{"list":"other","total":52,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","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":"2410.05317","title":"Accelerating Diffusion Transformers with Token-wise Feature Caching","created":"2024-10-05","cited_by_count":156},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"id":"2510.09608","title":"StreamingVLM: Real-Time Understanding for Infinite Video Streams","created":"2025-10-10","cited_by_count":95},{"id":"2512.04678","title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","created":"2025-12-04","cited_by_count":86},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65},{"id":"2501.01986","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models","created":"2024-12-30","cited_by_count":54},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42},{"id":"2505.21996","title":"VRAG: Learning World Models for Interactive Video Generation","created":"2025-05-28","cited_by_count":38},{"id":"2602.08025","title":"MIND: Benchmarking Memory Consistency and Action Control in World Models","created":"2026-02-08","cited_by_count":35},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29},{"id":"2412.18911","title":"Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching","created":"2024-12-25","cited_by_count":28},{"id":"2601.03655","title":"VideoMemory: Toward Consistent Video Generation via Memory Integration","created":"2026-01-07","cited_by_count":25},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25},{"id":"2606.00793","title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","created":"2026-05-30","cited_by_count":18},{"id":"2211.10636","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","created":"2022-11-19","cited_by_count":15},{"id":"2512.23851","title":"TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning","created":"2025-12-29","cited_by_count":15},{"id":"2608.07408","title":"Addressable Memory for Video World Models","created":"2026-08-07","cited_by_count":15},{"id":"2601.04359","title":"PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache","created":"2026-01-07","cited_by_count":13},{"id":"2606.27537","title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","created":"2026-06-25","cited_by_count":12},{"id":"2606.31734","title":"MemLearner: Learning to Query Context memory for Video World Models","created":"2026-06-30","cited_by_count":9},{"id":"2605.30083","title":"Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation","created":"2026-05-28","cited_by_count":8},{"id":"2605.06924","title":"A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency","created":"2026-05-07","cited_by_count":6},{"id":"2605.31033","title":"SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation","created":"2026-05-29","cited_by_count":6},{"id":"2605.13111","title":"Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation","created":"2026-05-13","cited_by_count":4},{"id":"2608.27328","title":"R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models","created":"2026-08-27","cited_by_count":4},{"id":"2608.26671","title":"RECAP-Forcing: Retaining Content Appearances for Long Video Generation","created":"2026-08-27","cited_by_count":3}],"next_cursor":null}