{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163},{"id":"2504.13914","title":"Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":161},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2402.15627","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","created":"2024-02-23","cited_by_count":112},{"id":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87},{"id":"2507.19427","title":"Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding","created":"2025-07-25","cited_by_count":55},{"id":"2204.12013","title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs","created":"2022-04-26","cited_by_count":49},{"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},{"id":"2506.02634","title":"KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider","created":"2025-06-03","cited_by_count":41},{"id":"2309.08125","title":"Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates","created":"2023-09-15","cited_by_count":40},{"id":"2406.14088","title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation","created":"2024-06-20","cited_by_count":37},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37},{"id":"2504.02263","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism","created":"2025-04-03","cited_by_count":32},{"id":"2505.09999","title":"ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production","created":"2025-05-15","cited_by_count":29},{"id":"2407.20143","title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development","created":"2024-07-29","cited_by_count":24},{"id":"2403.14097","title":"Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances","created":"2024-03-21","cited_by_count":17},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16},{"id":"2405.14009","title":"ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation","created":"2024-05-22","cited_by_count":14},{"id":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","cited_by_count":13},{"id":"2505.05713","title":"Understanding Stragglers in Large Model Training Using What-if Analysis","created":"2025-05-09","cited_by_count":12},{"id":"2411.01791","title":"Minder: Faulty Machine Detection for Large-scale Distributed Model Training","created":"2024-11-04","cited_by_count":11},{"id":"2506.14813","title":"Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks","created":"2025-06-06","cited_by_count":10},{"id":"2510.27656","title":"fabric-lib: RDMA Point-to-Point Communication for LLM Systems","created":"2025-10-31","cited_by_count":8},{"id":"2509.03018","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","created":"2025-09-03","cited_by_count":6},{"id":"2408.08586","title":"Rubick: Exploiting Job Reconfigurability for Deep Learning Cluster Scheduling","created":"2024-08-16","cited_by_count":4},{"id":"2506.15961","title":"TrainVerify: Equivalence-Based Verification for Distributed LLM Training","created":"2025-06-19","cited_by_count":3},{"id":"2509.25279","title":"RL in the Wild: Characterizing RLVR Training in LLM Deployment","created":"2025-09-29","cited_by_count":2}],"next_cursor":null}