{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"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":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"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":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"1804.05685","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","created":"2018-04-16","cited_by_count":478},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232},{"id":"2405.04532","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","created":"2024-05-07","cited_by_count":208},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2308.00708","title":"VeriGen: A Large Language Model for Verilog Code Generation","created":"2023-07-28","cited_by_count":200},{"id":"2308.16369","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","created":"2023-08-31","cited_by_count":193},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189},{"id":"2005.03842","title":"GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference","created":"2020-05-08","cited_by_count":106},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82},{"id":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51},{"id":"2502.02723","title":"Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives","created":"2025-02-04","cited_by_count":48},{"id":"2106.10860","title":"Multiplying Matrices Without Multiplying","created":"2021-06-21","cited_by_count":30},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28},{"id":"2401.14732","title":"Residual Quantization with Implicit Neural Codebooks","created":"2024-01-26","cited_by_count":25},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16},{"id":"2502.15816","title":"GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices","created":"2025-02-19","cited_by_count":14},{"id":"2505.06901","title":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression","created":"2025-05-11","cited_by_count":14},{"id":"2509.12019","title":"AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models","created":"2025-09-15","cited_by_count":14},{"id":"2503.02236","title":"VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference","created":"2025-03-04","cited_by_count":13},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9},{"id":"2504.16339","title":"Transitive Array: An Efficient GEMM Accelerator with Result Reuse","created":"2025-04-23","cited_by_count":7},{"id":"2503.03379","title":"Prosperity: Accelerating Spiking Neural Networks via Product Sparsity","created":"2025-03-05","cited_by_count":6},{"id":"2505.10909","title":"Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks","created":"2025-05-16","cited_by_count":5},{"id":"2510.12721","title":"CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression","created":"2025-10-14","cited_by_count":3},{"id":"2512.14661","title":"Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models","created":"2025-12-16","cited_by_count":3},{"id":"2512.17970","title":"CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs","created":"2025-12-19","cited_by_count":3},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","cited_by_count":2}],"next_cursor":null}