34 citations · 142 across the 32 of their papers we have counts for
32 papers
In-situ tunable giant electrical anisotropy in a grating gated AlGaN/GaN two-dimensional electron gas
Ting-Ting Wang, Sining Dong, Chong Li +14
Materials with in-plane electrical anisotropy have great potential for designing artificial synaptic devices. However, natural materials with strong intrinsic in-plane electrical a…
Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech
Rui Liu, Bin Liu, Haizhou Li
Prosodic phrasing is crucial to the naturalness and intelligibility of end-to-end Text-to-Speech (TTS). There exist both linguistic and emotional prosody in natural speech. As the…
Data Generation-based Operator Learning for Solving Partial Differential Equations on Unbounded Domains
Jihong Wang, Xin Wang, Jing Li +1
Wave propagation problems are typically formulated as partial differential equations (PDEs) on unbounded domains to be solved. The classical approach to solving such problems invol…
Proton-Boron Fusion Yield Increased by Orders of Magnitude with Foam Targets
Wen-Qing Wei, Shi-Zheng Zhang, Zhi-Gang Deng +35
A novel intense beam-driven scheme for high yield of the tri-alpha reaction 11B(p,α)2α was investigated. We used a foam target made of cellulose triacetate (TAC, C_9H_{16}O_8) dope…
Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion
Yutao Jin, Bin Liu, Jing Wang
The application of video captioning models aims at translating the content of videos by using accurate natural language. Due to the complex nature inbetween object interaction in t…
Debiased Pairwise Learning from Positive-Unlabeled Implicit Feedback
Bin Liu, Qin Luo, Bang Wang
Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and informat…
Class-Incremental Learning based on Label Generation
Yijia Shao, Yiduo Guo, Dongyan Zhao +1
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) se…
Parameter-Level Soft-Masking for Continual Learning
Tatsuya Konishi, Mori Kurokawa, Chihiro Ono +3
Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved lea…
Open-loop and closed-loop solvabilities for discrete-time mean-field stochastic linear quadratic optimal control problems
Teng Song, Bin Liu
This paper discusses the discrete-time mean-field stochastic linear quadratic optimal control problems, whose weighting matrices in the cost functional are not assumed to be defini…
Learnability and Algorithm for Continual Learning
Gyuhak Kim, Changnan Xiao, Tatsuya Konishi +1
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or cl…
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Bin Hu, Chenyang Zhao, Pu Zhang +4
Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in…
Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast
Yiduo Guo, Yaobo Liang, Dongyan Zhao +2
Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, ev…
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
Neeraj Varshney, Himanshu Gupta, Eric Robertson +2
State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are know…
Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
Gyuhak Kim, Changnan Xiao, Tatsuya Konishi +2
As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detec…
Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation
Hao Liu, Xin Li, Mingming Gong +5
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community. While impr…
Three-dimensional real Chern insulator in bulk -graphyne
Xu-Tao Zeng, Bin-Bin Liu, Fan Yang +4
The real Chern insulator state, featuring nontrivial real Chern number and second-order boundary modes, has been revealed in a few two-dimensional systems. The concept can be exten…
Continual Pre-training of Language Models
Zixuan Ke, Yijia Shao, Haowei Lin +3
Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain…
Adapting a Language Model While Preserving its General Knowledge
Zixuan Ke, Yijia Shao, Haowei Lin +3
Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a…
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
Kailin Liang, Bin Liu, Yifan Hu +3
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongoli…
Fine-Grained Selective Similarity Integration for Drug-Target Interaction Prediction
Bin Liu, Jin Wang, Kaiwei Sun +1
The discovery of drug-target interactions (DTIs) is a pivotal process in pharmaceutical development. Computational approaches are a promising and efficient alternative to tedious a…
A Theoretical Study on Solving Continual Learning
Gyuhak Kim, Changnan Xiao, Tatsuya Konishi +2
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL). A major c…
Continual Learning of Natural Language Processing Tasks: A Survey
Zixuan Ke, Bing Liu
Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowl…
Continual Training of Language Models for Few-Shot Learning
Zixuan Ke, Haowei Lin, Yijia Shao +3
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can pr…
Learnable Distribution Calibration for Few-Shot Class-Incremental Learning
Binghao Liu, Boyu Yang, Lingxi Xie +3
Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. In this study,…