- 1 MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries ↗
- 2 Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models ↗
- 3 How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability ↗
- 4 Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features ↗
- 5 Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs ↗
- 6 Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo ↗
- 7 CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure ↗
- 8 Multi-Rollout On-Policy Distillation via Peer Successes and Failures ↗
- 9 Plan Before You Trade: Inference-Time Optimization for RL Trading Agents ↗
- 10 Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise ↗
- 11 Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic ↗
- 12 Learning to Decide with AI Assistance under Human-Alignment ↗
- 13 OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting ↗
- 14 Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity ↗
- 15 Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention ↗
- 16 scShapeBench: Discovering geometry from high dimensional scRNAseq data ↗
- 17 ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin ↗
- 18 ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization ↗
- 19 Efficient distributional regression trees learning algorithms for calibrated non-parametric probabilistic forecasts ↗
- 20 Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction ↗
- 21 Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation ↗
- 22 A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions ↗
- 23 TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning ↗
- 24 IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback ↗
- 25 A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots ↗
- 26 Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification ↗
- 27 Do Activation Verbalization Methods Convey Privileged Information? ↗
- 28 UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning ↗
- 29 SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling ↗
- 30 Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions ↗
- 31 When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation ↗
- 32 Early Data Exposure Improves Robustness to Subsequent Fine-Tuning ↗
- 33 Continual Learning with Multilingual Foundation Model ↗
- 34 A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data ↗
- 35 Characterizing Universal Object Representations Across Vision Models ↗
- 36 Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations ↗
- 37 Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces ↗
- 38 Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs ↗
- 39 RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records ↗
- 40 Scaling Laws for Mixture Pretraining Under Data Constraints ↗
- 41 Latent-Augmented Discrete Diffusion Models ↗
- 42 Before the Last Token: Diagnosing Final-Token Safety Probe Failures ↗
- 43 High-Order Epistasis Detection Using Factorization Machine with Quadratic Optimization Annealing and MDR-Based Evaluation ↗
- 44 From Generalist to Specialist Representation ↗
- 45 Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference ↗
- 46 ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis ↗
- 47 Data Agent: Learning to Select Data via End-to-End Dynamic Optimization ↗
- 48 Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation ↗
- 49 (Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models ↗
- 50 Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning ↗
- 51 DataMaster: Data-Centric Autonomous AI Research ↗
- 52 Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling ↗
- 53 A3 : an Analytical Low-Rank Approximation Framework for Attention ↗
- 54 Predicting Channel Closures in the Lightning Network with Machine Learning ↗
- 55 Differentially Private Nonparametric Confidence Intervals Under Minimal Distributional Assumptions ↗
- 56 Multi-Quantile Regression for Extreme Precipitation Downscaling ↗
- 57 DiscoverLLM: From Executing Intents to Discovering Them ↗
- 58 State-Space NTK Collapse Near Bifurcations ↗
- 59 TStore: Rethinking AI Model Hub with Tensor-Centric Compression ↗
- 60 Inference-Time Machine Unlearning via Gated Activation Redirection ↗
- 61 LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges ↗
- 62 WriteSAE: Sparse Autoencoders for Recurrent State ↗
- 63 Proximal-Based Generative Modeling for Bayesian Inverse Problems ↗
- 64 Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization ↗
- 65 Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling ↗
- 66 ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery ↗
- 67 On the Limits of Latent Reuse in Diffusion Models ↗
- 68 Identifying the nonlinear string dynamics with port-Hamiltonian neural networks ↗
- 69 Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models ↗
- 70 From Heuristics to Analytics: Forecasting Effort and Progress in Online Learning ↗
- 71 Humanwashing -- It Should Leave You Feeling Dirty ↗
- 72 SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions ↗
- 73 R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow ↗
- 74 Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer ↗
- 75 Causal Fine-Tuning under Latent Confounded Shift ↗
- 76 Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles ↗
- 77 A Faster Generalized Two-Stage Approximate Top-K ↗
- 78 Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels ↗
- 79 Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies ↗
- 80 Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse ↗
- 81 Beyond Softmax: A Natural Parameterization for Categorical Random Variables ↗
- 82 Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces ↗
- 83 Higher-order Linear Attention ↗
- 84 AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers ↗
- 85 QSMOTE-PGM/kPGM: QSMOTE Based PGM and kPGM for Imbalanced Dataset Classification ↗
- 86 Training Large Language Models to Predict Clinical Events ↗
- 87 Perceptrons and localization of attention's mean-field landscape ↗
- 88 Hessian Matching for Machine-Learned Coarse-Grained Molecular Dynamics ↗
- 89 Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions ↗
- 90 Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion ↗
- 91 Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration ↗
- 92 Quantifying Potential Observation Missingness in Inverse Reinforcement Learning ↗
- 93 Physics-informed neural particle flow for the Bayesian update step ↗
- 94 Discrete Stochastic Localization for Non-autoregressive Generation ↗
- 95 Delightful Distributed Policy Gradient ↗
- 96 Bayesian Model Merging ↗
- 97 Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning ↗
- 98 Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response ↗
- 99 Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback ↗
- 100 SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning ↗