{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"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":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2406.07524","title":"Simple and Effective Masked Diffusion Language Models","created":"2024-06-11","cited_by_count":848},{"id":"2310.16834","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","created":"2023-10-25","cited_by_count":745},{"id":"2406.04329","title":"Simplified and Generalized Masked Diffusion for Discrete Data","created":"2024-06-06","cited_by_count":626},{"id":"2508.15487","title":"Dream 7B: Diffusion Large Language Models","created":"2025-08-21","cited_by_count":544},{"id":"2505.22618","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","created":"2025-05-28","cited_by_count":420},{"id":"2503.09573","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","created":"2025-03-12","cited_by_count":409},{"id":"2406.03736","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","created":"2024-06-06","cited_by_count":381},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2505.19223","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","created":"2025-05-25","cited_by_count":285},{"id":"2410.17891","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","created":"2024-10-23","cited_by_count":274},{"id":"2502.06768","title":"Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions","created":"2025-02-10","cited_by_count":214},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187},{"id":"2508.02193","title":"Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference","created":"2025-08-04","cited_by_count":178},{"id":"2512.15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","created":"2025-12-10","cited_by_count":166},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2211.00802","title":"Concrete Score Matching: Generalized Score Matching for Discrete Data","created":"2022-11-02","cited_by_count":148},{"id":"2509.26328","title":"Fast-dLLM v2: Efficient Block-Diffusion LLM","created":"2025-09-30","cited_by_count":139},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130},{"id":"2510.06303","title":"SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation","created":"2025-10-07","cited_by_count":129},{"id":"2509.01142","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","created":"2025-09-01","cited_by_count":81},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80},{"id":"2509.24389","title":"LLaDA-MoE: A Sparse MoE Diffusion Language Model","created":"2025-09-29","cited_by_count":57},{"id":"1403.3610","title":"Making Risk Minimization Tolerant to Label Noise","created":"2014-03-14","cited_by_count":54},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48},{"id":"2511.03276","title":"Diffusion Language Models are Super Data Learners","created":"2025-11-05","cited_by_count":48},{"id":"2510.04767","title":"ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs","created":"2025-10-06","cited_by_count":43},{"id":"2512.22737","title":"WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference","created":"2025-12-28","cited_by_count":41},{"id":"2510.08666","title":"dInfer: An Efficient Inference Framework for Diffusion Language Models","created":"2025-10-09","cited_by_count":37},{"id":"2511.08923","title":"TiDAR: Think in Diffusion, Talk in Autoregression","created":"2025-11-12","cited_by_count":37},{"id":"2512.10858","title":"Scaling Behavior of Discrete Diffusion Language Models","created":"2025-12-11","cited_by_count":35},{"id":"2510.03280","title":"Training Optimal Large Diffusion Language Models","created":"2025-09-28","cited_by_count":25},{"id":"2512.06776","title":"From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs","created":"2025-12-07","cited_by_count":24},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19},{"id":"2509.24007","title":"Sequential Diffusion Language Models","created":"2025-09-28","cited_by_count":19},{"id":"2509.20624","title":"FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models","created":"2025-09-24","cited_by_count":17},{"id":"2512.16229","title":"LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding","created":"2025-12-18","cited_by_count":17},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","cited_by_count":16},{"id":"2410.03170","title":"Autoregressive Large Language Models are Computationally Universal","created":"2024-10-04","cited_by_count":15},{"id":"2510.18087","title":"Planned Diffusion","created":"2025-10-20","cited_by_count":9},{"id":"2510.04071","title":"What Makes Diffusion Language Models Super Data Learners?","created":"2025-10-05","cited_by_count":8},{"id":"2302.05971","title":"Review of Extreme Multilabel Classification","created":"2023-02-12","cited_by_count":5},{"id":"2510.03289","title":"Why mask diffusion does not work","created":"2025-09-29","cited_by_count":2}],"next_cursor":null}