Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Yongheng Zhang
Observed name:
Zhang, Yongheng
Institutions:
Central South University,
Tencent (China),
Tsinghua University
Observed institutions:
Central South University,
Tencent (China),
Tsinghua University
OpenAlex ID:
A5146593270
Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
2026
·
Li, Yinghui
, Kuang, Jiayi
, et al.
·
arXiv (Cornell University)
·
8
PDF
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
2026
·
Zhang, Yongheng
, Liu, Ziang
, et al.
·
arXiv (Cornell University)
·
7
PDF
Latent Visual Cache for Video Reasoning
2026
·
Zhang, Yongheng
, Xu, Zhipeng
, et al.
·
arXiv (Cornell University)
·
6
PDF
OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning
2026
·
Wu, Hao
, Zhang, Yongheng
, et al.
·
arXiv (Cornell University)
·
6
PDF
Thinking in Video: Can Video Generators Really Reason About the Real World?
2026
·
Zhang, Yongheng
, Yang, Guang
, et al.
·
arXiv (Cornell University)
·
5
PDF
Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning
2026
·
Shen, Ao
, Zhang, Yongheng
, et al.
·
arXiv (Cornell University)
·
2
PDF
ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
2026
·
Peng, Chunyi
, Xu, Zhipeng
, et al.
·
arXiv (Cornell University)
·
2
PDF
LUT: Latent Utility Training for Visual Reasoning
2026
·
Kang, Jiaxuan
, Chen, Siyu
, et al.
·
arXiv (Cornell University)
·
2
PDF
Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
2026
·
Liu, Xu
, Zhang, Yongheng
, et al.
·
arXiv (Cornell University)
·
2
PDF
Let’s Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
2026
·
Xu Liu
, Yongheng Zhang
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
·
1
PDF
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
2026
·
Yan, Siyu
, Yan, Zhuoran
, et al.
·
arXiv (Cornell University)
PDF
Let’s Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
2026
·
Association for Artificial Intelligence 2026
, Chen, Qiguang
, et al.
·
Underline Science Inc.
Show more works
View as search
Works count:
13
Citation count:
41
H-index:
5
I10-index:
Year
Topic
Type
