{"total":21,"rows":[{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2412.13547","title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2509.24935","title":"Scalable GANs with Transformers","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2506.15881","title":"T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2509.20721","title":"Scaling Laws are Redundancy Laws","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2605.26248","title":"Unified Neural Scaling Laws","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.20536","title":"The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2607.29679","title":"Scaling Properties of Text Conditioning in Visual Generation","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2507.08920","title":"AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2606.06477","title":"Complexity-Balanced Diffusion Splitting","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2503.12964","title":"Training Video Foundation Models with NVIDIA NeMo","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2603.22339","title":"Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.21692","title":"Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2609.36599","title":"Scaling Video Generation for Reasoning: At What Cost?","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}