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.
- 19Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
- 19Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
- 19Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning
- 19ReCite: Agentic Reasoning for Faithful Citation
- 19MindView: Benchmarking Generative Multi-View Spatial Intelligence
- 19Learning Length-Extrapolatable Recurrent Models
- 19Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
- 19TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model
- 19Planning under Noise with Neural Operators
- 19Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
- 19Who Improves the Robot? Toward Physical Recursive Self-Improvement
- 19DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
- 19PaperGym: Rubric-Centered Evolution for Research-Plan Generation
- 19LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models
- 19UniWALM: Unified World Action Language Model for Embodied Robot Control
- 19Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
- 19EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning
- 19Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking
- 19The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
- 19GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery
- 19EIP-8372: Normalized state gas limit
- 19An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators
- 19Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
- 19FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
- 19On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
- 19Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria
- 19MFG: Multi-turn Feedback Guided Molecular Optimization
- 19Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
- 19Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory
- 19Exact Topological Compliance: Generating Persistence-Equivalent Graphs
- 19Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
- 19AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
- 19Hybrid Reasoning Agents
- 19DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning
- 19Data Free Training of Diffusion Models for Lattice Field Theories
- 19LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
- 19Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
- 19What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
- 19Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
- 19ChunkAct: Action Chunking for Agentic Robotics
- 19Orbitol: Crystal Generation on Wyckoff Orbits
- 19AutoSR: Automatic Symbolic Regression by Searching Research States
- 19A Systematic Study of Semantic ID Spaces for Generative Information Retrieval
- 19AVA-Encoder: Towards Agent-Native Video Representation Learning
- 19Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
- 19How I changed teaching after AI managed to do all my homework assignments
- 19Prefix Sliding for efficient test-time scaling
- 19Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run
- 19rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
- 19Verifiable Social Reasoning for LLM Assistants
- 19Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
- 19How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents
- 19Minimal-Norm Univariate Two-Layer ReLU Classification: Exact Solutions and Global Optimality with Skip Connections
- 19Optimal and Efficient Online Inverse Optimization
- 19Q-based Variational Inverse Reinforcement Learning
- 19Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
- 19GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay
- 19General Quantification of Covariate and Concept Shifts
- 19Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
- 19Can Edge-Deployable Vision-Language Models Identify Species?
- 19Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact
- 19Distance generalization in transformers: why bother with positional encoding?
- 19VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift
- 19Artificial Id: Drive and Persistent Alignment in Agentic AI
- 19Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling
- 19From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good
- 19On the Computational Tractability of Robust Bandits
- 19TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
- 19EIP-8371: RowDAS - Distributed Blobspace Reconstruction
- 19MindTopo: Can Foundation Models Reason in Topological Space?
- 19Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving
- 19Show HN: Open-source Stripe Connect alternative
- 19DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening
- 19CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
- 193D Point Splatting for mmWave Radar Novel View Synthesis
- 19Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
- 19A rule-based Korean dialect converter with no LLM: eight guards that keep standard Korean intact
- 19Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation
- 19Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
- 19Linear Bandits under Exact Sliding-Window Constraints
- 19ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
- 19CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search
- 19The Missing Minimal Pair: Stereotype Evaluation in LLMs
- 19Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models
- 19Implementing neural network mixed-effects models in Template Model Builder (TMB)
- 19SwarmWorld: Stigmergic technological evolution in societies of language-model agents
- 19EIPIP Meeting #131, Oct 20, 2026
- 19Domain-Specific Hallucination Detection in Large Language Models
- 19Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
- 19On the Regularization Landscape for the Linear Recommendation Models
- 19OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
- 19The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
- 19Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
- 19Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting
- 19Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
- 19Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
- 19Play two songs back to back in autoplay
- 19Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start
- 19AdamX: Cosine similarity meets gradient descent
- 19You still write `finally { resource.close() }`. The `using` keyword does it automatically.
- 19AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation
- 19Epistemic orientation predicts legislative effectiveness among members of the US Congress
- 19RetroThinker: Enabling Retrospective Thinking in Speech LLMs
- 19Differentially Private Sparse Reward Estimation with Preference Feedback
- 19Neural Petri flows for chemical reactions
- 19ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing
- 19Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
- 19From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
- 19Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation
- 19LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
- 19Nonequilibrium Phases of Repulsive Self-Attention: Chaos, Attention Condensation, and Emergent Locality
- 19Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark
- 19Inoculation Midtraining with Learned Neologisms
- 19Flag Game: A Toy Model for Mechanistic Swarm Interpretability
- 19Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
- 19IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing
- 19Affora: A Design System for Agent-Friendly Interfaces
- 19Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
- 19TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
- 19Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings
- 19Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
- 19Did the Problem Actually Get Harder? Testing LLMs on Paired P and NP-Complete Problems Hardened by Adversarial Multi-Agent Rewriting
- 19BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard
- 19Asymmetric On-Policy Distillation Learns In-Context Exploration
- 19Quenched Ensemble Sampling
- 19Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
- 19Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
- 19WorldSonus: Bringing Sound to Worlds
- 19Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
- 19VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
- 19Rapid Fredholm stabilization of the Kuramoto--Sivashinsky equation with unrestricted, spatially-varying anti-diffusion
- 19What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
- 19Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
- 19When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
- 19Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching
- 19PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans
- 19Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use
- 19Minimax Optimality of the NPMLE for Gaussian Mixtures in Hellinger Distance
- 19Even Sharper Bounds for Transductive Learning and Its Applications
- 19Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research
- 19Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
- 19Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's Role
- 19MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching
- 19PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
- 19The End of Consensus Research?
- 19A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
- 19Environment Duels: A Microcosm of LLM Co-Evolution
- 19ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
- 19Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations
- 19Mathematical Origami
- 19Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction
- 19The role of locality and weight sharing in convolutional neural networks
- 19Self-normalized Bernstein Inequalities for Regenerative Processes and Applications to Learning Without Independence
- 19A Quasipolynomial Algorithm for $\ell_\infty$ Contractions
- 19ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
- 19Agentic Societies Need a Social Harness
- 19AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
- 19Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
- 19PhysiCalWorld: In-Context Physics Calibration for World Models
- 19Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
- 19VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
- 19Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
- 19Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation
- 19StudentBench: AI and human tutoring yield equivalent GRE learning gains
- 19SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection
- 19FieldOS, Part 3: The App People Open, and What 10 Hours Taught Me About Pricing
- 19SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies
- 19Constant Individual Regret in General Games
- 19LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data
- 19Sherpa: Teaching LLMs to Teach Adaptively
- 19Our AI coding agents ignored their instructions for a month. Nothing errored.
- 19Contrastive Learning for Authorship Verification
- 19Context-Aware Interleaved Batching for WhisperX
- 19DepthWorld: 3D World Model for Robot Manipulation
- 19IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
- 194D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
- 19Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective
- 19On the Diffusibility of High-Dimensional Latents
- 19QF3: Fast Flow RL with Filtered Q-Gradients
- 19PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
- 19A Zeroth-Order Paradigm for LLM Preference Alignment
- 19Objective vs. Search: Decomposing What Makes a Good Tokeniser
- 19Safe Meta-Reinforcement Learning via Information Space Reachability
- 19Doesn't JavaScript have console input?
- 19Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
- 19Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations
- 19Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological Progress
- 19I shipped 200 tools as single HTML files. Here's what that constraint actually buys you.
- 19Recurrent GraphNeural NetworkswithSet-BasedAggregation
- 19Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
- 19Singular parameters and missing limits in neural PDE solvers
- 19My AI Agent Tried to Delete Every Customer Record. Here's What Stopped It.
- 19HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
- 19Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale
- 19On Learning Optimal Corners in Orthogonal Partially Observable Cooperative Guard Art Galleries
- 19Load Leveling: Why ERC-8415 Decouples Settlement Speed from Off-Chain Registry Throughput
- 19IdeaLens: Detecting AI Ideas in Long-form Writing
- 19T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search
- 19How to scale your HEP ML models: A recipe for robust architecture comparisons at scale
- 19Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication