Search Results for author: Guoqing Liu

Found 22 papers, 8 papers with code

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning

no code implementations26 May 2024 Hongfei Wu, Lijun Wu, Guoqing Liu, Zhirong Liu, Bin Shao, Zun Wang

In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning.

molecular representation Representation Learning

Token-level Direct Preference Optimization

1 code implementation18 Apr 2024 Yongcheng Zeng, Guoqing Liu, Weiyu Ma, Ning Yang, Haifeng Zhang, Jun Wang

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions.

Thermal-NeRF: Neural Radiance Fields from an Infrared Camera

no code implementations15 Mar 2024 Tianxiang Ye, Qi Wu, Junyuan Deng, Guoqing Liu, Liu Liu, Songpengcheng Xia, Liang Pang, Wenxian Yu, Ling Pei

In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit representation for 3D scene reconstruction.

3D Scene Reconstruction

Reinforcement Learning from Bagged Reward

no code implementations6 Feb 2024 Yuting Tang, Xin-Qiang Cai, Yao-Xiang Ding, Qiyu Wu, Guoqing Liu, Masashi Sugiyama

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy.

reinforcement-learning Reinforcement Learning (RL)

Empirical Evidence for the Fragment level Understanding on Drug Molecular Structure of LLMs

1 code implementation15 Jan 2024 Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang

AI for drug discovery has been a research hotspot in recent years, and SMILES-based language models has been increasingly applied in drug molecular design.

Drug Discovery

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

1 code implementation NeurIPS 2023 Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang

A central challenge in this field is to generate molecules with specific properties while also producing a wide range of diverse candidates.


StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences

1 code implementation28 Nov 2023 Shangkun Sun, Jiaming Liu, Thomas H. Li, Huaxia Li, Guoqing Liu, Wei Gao

To address this issue, multi-frame optical flow methods leverage adjacent frames to mitigate the local ambiguity.

Optical Flow Estimation

Re-evaluating Retrosynthesis Algorithms with Syntheseus

1 code implementation30 Oct 2023 Krzysztof Maziarz, Austin Tripp, Guoqing Liu, Megan Stanley, Shufang Xie, Piotr Gaiński, Philipp Seidl, Marwin Segler

The planning of how to synthesize molecules, also known as retrosynthesis, has been a growing focus of the machine learning and chemistry communities in recent years.

Benchmarking Multi-step retrosynthesis +1

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

1 code implementation15 Sep 2023 Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, Yujiu Yang

Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort.

Evolutionary Algorithms

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

1 code implementation ICCV 2023 Junyuan Deng, Xieyuanli Chen, Songpengcheng Xia, Zhen Sun, Guoqing Liu, Wenxian Yu, Ling Pei

To bridge this gap, in this paper, we propose a novel NeRF-based LiDAR odometry and mapping approach, NeRF-LOAM, consisting of three modules neural odometry, neural mapping, and mesh reconstruction.

Retrosynthetic Planning with Dual Value Networks

1 code implementation31 Jan 2023 Guoqing Liu, Di Xue, Shufang Xie, Yingce Xia, Austin Tripp, Krzysztof Maziarz, Marwin Segler, Tao Qin, Zongzhang Zhang, Tie-Yan Liu

Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design.

Drug Discovery Multi-step retrosynthesis +2

Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation

no code implementations18 Jul 2022 Guoqing Liu, Mengzhang Cai, Li Zhao, Tao Qin, Adrian Brown, Jimmy Bischoff, Tie-Yan Liu

In this work, we propose using only screenshots/pixels as input for automated game testing and build a general game testing agent, Inspector, that can be easily applied to different games without deep integration with games.

Imitation Learning Object

You May Not Need Ratio Clipping in PPO

no code implementations31 Jan 2022 Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson

Furthermore, we show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.

Continuous Control

Return-Based Contrastive Representation Learning for Reinforcement Learning

no code implementations ICLR 2021 Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL).

Atari Games reinforcement-learning +2

Suphx: Mastering Mahjong with Deep Reinforcement Learning

no code implementations30 Mar 2020 Junjie Li, Sotetsu Koyamada, Qiwei Ye, Guoqing Liu, Chao Wang, Ruihan Yang, Li Zhao, Tao Qin, Tie-Yan Liu, Hsiao-Wuen Hon

Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI.

reinforcement-learning Reinforcement Learning (RL)

Independence-aware Advantage Estimation

no code implementations25 Sep 2019 Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minglie Huang, Tao Qin, Tie-Yan Liu

Most of existing advantage function estimation methods in reinforcement learning suffer from the problem of high variance, which scales unfavorably with the time horizon.

Demonstration Actor Critic

no code implementations25 Sep 2019 Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu

One approach leverages demonstration data in a supervised manner, which is simple and direct, but can only provide supervision signal over those states seen in the demonstrations.

Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

no code implementations4 Jun 2019 Ikuro Sato, Kohta Ishikawa, Guoqing Liu, Masayuki Tanaka

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network.

Visual Recognition Using Directional Distribution Distance

no code implementations19 Apr 2015 Jianxin Wu, Bin-Bin Gao, Guoqing Liu

In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity.

Cannot find the paper you are looking for? You can Submit a new open access paper.