{"total":53,"rows":[{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2509.14128","title":"Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST","created":"2025-09-17","cited_by_count":60,"area":null},{"id":"2504.21039","title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","created":"2025-04-28","cited_by_count":31,"area":null},{"id":"2408.11029","title":"Scaling Law with Learning Rate Annealing","created":"2024-08-20","cited_by_count":29,"area":null},{"id":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2407.18743","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models","created":"2024-07-26","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2508.21741","title":"Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance","created":"2025-08-29","cited_by_count":13,"area":null},{"id":"2506.10766","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2501.09706","title":"Domain Adaptation of Foundation LLMs for e-Commerce","created":"2025-01-16","cited_by_count":9,"area":null},{"id":"2408.02600","title":"BioMamba: Domain-Adaptive Biomedical Language Models","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2505.14045","title":"From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2411.04257","title":"LSHBloom: Memory-efficient, Extreme-scale Document Deduplication","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.07796","title":"Learning Dynamics in Continual Pre-Training for Large Language Models","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2502.21147","title":"Same accuracy, twice as fast: continuous training surpasses retraining from scratch","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2508.01326","title":"Large-Scale Diverse Synthesis for Mid-Training","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2509.06990","title":"DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2607.11889","title":"Scaling Point-in-Time Language Models: Enabling Economic Evaluation of Embeddings","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2410.01098","title":"Exploring Gen-AI applications in building research and industry: A review","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2412.12674","title":"Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2504.03931","title":"NAACL2025 Tutorial: Adaptation of Large Language Models","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2504.06219","title":"Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.17818","title":"CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning","created":"2025-06-21","cited_by_count":2,"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":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2604.14010","title":"Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2504.09687","title":"Domain-Adaptive Continued Pre-Training of Small Language Models","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2505.22018","title":"Improving Continual Pre-training Through Seamless Data Packing","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.07129","title":"Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2510.26829","title":"Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.04969","title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2601.09716","title":"Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2604.09674","title":"How LLMs Might Think","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.10391","title":"Phoenix-VL 1.5 Medium Technical Report","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.10808","title":"Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.05610","title":"Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.10959","title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04180","title":"Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.35392","title":"The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40089","title":"Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02144","title":"Faynt: Scaling and Optimizing Policies for Competitive Melee","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17018","title":"LLM Evaluation is a Forecasting Problem","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}