{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2010.15277","title":"Class-incremental learning: survey and performance evaluation on image classification","created":"2020-10-28","cited_by_count":449},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229},{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2308.04014","title":"Continual Pre-Training of Large Language Models: How to (re)warm your model?","created":"2023-08-08","cited_by_count":137},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69},{"id":"2410.24206","title":"Understanding Optimization in Deep Learning with Central Flows","created":"2024-10-31","cited_by_count":64},{"id":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61},{"id":"2503.19206","title":"Overtrained Language Models Are Harder to Fine-Tune","created":"2025-03-24","cited_by_count":58},{"id":"2408.11053","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","created":"2024-08-20","cited_by_count":45},{"id":"2508.15096","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset","created":"2025-08-20","cited_by_count":38},{"id":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35},{"id":"2009.06125","title":"A Qualitative Study of the Dynamic Behavior for Adaptive Gradient Algorithms","created":"2020-09-14","cited_by_count":33},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21},{"id":"2412.06947","title":"PyraNet: A Multi-Layered Hierarchical Dataset for Verilog","created":"2024-12-09","cited_by_count":19},{"id":"2106.12772","title":"Task-agnostic Continual Learning with Hybrid Probabilistic Models","created":"2021-06-24","cited_by_count":16},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15},{"id":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13},{"id":"2502.07274","title":"Forget Forgetting: Continual Learning in a World of Abundant Memory","created":"2025-02-11","cited_by_count":11},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10},{"id":"2603.16177","title":"The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data","created":"2026-03-17","cited_by_count":9},{"id":"2601.16979","title":"A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs","created":"2026-01-23","cited_by_count":8},{"id":"2505.12745","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","created":"2025-05-19","cited_by_count":7},{"id":"2403.13130","title":"Self-generated Replay Memories for Continual Neural Machine Translation","created":"2024-03-19","cited_by_count":4},{"id":"2603.08647","title":"Grow, Don't Overwrite: Fine-tuning Without Forgetting","created":"2026-03-09","cited_by_count":1}],"next_cursor":null}