{"total":385,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740,"area":null},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613,"area":null},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339,"area":null},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2306.12873","title":"FuXi: A cascade machine learning forecasting system for 15-day global weather forecast","created":"2023-06-22","cited_by_count":241,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182,"area":null},{"id":"2308.02463","title":"Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data","created":"2023-08-04","cited_by_count":179,"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":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"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":"2410.10989","title":"Liger Kernel: Efficient Triton Kernels for LLM Training","created":"2024-10-14","cited_by_count":130,"area":null},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2402.15627","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","created":"2024-02-23","cited_by_count":112,"area":null},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2410.06511","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","created":"2024-10-09","cited_by_count":85,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75,"area":null},{"id":"2403.02545","title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","created":"2024-03-04","cited_by_count":74,"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":"2308.04948","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","created":"2023-08-09","cited_by_count":69,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2507.12144","title":"FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale","created":"2025-07-16","cited_by_count":62,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2406.06858","title":"FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion","created":"2024-06-11","cited_by_count":57,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","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":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45,"area":null},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2309.08125","title":"Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2407.09424","title":"TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models","created":"2024-07-12","cited_by_count":40,"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":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"area":null},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2510.14648","title":"In-Context Learning with Unpaired Clips for Instruction-based Video Editing","created":"2025-10-16","cited_by_count":35,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2307.14995","title":"TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer","created":"2023-07-27","cited_by_count":34,"area":null},{"id":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2310.03294","title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27,"area":null},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","cited_by_count":27,"area":null},{"id":"2507.09792","title":"CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design","created":"2025-07-13","cited_by_count":25,"area":null},{"id":"2407.20143","title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2502.07272","title":"GENERator: A Long-Context Generative Genomic Foundation Model","created":"2025-02-11","cited_by_count":22,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2509.25849","title":"Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21,"area":null},{"id":"2502.14844","title":"Dynamic Concepts Personalization from Single Videos","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2510.19944","title":"Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2412.01523","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","created":"2024-12-02","cited_by_count":19,"area":null},{"id":"2401.16448","title":"LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2310.03150","title":"Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2404.14712","title":"ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability","created":"2024-04-23","cited_by_count":17,"area":null},{"id":"2503.17924","title":"WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training","created":"2025-03-23","cited_by_count":17,"area":null},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17,"area":null},{"id":"2405.16684","title":"gzip Predicts Data-dependent Scaling Laws","created":"2024-05-26","cited_by_count":16,"area":null},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2512.23075","title":"Trust Region Masking for Long-Horizon LLM Reinforcement Learning","created":"2025-12-28","cited_by_count":16,"area":null},{"id":"2501.02625","title":"HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs","created":"2025-01-05","cited_by_count":15,"area":null},{"id":"2310.02784","title":"MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2311.14030","title":"PrivateLoRA For Efficient Privacy Preserving LLM","created":"2023-11-23","cited_by_count":14,"area":null},{"id":"2405.14009","title":"ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation","created":"2024-05-22","cited_by_count":14,"area":null},{"id":"2411.05239","title":"ZipNN: Lossless Compression for AI Models","created":"2024-11-07","cited_by_count":14,"area":null},{"id":"2412.14140","title":"GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2512.16928","title":"Dion2: A Simple Method to Shrink Matrix in Muon","created":"2025-12-01","cited_by_count":13,"area":null},{"id":"2311.10418","title":"DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines","created":"2023-11-17","cited_by_count":12,"area":null},{"id":"2312.02515","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2312.12705","title":"Optimizing Distributed Training on Frontier for Large Language Models","created":"2023-12-20","cited_by_count":12,"area":null},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2503.01868","title":"Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale","created":"2025-02-25","cited_by_count":12,"area":null}],"next_cursor":"100"}