PulseAugur
EN
LIVE 09:22:14

New AI method generates coherent co-speech motion over long sequences

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a new method for generating long-horizon co-speech motion, addressing the challenge of maintaining temporal coherence and style. The proposed approach, called PASPA, distinguishes between the past motion's style, which is compactly summarized, and the present segment's local dynamics, which are modeled with fine-grained attention. PASPA utilizes a persistent state for past history and bidirectional self-attention for the current segment, implemented within a blockwise flow matching framework. Experiments demonstrate that PASPA achieves state-of-the-art performance on public benchmarks and effectively preserves motion style over extended sequences. AI

IMPACT This method could improve the realism and coherence of AI-generated animations and virtual avatars in applications requiring synchronized speech and motion.

RANK_REASON The cluster contains a research paper detailing a new method for co-speech motion generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New AI method generates coherent co-speech motion over long sequences

How we ranked this

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper detailing a new method for co-speech motion generation. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Yi Liu, Xiangyue Zhang, Jianfang Li, Jia Ma, Yisheng He, Jianqiang Ren ·

    Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation

    arXiv:2610.32373v1 Announce Type: new Abstract: Co-speech motion generation remains challenging over long horizons due to the need for temporal coherence and consistent style. Existing methods typically generate long motions segment by segment, either conditioning on a short seed…

RELATED ENTITIES

RELATED TOPICS