{"total":61,"rows":[{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708,"area":"wm"},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309,"area":"mllm"},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276,"area":"wm"},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211,"area":"mllm"},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130,"area":"diffusion"},{"id":"2507.07966","title":"Scaling RL to Long Videos","created":"2025-07-10","cited_by_count":84,"area":"lr"},{"id":"2411.01738","title":"xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism","created":"2024-11-04","cited_by_count":56,"area":"diffusion"},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2502.06805","title":"Efficient Diffusion Models: A Survey","created":"2025-02-03","cited_by_count":35,"area":"diffusion"},{"id":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2405.14430","title":"PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference","created":"2024-05-23","cited_by_count":28,"area":"diffusion"},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2411.01783","title":"Context Parallelism for Scalable Million-Token Inference","created":"2024-11-04","cited_by_count":26,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16,"area":"diffusion"},{"id":"2502.07590","title":"DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training","created":"2025-02-11","cited_by_count":15,"area":"diffusion"},{"id":"2506.00830","title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","created":"2025-06-01","cited_by_count":14,"area":"diffusion"},{"id":"2604.06168","title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","created":"2026-04-07","cited_by_count":12,"area":"wm"},{"id":"2501.09706","title":"Domain Adaptation of Foundation LLMs for e-Commerce","created":"2025-01-16","cited_by_count":9,"area":null},{"id":"2511.20714","title":"Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation","created":"2025-11-25","cited_by_count":8,"area":"wm"},{"id":"2505.19151","title":"SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation","created":"2025-05-25","cited_by_count":7,"area":"diffusion"},{"id":"2510.10620","title":"DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2407.12117","title":"MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2505.22296","title":"360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2412.07894","title":"Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2506.13996","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2605.02641","title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","created":"2026-05-04","cited_by_count":3,"area":"moe"},{"id":"2606.12688","title":"M*: A Modular, Extensible, Serving System for Multimodal Models","created":"2026-06-10","cited_by_count":3,"area":"wm"},{"id":"2607.14952","title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2507.00394","title":"HelixPipe: Efficient Distributed Training of Long Sequence Transformers with Attention Parallel Pipeline Parallelism","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2507.17511","title":"Accelerating Parallel Diffusion Model Serving with Residual Compression","created":"2025-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2601.20273","title":"SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs","created":"2026-01-28","cited_by_count":2,"area":"diffusion"},{"id":"2601.22127","title":"EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers","created":"2026-01-29","cited_by_count":2,"area":"diffusion"},{"id":"2604.05182","title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2607.06216","title":"MoWorld: A Flash World Model","created":"2026-07-07","cited_by_count":2,"area":"wm"},{"id":"2607.16107","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2509.04719","title":"Spatio-Temporal Parallelism for Diffusion Model Inference on Heterogeneous Multi-GPU Systems","created":"2025-09-05","cited_by_count":1,"area":"diffusion"},{"id":"2510.18830","title":"MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2511.12056","title":"PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling","created":"2025-11-15","cited_by_count":1,"area":"diffusion"},{"id":"2602.10940","title":"FastUSP: A Multi-Level Collaborative Acceleration Framework for Distributed Diffusion Model Inference","created":"2026-02-11","cited_by_count":1,"area":"diffusion"},{"id":"2605.28691","title":"OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning","created":"2026-05-27","cited_by_count":1,"area":"diffusion"},{"id":"2607.09581","title":"Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation","created":"2026-07-10","cited_by_count":1,"area":"diffusion"},{"id":"2607.16190","title":"FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation","created":"2026-07-17","cited_by_count":1,"area":"diffusion"},{"id":"2608.11745","title":"LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.08368","title":"Miles v0.1: Production-Level Post-Training","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.09155","title":"SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators","created":"2026-09-08","cited_by_count":1,"area":"wm"},{"id":"2609.20744","title":"Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation","created":"2026-09-17","cited_by_count":1,"area":"diffusion"},{"id":"2503.15758","title":"ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2603.05800","title":"StreamWise: Serving Multi-Modal Generation in Real-Time at Scale","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.26294","title":"Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference","created":"2026-04-29","cited_by_count":0,"area":"moe"},{"id":"2607.23264","title":"X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.07524","title":"Training Variable Long Sequences with Data-Centric Parallel","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.03151","title":"BASP: Communication-Efficient Batch-Aware Sequence Parallelism for LLM Training","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.19924","title":"The Life of a Token: from Words to Bits on the Wire","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.07333","title":"Memory-Efficient Expert Routing for Distributed MoE Training","created":"2026-10-05","cited_by_count":0,"area":"moe"},{"id":"2610.17901","title":"FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20556","title":"Speculative Sampling in Interactive Video Generation","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}