{"total":17,"rows":[{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2607.05722","title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","created":"2026-07-07","cited_by_count":24,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2512.23422","title":"Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2604.03799","title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","created":"2026-04-04","cited_by_count":4,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2606.16246","title":"Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2602.11715","title":"DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2606.06888","title":"Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2509.24975","title":"DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.09885","title":"Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2603.00173","title":"Summer-22B: A Systematic Approach to Dataset Engineering and Training at Scale for Video Foundation Model","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.10019","title":"The two clocks and the innovation window: When and how generative models learn rules","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2601.02867","title":"Training Language Models with homotokens Leads to Delayed Overfitting","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.18698","title":"Are Video Generation Models Geographically Fair? An Attraction-Centric Evaluation of Global Visual Knowledge","created":"2026-01-26","cited_by_count":0,"area":null}],"next_cursor":null}