{"list":"other","total":147,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"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":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272},{"id":"1905.12322","title":"A Study of BFLOAT16 for Deep Learning Training","created":"2019-05-29","cited_by_count":232},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127},{"id":"1603.01025","title":"Convolutional Neural Networks using Logarithmic Data Representation","created":"2016-03-03","cited_by_count":99},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"2110.14883","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","created":"2021-10-28","cited_by_count":96},{"id":"2405.21015","title":"The rising costs of training frontier AI models","created":"2024-05-31","cited_by_count":95},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2310.18313","title":"FP8-LM: Training FP8 Large Language Models","created":"2023-10-27","cited_by_count":77},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75},{"id":"2409.12517","title":"Scaling FP8 training to trillion-token LLMs","created":"2024-09-19","cited_by_count":65},{"id":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57},{"id":"1511.04561","title":"8-Bit Approximations for Parallelism in Deep Learning","created":"2015-11-14","cited_by_count":56},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54},{"id":"1804.07802","title":"Value-aware Quantization for Training and Inference of Neural Networks","created":"2018-04-20","cited_by_count":52},{"id":"2306.10209","title":"ZeRO++: Extremely Efficient Collective Communication for Giant Model Training","created":"2023-06-16","cited_by_count":52},{"id":"2010.14298","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","created":"2020-10-27","cited_by_count":51},{"id":"1802.00930","title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","created":"2018-02-03","cited_by_count":45},{"id":"2010.12460","title":"Adaptive Gradient Quantization for Data-Parallel SGD","created":"2020-10-23","cited_by_count":45},{"id":"1711.02213","title":"Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks","created":"2017-11-06","cited_by_count":44},{"id":"1904.11943","title":"SWALP : Stochastic Weight Averaging in Low-Precision Training","created":"2019-04-26","cited_by_count":42},{"id":"1804.01526","title":"Training DNNs with Hybrid Block Floating Point","created":"2018-04-04","cited_by_count":40},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38},{"id":"2501.03035","title":"Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning","created":"2025-01-06","cited_by_count":37},{"id":"2502.20586","title":"Training LLMs with MXFP4","created":"2025-02-27","cited_by_count":37},{"id":"1909.02384","title":"Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers","created":"2019-09-05","cited_by_count":33},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33},{"id":"2206.11357","title":"GACT: Activation Compressed Training for Generic Network Architectures","created":"2022-06-22","cited_by_count":31},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28},{"id":"2004.14180","title":"Quantized Adam with Error Feedback","created":"2020-04-29","cited_by_count":27},{"id":"2407.20018","title":"Efficient Training of Large Language Models on Distributed Infrastructures: A Survey","created":"2024-07-29","cited_by_count":27},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24},{"id":"1905.12334","title":"Mixed Precision Training With 8-bit Floating Point","created":"2019-05-29","cited_by_count":23},{"id":"2001.05674","title":"Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks","created":"2020-01-16","cited_by_count":23},{"id":"2012.13113","title":"FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training","created":"2020-12-24","cited_by_count":23},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21},{"id":"1803.03383","title":"High-Accuracy Low-Precision Training","created":"2018-03-09","cited_by_count":20},{"id":"2009.13108","title":"NITI: Training Integer Neural Networks Using Integer-only Arithmetic","created":"2020-09-28","cited_by_count":20},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20},{"id":"1805.10111","title":"Double Quantization for Communication-Efficient Distributed Optimization","created":"2018-05-25","cited_by_count":19},{"id":"1901.07988","title":"Backprop with Approximate Activations for Memory-efficient Network Training","created":"2019-01-23","cited_by_count":19}],"next_cursor":"100"}