PaperHub
影响力指数
87.97/100
前 0.7%
全站排名 #462
发表论文32 篇
平均评分5.2
年均产出10.7 篇/年

Minlie Huang

Full Professor@Tsinghua University, Tsinghua University·中国·OpenReview
研究方向

natural language generation · dialogue systems · large language models · safety and alignment · social intelligence

6.0
23

Trust-Region Adaptive Policy Optimization

ICLR 2026Poster
6.0
19

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

ICLR 2026Poster
通讯
5.0
29

SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents

ICLR 2026Rejected
4.5
24

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!

ICLR 2026Poster
通讯
4.5
23

Think Socially via Cognitive Reasoning

ICLR 2026Rejected
通讯
4.5
18

Survive at All Costs: Exploring LLM's Risky Behavior under Survival Pressure

ICLR 2026Rejected
通讯
4.4
36

On the Self-awareness of Large Reasoning Models' Capability Boundaries

ICLR 2026Rejected
4.0
31

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks

ICLR 2026Rejected
通讯
3.5
21

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models

ICLR 2026Withdrawn
通讯
3.0
5

Understanding the Dilemma of Unlearning for Large Language Models

ICLR 2026Withdrawn
2.5
5

PROBE: Benchmarking Reasoning Paradigm Overfitting in Large Language Models

ICLR 2026Withdrawn
2.5
5

Beyond Nash Equilibrium: Bounded Rationality of LLMs and humans in Strategic Decision-making

ICLR 2026Withdrawn
8.0
25

Data Selection via Optimal Control for Language Models

ICLR 2025Oral
通讯
6.5
28

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

ICLR 2025Poster
6.5
14

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

ICLR 2025Poster
通讯
6.4
23

MiniPLM: Knowledge Distillation for Pre-training Language Models

ICLR 2025Poster
通讯
6.3
20

Language Models Learn to Mislead Humans via RLHF

ICLR 2025Poster
5.5
21

Does RLHF Scale? Exploring the Effects of Data, Model, and Method

ICLR 2025Rejected
5.3
27

RedHat: Towards Reducing Hallucination in Essay Critiques with Large Language Models

ICLR 2025Rejected
通讯
5.0
29

CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning

ICLR 2025Poster
通讯
4.8
10

Diffusion Attacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak

ICLR 2025Withdrawn
4.5
14

Model Extrapolation Expedites Alignment

ICLR 2025Withdrawn
3.0
23

Seeker: Enhancing Exception Handling in Code with a LLM-based Multi-Agent Approach

ICLR 2025Withdrawn
通讯
3.0
5

BlackDAN: A Black-Box Multi-Objective Approach to Effective and Contextual Jailbreaking of Language Models

ICLR 2025Rejected
通讯
合作者 (20)