188 citations · 445 across the 40 of their papers we have counts for
21 papers · 1 filter
No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection
Qi Zhang, Sipeng Zheng, Qin Jin
Temporal video grounding (TVG) aims to retrieve the time interval of a language query from an untrimmed video. A significant challenge in TVG is the low "Semantic Noise Ratio (SNR)…
Secrets of RLHF in Large Language Models Part I: PPO
Rui Zheng, Shihan Dou, Songyang Gao +24
Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, h…
Movie101: A New Movie Understanding Benchmark
Zihao Yue, Qi Zhang, Anwen Hu +3
To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of a…
Successive one-sided Hodrick-Prescott filter with incremental filtering algorithm for nonlinear economic time series
Yuxia Liu, Qi Zhang, Wei Xiao +1
We propose a successive one-sided Hodrick-Prescott (SOHP) filter from multiple time scale decomposition perspective to derive trend estimate for a time series. The idea is to apply…
Actively Supervised Clustering for Open Relation Extraction
Jun Zhao, Yongxin Zhang, Qi Zhang +4
Current clustering-based Open Relation Extraction (OpenRE) methods usually adopt a two-stage pipeline. The first stage simultaneously learns relation representations and assignment…
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
Jun Zhao, Wenyu Zhan, Xin Zhao +6
Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should ex…
Open Set Relation Extraction via Unknown-Aware Training
Jun Zhao, Xin Zhao, Wenyu Zhan +6
The existing supervised relation extraction methods have achieved impressive performance in a closed-set setting, where the relations during both training and testing remain the sa…
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model
Xiao Wang, Weikang Zhou, Qi Zhang +7
Pretrained language models have achieved remarkable success in various natural language processing tasks. However, pretraining has recently shifted toward larger models and larger…
Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition
Nan Li, Mehdi Bennis, Alexandros Iosifidis +1
This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following seman…
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Ting Wu, Rui Zheng, Tao Gui +2
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization. Group distributionally robust optimiza…
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
Ting Wu, Jingyi Liu, Rui Zheng +3
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge. While current endeavors in CRE succeed in preservi…
UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation
Guoqing Yang, Fuyou Xue, Qi Zhang +3
We present the UrbanBIS benchmark for large-scale 3D urban understanding, supporting practical urban-level semantic and building-level instance segmentation. UrbanBIS comprises six…
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
Zhiheng Xi, Senjie Jin, Yuhao Zhou +5
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which…
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
Limao Xiong, Jie Zhou, Qunxi Zhu +7
Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets, which always obtain using crowdsourcing. However, it is hard to obtain a unifie…
Joint Beamforming and Phase Shift Design for Hybrid-IRS-and-UAV-aided Directional Modulation Network
Rongen Dong, Hangjia He, Feng Shu +4
Recently, intelligent reflecting surface (IRS) and unmanned aerial vehicle (UAV) have been introduced into wireless communication systems to enhance the performance of air-ground t…
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Xiao Wang, Weikang Zhou, Can Zu +11
Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have diffic…
Change a Bit to save Bytes: Compression for Floating Point Time-Series Data
Francesco Taurone, Daniel E. Lucani, Marcell Fehér +1
The number of IoT devices is expected to continue its dramatic growth in the coming years and, with it, a growth in the amount of data to be transmitted, processed and stored. Comp…
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Junjie Ye, Xuanting Chen, Nuo Xu +12
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities. Howe…
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Xuanting Chen, Junjie Ye, Can Zu +7
The GPT-3.5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities. Ho…
Beamforming Design for RIS-Aided AF Relay Networks
Xuehui Wang, Feng Shu, Riqing Chen +5
Since reconfigurable intelligent surface (RIS) is considered to be a passive reflector for rate performance enhancement, a RIS-aided amplify-and-forward (AF) relay network is prese…
A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
Kun Yi, Qi Zhang, Wei Fan +7
Recently, frequency transformation (FT) has been increasingly incorporated into deep learning models to significantly enhance state-of-the-art accuracy and efficiency in time serie…