{"list":"other","total":62,"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"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":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198},{"id":"2303.12346","title":"NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation","created":"2023-03-22","cited_by_count":171},{"id":"2504.12369","title":"WorldMem: Long-term Consistent World Simulation with Memory","created":"2025-04-16","cited_by_count":168},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143},{"id":"2303.09769","title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners","created":"2023-03-17","cited_by_count":130},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128},{"id":"2411.10958","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","created":"2024-11-17","cited_by_count":114},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101},{"id":"2407.16655","title":"MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence","created":"2024-07-23","cited_by_count":89},{"id":"2311.18834","title":"ART$\\boldsymbol{\\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models","created":"2023-11-30","cited_by_count":76},{"id":"2502.21079","title":"Training-free and Adaptive Sparse Attention for Efficient Long Video Generation","created":"2025-02-28","cited_by_count":69},{"id":"2506.19852","title":"Radial Attention: $O(n\\log n)$ Sparse Attention with Energy Decay for Long Video Generation","created":"2025-06-24","cited_by_count":69},{"id":"2401.01256","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","created":"2024-01-02","cited_by_count":64},{"id":"2505.20171","title":"Long-Context State-Space Video World Models","created":"2025-05-26","cited_by_count":64},{"id":"2501.08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","created":"2025-01-14","cited_by_count":60},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48},{"id":"2411.18616","title":"Diffusion Self-Distillation for Zero-Shot Customized Image Generation","created":"2024-11-27","cited_by_count":47},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44},{"id":"2506.23858","title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","created":"2025-06-30","cited_by_count":37},{"id":"2408.11788","title":"DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework","created":"2024-08-21","cited_by_count":35},{"id":"2505.16864","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","created":"2025-05-22","cited_by_count":34},{"id":"2411.04925","title":"StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration","created":"2024-11-07","cited_by_count":31},{"id":"2503.10704","title":"Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework","created":"2025-03-12","cited_by_count":20},{"id":"2405.14040","title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","created":"2024-05-22","cited_by_count":19},{"id":"2502.12632","title":"MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation","created":"2025-02-18","cited_by_count":14},{"id":"2501.08994","title":"RepVideo: Rethinking Cross-Layer Representation for Video Generation","created":"2025-01-15","cited_by_count":12}],"next_cursor":null}