PaperHub

Kyunghyun Cho

~Kyunghyun_Cho1

32
论文总数
16.0
年均投稿
5.9
平均评分
接收情况21/32
会议分布
ICLR
17
NeurIPS
13
COLM
1
ICML
1

发表论文 (32 篇)

202518

7.0
3

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

NeurIPS 2025Poster
4.7
3

Hyperparameters in Continual Learning: A Reality Check

ICLR 2025withdrawn
6.8
4

Efficient semantic uncertainty quantification in language models via diversity-steered sampling

NeurIPS 2025Poster
4.8
4

Hyperparameter Loss Surfaces Are Simple Near their Optima

COLM 2025Poster
6.4
5

Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models

NeurIPS 2025Poster
4.0
4

An Asymptotic Theory of Random Search for Hyperparameters in Deep Learning

ICLR 2025Rejected
5.5
4

Generating All-Atom Protein Structure from Sequence-Only Training Data

ICLR 2025Rejected
4.5
4

Generalizing to any diverse distribution: uniformity, gentle finetuning & rebalancing

ICLR 2025Rejected
7.8
4

Test Time Scaling for Neural Processes

NeurIPS 2025Poster
6.3
4

Aioli: A Unified Optimization Framework for Language Model Data Mixing

ICLR 2025Poster
6.0
4

Implicit Generative Property Enhancer

NeurIPS 2025Poster
7.3
4

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

NeurIPS 2025Poster
4.4
5

Molecular Active Learning: How can LLMs Help?

ICLR 2025withdrawn
6.6
5

Concept Bottleneck Language Models For Protein Design

ICLR 2025Poster
6.0
4

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

ICLR 2025Poster
5.5
4

Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks

ICML 2025Poster
5.3
4

Supervised Contrastive Block Disentanglement

ICLR 2025Rejected
7.0
3

AION-1: Omnimodal Foundation Model for Astronomical Sciences

NeurIPS 2025Poster

202414