Alibaba just released Qwen3.8-LiveTranslate, a real-time interpretation model that cuts average latency to 2.3 seconds across 60 languages. It reconstructs speech into an interleaved audio-text stream and clones speakers' voices so translations sound just like them, making everyday bilingual meetings far less clunky.
Alibaba's Wan team just open-sourced Wan-Dancer-14B, a video model that turns audio tracks and a single image into rhythm-synced, minute-scale dance videos. Unlike tools requiring reference choreography videos, it plans long-range choreography directly from music context across genres like hip-hop and classical. Why it matters: Long-form music-to-motion generation just got a massive open-source leap.
Alibaba researchers just introduced StreamChar, a framework that generates synchronized character audio and video in real time on a single H100 GPU. By decoupling long-horizon planning from short-window denoising, it prevents visual drift and lip-sync lag, bringing responsive, full-body AI avatars closer to live interactive applications.
Alibaba just introduced Continuous-Time Distribution Matching (CDM), a distillation technique that accelerates image diffusion models down to 4 sampling steps. Unlike predecessors like DMD2 that often produce waxy, over-smoothed results, CDM preserves fine details without complex auxiliary reward models. It brings near real-time, high-fidelity generation to standard GPUs.
