Search Results for author: Yutong Hu

Found 6 papers, 3 papers with code

Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion

1 code implementation10 Jul 2024 Yutong Hu, Yang Tan, Andi Han, Lirong Zheng, Liang Hong, Bingxin Zhou

The advent of deep learning has introduced efficient approaches for de novo protein sequence design, significantly improving success rates and reducing development costs compared to computational or experimental methods.

Diversity

What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling

no code implementations17 Jun 2024 Yutong Hu, Quzhe Huang, Kangcheng Luo, Yansong Feng

In this paper, we aim to explore which kinds of words benefit more from long contexts in language models.

Language Modelling

Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?

no code implementations9 May 2024 Yutong Hu, Quzhe Huang, Mingxu Tao, Chen Zhang, Yansong Feng

Recent studies have shown that Large Language Models (LLMs) have the potential to process extremely long text.

Language Modelling Position

DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision

1 code implementation21 Mar 2024 Yutong Hu, Kehan Wen, Fisher Yu

Learning dexterous locomotion policy for legged robots is becoming increasingly popular due to its ability to handle diverse terrains and resemble intelligent behaviors.

More than Classification: A Unified Framework for Event Temporal Relation Extraction

no code implementations28 May 2023 Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao

After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events.

Multi-Label Classification Relation +1

SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints

1 code implementation10 Sep 2021 Ziwei Liao, Yutong Hu, Jiadong Zhang, Xianyu Qi, XiaoYu Zhang, Wei Wang

Object SLAM introduces the concept of objects into Simultaneous Localization and Mapping (SLAM) and helps understand indoor scenes for mobile robots and object-level interactive applications.

Object Object SLAM

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