Search Results for author: Sihang Li

Found 21 papers, 17 papers with code

Multiview Scene Graph

1 code implementation15 Oct 2024 Juexiao Zhang, Gao Zhu, Sihang Li, Xinhao Liu, Haorui Song, Xinran Tang, Chen Feng

In this work, we propose to build Multiview Scene Graphs (MSG) from unposed images, representing a scene topologically with interconnected place and object nodes.

Decoder Object +4

Text-guided Diffusion Model for 3D Molecule Generation

no code implementations4 Oct 2024 Yanchen Luo, Junfeng Fang, Sihang Li, Zhiyuan Liu, Jiancan Wu, An Zhang, Wenjie Du, Xiang Wang

The de novo generation of molecules with targeted properties is crucial in biology, chemistry, and drug discovery.

3D Molecule Generation Diversity +1

SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding

1 code implementation28 Aug 2024 Sihang Li, Jin Huang, Jiaxi Zhuang, Yaorui Shi, Xiaochen Cai, Mingjun Xu, Xiang Wang, Linfeng Zhang, Guolin Ke, Hengxing Cai

To develop an LLM specialized in scientific literature understanding, we propose a hybrid strategy that integrates continual pre-training (CPT) and supervised fine-tuning (SFT), to simultaneously infuse scientific domain knowledge and enhance instruction-following capabilities for domain-specific tasks. cIn this process, we identify two key challenges: (1) constructing high-quality CPT corpora, and (2) generating diverse SFT instructions.

Instruction Following scientific discovery

ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining

1 code implementation23 May 2024 Zhiyuan Liu, Yaorui Shi, An Zhang, Sihang Li, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua

To resolve the challenges above, we propose a new pretraining method, ReactXT, for reaction-text modeling, and a new dataset, OpenExp, for experimental procedure prediction.

Molecule Captioning Retrosynthesis

Uni-SMART: Universal Science Multimodal Analysis and Research Transformer

1 code implementation15 Mar 2024 Hengxing Cai, Xiaochen Cai, Shuwen Yang, Jiankun Wang, Lin Yao, Zhifeng Gao, Junhan Chang, Sihang Li, Mingjun Xu, Changxin Wang, Hongshuai Wang, Yongge Li, Mujie Lin, Yaqi Li, Yuqi Yin, Linfeng Zhang, Guolin Ke

Scientific literature often includes a wide range of multimodal elements, such as tables, charts, and molecule, which are hard for text-focused LLMs to understand and analyze.

MolTC: Towards Molecular Relational Modeling In Language Models

1 code implementation6 Feb 2024 Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, Xiang Wang

Molecular Relational Learning (MRL), aiming to understand interactions between molecular pairs, plays a pivotal role in advancing biochemical research.

Relational Reasoning

Towards 3D Molecule-Text Interpretation in Language Models

1 code implementation25 Jan 2024 Sihang Li, Zhiyuan Liu, Yanchen Luo, Xiang Wang, Xiangnan He, Kenji Kawaguchi, Tat-Seng Chua, Qi Tian

Through 3D molecule-text alignment and 3D molecule-centric instruction tuning, 3D-MoLM establishes an integration of 3D molecular encoder and LM.

Instruction Following Language Modelling +2

LLaRA: Large Language-Recommendation Assistant

1 code implementation5 Dec 2023 Jiayi Liao, Sihang Li, Zhengyi Yang, Jiancan Wu, Yancheng Yuan, Xiang Wang, Xiangnan He

Treating the "sequential behaviors of users" as a distinct modality beyond texts, we employ a projector to align the traditional recommender's ID embeddings with the LLM's input space.

Language Modelling Sequential Recommendation +1

BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT

1 code implementation24 Oct 2023 YiRong Chen, Zhenyu Wang, Xiaofen Xing, huimin zheng, Zhipei Xu, Kai Fang, Junhong Wang, Sihang Li, Jieling Wu, Qi Liu, Xiangmin Xu

Large language models (LLMs) have performed well in providing general and extensive health suggestions in single-turn conversations, exemplified by systems such as ChatGPT, ChatGLM, ChatDoctor, DoctorGLM, and etc.

Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation

no code implementations7 Oct 2023 Jingyi Pan, Sihang Li, Yucheng Chen, Jinjing Zhu, Lin Wang

Moreover, semantic segmentation models trained on daytime datasets often face difficulties in generalizing effectively to nighttime conditions.

Autonomous Driving Contrastive Learning +4

National Origin Discrimination in Deep-learning-powered Automated Resume Screening

no code implementations13 Jul 2023 Sihang Li, Kuangzheng Li, Haibing Lu

Many companies and organizations have started to use some form of AIenabled auto mated tools to assist in their hiring process, e. g. screening resumes, interviewing candi dates, performance evaluation.

Deep Learning Fairness

SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking

1 code implementation8 Mar 2023 Liangliang Yao, Changhong Fu, Sihang Li, Guangze Zheng, Junjie Ye

The proposed method designs a new task-specific object saliency mining network to refine the cross-correlation operation and effectively discriminate foreground and background information.

Object Tracking

Continuity-Aware Latent Interframe Information Mining for Reliable UAV Tracking

1 code implementation8 Mar 2023 Changhong Fu, Mutian Cai, Sihang Li, Kunhan Lu, Haobo Zuo, Chongjun Liu

To address the above issues, this work proposes a novel framework with continuity-aware latent interframe information mining for reliable UAV tracking, i. e., ClimRT.

Autonomous Navigation

Direct 3D information fusion for depth of field enhancement in optical-resolution photoacoustic microscopy

no code implementations24 Nov 2022 Xianlin Song, Sihang Li, Zhuangzhuang Wang

In this work, a 3D information fusion algorithm based on 3D stationary wavelet transform and joint weighted evaluation optimization is proposed to fuse multi-focus photoacoustic data to achieve large-volumetric and high-resolution 3D imaging.

HighlightNet: Highlighting Low-Light Potential Features for Real-Time UAV Tracking

1 code implementation14 Aug 2022 Changhong Fu, Haolin Dong, Junjie Ye, Guangze Zheng, Sihang Li, Jilin Zhao

Pixel-level range mask is introduced to make HighlightNet more focused on the enhancement of the tracking object and regions without light sources.

Image Enhancement

Local Perception-Aware Transformer for Aerial Tracking

1 code implementation1 Aug 2022 Changhong Fu, Weiyu Peng, Sihang Li, Junjie Ye, Ziang Cao

Specifically, with local-modeling to global-search mechanism, the proposed tracker replaces the global encoder by a novel local-recognition encoder.

Inductive Bias Visual Object Tracking

Let Invariant Rationale Discovery Inspire Graph Contrastive Learning

1 code implementation16 Jun 2022 Sihang Li, Xiang Wang, An Zhang, Yingxin Wu, Xiangnan He, Tat-Seng Chua

Specifically, without supervision signals, RGCL uses a rationale generator to reveal salient features about graph instance-discrimination as the rationale, and then creates rationale-aware views for contrastive learning.

Contrastive Learning

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

1 code implementation3 Mar 2022 Changhong Fu, Sihang Li, Xinnan Yuan, Junjie Ye, Ziang Cao, Fangqiang Ding

Therefore, to help increase awareness of the potential risk and the robustness of UAV tracking, this work proposes a novel adaptive adversarial attack approach, i. e., Ad$^2$Attack, against UAV object tracking.

Adversarial Attack Object Tracking +2

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