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.
- 19Retrofitting Code Using LLMs to Support Exceptional Behavior
- 19A searchable library of forgotten public-domain film clips from 1915 onward
- 19Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
- 19Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
- 19You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs
- 19The Physics Is the Network: Fast, Training-Free Neural Emulation
- 19HybridFLow: SDN-Orchestrated Client Partitioning for Hybrid Federated Learning
- 19Cliff: Learning Process Rewards from the First Mistake
- 19ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps
- 19Generative Representation Learning for Scalable Latent Tokenization
- 19Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics
- 19Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment
- 19VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
- 19Revisiting Simple Baselines for Relational Deep Learning
- 19Kalman Delta Networks: Uncertainty-aware Associative Memory
- 19Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
- 19MoTE: Mixture of Task Experts for Multi-Task Video Understanding
- 19Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
- 19Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs
- 19PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
- 19AlbumentationsX: One Augmentation Pipeline for Images and Related Annotations
- 19A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
- 19AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application
- 19Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
- 19Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks
- 19Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks
- 19SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs
- 19Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support
- 19Machine Learning Assisted Inverse Design of Pixelated mmWave Patch Antennas
- 19What I Learned Building a Developer Tool for AI Usage — 6 Weeks of Engineering and Product Lessons
- 19PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios
- 19InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
- 19The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN
- 19Learning Spectral-Like Mesh-Free Discretisations
- 19Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
- 19Algorithmic stability via ensembling
- 19MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
- 19Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
- 19What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
- 19StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models
- 19On the Threat Model of Weird Generalization and Emergent Misalignment
- 19Why does getObject() throw ORA-17004 for a VECTOR OUT parameter?
- 19Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models
- 19Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
- 19AI agents took over my YouTube channel (satire): the real guardrails
- 19Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillation
- 19Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response
- 19Q-Learning with Scalar Adjoint Matching
- 19Primal--Dual Alternating Neural Learning for Timely Classification with Performance Guarantees
- 19A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories
- 19PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition
- 19The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
- 19StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
- 19The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora
- 19Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control
- 19Do speech foundation models really learn words?
- 19Foundation Models for Generalizable Semantic and Goal-Oriented Communication
- 19Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
- 19Scaling Discovery Requires Forgetting
- 19RunningTab: Direct Workspace Interaction with Environment-Side Tabs
- 19Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
- 19Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
- 19Towards Zero-Shot Task Transfer with Neurosymbolic World Models
- 19OSWorld-Pro: Process-based Evaluation for Computer Use Agents
- 19Dead-pixel test sites are just colored divs — the actual engineering problem is the Fullscreen API, not the colors
- 19ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening
- 19Snippets - Introducing Laravel Snippets
- 19Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
- 19Perfect Instrumentation Won't Save an Underpowered Experiment
- 19Linear Probing Provides Robust and Efficient Detection of Machine-Generated Text
- 19SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward
- 19Best Resources to Learn AI (For Developers)
- 19A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching
- 19The Negative Control That Tested The Wrong Field
- 19A Digital Toolbox for Seven Locations (and Every Truck)
- 19Reinvention Is a Practice: Staying Open to What Comes Next
- 19How to Improve Playwright Test Coverage Using Agent Context
- 19Twelve Checks That Could Not Fail
- 19Keyboard Remapping on Steroids: keyd vs. kanata vs. keydo
- 19TanStack npm supply-chain attack: how a Dependabot bump spread a worm
- 19I Built an AI Agent That Talks Like Me. Here's What Actually Broke.
- 19I shipped a lock. Then I had to prove it could fail.
- 19I Built a Remote to Answer Claude Code From My Phone
- 19Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge
- 19The HTTP 429 That Turned Seven Minutes Into Zero Work
- 19ConvMem: Convolutional Memory for Long-Context Reasoning
- 19The Contract Test Is the Only Witness the Agent Cannot Author
- 19I built the running coach that actually listens to your body
- 19Shipping a vision-model verdict on Bedrock and Lightsail
- 19Discovery-Driven Integration of Disjoint Tables via Text
- 19Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
- 19SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
- 19How can I reduce the output size of a WinUI 3 desktop app with a fairly large set of NuGet dependencies?
- 19Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
- 19On My Japanese Team, the Retro Never Names a Name
- 19Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency
- 19One Vault, from Your Phone to the Browser
- 19One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
- 19UE5M3 FP4 Block Scaling for Stable Language Model Pretraining
- 19Your verifier is probably lying to you about floats
- 19What Protobuf descriptors don't tell you: building a generic mock generator
- 19Migrating from spatie/laravel-permission to Redis: A Production Playbook
- 19ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models
- 19sLTN: Structural Logic Tensor Networks
- 19Latent Compaction with Test-Time Training
- 19SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
- 19The baseline that quietly stopped meaning anything (and closed real trades)
- 19Player-1: Learning to Play from Synthetic Experience
- 19JavaScript in, HTML out: building a simpler static site generator
- 19Attention-Path Fragility as an Uncertainty Signal in Large Language Models
- 19Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
- 19Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes
- 19Post-Training Language Models for Gold-Medal Performance in Coding Competitions
- 19Continuum Attention
- 19Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
- 19Price of Anarchy of First-Price Auctions in Agentic Markets
- 19Fusing watchOS Sensor Signals Into a Risk Decision — Without Coupling to HealthKit
- 19Your Transformer Is Secretly Elastic
- 19PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
- 19164 disposable computers, one judging afternoon, and a question nobody had time to ask
- 19AI Coding Tip 033 - Protect Yourself Against AI Cheating
- 19[Bug Smash] The Amnesiac ORAM: Fixing Oblivious RAM That Forgot Everything
- 19ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue
- 19Repo-Local Documentation System for Humans & Agents
- 19What is BGP? How Facebook's 2021 outage took it off the internet
- 19The Backup Awakens: A Star Wars Story
- 19I attacked my own npm package before launching it. It let the proposer approve their own writes
- 19How to build a developer community
- 19Trademarx - A free public API for Indian Trademarks
- 19MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
- 19Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
- 19Co-Evolving Acting and Forecasting for Language Agents
- 19Gemma 4 on Amazon SageMaker or a VM? The Same Model Server at 1.40x the Price
- 19Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
- 19Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance
- 19A Recommendation System Approach for Interference-Robust Sensor Subset Selection
- 19NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
- 19Your App Center List Is Not a Security Audit
- 19I taught my CPU to sing — in pure Assembly
- 19Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts
- 19DevRel Has a Skim Problem
- 19JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition
- 19Evaluating and improving crop-yield forecasting methods during extreme drought
- 19FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
- 19The Implications of Linguistic Illegibility for LLM Security
- 19Five Frameworks, One Page, Zero Runtime Tax — Micro-frontends in Web Workers
- 19The Green Test That Lied
- 19Semantic search for 796 pages, with no server, no vector database, and no model at query time
- 19🪪 Avatar RS: Very Efficient Avatar Components for WASM Frameworks
- 19Is Structured Human Input the Missing Link in Agentic Work?
- 19How assigned AI use before class shapes active student engagement in class
- 19Learning the Cost of Reliable Inference
- 19Domain-Aware Lightweight Spectral-Grouped Convolutions for Hyperspectral Fish Freshness Classification
- 19Azure Virtual Network Routing Appliance: peering performance, hub-and-spoke control
- 19🐸 I Built a Mini Compiler From Scratch, Here's What I Learned
- 19TypeScript Path Aliases in 2026: `tsconfig` Paths, Bundler Resolution, and Why They Still Break at Runtime
- 19SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection
- 19Which parts of this are real? Should be a question with an answer
- 19A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
- 19Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
- 19The Illusion of Cross-Lingual Safety in Low-Resource Languages
- 19Improved Gradient Descent Lower Bounds Beyond Nesterov
- 19I built a free API for Pakistani mutual fund NAVs (because MUFAP's own one doesn't work)
- 19The time I screwed up a conference talk (And the talk on Pydantic I would have given)
- 19Sidewalk to Summit: reviving my founder-year idea by building it in public
- 19I measured his app with his own code. He measured my claim with his own corpus.
- 19Learning Random Geometric Graphs Drawn in Probabilistic Metric Spaces
- 19ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification
- 19I built an Open Source Linux cleaner because I couldn't find one I wanted to use
- 19Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images
- 19An Efficient Near-Optimal Algorithm for Adversarial $m$-Set Bandits
- 19Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
- 19When Readability and Source Retention Diverge: An Evaluability Gap in AI Translation
- 19Does Mapping Non-Maximal Probabilities to GMM Components Matter for S-JEPA Encoder Representations?
- 19DA-WAM: Decision-Aligned Future Latents for Driving World Models
- 19Nano Banana 2 Lite in Kiro CLI 3: MCP 2.0, the New Interactions API, and Headless Permissions
- 19User Feedback Provides a Unique Signal that LLMs Can not Detect
- 19How to self-host servers in your living room on static IPs
- 19When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era
- 19Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
- 19I Built a Windows Debugger From Scratch to Actually See a Stack Smash Happen -
- 19Recirculation
- 19The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic Reasoning
- 19Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework
- 19Keeping up with docs reviews: Building a tracker for Mautic's documentation PRs
- 19Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity
- 19Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
- 19Scheduling Mixed RL Rollouts Beyond Prefix Locality
- 19CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
- 19EIP-8435: Last-Written Block in PBT Leaves
- 19Our Daily Stand-up Is 15 Minutes. It Has Never Once Been 15 Minutes.
- 19A Spectral Theory of Grokking: Weight Decay induces Feature Learning
- 19SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm
- 19Almost Always Unsigned (2022)
- 19Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
- 19LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
- 19DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains
- 19RSA encryption: how it works, how it breaks, and why 2048 still holds
- 19Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
- 19Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media