PaperHub

Sungroh Yoon

~Sungroh_Yoon1

21
论文总数
10.5
年均投稿
5.5
平均评分
接收情况12/21
会议分布
ICLR
12
NeurIPS
6
ICML
3

发表论文 (21 篇)

20258 篇

6.6
4

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models

ICML 2025Poster
5.8
4

Balancing Gradient Frequencies Facilitates Inductive Inference in Algorithmic Reasoning

ICLR 2025Rejected
7.3
4

Interpretable Next-token Prediction via the Generalized Induction Head

NeurIPS 2025Poster
3.8
5

Enhancing Factuality in Detailed Image Captioning with LLM-MLLM Collaboration

ICLR 2025Rejected
6.8
4

Interpretable Language Modeling via Induction-head Ngram Models

ICLR 2025Rejected
6.6
4

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

ICML 2025Poster
4.9
4

Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

ICML 2025Poster
6.4
4

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

NeurIPS 2025Poster

202413 篇

4.0
4

Revisiting the Lottery Ticket Hypothesis for Pre-trained Networks

ICLR 2024withdrawn
4.5
4

Reduce, Reuse, and Recycle: Navigating Test-Time Adaptation with OOD-Contaminated Streams

ICLR 2024Rejected
6.3
4

SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation

ICLR 2024Poster
5.3
3

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization

NeurIPS 2024Poster
4.0
3

Robust Self-supervised Learning in Heterogeneous Graph Based on Feature-Topology Balancing

ICLR 2024Rejected
5.3
3

Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting

NeurIPS 2024Poster
4.8
4

ProtoReg: Prioritizing Discriminative Information for Fine-grained Transfer Learning

ICLR 2024Rejected
3.0
4

Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection

ICLR 2024withdrawn
4.6
5

Prototypical Influence Function for Fully Test-time Adaptation

ICLR 2024Rejected
6.3
4

DAFA: Distance-Aware Fair Adversarial Training

ICLR 2024Poster
6.0
4

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection

NeurIPS 2024Poster
7.0
4

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors

ICLR 2024Spotlight
6.3
3

Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation

NeurIPS 2024Poster
合作者 (20)