{"list":"other","total":54,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1907.00503","title":"Modeling Tabular data using Conditional GAN","created":"2019-07-01","cited_by_count":699},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"2310.09656","title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","created":"2023-10-14","cited_by_count":186},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100},{"id":"2002.09599","title":"Training Question Answering Models From Synthetic Data","created":"2020-02-22","cited_by_count":95},{"id":"2303.04132","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction","created":"2023-03-07","cited_by_count":89},{"id":"2304.12654","title":"CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis","created":"2023-04-25","cited_by_count":78},{"id":"1611.05013","title":"PixelVAE: A Latent Variable Model for Natural Images","created":"2016-11-15","cited_by_count":70},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67},{"id":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"id":"2401.02524","title":"Comprehensive Exploration of Synthetic Data Generation: A Survey","created":"2024-01-04","cited_by_count":60},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37},{"id":"2212.08307","title":"Controllable Text Generation via Probability Density Estimation in the Latent Space","created":"2022-12-16","cited_by_count":27},{"id":"2305.01735","title":"DiffuSum: Generation Enhanced Extractive Summarization with Diffusion","created":"2023-05-02","cited_by_count":25},{"id":"1801.09797","title":"Discrete Autoencoders for Sequence Models","created":"2018-01-29","cited_by_count":24},{"id":"2004.14758","title":"Preventing Posterior Collapse with Levenshtein Variational Autoencoder","created":"2020-04-30","cited_by_count":12},{"id":"1910.00382","title":"Latent-Variable Generative Models for Data-Efficient Text Classification","created":"2019-10-01","cited_by_count":4},{"id":"2402.10575","title":"Symbolic Autoencoding for Self-Supervised Sequence Learning","created":"2024-02-16","cited_by_count":2}],"next_cursor":null}