Author

Huacan Wang

Observed name: Wang, Huacan

Institutions: Midea Group (China), University of Chinese Academy of Sciences, Beihang University

Observed institutions: Midea Group (China), University of Chinese Academy of Sciences, Beihang University

ORCID: 0009-0002-3425-6576

Observed ORCID: 0009-0002-3425-6576

OpenAlex ID: A5122964996

Easy for Children, Hard for AI: The Limits of Multimodal LLMs in Early Childhood Learning

2026 · Jingping Liu, Xueyan Wu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1

Sema Core: An Open, Embeddable AI Coding Agent Runtime for the IDE and Beyond

2026 · Huacan Wang, Jie Zhou, et al. · ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH)

CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection

2026 · Pan, Qihua, Tang, Zhenheng, et al. · arXiv (Cornell University)

Explicit Representation Alignment for Multimodal Sentiment Analysis

2026 · Wang, Baode, Wang, Ziming, et al. · arXiv (Cornell University)

MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning

2026 · Association for Computational Linguistics 2026, Chen, Ronghao, et al. · Underline Science Inc.

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

2026 · Association for Computational Linguistics 2026, Chen, Ronghao, et al. · Underline Science Inc.

Tiny Scales, Great Challenges: The Limits of Multimodal LLMs in Scale Recognition

2026 · Association for Computational Linguistics 2026, Chen, Ronghao, et al. · Underline Science Inc.

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

2026 · Association for Computational Linguistics 2026, Chen, Zhisheng, et al. · Underline Science Inc.

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

2026 · Association for Computational Linguistics 2026, Bian, Haonan, et al. · Underline Science Inc.

CloneMem: Benchmarking Long-Term Memory for AI Clones

2026 · Association for Computational Linguistics 2026, Chen, Ronghao, et al. · Underline Science Inc.

LiveCANNBench: Benchmark SWE AI Coding for Ascend CANN

2026 · Association for Computational Linguistics 2026, Chen, Ronghao, et al. · Underline Science Inc.

SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory

2026 · Association for Computational Linguistics 2026, Lyu, Pin, et al. · Underline Science Inc.

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

2026 · Zhou, Yifan, Zhang, Zhentao, et al. · arXiv (Cornell University)

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering

2026 · Zhu, Ningyan, Wang, Huacan, et al. · arXiv (Cornell University)

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

2026 · Yu, Xinlei, Chen, Zhangquan, et al. · arXiv (Cornell University)

Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation

2026 · Li, Daiqiang, Pan, Zihao, et al. · arXiv (Cornell University)

PsyPARSE: Retrieval-Augmented Slow Thinking for Personalized Empathetic Counseling

2026 · Longxiang Wang, Pukun Zhao, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening

2026 · Yu, Zhenxiong, Yang, Zhi, et al. · arXiv (Cornell University)

EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

2026 · Zhang, Shuo, Yuan, Chaofa, et al. · arXiv (Cornell University)

CloneMem: Benchmarking Long-Term Memory for AI Clones

2026 · Hu, Sen, Zhang, Zhiyu, et al. · arXiv (Cornell University)

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

2026 · Bian, Haonan, Yao, Zhiyuan, et al. · arXiv (Cornell University)

FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

2026 · Yang, Zhi, Li, Runguo, et al. · arXiv (Cornell University)

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

2026 · Wu, Tingyu, Chen, Zhisheng, et al. · arXiv (Cornell University)

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging

2026 · Association for Artificial Intelligence 2026, Du, Yuntao, et al. · Underline Science Inc.

Easy for Children, Hard for AI: The Limits of Multimodal LLMs in Early Childhood Learning

2026 · Association for Artificial Intelligence 2026, Chen, Hanxuan, et al. · Underline Science Inc.

Works count: 28

Citation count: 1

H-index: 1

I10-index: