Author name cluster

Xiangyu Ren

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.

3 papers

2 author rows

IROS Conference 2025 Conference Paper

Design and Control of a 6-DOF Fully Actuated Aerial-Aquatic Robot with Thrust Vectoring

Bocheng Tian
Yuchen Liu
Xiangyu Ren
Donghe Chen
Zonghao Zuo
Li Wen

Single-medium, multi-degree-of-freedom robots often face limitations in aerial-aquatic tasks due to structural and weight constraints, which compromise their mobility in both air and water. To address this, we introduce a 6-degree-of-freedom fully actuated aerial-aquatic robot that employs thrust vectoring for enhanced performance. This innovative design incorporates four servos and four motors to facilitate coordinated operation. In air mode, the robot achieves decoupled control of attitude and position through servo angle feedforward compensation combined with dual-loop control. In underwater mode, it ensures high maneuverability by utilizing a dynamic model similar to a "weightless" state, employing single-loop control. Experimental results demonstrate that the robot can perform fully actuated movements in both air and water, successfully navigate the air-water boundary, and deploy sensors on inclined surfaces. These capabilities highlight the robot’s significant future application prospects.

Details

AAAI Conference 2025 Conference Paper

Multi-Instance Multi-Label Classification from Crowdsourced Labels

Ziquan Wang
Mingxuan Xia
Xiangyu Ren
Jiaqing Zhou
Gengyu Lyu
Tianlei Hu
Haobo Wang

Multi-instance multi-label classification (MIML) is a fundamental task in machine learning, where each data sample comprises a bag containing several instances and multiple binary labels. Despite its wide applications, the data collection process involves matching multiple instances and labels, typically resulting in high annotation costs. In this paper, we study a novel yet practical crowdsourced multi-instance multi-label classification (CMIML) setup, where labels are collected from multiple crowd sources. To address this problem, we first propose a novel data generation process for CMIML, i.e., cross-label transition, where cross-label annotation error is more likely to appear rather than previous single-label transition assumption, due to the inherent similarity of localized instances from different classes. Then, we formally define the cross-label transition by cross-label transition matrices which are dependent across classes. Subsequently, we establish the first unbiased risk estimator for CMIML and further improve it through aggregation techniques, along with a rigorous generalization error bound. We also provide a practical implementation of cross-label transition matrix estimation. Comprehensive experiments on six benchmark datasets under various scenarios demonstrate that our algorithm outperforms the baselines by a large margin, validating its effectiveness in handling the CMIML problem.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models

Xindi Wang
Mahsa Salmani
Parsa Omidi
Xiangyu Ren
Mehdi Rezagholizadeh
Armaghan Eshaghi

Recently, large language models (LLMs) have shown remarkable capabilities including understanding context, engaging in logical reasoning, and generating responses. However, this is achieved at the expense of stringent computational and memory requirements, hindering their ability to effectively support long input sequences. This survey provides an inclusive review of the recent techniques and methods devised to extend the sequence length in LLMs, thereby enhancing their capacity for long-context understanding. In particular, we review and categorize a wide range of techniques including architectural modifications, such as modified positional encoding and altered attention mechanisms, which are designed to enhance the processing of longer sequences while avoiding a proportional increase in computational cost. The diverse methodologies investigated in this study can be leveraged across different phases of LLMs, i. e. , training, fine-tuning and inference. This enables LLMs to efficiently process extended sequences. The limitations of the current methodologies is discussed in the last section along with the suggestions for future research directions, underscoring the importance of sequence length in the continued advancement of LLMs.

PDF Details DOI