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.
Canonical reference
arXiv preprint arXiv:2504.12626 , year=
Canonical reference. 89% of citing Pith papers cite this work as background.
28
Pith papers citing it
Background
89% of classified citations
citation-role summary
background 9
citation-polarity summary
roles
background 9representative citing papers
EM-Vid introduces an entity-centric latent patch memory bank with sparse token conditioning and budgeted updates for training-free consistent multi-shot video generation.
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.
ABC enables any-subset autoregressive generation of continuous stochastic processes via non-Markovian diffusion bridges that track physical time and allow path-dependent conditioning.
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.
AnimationBench is the first benchmark that operationalizes the twelve basic principles of animation and IP preservation into scalable, VLM-assisted metrics for animation-style I2V generation.
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
SurgVista mitigates spatial interaction incoherence and temporal fidelity collapse in surgical world models through trajectory-based contrastive regularization and drift-perturbed training, outperforming prior methods on a new long-horizon benchmark.
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.
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.
Light Interaction accelerates interactive video world models up to 2.59x via adaptive context management, denoising cache acceleration, and 3D block sparse attention without retraining.
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.
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.
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.
Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and 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.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
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.
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.
citing papers explorer
-
MemLearner: Learning to Query Context memory for Video World Models
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.
-
EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation
EM-Vid introduces an entity-centric latent patch memory bank with sparse token conditioning and budgeted updates for training-free consistent multi-shot video generation.
-
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.
-
ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
ABC enables any-subset autoregressive generation of continuous stochastic processes via non-Markovian diffusion bridges that track physical time and allow path-dependent conditioning.
-
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.
-
AnimationBench: Are Video Models Good at Character-Centric Animation?
AnimationBench is the first benchmark that operationalizes the twelve basic principles of animation and IP preservation into scalable, VLM-assisted metrics for animation-style I2V generation.
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
-
SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics
SurgVista mitigates spatial interaction incoherence and temporal fidelity collapse in surgical world models through trajectory-based contrastive regularization and drift-perturbed training, outperforming prior methods on a new long-horizon benchmark.
-
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.
-
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.
-
Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
Light Interaction accelerates interactive video world models up to 2.59x via adaptive context management, denoising cache acceleration, and 3D block sparse attention without retraining.
-
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.
-
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.
-
Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
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.
-
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
-
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.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
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.
-
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.
-
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.
-
Towards Error-Free Long Video Generation
An autoregressive diffusion framework with causal inter-clip attention, KV caching, and truncation-rectified flow produces coherent minute-level videos while reducing error accumulation.
-
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.
- FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion