{"total":102,"rows":[{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523,"area":null},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2406.15479","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","created":"2024-06-17","cited_by_count":116,"area":null},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2305.14235","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","created":"2023-05-23","cited_by_count":65,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2309.04255","title":"LLMCad: Fast and Scalable On-device Large Language Model Inference","created":"2023-09-08","cited_by_count":45,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2401.05605","title":"Scaling Laws for Forgetting When Fine-Tuning Large Language Models","created":"2024-01-11","cited_by_count":38,"area":null},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33,"area":null},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2403.06563","title":"Unraveling the Mystery of Scaling Laws: Part I","created":"2024-03-11","cited_by_count":24,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2406.16690","title":"Scaling Laws for Linear Complexity Language Models","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2210.13447","title":"Precision Machine Learning","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2502.19227","title":"Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems","created":"2025-02-26","cited_by_count":14,"area":null},{"id":"2504.02398","title":"Scaling Analysis of Interleaved Speech-Text Language Models","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"area":null},{"id":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2406.09366","title":"Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2305.14681","title":"Emergent inabilities? Inverse scaling over the course of pretraining","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2309.10706","title":"OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch","created":"2023-09-19","cited_by_count":7,"area":null},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2412.07585","title":"Scaling Sequential Recommendation Models with Transformers","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2406.04914","title":"Submodular Framework for Structured-Sparse Optimal Transport","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2407.21058","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2606.25008","title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2210.14593","title":"Scaling Laws Beyond Backpropagation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2402.01093","title":"Need a Small Specialized Language Model? Plan Early!","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2406.11721","title":"The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2511.04234","title":"Reusing Pre-Training Data at Test Time is a Compute Multiplier","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2603.22198","title":"Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2212.10066","title":"RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2501.02156","title":"The Race to Efficiency: A New Perspective on AI Scaling Laws","created":"2025-01-04","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2410.10672","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2410.18111","title":"Data Efficiency for Large Recommendation Models","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2503.23869","title":"Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","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":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.02227","title":"Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2503.04107","title":"Fractional Correspondence Framework in Detection Transformer","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2506.12932","title":"Complexity Scaling Laws for Neural Models using Combinatorial Optimization","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2207.09588","title":"New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2302.00003","title":"The Power of External Memory in Increasing Predictive Model Capacity","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2412.16423","title":"Technical Report: Small Language Model for Japanese Clinical and Medicine","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2501.08506","title":"Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2506.23170","title":"Compositions of Variant Experts for Integrating Short-Term and Long-Term Preferences","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.20991","title":"ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.09380","title":"Utilizing dynamic sparsity on pretrained DETR","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.13062","title":"Self-Adaptive Graph Mixture of Models","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2602.15253","title":"Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.21064","title":"Motivation is Something You Need","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.07365","title":"Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.28823","title":"Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2604.18866","title":"HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.05330","title":"Graph Normalization: Fast Binarizing Dynamics for Differentiable MWIS","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.01806","title":"ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2609.04238","title":"Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.05016","title":"Amortizing Scaling Law Construction Costs","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":"100"}