VideoMLA applies multi-head latent attention with 3D-RoPE decoupling to autoregressive video diffusion, delivering 92.7% KV memory reduction while matching short-horizon baselines and leading long-horizon VBench scores.
hub Canonical reference
Pyramidal flow matching for efficient video generative modeling.arXiv preprint arXiv:2410.05954
Canonical reference. 88% of citing Pith papers cite this work as background.
48
Pith papers citing it
Background
88% of classified citations
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
representative citing papers
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
Q-ARVD introduces final-quality-aware frame weighting and outlier-aware adaptive dual-scale quantization to enable accurate low-bit inference for autoregressive video diffusion models.
DySink maintains a memory bank and retrieves relevant historical frames as dynamic sinks while using an anomaly gate to suppress collapse, yielding higher temporal quality and dynamic degree on minute-long videos.
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
Stream-R1 improves distillation of autoregressive streaming video diffusion models by adaptively weighting supervision with a reward model at both rollout and per-pixel levels.
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
Stream-DiffVSR enables practical low-latency video super-resolution by combining a four-step distilled denoiser, auto-regressive temporal guidance, and a temporal processor in a strictly causal pipeline.
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
EcoVideo introduces entropy-driven dynamic frame selection for cloud-edge DiT video generation, yielding up to 2.9x speedup with adaptive keyframe budgets.
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
Echo-Infinity replaces handcrafted KV-cache schedules with end-to-end optimized Memory Queries and a Unified Relative RoPE recipe to support real-time infinite video generation in diffusion transformers.
MORPHOS introduces an autoregressive 4D generation method with Temporal Structured Latents (T-SLAT) that produces dynamic 3D assets from videos while handling topological changes and long sequences.
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
OmniMem enables scalable long video generation via adaptive sparse KV retrieval that addresses local bias and union explosion while preserving explicit historical access.
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
Mutual Forcing trains a single native autoregressive audio-video model with mutually reinforcing few-step and multi-step modes via self-distillation to match 50-step baselines at 4-8 steps.
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
DreamZero uses a 14B video diffusion model as a World Action Model to achieve over 2x better zero-shot generalization on real robots than state-of-the-art VLAs, real-time 7Hz closed-loop control, and cross-embodiment transfer with 10-30 minutes of data.
Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.
citing papers explorer
-
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
VideoMLA applies multi-head latent attention with 3D-RoPE decoupling to autoregressive video diffusion, delivering 92.7% KV memory reduction while matching short-horizon baselines and leading long-horizon VBench scores.
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
Q-ARVD introduces final-quality-aware frame weighting and outlier-aware adaptive dual-scale quantization to enable accurate low-bit inference for autoregressive video diffusion models.
-
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
DySink maintains a memory bank and retrieves relevant historical frames as dynamic sinks while using an anomaly gate to suppress collapse, yielding higher temporal quality and dynamic degree on minute-long videos.
-
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
-
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
-
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Stream-R1 improves distillation of autoregressive streaming video diffusion models by adaptively weighting supervision with a reward model at both rollout and per-pixel levels.
-
Efficient Video Diffusion Models: Advancements and Challenges
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
-
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
Stream-DiffVSR enables practical low-latency video super-resolution by combining a four-step distilled denoiser, auto-regressive temporal guidance, and a temporal processor in a strictly causal pipeline.
-
Exploring Cross-Modal Flows for Few-Shot Learning
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
-
History-Guided Video Diffusion
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
-
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
EcoVideo introduces entropy-driven dynamic frame selection for cloud-edge DiT video generation, yielding up to 2.9x speedup with adaptive keyframe budgets.
-
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
-
DisCo: World Models with Discrete Camera Motion Control
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
-
Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation
Echo-Infinity replaces handcrafted KV-cache schedules with end-to-end optimized Memory Queries and a Unified Relative RoPE recipe to support real-time infinite video generation in diffusion transformers.
-
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
MORPHOS introduces an autoregressive 4D generation method with Temporal Structured Latents (T-SLAT) that produces dynamic 3D assets from videos while handling topological changes and long sequences.
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
-
OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
OmniMem enables scalable long video generation via adaptive sparse KV retrieval that addresses local bias and union explosion while preserving explicit historical access.
-
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
-
Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation
Mutual Forcing trains a single native autoregressive audio-video model with mutually reinforcing few-step and multi-step modes via self-distillation to match 50-step baselines at 4-8 steps.
-
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
-
World Action Models are Zero-shot Policies
DreamZero uses a 14B video diffusion model as a World Action Model to achieve over 2x better zero-shot generalization on real robots than state-of-the-art VLAs, real-time 7Hz closed-loop control, and cross-embodiment transfer with 10-30 minutes of data.
-
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
-
Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.
-
Flow marching for a generative PDE foundation model
Flow Marching jointly samples noise and physical time to learn a velocity field for generative PDE modeling, paired with a latent autoencoder and efficient transformer for large-scale pretraining on 2.5M trajectories.
-
Test-Time Training Done Right
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
-
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
-
LTX-Video: Realtime Video Latent Diffusion
LTX-Video integrates Video-VAE and transformer for 1:192 latent compression and real-time video diffusion by moving patchifying to the VAE and letting the decoder finish denoising in pixel space.
-
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.
-
Bridging Video Understanding and Generation in a Unified Framework
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
-
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Sol Video Inference Engine uses parallel skill agents to optimize cache, sparse attention, token pruning, quantization, and kernel fusion, delivering over 2x end-to-end acceleration with near-lossless quality on three video models.
-
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.
-
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
MilliVid compresses video frames into multi-scale token hierarchies and uses coarse-to-fine rollout in a diffusion model to maintain long-range geometric and object consistency on Minecraft videos.
-
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
PILA aligns frozen flow-matching video models to a physics attribute bank via MoE experts and operational residuals, reporting SOTA physical plausibility on VBench-2.0, VideoPhy-2 and PhyGenBench while preserving visual quality.
-
KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing
KGEdit uses an ambiguity-aware knowledge graph and structured injection modules to improve semantic control and temporal consistency in training-free text-to-video diffusion models.
-
Tempered Self-Similarity Alignment for Physically Plausible Video Generation
Tempered Self-similarity Alignment transfers relational structure from foundation-model STSS into video generators via probabilistic correspondence alignment, yielding reported gains in physical plausibility on VideoPhy benchmarks.
-
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
Causal Forcing++ applies causal consistency distillation to enable scalable frame-wise 1-2 step autoregressive video generation, outperforming prior 4-step chunk-wise methods on quality metrics while halving first-frame latency.
-
Matrix-game 2.0: An open-source real-time and streaming interactive world model
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
Wan: Open and Advanced Large-Scale Video Generative Models
Wan releases open 1.3B and 14B video diffusion models claiming superior performance over open-source and commercial baselines across multiple tasks with consumer-grade efficiency.
-
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.
-
EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation
EchoTorrent combines multi-teacher distillation, adaptive CFG calibration, hybrid long-tail forcing, and VAE decoder refinement to enable few-pass autoregressive streaming video generation with improved temporal consistency and audio-lip sync.
-
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
This survey reviews trends, challenges, benchmarks, and future directions in action-conditioned interactive world modeling for video and 3D generation.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
- Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation