16 citations · 39 across the 22 of their papers we have counts for
23 papers
DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning
Yafeng Nan, Haifeng Sun, Zirui Zhuang +5
In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. The sota Text-to-SQL models have achieve…
AuroraRL: Fast, Fault-Tolerant, and Cost-Efficient Reinforcement Learning over Decentralized Network
Chaoyi Ruan, Geng Luo, Xinyi Wan +12
LLM reinforcement learning (RL) requires frequent synchronization of large model parameters between the trainer and distributed rollout actors. High-throughput RL post-training the…
Lightweight Edge Learning via Dataset Pruning
Laha Ale, Hu Luo, Mingsheng Cao +3
Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication…
Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting
Chengsen Wang, Qi Qi, Jingyu Wang +3
Time series forecasting holds significant importance across various industries, including finance, transportation, energy, healthcare, and climate. Despite the widespread use of li…
MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration
Jinguang Wang, Jingyu Wang, Haifeng Sun +6
Quantization has been widely used to compress and accelerate inference of large language models (LLMs). Existing methods focus on exploring the per-token dynamic calibration to ens…
OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest
Yuhan Jing, Jingyu Wang, Lei Zhang +6
With the growing adoption of time-series anomaly detection (TAD) technology, numerous studies have employed deep learning-based detectors to analyze time-series data in the fields…
Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
Huazheng Wang, Yongcheng Jing, Haifeng Sun +4
In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but a…
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
Chengsen Wang, Qi Qi, Jingyu Wang +5
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal nu…
Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
Yuanyi Wang, Haifeng Sun, Chengsen Wang +6
Anomaly detection in multivariate time series (MTS) is crucial for various applications in data mining and industry. Current industrial methods typically approach anomaly detection…
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
Chengsen Wang, Qi Qi, Jingyu Wang +4
Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate. Due to the abundant seasonal inform…
OutlierTune: Efficient Channel-Wise Quantization for Large Language Models
Jinguang Wang, Yuexi Yin, Haifeng Sun +5
Quantizing the activations of large language models (LLMs) has been a significant challenge due to the presence of structured outliers. Most existing methods focus on the per-token…
Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation
Yuanyi Wang, Wei Tang, Haifeng Sun +5
Weakly Supervised Entity Alignment (EA) is the task of identifying equivalent entities across diverse knowledge graphs (KGs) using only a limited number of seed alignments. Despite…
Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment
Yuanyi Wang, Haifeng Sun, Jiabo Wang +5
In Multi-Modal Knowledge Graphs (MMKGs), Multi-Modal Entity Alignment (MMEA) is crucial for identifying identical entities across diverse modal attributes. However, semantic incons…
Gradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding
Yuanyi Wang, Haifeng Sun, Jingyu Wang +3
Entity alignment (EA), a pivotal process in integrating multi-source Knowledge Graphs (KGs), seeks to identify equivalent entity pairs across these graphs. Most existing approaches…
An Empirical Study of NetOps Capability of Pre-Trained Large Language Models
Yukai Miao, Yu Bai, Li Chen +10
Nowadays, the versatile capabilities of Pre-trained Large Language Models (LLMs) have attracted much attention from the industry. However, some vertical domains are more interested…
How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?
Huazheng Wang, Daixuan Cheng, Haifeng Sun +5
Transformer-based pretrained language models (PLMs) have achieved great success in modern NLP. An important advantage of PLMs is good out-of-distribution (OOD) robustness. Recently…
Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
Xiang Yang, Dezhi Chen, Qi Qi +4
Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices. DNN surgery, which partitions DNN processing between mobile devi…
Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image
Pengfei Ren, Chao Wen, Xiaozheng Zheng +5
Reconstructing interacting hands from a single RGB image is a very challenging task. On the one hand, severe mutual occlusion and similar local appearance between two hands confuse…
Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding
Jiachang Hao, Haifeng Sun, Pengfei Ren +3
Temporal grounding aims to locate a target video moment that semantically corresponds to the given sentence query in an untrimmed video. However, recent works find that existing me…
PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices
Xiang Yang, Zikang Xu, Qi Qi +4
Distributing the inference of convolutional neural network (CNN) to multiple mobile devices has been studied in recent years to achieve real-time inference without losing accuracy.…
AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation
Weiting Huang, Pengfei Ren, Jingyu Wang +2
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods. Hand joint coordinates are…
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek +32
We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy…
OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
Jiashi Li, Qi Qi, Jingyu Wang +4
Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in…