Multi-head Gaussian kernels inject temporal scale discrepancy as inductive bias to enable full-duplex talking-listening avatar generation, supported by a new decoupled VoxHear dataset and claimed SOTA naturalness.
Speakervid-5m: A large-scale high-quality dataset for audio-visual dyadic interactive human generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 4representative citing papers
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.
Synthetic data complements real data in diffusion-based controllable human video generation, with effective sample selection improving motion realism, temporal consistency, and identity preservation.
citing papers explorer
-
Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
Multi-head Gaussian kernels inject temporal scale discrepancy as inductive bias to enable full-duplex talking-listening avatar generation, supported by a new decoupled VoxHear dataset and claimed SOTA naturalness.
-
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.
-
Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation
Synthetic data complements real data in diffusion-based controllable human video generation, with effective sample selection improving motion realism, temporal consistency, and identity preservation.
- OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation