{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"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":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"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":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"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":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367},{"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":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"1901.03429","title":"On the Turing Completeness of Modern Neural Network Architectures","created":"2019-01-10","cited_by_count":129},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2310.01082","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","created":"2023-10-02","cited_by_count":98},{"id":"2204.06618","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","created":"2022-04-13","cited_by_count":93},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2310.18313","title":"FP8-LM: Training FP8 Large Language Models","created":"2023-10-27","cited_by_count":77},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"2405.18512","title":"Understanding Transformer Reasoning Capabilities via Graph Algorithms","created":"2024-05-28","cited_by_count":67},{"id":"2409.04431","title":"Theory, Analysis, and Best Practices for Sigmoid Self-Attention","created":"2024-09-06","cited_by_count":64},{"id":"2402.08164","title":"On Limitations of the Transformer Architecture","created":"2024-02-13","cited_by_count":63},{"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},{"id":"1906.00532","title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","created":"2019-06-03","cited_by_count":59},{"id":"2010.14298","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","created":"2020-10-27","cited_by_count":51},{"id":"2412.02975","title":"Theoretical limitations of multi-layer Transformer","created":"2024-12-04","cited_by_count":45},{"id":"1906.08042","title":"Low-resource Deep Entity Resolution with Transfer and Active Learning","created":"2019-06-17","cited_by_count":37},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32},{"id":"2408.14332","title":"One-layer transformers fail to solve the induction heads task","created":"2024-08-26","cited_by_count":32},{"id":"2406.09347","title":"Separations in the Representational Capabilities of Transformers and Recurrent Architectures","created":"2024-06-13","cited_by_count":29},{"id":"2308.03212","title":"Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits","created":"2023-08-06","cited_by_count":26},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25},{"id":"2409.13629","title":"Transformers in Uniform TC$^0$","created":"2024-09-20","cited_by_count":25},{"id":"2407.15160","title":"When Can Transformers Count to n?","created":"2024-07-21","cited_by_count":24},{"id":"1805.12096","title":"Marian: Cost-effective High-Quality Neural Machine Translation in C++","created":"2018-05-30","cited_by_count":22},{"id":"2505.18948","title":"Exact Expressive Power of Transformers with Padding","created":"2025-05-25","cited_by_count":19},{"id":"2402.04902","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","created":"2024-02-07","cited_by_count":15},{"id":"2501.19215","title":"Strassen Attention, Split VC Dimension and Compositionality in Transformers","created":"2025-01-31","cited_by_count":12},{"id":"2404.03380","title":"On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers","created":"2024-04-04","cited_by_count":8},{"id":"2506.06179","title":"A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization","created":"2025-06-06","cited_by_count":5},{"id":"2312.05725","title":"FP8-BERT: Post-Training Quantization for Transformer","created":"2023-12-10","cited_by_count":4},{"id":"2503.22076","title":"Concise One-Layer Transformers Can Do Function Evaluation (Sometimes)","created":"2025-03-28","cited_by_count":3},{"id":"1907.01600","title":"Approximate Similarity Search Under Edit Distance Using Locality-Sensitive Hashing","created":"2019-07-02","cited_by_count":1}],"next_cursor":null}