XY
Xiangchao Yan
cs.CVcs.AIcs.CLcs.LG
On Valency
published · living versionsW_ap69b7ug·v1 · currentpublished
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
with Wenjie Lou, Tianshuo Peng, Shiyang Feng, Shengji Tang +94
1 version
Preprints & journals
27 papers in the corpus · 2023–2026Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition2610.28578v1 · Wenjie Lou, Tianshuo Peng, Shiyang Feng et al.2026 · 0 citationsarXivon Valency
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering2610.22344v1 · Shangheng Du, Jinxin Shi, Shuaiyu Zhang et al.2026 · 0 citationsarXiv
LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management2610.13075v1 · Songtao Huang, Zhijie Zhong, Xiaohan He et al.2026 · 0 citationsarXiv
Bi3D++: Hybrid Bi-Domain Active Learning for Cross-Domain 3D Object Detection.42048199 · Yuan, Jiakang, Yan, Xiangchao, Shi, Botian et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(9):11027-11043
Towards Physics-Faithful Generation of Scientific Diagrams2608.13112v1 · Minghui Zhang, Jinxin Shi, Yifan Chang et al.2026 · 0 citationsarXiv
Intern-S2-Preview: Scientific Agentic Foundation Model2608.13505v1 · Lei Bai, Jiaqi Cao, Chiyu Chen et al.2026 · 0 citationsarXiv
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation2607.08758v1 · Yifan Zhou, Qihao Yang, Yan Li et al.2026 · 0 citationsarXiv
StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding.41774644 · Xia, Renqiu, Peng, Haoyang, Ye, Hancheng et al.2026 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(7):8044-8059
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent2606.30616v2 · Lei Bai, Zongsheng Cao, Yang Chen et al.2026 · 0 citationsarXiv
Agents-K1: Towards Agent-native Knowledge Orchestration2606.13669v3 · Zongsheng Cao, Bihao Zhan, Jinxin Shi et al.2026 · 0 citationsarXiv
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery2606.06473v2 · Shangheng Du, Xiangchao Yan, Jinxin Shi et al.2026 · 0 citationsarXiv
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery2602.08990v1 · Shiyang Feng, Runmin Ma, Xiangchao Yan et al.2026 · 0 citationsarXiv
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence2512.22334v3 · Yiheng Wang, Yixin Chen, Shuo Li et al.2025 · 0 citationsarXiv
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows2512.16969v1 · Wanghan Xu, Yuhao Zhou, Yifan Zhou et al.2025 · 0 citationsarXiv
SPOT: Scalable 3D Pre-Training via Occupancy Prediction for Learning Transferable 3D Representations.40627478 · Yan, Xiangchao, Chen, Runjian, Zhang, Bo et al.2025 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):9609-9625
InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification2505.16938v3 · InternAgent Team: Bo Zhang, Shiyang Feng, Xiangchao Yan et al.2025 · 1 citationarXiv
OmniCaptioner: One Captioner to Rule Them All2504.07089v3 · Yiting Lu, Jiakang Yuan, Zhen Li et al.2025 · 0 citationsarXiv
SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing2503.04629v1 · Xiangchao Yan, Shiyang Feng, Jiakang Yuan et al.2025 · 8 citationsarXiv
Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback2501.03916v3 · Jiakang Yuan, Xiangchao Yan, Shiyang Feng et al.2025 · 5 citationsarXiv
ChartX and ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning.41082427 · Xia, Renqiu, Ye, Hancheng, Yan, Xiangchao et al.2025 · 15 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:7436-7447
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training2412.11863v2 · Renqiu Xia, Mingsheng Li, Hancheng Ye et al.2024 · 1 citationarXiv
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models2406.11633v2 · Renqiu Xia, Song Mao, Xiangchao Yan et al.2024 · 0 citationsarXiv
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text2406.08418v3 · Qingyun Li, Zhe Chen, Weiyun Wang et al.2024 · 1 citationarXiv
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites2404.16821v2 · Zhe Chen, Weiyun Wang, Hao Tian et al.2024 · 327 citationsarXiv
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning2402.12185v6 · Renqiu Xia, Bo Zhang, Hancheng Ye et al.2024 · 10 citationsarXiv
AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset2306.00612v3 · Jiakang Yuan, Bo Zhang, Xiangchao Yan et al.2023 · 14 citationsarXiv
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection2303.05886v1 · Jiakang Yuan, Bo Zhang, Xiangchao Yan et al.2023 · 29 citationsarXiv
Career total: 32 works. 27 are in this corpus.
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.