PaperHub
影响力指数
85.65/100
前 0.9%
全站排名 #564
发表论文40 篇
平均评分4.9
年均产出13.3 篇/年

Eunho Yang

Associate Professor@Korea Advanced Institute of Science & Technology·韩国·OpenReview
研究方向

Graphical models · Learning with sparsity · ML for Healthcare · Multitask Learning · Gaussian Process · Deep generative models

6.0
14

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

ICLR 2026Poster
通讯
6.0
22

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

ICLR 2026Poster
通讯
5.5
26

Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring

ICLR 2026Poster
通讯
5.3
15

Secure Inference for Diffusion Models via Unconditional Scores

ICLR 2026Poster
通讯
5.0
20

Faster Vision Transformers with Adaptive Patches

ICLR 2026Poster
5.0
5

Rethinking the High-Throughput LLM Inference: An Opportunity for Speculative Decoding

ICLR 2026Withdrawn
通讯
5.0
5

GridAR: Glimpse-and-Grow Test-Time Scaling for Autoregressive Image Generation

ICLR 2026Withdrawn
通讯
5.0
21

On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering

ICLR 2026Desk Rejected
4.7
15

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

ICLR 2026Rejected
通讯
4.5
12

Secure Autoregressive Inference with Prompt Separation via Key-Value Caching

ICLR 2026Rejected
三作
4.5
13

EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases

ICLR 2026Rejected
通讯
4.5
23

ReviewScore: Misinformed Peer Review Detection with Large Language Models

ICLR 2026Rejected
通讯
4.0
9

HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation

ICLR 2026Rejected
通讯
4.0
16

Co-Evolving Agents: Learning from Failures as Hard Negatives

ICLR 2026Rejected
通讯
3.7
7

Web Agents Are Still Greedy: Progress-Aware Action Generation and Selection via Meta-Plan

ICLR 2026Withdrawn
通讯
3.5
5

CaRE: Continual Real-time Unlearning with Ensured Preservation of LLM Knowledge

ICLR 2026Withdrawn
三作
3.5
15

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

ICLR 2026Withdrawn
通讯
2.5
5

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

ICLR 2026Withdrawn
三作
6.6
9

TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation

ICML 2025Spotlight
三作
6.5
24

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

ICLR 2025Poster
通讯
6.5
25

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

ICLR 2025Poster
通讯
6.3
35

REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

ICLR 2025Poster
通讯
6.0
22

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models

ICLR 2025Poster
5.7
23

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

ICLR 2025Poster
通讯
5.3
27

Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models

ICLR 2025Rejected
通讯
5.0
32

Don’t Discard, but Keep It Small: Context-Preserving KV Cache Compression with Importance-Aware Adaptive Precision

ICLR 2025Rejected
4.8
5

Playing the Fool: Jailbreaking Large Language Models with Out-of-Distribution Strategies

ICLR 2025Withdrawn
通讯
4.8
5

MeZO-A$^{3}$dam: Memory-efficient Zeroth-order Adam with Adaptivity Adjustments for Fine-tuning LLMs

ICLR 2025Withdrawn
通讯
4.3
9

Augmentation-Driven Metric for Balancing Preservation and Modification in Text-Guided Image Editing

ICLR 2025Withdrawn
通讯
3.8
5

Revised NTK Analysis of Optimization and Generalization with Its Extensions to Arbitrary Initialization

ICLR 2025Withdrawn
三作
3.0
8

Secure Diffusion Model Unlocked: Efficient Inference via Score Distillation

ICLR 2025Withdrawn
通讯
合作者 (20)