{"list":"other","total":87,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2505.20275","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","created":"2025-05-26","cited_by_count":231},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"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},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109},{"id":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74},{"id":"2410.09575","title":"Reconstructive Visual Instruction Tuning","created":"2024-10-12","cited_by_count":55},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53},{"id":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51},{"id":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51},{"id":"2509.03498","title":"OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation","created":"2025-09-03","cited_by_count":50},{"id":"2411.17762","title":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding","created":"2024-11-26","cited_by_count":44},{"id":"2507.23278","title":"UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing","created":"2025-07-31","cited_by_count":44},{"id":"2503.14324","title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","created":"2025-03-18","cited_by_count":42},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","cited_by_count":28},{"id":"2512.13687","title":"Towards Scalable Pre-training of Visual Tokenizers for Generation","created":"2025-12-15","cited_by_count":28},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23},{"id":"2506.09040","title":"Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better","created":"2025-06-10","cited_by_count":17},{"id":"2503.19480","title":"GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers","created":"2025-03-25","cited_by_count":16},{"id":"2506.02975","title":"HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation","created":"2025-06-03","cited_by_count":13},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7},{"id":"2603.15228","title":"HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding","created":"2026-03-16","cited_by_count":2}],"next_cursor":null}