{"list":"other","total":65,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"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":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","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":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"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":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1908.05033","title":"Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks","created":"2019-08-14","cited_by_count":238},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"2004.09576","title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","created":"2020-04-20","cited_by_count":189},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"2008.05000","title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","created":"2020-08-11","cited_by_count":96},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95},{"id":"1903.08066","title":"Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks","created":"2019-03-19","cited_by_count":90},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2310.03270","title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","created":"2023-10-05","cited_by_count":78},{"id":"2409.12517","title":"Scaling FP8 training to trillion-token LLMs","created":"2024-09-19","cited_by_count":65},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43},{"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":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26},{"id":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24},{"id":"2002.06517","title":"BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations","created":"2020-02-16","cited_by_count":23},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22},{"id":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","cited_by_count":12},{"id":"2211.11014","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","created":"2022-11-20","cited_by_count":11},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10},{"id":"2407.09527","title":"BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks","created":"2024-06-24","cited_by_count":8},{"id":"2410.08661","title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs","created":"2024-10-11","cited_by_count":7},{"id":"2502.12665","title":"A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization","created":"2025-02-18","cited_by_count":7},{"id":"2604.04722","title":"Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs","created":"2026-04-06","cited_by_count":7},{"id":"2502.11895","title":"Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?","created":"2025-02-17","cited_by_count":4}],"next_cursor":null}