Author name cluster

Wei Su

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2025 Journal Article

An improved traffic coordination control integrating traffic flow prediction and optimization

Wei Su
Chaoxu Mu
Lei Xue
Xiaobao Yang
Song Zhu

The rapid growth of the number of vehicles and the inadaptability of signal control have become major factors restricting traffic efficiency and people’s travel experience. Optimizing traffic signal timing can alleviate congestion and reduce delays, but accurately predicting traffic flow for the next signal cycle remains a complex challenge. To address this, this paper proposes an analytical signal control optimization algorithm that integrates prediction and coordination at urban regional intersections to improve traffic efficiency. First, an intelligent learning scheme is designed, embedding real datasets into the Long Short-Term Memory (LSTM) network to predict traffic condition information in subsequent signal queues. Then, an objective optimization model is established based on kinematic wave theory and flow-density diagram. This model seeks the globally optimal signal timing solution by dynamically adjusting signal timing, cycle length, and phase splits. For traffic congestion scenarios, the phase configuration of multi-phase intersections is improved to enhance green light time utilization and traffic capacity. Taking the traffic operation scenario of Songwei South Road in Shanghai as an example, the simulation study verifies the performance of the proposed strategy.

Details DOI

AAAI Conference 2025 Conference Paper

ReFF: Reinforcing Format Faithfulness in Language Models Across Varied Tasks

Jiashu Yao
Heyan Huang
Zeming Liu
Haoyu Wen
Wei Su
Boao Qian
Yuhang Guo

Following formatting instructions to generate well-structured content is a fundamental yet often unmet capability for large language models (LLMs). To study this capability, which we refer to as format faithfulness, we present FormatBench, a comprehensive format-related benchmark. Compared to previous format-related benchmarks, FormatBench involves a greater variety of tasks in terms of application scenes (traditional NLP tasks, creative works, autonomous agency tasks), human-LLM interaction styles (single-turn instruction, multi-turn chat), and format types (inclusion, wrapping, length, coding). Moreover, each task in FormatBench is attached with a format checker program. Extensive experiments on the benchmark reveal that state-of-the-art open- and closed-source LLMs still suffer from severe deficiency in format faithfulness. By virtue of the decidable nature of formats, we propose to Reinforce Format Faithfulness (ReFF) to help LLMs generate formatted output as instructed without compromising general quality. Without any annotated data, ReFF can substantially improve the format faithfulness rate (e.g., from 21.6% in original LLaMA3 to 95.0% on caption segmentation task), while keep the general quality comparable (e.g., from 47.3 to 46.4 in F1 scores). Combined with labeled training data, ReFF can simultaneously improve both format faithfulness (e.g., from 21.6% in original LLaMA3 to 75.5%) and general quality (e.g., from 47.3 to 61.6 in F1 scores). We further offer an interpretability analysis to explain how ReFF improves both format faithfulness and general quality.

PDF Details DOI

JBHI Journal 2024 Journal Article

Integrating Smart Computility for Subflow Orchestration in Remote Virtual Services

Liang Wang
Wei Su
Fei Song
IIsun You

The burgeoning domain of the metaverse has sparked significant interest from a diverse array of industries, including healthcare services. However, the metaverse and its associated applications present various challenges to existing networks. First, to meet the increasing demands of the metaverse, there is a need for enhanced bandwidth, reduced latency, and improved packet loss control. Furthermore, the transmission mechanism should exhibit flexibility to automatically adapt to the diverse hybrid needs of different healthcare services. In this article, a multipath transmission-based paradigm tailored for the metaverse-based healthcare services is developed. Significantly, we devise an orchestration framework to reconcile edge-side subflow management with diverse healthcare applications. Using machine learning techniques, the framework can produce near-optimal subflow adjustment strategies for client nodes and miscellaneous services. Comprehensive experiments are performed on applications with diverse requirements to validate the adaptability of the framework to the application needs. The experimental results demonstrate that the proposed method enables the network to autonomously adapt to changing network conditions and service requirements. This includes applications' preferences for high throughput, low delay, and high stability. Moreover, the test results show that the proposed approach can notably decrease the occurrences of network quality falling below the minimum requirement. Given its adaptability and impact on network quality, this work paves the way for future metaverse-based healthcare services.

Details DOI

AAAI Conference 2023 Conference Paper

Referring Expression Comprehension Using Language Adaptive Inference

Wei Su
Peihan Miao
Huanzhang Dou
Yongjian Fu
Xi Li

Different from universal object detection, referring expression comprehension (REC) aims to locate specific objects referred to by natural language expressions. The expression provides high-level concepts of relevant visual and contextual patterns, which vary significantly with different expressions and account for only a few of those encoded in the REC model. This leads us to a question: do we really need the entire network with a fixed structure for various referring expressions? Ideally, given an expression, only expression-relevant components of the REC model are required. These components should be small in number as each expression only contains very few visual and contextual clues. This paper explores the adaptation between expressions and REC models for dynamic inference. Concretely, we propose a neat yet efficient framework named Language Adaptive Dynamic Subnets (LADS), which can extract language-adaptive subnets from the REC model conditioned on the referring expressions. By using the compact subnet, the inference can be more economical and efficient. Extensive experiments on RefCOCO, RefCOCO+, RefCOCOg, and Referit show that the proposed method achieves faster inference speed and higher accuracy against state-of-the-art approaches.

PDF Details DOI