Search Results for author: Yuan Feng

Found 31 papers, 9 papers with code

Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective

1 code implementation6 Feb 2025 Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S Kevin Zhou

This paper presents a formal study on identifying critical KV cache entries by analyzing attention output perturbation.

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech

no code implementations5 Feb 2025 Jixun Yao, Yuguang Yang, Yu Pan, Yuan Feng, Ziqian Ning, Jianhao Ye, Hongbin Zhou, Lei Xie

In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems.

Language Modeling Language Modelling +1

FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs

no code implementations17 Jan 2025 Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, Xike Xie, S Kevin Zhou

By using the query text instead of the KG to infer the structural information of reasoning paths and employing adaptable retrieval strategies, FRAG improves retrieval quality while maintaining flexibility.

Hallucination Knowledge Graphs +2

PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors

no code implementations28 Nov 2024 Guangshun Wei, Yuan Feng, Long Ma, Chen Wang, Yuanfeng Zhou, Changjian Li

To fully exploit the priors, we have designed a shape fusion module for producing an initial complete shape from multi-modality input (\ie, images and point clouds), and a follow-up shape consolidation module to obtain the final complete shape by discarding unreliable points introduced by the inconsistency from diffusion priors.

Point Cloud Completion

CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs

1 code implementation19 Sep 2024 Junlin Lv, Yuan Feng, Xike Xie, Xin Jia, Qirong Peng, Guiming Xie

In this paper, we observe a locality in query criticality during the prefilling phase of long-context processing: adjacent query tokens tend to focus on similar subsets of the past Key-Value (KV) cache.

Innovative RIS Prototyping Enhancing Wireless Communication with Real-Time Spot Beam Tracking and OAM Wavefront Manipulation

no code implementations28 Jul 2024 Yufei Zhao, Yuan Feng, Afkar Mohamed Ismail, Ziyue Wang, Yong Liang Guan, Yongxin Guo, Chau Yuen

Owing to the capability of each unit cell on the metasurface to independently switch states, the entire RIS is not limited to controlling general beams with specific directional patterns, but also generates beams with more complex structures, including multi-focus 3D spot beams and vortex beams.

Blocking

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

2 code implementations16 Jul 2024 Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S. Kevin Zhou

In this paper, we establish a theoretical loss upper bound between pre- and post-eviction attention output, explaining the optimization target of prior cache eviction methods, while guiding the optimization of adaptive budget allocation.

Environment Sensing-aided Beam Prediction with Transfer Learning for Smart Factory

no code implementations24 May 2024 Yuan Feng, Chuanbing Zhao, Feifei Gao, Yong Zhang, Shaodan Ma

Therefore, we next design a transfer learning strategy that fine-tunes the pre-trained model by limited labeled data of the new environment.

Beam Prediction Prediction +1

Leveraging Federated Learning and Edge Computing for Recommendation Systems within Cloud Computing Networks

no code implementations5 Mar 2024 Yaqian Qi, Yuan Feng, Xiangxiang Wang, Hanzhe Li, Jingxiao Tian

To enable large-scale and efficient deployment of artificial intelligence (AI), the combination of AI and edge computing has spawned Edge Intelligence, which leverages the computing and communication capabilities of end devices and edge servers to process data closer to where it is generated.

Cloud Computing Deep Reinforcement Learning +3

MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation

1 code implementation CVPR 2023 Yong Yang, Qiong Chen, Yuan Feng, Tianlin Huang

Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set.

Few-Shot Semantic Segmentation General Knowledge +4

Two Views of Constrained Differential Privacy: Belief Revision and Update

no code implementations1 Mar 2023 Likang Liu, Keke Sun, Chunlai Zhou, Yuan Feng

Within the framework established in this paper, constrained DP algorithms in the literature can be classified either as belief revision or belief update.

Vocal Bursts Valence Prediction

AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems

no code implementations23 Jan 2023 Yuan Feng, Hyeran Jeon, Filip Blagojevic, Cyril Guyot, Qing Li, Dong Li

Transformer models gain popularity because of their superior inference accuracy and inference throughput.

MR Elastography with Optimization-Based Phase Unwrapping and Traveling Wave Expansion-based Neural Network (TWENN)

no code implementations6 Jan 2023 Shengyuan Ma, Runke Wang, Suhao Qiu, Ruokun Li, Qi Yue, Qingfang Sun, Liang Chen, Fuhua Yan, Guang-Zhong Yang, Yuan Feng

Here we propose a pipeline for processing MRE images using optimization-based displacement extraction and Traveling Wave Expansion-based Neural Network (TWENN) modulus estimation.

Revealing Secrets From Pre-trained Models

no code implementations19 Jul 2022 Mujahid Al Rafi, Yuan Feng, Hyeran Jeon

In this paper, we show a new observation that pre-trained models and fine-tuned models have significantly high similarities in weight values.

Model extraction Transfer Learning

Asymmetric Dual-Decoder U-Net for Joint Rain and Haze Removal

1 code implementation14 Jun 2022 Yuan Feng, Yaojun Hu, Pengfei Fang, Yanhong Yang, Sheng Liu, ShengYong Chen

However, jointly removing the rain and haze in scene images is ill-posed and challenging, where the existence of haze and rain and the change of atmosphere light, can both degrade the scene information.

Autonomous Driving Decoder +1

A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction

no code implementations28 Mar 2022 Ruiyang Zhao, Zhao He, Tao Wang, Suhao Qiu, Pawel Herman, Yanle Hu, Chencheng Zhang, Dinggang Shen, Bomin Sun, Guang-Zhong Yang, Yuan Feng

Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling.

MRI Reconstruction

PAFNet: An Efficient Anchor-Free Object Detector Guidance

1 code implementation28 Apr 2021 Ying Xin, Guanzhong Wang, Mingyuan Mao, Yuan Feng, Qingqing Dang, Yanjun Ma, Errui Ding, Shumin Han

Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios.

 Ranked #1 on Object Detection on COCO test-dev (Hardware Burden metric)

Object object-detection +1

Time-Continuous Energy-Conservation Neural Network for Structural Dynamics Analysis

no code implementations16 Dec 2020 Yuan Feng, Hexiang Wang, Han Yang, Fangbo Wang

Although the basic neural network provides an alternative approach for structural dynamics analysis, the lack of physics law inside the neural network limits the model accuracy and fidelity.

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 Sep 2020 Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.

Human Detection Object +2

A Tensor Network based Decision Diagram for Representation of Quantum Circuits

no code implementations6 Sep 2020 Xin Hong, Xiangzhen Zhou, Sanjiang Li, Yuan Feng, Mingsheng Ying

Tensor networks have been successfully applied in simulation of quantum physical systems for decades.

Quantum Physics Data Structures and Algorithms

Qubit Mapping Based on Subgraph Isomorphism and Filtered Depth-Limited Search

2 code implementations15 Apr 2020 Sanjiang Li, Xiangzhen Zhou, Yuan Feng

Mapping logical quantum circuits to Noisy Intermediate-Scale Quantum (NISQ) devices is a challenging problem which has attracted rapidly increasing interests from both quantum and classical computing communities.

Quantum Physics

Quantum Circuit Transformation Based on Simulated Annealing and Heuristic Search

1 code implementation23 Aug 2019 Xiangzhen Zhou, Sanjiang Li, Yuan Feng

Our algorithm runs in time polynomial in all parameters including the size and the qubit number of the input circuit, and the qubit number in the QPU.

Quantum Physics

Quantum Data Fitting Algorithm for Non-sparse Matrices

no code implementations16 Jul 2019 Guangxi Li, Youle Wang, Yu Luo, Yuan Feng

We propose a quantum data fitting algorithm for non-sparse matrices, which is based on the Quantum Singular Value Estimation (QSVE) subroutine and a novel efficient method for recovering the signs of eigenvalues.

Quantum Privacy-Preserving Perceptron

no code implementations31 Jul 2017 Shenggang Ying, Mingsheng Ying, Yuan Feng

Secondly when updating the current classifier, private random noise is used to protect the original data.

BIG-bench Machine Learning Privacy Preserving

Quantum Privacy-Preserving Data Mining

no code implementations13 Dec 2015 Shenggang Ying, Mingsheng Ying, Yuan Feng

Data mining is a key technology in big data analytics and it can discover understandable knowledge (patterns) hidden in large data sets.

Privacy Preserving

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