Yihua Cheng

76 papers A* 15A 5B 2Misc 2Journal 46Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
Efficient Driving Behavior Narration and Reasoning on Edge Device Using Large Language Models.
IEEE Trans. Veh. Technol.
Yizhou Huang, Yihua Cheng, Kezhi Wang
2026 J jnl
FoSS: Modeling Long Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier State Space Integration.
CoRR
Yizhou Huang, Gengze Jiang, Yihua Cheng, Kezhi Wang
2026 A* conf
Force-Aware 3D Contact Modeling for Stable Grasp Generation.
AAAI
Zhuo Chen, Zhongqun Zhang, Yihua Cheng, Ales Leonardis, Hyung Jin Chang
2026 A* conf
RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image.
AAAI
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2025 A* conf
3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation.
CVPR
Yihua Cheng, Hengfei Wang, Zhongqun Zhang, Yang Yue, Boeun Kim, Feng Lu, Hyung Jin Chang
2025 J jnl
3D Prior is All You Need: Cross-Task Few-shot 2D Gaze Estimation.
CoRR
Yihua Cheng, Hengfei Wang, Zhongqun Zhang, Yang Yue, Boeun Kim, Feng Lu, Hyung Jin Chang
2025 J jnl
AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving.
CoRR
Shaoting Feng, Hanchen Li, Kuntai Du, Zhuohan Gu, Yuhan Liu, Jiayi Yao, Siddhant Ray, Samuel Shen, Yihua Cheng, Ganesh Ananthanarayanan, Junchen Jiang
2025 J jnl
Behavior-Aware Knowledge-Embedded Model for Driver Attention Prediction.
IEEE Trans. Circuits Syst. Video Technol.
Yuchen Zhou, Chao Gou, Zipeng Guo, Yihua Cheng, Hyung Jin Chang
2025 A conf
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.
EuroSys
Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang
2025 J jnl
EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving.
CoRR
Shaoting Feng, Yuhan Liu, Hanchen Li, Xiaokun Chen, Samuel Shen, Kuntai Du, Zhuohan Gu, Rui Zhang, Yuyang Huang, Yihua Cheng, Jiayi Yao, Qizheng Zhang, Ganesh Ananthanarayanan, Junchen Jiang
2025 — conf
Earth+: On-Board Satellite Imagery Compression Leveraging Historical Earth Observations.
ASPLOS (1)
Kuntai Du, Yihua Cheng, Peder A. Olsen, Shadi A. Noghabi, Junchen Jiang
2025 J jnl
Excavate the Potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement.
IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens.
Zheng Cheng, Wenri Wang, Guang-Yong Chen, Yakun Ju, Yihua Cheng, Zhisong Liu, Yanda Meng, Jintao Song
2025 J jnl
Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement.
CoRR
Zheng Cheng, Wenri Wang, Guangyong Chen, Yakun Ju, Yihua Cheng, Zhisong Liu, Yanda Meng, Jintao Song
2025 J jnl
Force-Aware 3D Contact Modeling for Stable Grasp Generation.
CoRR
Zhuo Chen, Zhongqun Zhang, Yihua Cheng, Ales Leonardis, Hyung Jin Chang
2025 J jnl
HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse.
CoRR
Yuwei An, Yihua Cheng, Seo Jin Park, Junchen Jiang
2025 J jnl
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference.
CoRR
Yihua Cheng, Yuhan Liu, Jiayi Yao, Yuwei An, Xiaokun Chen, Shaoting Feng, Yuyang Huang, Samuel Shen, Kuntai Du, Junchen Jiang
2025 J jnl
Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Prediction.
CoRR
Yizhou Huang, Yihua Cheng, Kezhi Wang
2025 J jnl
Meta-Learning Enables Complex Cluster-Specific Few-Shot Binding Affinity Prediction for Protein-Protein Interactions.
J. Chem. Inf. Model.
Yang Yue, Yihua Cheng, Céline Marquet, Chenguang Xiao, Jingjing Guo, Shu Li, Shan He
2025 A conf
Multi-Hypothesis 3D Hand Mesh Recovering from a Single Blurry Image.
ICME
Yuming Chen, Rongyu Chen, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2025 A* conf
PersonaBooth: Personalized Text-to-Motion Generation.
CVPR
Boeun Kim, Hea In Jeong, JungHoon Sung, Yihua Cheng, Jeongmin Lee, Ju Yong Chang, Sang-Il Choi, Younggeun Choi, Saim Shin, Jungho Kim, Hyung Jin Chang
2025 J jnl
PersonaBooth: Personalized Text-to-Motion Generation.
CoRR
Boeun Kim, Hea In Jeong, JungHoon Sung, Yihua Cheng, Jeongmin Lee, Ju Yong Chang, Sang-Il Choi, Younggeun Choi, Saim Shin, Jungho Kim, Hyung Jin Chang
2025 A* conf
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications.
SOSP
Kuntai Du, Bowen Wang, Chen Zhang, Yiming Cheng, Qing Lan, Hejian Sang, Yihua Cheng, Jiayi Yao, Xiaoxuan Liu, Yifan Qiao, Ion Stoica, Junchen Jiang
2025 J jnl
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications.
CoRR
Kuntai Du, Bowen Wang, Chen Zhang, Yiming Cheng, Qing Lan, Hejian Sang, Yihua Cheng, Jiayi Yao, Xiaoxuan Liu, Yifan Qiao, Ion Stoica, Junchen Jiang
2025 J jnl
RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image.
CoRR
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2025 A* conf
Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation.
ACM Multimedia
YoungChan Choi, Hengfei Wang, Yihua Cheng, Boeun Kim, Hyung Jin Chang, Younggeun Choi, Sang-Il Choi
2025 J jnl
Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation.
CoRR
YoungChan Choi, Hengfei Wang, Yihua Cheng, Boeun Kim, Hyung Jin Chang, Younggeun Choi, Sang-Il Choi
2025 A* conf
Single-view Image to Novel-view Generation for Hand-Object Interactions.
AAAI
Zhongqun Zhang, Yihua Cheng, Eduardo Pérez-Pellitero, Yiren Zhou, Jiankang Deng, Hyung Jin Chang, Jifei Song
2025 J jnl
Towards More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache.
CoRR
Hanchen Li, Yuhan Liu, Yihua Cheng, Kuntai Du, Junchen Jiang
2025 A* conf
Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM.
CVPR
Yizhou Huang, Yihua Cheng, Kezhi Wang
2025 J jnl
Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM.
CoRR
Yizhou Huang, Yihua Cheng, Kezhi Wang
2025 J jnl
VL4Gaze: Unleashing Vision-Language Models for Gaze Following.
CoRR
Shijing Wang, Chaoqun Cui, Yaping Huang, Hyung Jin Chang, Yihua Cheng
2024 J jnl
Appearance-Based Gaze Estimation With Deep Learning: A Review and Benchmark.
IEEE Trans. Pattern Anal. Mach. Intell.
Yihua Cheng, Haofei Wang, Yiwei Bao, Feng Lu
2024 J jnl
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.
CoRR
Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang
2024 A* conf
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving.
SIGCOMM
Yuhan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, Yuyang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang
2024 J jnl
Chatterbox: Robust Transport for LLM Token Streaming under Unstable Network.
CoRR
Hanchen Li, Yuhan Liu, Yihua Cheng, Siddhant Ray, Kuntai Du, Junchen Jiang
2024 J jnl
Do Large Language Models Need a Content Delivery Network?
CoRR
Yihua Cheng, Kuntai Du, Jiayi Yao, Junchen Jiang
2024 J jnl
Earth+: on-board satellite imagery compression leveraging historical earth observations.
CoRR
Kuntai Du, Yihua Cheng, Peder A. Olsen, Shadi A. Noghabi, Ranveer Chandra, Junchen Jiang
2024 J jnl
Efficient Driving Behavior Narration and Reasoning on Edge Device Using Large Language Models.
CoRR
Yizhou Huang, Yihua Cheng, Kezhi Wang
2024 — conf
Eloquent: A More Robust Transmission Scheme for LLM Token Streaming.
NAIC
Hanchen Li, Yuhan Liu, Yihua Cheng, Siddhant Ray, Kuntai Du, Junchen Jiang
2024 Misc conf
GRACE: Loss-Resilient Real-Time Video through Neural Codecs.
NSDI
Yihua Cheng, Ziyi Zhang, Hanchen Li, Anton Arapin, Yue Zhang, Qizheng Zhang, Yuhan Liu, Kuntai Du, Xu Zhang, Francis Y. Yan, Amrita Mazumdar, Nick Feamster, Junchen Jiang
2024 A conf
Multi-Modal Gaze Following in Conversational Scenarios.
WACV
Yuqi Hou, Zhongqun Zhang, Nora Horanyi, Jaewon Moon, Yihua Cheng, Hyung Jin Chang
2024 — conf
NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model.
ECCV (28)
Zhongqun Zhang, Hengfei Wang, Ziwei Yu, Yihua Cheng, Angela Yao, Hyung Jin Chang
2024 J jnl
NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model.
CoRR
Zhongqun Zhang, Hengfei Wang, Ziwei Yu, Yihua Cheng, Angela Yao, Hyung Jin Chang
2024 A* conf
TextGaze: Gaze-Controllable Face Generation with Natural Language.
ACM Multimedia
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2024 J jnl
TextGaze: Gaze-Controllable Face Generation with Natural Language.
CoRR
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2024 A* conf
What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation.
CVPR
Yihua Cheng, Yaning Zhu, Zongji Wang, Hongquan Hao, Yongwei Liu, Shiqing Cheng, Xi Wang, Hyung Jin Chang
2024 J jnl
What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation.
CoRR
Yihua Cheng, Yaning Zhu, Zongji Wang, Hongquan Hao, Yongwei Liu, Shiqing Cheng, Xi Wang, Hyung Jin Chang
2023 J jnl
CacheGen: Fast Context Loading for Language Model Applications.
CoRR
Yuhan Liu, Hanchen Li, Kuntai Du, Jiayi Yao, Yihua Cheng, Yuyang Huang, Shan Lu, Michael Maire, Henry Hoffmann, Ari Holtzman, Ganesh Ananthanarayanan, Junchen Jiang
2023 A* conf
DVGaze: Dual-View Gaze Estimation.
ICCV
Yihua Cheng, Feng Lu
2023 J jnl
DVGaze: Dual-View Gaze Estimation.
CoRR
Yihua Cheng, Feng Lu
2023 J jnl
Enabling Perception-Driven Optimization in Networking.
SIGMETRICS Perform. Evaluation Rev.
Yihua Cheng, Xu Zhang, Junchen Jiang
2023 J jnl
Grace++: Loss-Resilient Real-Time Video Communication under High Network Latency.
CoRR
Yihua Cheng, Anton Arapin, Ziyi Zhang, Qizheng Zhang, Hanchen Li, Nick Feamster, Junchen Jiang
2023 A conf
High-Fidelity Eye Animatable Neural Radiance Fields for Human Face.
BMVC
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2023 J jnl
High-Fidelity Eye Animatable Neural Radiance Fields for Human Face.
CoRR
Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
2023 J jnl
Multi-Modal Gaze Following in Conversational Scenarios.
CoRR
Yuqi Hou, Zhongqun Zhang, Nora Horanyi, Jaewon Moon, Yihua Cheng, Hyung Jin Chang
2023 — conf
Online Profiling and Adaptation of Quality Sensitivity for Internet Video.
SoCC
Yihua Cheng, Hui Zhang, Junchen Jiang
2023 — conf
Optimizing Real-Time Video Experience with Data Scalable Codec.
EMS@SIGCOMM
Hanchen Li, Yihua Cheng, Ziyi Zhang, Qizheng Zhang, Anton Arapin, Nick Feamster, Amrita Mazumdar
2023 Misc conf
POLYCORN: Data-driven Cross-layer Multipath Networking for High-speed Railway through Composable Schedulerlets.
NSDI
Yunzhe Ni, Feng Qian, Taide Liu, Yihua Cheng, Zhiyao Ma, Jing Wang, Zhongfeng Wang, Gang Huang, Xuanzhe Liu, Chenren Xu
2023 A conf
Raising the Level of Abstraction for Time-State Analytics With the Timeline Framework.
CIDR
Henry Milner, Yihua Cheng, Jibin Zhan, Hui Zhang, Vyas Sekar, Junchen Jiang, Ion Stoica
2022 J jnl
GRACE: Loss-Resilient Real-Time Video Communication Using Data-Scalable Autoencoder.
CoRR
Yihua Cheng, Anton Arapin, Ziyi Zhang, Qizheng Zhang, Hanchen Li, Nick Feamster, Junchen Jiang
2022 B conf
Gaze Estimation using Transformer.
ICPR
Yihua Cheng, Feng Lu
2022 A* conf
PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation.
AAAI
Yihua Cheng, Yiwei Bao, Feng Lu
2021 J jnl
Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets.
CoRR
Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu
2021 J jnl
Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark.
CoRR
Yihua Cheng, Haofei Wang, Yiwei Bao, Feng Lu
2021 J jnl
Critique of "Planetary Normal Mode Computation: Parallel Algorithms, Performance, and Reproducibility" by SCC Team From Peking University.
IEEE Trans. Parallel Distributed Syst.
Yihua Cheng, Zejia Fan, Jing Mai, Yifan Wu, Pengcheng Xu, Yuxuan Yan, Zhenxin Fu, Yun Liang
2021 J jnl
Gaze Estimation using Transformer.
CoRR
Yihua Cheng, Feng Lu
2021 J jnl
PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation.
CoRR
Yihua Cheng, Yiwei Bao, Feng Lu
2020 A* conf
A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation.
AAAI
Yihua Cheng, Shiyao Huang, Fei Wang, Chen Qian, Feng Lu
2020 J jnl
A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation.
CoRR
Yihua Cheng, Shiyao Huang, Fei Wang, Chen Qian, Feng Lu
2020 J jnl
A First Look at Disconnection-Centric TCP Performance on High-Speed Railways.
IEEE J. Sel. Areas Commun.
Chenren Xu, Jing Wang, Zhiyao Ma, Yihua Cheng, Yunzhe Ni, WangYang Li, Feng Qian, Yuanjie Li
2020 B conf
Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets.
ICPR
Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu
2020 J jnl
Gaze Estimation by Exploring Two-Eye Asymmetry.
IEEE Trans. Image Process.
Yihua Cheng, Xucong Zhang, Feng Lu, Yoichi Sato
2019 A* conf
An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails.
MobiCom
Jing Wang, Yufan Zheng, Yunzhe Ni, Chenren Xu, Feng Qian, WangYang Li, Wantong Jiang, Yihua Cheng, Zhuo Cheng, Yuanjie Li, Xiufeng Xie, Yi Sun, Zhongfeng Wang
2018 J jnl
An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails.
CoRR
Jing Wang, Yufan Zheng, Yunzhe Ni, Chenren Xu, Feng Qian, WangYang Li, Wantong Jiang, Yihua Cheng, Zhuo Cheng, Yuanjie Li, Xiufeng Xie, Yi Sun, Zhongfeng Wang
2018 — conf
Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression.
ECCV (14)
Yihua Cheng, Feng Lu, Xucong Zhang
2018 J jnl
Student Cluster Competition 2017, Team Peking University: Reproducing vectorization of the Tersoff multi-body potential on the Intel Broadwell architecture.
Parallel Comput.
Zhenxin Fu, Lei Yang, Wenbin Hou, Zhuohan Li, Yifan Wu, Yihua Cheng, Xiaolin Wang, Yun Liang