{"total":142,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585,"area":"diffusion"},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089,"area":"mllm"},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565,"area":"mllm"},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563,"area":"mllm"},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509,"area":"mllm"},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392,"area":null},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279,"area":null},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260,"area":"mllm"},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255,"area":null},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208,"area":null},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170,"area":"mllm"},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2406.08394","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","created":"2024-06-12","cited_by_count":137,"area":"mllm"},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125,"area":"mllm"},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2310.02992","title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models","created":"2023-10-04","cited_by_count":105,"area":"mllm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75,"area":null},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68,"area":"mllm"},{"id":"2407.21770","title":"MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts","created":"2024-07-31","cited_by_count":62,"area":"moe"},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61,"area":null},{"id":"2506.09018","title":"Edit Flows: Flow Matching with Edit Operations","created":"2025-06-10","cited_by_count":55,"area":"diffusion"},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2406.11271","title":"MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens","created":"2024-06-17","cited_by_count":50,"area":"mllm"},{"id":"2407.21439","title":"MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training","created":"2024-07-31","cited_by_count":50,"area":"mllm"},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2311.16974","title":"COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design","created":"2023-11-28","cited_by_count":43,"area":null},{"id":"2210.16886","title":"DiffusER: Discrete Diffusion via Edit-based Reconstruction","created":"2022-10-30","cited_by_count":41,"area":"diffusion"},{"id":"2302.04858","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","created":"2023-02-09","cited_by_count":41,"area":"mllm"},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39,"area":null},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2309.15564","title":"Jointly Training Large Autoregressive Multimodal Models","created":"2023-09-27","cited_by_count":32,"area":null},{"id":"2401.01808","title":"aMUSEd: An Open MUSE Reproduction","created":"2024-01-03","cited_by_count":32,"area":"diffusion"},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32,"area":"mllm"},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2410.24159","title":"GPT or BERT: why not both?","created":"2024-10-31","cited_by_count":27,"area":null},{"id":"2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","created":"2022-11-20","cited_by_count":24,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2303.07295","title":"Meet in the Middle: A New Pre-training Paradigm","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"2302.07730","title":"Transformer models: an introduction and catalog","created":"2023-02-12","cited_by_count":21,"area":null},{"id":"2302.09170","title":"KILM: Knowledge Injection into Encoder-Decoder Language Models","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2311.15941","title":"Tell2Design: A Dataset for Language-Guided Floor Plan Generation","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2305.03668","title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2401.00849","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training","created":"2024-01-01","cited_by_count":18,"area":"mllm"},{"id":"2403.11905","title":"Tur[k]ingBench: A Challenge Benchmark for Web Agents","created":"2024-03-18","cited_by_count":18,"area":"agents"},{"id":"2504.17789","title":"Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models","created":"2025-04-24","cited_by_count":18,"area":null},{"id":"2206.07699","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","created":"2022-06-15","cited_by_count":17,"area":"mllm"},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2401.03321","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","created":"2024-01-06","cited_by_count":16,"area":null},{"id":"2409.19051","title":"Multimodal Markup Document Models for Graphic Design Completion","created":"2024-09-27","cited_by_count":16,"area":null},{"id":"2410.02155","title":"From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities","created":"2024-10-03","cited_by_count":16,"area":"mllm"},{"id":"2205.11726","title":"On the Role of Bidirectionality in Language Model Pre-Training","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2411.00304","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","created":"2024-11-01","cited_by_count":15,"area":"mllm"},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2402.08657","title":"PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs","created":"2024-02-13","cited_by_count":14,"area":"mllm"},{"id":"2403.12922","title":"Contextual AD Narration with Interleaved Multimodal Sequence","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2310.09930","title":"FiLM: Fill-in Language Models for Any-Order Generation","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2402.01293","title":"Can MLLMs Perform Text-to-Image In-Context Learning?","created":"2024-02-02","cited_by_count":13,"area":"mllm"},{"id":"2406.04823","title":"BERTs are Generative In-Context Learners","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2502.17297","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","created":"2025-02-24","cited_by_count":12,"area":"mllm"},{"id":"2305.18584","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","created":"2023-05-29","cited_by_count":9,"area":null}],"next_cursor":"100"}