xzf-thu

The first Large Audio Language Model that enables native in-depth thinking, which is trained on large-scale audio Chain-of-Thought data.

First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**

Tsinghua speech recognition foundation model tuned for noisy, far-field, in-the-wild audio, claiming up to 30 percent lower WER than Whisper and Qwen3-ASR on hard clips.

Mini-Omni-Reasoner: a real-time speech reasoning framework that interleaves silent reasoning tokens with spoken response tokens (“thinking-in-speaking”), exploiting the LLM–audio throughput gap to keep speech fluent and low-latency while maintaining structured internal reasoning.

Towards Self-Evolving Proactive AI with Perpetual Memory

No description.

No description.

Bilingual Chinese and English benchmark of 5000 noisy real and synthetic audio clips with a Python toolkit to score ASR models like Whisper and Canary.

I'm Xie Zhifei

Measuring Massive-Computational Math Reasoning with Code in LLMs