Presents multi-verifier framework and Adaptive Reward Weighting (ARW) for inference-time scaling in joint audio-video generation, reporting gains in alignment and synchronization on VGGSound and JavisBench-mini.
hub Canonical reference
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
Canonical reference. 89% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
89% of classified citations
abstract
Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hundreds of thousands of hours of raw audio, the audio tower learns to generate realistic sound effects, as well as speech that conveys rich speaker identity and emotion. Fusion is obtained by jointly training the identical video and audio towers via blockwise exchange of timing (via scaled-RoPE embeddings) and semantics (through bidirectional cross-attention) on a vast video corpus. Our model enables cinematic storytelling with natural speech and accurate, context-matched sound effects, producing movie-grade video clips. All the demos, code and model weights are published at https://aaxwaz.github.io/Ovi
hub tools
citation-role summary
background 8
method 1
citation-polarity summary
representative citing papers
NAVA proposes native audio-visual alignment via Align-then-Fuse MMDiT and Timbre-in-Context Conditioning for joint audio-video generation with improved synchronization and timbre control.
AVBench is a benchmark for human-centric AV generation evaluation featuring ten fine-grained dimensions and preference-learned evaluators that output continuous probabilistic scores from binary decisions.
InstructAV2AV is an end-to-end instruction-guided audio-video joint editing model that adapts a pre-trained backbone with gated attention and two-stage training, outperforming prior methods on 11 metrics after building the InsAVE-80K dataset.
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.
TMD-Bench is a multi-level benchmark that measures music-dance co-generation quality including beat-level rhythmic synchronization, supported by a new dataset and Music Captioner, and shows commercial models lag in rhythm while a new baseline performs competitively.
Hallo-Live achieves 20.38 FPS real-time text-to-audio-video avatar generation with 0.94s latency using asynchronous dual-stream diffusion and HP-DMD preference distillation, matching teacher model quality at 16x higher throughput.
Talker-T2AV achieves better lip-sync accuracy, video quality, and audio quality than dual-branch baselines by separating high-level shared autoregressive modeling from modality-specific low-level diffusion refinement in a joint audio-video generation framework.
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.
JUST-DUB-IT adapts a joint audio-visual diffusion model via LoRA to generate high-quality dubbed videos with translated audio and lip-synced facial motion.
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
AVI-Edit enables precise audio-synchronized instance-level video editing via a granularity-aware mask refiner, a self-feedback audio agent, and a new large-scale annotated dataset.
EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shape leakage.
MTAVG-Bench 2.0 is a new benchmark that evaluates omni LLMs on diagnosing high-level cinematic failures in multi-talker audio-video generation using a taxonomy of acting, narrative, atmosphere, and audio-visual language.
StreamChar decouples LLM-based orchestration from DiT denoising to achieve real-time long-horizon streaming character audio-video generation with reduced drift and misalignment.
SyncDPO improves temporal synchronization in video-audio joint generation using DPO with efficient on-the-fly negative sample construction and curriculum learning.
Unison presents a unified audio-video generation model that decouples speech and sound effects while using bidirectional forcing to synchronize with motion, claiming SOTA perceptual quality and alignment.
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.
OmniShow unifies text, image, audio, and pose conditions into an end-to-end model for high-quality human-object interaction video generation and introduces the HOIVG-Bench benchmark, claiming state-of-the-art results.
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
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.
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.
citing papers explorer
No citing papers match the current filters.