{"total":104,"rows":[{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"area":null},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"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":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"id":"2406.14833","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","created":"2024-06-21","cited_by_count":25,"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":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2410.18565","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2412.04614","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2508.01908","title":"Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models","created":"2025-08-03","cited_by_count":14,"area":null},{"id":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13,"area":null},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2405.20271","title":"ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2404.17733","title":"Building a Large Japanese Web Corpus for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2410.20098","title":"Self-Normalized Resets for Plasticity in Continual Learning","created":"2024-10-26","cited_by_count":11,"area":null},{"id":"2408.08295","title":"SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2412.02205","title":"DataLab: A Unified Platform for LLM-Powered Business Intelligence","created":"2024-12-03","cited_by_count":8,"area":null},{"id":"2501.07482","title":"TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time","created":"2025-01-13","cited_by_count":8,"area":null},{"id":"2506.04344","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","created":"2025-06-04","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":"2404.18311","title":"Towards Incremental Learning in Large Language Models: A Critical Review","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2406.16694","title":"Task Oriented In-Domain Data Augmentation","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.16724","title":"Structure-aware Domain Knowledge Injection for Large Language Models","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2504.20609","title":"WenyanGPT: A Large Language Model for Classical Chinese Tasks","created":"2025-04-29","cited_by_count":6,"area":null},{"id":"2505.02550","title":"Bielik v3 Small: Technical Report","created":"2025-05-05","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":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2505.05946","title":"Full-Parameter Continual Pretraining of Gemma2: Insights into Fluency and Domain Knowledge","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2505.12512","title":"Scalable Strategies for Continual Learning with Replay","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"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":"2412.18966","title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2508.15213","title":"Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2509.07177","title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2510.00206","title":"LoRAFusion: Efficient LoRA Fine-Tuning for LLMs","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2408.06423","title":"Evaluating LLMs on Entity Disambiguation in Tables","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2408.15793","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2501.10476","title":"Revisiting Rogers' Paradox in the Context of Human-AI Interaction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","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":"2508.06178","title":"Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime","created":"2025-08-08","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":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","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":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","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":"2511.03942","title":"MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.03843","title":"Re-Evaluating Continual Learning with Few-Shot Adaptation","created":"2026-06-02","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":"2608.05088","title":"MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.10850","title":"Diffract: Spectral View of LLM Domain Adaptation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.17530","title":"When to Review: Spaced Repetition for Continual Pre-Training of Language Models","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.06986","title":"Continual Learning Mechanisms Compose for Long-Horizon Memorization","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2504.08626","title":"Task-conditioned Ensemble of Expert Models for Continuous Learning","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2510.23198","title":"PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2512.06048","title":"The Road of Adaptive AI for Precision in Cybersecurity","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2603.19268","title":"Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimization","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.20390","title":"STELLAR: Scaling 3D Perception Large Models for Autonomous Driving","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.30080","title":"Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model","created":"2026-05-28","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":"2607.14571","title":"What Does Model Growth Really Add? Functional Capacity Beyond Parameter Count","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.06216","title":"Continual Learning in Transition","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.18803","title":"Forgetting, plasticity, and co-observation: a third facet of continual learning","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.25826","title":"Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.18560","title":"The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23916","title":"Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.32499","title":"Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models","created":"2026-09-26","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}],"next_cursor":"100"}