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.
- 19Untrained CNN and coefficient-space regularization for joint reconstruction in photoacoustic tomography
- 19From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory
- 19Interpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features
- 19Acquisition for Spherical-Linear Bayesian Optimization on the Cube
- 19Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
- 19LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs
- 19Inferring L1 Backgrounds from L2 English with LLM Token Probabilities
- 19What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
- 19MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
- 19SimOPD: Relational Knowledge Transfer for On-Policy Distillation
- 19Earth embeddings are decomposable records of the land surface
- 19Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs
- 19Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction
- 19Interpreting Supervised Pairwise Graph Representations: Local Evidence, Confounding, and Provable Post-hoc Correction
- 19Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research
- 19How the elastic axis folds the transonic flutter boundary: shock energy transfer and conformally calibrated active learning
- 19FlashReFocus: Interactive Image Refocusing in Seconds
- 19@agent-link/agent — AgentLink local agent CLI
- 19Learning angles for quantum approximate optimization
- 19LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling
- 19The Optimal Ranking Tradeoffs Between Two Ranking Scores in Two-Class Classification
- 19Trajectory Matching: Discrete Flow Matching with Structured Actions
- 19Let's Do Turbulence Right: In Space and Time!
- 19Distributed Performance Boosting through Neural Control for Plug-and-Play Networks
- 19CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective
- 19Data-Efficient Classifier Pretraining Through Diffusion Models
- 19Universal neural network approximation of symmetric polyconvex energies and envelopes
- 19Annotrace: A Workbench for Step-Level Annotation of Agent Traces
- 19I built a forum where rooms die when people stop talking
- 19Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection
- 19Contextual Decision Making: Predictive or Generative
- 19DeDiCa: A Scalable Deconfounding Discrete Causal Generative Model
- 19Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System
- 19NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models
- 19From Parameter Rebasin to Functional Transfer Across Heterogeneous Transformers
- 19Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents
- 19PHYRD: A Living Benchmark for Reproducing and Extending Theoretical Physics Research
- 19Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR
- 19Shared Is Not Enough: Predictor Width and Factor Readability Under Masked Latent Prediction
- 19noitomrobotics/HiPHI (dataset)
- 19ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language
- 19Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks
- 19Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance
- 19Your AI Assistant is Eating Money You Can't See. Here's the Math
- 19Exact Global Minimax Risk near Nonidentification
- 19Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecasting
- 19Beyond Channel Data: Configuration-Enriched Radio Foundation Models
- 19StarRTT: An End-to-End Real-Time Framework for Blind Zone-Free RTT Prediction in Starlink LEO Satellite Networks
- 19Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps
- 19IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints
- 19Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers
- 19Bi-HYCO: Bi-Objective Cooperative Learning for PDE Parameter Identification under Fragmented Observations
- 19Principled Nonlinear Concept Erasure and Steering
- 19Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations
- 19Amortized Thompson Sampling and Efficient Information-Directed Sampling for Simulator-Based Design
- 19The Punjabi Geet Toxicity Dataset (PGT-FG): Fine-Grained Multimodal Annotations for Toxic Content in Punjabi Songs
- 19Quantum-Classical Link Prediction on Dark Web Hyperlink Graphs
- 19BAARC: Uncertainty-Driven Adaptive Partial Spectral Measurement to Full Reconstruction for Material Classification
- 19Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign
- 19Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning
- 19DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization
- 19DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding
- 19Random Jump Forests
- 19MusicTwins: Training Audio-Language Models to Listen like Their Persona
- 19PyCharm option Jupyter: Notebook File Root (Set the root directory for Jupyter Notebooks) missing
- 19OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution
- 19Power Mean Estimation in Stochastic Continuous Monte Carlo Tree Search
- 19Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
- 19How Does Parameter Pruning Reshape DNN Representations? An Interaction-Driven Exploration
- 19Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents
- 19When Computed Becomes Async
- 19One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints
- 19Learning Kernels by Alignment for Multiclass Bayes Classification
- 19ngl, "asked an agent to find where my space went and the agent was the problem" is the most 2026 sentence I've read this week.
- 19Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs
- 19A Group-Based Resource Allocation Model for the Fractional Knapsack Problem
- 19One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control
- 19Machine Learning Approaches to Decoding Topological Quantum Codes
- 19Sector-Mean: Deterministic Initialization of K-Means Centroids via Angular Sector Partitioning
- 19Local and Global Stability in Performative Reinforcement Learning
- 19Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection
- 19Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving
- 19I guess I'm using WebP now?
- 19TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness
- 19Arch Linux disables AUR package adoption
- 19Ask HN: Advice on Migrating from 1Password?
- 19A Theoretical Framework for Masked Pretraining (MPT)
- 19Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification
- 19Decomposing LLM-Judge Uncertainty to Target Expert Labels
- 19TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
- 19Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection
- 19InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization
- 19Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning
- 19Large-Scale Pretraining for Improving Deep Learning-Based Geometric Distortion Correction of Diffusion-Weighted Imaging
- 19Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration
- 19Your CLAUDE.md Rules Achieve 0% Compliance. Here's the Data.
- 19Don't Start With RAG: Lessons From Building an Automotive AI Pipeline
- 19Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation
- 19Bend-SSZ: Formally proving SSZ
- 19Phase-cycled randomized benchmarking of quantum processors: recovering hidden classical noise correlations
- 19Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks
- 19ALKEMIE Agent: an autonomous platform for computational materials design
- 19We measured 139 small business websites. 3% meet Google's speed threshold
- 19Sparse Oblique Rule Boosting for Simpler Additive Rule Ensembles
- 19Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
- 19Inferential Evaluation of Surrogate-Derived Models under Covariate Shift
- 19RPC Standards # 37, October 19, 2026
- 19Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation
- 19On BatchNorm Forward Modes in Value-Based Reinforcement Learning
- 19Solution to Challenge 3 - Visual Testing with API Mocking
- 19CrevasseSeg: A Label-Efficient UAV Crevasse Segmentation Framework
- 19Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models
- 19What Comes After Git
- 19KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving
- 19Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception
- 19Using the Mimi codec for metalinguistic representations
- 19PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection
- 19Apache Data Lakehouse Weekly: September 3-9, 2026
- 19Experimenting with random() in CSS
- 19Hallucination Span Detection with Input-Side Evidence Alignment
- 19Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos
- 19HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
- 19Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
- 19Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
- 19Here's what being a street-smart coder means
- 19A Pre-Specified Construction-Confirmation Test of Operation-Level Causal Transfer Across Finite Isomorphic Symbolic Domains
- 19Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State
- 19Untangling the Mechanisms of Misleading Context in Medical Question Answering
- 19TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking
- 19A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa
- 19Uncertainty-Aware Deep Learning for Genomics Applications: Insights from an Empirical Study
- 19Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems
- 19KOALA: Koopman Operator Learning for WiFi-Based Anticipatory Hum
- 19Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents
- 19When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems
- 19LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders
- 19RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning
- 19Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training
- 19Replicating a Disjoint-Set Union Experiment over Various Notions of Micro Units to assess Translation Effort
- 19Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach
- 19Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit
- 19Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
- 19Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent Memory
- 19From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
- 19HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks
- 19Local gradient neural operator
- 19Data-directed programming in Haskell (SICP2.4.3)
- 19Cross-modal learning for SAR target recognition using optical vision foundation models
- 19Theranos-Style Fraud Has Become the Norm
- 19QuantumPhaseNet: A Gauge-Covariant Geometric and Quantum-Spectral Theory of Semantic Concept Hierarchies with Prototype Validation of a Classical Quantum-Inspired Model
- 19Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain
- 19CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
- 19Second-Moment Memory in Coordinatewise Adam
- 19Comparing INT4 and NVFP4 Palettes on Real Gradient Tensors
- 19A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay
- 19Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
- 19ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
- 19EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
- 19SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
- 19RTSKG: Building a Rail Transit Station Knowledge Graph Dataset
- 19EIP-8390: Remove the Sync Committee
- 19A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations
- 19EIP-8375: eMBER, ePBS Mandatory Burn of Execution Rewards
- 19SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
- 19The new Firefox design is here
- 19CardiacMamba: Fair and Robust RGB-RF Fusion for Remote Heart Rate Estimation via State Space Modeling
- 19The Authority Resolution Framework: A Five-Domain Ontology for Governing Who and What Decides, at Scale
- 19Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling
- 19Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing
- 19A Systematic Sample Size Analysis of ML-Based Path Loss Prediction for LPWAN
- 19How do dependency injection containers work at a low level?
- 19git --end-of-options
- 19Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment
- 19The Open Lakehouse Explained, Then Built on Your Laptop with Dremio and MinIO
- 19DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
- 19Dutch Books for Language Models
- 19Your LLM Pipeline Never Throws: Three Guardrails for Silent AI Failure
- 19OmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical Diagnosis
- 19Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives
- 19Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
- 19CodeTD: Topology of Attention Detects Hallucinations in Code LLMs
- 19PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
- 19frb100-40 After Two Decades: An Optimality Certificate and a Preregistered Search Study
- 19Four silent failures in my AI automations. All four ran green.
- 19Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis
- 19Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
- 19Saab has unveiled its A3 collaborative combat aircraft concept
- 19xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems
- 19What Does an LLM-Agent Leaderboard Rank Actually Compare?
- 19Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records
- 19ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
- 19Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
- 19Burning Man death rates – A short lesson in statistics
- 19MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production
- 19LLM Agents as Computational Typologists
- 19VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution
- 19ERC-8410: Portable Execution Plan Artifact
- 19A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records
- 19Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD
- 19Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences