AI Research News Feeds for October 2nd, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
• Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking
• IC-Custom: Diverse Image Customization via In-Context Learning
• Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner
• Semi-Supervised Unconstrained Head Pose Estimation in the Wild
• Scheduling Weight Transitions for Quantization-Aware Training
• DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection
• SL$^{2}$A-INR: Single-Layer Learnable Activation for Implicit Neural Representation
• Rectified Diffusion Guidance for Conditional Generation
• Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel KAN Adapter for Enhanced Feature Adaptation
• Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
• SEE: See Everything Every Time -- Adaptive Brightness Adjustment for Broad Light Range Images via Events
• Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
• H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
• SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework
• STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence
• ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction
• A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
• Visual Self-Refinement for Autoregressive Models
• SoftCFG: Uncertainty-guided Stable Guidance for Visual autoregressive Model
• POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
• ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
• Towards Adversarial Training under Hyperspectral Images
• Instant4D: 4D Gaussian Splatting in Minutes
• EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
• IMAGEdit: Let Any Subject Transform
• Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
• Adapting Large Language Models to Mitigate Skin Tone Biases in Clinical Dermatology Tasks: A Mixed-Methods Study
• Variable Rate Image Compression via N-Gram Context based Swin-transformer
• Behavioural Classification in C. elegans: a Spatio-Temporal Analysis of Locomotion
• A Fast and Precise Method for Searching Rectangular Tumor Regions in Brain MR Images
• Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation
• ProtoMask: Segmentation-Guided Prototype Learning
• Graph Integrated Multimodal Concept Bottleneck Model
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs
• Deep learning motion correction of quantitative stress perfusion cardiovascular magnetic resonance
• DEAP DIVE: Dataset Investigation with Vision transformers for EEG evaluation
• Defect Segmentation in OCT scans of ceramic parts for non-destructive inspection using deep learning
• ZQBA: Zero Query Black-box Adversarial Attack
• From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation
• PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
• NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
• PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
• Equivariant Splitting: Self-supervised learning from incomplete data
• Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
• InfVSR: Breaking Length Limits of Generic Video Super-Resolution
• JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
• Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation
• Assessing Foundation Models for Mold Colony Detection with Limited Training Data
• Arbitrary Generative Video Interpolation
• Color Models in Image Processing: A Review and Experimental Comparison
• Multi-level Dynamic Style Transfer for NeRFs
• LVLMs as inspectors: an agentic framework for category-level structural defect annotation
• Disentangling Foreground and Background for vision-Language Navigation via Online Augmentation
• Robust Context-Aware Object Recognition
• UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs
• LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection
• Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
• FIN: Fast Inference Network for Map Segmentation
• OTTER: Open-Tagging via Text-Image Representation for Multi-modal Understanding
• Weakly Supervised Cloud Detection Combining Spectral Features and Multi-Scale Deep Network
• Unsupervised Unfolded rPCA (U2-rPCA): Deep Interpretable Clutter Filtering for Ultrasound Microvascular Imaging
• Beyond one-hot encoding? Journey into compact encoding for large multi-class segmentation
• OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides Understanding
• Improved Hyperspectral Anomaly Detection via Unsupervised Subspace Modeling in the Signed Cumulative Distribution Transform Domain
• PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents
• BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
• VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
• MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzles
• Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
• Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
• CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?
• Hearing the Order: Investigating Selection Bias in Large Audio-Language Models
• Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting
• Improving Code Localization with Repository Memory
• Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
• Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
• Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions
• Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
• GuRE:Generative Query REwriter for Legal Passage Retrieval
• Precise Information Control in Long-Form Text Generation
• Through the Valley: Path to Effective Long CoT Training for Small Language Models
• REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
• CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
• Retain or Reframe? A Computational Framework for the Analysis of Framing in News Articles and Reader Comments
• Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?
• CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
• MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
• Family Matters: Language Transfer and Merging for Adapting Small LLMs to Faroese
• Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
• ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
• HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
• Making, not Taking, the Best of N
• Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks
• Syntax-Guided Diffusion Language Models with User-Integrated Personalization
• Research on the Integration of Embodied Intelligence and Reinforcement Learning in Textual Domains
• Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review
• Pay-Per-Search Models are Abstention Models
• Energy-Regularized Sequential Model Editing on Hyperspheres
• Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches
• QSearchNet: A Quantum Walk Search Framework for Link Prediction
• When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models
• TAMA: Tool-Augmented Multimodal Agent for Procedural Activity Understanding
• DRBench: A Realistic Benchmark for Enterprise Deep Research
• PrimeX: A Dataset of Worldview, Opinion, and Explanation
• Judging with Confidence: Calibrating Autoraters to Preference Distributions
• ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment
• CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage
• TokMem: Tokenized Procedural Memory for Large Language Models
• LongCodeZip: Compress Long Context for Code Language Models
• Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
• Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains
• Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations
• JoyAgent-JDGenie: Technical Report on the GAIA
• GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness
• ThinkBrake: Mitigating Overthinking in Tool Reasoning
• Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation
• ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
• Divergence-Based Similarity Function for Multi-View Contrastive Learning
• Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance
• Online Non-convex Optimization with Long-term Non-convex Constraints
• Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
• PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
• Statistically Truthful Auctions via Acceptance Rule
• Graph Transformer Networks for Accurate Band Structure Prediction: An End-to-End Approach
• Estimating quantum relative entropies on quantum computers
• Integration of Calcium Imaging Traces via Deep Generative Modeling
• An Iterative Bayesian Approach for System Identification based on Linear Gaussian Models
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• OBELiX: A Curated Dataset of Crystal Structures and Experimentally Measured Ionic Conductivities for Lithium Solid-State Electrolytes
• Toward a Robust R2D2 Paradigm for Radio-interferometric Imaging: Revisiting Deep Neural Network Training and Architecture
• Is Limited Participant Diversity Impeding EEG-based Machine Learning?
• Robustness and sex differences in skin cancer detection: logistic regression vs CNNs
• Learning simple heuristic rules for classifying materials based on chemical composition
• EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming
• Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
• Gauges and Accelerated Optimization over Smooth and/or Strongly Convex Sets
• Mutual information maximizing quantum generative adversarial networks
• The causal structure of galactic astrophysics
• Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem
• The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
• SMaRt: Improving GANs with Score Matching Regularity
• Neural Network Characterization and Entropy Regulated Data Balancing through Principal Component Analysis
• Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
• Out-of-Distribution Detection with Relative Angles
• Krony-PT: GPT2 compressed with Kronecker Products
• CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning
• Prompt Tuning Decision Transformers with Structured and Scalable Bandits
• Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
• Federated Dynamic Modeling and Learning for Spatiotemporal Data Forecasting
• Rapid training of Hamiltonian graph networks using random features
• Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving
• LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
• Scaling Linear Attention with Sparse State Expansion
• Parametric modeling of shear wave velocity profiles for the conterminous U.S
• A Deep Learning Pipeline for Epilepsy Genomic Analysis Using GPT-2 XL and NVIDIA H100
• Improving Virtual Contrast Enhancement using Longitudinal Data
• EuroSpeech: A Multilingual Speech Corpus
• Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
• Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset
• Multi-Domain Brain Vessel Segmentation Through Feature Disentanglement
• A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models
• Stochastic Self-Organization in Multi-Agent Systems
• Discovering Communities in Continuous-Time Temporal Networks by Optimizing L-Modularity
• GeoGraph: Geometric and Graph-based Ensemble Descriptors for Intrinsically Disordered Proteins
• AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
• COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates
• Modeling Market States with Clustering and State Machines
• Secure and reversible face anonymization with diffusion models
• Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
• Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
• FTSCommDetector: Discovering Behavioral Communities through Temporal Synchronization
• A Recall-First CNN for Sleep Apnea Screening from Snoring Audio
• DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
• Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
• Revealing the temporal dynamics of antibiotic anomalies in the infant gut microbiome with neural jump ODEs
• Quantum reservoir computing using Jaynes-Cummings model
• Learning from the electronic structure of molecules across the periodic table
• Board Gender Diversity and Carbon Emissions Performance: Insights from Panel Regressions, Machine Learning and Explainable AI
• Low Resource Audio Codec Challenge Baseline Systems
• SafePassage: High-Fidelity Information Extraction with Black Box LLMs
• Electron neural closure for turbulent magnetosheath simulations: energy channels
• Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization
• Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
• End-to-end Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation
• Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
• Gated X-TFC: Soft Domain Decomposition for Forward and Inverse Problems in Sharp-Gradient PDEs
• Eliciting Secret Knowledge from Language Models
• Predicting Diabetic Retinopathy Using a Two-Level Ensemble Model
• Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method
• Dynamical system reconstruction from partial observations using stochastic dynamics
• Geometric Properties of Neural Multivariate Regression
• Augmenting LLMs for General Time Series Understanding and Prediction
• Privacy Preserved Federated Learning with Attention-Based Aggregation for Biometric Recognition
• Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning
• Breaking the Euclidean Barrier: Hyperboloid-Based Biological Sequence Analysis
• Prompt Curriculum Learning for Efficient LLM Post-Training
• Sample-Efficient Differentially Private Fine-Tuning via Gradient Matrix Denoising
• Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
• Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
• BroRL: Scaling Reinforcement Learning via Broadened Exploration
• Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
• In-Place Feedback: A New Paradigm for Guiding LLMs in Multi-Turn Reasoning
• Complex System Exploration with Interactive Human Guidance
• Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection
• Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
• Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?
• LLM Routing with Dueling Feedback
• Population Synthesis using Incomplete Information
• The data-quality illusion: Rethinking Classifier-based quality filtering for LLM Pretraining
• Target Population Synthesis using CT-GAN
• Reducci\'on de ruido por medio de autoencoders: caso de estudio con la se\~nal GW150914
• Rectifying Regression in Reinforcement Learning
• BoMGene: Integrating Boruta-mRMR feature selection for enhanced Gene expression classification
• Large Reasoning Models Learn Better Alignment from Flawed Thinking
• It Takes Two: Your GRPO Is Secretly DPO
• Riemannian Consistency Model
• Random Feature Spiking Neural Networks
• Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
• Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt
• Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
• Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
• Diffusion Alignment as Variational Expectation-Maximization
• Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?
• Interpretable Machine Learning for Life Expectancy Prediction: A Comparative Study of Linear Regression, Decision Tree, and Random Forest
• Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
• Probability calibration for precipitation nowcasting
• Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport
• Multi-Agent Stage-wise Conservative Linear Bandits
• Physics-Informed Extreme Learning Machine (PIELM) for Tunnelling-Induced Soil-Pile Interactions
• Comparison of Machine Learning Models to Classify Documents on Digital Development
• TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
• How Foundational are Foundation Models for Time Series Forecasting?
• LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
• Cutting the Skip: Training Residual-Free Transformers
• Initial Distribution Sensitivity of Constrained Markov Decision Processes
• Flow Autoencoders are Effective Protein Tokenizers
• AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
• Continual Learning with Query-Only Attention
• The Transformer Cookbook
• GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
• Composer: A Search Framework for Hybrid Neural Architecture Design
• Efficient Probabilistic Tensor Networks
• Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes
• Bayesian Distributional Models of Executive Functioning
• Graph2Region: Efficient Graph Similarity Learning with Structure and Scale Restoration
• Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
• Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure
• Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
• On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
• On the Soundness and Consistency of LLM Agents for Executing Test Cases Written in Natural Language
• Linear Regression in p-adic metric spaces
• Federated Learning Meets LLMs: Feature Extraction From Heterogeneous Clients
• Large Language Models Inference Engines based on Spiking Neural Networks
• RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
• Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling
• Per-example gradients: a new frontier for understanding and improving optimizers
• Reward driven discovery of the optimal microstructure representations with invariant variational autoencoders
• CODED-SMOOTHING: Coding Theory Helps Generalization
• Delayed Attention Training Improves Length Generalization in Transformer--RNN Hybrids
• Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
• Robust Federated Inference
• DiSC-AMC: Token- and Parameter-Efficient Discretized Statistics In-Context Automatic Modulation Classification
• MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolution
• EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework
• Towards a Progress Bar for Reasoning: Progress Prediction in Large Reasoning Models
• Model Parallelism With Subnetwork Data Parallelism
• Fair CCA for Fair Representation Learning: An ADNI Study
• Nonlinear Framework for Speech Bandwidth Extension
• AS400-DET: Detection using Deep Learning Model for IBM i (AS/400)
• Training-free LLM Verification via Recycling Few-shot Examples
• Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
• A Physics-Inspired Optimizer: Velocity Regularized Adam
• Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI
• Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
• Federated Causal Inference from Multi-Site Observational Data via Propensity Score Aggregation
• Steering LLM Reasoning Through Bias-Only Adaptation
• Object Centric Concept Bottlenecks
• Text-to-CT Generation via 3D Latent Diffusion Model with Contrastive Vision-Language Pretraining
• PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models
• Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning
• MLLM-CL: Continual Learning for Multimodal Large Language Models
• Estimating Visceral Adiposity from Wrist-Worn Accelerometry
• LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model
• Graphon Particle Systems, Part II: Dynamics of Distributed Stochastic Continuum Optimization
• Balancing Multimodal Training Through Game-Theoretic Regularization
• 3D Interaction Geometric Pre-training for Molecular Relational Learning
• PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
• Stability Bounds for the Unfolded Forward-Backward Algorithm
• Exploring and Controlling Diversity in LLM-Agent Conversation
• Distilling Calibration via Conformalized Credal Inference
• Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
• ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
• Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework
• Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making
• Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing
• BlobCtrl: Taming Controllable Blob for Element-level Image Editing
• TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
• R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
• MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Experts
• AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
• Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
• Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
• What if Othello-Playing Language Models Could See?
• Code Like Humans: A Multi-Agent Solution for Medical Coding
• Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
• Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
• Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing
• TabINR: An Implicit Neural Representation Framework for Tabular Data Imputation
• mR3: Multilingual Rubric-Agnostic Reward Reasoning Models
• Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
• GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
• Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
• Fiaingen: A financial time series generative method matching real-world data quality
• Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
• COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier
• TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
• NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions
• Breast Cancer Diagnosis: A Comprehensive Exploration of Explainable Artificial Intelligence (XAI) Techniques
• Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance
• PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context
• Diffusion Model-based Parameter Estimation in Dynamic Power Systems
• ViLBias: Detecting and Reasoning about Bias in Multimodal Content
• MathConstruct: Challenging LLM Reasoning with Constructive Proofs
• Neural Theorem Proving: Generating and Structuring Proofs for Formal Verification
• Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM Reasoning
• GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
• Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration
• TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes
• RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
• Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
• Bridging the Gap Between Simulated and Real Network Data Using Transfer Learning
• TextCAM: Explaining Class Activation Map with Text
• CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
• Authentic Discrete Diffusion Model
• Interpreting Language Models Through Concept Descriptions: A Survey
• GEM: A Gym for Agentic LLMs
• Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach
• CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
• Rethinking Thinking Tokens: LLMs as Improvement Operators
• A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
• Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
• Neural Diffusion Processes for Physically Interpretable Survival Prediction
• From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling
• Multi-Objective Task-Aware Predictor for Image-Text Alignment
• UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching
• Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
• MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts
• Solar PV Installation Potential Assessment on Building Facades Based on Vision and Language Foundation Models
• MG2FlowNet: Accelerating High-Reward Sample Generation via Enhanced MCTS and Greediness Control
• What You See is What You Ask: Evaluating Audio Descriptions
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
• Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead
• Feature Identification for Hierarchical Contrastive Learning
• Mechanistic Interpretability as Statistical Estimation: A Variance Analysis of EAP-IG
• Can World Models Benefit VLMs for World Dynamics?
• Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
• Copy-Paste to Mitigate Large Language Model Hallucinations
• Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
• Architectural Transformations and Emerging Verification Demands in AI-Enabled Cyber-Physical Systems
• Forestpest-YOLO: A High-Performance Detection Framework for Small Forestry Pests
• EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases
• On Predictability of Reinforcement Learning Dynamics for Large Language Models
• Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
• Panorama: Fast-Track Nearest Neighbors
• Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
• SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation
• U-DFA: A Unified DINOv2-Unet with Dual Fusion Attention for Multi-Dataset Medical Segmentation
• AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation
• FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
• Tenyidie Syllabification corpus creation and deep learning applications
• Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
• Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
• Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments
• Domain-Specialized Interactive Segmentation Framework for Meningioma Radiotherapy Planning
• Automated Structured Radiology Report Generation with Rich Clinical Context
• Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
• Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising
• UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction
• TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
• Feature Identification via the Empirical NTK
• Analyzing Latent Concepts in Code Language Models
• PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation
• Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models
• Exploring System 1 and 2 communication for latent reasoning in LLMs
• Normal-Abnormal Guided Generalist Anomaly Detection
• MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
• Relative-Absolute Fusion: Rethinking Feature Extraction in Image-Based Iterative Method Selection for Solving Sparse Linear Systems
• Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
• SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
• Data driven approaches in nanophotonics: A review of AI-enabled metadevices
• o-MEGA: Optimized Methods for Explanation Generation and Analysis
• Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
• Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
• Digital Domination: A Case for Republican Liberty in Artificial Intelligence
• DecepChain: Inducing Deceptive Reasoning in Large Language Models
• A Framework for Selection of Machine Learning Algorithms Based on Performance Metrices and Akaike Information Criteria in Healthcare, Telecommunication, and Marketing Sector
• Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
• Structural Refinement of Bayesian Networks for Efficient Model Parameterisation
• In-Context Curiosity: Distilling Exploration for Decision-Pretrained Transformers on Bandit Tasks
• Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis
• Discrete Wavelet Transform as a Facilitator for Expressive Latent Space Representation in Variational Autoencoders in Satellite Imagery
• SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
• AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
• David and Goliath in Medical Vision: Convolutional Networks vs Biomedical Vision Language Models
• BigBang-Proton Technical Report: Next-Word-Prediction is Scientific Multitask Learner
• Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback
• Partial Identification Approach to Counterfactual Fairness Assessment
• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It
• Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
• PrunedLoRA: Robust Gradient-Based structured pruning for Low-rank Adaptation in Fine-tuning
• GRPO-$\lambda$: Credit Assignment improves LLM Reasoning
• LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
• Directed-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation
• Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
• The Pitfalls of KV Cache Compression
• BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
• Debunk the Myth of SFT Generalization
• TASER: Translation Assessment via Systematic Evaluation and Reasoning
• Learning Energy-based Variational Latent Prior for VAEs
• Retrieval-Augmented Generation for Electrocardiogram-Language Models
• Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
• DexBench: Benchmarking LLMs for Personalized Decision Making in Diabetes Management
• Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language Models
• Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness
• Beyond the Prompt: Gender Bias in Text-to-Image Models, with a Case Study on Hospital Professions
• Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models
• Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
• AI-Based Stroke Rehabilitation Domiciliary Assessment System with ST_GCN Attention
• Object-AVEdit: An Object-level Audio-Visual Editing Model
• HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
• FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation
• Survey of AI-Powered Approaches for Osteoporosis Diagnosis in Medical Imaging
• Efficient CNN Compression via Multi-method Low Rank Factorization and Feature Map Similarity
• AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
• Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning
• Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey
• SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction
• Simulating Student Success in the Age of GenAI: A Kantian-Axiomatic Perspective
• Methodological Framework for Quantifying Semantic Test Coverage in RAG Systems
• IA aplicada al an\'alisis del conflicto Ir\'an-Israel: Mapeo de discursos en YouTube
• EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis
• Learning Inter-Atomic Potentials without Explicit Equivariance
• Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling
• Enhancing Safety in Diabetic Retinopathy Detection: Uncertainty-Aware Deep Learning Models with Rejection Capabilities
• Temporal-Aware Iterative Speech Model for Dementia Detection
• VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs
• WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities
• Hybrid Deep Learning for Hyperspectral Single Image Super-Resolution
• Review of Hallucination Understanding in Large Language and Vision Models
• Deep Learning-Based Pneumonia Detection from Chest X-ray Images: A CNN Approach with Performance Analysis and Clinical Implications
• On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
• FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
• On Discovering Algorithms for Adversarial Imitation Learning
• Test-Time Search in Neural Graph Coarsening Procedures for the Capacitated Vehicle Routing Problem
• A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
• QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
• Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer
• Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling
• Uncovering the Computational Ingredients of Human-Like Representations in LLMs
• Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
• Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning
• Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
• Optimizing Fairness in Production Planning: A Human-Centric Approach to Machine and Workforce Allocation
• PRISM-Consult: A Panel-of-Experts Architecture for Clinician-Aligned Diagnosis
• Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
• Apriel-1.5-15b-Thinker
• Generalized Parallel Scaling with Interdependent Generations
• MARS: Audio Generation via Multi-Channel Autoregression on Spectrograms
• Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction
• Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
• Batch-CAM: Introduction to better reasoning in convolutional deep learning models
• Relevance-Zone Reduction in Game Solving
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning
• EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty
• DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
• AI in data science education: experiences from the classroom
• Benchmarking Agentic Systems in Automated Scientific Information Extraction with ChemX
• Semantic Bridges Between First Order c-Representations and Cost-Based Semantics: An Initial Perspective
• Logical Consistency Between Disagreeing Experts and Its Role in AI Safety
• Benchmarking Machine Learning Models for Fault Classification and Localization in Power System Protection
• Improving Cryptocurrency Pump-and-Dump Detection through Ensemble-Based Models and Synthetic Oversampling Techniques
• Learning Compact Representations of LLM Abilities via Item Response Theory
• Unveiling Interesting Insights: Monte Carlo Tree Search for Knowledge Discovery
• DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems
• MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
• ICL Optimized Fragility
• BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
• When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Markets
• Hierarchical Reasoning Model: A Critical Supplementary Material
• Semantic-Driven AI Agent Communications: Challenges and Solutions
• Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm
• Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization
• Expandable Decision-Making States for Multi-Agent Deep Reinforcement Learning in Soccer Tactical Analysis
• Rethinking Reward Models for Multi-Domain Test-Time Scaling
• VIRTUE: Visual-Interactive Text-Image Universal Embedder
• Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation
• Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation
• Learning to Lead Themselves: Agentic AI in MAS using MARL
• ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
• ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models
• NeurIPS should lead scientific consensus on AI policy
• Towards a Framework for Supporting the Ethical and Regulatory Certification of AI Systems
• Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction
• AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery
• Object-Centric Case-Based Reasoning via Argumentation
• Thinkquel: A Model Dedicated to Text-to-dbt Using Synthetic Data and a Span-Aware Objective
• Synthetic Census Data Generation via Multidimensional Multiset Sum
• A Framework for Double-Blind Federated Adaptation of Foundation Models
• Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
• A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions
• Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
• COOKIEGUARD: Characterizing and Isolating the First-Party Cookie Jar
• Noninterference Analysis of Irreversible or Reversible Systems with Nondeterminism and Probabilities
• A Hitchhiker's Guide to Privacy-Preserving Digital Payment Systems: A Survey on Anonymity, Confidentiality, and Auditability
• gh0stEdit: Exploiting Layer-Based Access Vulnerability Within Docker Container Images
• Extended c-differential distinguishers of full 9 and reduced-round Kuznyechik cipher
• Vectorised Hashing Based on Bernstein-Rabin-Winograd Polynomials over Prime Order Fields
• Verifiability and Privacy in Federated Learning through Context-Hiding Multi-Key Homomorphic Authenticators
• B-Privacy: Defining and Enforcing Privacy in Weighted Voting
• Differential Privacy of Network Parameters from a System Identification Perspective
• Blockchain-Based Secure Online Voting Platform Ensuring Voter Anonymity, Integrity, and End-to-End Verifiability
• Hot PATE: Private Aggregation of Distributions for Diverse Task
• Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
• Universally Composable Termination Analysis of Tendermint
• EditTrack: Detecting and Attributing AI-assisted Image Editing
• Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
• MOLM: Mixture of LoRA Markers
• Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
• LSPFuzz: Hunting Bugs in Language Servers
• Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
• Maven-Lockfile: High Integrity Rebuild of Past Java Releases
• Computational Monogamy of Entanglement and Non-Interactive Quantum Key Distribution
• Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
• Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
• HVAC-EAR: Eavesdropping Human Speech Using HVAC Systems
• Backdoor Attacks Against Speech Language Models
• Stealing AI Model Weights Through Covert Communication Channels
• Calyx: Privacy-Preserving Multi-Token Optimistic-Rollup Protocol
• CHAI: Command Hijacking against embodied AI
• SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
• MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement
• Privately Estimating Black-Box Statistics
• Security and Privacy Analysis of Tile's Location Tracking Protocol
• A Call to Action for a Secure-by-Design Generative AI Paradigm
• Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensics
• Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models
• Memory-Augmented Log Analysis with Phi-4-mini: Enhancing Threat Detection in Structured Security Logs
• Sentry: Authenticating Machine Learning Artifacts on the Fly
• IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
• A Monoid Ring Approach to Color Visual Cryptography
• HLTCOE at TREC 2024 NeuCLIR Track
• Privacy-Preserving Learning-Augmented Data Structures
• Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
• On Listwise Reranking for Corpus Feedback
• Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
• Deep Learning-Based Approach for Improving Relational Aggregated Search
• ModernVBERT: Towards Smaller Visual Document Retrievers
• AutoPK: Leveraging LLMs and a Hybrid Similarity Metric for Advanced Retrieval of Pharmacokinetic Data from Complex Tables and Documents
• Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?
• ALARB: An Arabic Legal Argument Reasoning Benchmark
• AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment
• Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
• PaECTER: Patent-level Representation Learning using Citation-informed Transformers
• Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems
• Stop Misusing t-SNE and UMAP for Visual Analytics
• Designing Psychometric Bias Measures for ChatBots: An Application to Racial Bias Measurement
• Confirmation Bias as a Cognitive Resource in LLM-Supported Deliberation
• "Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection
• Grounded GUI Understanding for Vision-Based Spatial Intelligent Agent: Exemplified by Extended Reality Apps
• XRZoo: A Large-Scale and Versatile Dataset of Extended Reality (XR) Applications
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system
• Motion In-Betweening for Densely Interacting Characters
• ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction
• Audio Driven Real-Time Facial Animation for Social Telepresence
• Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees
• Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval
• Virtual Reality Alters Perceived Functional Body Size
• "We are not Future-ready": Understanding AI Privacy Risks and Existing Mitigation Strategies from the Perspective of AI Developers in Europe
• Social Photo-Elicitation: The Use of Communal Production of Meaning to Hear a Vulnerable Population
• Intelligent 5S Audit: Application of Artificial Intelligence for Continuous Improvement in the Automotive Industry
• Multidimensional Bayesian Active Machine Learning of Working Memory Task Performance
• Make a Video Call with LLM: A Measurement Campaign over Five Mainstream Apps
• Data Quality Challenges in Retrieval-Augmented Generation
• AI Where It Matters: Where, Why, and How Developers Want AI Support in Daily Work
• A Visual Diagnostics Framework for District Heating Data: Enhancing Data Quality for AI-Driven Heat Consumption Prediction
• A Technique Based on Trade-off Maps to Visualise and Analyse Relationships Between Objectives in Optimisation Problems
• Visualizing Quantum Circuits: State Vector Difference Highlighting and the Half-Matrix
• Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
• Disc-Cover Complexity Trends in Music Illustrations from Sinatra to Swift
• Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
• Code2Video: A Code-centric Paradigm for Educational Video Generation
• DISCOVER: Data-driven Identification of Sub-activities via Clustering and Visualization for Enhanced Activity Recognition in Smart Homes
• Perceived Weight of Mediated Reality Sticks
• Data Melodification FM: Where Musical Rhetoric Meets Sonification
• Can AI agents understand spoken conversations about data visualizations in online meetings?
• Visualization Was Here: Reorienting Research When Visualizations Fade into the Background
• Navigating the Synchrony-Stability Frontier in Adaptive Chatbots
• The Feng Shui of Visualization: Design the Path to SUCCESS and GOOD FORTUNE
• Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
• Investigating Encoding and Perspective for Augmented Reality
• RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative Simulations
• Face2Feel: Emotion-Aware Adaptive User Interface
• PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering
• Rethinking Wine Tasting for Chinese Consumers: A Service Design Approach Enhanced by Multimodal Personalization
• Designing Wine Tasting Experiences for All: The role of Human Diversity and Personal food memory
• Datasets for Valence and Arousal Inference: A Survey
• ImpedanceGPT: VLM-driven Impedance Control of Swarm of Mini-drones for Intelligent Navigation in Dynamic Environment
• Adaptive Diffusion Constrained Sampling for Bimanual Robot Manipulation
• Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
• Heterogeneous Predictor-based Risk-Aware Planning with Conformal Prediction in Dense, Uncertain Environments
• Sampling-Based Global Optimal Control and Estimation via Semidefinite Programming
• Probabilistic Collision Risk Estimation through Gauss-Legendre Cubature and Non-Homogeneous Poisson Processes
• How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy
• RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems
• DBF-MA: A Differential Bayesian Filtering Planner for Multi-Agent Autonomous Racing Overtakes
• Certifiably Optimal Estimation and Calibration in Robotics via Trace-Constrained Semi-Definite Programming
• HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera
• On the Application of Model Predictive Control to a Weighted Coverage Path Planning Problem
• Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
• Real-Time Trajectory Generation and Hybrid Lyapunov-Based Control for Hopping Robots
• Less is More: Lean yet Powerful Vision-Language Model for Autonomous Driving
• The Formation of Trust in Autonomous Vehicles after Interacting with Robotaxis on Public Roads
• Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI
• Robust Attitude Control of Nonlinear Multi-Rotor Dynamics with LFT Models and $\mathcal{H}_\infty$ Performance
• A Hierarchical Agentic Framework for Autonomous Drone-Based Visual Inspection
• EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations
• Conflict-Based Search as a Protocol: A Multi-Agent Motion Planning Protocol for Heterogeneous Agents, Solvers, and Independent Tasks
• KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
• Predictive Control Barrier Functions for Discrete-Time Linear Systems with Unmodeled Delays
• Strategic Fusion of Vision Language Models: Shapley-Credited Context-Aware Dawid-Skene for Multi-Label Tasks in Autonomous Driving
• Active Shadowing (ASD): Manipulating Perception of Robotic Behaviors via Implicit Virtual Communication
• Optimization-based Task and Motion Planning under Signal Temporal Logic Specifications using Logic Network Flow
• HetSwarm: Cooperative Navigation of Heterogeneous Swarm in Dynamic and Dense Environments through Impedance-based Guidance
• GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks
• Hybrid Training for Vision-Language-Action Models
• What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Planners
• Trajectory Based Observer Design: A Framework for Lightweight Sensor Fusion
• Enabling High-Frequency Cross-Modality Visual Positioning Service for Accurate Drone Landing
• Shared Object Manipulation with a Team of Collaborative Quadrupeds
• HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
• MultiPhysio-HRC: Multimodal Physiological Signals Dataset for industrial Human-Robot Collaboration
• CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation
• Tele-rehabilitation with online skill transfer and adaptation in $\mathbb{R}^3 \times \mathit{S}^3$
• Semantic Visual Simultaneous Localization and Mapping: A Survey on State of the Art, Challenges, and Future Directions
• RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator
• Product-oriented Product-Process-Resource Asset Network and its Representation in AutomationML for Asset Administration Shell
• Non-submodular Visual Attention for Robot Navigation
• ROSflight 2.0: Lean ROS 2-Based Autopilot for Unmanned Aerial Vehicles
• Prometheus: Universal, Open-Source Mocap-Based Teleoperation System with Force Feedback for Dataset Collection in Robot Learning
• ROSplane 2.0: A Fixed-Wing Autopilot for Research
• The Gauss-Markov Adjunction Provides Categorical Semantics of Residuals in Supervised Learning
• RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modes
• A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
• A Novel Robust Control Method Combining DNN-Based NMPC Approximation and PI Control: Application to Exoskeleton Squat Movements
• TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
• BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control
• Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning
• DiSA-IQL: Offline Reinforcement Learning for Robust Soft Robot Control under Distribution Shifts
• Physics-Informed Neural Controlled Differential Equations for Scalable Long Horizon Multi-Agent Motion Forecasting
• VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
• Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
• Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation
• From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment
• Two stage GNSS outlier detection for factor graph optimization based GNSS-RTK/INS/odometer fusion
• How Does the Pretraining Distribution Shape In-Context Learning? Task Selection, Generalization, and Robustness
• A first-order method for constrained nonconvex--nonconcave minimax problems under a local Kurdyka-{\L}ojasiewicz condition
• On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
• Propagating Model Uncertainty through Filtering-based Probabilistic Numerical ODE Solvers
• Learning linear dynamical systems under convex constraints
• On the Natural Gradient of the Evidence Lower Bound
• A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
• Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
• Learning to Dissipate Energy in Oscillatory State-Space Models
• Learning to Rank Chain-of-Thought: Using a Small Model
• Direct Preference Optimization for Adaptive Concept-based Explanations
• Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model
• Accurate Estimation of Mutual Information in High Dimensional Data
• Guided Speculative Inference for Efficient Test-Time Alignment of LLMs
• Minimax and Bayes Optimal Best-Arm Identification
• Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
• Deep Learning Approaches with Explainable AI for Differentiating Alzheimer Disease and Mild Cognitive Impairment
• Directed Information $\gamma$-covering: An Information-Theoretic Framework for Context Engineering
• Approximately Unimodal Likelihood Models for Ordinal Regression
• Nonparametric Identification of Latent Concepts
• Lipschitz Bandits with Stochastic Delayed Feedback
• Train on Validation (ToV): Fast data selection with applications to fine-tuning
• Progressively Sampled Equality-Constrained Optimization
• Robust Spatiotemporally Contiguous Anomaly Detection Using Tensor Decomposition
• On the joint observability of flow fields and particle properties from Lagrangian trajectories: evidence from neural data assimilation
• Mathematical Theory of Collinearity Effects on Machine Learning Variable Importance Measures
• Error Feedback for Muon and Friends
• Learn to Guide Your Diffusion Model
• Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
• False Discovery Rate Control via Bayesian Mirror Statistic
• The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
• Equivariant Geometric Scattering Networks via Vector Diffusion Wavelets
• Identifying All {\epsilon}-Best Arms in (Misspecified) Linear Bandits
• Private Learning of Littlestone Classes, Revisited
• CINDES: Classification induced neural density estimator and simulator
• On the Adversarial Robustness of Learning-based Conformal Novelty Detection
• A universal compression theory: Lottery ticket hypothesis and superpolynomial scaling laws
• Bayesian Neural Networks for Functional ANOVA model
• Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
• Approximation of differential entropy in Bayesian optimal experimental design
• Optimal placement of wind farms via quantile constraint learning