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.
- 19TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations
- 19Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals
- 19Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority
- 19Minimally Invasive Steering of Language Models
- 19Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
- 19Token-Level Advertising
- 19A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model
- 19Constant regret in general games via higher-order optimism
- 19Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage
- 19Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
- 19D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
- 19Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings
- 19CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
- 19Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
- 19FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
- 19Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
- 19Which Eviction Policy Should an LLM Cache Use? A Systematic Study Across Workloads, Capacities, and Encoders
- 19Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning
- 19RecipeNet: A Hierarchical Transformer for Recipe Data
- 19Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems
- 19Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration
- 19Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
- 19You know you can automate screen reader tests right?
- 19CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
- 19CSF: Contextual Safety Filtering for Motion Generators
- 19A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control
- 19On the estimation and validity of AI time horizons---a statistical look at the METR plot
- 19Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
- 19Interaction Creates Dynamical AI Behavior Absent in Isolation
- 19What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
- 19COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules
- 19The Alignment Illusion in Multimodal Large Language Models
- 19Hardware-Aware FP4 FlashAttention-4
- 19Rethinking Sequence Compression with Test-time Regression
- 19BrickBench: Evaluating Agentic Brick Design
- 19Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
- 19One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- 19Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
- 19Universal Thermodynamic Interatomic Potentials for Crystalline Materials
- 19Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
- 19Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization
- 19Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding
- 19A Living Benchmark for Information Retrieval from Electronic Health Records
- 19Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
- 19Synthetic Persona Pretraining: Alignment from Token Zero
- 19Density Ratio Estimation with Stein Displacement Fields
- 19Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
- 19VioLA: Learning Generalist Humanoid Control Policies from Human Data
- 19DiaVLo: Diagnosing Behaviours of Vision-Language Models
- 19On the Token Collapse Phenomenon in Textual Graph Soft Prompting
- 19Across-Design Uncertainty in Short Pricing Panels: Evidence from Simulated Price Trajectories
- 19Strategy-first synthesis planning for complex natural products
- 19FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems
- 19Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models
- 19Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning
- 19Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers
- 19Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
- 19Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training
- 19Monetizing Intelligence: Advertising and Subscription Design on LLM Platforms
- 19Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation
- 19Planning to Learn
- 19FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?
- 19RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
- 19Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation
- 19Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models
- 19Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
- 19Universality and sharp thresholds for ellipsoid fitting
- 19Forecasting from Counterfactual Simulator Rollouts: A Sim2Real Evaluation
- 19ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
- 19Knowledge Distillation across Item and Code Spaces for Parallel Generative Recommendation
- 19Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
- 19Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
- 19A Unified Bellman Operator for Safety-Critical Reinforcement Learning
- 19Generating Benchmark Health Data Using a Tabular Diffusion Transformer
- 19WOVEN: Weaving Visual World Modeling into Multimodal LLMs
- 19MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
- 19Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
- 19Learning When to Trust via Selective Context Preference Optimization
- 19Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090
- 19RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
- 19The Dynamics of Intelligence Explosions
- 19Learning Personalized Memory Gating from Delayed One-Sided Feedback
- 19If at First You Don't Succeed, Backtrack: Lightweight Recovery for Frozen VLAs
- 19Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
- 19Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete
- 19Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
- 19Asynchronous I/O in DuckDB: Work, Thread, Work
- 19Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
- 19The Bitter Lesson of Tool Calling
- 19Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
- 19SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
- 19ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
- 19MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
- 19Learning Positive Linear Combinations of ReLUs in Fully Polynomial Time
- 19SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
- 19PoCoFL: POlicy-COmpliant Federated Learning
- 19Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
- 19Approximate Muon with low-rank adapters
- 19When to Follow the Teacher: Advantage-Based On-Policy Distillation
- 19Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
- 19Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models
- 19Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeria
- 19On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
- 19An Optimal Agnostic PAC Algorithm
- 19Stageboost: Recommending Signals Based on Counterfactual Estimation
- 19Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy
- 19Optimal Scheduling of Road Maintenance Jobs Considering Impact on Traffic Flows
- 19AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games
- 19The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
- 19Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
- 19DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
- 19When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity
- 19KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representations
- 19Time-Aware Tranformer-Based Prediction Model for AECOPD
- 19Twin: Playing an Unknown Game with a Test-Time Digital Twin
- 19Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents
- 19Sophistication in GenAI Use: Field Evidence from a Large Firm
- 19A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
- 19I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
- 19Predicting Alignment Generalization with Value Representations
- 19Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal
- 19Assessment of Machine Learning-Based Critical Heat Flux Models in the CTF Subchannel Code for Square Rod Bundle Prediction
- 19Jev-Mobile: Jev as an Executor for Mobile GUI Agents
- 19Intrinsic-Extrinsic Coupling in Learning Dynamics
- 19Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
- 19On the Convergence of Success Conditioning for Policy Optimization
- 19Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model
- 19ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
- 19IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models
- 19Broken scale symmetries in undercomplete linear autoencoders
- 19LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
- 19MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
- 19Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
- 19CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
- 19Challenges in Evaluating Explanation Methods for Static and Evolving Data
- 19More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It
- 19REPLICANT: Learning Policies for Evading and Hardening Malware Detectors
- 19Unified Branch-and-Bound Search for the Steiner Traveling Salesman Problem on Graphs of Convex Sets
- 19Your Voice Cloning System is Secretly a Voice Anonymizer
- 19Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
- 19ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
- 19SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
- 19RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer
- 19From Regulation to Implementation: A Critical Evaluation of LLM-Assisted Regulatory Compliance in Industry
- 19GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks
- 19Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
- 19Learning Kilometer-Scale Weather Prediction with Global-Regional Alignment
- 19TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
- 19LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
- 19On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces
- 19AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
- 19SpaceFlow: Locally Controllable 3D Generation
- 19Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
- 19Prompt-Model Interaction Reaches the Fixed Points: A deterministic, task-free structural readout -- and the factorizations of it that failed
- 19Scalable estimation of VARMA models
- 19Beyond SAEs: Consistent Concept Discovery with Sparse Coding
- 19GridSFM: A Foundation Model for Solving AC Optimal Power Flow
- 19Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
- 19Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents
- 19Prospective Prediction of OOD Degradation from Source-Side Training Dynamics
- 19Addressable Memory for Video World Models
- 19World Embedding Benchmark
- 19CytoBERT: A Foundation Model for Cytometry Data
- 19Task-aware Kernel Stein certificates for Rényi differential privacy
- 19DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers
- 19NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents
- 19Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation
- 19Time series generation with spectrally aligned latent flow matching
- 19ZENO: Nonlinear filtering with Zakai Equation Neural Operators
- 19Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes
- 19OpenBSD EuroBSDcon 2015 presentations
- 19HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling
- 19Transfer Learning in Nonparametric Regression with Deep ReLU Networks
- 19GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
- 19FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
- 19How to move the responsibility of executing some logic to the SQL Server instead of executing that logic inside the application?
- 19GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation
- 19Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
- 19RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting
- 19Do Audio Language Models Hear and Read Distinctive Features Alike?
- 19Optimal Rates for Learning with Monotone Adversaries
- 19You can't transition a CSS variable. @property says otherwise.
- 19Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora
- 19DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
- 19Depth as Time in One-Step Generative Models
- 19FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
- 1912 Important Concepts All Software Developers Should Know
- 19SemantEq: Faithful Bidirectional Equivalence of Formal Statements
- 19Parametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPs
- 19DLite: History-free Speculative Decoding for Agentic AI
- 19Online Inference in Distributional Temporal-Difference Learning
- 19LP-NAS: Linear Programming-based Neural Architecture Search
- 19AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction
- 19A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition
- 19LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
- 19Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
- 19Blast Radius
- 19Sampling the XY model with an attention-based neural network
- 19A Tutorial on Physics Constrained Machine Learning for Hybrid Modeling, Optimization, and Control
- 19Can guitar frets perform multiplication?