Katherine Xu @KateYXu Twitter Profile

Katherine Xu

@KateYXu

PhD student @Penn @GRASPlab • @MIT CS '22 🤺 • Research Intern @AdobeResearch

17Posts 245Followers 972Following

Similar User

@SharonYixuanLi

@MinhyukSung

@dqj5182

@avinab_saha

@JiahuiLei1998

@AlbalakAlon

@weizeming25

@TheCamdar

@MeganJWei

@liyuan_zz

@SpyrosPavlatos

@EChatzipantazis

@aaditya_naik

@shreyahavaldar

@tuanlda78202

Pinned

Katherine Xu

@KateYXu

7 Apr

Excited to share our #CVPR2024 Highlight paper! 🌟 “Amodal Completion via Progressive Mixed Context Diffusion” Our method fully visualizes occluded objects using pretrained diffusion models (without finetuning!) by overcoming occlusion + co-occurrence k8xu.github.io/amodal

Katherine Xu Reposted

Katherine Xu

@KateYXu

17 Jun

Synthetic data has huge potential to drive new improvements in training and evaluation for computer vision. Interested in learning more about advancements and challenges? Join us at the SynData4CV Workshop at #CVPR2024 tomorrow (June 18)! syndata4cv.github.io

Jieyu Zhang

@JieyuZhang20

14 Jun

Calling all #CVPR2024 attendees! Join us at the SynData4CV Workshop at @CVPR (Jun 18 full day at Summit 423-425) to learn more about recent advancements in synthetic data! Explore more: syndata4cv.github.io

Katherine Xu Reposted

Katherine Xu

@KateYXu

18 Apr

What do you see in these images? These are called hybrid images, originally proposed by Aude Oliva et al. They change appearance depending on size or viewing distance, and are just one kind of perceptual illusion that our method, Factorized Diffusion, can make.

Katherine Xu

@KateYXu

3 Apr

Had a fun time attending NYC Computer Vision Day + sharing my work on Amodal Completion via Progressive Mixed Context Diffusion #CVPR2024 Project page: k8xu.github.io/amodal/ Event: cs.nyu.edu/~fouhey/NYCVis… Thank you to the organizers and sponsors! 🗽

Katherine Xu Reposted

Katherine Xu

@KateYXu

8 Dec

I’ll be at #NeurIPS2023 next week! Super excited to present our spotlight work, DreamSim, with @xkungfu . Come check out our poster (#127) on Wednesday morning, and please reach out if you want to chat about representation learning, synthetic data, and/or computer vision! (1/2)

Phillip Isola

@phillip_isola

16 Jun 2023

We’re releasing a new image similarity metric and dataset! --> DreamSim: a metric which outperforms LPIPS, CLIP, and DINO on similarity and retrieval tasks --> NIGHTS: a dataset of synthetic images with human similarity ratings paper+code+data: dreamsim-nights.github.io 1/n

Katherine Xu Reposted

Katherine Xu

@KateYXu

5 Dec

Brain🧠and Deep-nets🤖are massive black boxes, we don’t know how they work. Others use Deep-nets to explain the brain:🤖 ->🧠 We do the opposite:🧠->🤖 𝐁𝐫𝐚𝐢𝐧 𝐃𝐞𝐜𝐨𝐝𝐞𝐬 𝐃𝐞𝐞𝐩 𝐍𝐞𝐭𝐬 arxiv:arxiv.org/abs/2312.01280 webpage&video:huzeyann.github.io/brain-decodes-… read on 🧵

Katherine Xu Reposted

Katherine Xu

@KateYXu

17 Aug 2023

Check out our #ICCV2023 work "NeuS2" (vcai.mpi-inf.mpg.de/projects/NeuS2/), which reconstructs high-quality 3D geometry from multi-view images in <2 minutes. We derived a new analytical formula of the second-order derivatives for ReLU-based MLPs, leading to an efficient CUDA implementation.

Katherine Xu Reposted

Katherine Xu

@KateYXu

3 Aug 2023

0/. Brain is not ViT. we scored 70.8 in the Algonauts 2023 visual brain competition, w/o ensemble we can do 66.8 score. other teams (including me in the past) are struggling with 60. “memory” is the secret. paper: arxiv.org/abs/2308.01175 code&webpage: huzeyann.github.io/mem

Katherine Xu Reposted

Katherine Xu

@KateYXu

20 Jul 2023

In our #ICCV2023 paper, we find the existence of common features we call “Rosetta Neurons” across a variety of models with different architectures, sources of supervision. and training datasets. abs: arxiv.org/abs/2306.09346 proj: yossigandelsman.github.io/rosetta_neuron… 1/n