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.
- 9Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs
- 9CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
- 9Can AI agents conduct open-ended AI research? Early evidence from two case studies
- 9The Condition-Number Barrier in Sparse Least Squares
- 9APEX-Accounting
- 9Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes
- 9Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
- 9The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
- 9Agents in the Wild: Where Research Meets Deployment
- 9GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
- 91-Lipschitz Neural Networks on Hadamard Manifolds
- 9DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
- 9I Ran an AMA on Dev.to. Here Are My Favorite Questions
- 9UEmbed: Unified Sparse and Dense Multimodal Embeddings
- 9Fundamental limits of distributed multiclass classification from simple binary decisions
- 9Provable diffusion-based posterior sampling for linear inverse problems via DDIM
- 9GigaPath-Flash and GigaTIME-Flash: Efficient Pathology Foundation Models for Whole-Slide and Tumor Microenvironment Analysis
- 9Pangram 4 Technical Report
- 9ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
- 9Cloudflare OS — Build the AI operating system for your company
- 9ISO: An RLVR-Native Optimization Stack
- 9Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
- 9CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs
- 9Smooth Reparameterizations of Functions on Simplicial Product Spaces: Applications to Probabilistic Tensor Decomposition and Functional Data Registration
- 9Firefox Containers Preview
- 9The Social Cost of an AI Teammate: How an Artificial Teammate Reshapes Human-Human Communication in Small-Team Decision-Making
- 9Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
- 9DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search
- 9Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
- 9Associative Emotional Learning in Convolutional Neural Networks
- 9Selective State-Space Adaptation and Retrieval for Language Model Reasoning
- 9SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
- 9ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
- 9Improving Item Discoverability in e-Commerce Search via Related Intent Generation
- 9AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies
- 9Unveiling Invariant and Transferable Latent Factors Across Heterogeneous Environments via ATLAS
- 9When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems
- 9Persian Pixel: A large-scale synthetic OCR dataset for Persian language
- 9Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection
- 9Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness
- 9SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
- 9FMRP-LEAN: A HIPAA-Compliant AI-Augmented LIMS Architecture for End-to-End Clinical Assay Workflow Optimization
- 9ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
- 9Benchmarking Sheaf Neural Networks for Inductive Tasks
- 9Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
- 9Learning Adaptive Safety Margins for Visual Navigation
- 9Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation
- 9PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs
- 9PPL-Factory: Task-Aware and Budget-Aware Data Selection from Language Modeling to Reasoning
- 9Three-Body Scattering for Generative Modeling
- 9A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI
- 9Certified Training for Convolutional Perturbations
- 9Statevector-Referenced Geometry Survival of a Four-Qubit ZZ Quantum Kernel on IBM Quantum Hardware: A Fixed-Subset Diagnostic Across Three Execution Configurations
- 9Who Should Be Generated? Justifying Demographic Targets in Open-Ended Generation
- 9Online Variance Reduction for Domain Adaptation on Streaming Data
- 9Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines
- 9CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
- 9OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
- 9Notes to Self: Can LLMs Benefit from Experiential Abstractions?
- 9Anatomy Contextualized Adaption of CT Foundation Models
- 9Skillful forecasting of offshore winds from satellite scatterometer constellations
- 9Pass the Baton: Trajectory-Relayed On-Policy Distillation
- 9Beyond Scale and Generation: Understanding Language Model-based Entity Matching
- 9$π\mathbf{R}^2$: Reactive Real-time Flow Policies
- 9Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training
- 9Variance-reduced Domain Adaptation using Paired Sampling
- 9Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
- 9Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
- 9I Built a Free API That Detects Phishing Sites Using AI Vision — And It Catches Prompt Injection Too
- 9Quake_4_Alpha — Quake 4 alpha released for preservation purposes only.
- 9A Simple Approximation to the Distribution of the Ridge Regression Estimator
- 9OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
- 9Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation
- 9Staypoint Detection from Noisy Trajectory Data [Experiment Paper]
- 9Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
- 9Optimal Unambiguous DNFs and Alon-Saks-Seymour
- 9Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
- 9EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database
- 9The Loss Does Not See the Basis, but Adam Does
- 9Hetzner is working on LLM Inference
- 9Stacking the Deck: Tunable Trainability in Stacked LCUs
- 9Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
- 9Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
- 9Predicting Brain Morphometry with MT-GNN: Mesh Evolution in Continuous Time with Graph-Based Metric Tensor Embeddings
- 9OPD-V: Visual On-Policy Self-Distillation with Modality Balance
- 9Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosis
- 9MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
- 9SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
- 9Trying to Change A Pixel in Python
- 9VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening
- 9Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models
- 9Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?
- 9Chained Recursive Language Models for Multi-Iteration Reasoning
- 9Show HN: Gander, an Android file viewer that asks for no permissions
- 9From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs
- 9DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery
- 9Riemannian Deep Learning:Modules, Networks, and Geometries
- 9MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs
- 9VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design
- 9Analytic Planning under Uncertainty with Moment Closure
- 9Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling
- 9Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
- 9Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation
- 9Causal-TS: A Python Library for Causal Discovery in High-Dimensional and Nonstationary Time Series
- 9Explainable Reinforcement Learning via Physics-Aware Policy Distillation
- 9Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift
- 9Cost-Sensitive Conformal Prediction and Human-in-the-Loop Abstention for Imbalanced High-Stakes Decision Support: A Multi-Domain Benchmark
- 9Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning
- 9Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth
- 9Falling Behind Drives Unsafe Development in an Idealised AI Race Experiment
- 9Real-time optimal control with shallow recurrent decoder networks
- 9CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
- 9FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
- 9BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning
- 9Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Flow-matching
- 9LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
- 9Investigating reservoir computing for branch predictionin pipelined processors using emerging CMOS memristor devices
- 9ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
- 9LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior
- 9Why AI Still Can't Write Well and Which Half of That Problem Is Actually Yours
- 9DLAM: Distributional Latent Actions with Temporal Constraints
- 9Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating
- 9Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies
- 9A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing
- 9OR Else: A Differentiable Trust Region for Policy Optimization
- 9RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
- 9The Calibration Channel Determines the Bayes-Error Proxy: An Exact Law for Temperature-Induced Distortion
- 9Beyond Modern Asymptotics for Log-Likelihood Ratios in Logistic Regression
- 9Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes
- 9Test-Time Training for Modality Order Consistency in Vision-Language Models
- 9TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
- 9CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
- 9MMOE: Modernizing Diffusion Transformers with Efficient Expert Design
- 9Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation
- 9CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization
- 9Linguistic Monoculture in LLM-Assisted Language Use
- 9Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?
- 9Generative AI floods and dilutes the market for books
- 9SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
- 9Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes
- 9The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
- 9Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
- 9DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
- 9Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids
- 9When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction
- 9UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
- 9MDTransformer: A Hardware-Software Co-Design of Mode-Division Photonic Transformer Accelerator with Inverse-Designed Coherent Crossbar
- 9Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Do
- 9AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
- 9Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
- 9MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning
- 9Item Response Theory for AI Safety
- 9Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
- 9Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control
- 9jaq: A jq clone focussed on correctness, speed, and simplicity
- 9A Reinforcement-Learning-Augmented Liquid-Fueled Reactor Network Model for Predicting Lean Blowout in Gas Turbine Combustors
- 9Voronoi Histograms for Adaptive Vectorization of Expected Persistence Diagrams
- 9Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
- 9Auditing Agent Skills: A Threat Model for the Next Generation of AI Package Managers
- 9Pictura: Perspective-View Self-Play at Scale for Driving
- 9Parallel Decoding Distillation for Fast Image and Video Generation
- 9How to Test 40+ UI Components in Under a Minute: Speeding Up Screenshot Tests
- 9Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels
- 9MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
- 9Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
- 9German parties shifted towards intuition-based rhetoric after the far right's parliamentary breakthrough
- 9Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm
- 9Totally Positive Matrices and the Highest-Order Coefficients of the Characteristic Polynomial
- 9Reason-Mediated Behavioral Models for Auditing LLM Social Simulators
- 9Efficiency Matters in Autonomous Research
- 9Empirical Evaluation of Out-Of-Distribution Performance of Tabular Foundation Models
- 9m3e-canvas — Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
- 9Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
- 9Episode 6 — Watching Something You Can't See
- 9LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
- 9Understanding Generative AI-mediated User Engagement with Academic Library Resources
- 9PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference
- 9Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
- 9That Arrow in Every RAG Diagram Cost Us Three Weeks.
- 9Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout
- 9VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detection
- 9GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Models
- 9Multi-modal transformer for signal classification in nanopore blockade experiments
- 9MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
- 9They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface
- 9Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation
- 9MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning
- 9Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields
- 9Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networks
- 9Generator-Aligned Representation Interfaces for Diagnostic Soft Equivariance
- 9Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics
- 9O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
- 9Schrödinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics
- 9BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance
- 9PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image
- 9Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions
- 9Benchmarking Generalization in Financial Statement Fraud Detection: robust evaluation and novel tasks
- 9Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting
- 9Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
- 9Detecting seizure onset and offset times using human intelligence: A critical-transitions-based approach