arXiv:2609.10317v1 Announce Type: new Abstract: Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite directio...
Real-time long-form avatar audio--video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas.
arXiv:2608.31106v1 Announce Type: new Abstract: Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We...
Encore is a new framework for generating long, synchronized audio‑video content. It splits the problem into local continuity, handled by iterative chunk‑wise synthesis with cross‑chunk context, and global consistency, enforced through reference audio‑video signals with shifted position embeddings. The Adaptive Signal Routing mechanism learns attention biases and residual scales to modulate the influence of each conditioning signal, enabling end‑to‑end joint audio‑video generation and infinite‑length inference.
Instruction-Based Video Editing by Repurposing an Image Editing Model demonstrates that a strong image‑editing model can be adapted to edit videos by operating on video‑VAE latents. The authors tile latent frames into a large virtual image, reuse the editor’s positional encoding, and bridge latent spaces with lightweight projections, fine‑tuning on Ditto‑1M editing triplets. Their experiments show that per‑frame video latents are close enough to the image domain that mature image‑editing priors transfer with minimal adaptation.
ViRDM is a new post‑training method for few‑step causal video generation that eliminates the need for a large teacher model and an online critic. By applying representation distribution matching (RDM) with a precomputed target distribution, a lightweight VAE decoder, and staged vector–Jacobian products, ViRDM overcomes memory, optimization, and temporal dynamics challenges. The approach reduces GPU memory usage and training time, achieving state‑of‑the‑art VBench performance with only 20 generator updates and 16 A100 GPU‑hours.
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.
arXiv:2609.24788v1 Announce Type: new Abstract: In this paper, we propose SVEET, a framework that requires merely training on a pretrained bidirectional video diffusion model but supports high-qualit...
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both...
StreamAV-Bench is the first comprehensive benchmark designed for streaming audio‑video generation, addressing the limitations of existing benchmarks that focus on completed sequences. It introduces a unified evaluation framework with a progressive track for instruction adherence and long‑horizon stability, and an interactive track for responsive interaction and state retention. The benchmark includes 32 fine‑grained, expert‑verified evaluation cases and evaluates 13 representative systems, revealing temporal drift in progressive generation and responsiveness bottlenecks in interactive control.
arXiv:2606. 25041v2 Announce Type: replace-cross Abstract: We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction.
The paper introduces Conditional Residual Prediction (CRP), a technique that reduces a causal video diffusion model’s dependence on past frames by having the model first predict the current frame without conditioning on history and then adding a residual based on the past. This approach allows training a causal model from an image‑model initialization without requiring a bidirectional teacher or complex distillation, and it nearly closes a 6.14‑point quality gap to a bidirectional model. Using CRP, the authors train Optica, a 2‑billion‑parameter causal video model that generates 5‑second 480p videos and achieves an 82.78 score on VBench with only about 15 million training videos.