{"total":39,"rows":[{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2510.25108","title":"Shift is Good: Mismatched Data Mixing Improves Test Performance","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2604.27083","title":"Co-Evolving Policy Distillation","created":"2026-04-29","cited_by_count":5,"area":null},{"id":"2605.10770","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2510.00866","title":"Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2601.21414","title":"System 1&2 Synergy via Dynamic Model Interpolation","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2608.07222","title":"Skaling: Chinchilla's Exponents Meet Kaplan's Coupling","created":"2026-08-07","cited_by_count":3,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2603.05280","title":"Layer by layer, module by module: Choose both for optimal OOD probing of ViT","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2607.11052","title":"Domain-Aware Scaling Laws Uncover Data Synergy","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2608.14071","title":"Scaling Domain Data Repetition in LLM Pretraining","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2603.08022","title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.09271","title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2606.08167","title":"Explaining Data Mixing Scaling Laws","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.28308","title":"Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2602.08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","created":"2026-02-09","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":"2605.06859","title":"Knowledge Transfer Scaling Laws for 3D Medical Imaging","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08541","title":"Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.09154","title":"Predicting Large Model Test Losses with a Noisy Quadratic System","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.13225","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18364","title":"Proximal basin hopping: global optimization with guarantees","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.31164","title":"D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.31175","title":"Towards Efficient LLMs Annealing with Principled Sample Selection","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.27928","title":"Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36263","title":"Paired Multimodal Scaling Laws","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40295","title":"How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05126","title":"Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19443","title":"More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}