Get started
Author

Yuwei Niu

Observed name: Niu, Yuwei
OpenAlex ID: A5123970532
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
2026 · Diao, Haiwen, Wu, Penghao, et al. · arXiv (Cornell University) · 54
PDF
Look-Back: Implicit Visual Re-focusing in MLLM Reasoning
2026 · Shuo Yang, Yuwei Niu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 46
PDF
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
2026 · Meng, Fanqing, Du, Lingxiao, et al. · arXiv (Cornell University) · 25
PDF
SenseNova-U1.5: Towards Native Unified Visual Intelligence
2026 · Diao, Haiwen, Wang, Jiahao, et al. · arXiv (Cornell University) · 13
PDF
From Pixels to Words -- Towards Native One-Vision Models at Scale
2026 · Diao, Haiwen, Wang, Jiahao, et al. · arXiv (Cornell University) · 9
PDF
OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
2026 · Junzhe Chen, Tianshu Zhang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 7
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
2026 · Lin, Bin, Li, Zongjian, et al. · arXiv (Cornell University) · 7
PDF
UniWorld-Design: From Pixel Generation to Layer-Native Design
2026 · Li, Zongjian, Yan, Zhiyuan, et al. · arXiv (Cornell University) · 1
PDF
Execution Before Memory: Diagnosing Memory Failures in Video World Models
2026 · Jin, Weiyang, Yu, Jiwen, et al. · arXiv (Cornell University)
PDF
ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
2026 · Wu, Feize, Yan, Zhiyuan, et al. · arXiv (Cornell University)
PDF
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
2026 · Huang, Xu, Huang, Ye, et al. · arXiv (Cornell University)
PDF
ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?
2026 · Zhu, Bin, Jia, Yanhao, et al. · arXiv (Cornell University)
PDF
Look-Back: Implicit Visual Re-focusing in MLLM Reasoning
2026 · Association for Artificial Intelligence 2026, Lin, Bin, et al. · Underline Science Inc.
Works count: 13
Citation count: 162
H-index: 7
I10-index: 4
Year
Topic
Type