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
MAGI-1: Autoregressive Video Generation at Scale
Canonical reference. 74% of citing Pith papers cite this work as background.
81
Pith papers citing it
Background
74% of classified citations
abstract
We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai.
hub tools
citation-role summary
background 15
baseline 2
dataset 1
method 1
citation-polarity summary
representative citing papers
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
PhysInOne is a new dataset of 2 million videos across 153,810 dynamic 3D scenes covering 71 physical phenomena, shown to improve AI performance on physics-aware video generation, prediction, property estimation, and motion transfer.
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.
MemLearner introduces a learning-based adaptive context query method using query tokens in video world models to improve long-term scene consistency over rule-based retrieval.
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
FadeMem introduces distance-aware KV memory consolidation for autoregressive video diffusion that builds a temporal hierarchy with power-law merging to preserve short-term dynamics and long-range coherence under fixed cache budget.
PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.
LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
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.
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.
FreeSpec uses SVD-based spectral reconstruction to fuse global low-rank and local high-rank features, reducing content drift and preserving temporal dynamics in long 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 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.
An autoregressive diffusion model on sparse point trajectories predicts multi-modal future scene dynamics from single images with orders-of-magnitude faster sampling than dense video simulators while matching accuracy.
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.
A single transformer model using a new markup representation generates functional floorplans from diverse conditions and outperforms prior task-specific methods on the RPLAN dataset.
SCOPE accelerates autoregressive video diffusion up to 4.73x by using a tri-modal cache-predict-recompute scheduler with Taylor extrapolation and selective active-frame computation while preserving output quality.
GEOPHYS defines five geometric properties of per-frame embeddings from image encoders that detect physical implausibility in videos with SOTA accuracy and serve as an efficient verifier.
ARGUS converts MLLM-selected identity evidence into a synchronized 3x3 mosaic injected as negative-time memory in a diffusion model, plus supporting training techniques, to achieve SOTA subject preservation on human video benchmarks.
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.
citing papers explorer
-
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.
-
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.
-
Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
SCOPE accelerates autoregressive video diffusion up to 4.73x by using a tri-modal cache-predict-recompute scheduler with Taylor extrapolation and selective active-frame computation while preserving output quality.
-
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Forcing-KV applies head-specific static and dynamic pruning to KV caches in AR video diffusion models, achieving over 29 fps, 30% memory reduction, and up to 2.82x speedup at maintained quality.
-
SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
SwiftI2V achieves comparable 2K I2V quality to end-to-end models on VBench-I2V while cutting GPU time by 202x through low-resolution motion planning followed by strongly image-conditioned segment-wise high-resolution synthesis.
-
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.
-
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.
-
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
MAR-GRPO stabilizes GRPO for AR-diffusion hybrids via multi-trajectory expectation and uncertainty-based token selection, yielding better visual quality, stability, and spatial understanding than baselines.
-
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.
-
Video Generation with Predictive Latents
PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.
-
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
-
Image-to-Video Diffusion: From Foundations to Open Frontiers
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.
- Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation