Ming Jin
~Ming_Jin2
17
论文总数
8.5
年均投稿
平均评分
接收情况11/17
会议分布
ICLR
9
NeurIPS
6
ICML
2
发表论文 (17 篇)
202512 篇
4
Data-Centric Human Preference Optimization with Rationales
ICLR 2025Rejected
5
LLMs Can Plan Only If We Tell Them
ICLR 2025Poster
4
Actions Speak Louder Than States: Going Beyond Bayesian Inference in In-Context Reinforcement Learning
ICLR 2025Rejected
4
Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL
NeurIPS 2025Poster
4
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
ICLR 2025Poster
4
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
ICML 2025Poster
4
A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
ICLR 2025Poster
4
Probing Hidden Knowledge Holes in Unlearned LLMs
NeurIPS 2025Poster
4
Reinforcement Learning with Backtracking Feedback
NeurIPS 2025Poster
4
LLM Spark: Critical Thinking Evaluation of Large Language Models
ICLR 2025Rejected
4
LLMs Can Reason Faster Only If We Let Them
ICML 2025Poster
4
Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
ICLR 2025Rejected
20245 篇
3
Teaching LLMs to Teach Themselves Better Instructions via Reinforcement Learning
ICLR 2024withdrawn
4
Data-Centric Defense: Shaping Loss Landscape with Augmentations to Counter Model Inversion
ICLR 2024withdrawn
4
Fairness-Aware Meta-Learning via Nash Bargaining
NeurIPS 2024Poster
4
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
NeurIPS 2024Poster
4
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
NeurIPS 2024Poster