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. 76% of citing Pith papers cite this work as background.
239
Pith papers citing it
Background
76% 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 61
method 9
baseline 7
dataset 1
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.
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video, plus a diffusion-based rendering module and extension to 4D feature fields.
Presents Decoupled Time Guidance (DTG) for training-free generative video super-resolution by temporally decoupling conditional and unconditional diffusion signals.
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
Aero-World adapts a pretrained latent diffusion transformer for action-conditioned aerial video generation by injecting inertial action tokens and using a frozen latent-space Physics Probe for inertial consistency supervision during LoRA finetuning, with a new AeroBench benchmark showing improved AA
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.
Echo-Forcing decouples stable anchors, compressed history, and recent dynamics in video diffusion KV caches using hierarchical memory, scene recall frames, and difference-aware decay to support interactive long video generation under bounded cache.
WorldVLN proposes the first autoregressive world action model for aerial vision-language navigation that predicts short-horizon latent world states, decodes them to waypoints in closed loop, and uses two-stage training with Action-aware GRPO to achieve over 12% success-rate gains on benchmarks plus零
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.
R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow 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 unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
ACWM-Phys is a controllable simulator benchmark with in- and out-of-distribution protocols for evaluating action-conditioned world models across rigid, kinematic, deformable, and particle dynamics.
citing papers explorer
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
-
Setting the Stage: Text-Driven Scene-Consistent Image Generation
A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
-
VABench: A Comprehensive Benchmark for Audio-Video Generation
VABench is a new multi-dimensional benchmark for evaluating synchronous audio-video generation across text-to-AV, image-to-AV, and stereo tasks.
-
GimbalDiffusion: Gravity-Aware Camera Control for Video Generation
GimbalDiffusion adds gravity-referenced absolute camera control and null-pitch conditioning to text-to-video diffusion models, trained on full-sphere panoramic data, to support extreme trajectories and reduce prompt entanglement.
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
-
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
-
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.
-
Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
Vid-Freeze immunizes images by adding perturbations that target attention dynamics in I2V models to enforce temporal freezing and suppress motion synthesis.
-
CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion
CamPVG is the first diffusion-based framework for generating geometrically consistent panoramic videos from camera pose inputs using a panoramic Plücker embedding and spherical epipolar attention module.
-
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
SVG2 accelerates DiT video generation via semantic-aware token permutation with k-means, achieving up to 2.3x speedup and PSNR of 30 while fixing position-based clustering and scattered-token waste.
-
DreamGen: Unlocking Generalization in Robot Learning through Video World Models
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
-
Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos
A generative model produces realistic and coherent 360 panoramic videos from in-the-wild perspective videos via curated online data and geometry-motion aware operations.
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
History-Guided Video Diffusion
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
-
DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
DriveLaW unifies video world modeling and trajectory planning by injecting video-generator latents into a diffusion planner, achieving SOTA video prediction and a new record on the NAVSIM planning benchmark.
-
GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
GeCo is a new geometry-based metric that produces dense maps of motion and structure inconsistencies in video generation by fusing residual motion and depth priors.
-
The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
KeyTailor improves video virtual try-on realism by using instruction-guided keyframes to enhance garment details and background integrity in DiT models without major architectural changes.
-
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
-
VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification
VHOI densifies sparse trajectories into color-encoded HOI mask sequences and conditions a fine-tuned video diffusion model on them to produce controllable human-object interaction videos, including full navigation sequences.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models
A new dataset and fine-tuned VLM detector/explainer called PhyDetEx shows that current T2V models still struggle to generate videos that obey physical laws, with open-source models performing worse.
-
IGen: Scalable Data Generation for Robot Learning from Open-World Images
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
-
SURF: Signature-Retained Fast Video Generation
SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.
-
Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
A new dataset with high-fidelity close-up garment images and full/close-up try-on videos plus the VGID metric enables better texture and structure preservation in high-resolution video virtual try-on.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
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.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
World-Env replaces physical robot interactions with a world model-based virtual environment and VLM-guided rewards to enable efficient RL post-training for VLA models, showing gains with only five demonstrations per task.
-
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
Genie Envisioner unifies robotic policy learning, simulation, and evaluation inside one instruction-conditioned video diffusion framework using GE-Base, GE-Act, and GE-Sim.
-
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
-
JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
JAM-Flow introduces a unified flow-matching model with a Multi-Modal Diffusion Transformer that jointly synthesizes facial motion and speech from text, audio, or motion inputs.
-
Test-Time Training Done Right
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback
NeuS-E is a post-generation refinement method that uses neuro-symbolic analysis of a formal video representation to detect and correct semantic and temporal inconsistencies in text-to-video outputs, improving prompt alignment by nearly 40%.
-
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
A zero-shot subject-driven video generation framework that decomposes the task into identity injection from 200K subject-image pairs and motion preservation from 4K arbitrary videos, trained in 288 A100 GPU hours on CogVideoX-5B to match prior performance at 1% compute.
-
SkyReels-V2: Infinite-length Film Generative Model
SkyReels-V2 produces infinite-length film videos via MLLM-based captioning, progressive pretraining, motion RL, and diffusion forcing with non-decreasing noise schedules.
-
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
-
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.
-
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
GR00T N1 is a new open VLA foundation model for humanoid robots that outperforms imitation learning baselines in simulation and shows strong performance on real-world bimanual manipulation tasks.
-
Improving Video Generation with Human Feedback
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
-
MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
MASS adds spatiotemporal motion signals and 3D grounding to VLMs and releases MASS-Bench, yielding physics-reasoning performance within 2% of Gemini-2.5-Flash after reinforcement fine-tuning.
-
Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
OASIS reduces redundancy in diffusion models for real-world video super-resolution via attention specialization routing and progressive training, delivering state-of-the-art quality with 6.2x faster inference than prior one-step baselines.
-
Matrix-game 2.0: An open-source real-time and streaming interactive world model
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
SynMotion combines disentangled semantic embeddings, parameter-efficient motion adapters, and alternate subject-motion training on a new SPV dataset to improve motion customization in text-to-video and image-to-video generation.
-
DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment
DriVerse is a generative model that simulates driving scenes from an image and trajectory using multimodal prompting and motion alignment, achieving better performance on nuScenes and Waymo datasets with minimal training.
-
World Simulation with Video Foundation Models for Physical AI
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.
-
Show-o2: Improved Native Unified Multimodal Models
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.
-
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.
-
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.