AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
super hub Canonical reference
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
Canonical reference. 78% of citing Pith papers cite this work as background.
123
Pith papers citing it
Background
78% of classified citations
abstract
We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels. Previous video generation models often had limited movement and short durations, and is difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we propose a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions, to improve both compression rate and video fidelity. Second, to improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing a progressive training and multi-resolution frame pack technique, CogVideoX is adept at producing coherent, long-duration, different shape videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method, greatly contributing to the generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of both 3D Causal VAE, Video caption model and CogVideoX are publicly available at https://github.com/THUDM/CogVideo.
hub tools
citation-role summary
background 7
baseline 2
citation-polarity summary
claims ledger
- abstract We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels. Previous video generation models often had limited movement and short durations, and is difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we propose a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions, to improve both compression rate and v
authors
co-cited works
representative citing papers
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
ViPS distills a compact, controllable distribution of valid joint configurations for any auto-rigged mesh from video diffusion priors, matching 4D-trained methods in plausibility while generalizing zero-shot to unseen species and skeletal topologies.
EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.
HASTE delivers up to 1.93x speedup on Wan2.1 video DiTs via head-wise adaptive sparse attention using temporal mask reuse and error-guided per-head calibration while preserving video quality.
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
HorizonDrive enables stable long-horizon autoregressive driving simulation via anti-drifting teacher training with scheduled rollout recovery and teacher rollout distillation.
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
OphEdit enables text-guided editing of eye surgery videos without training by injecting preserved attention value tensors into the diffusion denoising process to maintain anatomical structure.
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.
Presents the first large-scale benchmark for multi-frame geometric distortion removal in videos under severe refractive warping, using real and synthetic data across four distortion levels and evaluating classical and learning-based methods including a proposed diffusion-based V-cache.
Stream-R1 improves distillation of autoregressive streaming video diffusion models by adaptively weighting supervision with a reward model at both rollout and per-pixel levels.
AniMatrix generates anime videos by structuring artistic production rules into a controllable taxonomy and training the model to prioritize those rules over physical realism, achieving top scores from professional animators on prompt understanding and artistic motion.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
YOSE accelerates DiT video object removal up to 2.5x by using BVI for adaptive token selection and DiffSim to simulate unmasked token effects, while preserving visual quality.
OmniShotCut treats shot boundary detection as structured relational prediction via a shot-query Transformer, uses fully synthetic transitions for training data, and releases OmniShotCutBench for evaluation.
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
citing papers explorer
-
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
-
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
-
ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes
ViPS distills a compact, controllable distribution of valid joint configurations for any auto-rigged mesh from video diffusion priors, matching 4D-trained methods in plausibility while generalizing zero-shot to unseen species and skeletal topologies.
-
EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
EntityBench is a new benchmark with detailed per-shot entity schedules from real media, and the EntityMem baseline using persistent per-entity memory achieves the highest character fidelity with Cohen's d of +2.33.
-
HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention
HASTE delivers up to 1.93x speedup on Wan2.1 video DiTs via head-wise adaptive sparse attention using temporal mask reuse and error-guided per-head calibration while preserving video quality.
-
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
-
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.
-
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
-
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
HorizonDrive enables stable long-horizon autoregressive driving simulation via anti-drifting teacher training with scheduled rollout recovery and teacher rollout distillation.
-
From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
-
OphEdit: Training-Free Text-Guided Editing of Ophthalmic Surgical Videos
OphEdit enables text-guided editing of eye surgery videos without training by injecting preserved attention value tensors into the diffusion denoising process to maintain anatomical structure.
-
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.
-
A unified Benchmark for Multi-Frame Image Restoration under Severe Refractive Warping
Presents the first large-scale benchmark for multi-frame geometric distortion removal in videos under severe refractive warping, using real and synthetic data across four distortion levels and evaluating classical and learning-based methods including a proposed diffusion-based V-cache.
-
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Stream-R1 improves distillation of autoregressive streaming video diffusion models by adaptively weighting supervision with a reward model at both rollout and per-pixel levels.
-
AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics
AniMatrix generates anime videos by structuring artistic production rules into a controllable taxonomy and training the model to prioritize those rules over physical realism, achieving top scores from professional animators on prompt understanding and artistic motion.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal
YOSE accelerates DiT video object removal up to 2.5x by using BVI for adaptive token selection and DiffSim to simulate unmasked token effects, while preserving visual quality.
-
OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
OmniShotCut treats shot boundary detection as structured relational prediction via a shot-query Transformer, uses fully synthetic transitions for training data, and releases OmniShotCutBench for evaluation.
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
Latent Space Probing for Adult Content Detection in Video Generative Models
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
-
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.
-
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
-
HumanScore: Benchmarking Human Motions in Generated Videos
HumanScore defines six metrics for kinematic plausibility, temporal stability, and biomechanical consistency to benchmark human motions in videos from thirteen state-of-the-art generation models, revealing gaps between visual appeal and physical fidelity.
-
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.
-
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
UniGeo unifies geometric guidance across three levels in video models to reduce geometric drift and improve consistency in camera-controllable image editing.
-
DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos
DreamStereo uses GAPW, PBDP, and SASI to enable real-time stereo video inpainting at 25 FPS for HD videos by reducing over 70% redundant computation while maintaining quality.
-
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.
-
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
-
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
Prompt Relay is an inference-time plug-and-play method that penalizes cross-attention to enforce temporal prompt alignment and reduce semantic entanglement in multi-event video generation.
-
CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
-
Novel View Synthesis as Video Completion
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
-
DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioning
DiV-INR integrates implicit neural representations as conditioning signals for diffusion models to achieve better perceptual quality than HEVC, VVC, and prior neural codecs at extremely low bitrates under 0.05 bpp.
-
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
-
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.
-
Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressive video synthesis.
-
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
-
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.
-
UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining
UENR-600K is a 600,000-frame synthetic dataset for nighttime video deraining that uses 3D rain particle simulation in Unreal Engine to enable better generalization to real scenes.
-
Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
SCOPE accelerates autoregressive video diffusion up to 4.73x by using a tri-modal cache-predict-recompute scheduler with Taylor extrapolation and selective active-frame computation while preserving output quality.
-
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics.
-
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Warp-as-History enables zero-shot camera trajectory following in frozen video models by supplying camera-warped pseudo-history, with single-video LoRA fine-tuning improving generalization to unseen videos.
-
Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
CineNeuron improves fMRI-to-video reconstruction by combining bottom-up semantic enrichment with top-down Mixture-of-Memories integration and outperforms prior methods on benchmarks.
-
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.
-
RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
-
Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation
Pyramid Forcing classifies attention heads into Anchor, Wave, and Veil types and applies type-specific KV cache policies to improve long-horizon autoregressive video generation quality.
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
V2V-Zero adapts frozen VLMs for visual conditioning via hidden states from specification pages, scoring 0.85 on GenEval and 32.7 on a new seven-task benchmark while revealing capability hierarchies in attribute binding and structural control.
-
PresentAgent-2: Towards Generalist Multimodal Presentation Agents
PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.