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.
- 19$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
- 19Defensive Boosting for Online Probabilistic Forecasting
- 19SoftServe: A Scalable Quasi-Newton Method for Deep Learning
- 19BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings
- 19Generative Cinematographer: Composing Camera and Object Motion in 3D
- 19Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
- 19A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
- 19From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
- 19Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
- 19Advancing Interaction-Sensitive Feature Selection: Novel Relief-Based Algorithms, Expanded Comparisons, and Recommendations for Biomedical Data Mining
- 19An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
- 19MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling
- 19Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
- 19CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
- 19Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
- 19Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
- 19Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
- 19WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- 19Phase Transition from Random Features to Fully Trainable Networks
- 19Inducing Task Models from Computer-Use Traces
- 19Reliable AI-Assisted Decisions via Selective Auditing
- 19AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
- 19Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
- 19SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing
- 19QuoteBench: How Matched Scores Can Hide Command-Path Failures
- 19Cost-Aware Abstention for LLM-Based IT Ticket Classification
- 19Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination
- 19SWE-Prime: Fewer Trajectories, Better Performance
- 19TTPO: Test-Time Policy Optimization
- 19METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
- 19A Computationally Feasible Framework for Causal Probabilistic Explanation
- 19Extending Slugs Across Templates and Entities for Deterministic API Workflows
- 19LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
- 19AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents
- 19@llm-ports/core — Provider-agnostic LLM port interface, registry, cost gating, content blocks, validation strategies. The foundation of llm-
- 19EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
- 19Last Translation Benchmark
- 19Retrainable physics-integrated neural differentiable modeling of sintering across material systems
- 19Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
- 19Rethinking On-Policy Distillation of Large Language Models II: One Training Example
- 19From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
- 19Video Generative Models as Geometry Learner
- 19Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records
- 19Rust malware in arrayref: how a build.rs ran a payload at compile time
- 19A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
- 19MidTool: Mid-training Data Synthesis for Agentic Tool Use
- 19Low-Bit N-Gram Embeddings for Language Models
- 19On-Demand Attention: Language Models Know When to Recall
- 19Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs
- 19DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication
- 19RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
- 19SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents
- 19SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
- 19When Do Intrinsic Rewards Lead to Exploration?
- 19Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
- 19A Fix for Softmax and Cross-Entropy
- 19Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
- 19From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
- 19DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
- 19Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
- 19From Knowledge Access to Source Learning: Developing Source-Specific Competence
- 19Benchmarking World Models for Continual Learning on Compositional Tasks
- 19Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
- 19Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomography
- 19Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise
- 19Can an Agent Debug a Web Corpus? Agentic Auditing of Slovak FineWeb2
- 19Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
- 19ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
- 19SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center
- 19Faynt: Scaling and Optimizing Policies for Competitive Melee
- 19Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
- 19Stochastic Estimation of Transduced Language Models
- 19Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit
- 19Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
- 19BeNice! Closing Looping's Inference-Memory Gap via KV-Sharing
- 19Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
- 19Decoding the Past: An Uncertainty-Aware Deep Learning Framework for Sex Attribution in Prehistoric Hand Stencils
- 19Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
- 19Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
- 19An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models
- 19Boosting LLM Exploration via Weak-Model Guidance in RLVR
- 19Marionette: Predicting World States, Rendering Geometry, Painting Appearance
- 19DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
- 19Handover of In-Context Learning State Across Session Boundaries
- 19Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3
- 19Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
- 19Available Guardrails: Certifying Selective Prediction across ML Systems
- 19Vero: Can AI Agents Build Formally Verified Software Repositories?
- 19Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
- 19A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle
- 19Exponential quantum advantage for learning signals with a single qubit
- 19Bilingual Language Models Capture Cross-Linguistic Influence in Second-Language Reading
- 19Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
- 19The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
- 19OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation
- 19Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers
- 19InstructMesh: Selective Refinement of Generative 3D Models for Fabrication
- 19An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
- 19Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
- 19$λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource
- 19Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology
- 19DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
- 19Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
- 19Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
- 19Bagging Robustly Learns VC Classes with Linear Sample Complexity
- 19Physical-Support Confidence Sets for Highly Coherent Dictionaries
- 19Gricea: An Open Science Platform for Conversational AI Research
- 19TabSOM: A tabular-to-image encoding method based on self-organizing maps
- 19QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge
- 19What should a personal website be?
- 19On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective
- 19How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions
- 19Efficient Test-Time Adaptation through Human-AI Interaction
- 19CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
- 19Equivariant learning of a transferable three-dimensional classical density functional
- 19Intern-S2-Preview: Scientific Agentic Foundation Model
- 19Sparse Orthogonal Regression Technique: A Spectral Framework for Equation Discovery, Approximation, and Integration
- 19Phantom Gains: Auditing Self-Improvement Against a Measured Null
- 19The Natural Language Interaction Protocol and Standard for AI Agents
- 19Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
- 19LLM Agents Can Easily Tamper With Their Own Traces
- 19AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
- 19Primal Acceleration of Newton's Method
- 19Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks
- 19Rethinking the design space of Vanilla Pixel Diffusion Transformers
- 19VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences
- 19Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
- 19Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
- 19AI with Authority, from Application to Silicon
- 19The Language of Instruction: Genre and Generative AI
- 194DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
- 19Agentic Detection of Online Conspiracies
- 19Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
- 19SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
- 19What Should World Models Forget? Stratified Retention for Continual Adaptation
- 19RAPID: Robot Agentic Programming from Demonstrations
- 19How Language Models Organize and Structure Moral Knowledge
- 19RNADyn: A Benchmark for Generating and Understanding RNA Dynamics
- 19Behavioral Couplings: From Formation to Behavioral Emergence in Language Models
- 19Rolling-WAM: World Action Models with Rolling Imagination
- 19EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
- 19From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing
- 19AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery
- 19JevOut: Natural Context Can Flip Decision Models
- 19DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- 19RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
- 19Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
- 19Environment Evolution for Terminal Agents
- 19LESSER: Post-Training Data Selection with Output-Layer Gradients
- 19DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
- 19SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
- 19Designing Compact Neural Architectures via Neuron Gating and Mixed Activation
- 19Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable
- 19PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
- 19Language Models that Play Chess and Explain Their Moves
- 19CRANE: Post-Hoc Counterfactual Retrieval for Multimodal Classifiers
- 19Learning-to-Transition for Large-scale and High-Order MIMO Detection
- 19LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- 19When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI
- 19Simulated Control Evals
- 19Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems
- 19Truthful Calibration Measures for Sequential Prediction
- 19Coding Agents for Generalized Task and Motion Planning Problems
- 19TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval
- 19Task-aligned spectral inductive biases in parameterized quantum circuits
- 19Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies
- 19Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
- 19Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation
- 19RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
- 19PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
- 19Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection
- 19Asymmetric Capacity Allocation in Self-Refinement Pipelines
- 19VERA: A Responsible AI Dashboard for Assessing LLM Deployments in Light of the EU AI Act
- 19Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditions
- 19CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
- 19MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
- 19To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
- 19Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination
- 19PoEM: Predicting RL Outcomes from Existing Policies
- 19Split the Labor: Separating Evidence Interpretation from Decision Aggregation
- 19AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
- 19Dynamic Structural Causal Modeling for Sleep
- 19TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
- 19Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn?
- 19Conformal Uncertainty Quantification Guarantees for Neural Operators
- 19Action Learning for Scientific Simulations
- 19Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox
- 19Self-Building Labs
- 19CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
- 19ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference
- 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