FW
Fan Wu
cs.LGcs.AIcs.CLcs.DBcs.IRcs.GTcs.DCcs.CVcs.NIstat.ML
On Valency
published · living versionsW_v47c5d4w·v1 · currentpublished
DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects
with Yumou Liu, Mingju Chen, Zhoufutu Wen, Qianyu Yang +19
1 version
W_33ercfyh·v1published
Preprints & journals
121 papers in the corpus · 2013–2026CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness2610.04437v1 · Leyao Gu, Yingjie Xiong, Zirui Tang et al.2026 · 0 citationsarXiv
Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs2609.34727v1 · Zhengxiang Huang, Shengheng Chen, Chaoyue Niu et al.2026 · 0 citationsarXiv
Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments2609.29773v2 · Yukai Wu, Yuanjing Yang, Le Zhou et al.2026 · 0 citationsarXiv
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement2609.11873v3 · Yi Duan, Ying Liu, Zirui Tang et al.2026 · 0 citationsarXiv
EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs2609.06551v1 · Junming Zhang, Zhenzhe Zheng, Fan Wu et al.2026 · 0 citationsarXiv
TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing2609.05019v1 · Tianxing Wang, Mingming Zhao, Shuai Huang et al.2026 · 0 citationsarXivon Valency
ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction2609.05506v1 · Zhuoqiang Cai, Yujie Sun, Chaoyue Niu et al.2026 · 0 citationsarXiv
Reflection with Action-Induced Visual Differences for Desktop GUI Agents2608.24015v1 · Yijie Ma, Chaoyue Niu, Fan Wu et al.2026 · 0 citationsarXiv
TEngineDB-V: An OLAP-Native Vector Search System for Large- Workloads at Tencent2608.00650v1 · Xufei Wu, Pengcheng Zhang, Yitong Song et al.2026 · 0 citationsarXiv
Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs2607.23115v1 · Zhihao Xu, Hao Zhong, Zeting Zhou et al.2026 · 0 citationsarXiv
CKV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference2607.17715v1 · Chuheng Du, Junyi Chen, Hanlin Tang et al.2026 · 0 citationsarXiv
CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling2607.17842v1 · Tingjia Zhang, Bo Chen, Shengzhong Liu et al.2026 · 0 citationsarXiv
Are We Ready For An Agent-Native Memory System?2606.24775v1 · Wei Zhou, Xuanhe Zhou, Shaokun Han et al.2026 · 0 citationsarXiv
An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG2605.25716v1 · Chenxin Mao, Shangyu Liu, Zhenzhe Zheng et al.2026 · 0 citationsarXiv
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?2605.26186v2 · Zihang Zhou, Ziqian Ren, Yukai Wu et al.2026 · 0 citationsarXiv
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing2605.24973v2 · Bangrui Xu, Ziyang Miao, Xuanhe Zhou et al.2026 · 0 citationsarXiv
BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning2605.08862v1 · Yuhang Xu, Kaibin Tian, Yang Tian et al.2026 · 0 citationsarXiv
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies2605.03596v4 · Zirui Tang, Xuanhe Zhou, Yumou Liu et al.2026 · 0 citationsarXiv
Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM2604.17827v2 · Hang Zeng, Xiangyu Liu, Yong Hu et al.2026 · 0 citationsarXiv
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue2604.12385v1 · Jiarui Zhang, Xiangyu Liu, Yong Hu et al.2026 · 0 citationsarXiv
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding2604.08014v3 · Xuezhen Tu, Jingyu Wu, Fangyu Kang et al.2026 · 0 citationsarXiv
Automating Database-Native Function Code Synthesis with LLMs2604.06231v1 · Wei Zhou, Xuanhe Zhou, Qikang He et al.2026 · 4 citationsarXiv
CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration2603.25463v1 · Keming Ye, Zhou Zhao, Fan Wu et al.2026 · 0 citationsarXiv
FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures2603.23345v1 · Yujie Sun, Zhuoqiang Cai, Chaoyue Niu et al.2026 · 0 citationsarXiv
Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences2603.21508v1 · Chen Gong, Zhenzhe Zheng, Yiliu Chen et al.2026 · 0 citationsarXiv
SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning2603.08000v2 · Chenzhi Hu, Qinzhe Hu, Yuhang Xu et al.2026 · 0 citationsarXiv
Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System2603.07449v2 · Xiang Zhang, Hongming Xu, Le Zhou et al.2026 · 1 citationProceedings of the VLDB Endowment, 19(11): 3718-3731, 2026
Disk-Resident Graph ANN Search: An Experimental Evaluation2603.01779v2 · Xiaoyu Chen, Jinxiu Qu, Yitong Song et al.2026 · 0 citationsarXiv
OoDBench+: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization.41182941 · Ye, Nanyang, Li, Kaican, Wu, Fan et al.2025 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;PP
MoDora: Tree-Based Semi-Structured Document Analysis System2602.23061v3 · Bangrui Xu, Qihang Yao, Zirui Tang et al.2026 · 0 citationsarXiv
Qute: Towards Quantum-Native Database2602.14699v1 · Muzhi Chen, Xuanhe Zhou, Wei Zhou et al.2026 · 0 citationsarXiv
Identification of a Tertiary Lymphoid Structure Signature for Predicting Tumor Outcomes Through Transcriptomics Analysis.41751623 · Zhou, Mengdi, Meng, Fangliangzi, Wu, Fan et al.2026 · 0 citationsGenes. 2026;17(2)
Antibody-Dependent Heterotypic Syncytia Drive COVID-19 Inflammation and Disease Progression10.64898/2026.02.11.705426v2 · Yang, Y., Zhou, C., Zhang, T. et al.2026 · 0 citationsbioRxiv
ByteHouse: ByteDance's Cloud-Native Data Warehouse for Real-Time Multimodal Data Analytics2602.08226v2 · Yuxing Han, Yu Lin, Yifeng Dong et al.2026 · 0 citationsarXiv
ST-Raptor: An Agentic System for Semi-Structured Table QA2602.07034v1 · Jinxiu Qu, Zirui Tang, Hongzhang Huang et al.2026 · 0 citationsarXiv
Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion2601.20422v1 · Yumou Liu, Zhenzhe Zheng, Jiang Rong et al.2026 · 0 citationsarXiv
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs2601.17058v1 · Wei Zhou, Jun Zhou, Haoyu Wang et al.2026 · 1 citationarXiv
VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement2601.13664v2 · Tiancheng Fang, Bowen Pan, Lingxi Chen et al.2026 · 0 citationsarXiv
OSM+: Billion-Level OpenStreetMap Dataset for City-wide Experiments2512.06743v2 · Guanjie Zheng, Ziyang Su, Yiheng Wang et al.2025 · 0 citationsarXiv
TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin2511.17639v1 · Yibing Wan, Zhengxiong Guan, Chaoli Zhang et al.2025 · 0 citationsAAAI 2026 IAAI Track
CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs2510.15455v1 · Gucongcong Fan, Chaoyue Niu, Chengfei Lyu et al.2025 · 2 citationsarXiv
Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps2510.13405v1 · Chen Gong, Yan Zhuang, Zhenzhe Zheng et al.2025 · 1 citationarXiv
TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling2510.02758v1 · Junyi Chen, Chuheng Du, Renyuan Liu et al.2025 · 0 citationsarXiv
CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration2510.03038v1 · Tianqi Liu, Kairui Fu, Shengyu Zhang et al.2025 · 0 citationsarXiv
SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?2510.03120v2 · Zhaojun Sun, Xuzhou Zhu, Xuanhe Zhou et al.2025 · 0 citationsarXiv
LLM/Agent-as-Data-Analyst: A Survey2509.23988v3 · Zirui Tang, Weizheng Wang, Zihang Zhou et al.2025 · 2 citationsarXiv
Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization2509.21301v1 · Yuhang Xu, Shengzhong Liu, Dong Zhang et al.2025 · 1 citationarXiv
ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs2509.17730v1 · Bonan Zhang, Zhongqi Chen, Bowen Song et al.2025 · 1 citationarXiv
Metis: Training LLMs with FP4 Quantization2509.00404v4 · Hengjie Cao, Mengyi Chen, Yifeng Yang et al.2025 · 0 citationsarXiv
ST-Raptor: LLM-Powered Semi-Structured Table Question Answering2508.18190v3 · Zirui Tang, Boyu Niu, Xuanhe Zhou et al.2025 · 6 citationsarXiv
Career total: 547 works. 121 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.