EcoVideo introduces entropy-driven dynamic frame selection for cloud-edge DiT video generation, yielding up to 2.9x speedup with adaptive keyframe budgets.
Macro-from-micro planning for high-quality and parallelized autoregressive long video generation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
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.
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.
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.
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.
citing papers explorer
-
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
EcoVideo introduces entropy-driven dynamic frame selection for cloud-edge DiT video generation, yielding up to 2.9x speedup with adaptive keyframe budgets.
-
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.
-
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.
-
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.
-
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.