Get started
Author

Changyi Liu

Observed name: Liu, Changyi
Institution: Kuaishou (China)
Observed institution: Kuaishou (China)
OpenAlex ID: A5125550899
VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
2026 · Diao, Muxi, Xu, Wenbin, et al. · arXiv (Cornell University)
PDF
GSM: Efficient Language Modeling with Shared Global State
2026 · Zheng, Yunao, Wen, Bin, et al. · arXiv (Cornell University)
PDF
Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations
2026 · Zheng, Yunao, Wen, Bin, et al. · arXiv (Cornell University)
PDF
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
2026 · Liu, Wenqi, Ma, Shijie, et al. · arXiv (Cornell University)
PDF
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
2026 · Lu, Xingyu, Wang, Jinpeng, et al. · arXiv (Cornell University)
PDF
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
2026 · Lu, Xingyu, Wang, Jinpeng, et al. · arXiv (Cornell University)
PDF
UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
2026 · Wei, Hongyang, Wen, Bin, et al. · arXiv (Cornell University)
PDF
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
2026 · Liu, Wenqi, Wang, Yunxiao, et al. · arXiv (Cornell University)
PDF
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
2026 · Yang, Yankai, Long, Yancheng, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count:
H-index:
I10-index:
Year
Topic
Type