{"total":88,"rows":[{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84,"area":"distill"},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"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":"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":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2309.14592","title":"Efficient Post-training Quantization with FP8 Formats","created":"2023-09-26","cited_by_count":29,"area":"diffusion"},{"id":"2410.13229","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","created":"2024-10-17","cited_by_count":28,"area":"ssm"},{"id":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26,"area":"inference"},{"id":"2311.00502","title":"Efficient LLM Inference on CPUs","created":"2023-11-01","cited_by_count":24,"area":"inference"},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2305.12356","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2506.04648","title":"FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion","created":"2025-06-05","cited_by_count":19,"area":"diffusion"},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2404.15778","title":"BASS: Batched Attention-optimized Speculative Sampling","created":"2024-04-24","cited_by_count":11,"area":"inference"},{"id":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"area":"inference"},{"id":"2407.02089","title":"GPTCast: a weather language model for precipitation nowcasting","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2501.02423","title":"Scaling Laws for Floating Point Quantization Training","created":"2025-01-05","cited_by_count":8,"area":null},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2601.19026","title":"Is Finer Better? The Limits of Microscaling Formats in Large Language Models","created":"2026-01-26","cited_by_count":8,"area":null},{"id":"2403.08845","title":"Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs","created":"2024-03-13","cited_by_count":7,"area":"inference"},{"id":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2408.14398","title":"On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2412.16700","title":"TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models","created":"2024-12-21","cited_by_count":6,"area":"diffusion"},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2505.21591","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","created":"2025-05-27","cited_by_count":6,"area":"diffusion"},{"id":"2508.17467","title":"MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models","created":"2025-08-24","cited_by_count":6,"area":"mllm"},{"id":"2509.14008","title":"Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2311.12359","title":"Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2312.05725","title":"FP8-BERT: Post-Training Quantization for Transformer","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2401.14110","title":"Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2407.17353","title":"Scalify: scale propagation for efficient low-precision LLM training","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2311.11172","title":"Low-Precision Floating-Point for Efficient On-Board Deep Neural Network Processing","created":"2023-11-18","cited_by_count":3,"area":null},{"id":"2409.05905","title":"Towards Narrowing the Generalization Gap in Deep Boolean Networks","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2501.11006","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2504.09814","title":"DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2509.14388","title":"eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2510.23264","title":"PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization","created":"2025-10-27","cited_by_count":3,"area":"mechinterp"},{"id":"2605.13907","title":"AIS: Adaptive Importance Sampling for Quantized RL","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2407.18267","title":"MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2503.14932","title":"Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2604.24088","title":"TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2605.27379","title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.29640","title":"VikingMem: A Memory Base Management System for Stateful LLM-based Applications","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.07618","title":"ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2307.03712","title":"INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2407.02610","title":"Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2410.11203","title":"Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2505.14638","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.16335","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.24061","title":"FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2603.10444","title":"The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2607.01831","title":"Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference","created":"2026-07-02","cited_by_count":1,"area":"rag"},{"id":"2607.24062","title":"ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning","created":"2026-07-27","cited_by_count":1,"area":"lr"},{"id":"2304.02481","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2410.03692","title":"Floating-floating point: a highly accurate number representation with flexible Counting ranges","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2410.12187","title":"DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2412.07391","title":"A Data-Free Analytical Quantization Scheme for Deep Learning Models","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2510.16045","title":"AMS-QUANT: Adaptive Mantissa Sharing for Floating-point Quantization","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.07724","title":"The Native Spiking Microarchitecture: From Iontronic Primitives to Bit-Exact FP8 Arithmetic","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.10823","title":"Mugi: Value Level Parallelism For Efficient LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.08081","title":"Investigating Energy Bounds of Analog Compute-in-Memory with Local Normalization","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2605.17745","title":"StatQAT: Statistical Quantizer Optimization for Deep Networks","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.19195","title":"The Thermodynamic Costs of Simple Linear Regression","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.18502","title":"Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2606.27884","title":"SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.28968","title":"Efficient GPU Retrieval for Semantic Search","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.33496","title":"Chameleon: Dynamic Format Adapter for Efficient Diffusion","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.34380","title":"DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory","created":"2026-09-28","cited_by_count":0,"area":"inference"}],"next_cursor":null}