Search Results for author: Zuozhu Liu

Found 56 papers, 29 papers with code

M-MAD: Multidimensional Multi-Agent Debate Framework for Fine-grained Machine Translation Evaluation

1 code implementation28 Dec 2024 Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren, Yan Zhang, Jian Wu, Hongwei Wang, Zuozhu Liu

Recent advancements in large language models (LLMs) have given rise to the LLM-as-a-judge paradigm, showcasing their potential to deliver human-like judgments.

Machine Translation

MedCoT: Medical Chain of Thought via Hierarchical Expert

1 code implementation18 Dec 2024 Jiaxiang Liu, YuAn Wang, Jiawei Du, Joey Tianyi Zhou, Zuozhu Liu

Artificial intelligence has advanced in Medical Visual Question Answering (Med-VQA), but prevalent research tends to focus on the accuracy of the answers, often overlooking the reasoning paths and interpretability, which are crucial in clinical settings.

Medical Visual Question Answering Question Answering +1

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

1 code implementation10 Dec 2024 Jianhong Bai, Menghan Xia, Xintao Wang, Ziyang Yuan, Xiao Fu, Zuozhu Liu, Haoji Hu, Pengfei Wan, Di Zhang

Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency.

4D reconstruction Video Generation

PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray

no code implementations6 Nov 2024 Wen Ma, Huikai Wu, Zikai Xiao, Yang Feng, Jian Wu, Zuozhu Liu

Reconstructing the 3D anatomical structures of the oral cavity, which originally reside in the cone-beam CT (CBCT), from a single 2D Panoramic X-ray(PX) remains a critical yet challenging task, as it can effectively reduce radiation risks and treatment costs during the diagnostic in digital dentistry.

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest

no code implementations27 Oct 2024 Xupeng Chen, Zhixin Lai, Kangrui Ruan, Shichu Chen, Jiaxiang Liu, Zuozhu Liu

Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e. g., bounding boxes).

Medical Visual Question Answering Multiple-choice +2

FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

no code implementations25 Oct 2024 Zhiting Fan, Ruizhe Chen, Tianxiang Hu, Zuozhu Liu

Based on this, we curate a challenging dataset, \texttt{FairMT-1K}, and test 15 current state-of-the-art (SOTA) LLMs on this dataset.

Benchmarking Fairness +1

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment

no code implementations20 Oct 2024 Songtao Jiang, Yan Zhang, Ruizhe Chen, Yeying Jin, Zuozhu Liu

To address this, we propose Modality-Fair Preference Optimization (MFPO) to balance text and image preferences.

PAD: Personalized Alignment of LLMs at Decoding-Time

no code implementations5 Oct 2024 Ruizhe Chen, Xiaotian Zhang, Meng Luo, Wenhao Chai, Zuozhu Liu

Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational costs and data demands of traditional alignment methods.

Text Generation

Editable Fairness: Fine-Grained Bias Mitigation in Language Models

no code implementations7 Aug 2024 Ruizhe Chen, Yichen Li, Jianfei Yang, Joey Tianyi Zhou, Zuozhu Liu

Then, we propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.

Fairness

EC-Guide: A Comprehensive E-Commerce Guide for Instruction Tuning and Quantization

1 code implementation6 Aug 2024 Zhaopeng Feng, Zijie Meng, Zuozhu Liu

Large language models (LLMs) have attracted considerable attention in various fields for their cost-effective solutions to diverse challenges, especially with advancements in instruction tuning and quantization.

Quantization

VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary

1 code implementation28 Jul 2024 Hanjun Luo, Ziye Deng, Haoyu Huang, Xuecheng Liu, Ruizhe Chen, Zuozhu Liu

However, existing methods are designed for specific models with fixed prompts, limiting their adaptability to the fast-evolving models and diverse practical scenarios.

Attribute Fairness +3

BIGbench: A Unified Benchmark for Social Bias in Text-to-Image Generative Models Based on Multi-modal LLM

1 code implementation21 Jul 2024 Hanjun Luo, Haoyu Huang, Ziye Deng, Xuecheng Liu, Ruizhe Chen, Zuozhu Liu

Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, which also raises concerns about the social biases in their outputs, especially in the human generation.

Image Generation

BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs

no code implementations14 Jul 2024 Zhiting Fan, Ruizhe Chen, Ruiling Xu, Zuozhu Liu

Evaluating the bias in Large Language Models (LLMs) becomes increasingly crucial with their rapid development.

Bias Detection Question Answering +3

DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models

no code implementations1 Jul 2024 Jiabao Pan, Yan Zhang, Chen Zhang, Zuozhu Liu, Hongwei Wang, Haizhou Li

Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via popular Chains-of-Thought (COT) prompting.

Decision Making

Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level

3 code implementations22 Jun 2024 Zhaopeng Feng, Ruizhe Chen, Yan Zhang, Zijie Meng, Zuozhu Liu

By utilizing Gemma-2B/7B as the backbone, MT-Ladder-2B can elevate raw translations to the level of top-tier open-source models (e. g., refining BigTranslate-13B with +6. 91 BLEU and +3. 52 COMET for XX-En), and MT-Ladder-7B can further enhance model performance to be on par with the state-of-the-art GPT-4.

Machine Translation Translation

FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models

1 code implementation28 May 2024 Hanjun Luo, Ziye Deng, Ruizhe Chen, Zuozhu Liu

The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have raised concerns about the biases in their outputs, but existing research lacks a holistic definition and evaluation framework of biases, limiting the enhancement of debiasing techniques.

Learnable Privacy Neurons Localization in Language Models

no code implementations16 May 2024 Ruizhe Chen, Tianxiang Hu, Yang Feng, Zuozhu Liu

To bridge this gap, we introduce a pioneering method for pinpointing PII-sensitive neurons (privacy neurons) within LLMs.

Memorization Specificity

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing

no code implementations15 May 2024 Ruizhe Chen, Yichen Li, Zikai Xiao, Zuozhu Liu

Existing debiasing methods inevitably make unreasonable or undesired predictions as they are designated and evaluated to achieve parity across different social groups but leave aside individual facts, resulting in modified existing knowledge.

Fairness knowledge editing +4

MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale

no code implementations18 Apr 2024 Xiaotang Gai, Chenyi Zhou, Jiaxiang Liu, Yang Feng, Jian Wu, Zuozhu Liu

Medical Visual Question Answering (MedVQA), which offers language responses to image-based medical inquiries, represents a challenging task and significant advancement in healthcare.

Decision Making Medical Visual Question Answering +2

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

2 code implementations16 Apr 2024 Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making.

Image Classification Question Answering +1

Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models

1 code implementation6 Apr 2024 Songtao Jiang, Yan Zhang, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, Zuozhu Liu

In this paper, we present a novel approach, Joint Visual and Text Prompting (VTPrompt), that employs fine-grained visual information to enhance the capability of MLLMs in VQA, especially for object-oriented perception.

MME Object +2

UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

no code implementations20 Feb 2024 Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, Jiang Bian

Recent advances in text-guided video editing have showcased promising results in appearance editing (e. g., stylization).

Video Editing

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

1 code implementation17 Jan 2024 Zikai Xiao, Zihan Chen, Liyinglan Liu, Yang Feng, Jian Wu, Wanlu Liu, Joey Tianyi Zhou, Howard Hao Yang, Zuozhu Liu

Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution, has garnered considerable attention in recent times.

Personalized Federated Learning Representation Learning

DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs

2 code implementations10 Jan 2024 Zijie Meng, Yan Zhang, Zhaopeng Feng, Zuozhu Liu

Subsequently, we propose Filter Choices based Reasoning (FCR) to improve model performance on MCQs with low ($\mathcal{CS}$).

Question Answering

TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer

1 code implementation22 Nov 2023 Huimin Xiong, Kunle Li, Kaiyuan Tan, Yang Feng, Joey Tianyi Zhou, Jin Hao, Haochao Ying, Jian Wu, Zuozhu Liu

Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva.

Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models

1 code implementation15 Nov 2023 Tingyu Xie, Qi Li, Yan Zhang, Zuozhu Liu, Hongwei Wang

Exploring the application of powerful large language models (LLMs) on the named entity recognition (NER) task has drawn much attention recently.

In-Context Learning named-entity-recognition +3

How Well Do Text Embedding Models Understand Syntax?

1 code implementation14 Nov 2023 Yan Zhang, Zhaopeng Feng, Zhiyang Teng, Zuozhu Liu, Haizhou Li

Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data.

Empirical Study of Zero-Shot NER with ChatGPT

1 code implementation16 Oct 2023 Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, Hongwei Wang

Large language models (LLMs) exhibited powerful capability in various natural language processing tasks.

Arithmetic Reasoning named-entity-recognition +3

Towards Distribution-Agnostic Generalized Category Discovery

1 code implementation NeurIPS 2023 Jianhong Bai, Zuozhu Liu, Hualiang Wang, Ruizhe Chen, Lianrui Mu, Xiaomeng Li, Joey Tianyi Zhou, Yang Feng, Jian Wu, Haoji Hu

In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting.

Contrastive Learning Transfer Learning

ToothSegNet: Image Degradation meets Tooth Segmentation in CBCT Images

no code implementations5 Jul 2023 Jiaxiang Liu, Tianxiang Hu, Yang Feng, Wanghui Ding, Zuozhu Liu

In computer-assisted orthodontics, three-dimensional tooth models are required for many medical treatments.

Decoder Image Segmentation +3

A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis

no code implementations5 Jul 2023 Jiaxiang Liu, Tianxiang Hu, Yan Zhang, Xiaotang Gai, Yang Feng, Zuozhu Liu

Recent advances in pretrained vision-language models (VLMs) such as CLIP have shown great performance for zero-shot natural image recognition and exhibit benefits in medical applications.

Image Classification Medical Image Classification

On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning

2 code implementations8 Jun 2023 Jianhong Bai, Zuozhu Liu, Hualiang Wang, Jin Hao, Yang Feng, Huanpeng Chu, Haoji Hu

Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are expensive to collect.

Long-tail Learning Representation Learning +1

DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes

2 code implementations15 Feb 2023 Shenghao Hao, Peiyuan Liu, Yibing Zhan, Kaixun Jin, Zuozhu Liu, Mingli Song, Jenq-Neng Hwang, Gaoang Wang

Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including 1) missing real-world scenarios, 2) lacking diverse scenes, 3) owning a limited number of tracks, 4) comprising only static cameras, and 5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods.

Multi-Object Tracking Object +2

Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

1 code implementation30 Oct 2022 Yiming Chen, Yan Zhang, Bin Wang, Zuozhu Liu, Haizhou Li

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals.

Domain Adaptation Sentence +3

TFormer: 3D Tooth Segmentation in Mesh Scans with Geometry Guided Transformer

no code implementations29 Oct 2022 Huimin Xiong, Kunle Li, Kaiyuan Tan, Yang Feng, Joey Tianyi Zhou, Jin Hao, Zuozhu Liu

Optical Intra-oral Scanners (IOS) are widely used in digital dentistry, providing 3-Dimensional (3D) and high-resolution geometrical information of dental crowns and the gingiva.

Multi-Task Learning Segmentation

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning

1 code implementation22 Aug 2022 Hualiang Wang, Siming Fu, Xiaoxuan He, Hangxiang Fang, Zuozhu Liu, Haoji Hu

To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient.

Image Classification Instance Segmentation +1

Towards Federated Long-Tailed Learning

no code implementations30 Jun 2022 Zihan Chen, Songshang Liu, Hualiang Wang, Howard H. Yang, Tony Q. S. Quek, Zuozhu Liu

Data privacy and class imbalance are the norm rather than the exception in many machine learning tasks.

Federated Learning

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

no code implementations11 Mar 2022 Jin Hao, Jiaxiang Liu, Jin Li, Wei Pan, Ruizhe Chen, Huimin Xiong, Kaiwei Sun, Hangzheng Lin, Wanlu Liu, Wanghui Ding, Jianfei Yang, Haoji Hu, Yueling Zhang, Yang Feng, Zeyu Zhao, Huikai Wu, Youyi Zheng, Bing Fang, Zuozhu Liu, Zhihe Zhao

Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information.

Segmentation

Federated Stochastic Gradient Descent Begets Self-Induced Momentum

no code implementations17 Feb 2022 Howard H. Yang, Zuozhu Liu, Yaru Fu, Tony Q. S. Quek, H. Vincent Poor

Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems, in which a server and a host of clients collaboratively train a statistical model utilizing the data and computation resources of the clients without directly exposing their privacy-sensitive data.

Federated Learning

An Unsupervised Sentence Embedding Method by Mutual Information Maximization

1 code implementation EMNLP 2020 Yan Zhang, Ruidan He, Zuozhu Liu, Kwan Hui Lim, Lidong Bing

However, SBERT is trained on corpus with high-quality labeled sentence pairs, which limits its application to tasks where labeled data is extremely scarce.

Clustering Self-Supervised Learning +5

Biologically Plausible Sequence Learning with Spiking Neural Networks

no code implementations25 Nov 2019 Zuozhu Liu, Thiparat Chotibut, Christopher Hillar, Shaowei Lin

Motivated by the celebrated discrete-time model of nervous activity outlined by McCulloch and Pitts in 1943, we propose a novel continuous-time model, the McCulloch-Pitts network (MPN), for sequence learning in spiking neural networks.

Scheduling Policies for Federated Learning in Wireless Networks

no code implementations17 Aug 2019 Howard H. Yang, Zuozhu Liu, Tony Q. S. Quek, H. Vincent Poor

Due to limited bandwidth, only a portion of UEs can be scheduled for updates at each iteration.

Information Theory Signal Processing Information Theory

Vprop: Variational Inference using RMSprop

no code implementations4 Dec 2017 Mohammad Emtiyaz Khan, Zuozhu Liu, Voot Tangkaratt, Yarin Gal

Overall, this paper presents Vprop as a principled, computationally-efficient, and easy-to-implement method for Bayesian deep learning.

Deep Learning Variational Inference

Variational Probability Flow for Biologically Plausible Training of Deep Neural Networks

no code implementations21 Nov 2017 Zuozhu Liu, Tony Q. S. Quek, Shaowei Lin

The quest for biologically plausible deep learning is driven, not just by the desire to explain experimentally-observed properties of biological neural networks, but also by the hope of discovering more efficient methods for training artificial networks.

Biologically-plausible Training

Variational Adaptive-Newton Method for Explorative Learning

no code implementations15 Nov 2017 Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen

We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning.

Active Learning reinforcement-learning +3

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