Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
hub Canonical reference
LongLive: Real-time Interactive Long Video Generation
Canonical reference. 92% of citing Pith papers cite this work as background.
73
Pith papers citing it
Background
92% of classified citations
abstract
We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.
hub tools
citation-role summary
background 11
baseline 1
citation-polarity summary
representative citing papers
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.
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
MV-Forcing composes temporal and view-sequential autoregression in a single diffusion model, using a recurrent 3D reconstruction model as a geometric bridge to generate arbitrarily long, multi-view consistent videos.
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
CoDMD adds a copula-matching regularizer to DMD for distilling 50-step video diffusion models to 4 steps, reporting VBench scores of 84.46/84.87 on 1.3B/14B Wan-2.1-T2V models.
TurboServe introduces the first serving system for streaming video generation workloads, using migration-aware placement and load-driven autoscaling to cut worst-case latency by 37.5% and GPU cost by 37.2%.
SPAWN enables training-free insertion of custom visual concepts into autoregressive world models by swapping the pinned context-memory anchor over a short injection window.
Future Forcing constructs a future query proxy from historical pre-RoPE statistics to score and merge KV tokens, improving subject consistency by up to 1.49 on VBench-Long for 60s AR video generation.
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.
Anchored Tree Sampling converts horizon-compounding drift into anchor-bounded drift by organizing video generation as a sparse-to-dense tree of imputations instead of left-to-right autoregressive rollout.
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
Echo-Forcing decouples stable anchors, compressed history, and recent dynamics in video diffusion KV caches using hierarchical memory, scene recall frames, and difference-aware decay to support interactive long video generation under bounded cache.
EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.
KVPO aligns streaming autoregressive video generators with human preferences via ODE-native GRPO, using KV cache for semantic exploration and TVE for velocity-based policy modeling, yielding gains in quality and alignment.
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
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.
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
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.
Prompt Relay is an inference-time plug-and-play method that penalizes cross-attention to enforce temporal prompt alignment and reduce semantic entanglement in multi-event video generation.
Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressive video synthesis.
SPIRAL is a closed-loop think-act-reflect framework using PlanAgent, VideoGenerator, and CriticAgent plus GRPO self-evolution to improve long-horizon action-conditioned video generation, with new dataset and benchmark showing gains over open-loop baselines.
Causal Forcing distills few-step autoregressive video generators from an autoregressive diffusion teacher rather than a bidirectional one, avoiding conditional-expectation blur and beating Self Forcing on motion and quality metrics.
citing papers explorer
-
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
-
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.
-
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
-
MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
MV-Forcing composes temporal and view-sequential autoregression in a single diffusion model, using a recurrent 3D reconstruction model as a geometric bridge to generate arbitrarily long, multi-view consistent videos.
-
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
-
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
-
CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation
CoDMD adds a copula-matching regularizer to DMD for distilling 50-step video diffusion models to 4 steps, reporting VBench scores of 84.46/84.87 on 1.3B/14B Wan-2.1-T2V models.
-
TurboServe: Serving Streaming Video Generation Efficiently and Economically
TurboServe introduces the first serving system for streaming video generation workloads, using migration-aware placement and load-driven autoscaling to cut worst-case latency by 37.5% and GPU cost by 37.2%.
-
From Zero to Hero: Training-Free Custom Concept Spawning in World Models
SPAWN enables training-free insertion of custom visual concepts into autoregressive world models by swapping the pinned context-memory anchor over a short injection window.
-
Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
Future Forcing constructs a future query proxy from historical pre-RoPE statistics to score and merge KV tokens, improving subject consistency by up to 1.49 on VBench-Long for 60s AR video generation.
-
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.
-
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
Anchored Tree Sampling converts horizon-compounding drift into anchor-bounded drift by organizing video generation as a sparse-to-dense tree of imputations instead of left-to-right autoregressive rollout.
-
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
-
Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
Echo-Forcing decouples stable anchors, compressed history, and recent dynamics in video diffusion KV caches using hierarchical memory, scene recall frames, and difference-aware decay to support interactive long video generation under bounded cache.
-
EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.
-
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
KVPO aligns streaming autoregressive video generators with human preferences via ODE-native GRPO, using KV cache for semantic exploration and TVE for velocity-based policy modeling, yielding gains in quality and alignment.
-
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
-
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.
-
Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
-
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.
-
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
Prompt Relay is an inference-time plug-and-play method that penalizes cross-attention to enforce temporal prompt alignment and reduce semantic entanglement in multi-event video generation.
-
Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressive video synthesis.
-
SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents
SPIRAL is a closed-loop think-act-reflect framework using PlanAgent, VideoGenerator, and CriticAgent plus GRPO self-evolution to improve long-horizon action-conditioned video generation, with new dataset and benchmark showing gains over open-loop baselines.
-
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Causal Forcing distills few-step autoregressive video generators from an autoregressive diffusion teacher rather than a bidirectional one, avoiding conditional-expectation blur and beating Self Forcing on motion and quality metrics.
-
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
InteractiveAvatar is a real-time infinite-streaming avatar video generation system using autoregressive distillation, Long-Short Visual Memory for consistency, and a Reasoning-Reaction Module for intent-aware interactions.
-
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
UniTemp enables arbitrary temporal order video generation in autoregressive diffusion models via bidirectional distillation and blockwise anchor latents.
-
Echo-Memory: A Controlled Study of Memory in Action World Models
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
-
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.
-
Streaming Video Generation with Streaming Force Control
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
-
AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
AAD-1 uses a causal generator with a bidirectional holistic discriminator plus phased distribution matching before adversarial training to reach state-of-the-art one-step autoregressive video generation on VBench.
-
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.
-
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
SANA-Streaming delivers 1280x704 streaming video editing at 24 FPS end-to-end on an RTX 5090 using hybrid DiT blocks, cycle-reverse training, and mixed-precision quantization.
-
DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion
DexSIM is a bi-directional video diffusion model with hand trajectory embedding and spatial memory cache for real-time dexterous hand-object simulation at 15 FPS.
-
WorldKV: Efficient World Memory with World Retrieval and Compression
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
-
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.
-
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
DySink replaces static early-frame anchors in autoregressive video generation with dynamically retrieved, visually relevant history, filtered by an inter-head consensus gate, improving long-video temporal scores.
-
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching
FlowLong generates videos several times longer than native model windows by blending adjacent predictions with Tweedie matching to enforce manifold and temporal consistency while using stochastic noise injection early and deterministic sampling later.
-
Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
IAMFlow is a training-free identity-aware memory system that tracks entities via LLM global ID assignment and VLM frame verification to reduce identity drift in narrative long video generation from shifting prompts.
-
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
FashionChameleon achieves interactive multi-garment video customization at 23.8 FPS via in-context teacher models, streaming distillation, and training-free KV cache rescheduling while using only single-garment data.
-
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
EverAnimate restores drifted latent flow trajectories in chunked video generation via persistent latent propagation and restorative flow matching, achieving measurable gains in PSNR, SSIM, LPIPS, and FID over prior long-animation methods with only LoRA tuning.
-
Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.
-
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
HorizonDrive is a new anti-drifting autoregressive training and distillation method that enables minute-scale stable driving video rollouts by making the teacher model rollout-capable via scheduled rollout recovery and teacher rollout DMD.
-
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
RealCam is a causal autoregressive model for real-time camera-controlled video-to-video generation, using cross-frame in-context teacher distillation and loop-closed data augmentation to achieve high fidelity and consistency.
-
Stream-T1: Test-Time Scaling for Streaming Video Generation
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
-
Motion-Aware Caching for Efficient Autoregressive Video Generation
MotionCache accelerates autoregressive video generation up to 6.28x by motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on SkyReels-V2 and MAGI-1.
-
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.
-
Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers
Real-Time AttentionBender enables live, granular manipulation of self-attention, cross-attention, and feed-forward layers in video diffusion transformers during generation.
-
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
-
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.
-
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
Self-consistent distribution matching plus cache-aware mixed-step training improves 2–4 NFE video quality on Wan 2.1 and real-time autoregressive backbones without extra inference cost.