{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112},{"id":"1904.02632","title":"A Learned Representation for Scalable Vector Graphics","created":"2019-04-04","cited_by_count":91},{"id":"2206.04655","title":"Towards Layer-wise Image Vectorization","created":"2022-06-09","cited_by_count":79},{"id":"2312.16476","title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","created":"2023-12-27","cited_by_count":76},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75},{"id":"1901.02199","title":"FIGR: Few-shot Image Generation with Reptile","created":"2019-01-08","cited_by_count":56},{"id":"2306.14685","title":"DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models","created":"2023-06-26","cited_by_count":54},{"id":"2109.08857","title":"Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts","created":"2021-09-18","cited_by_count":40},{"id":"2212.02122","title":"CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics","created":"2022-12-05","cited_by_count":34},{"id":"2405.10317","title":"Text-to-Vector Generation with Neural Path Representation","created":"2024-05-16","cited_by_count":33},{"id":"2401.17093","title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","created":"2024-01-30","cited_by_count":26},{"id":"2106.04912","title":"ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis","created":"2021-06-09","cited_by_count":23},{"id":"2406.09794","title":"SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis","created":"2024-06-14","cited_by_count":19},{"id":"2404.19097","title":"Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations","created":"2024-04-29","cited_by_count":18},{"id":"2405.15217","title":"NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation","created":"2024-05-24","cited_by_count":17},{"id":"2111.03281","title":"Recognizing Vector Graphics without Rasterization","created":"2021-11-05","cited_by_count":11},{"id":"2205.03146","title":"CLIP-CLOP: CLIP-Guided Collage and Photomontage","created":"2022-05-06","cited_by_count":11}],"next_cursor":null}