{"total":71,"rows":[{"id":"2508.03645","title":"DiWA: Diffusion Policy Adaptation with World Models","created":"2025-08-05","cited_by_count":31,"area":"wm"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2510.15830","title":"SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2506.00288","title":"Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2603.00618","title":"Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models","created":"2026-02-28","cited_by_count":5,"area":null},{"id":"2604.15297","title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2604.08741","title":"LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2511.01282","title":"When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding","created":"2025-11-03","cited_by_count":3,"area":"lr"},{"id":"2603.21017","title":"Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness","created":"2026-03-22","cited_by_count":3,"area":"wm"},{"id":"2503.14545","title":"PANDORA: Diffusion Policy Learning for Dexterous Robotic Piano Playing","created":"2025-03-17","cited_by_count":2,"area":"diffusion"},{"id":"2504.02618","title":"Variational Online Mirror Descent for Robust Learning in Schr\\\"odinger Bridge","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2508.10894","title":"MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2601.20769","title":"Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2601.22132","title":"Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.13284","title":"Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Design","created":"2026-02-27","cited_by_count":2,"area":"diffusion"},{"id":"2505.18107","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2505.22085","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.08915","title":"Two-stage Vision Transformers and Hard Masking offer Robust Object Representations","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.00873","title":"FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2510.23637","title":"Combining Textual and Structural Information for Premise Selection in Lean","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2512.17979","title":"Adaptive Agents in Spatial Double-Auction Markets: Modeling the Emergence of Industrial Symbiosis","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.03237","title":"Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.05756","title":"Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compression","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.18759","title":"Model-Agnostic Meta Learning for Class Imbalance Adaptation","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.07841","title":"\\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.24357","title":"Refined Analysis of Entropy-Regularized Actor-Critic","created":"2026-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2606.23995","title":"EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games","created":"2026-06-22","cited_by_count":1,"area":"deeprl"},{"id":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2608.20913","title":"Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2412.00452","title":"Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2506.11691","title":"DMAF-Net: An Effective Modality Rebalancing Framework for Incomplete Multi-Modal Medical Image Segmentation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2507.01279","title":"Classification based deep learning models for lung cancer and disease using medical images","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.10606","title":"DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2509.25914","title":"ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.08160","title":"LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.11396","title":"SUG-Occ: Explicit Semantics and Uncertainty Guided Sparse Learning for Efficient 3D Occupancy Prediction","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.21690","title":"A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.06700","title":"Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.06838","title":"An Adaptive Differentially Private Federated Learning Framework","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.03903","title":"From Misclassifications to Outliers: Joint Reliability Assessment in Classification","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.13858","title":"Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.16241","title":"Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.12044","title":"VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation","created":"2026-04-13","cited_by_count":0,"area":"distill"},{"id":"2605.08577","title":"Improving Generative Adversarial Networks with Self-Distillation","created":"2026-05-09","cited_by_count":0,"area":"distill"},{"id":"2605.12197","title":"A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17671","title":"PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment","created":"2026-05-17","cited_by_count":0,"area":"distill"},{"id":"2605.28433","title":"Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2605.28531","title":"Stabilizing distribution-free probabilistic forecasts","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.30080","title":"Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31400","title":"FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.30937","title":"No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00078","title":"Exploring Line Bundle Standard Models with Transformers","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.05866","title":"Differentially Private Natural Gradient Descent","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.06887","title":"Converge to Surprise: Evolutionary Self-supervised Image Clustering","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.14150","title":"Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.20061","title":"Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts","created":"2026-08-20","cited_by_count":0,"area":"moe"},{"id":"2609.10433","title":"Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.13734","title":"PolicyMem: Geometric Policy Memory for LLM Governance","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.19076","title":"Double descent is the principle of least action","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.36638","title":"PE-OPSD: Internalizing Prompt Enhancement into Flow-matching Models via On-Policy Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05329","title":"Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05852","title":"RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14748","title":"More Domains, No Gains? FLO: Fast-Slow Reciprocal Learning for Multi-Domain Graph Pre-training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.20598","title":"DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}