Search Results for author: Zhuo Li

Found 49 papers, 14 papers with code

机器音译研究综述(Survey on Machine Transliteration)

no code implementations CCL 2022 Zhuo Li, Zhijuan Wang, Xiaobing Zhao

“机器音译是基于语音相似性自动将文本从一种语言转换为另一种语言的过程, 它是机器翻译的一个子任务, 侧重于语音信息的翻译。音译后可知道源单词在另一种语言中的发音, 使不熟悉源语言的人更容易理解该语言, 有益于消除语言和拼写障碍。机器音译在多语言文本处理、语料库对齐、信息抽取等自然语言应用中发挥着重要作用。本文阐述了目前机器音译任务中存在的挑战, 对主要的音译方法进行了剖析、分类和整理, 对音译数据集进行了罗列汇总, 并列出了常用的音译效果评价指标, 最后对该领域目前存在的问题进行了说明并对音译学的未来进行了展望。本文以期对进入该领域的新人提供快速的入门指南, 或供其他研究者参考。”

Transliteration

Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach

no code implementations26 Mar 2025 Xuying Li, Zhuo Li, Yuji Kosuga, Victor Bian

In this work, we propose a Group Relative Policy Optimization (GRPO) framework with a multi-label reward regression model to achieve safe and aligned language generation.

Text Generation

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking

no code implementations2 Mar 2025 Xuying Li, Zhuo Li, Yuji Kosuga, Victor Bian

Large Language Models (LLMs) have demonstrated strong reasoning capabilities, but their safety under adversarial conditions remains a challenge.

Simplify RLHF as Reward-Weighted SFT: A Variational Method

no code implementations16 Feb 2025 Yuhao Du, Zhuo Li, Pengyu Cheng, Zhihong Chen, Yuejiao Xie, Xiang Wan, Anningzhe Gao

More specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into a reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness.

Variational Inference

Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration

no code implementations19 Dec 2024 Junjia Liu, Zhuo Li, Minghao Yu, Zhipeng Dong, Sylvain Calinon, Darwin Caldwell, Fei Chen

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor.

Human-Object Interaction Detection motion retargeting

Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation

no code implementations5 Dec 2024 Xuying Li, Zhuo Li, Yuji Kosuga, Yasuhiro Yoshida, Victor Bian

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.

Fairness RAG

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

no code implementations22 Nov 2024 Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao liu, Hong Chang, Zimo Liu, Chen Li

Human motion generation plays a vital role in applications such as digital humans and humanoid robot control.

MORPH Motion Generation

Precision Knowledge Editing: Enhancing Safety in Large Language Models

no code implementations2 Oct 2024 Xuying Li, Zhuo Li, Yuji Kosuga, Yasuhiro Yoshida, Victor Bian

Large language models (LLMs) have demonstrated remarkable capabilities, but they also pose risks related to the generation of toxic or harmful content.

knowledge editing Management

Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs

no code implementations3 Sep 2024 Zhuo Li, Yuhao Du, Jinpeng Hu, Xiang Wan, Anningzhe Gao

To address these challenges, we introduce a self-instructed in-context learning framework that empowers LLMs to deliver more effective responses by generating reliable derived prompts to construct informative contextual environments.

In-Context Learning

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

1 code implementation30 Aug 2024 Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun, Chenghao Liu

Surprisingly, without further adaptation in the time-series domain, the proposed VisionTS could achieve superior zero-shot forecasting performance compared to existing TSF foundation models.

Image Reconstruction Time Series +1

Atoxia: Red-teaming Large Language Models with Target Toxic Answers

no code implementations27 Aug 2024 Yuhao Du, Zhuo Li, Pengyu Cheng, Xiang Wan, Anningzhe Gao

Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM.

Prompt Engineering Red Teaming

Extracting Clean and Balanced Subset for Noisy Long-tailed Classification

no code implementations10 Apr 2024 Zhuo Li, He Zhao, Zhen Li, Tongliang Liu, Dandan Guo, Xiang Wan

To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples.

Pseudo Label

PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning

no code implementations23 Feb 2024 Zhisheng Lin, Han Fu, Chenghao Liu, Zhuo Li, Jianling Sun

However, current approaches typically either train adapters on individual tasks or distill shared knowledge from source tasks, failing to fully exploit task-specific knowledge and the correlation between source and target tasks.

Mixture-of-Experts parameter-efficient fine-tuning +1

Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques

no code implementations4 Feb 2024 Qiheng Mao, Zemin Liu, Chenghao Liu, Zhuo Li, Jianling Sun

This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL.

Graph Representation Learning

GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting

no code implementations25 Jan 2024 Butian Xiong, Zhuo Li, Zhen Li

We introduce a novel large-scale scene reconstruction benchmark using the newly developed 3D representation approach, Gaussian Splatting, on our expansive U-Scene dataset.

3D Reconstruction

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift

2 code implementations23 Oct 2023 Mouxiang Chen, Lefei Shen, Han Fu, Zhuo Li, Jianling Sun, Chenghao Liu

In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained model.

Time Series Time Series Forecasting

Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank

1 code implementation27 Sep 2023 Mouxiang Chen, Chenghao Liu, Zemin Liu, Zhuo Li, Jianling Sun

Unbiased Learning to Rank (ULTR) aims to train unbiased ranking models from biased click logs, by explicitly modeling a generation process for user behavior and fitting click data based on examination hypothesis.

Learning-To-Rank

The Impact of Silence on Speech Anti-Spoofing

no code implementations21 Sep 2023 Yuxiang Zhang, Zhuo Li, Jingze Lu, Hua Hua, Wenchao Wang, Pengyuan Zhang

First, the reasons for the impact are explored, including the proportion of silence duration and the content of silence.

Action Detection Activity Detection +2

Visible and NIR Image Fusion Algorithm Based on Information Complementarity

no code implementations19 Sep 2023 Zhuo Li, Bo Li

Second, to generate the initial visible-NIR complementarity weight map, the difference maps of visible and NIR are filtered by the extend-DoG filter.

Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL

no code implementations20 Aug 2023 Yechen Zhang, Jian Sun, Gang Wang, Zhuo Li, Wei Chen

Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games.

Atari Games continuous-control +2

Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification

no code implementations22 May 2023 Zhuo Li, Jingze Lu, Zhenduo Zhao, Wenchao Wang, Pengyuan Zhang

Utilizing the large-scale unlabeled data from the target domain via pseudo-label clustering algorithms is an important approach for addressing domain adaptation problems in speaker verification tasks.

Clustering Diversity +5

Self-Edit: Fault-Aware Code Editor for Code Generation

1 code implementation6 May 2023 Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin

Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task.

Code Generation HumanEval

Implant Global and Local Hierarchy Information to Sequence based Code Representation Models

1 code implementation14 Mar 2023 Kechi Zhang, Zhuo Li, Zhi Jin, Ge Li

Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.

EdgeYOLO: An Edge-Real-Time Object Detector

1 code implementation15 Feb 2023 Shihan Liu, Junlin Zha, Jian Sun, Zhuo Li, Gang Wang

This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms.

Data Augmentation Edge-computing +1

Neural Episodic Control with State Abstraction

no code implementations27 Jan 2023 Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, Yan Zheng, Yan Song, Yingfeng Chen, Jianjun Zhao

Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms.

Deep Reinforcement Learning MuJoCo +1

Convolution-enhanced Evolving Attention Networks

1 code implementation16 Dec 2022 Yujing Wang, Yaming Yang, Zhuo Li, Jiangang Bai, Mingliang Zhang, Xiangtai Li, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong

To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps.

Image Classification Machine Translation +3

Poison Attack and Defense on Deep Source Code Processing Models

no code implementations31 Oct 2022 Jia Li, Zhuo Li, Huangzhao Zhang, Ge Li, Zhi Jin, Xing Hu, Xin Xia

The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.

Clone Detection Code Repair +1

CodeEditor: Learning to Edit Source Code with Pre-trained Models

1 code implementation31 Oct 2022 Jia Li, Ge Li, Zhuo Li, Zhi Jin, Xing Hu, Kechi Zhang, Zhiyi Fu

Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.

Language Modeling Language Modelling +1

Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion

no code implementations13 Oct 2022 Yuxiang Zhang, Jingze Lu, Xingming Wang, Zhuo Li, Runqiu Xiao, Wenchao Wang, Ming Li, Pengyuan Zhang

The overfitting of the model to the training set leads to extreme values of the scores and low correlation of the score distributions, which makes score fusion difficult.

Data Augmentation DeepFake Detection +1

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

no code implementations5 Aug 2022 Dandan Guo, Zhuo Li, Meixi Zheng, He Zhao, Mingyuan Zhou, Hongyuan Zha

Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set.

Bilevel Optimization imbalanced classification

Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases

no code implementations5 Jul 2022 Zhihao Yuan, Xu Yan, Zhuo Li, Xuhao Li, Yao Guo, Shuguang Cui, Zhen Li

Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description.

Object Representation Learning +3

SASV Based on Pre-trained ASV System and Integrated Scoring Module

no code implementations1 Jul 2022 Yuxiang Zhang, Zhuo Li, Wenchao Wang, Pengyuan Zhang

Based on the assumption that there is a correlation between anti-spoofing and speaker verification, a Total-Divide-Total integrated Spoofing-Aware Speaker Verification (SASV) system based on pre-trained automatic speaker verification (ASV) system and integrated scoring module is proposed and submitted to the SASV 2022 Challenge.

Speaker Verification

Geometry-Based Stochastic Probability Models for the LoS and NLoS Paths of A2G Channels under Urban Scenario

no code implementations19 May 2022 Minghui Pang, Qiuming Zhu, Cheng-Xiang Wang, Zhipeng Lin, Junyu Liu, Chongyu Lv, Zhuo Li

Path probability prediction is essential to describe the dynamic birth and death of propagation paths, and build the accurate channel model for air-to-ground (A2G) communications.

Graph Enhanced Contrastive Learning for Radiology Findings Summarization

1 code implementation ACL 2022 Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan, Tsung-Hui Chang

To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i. e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation.

Contrastive Learning

Height-Dependent LoS Probability Model for A2G MmWave Communications under Built-up Scenarios

no code implementations6 Sep 2021 Minghui Pang, Qiuming Zhu, Fei Bai, Zhuo Li, Hanpeng Li, Kai Mao, Yue Tian

Based on the three-dimensional propagation characteristic under built-up scenarios, a height-dependent line-of-sight (LoS) probability model for air-to-ground (A2G) millimeter wave (mmWave) communications is proposed in this paper.

SDN Controller Load Balancing Based on Reinforcement Learning

no code implementations11 Mar 2021 Zhuo Li, Xu Zhou, Junruo Gao, Yifang Qin

Under the constraint of the best efficiency of migration in the whole and without migration conflict, selecting multiple sets of triples based on reinforcement learning, as the final migration of this round to attain the global optimal controller load balancing with minimum cost.

Networking and Internet Architecture

An Optimal-Transport-Based Reinforcement Learning Approach for Computation Offloading

no code implementations11 Mar 2021 Zhuo Li, Xu Zhou, Taixin Li, Yang Liu

With the mass deployment of computing-intensive applications and delay-sensitive applications on end devices, only adequate computing resources can meet differentiated services' delay requirements.

Edge-computing Networking and Internet Architecture

A Machine Learning Framework for Data Ingestion in Document Images

no code implementations11 Feb 2020 Han Fu, Yunyu Bai, Zhuo Li, Jun Shen, Jianling Sun

Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations.

BIG-bench Machine Learning

Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation

1 code implementation19 Dec 2019 Jian Peng, Bo Tang, Hao Jiang, Zhuo Li, Yinjie Lei, Tao Lin, Haifeng Li

It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference.

Image Classification

Kernelized Multiview Subspace Analysis by Self-weighted Learning

no code implementations23 Nov 2019 Huibing Wang, Yang Wang, Zhao Zhang, Xianping Fu, Zhuo Li, Mingliang Xu, Meng Wang

With the popularity of multimedia technology, information is always represented or transmitted from multiple views.

Dimensionality Reduction Image Retrieval +1

Understanding the Importance of Single Directions via Representative Substitution

no code implementations20 Jan 2019 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

Overcoming Catastrophic Forgetting by Soft Parameter Pruning

1 code implementation4 Dec 2018 Jian Peng, Jiang Hao, Zhuo Li, Enqiang Guo, Xiaohong Wan, Deng Min, Qing Zhu, Haifeng Li

In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time.

Continual Learning

Understanding the Importance of Single Directions via Representative Substitution

no code implementations27 Nov 2018 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

Cannot find the paper you are looking for? You can Submit a new open access paper.