pith. sign in
Pith Number

pith:CRZPAPKX

pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI
not attested not anchored not stored refs resolved

Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation

Calder Katyal, Chetwin Low, Weimin Wang

Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.

arxiv:2510.01284 v1 · 2025-09-30 · cs.MM · cs.CV · cs.SD · eess.AS

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CRZPAPKXJPOXLUEXGPFLJY3DFI}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

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.

C2weakest assumption

That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing.

C3one line summary

A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.

References

20 extracted · 20 resolved · 6 Pith anchors

[1] Seed-TTS: A Family of High-Quality Versatile Speech Generation Models · arXiv:2406.02430
[2] com/research/video-generation-models-as-world-simulators 2025
[3] HuMo: Human-centric video generation via collaborative multi-modal conditioning
[4] CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens · arXiv:2407.05407
[5] Ace-step: A step towards music generation foundation model.arXiv preprint arXiv:2506.00045

Formal links

2 machine-checked theorem links

Cited by

20 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:46.035192Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4

Aliases

arxiv: 2510.01284 · arxiv_version: 2510.01284v1 · doi: 10.48550/arxiv.2510.01284 · pith_short_12: CRZPAPKXJPOX · pith_short_16: CRZPAPKXJPOXLUEX · pith_short_8: CRZPAPKX
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876",
    "cross_cats_sorted": [
      "cs.CV",
      "cs.SD",
      "eess.AS"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.MM",
    "submitted_at": "2025-09-30T21:03:50Z",
    "title_canon_sha256": "eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.01284",
    "kind": "arxiv",
    "version": 1
  }
}