Teahose.
SIGN IN
NEW HERE — WHAT TEAHOSE DOES
We read the entire AI & tech firehose — so you don't have to.
PODPodcastsAll-In, No Priors, Acquired…
NEWNewslettersStratechery, Newcomer…
PAPPapersPhysical AI research
PHProduct Huntdaily launches
VCInvestor ScoutSequoia, a16z, Benchmark…
CLAUDE DISTILLS →
7 reads, 30 sec each — free, 6 AM ET.
+ a live graph of the companies, people & themes underneath.
HOME/PEOPLE/YIJIE ZHU
// PERSON

Yijie Zhu

ROLE LEAD AUTHORAT HARBIN INSTITUTE OF TECHNOLOGYMENTIONS 6LAST SEEN MAY 4, 2026
// BIO

Yijie Zhu is a graduate researcher at Harbin Institute of Technology, Shenzhen, also affiliated with Great Bay University in Dongguan, China. He is best known as the lead author of ΔVLA, a prior-guided vision-language-action framework for robotic manipulation published on arXiv in March 2026, which models world-knowledge variations relative to an explicit current-world prior to improve long-horizon task performance. His research centers on multimodal large language models and embodied AI, with a focus on unifying perception, reasoning, and control for real-world robot systems.

// RECENT MENTIONS
// SIGNALS
6 SIGNALS
01
product·arXiv Physical AI·MAY 4, 2026

Instead of predying what the future looks like, ΔVLA predicts how the world changes — and that shift in framing delivers state-of-the-art manipulation performance at 3x faster training speed than comparable approaches.

Source
02
mention·arXiv Physical AI·MAY 4, 2026

The quality of an action is determined by the variation it induces rather than the absolute future state... modeling variation has long been a standard technique in many areas, as emphasizing differences can stabilize prediction and highlight transitions.

Source
03
mention·arXiv Physical AI·MAY 4, 2026

ΔVLA attains an average success rate of 72% on Galaxea R1 Lite and 69% on AgileX Cobot Magic... DreamVLA: 53% and 49% respectively.

Source
04
mention·arXiv Physical AI·MAY 4, 2026

For simulation, we build on OpenVLA as the backbone... fine-tuned using Low-Rank Adaptation (LoRA) with rank 32.

Source
05
mention·arXiv Physical AI·MAY 4, 2026

Inspired by Genie, we propose the Latent World Variation Quantization (LWVQ) module to encode world-knowledge variations in a fully unsupervised manner.

Source
06
mention·arXiv Physical AI·MAY 4, 2026

π₀ [RSS'25]: 94.2% LIBERO average, 67.4% RoboTwin 2.0 average

Source

AI-extracted from podcast / newsletter / paper summaries. May contain errors.