Skip To Main Content
Eunho Yang on Muck Rack

Eunho Yang

As seen in: arXiv, IEEE
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Eunho Yang’s profile

Articles by Eunho Yang

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

|
By Soohyun Ryu, Sohee Kim Verified, Eunho Yang
| huggingface.co
Abstract Large vision-language models trained on synthetic block-manipulation tasks improve 3D spatial reasoning and generalize to real-world visual tasks. Large Vision-Language Models (LVLMs) have achieved strong performance on diverse visual tasks, yet their ability to reconstruct and reason about the 3D structure of the scene depicted in 2D images -- referred to as spatial intelligence -- remains limited.
Open in Who Shared Issue with article?

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

|
By Myeongho Jeon, Eunho Yang, Gyouk Chu
| huggingface.co
Abstract J-Zero enables self-improving language models across verifiable and unverifiable domains through adversarial co-evolution of a task generator, solver, and judge using predefined preference pairs. Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision.
Open in Who Shared Issue with article?

[2509.03025] Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens

|
By Joonhyung Park, Eunho Yang, Soohyun Ryu
| arXiv
Open in Who Shared Issue with article?

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

|
By Yoonjeon Kim, Hyun Ho Ryu, Eunho Yang, Chanjae Park
| arXiv
Work on one of the world's most important websites and make an impact on open science.
Open in Who Shared View Duplicates (699) Issue with article?

Deep Self-Supervised Diversity Promoting Learning on Hierarchical Hyperspheres for Regularization

|
By Youngsung Kim, Eunho Yang, Yoonsuk Hyun, Jae-Joon Han
| IEEE
The pursuit of improved generalization performance in machine learning has led to the widespread adoption of diversity-promoting learning techniques [1], [2]. In diversity-promoting learning, maximizing the pairwise distance between parameters can enhance their margin,1 which allows projective representation to exhibit the desired discriminative property.
Open in Who Shared Issue with article?

ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models

|
By Sung Ju, Wooseok Han, Sung Ju Hwang, Eunho Yang
| arXiv
arXiv:2305.13831 (cs) Download a PDF of the paper titled ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models, by Minki Kang and 3 other authors Download PDF Submission history From: Wooseok Han [ view email] [v1] Tue, 23 May 2023 08:52:00 UTC (648 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart...
Open in Who Shared View Duplicates (278) Issue with article?

Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation

|
By June Yong, Eunho Yang, Hajin Shim
| arXiv
[Submitted on 2 Dec 2021 ( v1 ), last revised 5 Jul 2023 (this version, v2)] Title:Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation Download a PDF of the paper titled Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation, by Yeonsung Jung and 3 other authors Download PDF Abstract: Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often...
Open in Who Shared Issue with article?
Show More