# Is TaoMate-HD Preview SOTA?

Pending benchmarks. Announced Nov 2, 2026; no independent results yet.

As of Nov 22, 2026, TaoMate-HD Preview is pending benchmarks on isitsota: announced Nov 2, 2026, with no independent results on the boards we track yet.

Alibaba TaoLive AIGC team's streaming audio-video model: speech and high-resolution video are generated together in short chunks, two coarse 480p steps then one 768p step each. Preview LoRA weights on MiniMax H3 FL2VA, with inference code.

Canonical: https://isitsota.com/m/taomate-hd-preview
Last updated: 2026-11-03
Tracking since: 2026-11-03

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Alibaba / Qwen |
| Announced | Nov 2, 2026 |
| API | Not yet · None; self-hosted |
| Open weights | Published · Preview LoRA on Hugging Face TaoLiveAIGC/TaoMate-HD-preview, not gated; code at github.com/TaoLiveAIGC/TaoMate-HD |
| Parameters | LoRA adapter, r=128 (620,232,704 F32 parameters); requires the MiniMax H3 FL2VA base model |
| Type | Progressive-resolution autoregressive audio-video generation (joint speech and video, streamed chunk by chunk) |
| Team | Alibaba TaoLive AIGC Team |
| Base model | MiniMax H3 FL2VA (MiniMaxAI/MiniMax-H3, FL2VA folder), downloaded separately |
| Method | Each chunk takes two denoising steps at 480p for coarse structure and one at 768p for detail, with audio generated throughout; each stage keeps its own audio-video history for the next chunk |
| Output | 768x1376 example at 24 FPS with 32 kHz stereo audio; prompts cover five-second windows and can be continued with new dialogue |
| Hardware | Inference code targets eight GPUs (serial or pipelined accelerated mode); the 10-second example was run on eight H20 96 GB GPUs |
| License | MiniMax H3 Community License Agreement, covering base and adapter (card license: other) |
| Paper | arXiv 2611.03394, v1 Nov 2, 2026 |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: progressive resolution is 1.60x faster than direct 768p generation with matched BF16/SDPA execution, including audio-video decoding.
- Lab claim: the optimized eight-GPU deployment adds a further 1.92x over serial progressive generation on H20 GPUs.
- Lab claim: continuation training lowers character error rate from 30.75% to 19.57% (11.18 points), and the paper demonstrates hour-long audio-video streams.

## Sources

- PAPER: [TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation (arXiv 2611.03394)](https://arxiv.org/abs/2611.03394) (2026-11-02)
- LAB: [TaoMate-HD project page](https://taoliveaigc.github.io/TaoMate-HD/) (2026-11-03)
- REPO: [TaoLiveAIGC/TaoMate-HD-preview on Hugging Face](https://huggingface.co/TaoLiveAIGC/TaoMate-HD-preview)
- REPO: [TaoLiveAIGC/TaoMate-HD on GitHub](https://github.com/TaoLiveAIGC/TaoMate-HD)

Tracking continues until an independent board lists it.

## Related

- Lab: [Alibaba / Qwen](https://isitsota.com/labs/alibaba.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/taomate-hd-preview
