{"total":41,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144,"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":"2401.06949","title":"ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization","created":"2024-01-13","cited_by_count":61,"area":null},{"id":"2405.07719","title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI","created":"2024-05-13","cited_by_count":61,"area":null},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46,"area":null},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2412.10650","title":"DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification","created":"2024-12-14","cited_by_count":29,"area":null},{"id":"2507.13812","title":"SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing","created":"2025-07-18","cited_by_count":26,"area":null},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2504.09014","title":"MSCCL++: Rethinking GPU Communication Abstractions for AI Inference","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2512.01463","title":"hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware","created":"2025-12-01","cited_by_count":9,"area":null},{"id":"2408.14158","title":"Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2404.18924","title":"Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2504.14519","title":"SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training","created":"2025-04-20","cited_by_count":6,"area":null},{"id":"2511.15076","title":"GPU-Initiated Networking for NCCL","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2607.14952","title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2303.18120","title":"UKP-SQuARE v3: A Platform for Multi-Agent QA Research","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2505.23523","title":"Efficient AllReduce with Stragglers","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.02882","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2507.17445","title":"IndoorBEV: Joint Detection and Footprint Completion of Objects via Mask-based Prediction in Indoor Scenarios for Bird's-Eye View Perception","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2604.01621","title":"DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.27844","title":"ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.18192","title":"View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2609.12923","title":"Dissecting GPU Utilization for LLM Inference on Nvidia Hopper","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2405.02969","title":"Towards a Flexible and High-Fidelity Approach to Distributed DNN Training Emulation","created":"2024-05-05","cited_by_count":0,"area":null},{"id":"2411.15729","title":"OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2501.05563","title":"Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2512.12219","title":"Fine-Grained Zero-Shot Learning with Attribute-Centric Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2604.14540","title":"WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.11542","title":"Characterizing Job Power Elasticity for Power-Flexible AI Training","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.18519","title":"COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}