Search Results for author: Zhenyu Liu

Found 46 papers, 11 papers with code

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model

1 code implementation26 Jun 2025 Xinping Zhao, Xinshuo Hu, Zifei Shan, Shouzheng Huang, Yao Zhou, Zetian Sun, Zhenyu Liu, Dongfang Li, Xinyuan Wei, Qian Chen, Youcheng Pan, Yang Xiang, Meishan Zhang, Haofen Wang, Jun Yu, Baotian Hu, Min Zhang

In this paper, we propose KaLM-Embedding-V2, a versatile and compact embedding model, which achieves impressive performance in general-purpose text embedding tasks by leveraging superior training techniques and data.

Representation Learning Retrieval

D2R: dual regularization loss with collaborative adversarial generation for model robustness

no code implementations8 Jun 2025 Zhenyu Liu, HuiZhi Liang, Rajiv Ranjan, Zhanxing Zhu, Vaclav Snasel, Varun Ojha

The adversarial distribution and clean distribution optimizations enhance the target model's robustness by leveraging the strengths of different loss functions obtained via a suitable function space exploration to focus more precisely on the target model's distribution.

VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization

1 code implementation25 May 2025 Yunxin Li, Xinyu Chen, Zitao Li, Zhenyu Liu, Longyue Wang, Wenhan Luo, Baotian Hu, Min Zhang

Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning.

Reinforcement Learning (RL)

U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding

no code implementations23 May 2025 Anjie Le, Henan Liu, Yue Wang, Zhenyu Liu, Rongkun Zhu, Taohan Weng, Jinze Yu, Boyang Wang, Yalun Wu, Kaiwen Yan, Quanlin Sun, Meirui Jiang, Jialun Pei, Siya Liu, Haoyun Zheng, Zhoujun Li, Alison Noble, Jacques Souquet, Xiaoqing Guo, Manxi Lin, Hongcheng Guo

Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and anatomical structures.

Benchmarking Spatial Reasoning +1

Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM

no code implementations9 May 2025 Zehao Fan, Garrett Gagnon, Zhenyu Liu, Liu Liu

Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large language models (LLMs), places significant pressure on memory systems due to frequent memory accesses and growing key-value (KV) caches.

Clustering Semantic Similarity +1

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

1 code implementation8 May 2025 Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, Shouzheng Huang, Xinping Zhao, Borui Jiang, Lanqing Hong, Longyue Wang, Zhuotao Tian, Baoxing Huai, Wenhan Luo, Weihua Luo, Zheng Zhang, Baotian Hu, Min Zhang

Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning.

Multimodal Reasoning

Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment

1 code implementation13 Mar 2025 Zhenyu Liu, Dongfang Li, Xinshuo Hu, Xinping Zhao, Yibin Chen, Baotian Hu, Min Zhang

We find that the transformer embeds the task function learned from demonstrations into the separator token representation, which plays an important role in the generation of prior response tokens.

In-Context Learning

TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions

1 code implementation CVPR 2025 Wang YuHang, Junkang Guo, Aolei Liu, Kaihao Wang, Zaitong Wu, Zhenyu Liu, Wenfei Yin, Jian Liu

This paper provides a comprehensive analysis of adversarial training under long-tailed distributions and identifies limitations in the current state-of-the-art method, AT-BSL, in achieving robust performance under such conditions.

Adversarial Robustness Computational Efficiency

Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents

1 code implementation27 Feb 2025 Zhenyu Liu, Yunxin Li, Baotian Hu, Wenhan Luo, YaoWei Wang, Min Zhang

Specifically, our approach consists of 1) an image information quantification method via visual agents collaboration to select images with rich visual information, and 2) a visual-centric instruction quality assessment method to select high-quality instruction data related to high-quality images.

Image Quality Assessment

Importance-Aware Source-Channel Coding for Multi-Modal Task-Oriented Semantic Communication

no code implementations22 Feb 2025 Yi Ma, Chunmei Xu, Zhenyu Liu, Siqi Zhang, Rahim Tafazolli

This paper explores the concept of information importance in multi-modal task-oriented semantic communication systems, emphasizing the need for high accuracy and efficiency to fulfill task-specific objectives.

Semantic Communication

Bayesian Beamforming for Integrated Sensing and Communication Systems

no code implementations10 Feb 2025 Zongyao Zhao, Zhenyu Liu, Wei Dai, Xinke Tang, Xiao-Ping Zhang, Yuhan Dong

The uncertainty of the sensing target brings great challenge to the beamforming design of the integrated sensing and communication (ISAC) system.

Integrated sensing and communication ISAC

A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond

no code implementations27 Jan 2025 Yipeng Li, Xinchen Lyu, Zhenyu Liu

Using the general assumption, we develop a unified framework for permutation-based SGD with arbitrary permutations of examples, incorporating all the aforementioned representative algorithms.

Federated Learning

Collaborative Channel Access and Transmission for NR Sidelink and Wi-Fi Coexistence over Unlicensed Spectrum

no code implementations20 Jan 2025 Zhuangzhuang Yan, Xinyu Gu, Zhenyu Liu, Liyang Lu

To address this demand, 5G-Advanced has introduced sidelink communication over the unlicensed spectrum (SL-U) to increase data rates.

Deep Reinforcement Learning Fairness

Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models

no code implementations20 Jan 2025 Zhuangzhuang Yan, Xinyu Gu, Shilong Fan, Zhenyu Liu

In this paper, we propose GAT-LLM, a novel multivariate wireless link quality prediction model that combines Large Language Models (LLMs) with Graph Attention Networks (GAT) to enable accurate and reliable multivariate LQP of wireless communications.

Graph Attention Prediction +1

A CSI Feedback Framework based on Transmitting the Important Values and Generating the Others

no code implementations20 Nov 2024 Zhilin Du, Zhenyu Liu, Haozhen Li, Shilong Fan, Xinyu Gu, Lin Zhang

The application of deep learning (DL)-based channel state information (CSI) feedback frameworks in massive multiple-input multiple-output (MIMO) systems has significantly improved reconstruction accuracy.

Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection

no code implementations21 Oct 2024 Jianfei He, Lilin Wang, Jiaying Wang, Zhenyu Liu, Hongbin Na, Zimu Wang, Wei Wang, Qi Chen

Identifying offensive language is essential for maintaining safety and sustainability in the social media era.

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG

no code implementations14 Oct 2024 Xinping Zhao, Yan Zhong, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Dongfang Li, Baotian Hu, Min Zhang

In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency.

RAG Retrieval +1

Rate-Distortion-Perception Controllable Joint Source-Channel Coding for High-Fidelity Generative Communications

no code implementations26 Aug 2024 Kailin Tan, Jincheng Dai, Zhenyu Liu, Sixian Wang, Xiaoqi Qin, Wenjun Xu, Kai Niu, Ping Zhang

Based on this framework, we introduce a distortion-perception controllable transmission (DPCT) model, which addresses the variation in the perception-distortion trade-off.

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks

no code implementations23 Aug 2024 Zhenyu Liu, Haoran Duan, HuiZhi Liang, Yang Long, Vaclav Snasel, Guiseppe Nicosia, Rajiv Ranjan, Varun Ojha

Additionally, we found that a budgeted dimension of inner optimization for the target model may contribute to the trade-off between clean accuracy and robust accuracy.

Csi-LLM: A Novel Downlink Channel Prediction Method Aligned with LLM Pre-Training

no code implementations15 Aug 2024 Shilong Fan, Zhenyu Liu, Xinyu Gu, Haozhen Li

In this work, we introduce Csi-LLM, a novel LLM-powered downlink channel prediction technique that models variable-step historical sequences.

Prediction

B-ISAC: Backscatter Integrated Sensing and Communication for IoE Applications

no code implementations27 Jul 2024 Zongyao Zhao, Yuhan Dong, Tiankuo Wei, Xinke Tang, Xiao-Ping Zhang, Zhenyu Liu

In this paper, we propose a novel cognitive wireless system called backscatter-ISAC (B-ISAC) and develop a joint beamforming framework for different stages (task modes).

Integrated sensing and communication ISAC +1

In-Context Learning State Vector with Inner and Momentum Optimization

1 code implementation17 Apr 2024 Dongfang Li, Zhenyu Liu, Xinshuo Hu, Zetian Sun, Baotian Hu, Min Zhang

In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector.

In-Context Learning Test-time Adaptation

Robotics and Computer-Integrated Manufacturing

no code implementations Robotics and Computer-Integrated Manufacturing 2024 Yu Huang, Daxin Liu *, Zhenyu Liu, Ke Wang, Qide Wang, Jianrong Tan

In real- world experiments on grasping objects in different shapes and trajectories, the average grasping prediction success rate (GPSR) and grasping reaching success rate (GRSR) of MA-TD3H are above 90 percent and 80 percent respectively, and the average GRSR is improved by 20–30 percent compared with the other algorithms.

Robotic Grasping

Improving Attributed Text Generation of Large Language Models via Preference Learning

no code implementations27 Mar 2024 Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content.

Misinformation Retrieval +2

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons

no code implementations6 Feb 2024 Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani, Liu Liu

Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making.

Adversarial Robustness Decision Making

Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework

no code implementations10 Dec 2023 Zhilin Du, Haozhen Li, Zhenyu Liu, Shilong Fan, Xinyu Gu, Lin Zhang

The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems.

Decoder

A Survey of Large Language Models Attribution

1 code implementation7 Nov 2023 Dongfang Li, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Ziyang Chen, Baotian Hu, Aiguo Wu, Min Zhang

Open-domain generative systems have gained significant attention in the field of conversational AI (e. g., generative search engines).

Survey

Explaining How a Neural Network Play the Go Game and Let People Learn

no code implementations15 Oct 2023 Huilin Zhou, Huijie Tang, Mingjie Li, Hao Zhang, Zhenyu Liu, Quanshi Zhang

The AI model has surpassed human players in the game of Go, and it is widely believed that the AI model has encoded new knowledge about the Go game beyond human players.

Game of Go

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

1 code implementation16 Aug 2023 Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang

To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.

Language Modeling Language Modelling +1

HybridCVLNet: A Hybrid CSI Feedback System and its Domain Adaptation

no code implementations30 Mar 2023 Haozhen Li, Xinyu Gu, Boyuan Zhang, Dongliang Li, Zhenyu Liu, Lin Zhang

Deep Learning (DL)-based channel state information (CSI) feedback is a promising technique for the transmitter to accurately acquire the CSI of massive multiple-input multiple-output (MIMO) systems.

Domain Adaptation Transfer Learning

Task-Balanced Distillation for Object Detection

no code implementations5 Aug 2022 Ruining Tang, Zhenyu Liu, Yangguang Li, Yiguo Song, Hui Liu, Qide Wang, Jing Shao, Guifang Duan, Jianrong Tan

To alleviate this problem, a novel Task-decoupled Feature Distillation (TFD) is proposed by flexibly balancing the contributions of classification and regression tasks.

Classification Knowledge Distillation +4

A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI Feedback

no code implementations20 Sep 2020 Zhenyu Liu, Mason del Rosario, Zhi Ding

Forward channel state information (CSI) often plays a vital role in scheduling and capacity-approaching transmission optimization for massive multiple-input multiple-output (MIMO) communication systems.

Quantization Scheduling

Text Classification based on Multi-granularity Attention Hybrid Neural Network

no code implementations12 Aug 2020 Zhenyu Liu, Chaohong Lu, Haiwei Huang, Shengfei Lyu, Zhenchao Tao

Conventionally, there are two mainstream neural architectures for NLP tasks: the recurrent neural network (RNN) and the convolution neural network (ConvNet).

General Classification Sentence +2

Multichannel CNN with Attention for Text Classification

no code implementations29 Jun 2020 Zhenyu Liu, Haiwei Huang, Chaohong Lu, Shengfei Lyu

Alternatively, CNN is able to capture n-gram features of texts by utilizing convolutional filters.

General Classification Sentence +2

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

no code implementations29 Jun 2020 Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng

In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.

Human Activity Recognition

A Novel Decision Tree for Depression Recognition in Speech

no code implementations22 Feb 2020 Zhenyu Liu, Dongyu Wang, Lan Zhang, Bin Hu

Depression is a common mental disorder worldwide which causes a range of serious outcomes.

MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis

no code implementations20 Feb 2020 Hanshu Cai, Yiwen Gao, Shuting Sun, Na Li, Fuze Tian, Han Xiao, Jianxiu Li, Zhengwu Yang, Xiaowei Li, Qinglin Zhao, Zhenyu Liu, Zhijun Yao, Minqiang Yang, Hong Peng, Jing Zhu, Xiaowei Zhang, Guoping Gao, Fang Zheng, Rui Li, Zhihua Guo, Rong Ma, Jing Yang, Lan Zhang, Xiping Hu, Yumin Li, Bin Hu

The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.

EEG

Computation Error Analysis of Block Floating Point Arithmetic Oriented Convolution Neural Network Accelerator Design

no code implementations22 Sep 2017 Zhourui Song, Zhenyu Liu, Dongsheng Wang

The heavy burdens of computation and off-chip traffic impede deploying the large scale convolution neural network on embedded platforms.

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