Skip to main content

Delete

Are you sure you want to delete the Feed “https://rss.arxiv.org/rss/cs”? All of the following related items will be deleted:

Summary

  • Feeds: 1
  • Entries: 504

Objects

  • Feed: https://rss.arxiv.org/rss/cs
    • Entry: Spectral origin of the topological gap exponent d + {\eta}: mechanism, kernel, decomposition, and scope
    • Entry: LBFAST: A Lightweight Moment-Represented Lattice Boltzmann Solver for Multi-GPU Architectures
    • Entry: SMCC-Empowered Digital Twins for Sensorless Monitoring in Large-Scale AI-Driven IoT Systems
    • Entry: Physics-informed neural networks by Gradient-Guided Gaussian Adaptive Sampling (3GAS-PINNs)
    • Entry: World-Time Compute with Verified Code World Models
    • Entry: HELIOS: Guardrailed LLM-Driven Evolution of Autonomous Resource Orchestration Policies for Multi-Cloud Distributed Systems
    • Entry: TFR-GNN: Topology- and Fault-Aware Graph Neural Scheduling for Heterogeneous Distributed Computing Systems
    • Entry: X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding
    • Entry: OASIS: A Rubric-Based Multimodal Assessment Platform Using Large Language Models
    • Entry: Evaluating Enterprise Analytics Agents: An End-to-End, Trace-Backed Methodology
    • Entry: Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence
    • Entry: Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification
    • Entry: M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
    • Entry: AgenticGen: Reward-Guided Agentic Video Generation for Advertising
    • Entry: Lensless Gaze Is Not Private by Default: Auditing Identity Leakage Across Disclosure Surfaces
    • Entry: CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting
    • Entry: OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows
    • Entry: MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
    • Entry: Shift-Accumulate Attention: Multiplier-Free Query--Key Products for Transformer Decoding
    • Entry: Identifying Habit, Physics, and Nuisance in Robot World Models
    • Entry: The Internet of Collaborating Things: Agentic Edge AI for Autonomous Cross-Domain Collaboration
    • Entry: The Privacy Subsidy in Market Microstructure
    • Entry: MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated Learning
    • Entry: Optimal Networks with Accumulative Costs and Bidirectional Communication
    • Entry: From Token Interfaces to Token Semantics: A Formal Composition and Conformance Model for Implementation-Neutral Token Specifications
    • Entry: When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems
    • Entry: Compass: Dissecting Communication and Computation Operators for Efficient LLM Training
    • Entry: Optimizing AI Inference Across the Deployment Stack
    • Entry: Design and Operation of a Federated GPU Cluster for Digital Humanities within DHinfra.at
    • Entry: Memory Profiling and Migration for Heterogeneous Memory Architectures
    • Entry: MLN-EIGS: A multilayer network framework for solving Stackelberg escape interdiction games on dynamic transportation networks
    • Entry: Why Customer Choice Models Matter
    • Entry: M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction
    • Entry: Who Pays for a Connected Public Good?
    • Entry: Rethinking Handwritten Character Recognition
    • Entry: Strategic Information Transmission over Gossip Networks
    • Entry: Collective Hysteresis and Multistability in Threshold Networks
    • Entry: Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement
    • Entry: EFX Allocations for Three Agents and Seven or Eight Chores
    • Entry: Threshold-Based Selection for Continuous Optimization: A Leaf-Abscission Instantiation
    • Entry: MaRDMO: FAIR Documentation of In-Silico Research
    • Entry: Throughput per Megabyte: A Pilot Benchmark of Language-Stack Efficiency for Self-Hosted HTTP Services on a Raspberry Pi 5
    • Entry: Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems
    • Entry: Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators
    • Entry: One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training
    • Entry: Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
    • Entry: Hardware-Attributed Operator Profiling for PyTorch
    • Entry: Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge
    • Entry: The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices
    • Entry: A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFD
    • Entry: Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation
    • Entry: PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale
    • Entry: Asynchronous Parallel Search for Exact Multi-Objective Shortest Paths with Versioned Frontier Snapshots and Indexed Dominance Pruning
    • Entry: Who Are We Recommending To? Recommender Systems in the Agentic Web
    • Entry: Hyperion: An AI-powered HPC cluster for sciences and humanities research that utilizes ML for predicting job turnaround time
    • Entry: Scenario-Independent Criticality Assessment and Prediction for Vulnerable Road Users in Autonomous Driving
    • Entry: MemRetriever: Learning to Search, Reflect, and Retrieve from Long-Term Memory
    • Entry: ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents
    • Entry: InitGen: Candidate Generation for Interaction Initiation in Intelligent Assistants
    • Entry: Efficient AI Model Deployment Using Quantization Analysis Tool
    • Entry: Refracted Light Interaction in Turbulent Bubbling Water (RLITBW): A Macroscopic Fluid-Optic Entropy Source
    • Entry: When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels
    • Entry: BudgetBench: A Budget-Tiered Protocol and Pilot Harness for Memory Strategy Evaluation in Local Large Language Model Agents
    • Entry: The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech
    • Entry: Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning
    • Entry: PhysMent: An Interactive Approach For LLM Reasoning In Physics Problems
    • Entry: DVFS for Small Language Model Inference on Mobile Edge Devices
    • Entry: Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories
    • Entry: PAUSE: A Privacy-Preserving Self-Reflection Tool for AI-Associated Cognitive Offloading
    • Entry: Modeling Quantum Computing with $\pi$-calculus
    • Entry: Partitioning-free 3D-IC Floorplanning
    • Entry: TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams
    • Entry: MobiBench: Benchmarking LLMs for On-Device Performance
    • Entry: picoRing dual: ultralow-power bimanual ring controllers for everyday AR
    • Entry: PDD: Unleashing Economical and Flexible Heterogeneous LLM Inference via Cross-Datacenter Prefill-Decode Disaggregation
    • Entry: The Landscape of Misinformation Literacy Games: A Systematic Mapping Review of Game Designs and Evaluation Practices
    • Entry: Yeah, I Can Play That - Aesthetic Education in Kindergarten Using a Social Robot
    • Entry: User-Side Contextual Phenomena in Long-Term Human-AI Interaction
    • Entry: NPU Hardware Evaluation v1.0
    • Entry: Code in Space: How Multimodal Human-AI Experience Can Reshape the Future of Tech Creation
    • Entry: Few-Shot Degradation Is Not What It Seems: Behavioral Evidence, Representation Analysis, and a Random-Text Control Across 12 Models, 2 Tasks, and 2 Architectures
    • Entry: The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
    • Entry: Optimal Model Activation Policies for Inference Networks of Large Language Models
    • Entry: Single Document Extractive Summarization using Domination in Hypergraph
    • Entry: Latent Undertow: How Ordinary Typos Break Probes
    • Entry: Bias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier Models
    • Entry: Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions
    • Entry: Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety
    • Entry: Self-reported archetypes and behavioral failures in Large Language Models
    • Entry: NepKANUN: A RAG-Based Nepali Legal Assistant
    • Entry: Using Codebooks to Detect Cybercrime Topics in Text Narratives
    • Entry: Scheduling Jobs with Multiple Operational Modes and Tail Times
    • Entry: DT-RAID: A Software-Defined Tiered RAID Architecture for Heterogeneous SSDs
    • Entry: Measuring AI harms with multidimensional Lorenz Zonoids
    • Entry: Automated Comment Moderation Enhances Social Media Advertising Performance
    • Entry: Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
    • Entry: Novel Iterative Construction Methods for the Blocking Job Shop Scheduling Problem
    • Entry: Co-Skill: A Collaborative Communication Framework for Skill Evolution
    • Entry: Vectorization Of Narrow Matrix Multiplication for Ascend AI Inference Acceleration
    • Entry: Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)
    • Entry: Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
    • Entry: GPU-Accelerated Search for Fast Matrix Multiplication over $\mathbb{F}_2$
    • Entry: Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
    • Entry: DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling
    • Entry: Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
    • Entry: Relation Before Entity: Deferred Commitment in Language Model Factual Recall
    • Entry: From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings
    • Entry: MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation
    • Entry: Human-Centric Grasp State Assessment: Toward Transferring Subjective Evaluation to Robots
    • Entry: Real-Time Service Robot Replanning via Simple Button Interaction for Improved Task Success and User Experience
    • Entry: Register Bias in Complexity-Based Large Language Model Routing
    • Entry: Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation
    • Entry: Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification
    • Entry: Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant
    • Entry: How AI Assistants Respond to Repeated Abuse
    • Entry: Myovox: Reading Speech from the Muscles of the Face
    • Entry: Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues
    • Entry: No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
    • Entry: Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks
    • Entry: The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models
    • Entry: Do small language models know what they don't know?
    • Entry: HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
    • Entry: TALON: A Temporally Aware Longitudinal Framework for Radiology Report Generation
    • Entry: From Discharge Notes to Patient Understanding: Persona-Grounded, Open-Ended Simulation of LLMs as Discharge Educators
    • Entry: Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR
    • Entry: SAGE: Schema-Guided LLMs for Grant Review
    • Entry: Reviser: Revision-Capable Text Generation via Autoregressive Cursor Actions
    • Entry: Recursive Language Models Generalize Out of Domain
    • Entry: TatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar
    • Entry: Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge
    • Entry: Towards Secure Cloud-Native Computing: Unveiling Kubernetes Misconfigurations with Large Language Models
    • Entry: A Generative Grammar Underlying the Voynich Manuscript, the Pastiche Hypothesis: Evidence from Large Language Models
    • Entry: PhysioBench: A Unified Benchmark for Physiological Signal Question Answering
    • Entry: From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News
    • Entry: Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition
    • Entry: From Papers to Interpretive Knowledge Nodes: Proposing the Missing Object in Scholarly Knowledge Circulation
    • Entry: COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training
    • Entry: VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering
    • Entry: Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
    • Entry: Reading Less While Writing: A Closed-Form Bandwidth Dial for Streaming Multimodal Decoders
    • Entry: What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus
    • Entry: Training a Language Model End-to-End in Rust: An Experience Report
    • Entry: Same Quantity, Different Answer: Numerical Representation Invariance in Language Models
    • Entry: Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
    • Entry: A Computational Approach to Measuring Semantic Change in Sanskrit Literature
    • Entry: Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization
    • Entry: Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models
    • Entry: Deepfakes and Synthetic Media: Generation, Detection, and Governance
    • Entry: OSFoundry: Building and Evolving Operating Systems with Specification-Guided Agents
    • Entry: Compressibility is not Feedback: A Random-access Gap in Causal Semantic Repair
    • Entry: "As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
    • Entry: NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers
    • Entry: Pushout Attachments and Conditional Complexity of Executable Models
    • Entry: Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum
    • Entry: Towards Adaptive Interaction Strategies for Human Companion Robot via Deep Reinforcement Learning
    • Entry: From Tone to Trajectory: Continuous Sentiment and the Shape of Monetary Policy Communication
    • Entry: 4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting
    • Entry: Peerify: Benchmarking Peer-Review Claim Verification
    • Entry: AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search
    • Entry: Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation
    • Entry: G\"odel's and Scott's Variants of the Ontological Argument in Lean 4
    • Entry: AgroBench: A Reproducible Multimodal Benchmark for Weakly Supervised Crop Yield Learning from County Statistics and Pixel Observations
    • Entry: The Drift Contract: Spectral Updates for Depth-Robust Local Learning
    • Entry: FedCoT-VQA: A Federated Learning and Unlearning Framework for Chain-of-Thought Planners in VideoQA
    • Entry: Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection
    • Entry: HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting
    • Entry: Text Scores Can Miss Waveform Use: A Qwen2-Audio Quantization Case Study
    • Entry: FINN-Tro: Exploiting Verification Gaps in Dataflow Inference Accelerators
    • Entry: What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus
    • Entry: Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management
    • Entry: Balancing Generality and Specialization: A Survey on AI Datacenter Hardware Architecture
    • Entry: Validation and Simulation Catch Different Errors: Four Levels of Evaluation for LLM-Generated Circuits
    • Entry: Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation
    • Entry: Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
    • Entry: A Hybrid Rule-Based and AI-Augmented Framework for Automatic Failure Recovery in DevOps Deployments
    • Entry: LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels
    • Entry: NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution
    • Entry: Gaussian-process surrogate indicators for residual-based adaptive GMsFEM
    • Entry: Reconstruction and Range Characterization for a Directional Confocal Non-Line-of-Sight Imaging Model
    • Entry: Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests
    • Entry: Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests
    • Entry: When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
    • Entry: A Vision-Language Framework for Measuring Social Life on Sidewalks
    • Entry: From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review
    • Entry: When Evaluators Cry Wolf: Lessons from Production LLM-as-Judge Evaluation in Educational AI
    • Entry: The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI
    • Entry: RADAR: Readiness for AI Discovery and Agentic Reach
    • Entry: Drafter: A Python Library for Full-Stack Web Development in CS1
    • Entry: Unsnarling the Red Tape: Computational Infrastructure for Regulatory Systems
    • Entry: Generative AI May Reinforce Social Biases in Software Engineering Education
    • Entry: Measuring the Professional Educational Competence of Foundation Models
    • Entry: Make it SewSimple: Navigating UK Curriculum and Classroom Practice in Secondary Computing Education with E-textiles
    • Entry: Political Sorting Can Drive AI Models Apart Through User Feedback
    • Entry: Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025
    • Entry: IaC-Guard-V: A Verification Framework for LLM-Generated Infrastructure-as-Code Repairs
    • Entry: Stable and Faithful Explanations for Knowledge Tracing
    • Entry: TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
    • Entry: Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift
    • Entry: An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting
    • Entry: Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs
    • Entry: Virtual Backhaul Connectivity for Enhanced Coverage in Fiber-Less Areas
    • Entry: HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference
    • Entry: When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization
    • Entry: ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers
    • Entry: Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments
    • Entry: Cosine Similarity Is Not Evidence: Measuring the Noise Floor of Interpretability Transfer Under Quantization
    • Entry: Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness
    • Entry: Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation
    • Entry: Neural Ideals and Neural Codes: An Algebraic Framework for Neural Network Classification and Feature Interpretation
    • Entry: Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting
    • Entry: When Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator
    • Entry: A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID
    • Entry: Manifold Projection and Iterative Autoencoder Refinement for Masked Language Modeling
    • Entry: Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents
    • Entry: Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline
    • Entry: Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence
    • Entry: A Survey on Fake Review Detection: From Pre-trained Language Models to Large Language Models
    • Entry: Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents
    • Entry: SlideLab: Audience-Centered Scientific Slide Generation and Evaluation
    • Entry: SignTrace: Describe a Sign, Find the Word
    • Entry: NeuralCert: certified computational discovery of extremal mathematical constructions
    • Entry: The Death of the Legal Author. Authority, Intention, And Law-Creation in the Advent of GenAI
    • Entry: The Multi-Lab Enterprise: Governance, FinOps, and Telemetry Challenges of Multi-Model AI Adoption
    • Entry: Digital Twins for Small Towns and Rural Regions: Data Integration, Simulation and Visualisation Across Three Use Cases in Lower Austria
    • Entry: Analysis of Regional Disparities of Location of Sports Facilities and Sports Education Using Scientific Satellite Data
    • Entry: Perceived and Actual AI Deepfakes: The Case of Sudan
    • Entry: HIPAA-Compliant AI Deployment Patterns in Clinical Settings: Privacy-Preserving Techniques and Governance Controls
    • Entry: ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports
    • Entry: Replay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase
    • Entry: OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit
    • Entry: EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis
    • Entry: Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators
    • Entry: Symmetry-quotient Flatness and Generalization
    • Entry: What Next-Event Accuracy Cannot See: Closed-Loop Evaluation of Emergency Department Trajectory Simulators
    • Entry: Grounding Vision-Language Models in Driving Semantics: A Multi-Dataset Predicate Framework for Explainable Reasoning
    • Entry: FIDAL: Diversity-Aware Federated Active Learning Under Real-World Distribution Shifts
    • Entry: Energy-aware frugal Bayesian optimization
    • Entry: When Does Domain Adaptation Help on Physical Vibration Sensors? A Held-Out-Bearing Study of Neural-Operator and Convolutional Models
    • Entry: Measure Learning at Steady State: A BIRD-SQL Formula 1 Case Study
    • Entry: Product-Aware Deterministic Rounding for Quantized Matrix Multiplication
    • Entry: Information Design Against Gaming and Learning Adversaries
    • Entry: Large Language Models are Approximate Survival Estimators
    • Entry: EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance
    • Entry: One Tool, One Taste? How Vibe Coding Trades Collective Diversity for Individual Creativity
    • Entry: RealGUINoise: An Interactive Cross-Platform Benchmark for GUI Agent Robustness under Real-World Interface Noise
    • Entry: Baseline Exposure to Common Data Visualization Types Among the U.S. Adult Population
    • Entry: Why and How People Check Generative AI Output for Mistakes
    • Entry: AI-Powered Symptom Assessment and User Experience: A Case Study of Simtomi and Simtomi-Care
    • Entry: Travel Time Prediction in Supply Chain Management Using Machine Learning
    • Entry: EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents
    • Entry: A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees
    • Entry: A Data-Free Physics-Informed Neural Operator for Level-Set Interface Advection
    • Entry: Conformal Adversarial Generative Ensemble
    • Entry: DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
    • Entry: FlashDiffusion: Fused Tiled Kernel Spectral Decomposition
    • Entry: TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
    • Entry: Optimize, Learn, Refine: Whole-Body Grasping and Pick-and-Throw with a Spiral Soft Robot
    • Entry: Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling
    • Entry: The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models
    • Entry: Moment-based approximation of cell and face integrals in THINC/QQ reconstruction on unstructured grids
    • Entry: Fiatlux: A Long-Horizon Benchmark for Humanoid Ladder Climbing and Light-Bulb Replacement
    • Entry: PEDAL: Open Infrastructure for Citable AI Prompts in STEM Education and Research
    • Entry: Reverse Item Response Theory for Sparsity-Robust Ranking in Fragmented Cancer Drug-Response Matrices
    • Entry: STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets
    • Entry: How Far is Adam from Natural Gradient Descent?
    • Entry: Emergent Object Binding Has a Finite Spatial Horizon
    • Entry: On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and Confidence
    • Entry: Bounded-Fidelity Sim-as-Demo-Stage: Mocap Handoff for Governance Benchmarks
    • Entry: FourierQK: Filter Shape, Admissibility and the Leakage-Coverage Law
    • Entry: Heavy-Tailed Memory Traces in Long-Horizon Language Agents
    • Entry: When Do Causal World Models Help Modular LLM Agents
    • Entry: From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
    • Entry: Spatial Lifting for Dense Prediction
    • Entry: What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA
    • Entry: Topologically Relevant Landmark Selection on Point Clouds
    • Entry: Smooth Curves from Curvature-Driven Subdivision
    • Entry: Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null
    • Entry: Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
    • Entry: High-Value Synthetic Supervision for Parameter-Efficient Adaptation of a Compact Japanese Speech Model
    • Entry: Software Project Management with LLM-Based Automation: Coordination, Validation, and Governance in Practice
    • Entry: Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap
    • Entry: Beyond the Good, the Bad, and the Ugly: Colormap Assessment through Data-Aware Perceptual Metric
    • Entry: EvoMaestro: Toward Interpretable and Steerable LLM-Driven Program Evolution
    • Entry: Judgement and the Feeling of Agency When Instructing a Computer to Act
    • Entry: No speech articulator robustly favours retroauricular electrodes over canonical jaw sites: a volume-conductor model with orientation and electrode-count controls
    • Entry: From Community Values to AI Design Constraints: A Mixed-Methods Study of a Proposed AI-Driven Wildfire Risk Assessment Tool in Los Angeles County
    • Entry: Sycophancy Through a Five-Level AI Response Validation Framework
    • Entry: A linear-in-$q$ range of dimensions for the MDS conjecture over $\mathbb F_q$ in odd characteristic
    • Entry: Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks
    • Entry: Suslin-Rao Codes : the bridge between pure and applied
    • Entry: Fractal Cross Product: Theory, Differentiable Implementation and Application to Medical Image Analysis
    • Entry: Quaternary Preparata codes are quasi-perfect covering codes in the Hamming metric
    • Entry: Statistical Dark Matter: Synergy is everywhere but is hard to capture
    • Entry: Do Motion Tokenizers for Co-Speech Gesture Generation Encode Gesture Semantics?
    • Entry: Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?
    • Entry: LoRA Direction Extraction for Controllable Light Toggling in FLUX.1 Kontext
    • Entry: Energy Variation in Training Modern Computer Vision Architectures
    • Entry: What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study
    • Entry: ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents
    • Entry: WAMJET: A Harness for World Action Model Acceleration
    • Entry: StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
    • Entry: Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generation
    • Entry: TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning
    • Entry: Diff-SQL: SQL Efficiency Optimization via Patch Generation and Constraint Alignment
    • Entry: Trajectools Demo: Towards No-Code Solutions for Movement Data Analytics
    • Entry: Dynamic Modeling, Efficiency Analysis, and Hierarchical Control of Industrial Airborne Pulp Dryers
    • Entry: When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO
    • Entry: Generalizable Robustness Testing of DNN-Based Robotic Navigation Systems via XAI-Guided Search
    • Entry: RMRRT: Riemannian Barrier Metric RRT for Inequality-Aware Steering on Equality Manifolds
    • Entry: Exact Sizewise Least Cores for Candidate-Disjoint Approval Chains
    • Entry: Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks
    • Entry: Comparative review of hybrid forecasting models for short-term prediction of building thermal load
    • Entry: Geometric Coherence via Weighted Matching for 3D Heterogeneous Multi-Agent Reach-Avoid Games
    • Entry: Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers
    • Entry: Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense
    • Entry: Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes
    • Entry: Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience
    • Entry: A New Upper Bound for 7-Universal Tournaments
    • Entry: Axiom Satisfiability of Linear Rewards in Alignment
    • Entry: Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models
    • Entry: Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable
    • Entry: Comparative review of hybrid forecasting models for short-term prediction of building thermal load
    • Entry: Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense
    • Entry: An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
    • Entry: A Modular Event-Driven Software Architecture for Open-Source Industrial IoT Edge Gateways
    • Entry: DLCB: Ahead-of-Time Compilation for Dynamic Deep Learning
    • Entry: Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
    • Entry: Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models
    • Entry: Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression
    • Entry: GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations
    • Entry: LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking
    • Entry: SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
    • Entry: Does Dynamic-Point Filtering Help When Texture Is Scarce? A Controlled Study of ORB-SLAM2 Front-Ends in Synthetic Indoor Scenes
    • Entry: SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
    • Entry: CacheFit: The Rising Cost of Cache Replacement and Constraint-Driven Redesign of Last-Level Cache Replacement Policies
    • Entry: A Survey on LLM-Integrated Hardware Design Verification
    • Entry: Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
    • Entry: Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch
    • Entry: A faster matrix multiplication algorithm through structured optimization
    • Entry: Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs
    • Entry: Dijkstra Is NOT Greedy: A Global-to-Local Proof of Correctness
    • Entry: Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
    • Entry: Performance Analysis and Sensing-Aware Resource Allocation for Full-Duplex Massive MIMO ISCC Networks
    • Entry: MDN-VJEPA: Multimodal Probabilistic Joint-Embedding World Models
    • Entry: LACRM: LLM-Guided Mining of Directed Advertiser Competition Relationships in E-Commerce Advertising
    • Entry: MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction
    • Entry: PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression
    • Entry: PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems
    • Entry: DoSA: Dots Sparse Attention
    • Entry: Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents
    • Entry: How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings
    • Entry: Posterior Flow Matching
    • Entry: GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
    • Entry: Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures
    • Entry: SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
    • Entry: Enhanced Trading Systems with Intelligent Market Analysis
    • Entry: SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions
    • Entry: VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning
    • Entry: PreSO: Privileged Representation Isolation for On-Policy Self-Distillation
    • Entry: Showing versus Doing: Teaching by Demonstration
    • Entry: Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence
    • Entry: Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data
    • Entry: What Can Language Models Inherit from Solomonoff Induction? Limits, Attainable Properties, and What Served Conditionals Reveal
    • Entry: Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides
    • Entry: Memory Bandwidth, Not FLOPs: Profiling and Accelerating Query-Based Segmentation Decoders on Edge GPUs
    • Entry: When is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration
    • Entry: Trust but Verify: Designing Region-Inhomogeneous Forward Dynamics for Discrete Diffusion
    • Entry: Binding-Specific Relearning Savings for Test-Time Continual Learning
    • Entry: Eliciting Specifications: When Does Interactive Clarification Help?
    • Entry: Not All Frames Are Equal:Difference-Aware Quantization for Ultra-Low-Bit ASR
    • Entry: When the implementation matters more than the algorithm: NSGA-II and other multi-objective optimizers in engineering design tools
    • Entry: Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
    • Entry: Audio System One Model: Typed Probabilistic Perception of Emotion in Speech
    • Entry: From Events to Reasoning: Hierarchical Rule Composition over Explicit States
    • Entry: Aligning Information Theory and Formal Verification: A Lean Formalization of Rate-Distortion Theory
    • Entry: MedSonor: Learning to Use Clinical Audio in Medical LLMs
    • Entry: Towards Adaptive and Real-Survey-Aligned Simulated Urban Mobility Behaviour of Generative Agents
    • Entry: ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
    • Entry: Social Bias or Social Desirability? Comparing Factorial Survey Experiments for Humans and Large Language Models
    • Entry: Decomposing URLLC Deadline Failures in Beam-Managed 6G Networks: Implications for Mission-Critical Wireless Systems
    • Entry: EnterpriseSynth: Zero-Execution SFT and Evaluation Data from OpenAPI Specs
    • Entry: From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory
    • Entry: Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological Model
    • Entry: Web Agent Agentic Reinforcement Learning Decision Model Under Multi-Cost and Failure Risk
    • Entry: I$^2$-Med: Interpretable Medical Inference through Visual-Guided Dynamic Logits Calibration
    • Entry: Modeling Human Behavior in the Prisoner's Dilemma with Large Language Models
    • Entry: PolyGraph: Plan-Buffered CUDA Graphs for Adaptive Speculative Decoding
    • Entry: Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
    • Entry: Measuring the Influence of Modality-Specific Node Representations on Graphs
    • Entry: SAGE-CP: When Marginal Coverage Hides Route-Conditional Failures in Adaptive VLM Ensembles
    • Entry: GardenBench: A lightweight, daily evaluation of LLM capabilities
    • Entry: Composable Parametric Demographic Injection for Values Survey Simulation
    • Entry: Translating in style: An open-weight alternative to GPT-4 for culturally aligned machine translation
    • Entry: DUET: Decoupled Upper- and Lower-Body Execution for Task-Agnostic Humanoid Loco-Manipulation
    • Entry: Context-Aware RGB-Thermal-Radar Obstacle Perception for Resource-Constrained ASVs
    • Entry: Adaptive Question Generation for Ambiguous Robot Instructions Based on Information Gain and Human Cognitive Characteristics
    • Entry: Stress-Query and Temporal Reliability of Vision-Language Models as copilots in Autonomous UAV Navigation
    • Entry: A Heterogeneous UAV UGV Methodology for Aerial Tracking of Mini Autonomous Cars
    • Entry: Adaptive Rejection of Unknown Hybrid Sinusoidal Disturbances with Application to Humanoid Walking under Unknown Ground Motion
    • Entry: AutoPruner: Agentic Depth Pruning for Vision-Language-Action Models
    • Entry: Lubricant Temperature Observer for Gearboxes in Industrial Robots
    • Entry: Transmission Error Compensation for Industrial Robots Using Fourier Series
    • Entry: Learning Whole-Body Kinetic Coordination for Wheeled-Quadruped Long-Range Throwing
    • Entry: H2DF: Calibrated Target Bands for Controllable Language-Model Unlearning
    • Entry: AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation
    • Entry: High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference
    • Entry: WaveCommitments: Private and Verifiable Speech-Agent Marketplaces
    • Entry: Multimodal Ambivalence and Hesitancy Recognition with Bidirectional Audio--Text Cross-Attention
    • Entry: Commanding at the Speed of Sound: Audio-Centric Referring Expression Segmentation for Aerial Scenes
    • Entry: Exploring Representation Autoencoders for Text-to-Audio Generation
    • Entry: Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training
    • Entry: Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition
    • Entry: Learning from Past Mistakes: AI-Assisted Analytics of Software Defects and Their Fixes for Future Defect Prevention - An Industrial Case Study
    • Entry: TRACE: Trustworthy Reasoning from Acoustic Cues and Evidence
    • Entry: EGGHead: Efficient Generalizable Gaussian Heads from a Single Image
    • Entry: Large language model and reinforcement learning based autonomous construction and progress updates
    • Entry: MOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems
    • Entry: Beckmann World Models: Direct Terminal-Map Learning for One-Step Action-Conditioned Prediction
    • Entry: Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
    • Entry: InterType: Breaking the Single-Function Barrier in Neural Binary Type Inference
    • Entry: Uncertainty Gates the Gradient: Adaptive Updates for Generalized Few-Shot 3D Segmentation
    • Entry: Memory Internalization via Test-Time Training for Long-Video Understanding
    • Entry: MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring
    • Entry: RESEARCHHUB: A Personalized Literature Discovery System for Biomedical Preprints
    • Entry: To Keep or Not to Keep: Learning KV Cache Retention in Disaggregated LLM Serving Systems
    • Entry: TAGR: Task-Adaptive Geo-Semantic Retrieval across Heterogeneous Urban Delivery Tasks
    • Entry: Can AI Chat Replace Traditional Search? Evidence from a RAG-based Live Events Experiment
    • Entry: Gender Stereotypes Make Women Invisible: The Presence of Female Scientists in the Media
    • Entry: Transaction Foundation Models for Retrieval-Augmented Generation over Financial Transaction Data: A Comparative Evaluation with Text Embeddings
    • Entry: Controllable Generative Recommendation via Guided Token Refinement
    • Entry: Evolution of article processing charges in medicine: disciplinary position, access gaps and future prospects
    • Entry: MultiphaseHUB for Evidence-Grounded Metadata Curation and Task-Aware Compression of Multiphase Data
    • Entry: Peer review should constrain evaluative authority
    • Entry: An Open-Source Data Infrastructure for Alloy Synthesis Research: Stage 1 --- Composition Screening and Literature Cross-Referencing
    • Entry: Building Knowledge Graphs for Theses: A Survey
    • Entry: Zero-Cost Detection of Fabricated Citations: A Staged Heuristic Approach for Computing Dissertation Assessment
    • Entry: The CIDOC CRM Periodic Table: Documentation You Can Test to Support the Adoption of Scientific Research Ontologies for the Humanities
    • Entry: The Scientific Research Taste Benchmark (SciTaste-Bench): A Multi-Disciplinary Benchmark for Assessing Large Language Models' Judgment of Research Taste in Scientific Papers
    • Entry: What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
    • Entry: FutureLens: Longitudinal Topic Patterns in Scholarly Text and Future-Work References
    • Entry: CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet Needs
    • Entry: Beyond source attribution: Address authorship and comparability decisions in an LLM-built scholarly knowledge graph
    • Entry: Learning Checklists to Reduce Lottery Effects in Scientific Peer Review
    • Entry: Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation
    • Entry: MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring
    • Entry: Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?
    • Entry: Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions
    • Entry: The Schema Coherence Inventory: Measuring Whether an Assigned Belief Organizes a Language Model's Cognition
    • Entry: Knowledge Graphs Quality Assessment in the Era of LLMs: A Conceptual Framework
    • Entry: An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation
    • Entry: From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
    • Entry: Distributional Alignment of LLMs and Its Generalization Properties
    • Entry: Fooling LLM Safety Guards into Judging the Wrong Text
    • Entry: Links of minimum degree and exact covering numbers
    • Entry: Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study
    • Entry: Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation
    • Entry: Collaborative In-Context Learning for Indoor Radio Map Estimation
    • Entry: Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
    • Entry: The Path to NDE 4.0: A Review of Algorithms, Techniques, and Strategies for Autonomous Inspection
    • Entry: RubricCraft: Where Solutions Diverge, Criteria Emerge
    • Entry: Mining the Design Space of Multi-Agent Workflows
    • Entry: Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents
    • Entry: MBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability
    • Entry: New Lenses on Learning Design: Course Types and Indicators from Large-Scale Moodle Data
    • Entry: OpenHamoye: A Multi-Scale Open Geospatial Intelligence Framework for Decision Support Across Nigeria
    • Entry: Governing Artificial Intelligence as a Macro Socio-Technical Regime: The F-I-C-P Framework for Regime-Level AI Infrastructure and Governance
    • Entry: LLM-as-a-Judge Version Shift: The Instrument Changed, Not the Standard
    • Entry: LLM-Augmented Agent-Based Simulation of Cyber Social Agents
    • Entry: DairySocialTwin: Auditing the video-to-graph evidence chain in cattle social networks
    • Entry: Whispering Wisely: Smart Subset Selection for ASR Fine-Tuning
    • Entry: From Writing Advice to Manuscript Governance: A Constrained-Transformation Framework for Academic Revision
    • Entry: Entity-Aware Evaluation of OCR Systems for Historical Document Transcription
    • Entry: OpenESM: Energy-Steered Models Are Scalable Foundation Learners
    • Entry: Linear-Time Context Compression with State-Space Encoding
    • Entry: Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks
    • Entry: TraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models
    • Entry: When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems
    • Entry: Recursive Semantic Divergence for LLM Agent Consistency
    • Entry: UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
    • Entry: The Social World Model Evaluation Gap
    • Entry: SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory
    • Entry: Merge-Based Vocabulary Extension Stalls at the Pre-Tokenizer: An English-Preserving Repair for Nepali, Tested in Continued Pretraining
    • Entry: AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages
    • Entry: New Lenses on Learning Design: Course Types and Indicators from Large-Scale Moodle Data
    • Entry: KORA: Deterministic-First Execution Control for AI Workloads
    • Entry: Packet Interval Modulation-based NFC for Scalable IoT around Meandered E-textile
    • Entry: Real-Time Smart Retail Analytics through Fog Computing using the RetailLightNet Lightweight Model
    • Entry: NSB2: An Open-Source Modular Pipeline for Application-Network Co-Simulation
    • Entry: IoT-based Smart Real-Time Energy-Aware Server Room Monitoring System
    • Entry: Where Does My Call Go? Measuring Google Meet, Zoom, and Microsoft Teams on Starlink
    • Entry: Calibrated for Which Policy? Conformal Uncertainty for Fixed World Models Under Intervention
    • Entry: StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting
    • Entry: ObjectTwin: Measuring the Asset Correspondence Gap for Capture-Anchored Digital Twins
    • Entry: Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks
    • Entry: Beyond Structural Unification: A Perspective and Roadmap on Unified Multimodal Models
    • Entry: People's Views on Smiley Emoji on WeChat Platform, Positive Emotion and Sarcasm
    • Entry: Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation
    • Entry: ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking Datasets
    • Entry: What Has Actually Been Proved? Auditable Paper-to-Lean Alignment with LeanTrail
    • Entry: SCOPE: Source Credibility and Outlet Profiling Engine
    • Entry: Who Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems
    • Entry: Deterministic Causal Quantization with Representative States and Bounded Error
    • Entry: RV565: Cross-Layer Co-Design for Frame-Independent Video Playback on MicroPython-Class ESP32-S3 Systems
    • Entry: Counting the Bandages: On measuring the time that AI saves