{"total":1572,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396,"area":null},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567,"area":null},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564,"area":null},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559,"area":null},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237,"area":null},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173,"area":null},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150,"area":null},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148,"area":null},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137,"area":null},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134,"area":null},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2206.05941","title":"Towards Universal Sequence Representation Learning for Recommender Systems","created":"2022-06-13","cited_by_count":121,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2105.04663","title":"GSPMD: General and Scalable Parallelization for ML Computation Graphs","created":"2021-05-10","cited_by_count":111,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2412.10859","title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting","created":"2024-12-14","cited_by_count":107,"area":null},{"id":"2506.23971","title":"UMA: A Family of Universal Models for Atoms","created":"2025-06-30","cited_by_count":105,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2103.00823","title":"M6: A Chinese Multimodal Pretrainer","created":"2021-03-01","cited_by_count":91,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"area":null},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84,"area":null},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82,"area":null},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2309.12659","title":"OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling","created":"2023-09-22","cited_by_count":74,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"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":"2406.08660","title":"Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification","created":"2024-06-12","cited_by_count":70,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2401.17868","title":"Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model","created":"2024-01-31","cited_by_count":69,"area":null},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","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":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63,"area":null},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62,"area":null},{"id":"2406.13415","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","created":"2024-06-19","cited_by_count":61,"area":null},{"id":"2501.10326","title":"Large language models for automated scholarly paper review: A survey","created":"2025-01-17","cited_by_count":61,"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":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57,"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":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2204.00102","title":"Dynamic Multimodal Fusion","created":"2022-03-31","cited_by_count":55,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null}],"next_cursor":"100"}