ZL
Zheng Liu
cs.CLcs.AIcs.IRcs.CVcs.LGcs.CRcs.DBcs.DLcs.GRcs.HC
On Valency
published · living versionsW_p2vwjgkt·v1 · currentpublished
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
with Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu +6
1 version
Preprints & journals
134 papers in the corpus · 2016–2026Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses2609.36630v1 · Ziluowen Luo, Senzhang Wang, Chaozhuo Li et al.2026 · 0 citationsarXiv
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks2609.38288v1 · Hongjin Qian, Chaofan Li, Kun Luo et al.2026 · 0 citationsarXiv
Just-In-Time Agent Memory with Runtime Agentic Research2609.34385v1 · Bingyu Yan, Chaofan Li, Hongjin Qian et al.2026 · 0 citationsarXiv
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills2609.02749v1 · Jianlyu Chen, Yuyang Hu, Hongjin Qian et al.2026 · 0 citationsarXivon Valency
AREX: Towards a Recursively Self-Improving Agent for Deep Research2607.21461v3 · Shuqi Lu, Chaofan Li, Kun Luo et al.2026 · 0 citationsarXiv
DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning2606.08035v2 · Hangui Lin, Yan Shu, Zhengyang Liang et al.2026 · 0 citationsarXiv
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent2605.24468v1 · Yuyang Hu, Hongjin Qian, Shuting Wang et al.2026 · 0 citationsarXiv
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning2605.24486v1 · Yuyang Hu, Hongjin Qian, Shuting Wang et al.2026 · 0 citationsarXiv
AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery2604.25256v1 · Lei Xiong, Kun Luo, Ziyi Xia et al.2026 · 1 citationarXiv
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent2604.17931v5 · Bince Qu, Wanli Li, Bo Pan et al.2026 · 0 citationsarXiv
PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers2604.11307v1 · Lei Xiong, Huaying Yuan, Zheng Liu et al.2026 · 0 citationsarXiv
C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts2604.11796v2 · Chenxi Qing, Junxi Wu, Zheng Liu et al.2026 · 0 citationsarXiv
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs2604.10480v1 · Yu Li, Xiaoran Shang, Qizhi Pei et al.2026 · 0 citationsarXiv
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers2603.24414v1 · Songyang Liu, Chaozhuo Li, Chenxu Wang et al.2026 · 0 citationsarXiv
AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse2603.18000v1 · Zhang Zhang, Shuqi Lu, Hongjin Qian et al.2026 · 0 citationsarXiv
DeepXiv-SDK: An Agentic Data Interface for Scientific Literature2603.00084v2 · Hongjin Qian, Ziyi Xia, Ze Liu et al.2026 · 0 citationsarXiv
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies2602.09877v2 · Chenxu Wang, Chaozhuo Li, Songyang Liu et al.2026 · 1 citationarXiv
MemoBrain: Executive Memory as an Agentic Brain for Reasoning2601.08079v1 · Hongjin Qian, Zhao Cao, Zheng Liu2026 · 1 citationarXiv
EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos2601.01050v2 · Hongming Fu, Wenjia Wang, Xiaozhen Qiao et al.2026 · 0 citationsarXiv
Video-Browser: Towards Open-web Agentic Video Browsing2512.23044v3 · Zhengyang Liang, Yan Shu, Xiangrui Liu et al.2025 · 0 citationsarXiv
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value2512.14051v1 · Mengzhang Cai, Xin Gao, Yu Li et al.2025 · 0 citationsarXiv
General Agentic Memory Via Deep Research2511.18423v1 · B.Y. Yan, Chaofan Li, Hongjin Qian et al.2025 · 0 citationsarXiv
Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference2511.16449v5 · Ziyan Liu, Yeqiu Chen, Hongyi Cai et al.2025 · 0 citationsarXiv
InfoFlow: Reinforcing Search Agent Via Reward Density Optimization2510.26575v1 · Kun Luo, Hongjin Qian, Zheng Liu et al.2025 · 0 citationsarXiv
Model-Document Protocol for AI Search2510.25160v2 · Hongjin Qian, Zheng Liu2025 · 0 citationsarXiv
ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval2510.08252v2 · Jianlyu Chen, Junwei Lan, Chaofan Li et al.2025 · 2 citationsarXiv
TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos2509.26360v3 · Xiangrui Liu, Minghao Qin, Yan Shu et al.2025 · 0 citationsarXiv
MR-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval2509.26378v1 · Junjie Zhou, Ze Liu, Lei Xiong et al.2025 · 0 citationsarXiv
Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval2509.24869v2 · Junwei Lan, Jianlyu Chen, Zheng Liu et al.2025 · 0 citationsarXiv
EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling2509.23909v3 · Xin Luo, Jiahao Wang, Chenyuan Wu et al.2025 · 0 citationsarXiv
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing2509.22186v2 · Junbo Niu, Zheng Liu, Zhuangcheng Gu et al.2025 · 10 citationsarXiv
Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature2509.16591v2 · Zheng Liu, Mengjie Liu, Siwei Wen et al.2025 · 0 citationsarXiv
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds2509.02499v3 · Junxi Wu, Jinpeng Wang, Zheng Liu et al.2025 · 0 citationsarXiv
Open Data Synthesis For Deep Research2509.00375v1 · Ziyi Xia, Kun Luo, Hongjin Qian et al.2025 · 1 citationarXiv
MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning2508.00271v2 · Hongjin Qian, Zheng Liu2025 · 0 citationsarXiv
Task-Aware KV Compression For Cost-Effective Long Video Understanding2506.21184v1 · Minghao Qin, Yan Shu, Peitian Zhang et al.2025 · 0 citationsarXiv
Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification2506.19225v1 · Minghao Qin, Xiangrui Liu, Zhengyang Liang et al.2025 · 1 citationarXiv
OmniGen2: Towards Instruction-Aligned Multimodal Generation2506.18871v4 · Chenyuan Wu, Pengfei Zheng, Ruiran Yan et al.2025 · 0 citationsarXiv
VideoExplorer: Think With Videos For Agentic Long-Video Understanding2506.10821v6 · Huaying Yuan, Zheng Liu, Junjie Zhou et al.2025 · 0 citationsarXiv
Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification2506.07446v1 · Liwen Zheng, Chaozhuo Li, Zheng Liu et al.2025 · 6 citationsarXiv
Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models2507.02870v1 · Chaozhuo Li, Pengbo Wang, Chenxu Wang et al.2025 · 8 citationsarXiv
Towards Effective Code-Integrated Reasoning2505.24480v1 · Fei Bai, Yingqian Min, Beichen Zhang et al.2025 · 1 citationarXiv
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis2505.16834v3 · Shuang Sun, Huatong Song, Yuhao Wang et al.2025 · 1 citationarXiv
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization2505.15444v1 · Yutao Zhu, Jiajie Jin, Hongjin Qian et al.2025 · 0 citationsarXiv
R2MED: A Benchmark for Reasoning-Driven Medical Retrieval2505.14558v2 · Xiangxu Zhang, Lei Li, Xiao Zhou et al.2025 · 1 citationarXiv
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis2505.12697v1 · Chaofan Li, Jianlyu Chen, Yingxia Shao et al.2025 · 1 citationarXiv
Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging2505.09316v2 · Hongjin Qian, Zheng Liu2025 · 0 citationsarXiv
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?2503.23765v6 · Yun Li, Yiming Zhang, Tao Lin et al.2025 · 8 citationsarXiv
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding2503.18478v2 · Xiangrui Liu, Yan Shu, Zheng Liu et al.2025 · 0 citationsarXiv
MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers2503.16856v2 · Yang Tian, Zheng Lu, Mingqi Gao et al.2025 · 0 citationsarXiv
Career total: 221 works. 134 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.