{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"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":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"1903.05789","title":"Diagnosing and Enhancing VAE Models","created":"2019-03-14","cited_by_count":193},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2409.04410","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","created":"2024-09-06","cited_by_count":155},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146},{"id":"2307.08041","title":"Planting a SEED of Vision in Large Language Model","created":"2023-07-16","cited_by_count":140},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2407.06135","title":"ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation","created":"2024-07-08","cited_by_count":114},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112},{"id":"2502.13967","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","created":"2025-02-19","cited_by_count":110},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99},{"id":"2504.11455","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","created":"2025-04-15","cited_by_count":86},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79},{"id":"2405.14224","title":"DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis","created":"2024-05-23","cited_by_count":72},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50},{"id":"2501.10064","title":"One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression","created":"2025-01-17","cited_by_count":48},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","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":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36},{"id":"2412.13061","title":"VidTok: A Versatile and Open-Source Video Tokenizer","created":"2024-12-17","cited_by_count":35},{"id":"2501.09755","title":"Learnings from Scaling Visual Tokenizers for Reconstruction and Generation","created":"2025-01-16","cited_by_count":32},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30},{"id":"2501.18593","title":"Diffusion Autoencoders are Scalable Image Tokenizers","created":"2025-01-30","cited_by_count":28},{"id":"2504.14666","title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens","created":"2025-04-20","cited_by_count":28},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27},{"id":"2507.08441","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation","created":"2025-07-11","cited_by_count":21},{"id":"2506.05289","title":"Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","created":"2025-06-05","cited_by_count":20},{"id":"2507.15856","title":"Latent Denoising Makes Good Tokenizers","created":"2025-07-21","cited_by_count":20},{"id":"2505.21473","title":"DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction","created":"2025-05-27","cited_by_count":18},{"id":"2506.08257","title":"Highly Compressed Tokenizer Can Generate Without Training","created":"2025-06-09","cited_by_count":18},{"id":"2410.04081","title":"Epsilon-VAE: Denoising as Visual Decoding","created":"2024-10-05","cited_by_count":16},{"id":"2410.22655","title":"FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution","created":"2024-10-30","cited_by_count":16},{"id":"2505.17011","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space","created":"2025-05-22","cited_by_count":16},{"id":"2509.16197","title":"MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer","created":"2025-09-19","cited_by_count":15},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14},{"id":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10},{"id":"2503.03708","title":"Rethinking Video Tokenization: A Conditioned Diffusion-based Approach","created":"2025-03-05","cited_by_count":9},{"id":"2505.23660","title":"D-AR: Diffusion via Autoregressive Models","created":"2025-05-29","cited_by_count":9},{"id":"2506.07136","title":"MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding","created":"2025-06-08","cited_by_count":9},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8},{"id":"2507.10547","title":"Quantize-then-Rectify: Efficient VQ-VAE Training","created":"2025-07-14","cited_by_count":7},{"id":"2505.10562","title":"End-to-End Vision Tokenizer Tuning","created":"2025-05-15","cited_by_count":5},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3}],"next_cursor":"100"}