Jing Peng

Claim drift in automated research can lead to significant discrepancies, but Xcientist ensures that every generated mechanism remains accountable and traceable back to its evidential roots.

Compressing audio semantics into just 128 dimensions doesn't just reduce DiT modeling burden; it actually *improves* audio generation quality across diverse domains.

Over-reliance on agentic decomposition can actually *hurt* audio understanding when a strong audio frontend already provides sufficient information, highlighting the importance of conditional evidence acquisition.

ASR systems can now be more trustworthy: this work shows how to train them to abstain from transcribing uncertain segments, leading to more reliable outputs.

Forget expensive audio-text data collection: TASU2 lets you dial in the perfect amount of noise for training your speech LLM, all from text.