PaperHub

Mingyi Hong

~Mingyi_Hong1

27
论文总数
13.5
年均投稿
5.6
平均评分
接收情况18/27
会议分布
ICLR
14
NeurIPS
8
ICML
5

发表论文 (27 篇)

202516

7.5
4

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

ICLR 2025Oral
7.0
4

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction

ICLR 2025Poster
6.1
4

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization

ICML 2025Poster
5.5
4

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization

ICLR 2025Rejected
6.6
4

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

ICML 2025Poster
3.5
4

Policy optimization can be memory-efficient: LLM Alignment Through Successive Policy Re-weighting (SPR)

ICLR 2025Rejected
4.8
4

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

ICLR 2025Rejected
5.0
4

A Lazy Hessian Evaluation Framework for Accelerating Stochastic Bilevel Optimization

ICLR 2025Rejected
-

Unlearning as Multi-Task Optimization: a normalized gradient difference approach with adaptive learning rate

ICLR 2025withdrawn
5.5
4

RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models

ICML 2025Poster
4.5
4

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

ICLR 2025withdrawn
7.3
4

Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment

ICLR 2025Spotlight
5.5
5

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

ICML 2025Poster
5.5
4

Effectively Steer LLM To Follow Preference via Building Confident Directions

ICLR 2025Rejected
6.8
4

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

NeurIPS 2025Poster
5.5
3

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

ICML 2025Poster

202411