10 citations · 40 across the 26 of their papers we have counts for
26 papers
Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
Huifeng Lin, Gang Su, Jintao Liang +3
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG…
Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Jihua Peng, Qianxiong Xu, Yichen Liu +4
Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods…
SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking
Qianxiong Xu, Lanyun Zhu, Chenxi Liu +4
Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos. Existing methods can be roughly categorized into templa…
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
Jintao Liang, Gang Su, Huifeng Lin +3
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval wit…
Unlocking the Power of SAM 2 for Few-Shot Segmentation
Qianxiong Xu, Lanyun Zhu, Xuanyi Liu +4
Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use…
Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation
Chenxi Liu, Hao Miao, Qianxiong Xu +5
Multivariate time series forecasting (MTSF) endeavors to predict future observations given historical data, playing a crucial role in time series data management systems. With adva…
Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
Chenxi Liu, Shaowen Zhou, Qianxiong Xu +4
The proliferation of edge devices has generated an unprecedented volume of time series data across different domains, motivating various well-customized methods. Recently, Large La…
DTPPO: Dual-Transformer Encoder-based Proximal Policy Optimization for Multi-UAV Navigation in Unseen Complex Environments
Anning Wei, Jintao Liang, Kaiyuan Lin +2
Existing multi-agent deep reinforcement learning (MADRL) methods for multi-UAV navigation face challenges in generalization, particularly when applied to unseen complex environment…
Hybrid Mamba for Few-Shot Segmentation
Qianxiong Xu, Xuanyi Liu, Lanyun Zhu +4
Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can…
GuideLight: "Industrial Solution" Guidance for More Practical Traffic Signal Control Agents
Haoyuan Jiang, Xuantang Xiong, Ziyue Li +7
Currently, traffic signal control (TSC) methods based on reinforcement learning (RL) have proven superior to traditional methods. However, most RL methods face difficulties when ap…
Eliminating Feature Ambiguity for Few-Shot Segmentation
Qianxiong Xu, Guosheng Lin, Chen Change Loy +3
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively…
CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
Jingqing Ruan, Ziyue Li, Hua Wei +5
Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic signal control to alleviate congestion. Existing work mainly chooses neighboring inte…
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
Chenxi Liu, Qianxiong Xu, Hao Miao +5
Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suf…
SQL-to-Schema Enhances Schema Linking in Text-to-SQL
Sun Yang, Qiong Su, Zhishuai Li +4
In sophisticated existing Text-to-SQL methods exhibit errors in various proportions, including schema-linking errors (incorrect columns, tables, or extra columns), join errors, nes…
X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner
Haoyuan Jiang, Ziyue Li, Hua Wei +5
The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights.…
PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency
Zhishuai Li, Xiang Wang, Jingjing Zhao +8
Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face c…
SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models
Bin Zhang, Yuxiao Ye, Guoqing Du +8
Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to-SQL task, significantly outperforming traditional methods.Nevertheless, as a nascent research…
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning
Zhishuai Li, Yunhao Nie, Ziyue Li +3
Kriging aims at estimating the attributes of unsampled geo-locations from observations in the spatial vicinity or physical connections, which helps mitigate skewed monitoring cause…
Spatial-Temporal Large Language Model for Traffic Prediction
Chenxi Liu, Sun Yang, Qianxiong Xu +4
Traffic prediction, an essential component for intelligent transportation systems, endeavours to use historical data to foresee future traffic features at specific locations. Altho…
PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning
Hangyu Mao, Rui Zhao, Ziyue Li +7
Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work studies the former. Specifically, the Perception and Deci…
DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge
Jiaming Lu, Jingqing Ruan, Haoyuan Jiang +3
Reinforcement learning has been revolutionizing the traditional traffic signal control task, showing promising power to relieve congestion and improve efficiency. However, the exis…
VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network
Zhishuai Li, Ziyue Li, Xiaoru Hu +5
Trajectory recovery based on the snapshots from the city-wide multi-camera network facilitates urban mobility sensing and driveway optimization. The state-of-the-art solutions devo…
A Critical Perceptual Pre-trained Model for Complex Trajectory Recovery
Dedong Li, Ziyue Li, Zhishuai Li +5
The trajectory on the road traffic is commonly collected at a low sampling rate, and trajectory recovery aims to recover a complete and continuous trajectory from the sparse and di…
Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
Bin Zhang, Hangyu Mao, Jingqing Ruan +9
The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS). However, as the numb…