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.
- 7agent-device — Agent-native CLI for AI app automation across iOS, Android, tvOS, Android TV, macOS, Linux, and web.
- 7Deep and Probabilistic Models for Gene Regulatory Network Inference
- 7Two Includes, 2,880 Rows: EF Core's Quiet Cartesian Tax
- 7Context-weighted Discrete Flow Matching
- 7Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
- 7My USB Drive Has a Hidden Encrypted Vault
- 7Learning to Trace Seiberg Dualities
- 7ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
- 7Loop the Loopies!
- 7PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
- 7AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
- 7AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
- 7DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings
- 7An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations
- 7OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
- 7KAISEN: Reproducible Subgroup Fairness Auditing for Clinical Risk Models
- 7Inducing language models to assert their own consciousness restores human beliefs and values
- 7Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for Dynamic Graph Systems
- 7PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
- 7Graph-Based Correlation Matrix Generation: A Convex Optimization Approach
- 7Robot Learning to Communicate through Projected Visual Abstractions
- 7On the Identifiability of Controlled World Models
- 7Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment
- 7Learning in Infinitesimal Non-Compositional Sketches
- 7Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability
- 7TOOD: Task-Aware Out-of-Distribution Score Calibration for Continual Learners
- 7Logical Regression for Planning with Axioms
- 7PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing
- 7ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression
- 7Long-Context Fine-Tuning with Limited VRAM
- 7Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
- 7Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
- 7SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
- 7GLM 5.2 is nearly as accurate as a human book keeper
- 7VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
- 7MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
- 7The Silurian Hypothesis (2020)
- 7Cautious optimism for deep parameterized quantum circuits
- 7PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks
- 7🐈⬛Check Out Catbot's New Leg!
- 7$β$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
- 7TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
- 7DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation
- 7Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks
- 7Aristotle quotes on virtue, knowledge, and happiness
- 7Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
- 7Taylor Farms has rewritten its cyclospora statement four times in sixteen days
- 7Keeping code alive on a DOM you don't own: 12-year Chrome extension story
- 7Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
- 7AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
- 7Cycle-Consistent and Uncertainty-Aware Neural Surrogates for Tokamak Edge Plasmas
- 7I got tired of uploading my HEIC photos to random servers, so I built a WASM-powered client-side converter
- 7Algorithms for Structured Elections under Thiele Voting Rules
- 7Revisiting data-driven dynamic security assessment with a tabular foundation model
- 7SpaceX stock erases all its gains and slides below IPO price in intraday trading
- 7Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs
- 7Anti-Periodic Positional Encoding: Möbius Boundary Conditions Make In-Context Retrieval Reliable
- 7MemTools: A Unified Research Framework for Interoperable Agent Memory
- 7A Diffusion-Model Subpopulation Digital Twin for Mobile Health Deployment: A Case Study on the HeartSteps Intervention
- 7MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning
- 7DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat
- 7Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
- 7When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation
- 7Doubly Robust Functional Representation Learning for Longitudinal Causal Inference with Irregular Histories
- 7Rethinking Quantum Continual Learning with Quantum Fisher Information
- 7VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
- 7CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach
- 7Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence
- 7Reflector: Arrangement-Aware Harmonic Retrieval for Sample-Based Composition
- 7Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints
- 7Candidate Attended Dialogue State Tracking Using BERT
- 7I stopped reviewing my own code. Here's what had to be true first.
- 7Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation
- 7LunarFM: A Shared Multimodal Representation of the Moon's Surface
- 7ERC-8378: Parametric Token
- 7Towards Hierarchical Structure Understanding of Newspaper Images
- 7A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation
- 7Learning Ergodic Dynamical Systems from a Finite Trajectory
- 7MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models
- 7Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models
- 7APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems
- 7LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
- 7Evaluating covariate balance for long time horizon Markov decision processes
- 7BrainPilot: Automating Brain Discovery with Agentic Research
- 7Twenty Years of Pandoc
- 7Pyramidal Width Can Increase Under Vertex Insertion
- 7SceneActBench: Can Agents Act on the 3D Scenes They See?
- 7An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications
- 7DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
- 7AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation
- 7COntExt: Towards Context-Aware Ontology Extension from Operational Metrics
- 7HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding
- 794 Million Hausa Speakers, and AI Still Barely Understands Them. What Three Years of Grassroots Work Taught Me.
- 7ORCA-bench: How Ready Are Language Model Agents for Oncall?
- 7Testing Non-Deterministic LLM Pipelines in CI: A Contract-Based Approach
- 7AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
- 7Agentic Root Cause Analysis through Evidence-Grounded Reasoning
- 7Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
- 7BayesPO: Bayesian Prompt Optimization via Parallel-Tempered Gradient-Guided Discrete MCMC
- 7Kernel weighted importance sampling for off-policy evaluation in contextual bandits
- 7Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature
- 7DriftWorld: Fast World Modeling through Drifting
- 7Can Google ADK Talk to Microsoft Foundry on Azure? A Cross-Cloud A2A Benchmark
- 7Future euro banknote design proposals
- 7ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation
- 7Businesses with ugly AI menu redesigns
- 7How can I use Microsoft Entra on a GitHub Page for an Azure Function?
- 7ScaFE: Data-Efficient Scar Classification with LLM-Generated Clinical Feature Programs
- 7Graph Neural Network Force Fields for Spin Dynamics in Metallic Magnets
- 7A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books
- 7IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
- 7ANet Patu-1: The Value of Connection in the Agent Network
- 7AI Coding Agents Can Make Junior Developers Faster. Can They Still Make Them Better?
- 7CanonicalPhys: Pose-Robust Remote Photoplethysmography via Canonical-Space Priors
- 7AI systems and the reproduction of (standard) language ideologies in World Englishes
- 7MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
- 7What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
- 7Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
- 7Selective Credibility-Limited Belief Update
- 7A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer's Disease
- 7Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI
- 7Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
- 7Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening
- 7Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
- 7Vision-Language-Action Models: When LLMs Learn to Use Their Hands
- 7A Formally Grounded ODRL Evaluator: Implementation and Comparison
- 7DebrisTracer: Reliable Tracking in Hypervelocity Impact Fast Imaging
- 7Evidence of inconsistencies in evaluation process and selection of winners
- 7Interior interpretability with attention rollout: contraction and propagation profiles in Transformers
- 7Creative Transformation in Literary Texts: Modelling Change Across Representational Levels
- 7Learning Structural Convergence: A Neuro-Symbolic Benchmark for Temporal Reasoning
- 7雲吞麵 Midnight Wonton Noodle — Pure CSS Art
- 7Show HN: I made a game where you build a CPU from logic gates
- 7xCurl, a cut-down fork of libcurl for the Microsoft Game Development Kit
- 7Indexing: the Beginning and the End
- 7Man, Machine, and Masterpiece: Artistic Ownership in the AI Era
- 7The LLM API Failure Policy I Wish I Had Before My First Production Incident
- 7Computers Finally Care About Code
- 7Nix's Substituter List Is Not a Routing Table
- 7Modern email can be built from borrowed parts
- 7Integrated Order Dispatching and Routing for Last-Mile Pickup via Deep Reinforcement Learning
- 7SiPhy: Single-Image Physical Property Reasoning
- 7An Exploratory Study of Single Channel Surface Electromyography for Hand Gesture Classification
- 7The Productivity Mirage
- 7cGAP: Generalized Association Plots with HOMALS-Guided Heatmaps for Visualization of High-Dimensional Categorical Data
- 7Code-Poisoning Property Inference Attacks
- 7Time-Reversed Imaging: A Multimodal Benchmark and Framework for Reconstructing Past Human-Environment Interactions
- 7IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data
- 7Sociocultural Influences on Opinion Formation: Word of Mouth Dynamics, Mass Media and Behavioural Development
- 7@better-auth/stripe — Stripe plugin for Better Auth
- 7OpenWhen - For Intentional Lovers
- 7Teachy Mini: Development and Preliminary Evaluation of a Knowledge-Based Generative Social Robot for Higher Education
- 7I built a tool to prove my multi-agent harness was worth it. It told me it wasn't.
- 7When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration
- 7How to Shine as an Introvert in a Loud Tech World
- 7SMC-ES: Automated synthesis of formally verified control policies
- 7My Verification Gate Cleared on a Keyword, Not Evidence
- 7LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
- 7I Added `--retries 2` to Our Pipeline. It Took Me Eight Months to Understand What I'd Done.
- 7Beyond Binary Rooftop Mapping: A Four-Class Deep Learning Framework for Green Roof Potential Assessment from Open Swiss Geospatial Data
- 7The Capitalist Supremacy Trap: Why Our DAO Governance is a Digitized Feudal State
- 7AI Is Great at Reasoning. Stop Using It for Workflows.
- 7From Plausible to Actionable: A Position on LLM Self-Explanations
- 7Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
- 7firebase_ai Flutter plugin fails with "Cannot query the value of this provider because it has no value available" on Gradle 9.1.0
- 7I love LLMs, I hate hype
- 7I Built a Tool That Auto-Fixes Downstream Code When You Change an API
- 7Long presumed dead, a thriving coral reef is discovered in West Africa
- 7Leanstral 1.5: Proof abundance for all
- 7Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAG
- 7When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations
- 7More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
- 7Mesh LLM: distributed AI computing on iroh
- 7Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs
- 7Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks
- 7Opinionated and easy Pi.dev configuration
- 7SpaceX wants to launch 100k more Starlink satellites for 100x the bandwidth
- 7Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark
- 7A Roadmap to Impactful Pluralistic Alignment Research
- 7Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloning
- 7My AI agent tried to ship a mistake we'd already reverted
- 7Biomedical Machine Translation for Low-Resource Arabic-Script Languages via Cross-Lingual Transfer and LoRA Adapter Merging
- 7Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
- 7How to use a script Injector to Block Rufus on Amazon permanently
- 7Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment
- 7Small Penis Rule
- 7Dua Lipa opens library for banned and censored books in Portugal
- 7Telegram Serverless
- 7Launch HN: Bloomy (YC S26) – AI-powered mastery learning for K-12
- 7How Doctors die. It’s not like the rest of us (2016)
- 7How I made a scroll-scrubbed video portfolio fast (Next.js 15 + GSAP + canvas)
- 7SearXNG: A free internet metasearch engine
- 7Ghost Font: A font that humans can read but AI cannot
- 7Why American ambulance rides are so expensive
- 7Efficient Recommendations via Graph Coarsening and Label Propagation
- 7jdeps does not seem to ignore missing dependencies
- 7An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detection
- 7How to read more books
- 7Does creatine make you smarter?
- 7Every AI Commit Is Someone's Future Legacy Code