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
-
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.
-
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.
-
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Attention sparsity in video DiTs is an input-stable layer-wise property, enabling offline profiling and online bidirectional QK co-clustering for up to 1.93x speedup with PSNR up to 29 dB.
-
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
GeCO replaces time-dependent flow matching with time-unconditional optimization, enabling adaptive inference and intrinsic OOD detection for robotic imitation learning.
-
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.
-
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.
-
Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks
Fully aligned instructional videos for physical tasks yield 11.1% better completion quality and 15.5% faster times, with four decomposable visual attributes whose isolated misalignments degrade performance without users noticing.
-
Motion-Aware Caching for Efficient Autoregressive Video Generation
MotionCache accelerates autoregressive video generation up to 6.28x by motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on SkyReels-V2 and MAGI-1.
-
Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model
MV-VDP jointly predicts multi-view RGB and heatmap videos via diffusion to achieve data-efficient, robust robotic manipulation policies.
-
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Single-stage fine-tuning of a video model to generate actions as latent frames plus future states and values yields state-of-the-art robot policy performance on LIBERO, RoboCasa, and bimanual tasks.
-
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.
-
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.
-
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.
-
LTX-Video: Realtime Video Latent Diffusion
LTX-Video integrates Video-VAE and transformer for 1:192 latent compression and real-time video diffusion by moving patchifying to the VAE and letting the decoder finish denoising in pixel space.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)
The PhyScore challenge creates the first benchmark requiring metrics to jointly score video quality, physical realism, condition alignment, and temporal consistency while localizing physical anomalies in 1554 videos from seven generative models across text-to-2D, image-to-4D, and video-to-4D tracks.