Bernini: Latent Semantic Planning for Video Diffusion

arXiv:2605.22344 · cs.CV, cs.AI, cs.MM · Submitted 2026-05-21 · Read on arXiv

cs.CV, cs.AI, cs.MM

Submitted: 2026-05-21

Updated: 2026-09-02

Code: https://github.com/Dao-AILab/quack

Project page: https://bernini-ai.github.io

Terminology

• Consistency — 48× in this paper · explained in 3 episodes
• Embeddings — 26× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Diffusion Model — 22× in this paper · explained in 8 episodes
• Diffusion Models — 15× in this paper · explained in 6 episodes
• Generation Quality — 15× in this paper
• Video Consistency — 15× in this paper
• Generalization — 13× in this paper · explained in 13 episodes
• Transformer — 13× in this paper · explained in 2 episodes
• Fidelity — 10× in this paper · explained in 2 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Grounding — 8× in this paper · explained in 3 episodes
• Instruction Following — 8× in this paper
• Unified Framework — 8× in this paper · explained in 5 episodes
• Reference Image Consistency — 7× in this paper
• Distillation — 6× in this paper · explained in 2 episodes
• Latent Space — 6× in this paper · explained in 7 episodes
• Ablation — 5× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 5× in this paper
• Overall Score — 5× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Causal Reasoning — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 3× in this paper · explained in 4 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Rectified Flow — 3× in this paper · explained in 3 episodes
• Temporal Reasoning — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Evaluation Dimensions — 2× in this paper · explained in 3 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Multimodal Inputs — 2× in this paper · explained in 2 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Temporal consistency — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• alpha — 2× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Communication Overhead — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Frustration — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• In International Conference on Learning Representations — 1× in this paper
• Information Leakage — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
• Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
• Qwen3-VL Technical Report
• HunyuanImage 3.0 Technical Report
• VINO: A Unified Visual Generator with Interleaved OmniModal Context
• ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
• Consistent Video-to-Video Transfer Using Synthetic Dataset
• Emu3.5: Native Multimodal Models are World Learners
• Emerging Properties in Unified Multimodal Pretraining
• MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
• Flex Attention: A Programming Model for Generating Optimized Attention Kernels
• SkyReels-A2: Compose Anything in Video Diffusion Transformers
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
• UniREditBench: A Unified Reasoning-based Image Editing Benchmark
• OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
• VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
• DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
• EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models