Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
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.
314
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
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
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.
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
MemLearner introduces a learning-based adaptive context query method using query tokens in video world models to improve long-term scene consistency over rule-based retrieval.
Introduces CIPE-Dance as the largest dance video dataset and OmniDance framework for unified text-music multimodal dance video generation achieving SOTA on TI2V, MI2V, and MTI2V tasks.
DRIVE-CHOREO uses three LLM agents to create a unified position-aware token sequence co-compressed with multi-view video, achieving SOTA BEV mAP of 21.6 and +2.4 NDS improvement on nuScenes.
Introduces PexelsCustom-1M dataset, CustoMDiT parameter-efficient model, and OpenCustom benchmark for open-domain customized video generation.
FadeMem introduces distance-aware KV memory consolidation for autoregressive video diffusion that builds a temporal hierarchy with power-law merging to preserve short-term dynamics and long-range coherence under fixed cache budget.
OmniTryOn performs multi-object video virtual try-on in one pass using first-frame wearable caching and spatiotemporal RoPE, outperforming single-garment baselines on a new TryAny-Bench dataset.
LA-LQR applies latent-space linear-quadratic regulator control to steer text-to-video model activations toward desired features while penalizing excessive changes.
DCVC-UF uses chunk-based joint encoding and parallel frame-specific decoding to deliver ultra-fast neural video compression while claiming new state-of-the-art rate-distortion performance.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
SPAWN enables training-free insertion of custom visual concepts into autoregressive world models by swapping the pinned context-memory anchor over a short injection window.
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
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.
What-If World is a new paired-prompt benchmark showing that nine state-of-the-art video generation models achieve at most 52% on causal intervention tests and cluster near 28% for open-source systems.
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
citing papers explorer
-
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.
-
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
-
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
L2P trains per-timestep linear weights on feature trajectories in about 20 seconds to enable aggressive caching in DiT models, delivering up to 4.55x FLOPs reduction with maintained visual quality.
-
MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
-
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.
-
HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation
HuM-Eval evaluates human motion videos with a coarse-to-fine approach using VLM global checks plus 2D pose and 3D motion analysis, reaching 58.2% average correlation with human judgments and introducing a 1000-prompt benchmark.
-
PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics
PhysLayer is a framework that decomposes images into depth layers, simulates physics with depth awareness, and synthesizes videos guided by language for more plausible animations.
-
BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors
BurstGP enhances raw burst image super-resolution by integrating pretrained video diffusion priors through a multiframe-aware model, degradation-aware conditioning, and color-space conversion, outperforming prior methods on perceptual metrics.
-
DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
DynamicRad achieves 1.7x-2.5x inference speedups in long video diffusion with over 80% sparsity by grounding adaptive selection in a radial locality prior, using dual-mode static/dynamic strategies and offline BO with a semantic motion router.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
-
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
-
Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.
-
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
DreamShot uses video diffusion priors and a role-attention consistency loss to produce coherent, personalized storyboards with better character and scene continuity than text-to-image methods.
-
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
RTR-DiT distills a bidirectional DiT teacher into an autoregressive few-step model using Self Forcing and Distribution Matching Distillation, plus a reference-preserving KV cache, to enable stable real-time text- and reference-guided video stylization.
-
VibeFlow: Versatile Video Chroma-Lux Editing through Self-Supervised Learning
VibeFlow performs versatile video chroma-lux editing in zero-shot fashion by self-supervised disentanglement of structure and color-illumination cues inside pre-trained video models, plus residual velocity fields and consistency regularization.
-
Generative Refinement Networks for Visual Synthesis
GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.
-
HDR Video Generation via Latent Alignment with Logarithmic Encoding
HDR video generation is achieved by logarithmically encoding HDR imagery to align with pretrained generative model latents, enabling minimal fine-tuning and degradation-based inference of missing content.
-
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
A 64x temporally compressed motion embedding learned from trackers enables efficient conditional flow-matching generation of long-term motions that outperform video models and task-specific methods.
-
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Re2Pix decomposes video prediction into semantic feature forecasting followed by representation-conditioned diffusion synthesis, with nested dropout and mixed supervision to handle prediction errors.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
Latent-Compressed Variational Autoencoder for Video Diffusion Models
A frequency-based latent compression method for video VAEs yields higher reconstruction quality than channel-reduction baselines at fixed compression ratios.
-
VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
VGA-Bench creates a three-tier taxonomy, 1,016-prompt dataset of 60k+ videos, and three multi-task neural models (VAQA-Net, VTag-Net, VGQA-Net) that align with human judgments for video aesthetics and generation quality.
-
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
DiffHDR converts LDR videos to HDR by formulating the task as generative radiance inpainting in a video diffusion model's latent space, using Log-Gamma encoding and synthesized training data to achieve better fidelity and stability than prior methods.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
-
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.
-
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
SynthForensics is a people-centric benchmark where face-based detectors lose 13-55 AUC points on modern synthetic videos compared to legacy manipulation sets.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.