Pinned
We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026
Project Page: denghilbert.github.io/selfi
youming.deng
@denghilbert
CS Ph.D. Student @Cornell | a fan of @ChipotleTweets | Previous Visiting @EPFL and @ucmerced | B.Eng. @WHU_1893
- Amazing work🥳🥳Today, we’re introducing [schema]: a harness reaching 99% RHAE with Opus 4.8 + Fable 5 and 95.35% with GPT-5.6 Sol on ARC-AGI-3 Public set. [schema] makes an LLM think like a physicist. 🧵
- bunch of bullshitYesterday, I was giving an intro talk to our dept's new PhD students. Technical things aside, my number 1 suggestion has remained the same over the years: Treat your PhD like a job. - Avoid 1.5h lunch and three tea breaks. - Avoid gossiping and loitering at work. - Lab at 9 am
- Super cool. Self-improving makes model better and better!Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.
- Our paper was selected as an oral presentation in #CVPR2026We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026 Project Page: denghilbert.github.io/selfi
