{"total":22,"rows":[{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2506.01732","title":"Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training","created":"2025-06-02","cited_by_count":20,"area":null},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2504.15431","title":"Trillion 7B Technical Report","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2506.18777","title":"Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2607.17624","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2502.05765","title":"Privacy-Preserving Dataset Combination","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2509.06052","title":"Empirical Study of Code Large Language Models for Binary Security Patch Detection","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2410.15173","title":"Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation","created":"2024-10-19","cited_by_count":0,"area":null},{"id":"2606.24408","title":"Natural Identifiers for Privacy and Data Audits in Large Language Models","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.24585","title":"From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.10690","title":"Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.18083","title":"Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2609.33845","title":"How code helps different tasks? A decompositional lens on LLM post-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39827","title":"Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}