{"list":"other","total":56,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127},{"id":"1511.06324","title":"Global Convergence of ADMM in Nonconvex Nonsmooth Optimization","created":"2015-11-18","cited_by_count":98},{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91},{"id":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79},{"id":"2002.11794","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","created":"2020-02-26","cited_by_count":67},{"id":"1410.1390","title":"Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems","created":"2014-10-06","cited_by_count":64},{"id":"1707.09870","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","created":"2017-07-24","cited_by_count":61},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41},{"id":"2411.09009","title":"Cut Your Losses in Large-Vocabulary Language Models","created":"2024-11-13","cited_by_count":40},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31},{"id":"2303.17045","title":"Training Neural Networks is NP-Hard in Fixed Dimension","created":"2023-03-29","cited_by_count":23},{"id":"2403.06408","title":"What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation","created":"2024-03-11","cited_by_count":23},{"id":"2001.02786","title":"Least squares binary quantization of neural networks","created":"2020-01-09","cited_by_count":21},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19},{"id":"2406.07831","title":"ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models","created":"2024-06-12","cited_by_count":19},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11},{"id":"2006.07278","title":"Convergence for nonconvex ADMM, with applications to CT imaging","created":"2020-06-12","cited_by_count":8},{"id":"2502.13179","title":"PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models","created":"2025-02-18","cited_by_count":8},{"id":"2009.03482","title":"Alternating Direction Method of Multipliers for Quantization","created":"2020-09-08","cited_by_count":6},{"id":"2308.04595","title":"Quantization Aware Factorization for Deep Neural Network Compression","created":"2023-08-08","cited_by_count":6},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5},{"id":"2510.01650","title":"The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM","created":"2025-10-02","cited_by_count":5},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4},{"id":"2512.00862","title":"HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs","created":"2025-11-30","cited_by_count":4},{"id":"2205.01951","title":"Proximal ADMM for Nonconvex and Nonsmooth Optimization","created":"2022-05-04","cited_by_count":3},{"id":"2111.14836","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","created":"2021-11-29","cited_by_count":2}],"next_cursor":null}