{"list":"other","total":58,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2302.06590","title":"The Impact of AI on Developer Productivity: Evidence from GitHub Copilot","created":"2023-02-13","cited_by_count":274},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252},{"id":"2006.06762","title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning","created":"2020-06-11","cited_by_count":201},{"id":"2308.00708","title":"VeriGen: A Large Language Model for Verilog Code Generation","created":"2023-07-28","cited_by_count":200},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174},{"id":"1805.08166","title":"Learning to Optimize Tensor Programs","created":"2018-05-21","cited_by_count":140},{"id":"2305.13243","title":"Chip-Chat: Challenges and Opportunities in Conversational Hardware Design","created":"2023-05-22","cited_by_count":140},{"id":"2308.10204","title":"ChatEDA: A Large Language Model Powered Autonomous Agent for EDA","created":"2023-08-20","cited_by_count":122},{"id":"2305.14019","title":"ChipGPT: How far are we from natural language hardware design","created":"2023-05-23","cited_by_count":105},{"id":"2311.16543","title":"RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models","created":"2023-11-28","cited_by_count":100},{"id":"2402.03375","title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","created":"2024-02-03","cited_by_count":100},{"id":"2306.06283","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","created":"2023-06-09","cited_by_count":86},{"id":"2004.10746","title":"Chip Placement with Deep Reinforcement Learning","created":"2020-04-22","cited_by_count":83},{"id":"2307.08849","title":"Autoregressive Diffusion Model for Graph Generation","created":"2023-07-17","cited_by_count":83},{"id":"2311.04887","title":"AutoChip: Automating HDL Generation Using LLM Feedback","created":"2023-11-08","cited_by_count":83},{"id":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80},{"id":"2312.08617","title":"RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution","created":"2023-12-14","cited_by_count":71},{"id":"2009.01026","title":"DAVE: Deriving Automatically Verilog from English","created":"2020-08-27","cited_by_count":48},{"id":"1911.04021","title":"DRiLLS: Deep Reinforcement Learning for Logic Synthesis","created":"2019-11-11","cited_by_count":47},{"id":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35},{"id":"2205.07000","title":"PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning","created":"2022-05-14","cited_by_count":18},{"id":"1907.12952","title":"Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Design","created":"2019-07-29","cited_by_count":17},{"id":"2108.07639","title":"Learning C to x86 Translation: An Experiment in Neural Compilation","created":"2021-08-17","cited_by_count":12},{"id":"1905.03852","title":"Machine Learning Based Routing Congestion Prediction in FPGA High-Level Synthesis","created":"2019-05-06","cited_by_count":8},{"id":"2012.02530","title":"Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization","created":"2020-12-04","cited_by_count":8},{"id":"2006.13607","title":"Circuit Routing Using Monte Carlo Tree Search and Deep Neural Networks","created":"2020-06-24","cited_by_count":6},{"id":"2002.00190","title":"Improving Performance Estimation for FPGA-based Accelerators for Convolutional Neural Networks","created":"2020-02-01","cited_by_count":5},{"id":"2505.06302","title":"QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives","created":"2025-05-08","cited_by_count":5},{"id":"2004.04852","title":"Predictable Accelerator Design with Time-Sensitive Affine Types","created":"2020-04-09","cited_by_count":4},{"id":"2505.02146","title":"QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach","created":"2025-05-04","cited_by_count":4},{"id":"2007.01465","title":"Deep-PowerX: A Deep Learning-Based Framework for Low-Power Approximate Logic Synthesis","created":"2020-07-03","cited_by_count":3},{"id":"2012.15342","title":"ConfigFix: Interactive Configuration Conflict Resolution for the Linux Kernel","created":"2020-12-30","cited_by_count":3},{"id":"2506.02929","title":"Large Processor Chip Model","created":"2025-06-03","cited_by_count":2},{"id":"2505.03195","title":"QiMeng-CPU-v2: Automated Superscalar Processor Design by Learning Data Dependencies","created":"2025-05-06","cited_by_count":1}],"next_cursor":null}