PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.
hub Canonical reference
Emu video: Factorizing text-to-video generation by explicit image conditioning
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 7
citation-polarity summary
roles
background 7polarities
background 7representative citing papers
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
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.
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
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.
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
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 training-free framework uses physics-violating counterfactual prompts and Synchronized Decoupled Guidance to suppress implausible motions in diffusion-based video generation while preserving photorealism.
UVA learns a joint video-action latent representation with decoupled diffusion decoding heads, enabling a single model to perform accurate fast policy learning, forward/inverse dynamics, and video generation without performance loss versus task-specific methods.
Gen2Act enables generalizable robot manipulation for unseen objects and novel motions by using zero-shot human video generation from web data to condition a policy trained on an order of magnitude less robot interaction data.
A multi-view diffusion model generates consistent novel views from sparse images to enable fast 3D scene reconstruction.
HunyuanVideo presents a 13B-parameter open-source video generative model with integrated data, architecture, training, and inference systems whose professional evaluations show it outperforming prior SOTA models including Runway Gen-3 and Luma 1.6.
KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.
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 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.
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.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
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.
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
RoboDreamer: Learning Compositional World Models for Robot Imagination
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
-
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.
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
-
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.
-
Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility
A training-free framework uses physics-violating counterfactual prompts and Synchronized Decoupled Guidance to suppress implausible motions in diffusion-based video generation while preserving photorealism.
-
Unified Video Action Model
UVA learns a joint video-action latent representation with decoupled diffusion decoding heads, enabling a single model to perform accurate fast policy learning, forward/inverse dynamics, and video generation without performance loss versus task-specific methods.
-
Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
Gen2Act enables generalizable robot manipulation for unseen objects and novel motions by using zero-shot human video generation from web data to condition a policy trained on an order of magnitude less robot interaction data.
-
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
A multi-view diffusion model generates consistent novel views from sparse images to enable fast 3D scene reconstruction.
-
HunyuanVideo: A Systematic Framework For Large Video Generative Models
HunyuanVideo presents a 13B-parameter open-source video generative model with integrated data, architecture, training, and inference systems whose professional evaluations show it outperforming prior SOTA models including Runway Gen-3 and Luma 1.6.
-
KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.
-
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.
-
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.
-
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.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.