影响力指数

85.5/100

前 0.9%

全站排名 #573

发表论文25 篇

平均评分5.3

年均产出8.3 篇/年

Ling Pan

Assistant Professor@Hong Kong University of Science and Technology·中国香港·OpenReview

研究方向

Generative flow networks (GFlowNets) · Deep reinforcement learning (DRL) · Multi-agent reinforcement learning (MARL)

6.0

Tricks or Traps? A Deep Dive into RL for LLM Reasoning

ICLR 2026Poster

5.5

Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration

ICLR 2026Rejected

二作

5.5

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

NeurIPS 2025Poster

通讯

6.8

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

ICLR 2025Poster

通讯

6.6

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

ICML 2025Poster

通讯

6.5

Neuroplastic Expansion in Deep Reinforcement Learning

ICLR 2025Poster

通讯

6.4

Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization

NeurIPS 2025Poster

三作

4.9

Random Policy Evaluation Uncovers Policies of Generative Flow Networks

ICML 2025Poster

通讯

4.3

Evolution guided generative flow networks

ICLR 2025Withdrawn

二作

3.0

Small features matter: Robust representation for world models

合作者 (20)

Ling Pan

Tricks or Traps? A Deep Dive into RL for LLM Reasoning

Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models

Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

AGOF: A GFlowNet-Guided 2-Opt Framework for Vehicle Routing Problems

Scaling Image and Video Generation via Test-Time Evolutionary Search