ZL
Zhiyuan Liu
cs.CLcs.AIcs.LGcs.IRcs.CVcs.CRstat.MLcs.HCcs.SIcs.SE
On Valency
published · living versionsW_ax2cmvsd·v1 · currentpublished
E0.5: From Reconstructive to Future-Predictive 3D Foundations for Robotic World-Action Modeling
with Era AI Lab Team, Jianhao Lai, Zhihao Zhan, Zhiquan Liao +22
1 version
W_sgts2h6a·v1published
Preprints & journals
327 papers in the corpus · 1992–2026Test-Time Deep Thinking to Explore Implicit Rules2605.24828v2 · Wentong Chen, Xin Cong, Zhong Zhang et al.2026 · 0 citationsarXiv
Capacity drop accounting for microscopic vehicle interaction effects: analytical model and validation with high-resolution trajectories2602.22019v2 · Yu Han, Pan Liu, Zhiyuan Liu et al.2026 · 0 citationsarXiv
Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science2602.05289v1 · Jingru Fan, Dewen Liu, Yufan Dang et al.2026 · 0 citationsarXiv
Let Experts Feel Uncertainty: A Multi-Expert Label Distribution Approach to Probabilistic Time Series Forecasting2602.04678v1 · Zhen Zhou, Zhirui Wang, Qi Hong et al.2026 · 0 citationsarXiv
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention2601.21444v2 · Yuxiang Huang, Mingye Li, Xu Han et al.2026 · 0 citationsarXiv
LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation2601.04516v1 · Yuxiao Ye, Yiming Zhang, Yiran Ma et al.2026 · 0 citationsarXiv
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models2601.01373v1 · Qundong Shi, Jie Zhou, Biyuan Lin et al.2026 · 0 citationsarXiv
3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding2510.16780v2 · Chang Wu, Zhiyuan Liu, Wen Shu et al.2025 · 0 citationsarXiv
Personalized Learning Path Planning with Goal-Driven Learner State Modeling2510.13215v2 · Joy Jia Yin Lim, Ye He, Jifan Yu et al.2025 · 0 citationsarXiv
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning2509.24650v1 · Yixuan Zhou, Guoyang Zeng, Xin Liu et al.2025 · 0 citationsarXiv
StateX: Enhancing RNN Recall via Post-training State Expansion2509.22630v3 · Xingyu Shen, Yingfa Chen, Zhen Leng Thai et al.2025 · 0 citationsarXiv
BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens2509.19836v1 · Ao Sun, Weilin Zhao, Xu Han et al.2025 · 1 citationarXiv
Design of a binocular multispectral stereo imaging system and its application in plant phenotyping.42041016 · Wan, Wenxiu, Liu, Zhiyuan, Yu, Ziru et al.2026 · 4 citationsPlant phenomics (Washington, D.C.). 2025;7(4):100105
Learning in Context: Personalizing Educational Content with Large Language Models to Enhance Student Learning2509.15068v1 · Joy Jia Yin Lim, Daniel Zhang-Li, Jifan Yu et al.2025 · 0 citationsarXiv
Efficient GPT-4V level multimodal large language model for deployment on edge devices.40593624 · Yao, Yuan, Yu, Tianyu, Zhang, Ao et al.2026 · 46 citationsNature communications. 2025;16(1):5509
KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs2506.09542v2 · Dingjun Wu, Yukun Yan, Zhenghao Liu et al.2025 · 0 citationsarXiv
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning2506.01391v2 · Zhong Zhang, Yaxi Lu, Yikun Fu et al.2025 · 5 citationsarXiv
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation2505.24388v2 · Hao Chen, Yukun Yan, Sen Mei et al.2025 · 1 citationarXiv
A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings2505.24550v2 · Xiaoang Xu, Shuo Wang, Xu Han et al.2025 · 0 citationsarXiv
Expression of lumbrokinase protein genes in Escherichia coli.40450921 · Zhao, Zhihui, Liu, Zhiyuan, Li, Xiaojiaoyang et al.2025 · 1 citationJournal of chromatography. B, Analytical technologies in the biomedical and life sciences. 2025;1263:124675
Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data2505.05427v1 · Yudong Wang, Zixuan Fu, Jie Cai et al.2025 · 0 citationsarXiv
AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset2504.03612v2 · Bingxiang He, Wenbin Zhang, Jiaxi Song et al.2025 · 0 citationsarXiv
Effects of dietary supplementation with Bacillus subtilis and bacteriophage on growth performance, intestinal morphology and microbiota structure in 0-90 d MaGang geese.40242163 · Zhu, Chenyu, Luo, Yongquan, Xu, Kunjie et al.2025 · 6 citationsFrontiers in nutrition. 2025;12:1537724
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective2502.20653v1 · Shaobo Wang, Yicun Yang, Zhiyuan Liu et al.2025 · 15 citationsConference on Computer Vision and Pattern Recognition, 2025
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models2502.18817v1 · Shuliang Liu, Xinze Li, Zhenghao Liu et al.2025 · 5 citationsarXiv
Learning to Generate Structured Output with Schema Reinforcement Learning2502.18878v2 · Yaxi Lu, Haolun Li, Xin Cong et al.2025 · 19 citationsarXiv
AgentRM: Enhancing Agent Generalization with Reward Modeling2502.18407v2 · Yu Xia, Jingru Fan, Weize Chen et al.2025 · 2 citationsarXiv
LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models2502.14834v1 · Shangqing Tu, Yucheng Wang, Daniel Zhang-Li et al.2025 · 0 citationsarXiv
Artificial intelligence-based model to predict recurrence after local excision in T1 rectal cancer.40043596 · Su, Jiarui, Liu, Zhiyuan, Li, Haiming et al.2025 · 8 citationsEuropean journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology. 2025;51(6):109717
Craw4LLM: Efficient Web Crawling for LLM Pretraining2502.13347v3 · Shi Yu, Zhiyuan Liu, Chenyan Xiong2025 · 4 citationsarXiv
ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation2501.06598v3 · Xuanle Zhao, Xianzhen Luo, Qi Shi et al.2025 · 5 citationsarXiv
Pathogen stress heightens sensorimotor dimensions in the human collective semantic space.39757308 · Fu, Ze, Chen, Huimin, Liu, Zhan et al.2025 · 1 citationCommunications psychology. 2025;3(1):2
Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training2412.13842v1 · Shuyin Xia, Xinjun Ma, Zhiyuan Liu et al.2024 · 13 citationsarXiv
LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer2412.13871v2 · Yipeng Zhang, Yifan Liu, Zonghao Guo et al.2024 · 0 citationsarXiv
Effect of Sr on Mechanical Properties and Corrosion Behavior of Rolled ZM60 Alloy.39769762 · Yin, Dongsong, Zhou, Yuting, Liu, Zhiyuan et al.2025 · 1 citationMaterials (Basel, Switzerland). 2024;17(24)
KBAlign: Efficient Self Adaptation on Specific Knowledge Bases2411.14790v4 · Zheni Zeng, Yuxuan Chen, Shi Yu et al.2024 · 0 citationsarXiv
Language-specific representation of emotion-concept knowledge causally supports emotion inference.39669430 · Li, Ming, Su, Yusheng, Huang, Hsiu-Yuan et al.2024 · 12 citationsiScience. 2024;27(12):111401
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning2410.22782v1 · Xujia Wang, Haiyan Zhao, Shuo Wang et al.2024 · 4 citationsarXiv
RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards2410.13509v2 · Xinze Li, Sen Mei, Zhenghao Liu et al.2024 · 0 citationsarXiv
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents2410.10594v2 · Shi Yu, Chaoyue Tang, Bokai Xu et al.2024 · 6 citationsarXiv
LLMMapReduce: Simplified Long-Sequence Processing using Large Language Models2410.09342v1 · Zihan Zhou, Chong Li, Xinyi Chen et al.2024 · 1 citationarXiv
Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System2410.08115v2 · Weize Chen, Jiarui Yuan, Chen Qian et al.2024 · 12 citationsarXiv
Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs2410.06581v1 · Cheng Gao, Chaojun Xiao, Zhenghao Liu et al.2024 · 10 citationsarXiv
Stuffed Mamba: Oversized States Lead to the Inability to Forget2410.07145v4 · Yingfa Chen, Xinrong Zhang, Shengding Hu et al.2024 · 1 citationarXiv
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models2410.05639v1 · Ranchi Zhao, Zhen Leng Thai, Yifan Zhang et al.2024 · 1 citationEMNLP 2024
Comprehensive assessment of matcha qualities and visualization of constituents using hyperspectral imaging technology.39614577 · Hu, Yan, Yu, Huahao, Song, Xinbei et al.2024 · 17 citationsFood research international (Ottawa, Ont.). 2024;196:115110
Awaking the Slides: A Tuning-free and Knowledge-regulated AI Tutoring System via Language Model Coordination2409.07372v1 · Daniel Zhang-Li, Zheyuan Zhang, Jifan Yu et al.2024 · 3 citationsarXiv
Configurable Foundation Models: Building LLMs from a Modular Perspective2409.02877v1 · Chaojun Xiao, Zhengyan Zhang, Chenyang Song et al.2024 · 5 citationsarXiv
ChatMol: interactive molecular discovery with natural language.39222004 · Zeng, Zheni, Yin, Bangchen, Wang, Shipeng et al.2024 · 19 citationsBioinformatics (Oxford, England). 2024;40(9)
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation2409.00342v3 · Zanlin Ni, Yulin Wang, Renping Zhou et al.2024 · 4 citationsarXiv
Career total: at least 786 works. 327 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.