VLM with textual-driven GRPO training for vision-grounded decision making (https://arxiv.org/pdf/2503.16965, NeurIPS 2025)
Derek Zhe Hu
zhehuderek
AI & ML interests
NLP, Multimodality
Recent Activity
liked
a dataset
1 day ago
builddotai/Egocentric-10K
liked
a dataset
about 1 month ago
nvidia/PBench
liked
a dataset
about 1 month ago
luckychao/EMMA
Organizations
None yet
The collections of visual humor understanding and comparative reasoning.
-
zhehuderek/YESBUT_Benchmark
Viewer • Updated • 348 • 23 • 1 -
zhehuderek/YESBUT_Benchmark_V2
Viewer • Updated • 1.26k • 27 • 1 -
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Paper • 2405.19088 • Published -
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Paper • 2503.23137 • Published
VLM with textual-driven GRPO training for vision-grounded decision making (https://arxiv.org/pdf/2503.16965, NeurIPS 2025)
The collections of visual humor understanding and comparative reasoning.
-
zhehuderek/YESBUT_Benchmark
Viewer • Updated • 348 • 23 • 1 -
zhehuderek/YESBUT_Benchmark_V2
Viewer • Updated • 1.26k • 27 • 1 -
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Paper • 2405.19088 • Published -
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Paper • 2503.23137 • Published