Search Results for author: Fei Yu

Found 38 papers, 12 papers with code

Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs

no code implementations16 Feb 2025 Fei Yu, Yingru Li, Benyou Wang

Value model-guided search is effective in steering the generation but suffers from scaling flaws: Its superiority diminishes with larger sample sizes, underperforming non-search baselines.

GSM8K Thompson Sampling +1

Scene Understanding Enabled Semantic Communication with Open Channel Coding

no code implementations24 Jan 2025 Zhe Xiang, Fei Yu, Quan Deng, Yuandi Li, Zhiguo Wan

This approach prioritizes high-level semantic information, improving robustness and reducing redundancy across modalities like text, speech, and images.

Question Answering Scene Understanding +2

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models

1 code implementation9 Jan 2025 Qingyu Ren, Jie Zeng, Qianyu He, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints.

Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering

no code implementations30 Dec 2024 Junxiao Xue, Quan Deng, Fei Yu, Yanhao Wang, Jun Wang, Yuehua Li

Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning, and content retrieval.

Image Captioning Object Recognition +4

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

no code implementations16 Dec 2024 Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Abdulmohsen Alharthik, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Zhuoheng Ma, Yuhao Du, He Zhang, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to state-of-the-art offerings like GPT-4 or ChatGPT 3. 5, due to a predominant focus on mainstream languages (e. g., English and Chinese).

Pilot-guided Multimodal Semantic Communication for Audio-Visual Event Localization

no code implementations9 Dec 2024 Fei Yu, Zhe Xiang, Nan Che, Zhuoran Zhang, Yuandi Li, Junxiao Xue, Zhiguo Wan

Existing methods often focus on single modality tasks and fail to handle multimodal stream data, such as video and audio, and their corresponding tasks.

audio-visual event localization Autonomous Driving +1

Multimodal Trustworthy Semantic Communication for Audio-Visual Event Localization

no code implementations4 Nov 2024 Yuandi Li, Zhe Xiang, Fei Yu, Zhangshuang Guan, Hui Ji, Zhiguo Wan, Cheng Feng

This letter introduces MMTrustSC, a novel framework designed to address these challenges by enhancing the security and reliability of multimodal communication.

audio-visual event localization Semantic Communication

Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search

no code implementations14 Oct 2024 Chenglin Li, Qianglong Chen, Zhi Li, Feng Tao, Yicheng Li, Hao Chen, Fei Yu, Yin Zhang

With tree search and evaluation models, it can efficiently guide each instruction to evolve into a high-quality form, aiding in instruction fine-tuning.

Instruction Following

Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression

1 code implementation28 Aug 2024 Haowen Hou, Fei Ma, Binwen Bai, Xinxin Zhu, Fei Yu

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks.

PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods

1 code implementation9 Jul 2024 Yiying Wang, Xiaojing Li, Binzhu WANG, Yueyang Zhou, Yingru Lin, Han Ji, Hong Chen, Jinshi Zhang, Fei Yu, Zewei Zhao, Song Jin, Renji Gong, Wanqing Xu

In domain-specific applications, GPT-4, augmented with precise prompts or Retrieval-Augmented Generation (RAG), shows notable potential but faces the critical tri-lemma of performance, cost, and data privacy.

Information Retrieval LEMMA +3

Towards Secure and Efficient Data Scheduling for Vehicular Social Networks

no code implementations28 Jun 2024 Youhua Xia, Tiehua Zhang, Jiong Jin, Ying He, Fei Yu

Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks.

Q-Learning Scheduling

MileBench: Benchmarking MLLMs in Long Context

no code implementations29 Apr 2024 Dingjie Song, Shunian Chen, Guiming Hardy Chen, Fei Yu, Xiang Wan, Benyou Wang

Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope.

Benchmarking

MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction

no code implementations19 Jan 2024 Hao Qian, Hongting Zhou, Qian Zhao, Hao Chen, Hongxiang Yao, Jingwei Wang, Ziqi Liu, Fei Yu, Zhiqiang Zhang, Jun Zhou

The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment.

Graph Neural Network

OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning

1 code implementation16 Nov 2023 Fei Yu, Anningzhe Gao, Benyou Wang

These findings offer a novel perspective on the role of outcome supervision in training value models for multi-step reasoning tasks and provide theoretical justification for its advantage in value estimation for guided decoding.

Arithmetic Reasoning GSM8K +1

Data-Centric Financial Large Language Models

no code implementations7 Oct 2023 Zhixuan Chu, Huaiyu Guo, Xinyuan Zhou, Yijia Wang, Fei Yu, Hong Chen, Wanqing Xu, Xin Lu, Qing Cui, Longfei Li, Jun Zhou, Sheng Li

Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.

Financial Analysis

AceGPT, Localizing Large Language Models in Arabic

1 code implementation21 Sep 2023 Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Juncai He, Ziche Liu, Zhiyi Zhang, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.

Instruction Following Language Modeling +3

AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition

no code implementations30 Aug 2023 Nan Che, Chenrui Liu, Fei Yu

In particular, there is no public common data set for the research field of sound event recognition for the data set of the indoor environmental sound scene.

Stochastic Step-wise Feature Selection for Exponential Random Graph Models (ERGMs)

no code implementations24 Jul 2023 Helal El-Zaatari, Fei Yu, Michael R Kosorok

Statistical analysis of social networks provides valuable insights into complex network interactions across various scientific disciplines.

feature selection Variable Selection

HuatuoGPT, towards Taming Language Model to Be a Doctor

2 code implementations24 May 2023 Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu, Zhihong Chen, Jianquan Li, Guiming Chen, Xiangbo Wu, Zhiyi Zhang, Qingying Xiao, Xiang Wan, Benyou Wang, Haizhou Li

Experimental results demonstrate that HuatuoGPT achieves state-of-the-art results in performing medical consultation among open-source LLMs in GPT-4 evaluation, human evaluation, and medical benchmark datasets.

Language Modeling Language Modelling +1

Natural Language Reasoning, A Survey

1 code implementation26 Mar 2023 Fei Yu, Hongbo Zhang, Prayag Tiwari, Benyou Wang

This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically.

Logical Reasoning Mathematical Reasoning +5

Accurate 3D Face Reconstruction with Facial Component Tokens

no code implementations ICCV 2023 Tianke Zhang, Xuangeng Chu, Yunfei Liu, Lijian Lin, Zhendong Yang, Zhengzhuo Xu, Chengkun Cao, Fei Yu, Changyin Zhou, Chun Yuan, Yu Li

However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring temporal stability in single-frame methods for 3D face tracking on video data.

3D Face Reconstruction

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

1 code implementation17 May 2022 Hexin Dong, ZiFan Chen, Mingze Yuan, Yutong Xie, Jie Zhao, Fei Yu, Bin Dong, Li Zhang

Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning.

Anomaly Segmentation Few-Shot Learning +3

Unsupervised Domain Adaptation in Semantic Segmentation Based on Pixel Alignment and Self-Training

no code implementations29 Sep 2021 Hexin Dong, Fei Yu, Jie Zhao, Bin Dong, Li Zhang

This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training.

Segmentation Semantic Segmentation +1

ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph

no code implementations30 Jun 2020 Fei Yu, Jiji Tang, Weichong Yin, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Thus, ERNIE-ViL can learn the joint representations characterizing the alignments of the detailed semantics across vision and language.

Attribute Prediction +3

Attentive Geo-Social Group Recommendation

no code implementations6 Nov 2019 Fei Yu, Feiyi Fan, Shouxu Jiang, Kaiping Zheng

In this paper, a novel group recommendation method, called attentive geo-social group recommendation, is proposed to recommend the target user with both activity locations and a group of users that may join the activities.

Decision Making Single Particle Analysis

PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation

1 code implementation4 Nov 2019 Jie Zhao, Lei Dai, Mo Zhang, Fei Yu, Meng Li, Hongfeng Li, Wenjia Wang, Li Zhang

The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.

Segmentation

Multi-level Domain Adaptive learning for Cross-Domain Detection

no code implementations26 Jul 2019 Rongchang Xie, Fei Yu, Jiachao Wang, Yizhou Wang, Li Zhang

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment.

Object object-detection +1

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

no code implementations26 Jul 2019 Fei Yu, Jie Zhao, Yanjun Gong, Zhi Wang, Yuxi Li, Fan Yang, Bin Dong, Quanzheng Li, Li Zhang

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.

Generative Adversarial Network Transfer Learning

Differentially-Private Logistic Regression for Detecting Multiple-SNP Association in GWAS Databases

no code implementations30 Jul 2014 Fei Yu, Michal Rybar, Caroline Uhler, Stephen E. Fienberg

Following the publication of an attack on genome-wide association studies (GWAS) data proposed by Homer et al., considerable attention has been given to developing methods for releasing GWAS data in a privacy-preserving way.

Privacy Preserving regression

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