Yucheng Mao

@_OutofMemory_ 👍👍👍

🤖Co-training is everywhere (sim↔real[e.g. GR00T, LBM], human↔robot[e.g. PI, EgoScale], even non-robot data[e.g. PI, LBM). But why does it work? How can we improve it further? Taking sim-and-real imitation learning in diffusion/ flow-based models as the test bed, we performed a rigorous mechanistic analysis, drawing on theoretical insights and multi-layered experiments. 😮Key insight: it’s all about representations. - Alignment → enables transfer - Discernibility → enables adaptation ⚖️Both are necessary — it's better to have more aligned representations, but the model must be able to discern the domains. We term this as structured representation alignment. ⬇️Let’s take a deep dive into that: Paper: arxiv.org/pdf/2604.13645 Website: science-of-co-training.github.io

Sharing our #CVPR2025 paper: "GPS as a Control Signal for Image Generation"! 🛰️+✍️ We turn the GPS tag stored in EXIF of photos into a control signal for diffusion models—so they don’t just know what you asked for, but where you want it to look like. Come to see our poster at Friday 13 Jun 10:30 a.m. — 12:30 p.m. (CT) in ExHall D, Poster #250.

@CVPR @ShingHoLin77 @Qi12Tom @aliathar94 @_vztu Is there any possibility that we can get the result within 2 hours?

@ShingHoLin77 @Qi12Tom @aliathar94 @_vztu When we hear anything here at #CVPR2025 social media central we’ll let you all know.

😟Hey friends, star/reply to this tweet if you're also waiting for @CVPR decisions

@SimianLuo solid!