{"list":"other","total":82,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2103.17230","title":"Rainbow Memory: Continual Learning with a Memory of Diverse Samples","created":"2021-03-31","cited_by_count":273},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"2406.11409","title":"CodeGemma: Open Code Models Based on Gemma","created":"2024-06-17","cited_by_count":150},{"id":"1511.06807","title":"Adding Gradient Noise Improves Learning for Very Deep Networks","created":"2015-11-21","cited_by_count":145},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2004.00713","title":"Memory-Efficient Incremental Learning Through Feature Adaptation","created":"2020-04-01","cited_by_count":107},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94},{"id":"2408.06142","title":"Med42-v2: A Suite of Clinical LLMs","created":"2024-08-12","cited_by_count":90},{"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":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47},{"id":"2512.01374","title":"Stabilizing Reinforcement Learning with LLMs: Formulation and Practices","created":"2025-12-01","cited_by_count":41},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37},{"id":"2302.01386","title":"Continual Learning with Scaled Gradient Projection","created":"2023-02-02","cited_by_count":34},{"id":"2601.08521","title":"Your Group-Relative Advantage Is Biased","created":"2026-01-13","cited_by_count":34},{"id":"2305.04769","title":"BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning","created":"2023-05-08","cited_by_count":25},{"id":"2406.14833","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","created":"2024-06-21","cited_by_count":25},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23},{"id":"2510.25628","title":"EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis","created":"2025-10-29","cited_by_count":18},{"id":"2312.00949","title":"Hyperparameter Optimization for Large Language Model Instruction-Tuning","created":"2023-12-01","cited_by_count":17},{"id":"2505.22697","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","created":"2025-05-28","cited_by_count":17},{"id":"2407.09435","title":"MUSCLE: A Model Update Strategy for Compatible LLM Evolution","created":"2024-07-12","cited_by_count":15},{"id":"2501.13669","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","created":"2025-01-23","cited_by_count":13},{"id":"2408.03511","title":"MoExtend: Tuning New Experts for Modality and Task Extension","created":"2024-08-07","cited_by_count":12},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12},{"id":"2408.09053","title":"Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models","created":"2024-08-16","cited_by_count":11},{"id":"2402.12749","title":"Me LLaMA: Foundation Large Language Models for Medical Applications","created":"2024-02-20","cited_by_count":10},{"id":"2512.10150","title":"Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning","created":"2025-12-10","cited_by_count":10},{"id":"2512.04601","title":"Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space","created":"2025-12-04","cited_by_count":8},{"id":"2301.12131","title":"Restricted Orthogonal Gradient Projection for Continual Learning","created":"2023-01-28","cited_by_count":6},{"id":"2410.01610","title":"Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging","created":"2024-10-02","cited_by_count":6},{"id":"2509.22335","title":"Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning","created":"2025-09-26","cited_by_count":6},{"id":"2411.06448","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","created":"2024-11-10","cited_by_count":5},{"id":"2602.00642","title":"LegalOne: A Family of Foundation Models for Reliable Legal Reasoning","created":"2026-01-31","cited_by_count":5},{"id":"2505.05946","title":"Full-Parameter Continual Pretraining of Gemma2: Insights into Fluency and Domain Knowledge","created":"2025-05-09","cited_by_count":4},{"id":"2405.10992","title":"Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System","created":"2024-05-16","cited_by_count":3},{"id":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3},{"id":"2603.02951","title":"CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning","created":"2026-03-03","cited_by_count":3},{"id":"2509.02555","title":"Surrogate Benchmarks for Model Merging Optimization","created":"2025-09-02","cited_by_count":2},{"id":"2502.10966","title":"Neural Networks Remember More: The Power of Parameter Isolation and Combination","created":"2025-02-16","cited_by_count":1},{"id":"2502.18471","title":"FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data","created":"2025-02-04","cited_by_count":1}],"next_cursor":null}