CoFi is a two-stage coarse-to-fine sampler that enforces global coherence via scaffold alignment before restoring local structure with a pretrained prior, yielding better quality and 2-8x fewer evaluations across planning and generation tasks.
hub
Gen-l-video: Multi-text to long video generation via temporal co-denoising
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 2polarities
background 2representative citing papers
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
TIE derives a sinc-based interval encoding from Temporal Integrability and Duration Invariance principles, raising human-verified temporal constraint satisfaction from 77.34% to 96.03% while preserving visual quality in DiT models.
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
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.
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
DrawVideo is a sketch-guided framework that decomposes long videos into controllable shots using keyframe sketches, appearance prompts, and motion prompts, supported by a new SketchLongVideo dataset.
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
A prompt fusion approach combines bidirectional time-weighted latent blending, dynamics-informed prompt weighting via CLIP, and semantic action representations to produce temporally consistent long videos from text without retraining.
citing papers explorer
-
Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
CoFi is a two-stage coarse-to-fine sampler that enforces global coherence via scaffold alignment before restoring local structure with a pretrained prior, yielding better quality and 2-8x fewer evaluations across planning and generation tasks.
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
-
TIE: Time Interval Encoding for Video Generation over Events
TIE derives a sinc-based interval encoding from Temporal Integrability and Duration Invariance principles, raising human-verified temporal constraint satisfaction from 77.34% to 96.03% while preserving visual quality in DiT models.
-
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
-
FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
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.
-
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
-
DrawVideo: Generating Long Video from Storyboard Keyframe Sketches
DrawVideo is a sketch-guided framework that decomposes long videos into controllable shots using keyframe sketches, appearance prompts, and motion prompts, supported by a new SketchLongVideo dataset.
-
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
-
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
-
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
-
Character-Centered Dialogue Generation from Scene-Level Prompts
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
-
Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling
A prompt fusion approach combines bidirectional time-weighted latent blending, dynamics-informed prompt weighting via CLIP, and semantic action representations to produce temporally consistent long videos from text without retraining.