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.
hub Canonical reference
Wan-s2v: Audio-driven cinematic video generation
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
fields
cs.CV 19roles
background 6polarities
background 6representative citing papers
ReFree-S2V applies multilevel speech guidance and reward-free reinforcement learning inside a flow-matching model built on a pretrained video generator to improve lip synchronization and natural expressivity in talking-head videos.
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
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.
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
StreamChar decouples LLM-based orchestration from DiT denoising to achieve real-time long-horizon streaming character audio-video generation with reduced drift and misalignment.
VidSplat iteratively synthesizes novel views with geometry-guided video diffusion to enable robust Gaussian splatting reconstruction from sparse or single-image inputs.
TAVR generates high-fidelity talking avatars from cross-scene video references via token selection and three-stage training (same-scene pretraining, cross-scene fine-tuning, identity RL), outperforming baselines on a new 158-pair benchmark.
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.
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.
Omni-Customizer proposes an end-to-end framework using Omni-Context Fusion, Masked TTS Cross-Attention, Semantic-Anchored Multimodal RoPE, and specialized training curricula to achieve precise multimodal identity binding in joint audio-video generation.
Tora3 uses shared object trajectories as kinematic priors to jointly guide visual motion and acoustic events in audio-video generation, improving realism and synchronization.
AUHead uses audio-language models to generate Action Unit sequences from speech and feeds them into a controllable diffusion model to synthesize realistic emotional talking-head videos.
LTX-2 generates high-quality synchronized audiovisual content from text prompts via an asymmetric 14B-video / 5B-audio dual-stream transformer with cross-attention and modality-aware guidance.
EchoTorrent combines multi-teacher distillation, adaptive CFG calibration, hybrid long-tail forcing, and VAE decoder refinement to enable few-pass autoregressive streaming video generation with improved temporal consistency and audio-lip sync.
LongCat-Video-Avatar 1.5 delivers an engineering-focused upgrade to audio-driven video generation with claimed competitive performance against closed-source systems on a 500-case benchmark.
citing papers explorer
-
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data
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.
-
ReFree: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
ReFree-S2V applies multilevel speech guidance and reward-free reinforcement learning inside a flow-matching model built on a pretrained video generator to improve lip synchronization and natural expressivity in talking-head videos.
-
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
-
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.
-
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
-
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
-
StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration
StreamChar decouples LLM-based orchestration from DiT denoising to achieve real-time long-horizon streaming character audio-video generation with reduced drift and misalignment.
-
VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
VidSplat iteratively synthesizes novel views with geometry-guided video diffusion to enable robust Gaussian splatting reconstruction from sparse or single-image inputs.
-
Generate Your Talking Avatar from Video Reference
TAVR generates high-fidelity talking avatars from cross-scene video references via token selection and three-stage training (same-scene pretraining, cross-scene fine-tuning, identity RL), outperforming baselines on a new 158-pair 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.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
LPM 1.0: Video-based Character Performance Model
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.
-
Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
Omni-Customizer proposes an end-to-end framework using Omni-Context Fusion, Masked TTS Cross-Attention, Semantic-Anchored Multimodal RoPE, and specialized training curricula to achieve precise multimodal identity binding in joint audio-video generation.
-
Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
Tora3 uses shared object trajectories as kinematic priors to jointly guide visual motion and acoustic events in audio-video generation, improving realism and synchronization.
-
AUHead: Realistic Emotional Talking Head Generation via Action Units Control
AUHead uses audio-language models to generate Action Unit sequences from speech and feeds them into a controllable diffusion model to synthesize realistic emotional talking-head videos.
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
LTX-2 generates high-quality synchronized audiovisual content from text prompts via an asymmetric 14B-video / 5B-audio dual-stream transformer with cross-attention and modality-aware guidance.
-
EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation
EchoTorrent combines multi-teacher distillation, adaptive CFG calibration, hybrid long-tail forcing, and VAE decoder refinement to enable few-pass autoregressive streaming video generation with improved temporal consistency and audio-lip sync.
-
LongCat-Video-Avatar 1.5 Technical Report
LongCat-Video-Avatar 1.5 delivers an engineering-focused upgrade to audio-driven video generation with claimed competitive performance against closed-source systems on a 500-case benchmark.