Archive
Everything we've scored that's past the 48-hour window — open to everyone, no account needed. The live feed only shows what's moving right now; this is the record behind it.
- 19HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Maps
- 19Scanning While Imagining: A Scene-Graph World Model for Robotic Ultrasound Navigation
- 19Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
- 19Radiomap Blind Prediction under Incomplete Observation: Error Characterization and Correctable Propagation-Prior Learning
- 19FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors
- 19Capturing users' ssh keys
- 19Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation
- 19Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
- 19UniCache: Task- and Type-Aware KV Cache Compression for Unified Multimodal Models
- 19LLM-Based Evaluation Planning for Heterogeneous Optimization
- 19Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping
- 19Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning
- 19Improving LLM Collaboration via Multi-Agent Preference Learning
- 19MisleadQA: Diagnosing LLM Failures under Misleading Context
- 19CineForge: Self-Improving Agents for Long-Horizon Video Generation
- 19AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
- 19The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces
- 19MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation
- 19PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization
- 19Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs
- 19Learning Shuffle Ideals with Membership Queries and Contrastive Examples
- 19Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic
- 19When Can First-Order Models of Fine-Tuning Bound Forgetting?
- 19Right Answer, Wrong Reason: Accuracy, Consistency, and Consensus Are Misleading Indicators of LLM Faithfulness in Clinical Decision Support
- 19An Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning
- 19Hey guys, I'm Dream LOL
- 19Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers
- 19Pair-Aware Optimization: Coordinating Exploration and Refinement for Jailbreaking LLM Agents
- 19A Statistical Viewpoint on Adam, Shampoo and Muon
- 19USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments
- 19OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories
- 19What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements
- 19ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution
- 19Overwhelmed by Choice: Studying LLM Decision Making at Scale
- 19Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models
- 19Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning
- 19Towards Anticipatory Databases Through Shared Data and Workload Semantics
- 19Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs
- 19Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret
- 19Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding
- 19Document Topic Alignment Metrics for Evaluating Topic Models of Short-Text Public Health Communications on Social Media
- 19Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
- 19Efficiency Measured in English: Tokeniser Coverage Bounds Small Language Models on Indic Scripts
- 19Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault
- 19Recurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences
- 19DenMark: Robust Semantic Watermarking for Diffusion Language Models
- 19Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment
- 19VGFM: Expressive Robot Policies via Dense Value Guidance in Flow Matching
- 19Bayesian optimization with kernel ensembles and disagreement-based acquisition for source localization and acoustic inversion
- 19Compose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off
- 19First-Order LoRA Training with Phone NPUs
- 19Amazon Bedrock Agents Orchestrating Google ADK over A2A
- 19Teaching Code Agents to Ask Without Leaking Private Code
- 19LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
- 19EIP-8397: Frame Authenticator Signatures
- 19"Module: A Reusable State-Machine Framework for NFT Capabilities (Ownership Module v0.5 → v1.0)"
- 19Parameter Estimation of Ringdown Quasinormal Modes with Autoencoder
- 19Tilted Mondrian: Triage and Mitigation of Fine-grained Disparities in Conformal Prediction
- 19Why is my _SelectionChanged subroutine called twice when selection is changed via a DateTimePicker or a button?
- 19SpermYOLO: A Coordinated YOLO-Based Detector for Accurate and Efficient Sperm and Impurity Detection in Microscopic Images
- 19Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion
- 19Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors
- 19Conducting Stylistic Analysis of Paintings through an Art-History Agent
- 19Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework
- 19The Day WhatsApp goes dark
- 19Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems
- 19Reward-guided Fine-Tuning of One-Step Generative Models via Wasserstein Gradient Flow
- 19ERC-8420: AA-Compatible Solver
- 19Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers
- 19Editorial routing shapes how computational results are qualified in AI-assisted scientific writing
- 19Table Serialization Determines Which Relations Language Models Preserve
- 19Fusing Spectral Signatures and Activation Clustering for Backdoor Detection in Healthcare Imaging Models: Method, Implementation, and Evaluation
- 19Who Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models
- 19Cooperation Without Shared Rewards via Reciprocal Q-Augmentation
- 19Learning Source Acquisition Policies by Offline Planning
- 19EIP-8453: Decoupled Consensus
- 19E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
- 19nvidia/Qwen3.8-Flash-Next-NVFP4 (image-text-to-text)
- 19DB Connect: a database IDE that lets your AI assistant actually query your database
- 19S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks
- 19What side projects have you enjoyed the most?
- 19SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
- 19AI Assisted Workflow Optimization and Automation
- 19Nonparametric Variance-Penalized Actor-Critic: Statistical Inference for Risk-Sensitive Reinforcement Learning
- 19Communication-Efficient LLM Adaptation over Decentralized GPU Meshes
- 19AURA: Unified Multimodal Framework for Conversational Music Editing
- 19Ant, a lightweight JavaScript runtime
- 19AutoRecLab: Describe the Experiment, Get the Code!
- 19TrialAtlas: Multi-Agent Research Organization for Clinical Trial Design and Optimization
- 19Watermarkable Multi-Draft Speculative Sampling via Poisson Processes
- 19Do Personality-Tuned LLMs Make Better Social Agents?
- 19The Review Tax: Why 81% of Developers Are Buried in AI Code Review
- 19The Weight Is Over - Interactive Diffusion on Consumer GPUs
- 19Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts
- 19EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise
- 19RISE: Recursive Improvement via Self-Extrapolating Policy Distillation
- 19Anatomy-Aware Promptable Segmentation with Online Interactive Training for AUTOPET V
- 19Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar
- 19Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data
- 19Touvigation: Embodied Adaptive Object Acquisition for Blind and Low-Vision Users in Unfamiliar Indoor Environments
- 19RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding
- 19Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
- 19Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods
- 19ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
- 19Adaptive Uncertainty-Aware Modeling and Stochastic Radial Basis Function Predictive Control for Personalized Fluid Resuscitation
- 19GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity
- 19Matrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods
- 19MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention
- 19An Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data
- 19Testing Interchangeability in LLM Agent Teams
- 19Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
- 19Generalized Splines and Gaussian Processes
- 19LLM-Generated Feature Pools for Time Series Anomaly Detection
- 19Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference
- 19How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method
- 19EIP-8247: Ancestor-Indexed BALs
- 19Sliding-window beats linear attention
- 19AI for Computational Design Science: A Responsible Human-AI Framework and Case Study on Short-Form Video Safety Surveillance
- 19CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls
- 19Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining
- 19EIP-8440: Execution Chain Proofs
- 19Shallow neural network approximation in mixed Sobolev spaces
- 19Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference
- 19CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation
- 19Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
- 19RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer
- 19Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
- 19Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech
- 19From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
- 19Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
- 19Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions
- 19GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection
- 19A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability
- 19Proton Irradiation Characterization of an Open-Source ML Accelerator on a Zynq UltraScale+ MPSoC
- 19Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
- 19Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory
- 19ERC-XXXX: Consent Verification Extension for ERC-4626 Tokenized Vaults
- 19Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL
- 19Euclidean Fourier Neural Operators
- 19Uncensored Open-weight Models: Redistribution as the Persistence Layer
- 19Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs
- 19PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
- 19Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials
- 19LongPIBench: A Long-Context Benchmark for Prompt Injection
- 19Substrate-Aware AI Agents: Execution Context as a First-Class Input
- 19Signaling Mach semaphores from an IOProc
- 19ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
- 19SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data
- 19A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
- 19Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening
- 19EIP-8449: Engine API proposal lookahead
- 19Complete Neural Electronic Initialization Accelerates Materials DFT
- 19Bilevel Optimization of Topology and Hyperparameters (BOTH)
- 19ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction
- 19ForceTwin: Physics-informed Digital Twins for Robotic Manipulation from Instrumented Human Interaction
- 19GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
- 19World Modeling in Transformers
- 19Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization
- 19Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation
- 19RPC Standards # 33, August 24, 2026
- 19GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning
- 19S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks
- 19JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
- 19An agent that knows which pygame you are actually running
- 19Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening
- 19Architecture-Dependent Fusion Pathways in MLLMs
- 19CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords
- 19EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation
- 19Shrome at Touché: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction
- 19SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining
- 19Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures
- 19Post-Training VLMs for Video Mistake Detection
- 19CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
- 19PaMIR: Open Benchmark of Public Credit-Default Datasets
- 19VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings
- 19Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal Discovery
- 19RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
- 19Cross-cohort TB classification using clinical data gathered in Uganda and South Africa
- 19Learning a Fact Is Not Learning How to Retrieve It
- 19BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence
- 19Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation
- 19CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
- 19MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places
- 19Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs
- 19Collective Bias Mitigation via Model Routing and Collaboration
- 19When Linguistic and Internal Confidence Diverge in Large Language Models
- 19WAMpy: Efficient Synthesis of Prolog Programs in Python
- 19D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?
- 19The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning
- 19Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis
- 19AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning
- 19Near-Optimal Convex Optimization with Lazy Second-Order Oracles
- 19Evolving Hybrid Quantum-Classical Architectures for Image Classification
- 19Kernel Singular Value Decomposition with Extension to Multiple Data Sources
- 19StanceEval 2026: The Second Stance Detection Shared Task
- 19EIP-8301: MATMUL Opcode - Sharded Tensor State Transition Engine
- 19Toward SLM-based agentic task-tool intent matching
- 19HyperFuse: Fast Self-Supervised Node Embeddings for Attributed Hypergraphs
- 19FOCIL Breakout #44, October 13, 2026
- 19Language Models Learn to Improve Language Models