Live Music Diffusion Models adapt bidirectional diffusion for interactive music generation via KV caching and ARC-Forcing, recovering and exceeding discrete autoregressive efficiency while enabling post-training alignment without RL.
hub Canonical reference
History-Guided Video Diffusion
Canonical reference. 90% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
90% of classified citations
abstract
Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos. Project website: https://boyuan.space/history-guidance
hub tools
citation-role summary
background 9
method 1
citation-polarity summary
representative citing papers
3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
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.
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
Unison introduces a unified framework using semantic-guided harmonization and bidirectional cross-modal forcing to generate human-centric videos with improved synchronization between motion, speech, and sound effects.
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal 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.
CityRAG generates minutes-long 3D-consistent videos of real-world cities by grounding outputs in geo-registered data and using temporally unaligned training to disentangle fixed scenes from transient elements like weather.
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
Interpolating exo and ego videos into a single continuous sequence lets diffusion sequence models generate more coherent first-person videos than direct conditioning, even without pose interpolation.
EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.
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.
Quant VideoGen reduces KV cache memory by up to 7 times in autoregressive video diffusion models via semantic aware smoothing and progressive residual quantization, achieving better quality than baselines with under 4% latency overhead.
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.
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.
LongLive is a causal autoregressive video generator that produces up to 240-second interactive videos at 20.7 FPS on one H100 GPU after 32 GPU-days of fine-tuning from a 1.3B short-clip model.
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
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.
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.
citing papers explorer
-
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
Live Music Diffusion Models adapt bidirectional diffusion for interactive music generation via KV caching and ARC-Forcing, recovering and exceeding discrete autoregressive efficiency while enabling post-training alignment without RL.
-
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
-
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.
-
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
-
Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
Unison introduces a unified framework using semantic-guided harmonization and bidirectional cross-modal forcing to generate human-centric videos with improved synchronization between motion, speech, and sound effects.
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal video generation.
-
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.
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
CityRAG generates minutes-long 3D-consistent videos of real-world cities by grounding outputs in geo-registered data and using temporally unaligned training to disentangle fixed scenes from transient elements like weather.
-
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.
-
From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
Interpolating exo and ego videos into a single continuous sequence lets diffusion sequence models generate more coherent first-person videos than direct conditioning, even without pose interpolation.
-
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.
-
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.
-
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Quant VideoGen reduces KV cache memory by up to 7 times in autoregressive video diffusion models via semantic aware smoothing and progressive residual quantization, achieving better quality than baselines with under 4% latency overhead.
-
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.
-
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.
-
LongLive: Real-time Interactive Long Video Generation
LongLive is a causal autoregressive video generator that produces up to 240-second interactive videos at 20.7 FPS on one H100 GPU after 32 GPU-days of fine-tuning from a 1.3B short-clip model.
-
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
-
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
-
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.
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
-
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.
-
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.
- Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation