S}_m$
• General Intelligence Requires Reward-based Pretraining
• Seal Your Backdoor with Variational Defense
• VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG
• ChemKANs for Combustion Chemistry Modeling and Acceleration
• Local Learning Rules for Out-of-Equilibrium Physical Generative Models
• Deep Generative Methods and Tire Architecture Design
• Multi-Component VAE with Gaussian Markov Random Field
• PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
• Data Compression using Rank-1 Lattices for Parameter Estimation in Machine Learning
• Deep vectorised operators for pulsatile hemodynamics estimation in coronary arteries from a steady-state prior
• MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU
• Human Vision Constrained Super-Resolution
• Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives
• SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
• Multi-timescale time encoding for CNN prediction of Fenna-Matthews-Olson energy-transfer dynamics
• Data Requirement Goal Modeling for Machine Learning Systems
• Steerable Scene Generation with Post Training and Inference-Time Search
• Uni-AIMS: AI-Powered Microscopy Image Analysis
• Distribution free M-estimation
• Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
• Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
• Investigating the Robustness of Extreme Precipitation Super-Resolution Across Climates
• Deterministic Coreset Construction via Adaptive Sensitivity Trimming
• Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
• DenseRec: Revisiting Dense Content Embeddings for Sequential Transformer-based Recommendation
• From Prediction to Simulation: AlphaFold 3 as a Differentiable Framework for Structural Biology
• Context-Aware Zero-Shot Anomaly Detection in Surveillance Using Contrastive and Predictive Spatiotemporal Modeling
• Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
• An Analytical Approach to Privacy and Performance Trade-Offs in Healthcare Data Sharing
• Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
• Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets
• Stress-testing cross-cancer generalizability of 3D nnU-Net for PET-CT tumor segmentation: multi-cohort evaluation with novel oesophageal and lung cancer datasets
• ModAn-MulSupCon: Modality-and Anatomy-Aware Multi-Label Supervised Contrastive Pretraining for Medical Imaging
• Taming the One-Epoch Phenomenon in Online Recommendation System by Two-stage Contrastive ID Pre-training
• Data-Driven Discovery and Formulation Refines the Quasi-Steady Model of Flapping-Wing Aerodynamics
• Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
• Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
• Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models
• Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
• PseudoMapTrainer: Learning Online Mapping without HD Maps
• Temperature-Aware Recurrent Neural Operator for Temperature-Dependent Anisotropic Plasticity in HCP Materials
• Learning Real-World Acrobatic Flight from Human Preferences
• Sparse minimum Redundancy Maximum Relevance for feature selection
• Forecasting Probability Distributions of Financial Returns with Deep Neural Networks
• The GINN framework: a stochastic QED correspondence for stability and chaos in deep neural networks
• Enhancing compact convolutional transformers with super attention
• USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
• Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models
• GReAT: leveraging geometric artery data to improve wall shear stress assessment
• Learning Binary Sampling Patterns for Single-Pixel Imaging using Bilevel Optimisation
• CARMA: Collocation-Aware Resource Manager with GPU Memory Estimator
• Universal Dynamics with Globally Controlled Analog Quantum Simulators
• Random forest-based out-of-distribution detection for robust lung cancer segmentation
• A Bag of Tricks for Efficient Implicit Neural Point Clouds
• Echoes of the past: A unified perspective on fading memory and echo states
• Leveraging Evolutionary Surrogate-Assisted Prescription in Multi-Objective Chlorination Control Systems
• Planning-Query-Guided Model Generation for Model-Based Deformable Object Manipulation
• Branch and Bound for Piecewise Linear Neural Network Verification
• Sharp Lower Bounds on Interpolation by Deep ReLU Neural Networks at Irregularly Spaced Data
• Contraction Properties of the Global Workspace Primitive
• Learning Optimal Classification Trees Robust to Distribution Shifts
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting
• TopoBench: A Framework for Benchmarking Topological Deep Learning
• Large Language Model Aided QoS Prediction for Service Recommendation
• Activation degree thresholds and expressiveness of polynomial neural networks
• Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
• PinnDE: Physics-Informed Neural Networks for Solving Differential Equations
• Gradient Boosting Decision Trees on Medical Diagnosis over Tabular Data
• fLSA: Learning Semantic Structures in Document Collections Using Foundation Models
• Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
• Graph Neural Network Based Action Ranking for Planning
• Learning Spatio-Temporal Dynamics via Operator-Valued RKHS and Kernel Koopman Methods
• ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputation
• Linear cost mutual information estimation and independence test of similar performance as HSIC
• DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
• LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning
• Enhancing Trust-Region Bayesian Optimization via Newton Methods
• Breaking Through Barren Plateaus: Reinforcement Learning Initializations for Deep Variational Quantum Circuits
• Quantifying The Limits of AI Reasoning: Systematic Neural Network Representations of Algorithms
• BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration
• Enhancing Chemical Explainability Through Counterfactual Masking
• A Note on Graphon-Signal Analysis of Graph Neural Networks
• Improving Long-term Autoregressive Spatiotemporal Predictions: A Proof of Concept with Fluid Dynamics
• Sparse Autoencoders for Low-$N$ Protein Function Prediction and Design
• History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL
• Linear Trading Position with Sparse Spectrum
• Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data
• STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
• Biologically Disentangled Multi-Omic Modeling Reveals Mechanistic Insights into Pan-Cancer Immunotherapy Resistance
• Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding
• End to End Autoencoder MLP Framework for Sepsis Prediction
• Natural Image Classification via Quasi-Cyclic Graph Ensembles and Random-Bond Ising Models at the Nishimori Temperature
• Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning
• Stability and Generalization for Bellman Residuals
• Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programming
• UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
• Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement
• Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
• Federated Learning with Heterogeneous and Private Label Sets
• SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
• DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
• Recycling History: Efficient Recommendations from Contextual Dueling Bandits
• C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning
• MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processes
• Generalization Bound for a General Class of Neural Ordinary Differential Equations
• Energy-Based Flow Matching for Generating 3D Molecular Structure
• Estimating Conditional Covariance between labels for Multilabel Data
• On the Generalisation of Koopman Representations for Chaotic System Control
• FedProtoKD: Dual Knowledge Distillation with Adaptive Class-wise Prototype Margin for Heterogeneous Federated Learning
• Learning with springs and sticks
• Working My Way Back to You: Resource-Centric Next-Activity Prediction
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
• When recalling in-context, Transformers are not SSMs
• Breaking the Black Box: Inherently Interpretable Physics-Informed Machine Learning for Imbalanced Seismic Data
• Automated discovery of finite volume schemes using Graph Neural Networks
• Composition and Alignment of Diffusion Models using Constrained Learning
• Active Query Selection for Crowd-Based Reinforcement Learning
• Saddle Hierarchy in Dense Associative Memory
• Get Global Guarantees: On the Probabilistic Nature of Perturbation Robustness
• Predicting the Order of Upcoming Tokens Improves Language Modeling
• Approximating High-Dimensional Earth Mover's Distance as Fast as Closest Pair
• Cultural Dimensions of AI Perception: Charting Expectations, Risks, Benefits, Tradeoffs, and Value in Germany and China
• TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
• Safe Multiagent Coordination via Entropic Exploration
• Generative Artificial Intelligence-Supported Pentesting: A Comparison between Claude Opus, GPT-4, and Copilot
• Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis
• StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel
• TableTalk: Scaffolding Spreadsheet Development with a Language Agent
• Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
• Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials
• Faster Parameter-Efficient Tuning with Token Redundancy Reduction
• Noise-based reward-modulated learning
• A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Disease Detection from Retinal Fundus Images
• Video CLIP Model for Multi-View Echocardiography Interpretation
• Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models
• An Ontology-Driven Graph RAG for Legal Norms: A Hierarchical, Temporal, and Deterministic Approach
• Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study
• Concept-Guided Interpretability via Neural Chunking
• Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing
• RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection
• EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion
• UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
• Spectra-to-Structure and Structure-to-Spectra Inference Across the Periodic Table
• An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
• Solar Altitude Guided Scene Illumination
• Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing
• Demographic-aware fine-grained classification of pediatric wrist fractures
• Apple Intelligence Foundation Language Models: Tech Report 2025
• Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMs
• Data-driven models for production forecasting and decision supporting in petroleum reservoirs
• A Fast and Minimal System to Identify Depression Using Smartphones: Explainable Machine Learning-Based Approach
• Secure Reinforcement Learning via Shuffle Privacy Model
• From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
• Hierarchical Object-Oriented POMDP Planning for Object Rearrangement
• Perception Gaps in Risk, Benefit, and Value Between Experts and Public Challenge Socially Accepted AI
• CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers
• Optimization of Latent-Space Compression using Game-Theoretic Techniques for Transformer-Based Vector Search
• HAEPO: History-Aggregated Exploratory Policy Optimization
• pyFAST: A Modular PyTorch Framework for Time Series Modeling with Multi-source and Sparse Data
• Interpretable Decision-Making for End-to-End Autonomous Driving
• Distance-informed Neural Processes
• SegReConcat: A Data Augmentation Method for Voice Anonymization Attack
• Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
• HOTSPOT-YOLO: A Lightweight Deep Learning Attention-Driven Model for Detecting Thermal Anomalies in Drone-Based Solar Photovoltaic Inspections
• HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling
• Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework
• The point is the mask: scaling coral reef segmentation with weak supervision
• PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbations
• Interpretable by AI Mother Tongue: Native Symbolic Reasoning in Neural Models
• Automatic Prompt Optimization with Prompt Distillation
• GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
• RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation
• STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
• Metric Matters: A Formal Evaluation of Similarity Measures in Active Learning for Cyber Threat Intelligence
• No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes
• Tackling Federated Unlearning as a Parameter Estimation Problem
• Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
• Attackers Strike Back? Not Anymore - An Ensemble of RL Defenders Awakens for APT Detection
• An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
• HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance
• APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration
• SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications
• ZeST: an LLM-based Zero-Shot Traversability Navigation for Unknown Environments
• Uncertainty-Resilient Active Intention Recognition for Robotic Assistants
• RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
• Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents
• From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
• Real-Time Model Checking for Closed-Loop Robot Reactive Planning
• Emotions as Ambiguity-aware Ordinal Representations
• Understanding Tool-Integrated Reasoning
• LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding
• VibeVoice Technical Report
• Interpolating Speaker Identities in Embedding Space for Data Expansion
• Generative Interfaces for Language Models
• A Survey on Causal Discovery: Theory and Practice
• Integrating Large Language Model for Improved Causal Discovery
• Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
• Pessimistic Iterative Planning with RNNs for Robust POMDPs
• Consensus in Motion: A Case of Dynamic Rationality of Sequential Learning in Probability Aggregation
• YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models
• The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners
• mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation
• Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions
• Multi-Agent LLMs as Ethics Advocates for AI-Based Systems
• Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing
• Beyond Discriminant Patterns: On the Robustness of Decision Rule Ensembles
• DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
• Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
• Memory augment is All You Need for image restoration
• Learning county from pixels: corn yield prediction with attention-weighted multiple instance learning
• Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis
• Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
• ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
• GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration
• Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning
• HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation
• Benchmarking XAI Explanations with Human-Aligned Evaluations
• Overcoming label shift with target-aware federated learning
• H-PRM: A Pluggable Hotword Pre-Retrieval Module for Various Speech Recognition Systems
• Federative ischemic stroke segmentation as alternative to overcome domain-shift multi-institution challenges
• Can VLMs Recall Factual Associations From Visual References?
• Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
• Learning Explainable Imaging-Genetics Associations Related to a Neurological Disorder
• scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
• SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds
• CoPE: A Lightweight Complex Positional Encoding
• What Matters in Data for DPO?
• ProtoEHR: Hierarchical Prototype Learning for EHR-based Healthcare Predictions
• Automated Landfill Detection Using Deep Learning: A Comparative Study of Lightweight and Custom Architectures with the AerialWaste Dataset
• Evaluating Federated Learning for At-Risk Student Prediction: A Comparative Analysis of Model Complexity and Data Balancing
• Does Calibration Affect Human Actions?
• LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
• Structures Meet Semantics: Multimodal Fusion via Graph Contrastive Learning
• Facilitating Matches on Allocation Platforms
• EAI-Avatar: Emotion-Aware Interactive Talking Head Generation
• Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails
• Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning
• Mining the Long Tail: A Comparative Study of Data-Centric Criticality Metrics for Robust Offline Reinforcement Learning in Autonomous Motion Planning
• Toward Generalized Autonomous Agents: A Neuro-Symbolic AI Framework for Integrating Social and Technical Support in Education
• Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering
• Low-Rank Tensor Decompositions for the Theory of Neural Networks
• CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering
• A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
• SwiftF0: Fast and Accurate Monophonic Pitch Detection
• How Reliable are LLMs for Reasoning on the Re-ranking task?
• VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning
• Vectorized Attention with Learnable Encoding for Quantum Transformer
• Principled Detection of Hallucinations in Large Language Models via Multiple Testing
• DRTA: Dynamic Reward Scaling for Reinforcement Learning in Time Series Anomaly Detection
• Collaborative Intelligence: Topic Modelling of Large Language Model use in Live Cybersecurity Operations
• Data Augmentation Improves Machine Unlearning
• Analise de Desaprendizado de Maquina em Modelos de Classificacao de Imagens Medicas
• A Deep Learning Application for Psoriasis Detection
• SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors
• Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learning
• The Quasi-Creature and the Uncanny Valley of Agency: A Synthesis of Theory and Evidence on User Interaction with Inconsistent Generative AI
• DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model
• A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants
• What do language models model? Transformers, automata, and the format of thought
• Scaling Laws for Task-Stratified Knowledge in Post-Training Quantized Large Language Models
• ROSE: Remove Objects with Side Effects in Videos
• LaQual: A Novel Framework for Automated Evaluation of LLM App Quality
• Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection
• PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
• Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
• The Sound of Risk: A Multimodal Physics-Informed Acoustic Model for Forecasting Market Volatility and Enhancing Market Interpretability
• FFT-MoE: Efficient Federated Fine-Tuning for Foundation Models via Large-scale Sparse MoE under Heterogeneous Edge
• Membership Inference Attacks on LLM-based Recommender Systems
• Auditing Approximate Machine Unlearning for Differentially Private Models
• Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
• Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
• FALCON: Autonomous Cyber Threat Intelligence Mining with LLMs for IDS Rule Generation
• AgriChrono: A Multi-modal Dataset Capturing Crop Growth and Lighting Variability with a Field Robot
• Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare
• Cross-Learning Fine-Tuning Strategy for Dysarthric Speech Recognition Via CDSD database
• Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion
• SkyTrust: Blockchain-Enhanced UAV Security for NTNs with Dynamic Trust and Energy-Aware Consensus
• FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks
• M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations
• Text to Query Plans for Question Answering on Large Tables
• Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
• Long-Term Variability in Physiological-Arousal Relationships for Robust Emotion Estimation
• Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
• EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding
• A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally
• ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
• ReflectivePrompt: Reflective evolution in autoprompting algorithms
• AI LLM Proof of Self-Consciousness and User-Specific Attractors
• Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
• PKG-DPO: Optimizing Domain-Specific AI systems with Physics Knowledge Graphs and Direct Preference Optimization
• The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game
• Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
• Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study
• Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Features
• Generic Guard AI in Stealth Game with Composite Potential Fields
• A Database-Driven Framework for 3D Level Generation with LLMs
• SchemaCoder: Automatic Log Schema Extraction Coder with Residual Q-Tree Boosting
• eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
• RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing
• Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
• MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use
• AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance
• VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft
• Bias Mitigation Agent: Optimizing Source Selection for Fair and Balanced Knowledge Retrieval
• CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution
• Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Prediction
• Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
• Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units
• AniME: Adaptive Multi-Agent Planning for Long Animation Generation
• CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
• Judicial Requirements for Generative AI in Legal Reasoning
• Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks
• FormaRL: Enhancing Autoformalization with no Labeled Data
• Who Is Lagging Behind: Profiling Student Behaviors with Graph-Level Encoding in Curriculum-Based Online Learning Systems
• VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
• Novel Approaches to Artificial Intelligence Development Based on the Nearest Neighbor Method
• Enabling MoE on the Edge via Importance-Driven Expert Scheduling
• AI Models Exceed Individual Human Accuracy in Predicting Everyday Social Norms
• Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
• Sense of Self and Time in Borderline Personality. A Comparative Robustness Study with Generative AI
• MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP
• Investigating Advanced Reasoning of Large Language Models via Black-Box Interaction
• A Concurrent Modular Agent: Framework for Autonomous LLM Agents
• Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty
• Trustworthy Agents for Electronic Health Records through Confidence Estimation
• Reasoning LLMs in the Medical Domain: A Literature Survey
• Hybrid Deep Searcher: Integrating Parallel and Sequential Search Reasoning
• Algorithmic Collective Action with Multiple Collectives
• Playstyle and Artificial Intelligence: An Initial Blueprint Through the Lens of Video Games
• MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation
• The Ramon Llull's Thinking Machine for Automated Ideation
• The Subset Sum Matching Problem
• StepWiser: Stepwise Generative Judges for Wiser Reasoning
• Model Context Protocols in Adaptive Transport Systems: A Survey
• Technology-assisted Personalized Yoga for Better Health - Challenges and Outlook
• Multi-Modal Drift Forecasting of Leeway Objects via Navier-Stokes-Guided CNN and Sequence-to-Sequence Attention-Based Models
• Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology
• Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models
• Towards Training-Free Underwater 3D Object Detection from Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches
• MobileDenseAttn:A Dual-Stream Architecture for Accurate and Interpretable Brain Tumor Detection