no code implementations • 29 Oct 2024 • Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang, Xuyang Liu, Weiya Li, Xuming Hu, Linfeng Zhang
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI).
no code implementations • 3 Oct 2024 • Mingyang Wang, Lukas Lange, Heike Adel, Jannik Strötgen, Hinrich Schütze
Evaluations on three model editing benchmarks show that SAUL is a practical and reliable solution for model editing outperforming state-of-the-art methods while maintaining generation quality and reducing computational overhead.
1 code implementation • 26 Sep 2024 • Yihong Liu, Haotian Ye, Chunlan Ma, Mingyang Wang, Hinrich Schütze
However, this removal increases the burden on token embeddings to encode all language-specific information, which may hinder the model's ability to produce more language-neutral representations.
1 code implementation • 25 Sep 2024 • Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Ayyoob Imani, Orgest Xhelili, Haotian Ye, Chunlan Ma, François Yvon, Hinrich Schütze
However, we also show that better alignment does not always yield better downstream performance, suggesting that further research is needed to clarify the connection between alignment and performance.
no code implementations • 17 Jul 2024 • Jike Wang, Jianwen Feng, Yu Kang, Peichen Pan, Jingxuan Ge, Yan Wang, Mingyang Wang, Zhenxing Wu, Xingcai Zhang, Jiameng Yu, Xujun Zhang, Tianyue Wang, Lirong Wen, Guangning Yan, Yafeng Deng, Hui Shi, Chang-Yu Hsieh, Zhihui Jiang, Tingjun Hou
Within 11 days, AMP-Designer enables de novo design of 18 novel candidates with broad-spectrum potency against Gram-negative bacteria.
1 code implementation • 10 Jul 2024 • Jike Wang, Rui Qin, Mingyang Wang, Meijing Fang, Yangyang Zhang, Yuchen Zhu, Qun Su, Qiaolin Gou, Chao Shen, Odin Zhang, Zhenxing Wu, Dejun Jiang, Xujun Zhang, Huifeng Zhao, Xiaozhe Wan, Zhourui Wu, Liwei Liu, Yu Kang, Chang-Yu Hsieh, Tingjun Hou
This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm.
no code implementations • 26 Jun 2024 • Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze
In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned.
no code implementations • 25 Jun 2024 • Ercong Nie, Bo Shao, Zifeng Ding, Mingyang Wang, Helmut Schmid, Hinrich Schütze
Large language models (LLMs) possess extensive parametric knowledge, but this knowledge is difficult to update with new information because retraining is very expensive and infeasible for closed-source models.
1 code implementation • 20 May 2024 • Zhenwei Shao, Zhou Yu, Jun Yu, Xuecheng Ouyang, Lihao Zheng, Zhenbiao Gai, Mingyang Wang, Jiajun Ding
By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding.
Ranked #84 on
Visual Question Answering
on MM-Vet
1 code implementation • 1 Apr 2024 • Miaoran Zhang, Mingyang Wang, Jesujoba O. Alabi, Dietrich Klakow
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages.
1 code implementation • 31 Mar 2024 • Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze
Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge.
no code implementations • 15 Mar 2024 • Odin Zhang, Yufei Huang, Shichen Cheng, Mengyao Yu, Xujun Zhang, Haitao Lin, Yundian Zeng, Mingyang Wang, Zhenxing Wu, Huifeng Zhao, Zaixi Zhang, Chenqing Hua, Yu Kang, Sunliang Cui, Peichen Pan, Chang-Yu Hsieh, Tingjun Hou
Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets.
1 code implementation • 20 Feb 2024 • Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba O. Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach
In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates.
1 code implementation • 15 Nov 2023 • Yihong Liu, Peiqin Lin, Mingyang Wang, Hinrich Schütze
Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining.
no code implementations • 23 Oct 2023 • Zihao Yan, Fubao Su, Mingyang Wang, Ruizhen Hu, Hao Zhang, Hui Huang
We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i. e., unexposed, geometries of a target 3D object.
no code implementations • 23 Oct 2023 • Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze
However, not all languages positively influence each other and it is an open research question how to select the most suitable set of languages for multilingual training and avoid negative interference among languages whose characteristics or data distributions are not compatible.
no code implementations • 29 Apr 2023 • Mingyang Wang, Zhenshan Bing, Xiangtong Yao, Shuai Wang, Hang Su, Chenguang Yang, Kai Huang, Alois Knoll
On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.
no code implementations • 28 Apr 2023 • Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze
In this work, we propose to leverage language-adaptive and task-adaptive pretraining on African texts and study transfer learning with source language selection on top of an African language-centric pretrained language model.
no code implementations • 4 Jun 2020 • Xiang Li, Mingyang Wang, Yi Fang
Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multi-view image matching.
no code implementations • 14 Oct 2019 • Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang
Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.