1 code implementation • 18 Apr 2024 • Dawei Zhu, Liang Wang, Nan Yang, YiFan Song, Wenhao Wu, Furu Wei, Sujian Li
This paper explores context window extension of existing embedding models, pushing the limit to 32k without requiring additional training.
no code implementations • 9 Apr 2024 • Junpeng Liu, YiFan Song, Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li, Xiang Yue
Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks.
1 code implementation • 31 Mar 2024 • Dawei Zhu, Wenhao Wu, YiFan Song, Fangwei Zhu, Ziqiang Cao, Sujian Li
Due to the scarcity of annotated data, data augmentation is commonly used for training coherence evaluation models.
1 code implementation • 4 Mar 2024 • YiFan Song, Da Yin, Xiang Yue, Jie Huang, Sujian Li, Bill Yuchen Lin
This iterative cycle of exploration and training fosters continued improvement in the agents.
no code implementations • 16 Dec 2023 • Jiarui Yang, Songpengcheng Xia, YiFan Song, Qi Wu, Ling Pei
Human body reconstruction with Millimeter Wave (mmWave) radar point clouds has gained significant interest due to its ability to work in adverse environments and its capacity to mitigate privacy concerns associated with traditional camera-based solutions.
1 code implementation • 10 Oct 2023 • Weimin Xiong, YiFan Song, Peiyi Wang, Sujian Li
Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations.
1 code implementation • 10 Oct 2023 • YiFan Song, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks.
no code implementations • 1 Oct 2023 • YiFan Song, Keyang Yu, Seth Young
This work leverages the U. S. Federal Aviation Administration's Traffic Flow Management System dataset and DV8, a recently developed tool for highly interactive visualization of air traffic data, to develop clustering algorithms for categorizing air traffic by their varying flight paths.
1 code implementation • 19 Sep 2023 • Dawei Zhu, Nan Yang, Liang Wang, YiFan Song, Wenhao Wu, Furu Wei, Sujian Li
To decouple train length from target length for efficient context window extension, we propose Positional Skip-wisE (PoSE) training that smartly simulates long inputs using a fixed context window.
no code implementations • 5 Sep 2023 • YiFan Song, Mengkun She, Kevin Köser
To validate the effectiveness of our approach, we conducted extensive experiments on simulated and real-world datasets.
no code implementations • 11 Aug 2023 • Mengkun She, YiFan Song, David Nakath, Kevin Köser
Driven by the increasing number of marine data science applications, there is a growing interest in surveying and exploring the vast, uncharted terrain of the deep sea with robotic platforms.
no code implementations • 11 Jun 2023 • YiFan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian, Mingbo Song, Hailiang Huang, Cheng Li, Ke Wang, Rong Yao, Ye Tian, Sujian Li
To address the practical challenges of tackling complex instructions, we propose RestGPT, which exploits the power of LLMs and conducts a coarse-to-fine online planning mechanism to enhance the abilities of task decomposition and API selection.
no code implementations • 12 May 2023 • YiFan Song, Peiyi Wang, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks.
1 code implementation • 20 Mar 2023 • Hongbo Wang, Weimin Xiong, YiFan Song, Dawei Zhu, Yu Xia, Sujian Li
Joint entity and relation extraction (JERE) is one of the most important tasks in information extraction.
no code implementations • 16 Mar 2023 • Jaromir Savelka, Arav Agarwal, Christopher Bogart, YiFan Song, Majd Sakr
We evaluated the capability of generative pre-trained transformers (GPT), to pass assessments in introductory and intermediate Python programming courses at the postsecondary level.
1 code implementation • 10 Oct 2022 • Peiyi Wang, YiFan Song, Tianyu Liu, Binghuai Lin, Yunbo Cao, Sujian Li, Zhifang Sui
In this paper, through empirical studies we argue that this assumption may not hold, and an important reason for catastrophic forgetting is that the learned representations do not have good robustness against the appearance of analogous relations in the subsequent learning process.
1 code implementation • 7 Oct 2022 • Qingxiu Dong, Damai Dai, YiFan Song, Jingjing Xu, Zhifang Sui, Lei LI
However, we find that facts stored in the PLMs are not always correct.
1 code implementation • COLING 2022 • Dawei Zhu, Qiusi Zhan, Zhejian Zhou, YiFan Song, Jiebin Zhang, Sujian Li
Different from previous token-level or sentence-level counterparts, ConFiguRe aims at extracting a figurative unit from discourse-level context, and classifying the figurative unit into the right figure type.
no code implementations • 1 Sep 2022 • Peiyi Wang, YiFan Song, Tianyu Liu, Rundong Gao, Binghuai Lin, Yunbo Cao, Zhifang Sui
2) Balanced Tuning (BT) finetunes the model on the balanced memory data.
no code implementations • 26 Jul 2022 • Ziqiao Ao, Gergely Horvath, Chunyuan Sheng, YiFan Song, Yutong Sun
In this paper, we compare different methods to extract skill requirements from job advertisements.
1 code implementation • 2 May 2022 • Shoujie Tong, Qingxiu Dong, Damai Dai, YiFan Song, Tianyu Liu, Baobao Chang, Zhifang Sui
For each instance in a batch, we involve other instances in the same batch to interact with it.
no code implementations • 14 Dec 2021 • Mengkun She, Tim Weiß, YiFan Song, Peter Urban, Jens Greinert, Kevin Köser
Beside reporting the steps to make bubble characterization robust and autonomous, we carefully evaluate the reachable accuracy to be in the range of 1-2\% of the bubble radius and propose a novel auto-calibration procedure that, due to the lack of point correspondences, uses only the silhouettes of bubbles.
no code implementations • 1 Oct 2021 • Kevin Köser, YiFan Song, Lasse Petersen, Emanuel Wenzlaff, Felix Woelk
The majority of Earth's surface lies deep in the oceans, where no surface light reaches.
no code implementations • 14 Aug 2021 • Mengkun She, David Nakath, YiFan Song, Kevin Köser
Underwater cameras are typically placed behind glass windows to protect them from the water.