@subin_kim____ Profile picture

Subin Kim

@subin_kim____

Ph.D. student @kaist_ai

Similar User
Dongkeun Yoon photo

@dongkeun_yoon

Jinheon Baek photo

@jinheonbaek

Sangmin Bae photo

@raymin0223

Sihyun Yu photo

@sihyun_yu

Hyeon min Yun photo

@hyeonmin_Lona

Changyeon Kim photo

@cykim1006

Junsu Kim photo

@JunsuKim97

Sungnyun Kim photo

@kim_sungnyun

Hoyeon Chang photo

@hoyeon_chang

Jaehong Yoon photo

@jaeh0ng_yoon

Jaemin Yoo photo

@seeyoojm

Minki Kang photo

@mkkang_1133

Seonghyeon Ye photo

@SeonghyeonYe

Seokeon Choi photo

@SeokeonC

Junghyun Lee photo

@nick_jhlee

Subin Kim Reposted

Cool work from @JitengMu on image editing! This looks like the future of Photoshop! Just select a few patches and move it, and boom, you get the edited picture! This enables the new control ability of the diffusion model: Only change the part you want to change.…

We introduce🌟Editable Image Elements🥳, a new disentangled and controllable latent space for diffusion models, that allows for various image editing operations (e.g., move, resize,  de-occlusion, object removal, variations, composition) jitengmu.github.io/Editable_Image… More details🧵👇



Subin Kim Reposted

Official Demos: Hyper-SDXL-1Step-T2I huggingface.co/spaces/ByteDan… Hyper-SD15-Scribble huggingface.co/spaces/ByteDan… Unoffical Demos: InstantStyle + Hyper SD1.5 (not great but superfast) huggingface.co/spaces/radames… InstantStyle + Hyper SDXL huggingface.co/spaces/radames…


Subin Kim Reposted

Suppose that we train two INRs: One for a natural image, and another for its pixel-shuffled version. Which INR would fit faster? Expected: Natural Image Reality: Pixel-permuted image 🤯 (under some conditions) We look closer into when & why this happens in our #CVPR2024 oral.

Tweet Image 1

Subin Kim Reposted

We are organizing INRs for vision workshop at CVPR 2024! Please submit your awesome work related to INRs/neural fields 🙂

Call for Papers: #INRV2024 Workshop on Implicit Neural Representation for Vision @ #CVPR2024! Topics: Compression, Representation using INR’s for images, audio, video & more! Ddl: 3/31. Submit now! @CVPR Website: inrv.github.io Submission Link: shorturl.at/vzBR8



Subin Kim Reposted

Call for Papers: #INRV2024 Workshop on Implicit Neural Representation for Vision @ #CVPR2024! Topics: Compression, Representation using INR’s for images, audio, video & more! Ddl: 3/31. Submit now! @CVPR Website: inrv.github.io Submission Link: shorturl.at/vzBR8


Subin Kim Reposted

🙌 At #NeurIPS to present two papers Wed. 10AM: Efficient meta-learning / 5PM: Improving MAE with meta-learning. I am working on continual learning/efficiency/AutoML for LLMs! DM me if you are interested in chatting 👀 Also looking for an internship, welcome any recommendations

Tweet Image 1
Tweet Image 2

Subin Kim Reposted

Excited to share Adaptive Return-conditioned Policy (ARP): a return-conditioned policy utilizing adaptive multimodal reward from pre-trained CLIP encoders! ARP can mitigate goal misgeneralization and execute unseen text instructions! sites.google.com/view/2023arp 🧵👇 1/N


Subin Kim Reposted

colab for clip guided gaussian splatting: colab.research.google.com/drive/1YniEH63… cc @GKopanas :)


Subin Kim Reposted

Best Paper Award Honorable Mention at #3DV2019 Learned Multi-View Texture Super-resolution Audrey Richard; Ian Cherabier; Martin R. Oswald; Vagia Tsiminaki; Marc Pollefeys @mapo1; Konrad Schindler #TBThursday #3DV2024

Tweet Image 1

Subin Kim Reposted

I will present Multi-View Masked World Models (MV-MWM) for visual robotic manipulation. Please visit #ICML2023 poster session at 7/25 (Tue) 2:00-3:30pm!

MV-MWM is accepted to #ICML2023! We have updated the draft to include new exciting imitation learning results and have a new format. Please check the paper! arxiv.org/abs/2302.02408



Subin Kim Reposted

Imagine a 2D image serving as a window to a 3D world that you could reach into, manipulate objects, and see changes reflected in the image. In our new OBJect 3DIT work, we edit images in this 3D-aware fashion while only operating in the pixel space! 🧵

Tweet Image 1

Subin Kim Reposted

ResMatch: Residual Attention Learning for Local Feature Matching Yuxin Deng, Jiayi Ma tl;dr: descriptor similarity->cross-attention; relative position->self-attention arxiv.org/pdf/2307.05180…

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

Subin Kim Reposted

Collaborative Score Distillation for Consistent Visual Synthesis paper page: huggingface.co/papers/2307.04… Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when…


Subin Kim Reposted

🤔 Learning large-scale neural fields (NFs) requires a huge amount of memory and time to train… 💡I’m excited to share “Learning Large-scale Neural Fields via Context Pruned Meta-Learning”. Paper: arxiv.org/abs/2302.00617

Tweet Image 1

Subin Kim Reposted

"JPEG Compressed Images Can Bypass Protections Against AI Editing" Since neural nets are vulnerable to adversarial perturbations, you might hope that you could modify your image to resist AI image editing. But... [1/2]

Tweet Image 1

Subin Kim Reposted

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation code release is out github: github.com/csyxwei/ELITE @Gradio demo: huggingface.co/spaces/ELITE-l…

Tweet Image 1

Subin Kim Reposted

We are proud to introduce Wonder Studio. An AI tool that automatically animates, lights and composes CG characters into a live-action scene. No complicated 3D software, no expensive production hardware—all you need is a camera. Sign up for closed beta at wonderdynamics.com


Subin Kim Reposted

Can Hopper 🤖 agent learn multiple backflips without shaped rewards? Yes! 😆 Excited to share Preference Transformer (PT) that learns non-Markovian human preferences using Transformer architecture. sites.google.com/view/preferenc… 🧵 Thread 1/N


Subin Kim Reposted

Excited to share Video Probabilistic Diffusion Models in Projected Latent Space accepted to #CVPR2023 ! We train an autoencoder that “projects” each video to triplane latents, then train a diffusion model that learns the latent distribution. arxiv.org/abs/2302.07685 🧵 Thread


Subin Kim Reposted

Video Probabilistic Diffusion Models in Projected Latent Space abs: arxiv.org/abs/2302.07685 project page: sihyun.me/PVDM/


Loading...

Something went wrong.


Something went wrong.