MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence.
hub Canonical reference
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Canonical reference. 80% of citing Pith papers cite this work as background.
98
Pith papers citing it
Background
80% of classified citations
abstract
Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model understanding complex movement semantics. In this work, we present 9B-parameter transformer CogVideo, trained by inheriting a pretrained text-to-image model, CogView2. We also propose multi-frame-rate hierarchical training strategy to better align text and video clips. As (probably) the first open-source large-scale pretrained text-to-video model, CogVideo outperforms all publicly available models at a large margin in machine and human evaluations.
hub tools
citation-role summary
background 26
baseline 2
dataset 1
method 1
citation-polarity summary
claims ledger
- abstract Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model understanding complex movement semantics. In this work, we present 9B-parameter transformer CogVideo, trained by inheriting a pretrained text-to-image model, CogView2. We also propose multi-frame-rate hierarchical training strategy to better align te
co-cited works
representative citing papers
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
OmniNFT introduces modality-wise advantage routing, layer-wise gradient surgery, and region-wise loss reweighting in an online diffusion RL framework to improve audio-video quality, alignment, and synchronization.
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.
DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.
ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.
RoboWM-Bench evaluates video world models by converting their manipulation video predictions into executable actions validated in simulation, showing that visual plausibility does not guarantee physical executability.
MCSC-Bench is the first large-scale dataset for the Multimodal Context-to-Script Creation task, requiring models to select relevant shots from redundant materials, plan missing shots, and generate coherent scripts with voiceovers.
LottieGPT tokenizes Lottie animations into compact sequences and fine-tunes Qwen-VL to autoregressively generate coherent vector animations from natural language or visual prompts, outperforming prior SVG models.
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
OmniCamera disentangles video content and camera motion for multi-task generation with arbitrary camera control via the OmniCAM hybrid dataset and Dual-level Curriculum Co-Training.
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
EduVQA introduces the first concept-aware benchmark for educational AI-generated video assessment and a S2D-MoE framework that jointly evaluates perceptual quality and fine-grained semantic alignment.
OSDEnhancer delivers state-of-the-art real-world space-time video super-resolution via one-step diffusion with temporal coherence and texture enrichment LoRAs plus a deformable recurrent VAE decoder.
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new BG-Flicker metric.
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.
citing papers explorer
-
MusicLM: Generating Music From Text
MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence.
-
YoCausal: How Far is Video Generation from World Model? A Causality Perspective
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
-
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
OmniNFT introduces modality-wise advantage routing, layer-wise gradient surgery, and region-wise loss reweighting in an online diffusion RL framework to improve audio-video quality, alignment, and synchronization.
-
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.
-
DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.
-
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.
-
RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
RoboWM-Bench evaluates video world models by converting their manipulation video predictions into executable actions validated in simulation, showing that visual plausibility does not guarantee physical executability.
-
MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production
MCSC-Bench is the first large-scale dataset for the Multimodal Context-to-Script Creation task, requiring models to select relevant shots from redundant materials, plan missing shots, and generate coherent scripts with voiceovers.
-
LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
LottieGPT tokenizes Lottie animations into compact sequences and fine-tunes Qwen-VL to autoregressively generate coherent vector animations from natural language or visual prompts, outperforming prior SVG models.
-
MoRight: Motion Control Done Right
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
-
OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
OmniCamera disentangles video content and camera motion for multi-task generation with arbitrary camera control via the OmniCAM hybrid dataset and Dual-level Curriculum Co-Training.
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos
EduVQA introduces the first concept-aware benchmark for educational AI-generated video assessment and a S2D-MoE framework that jointly evaluates perceptual quality and fine-grained semantic alignment.
-
Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion
OSDEnhancer delivers state-of-the-art real-world space-time video super-resolution via one-step diffusion with temporal coherence and texture enrichment LoRAs plus a deformable recurrent VAE decoder.
-
CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
-
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
-
Recurrent Video Masked Autoencoders
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
-
ASTRA: Let Arbitrary Subjects Transform in Video Editing
ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.
-
FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new BG-Flicker metric.
-
Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
Phenaki: Variable Length Video Generation From Open Domain Textual Description
Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.
-
Streaming Video Generation with Streaming Force Control
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
-
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
RhymeFlow is a training-free acceleration framework that decouples denoising trajectories across video frames by dense processing of semantic keyframes and asynchronous skipping for non-keyframes, augmented by a latent trajectory projection module to maintain consistency.
-
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Physical plausibility is linearly decodable from diffusion transformer states in video models at 81.27% accuracy on IntPhys and InfLevel, absent from VAE latents and outperforming V-JEPA and VideoMAE.
-
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
PAI-Studio reformulates cinematic background replacement as in-context conditional generation inside a Diffusion Transformer with bidirectional attention, trained on a new 30K film-sourced dataset, and reports better motion consistency and relighting than prior open-source and commercial systems.
-
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
AlbedoEdit fine-tunes video foundation models to translate RGB videos into edited versions conditioned on user-edited first-frame albedo maps, trained on a new synthetic paired dataset for insertion, removal, and texture tasks.
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
-
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.
-
Refining Multidimensional Video Reward Models via Disentangled Influence Functions
Introduces dimension-disentangled influence estimation to prune or reweight training samples for MVRMs, outperforming global scalar filtering in alignment with ground truth.
-
CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection
Introduces a commercial-model contrastive AIGC video dataset and a hybrid contrastive-MLLM detection framework claiming SOTA performance on realistic video forgery detection.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
-
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
-
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
AtlasVid proposes a decoupled global-local diffusion framework that trains at low resolution with LoRA and generalizes to ultra-high-resolution long video synthesis via semantic proxy guidance and locality-preserving attention.
-
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Flash-GRPO is a one-step GRPO framework for video diffusion alignment that applies iso-temporal grouping and temporal gradient rectification to achieve higher alignment quality and stability than full-trajectory training under low compute budgets on 1.3B-14B models.
-
Video Models Can Reason with Verifiable Rewards
VideoRLVR uses SDE-GRPO optimization, dense decomposed rewards, and Early-Step Focus to train video diffusion models on verifiable reasoning tasks, outperforming supervised fine-tuning and other video generators on Maze, FlowFree, and Sokoban.
-
Compositional Video Generation via Inference-Time Guidance
CVG improves compositional faithfulness in frozen text-to-video diffusion models by steering early denoising steps with gradients from a classifier trained on the model's own cross-attention features.
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
-
Detecting AI-Generated Videos with Spiking Neural Networks
MAST with spiking neural networks achieves 93.14% mean accuracy detecting AI-generated videos from 10 unseen generators by exploiting smoother pixel residuals and compact semantic trajectories.
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models
VAP is a training-free active-perception method that improves zero-shot long-form video QA performance and frame efficiency up to 5.6x in VLMs by selecting keyframes that differ from priors generated by a text-conditioned video model.
-
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
-
PhyCo: Learning Controllable Physical Priors for Generative Motion
PhyCo adds continuous physical control to video diffusion models via physics-supervised fine-tuning on a large simulation dataset and VLM-guided rewards, yielding measurable gains in physical realism on the Physics-IQ benchmark.
-
Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation
Mutual Forcing trains a single native autoregressive audio-video model with mutually reinforcing few-step and multi-step modes via self-distillation to match 50-step baselines at 4-8 steps.
-
ELT: Elastic Looped Transformers for Visual Generation
Elastic Looped Transformers share weights across recurrent blocks and apply intra-loop self-distillation to deliver 4x parameter reduction while matching competitive FID and FVD scores on ImageNet and UCF-101.
-
InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.
-
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
-
GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
GENSERVE improves SLO attainment by up to 44% for co-serving heterogeneous T2I and T2V diffusion workloads via step-level preemption, elastic parallelism, and joint scheduling.