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
Context as memory: Scene-consistent interactive long video generation with memory retrieval
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 18roles
background 3polarities
background 3representative citing papers
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.
AdaState replaces the static first-frame KV anchor with an evolving hidden latent that the model denoises alongside content, treating time as relative to enable recurrence and richer dynamics in streaming 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.
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.
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.
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.
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.
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
OmniMem enables scalable long video generation via adaptive sparse KV retrieval that addresses local bias and union explosion while preserving explicit historical access.
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.
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.
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
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.
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.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
In twisted bilayer nodal d-wave superconductors, interlayer hopping creates nodes on the C2 axis and Bogoliubov flat bands when the single-layer Berry connection is parallel to that axis.
AlayaWorld is a full-stack open-source framework for interactive video world generation, combining 3D spatial caching, error-bank training, and few-step distillation for real-time playable worlds.
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.
-
LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
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.
-
AdaState: Self-Evolving Anchors for Streaming Video Generation
AdaState replaces the static first-frame KV anchor with an evolving hidden latent that the model denoises alongside content, treating time as relative to enable recurrence and richer dynamics in streaming video generation.
-
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.
-
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.
-
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.
-
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.
-
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.
-
Geometry-Aware Implicit Memory for Video World Models
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
-
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.
-
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.
-
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.
-
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
-
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.
-
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.
-
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
-
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
In twisted bilayer nodal d-wave superconductors, interlayer hopping creates nodes on the C2 axis and Bogoliubov flat bands when the single-layer Berry connection is parallel to that axis.
-
AlayaWorld: Long-Horizon and Playable Video World Generation
AlayaWorld is a full-stack open-source framework for interactive video world generation, combining 3D spatial caching, error-bank training, and few-step distillation for real-time playable worlds.