PaperHub

Sung Ju Hwang

~Sung_Ju_Hwang1

38
论文总数
19.0
年均投稿
5.9
平均评分
接收情况22/38
会议分布
ICLR
25
NeurIPS
11
ICML
2

发表论文 (38 篇)

202521

3.5
4

Preventing Unintended Memorization by Covering with Over-Memorization

ICLR 2025Rejected
5.5
4

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

ICLR 2025Rejected
5.5
4

Continuous Diffusion Model for Language Modeling

NeurIPS 2025Poster
8.9
4

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

ICML 2025Poster
6.4
4

System Prompt Optimization with Meta-Learning

NeurIPS 2025Poster
6.4
4

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

NeurIPS 2025Poster
6.8
4

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

NeurIPS 2025Poster
5.8
5

Understanding Dimensional Collapse in Cross-Modal Feature Distillation

ICLR 2025Rejected
7.3
4

Distilling LLM Agent into Small Models with Retrieval and Code Tools

NeurIPS 2025Spotlight
5.7
6

Automatic Jailbreaking of Text-to-Image Generative AI Systems for Copyright Infringement

ICLR 2025Rejected
6.1
4

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

ICML 2025Poster
4.0
4

Unified Multi-Modal Interleaved Document Representation for Information Retrieval

ICLR 2025withdrawn
-

Realistic World Model for Autonomous Driving: Integrating Physical Constraints and Multi-agent Interactions

ICLR 2025withdrawn
6.0
4

Training Free Exponential Context Extension via Cascading KV Cache

ICLR 2025Poster
4.8
5

Cost-Sensitive Multi-Fidelity Bayesian Optimization

ICLR 2025Rejected
7.0
5

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

ICLR 2025Poster
6.8
4

Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning

NeurIPS 2025Poster
6.0
5

Diffusion-based Neural Network Weights Generation

ICLR 2025Poster
7.3
4

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

NeurIPS 2025Poster
7.0
4

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

ICLR 2025Poster
6.3
4

A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention

ICLR 2025Poster

202417

4.8
4

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

NeurIPS 2024Poster
5.7
3

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

ICLR 2024Rejected
6.3
3

Drug Discovery with Dynamic Goal-aware Fragments

ICLR 2024Rejected
6.0
4

Targeted Model Inversion: Distilling Style Encoded in Predictions

ICLR 2024Rejected
4.8
4

Set-based Neural Network Encoding

ICLR 2024Rejected
6.3
4

Graph Generation with Destination-Predicting Diffusion Mixture

ICLR 2024Rejected
4.3
4

Learning Transferable Robust Representations for Few-shot Learning via Multi-view Consistency

ICLR 2024Rejected
5.3
3

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

ICLR 2024Rejected
6.7
3

SEA: Sparse Linear Attention with Estimated Attention Mask

ICLR 2024Poster
7.0
4

Progressive Fourier Neural Representation for Sequential Video Compilation

ICLR 2024Poster
5.8
4

Set-based Neural Network Encoding Without Weight Tying

NeurIPS 2024Poster
5.8
4

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

NeurIPS 2024Poster
5.6
5

Lifelong Audio-video Masked Autoencoder with Forget-robust Localized Alignments

ICLR 2024Rejected
4.8
4

Mixture-of-Experts in Prompt Optimization

ICLR 2024Rejected
6.0
4

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

NeurIPS 2024Poster
5.8
4

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

ICLR 2024Poster
6.2
5

Self-Supervised Dataset Distillation for Transfer Learning

ICLR 2024Poster