VLM with GRPO training for vision-grounded decision making (https://arxiv.org/pdf/2503.16965)
Derek Zhe Hu
zhehuderek
AI & ML interests
NLP, Multimodality
Recent Activity
liked
a dataset
8 days ago
ProlificAI/social-reasoning-rlhf
updated
a dataset
about 2 months ago
zhehuderek/humor_understanding_combined
published
a dataset
about 2 months ago
zhehuderek/humor_understanding_combined
Organizations
None yet
The collections of visual humor understanding and comparative reasoning.
-
zhehuderek/YESBUT_Benchmark
Viewer • Updated • 348 • 45 • 1 -
zhehuderek/YESBUT_Benchmark_V2
Viewer • Updated • 1.26k • 50 • 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 GRPO training for vision-grounded decision making (https://arxiv.org/pdf/2503.16965)
The collections of visual humor understanding and comparative reasoning.
-
zhehuderek/YESBUT_Benchmark
Viewer • Updated • 348 • 45 • 1 -
zhehuderek/YESBUT_Benchmark_V2
Viewer • Updated • 1.26k • 50 • 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
models
5
zhehuderek/qwen2_5_vl_3b_sft_decisionmaking_gpt4reason
Image-to-Text
•
4B
•
Updated
•
2
zhehuderek/qwen2_5_vl_3b_grpo_decisionmaking_scratch_run3_85
Image-to-Text
•
4B
•
Updated
•
1
zhehuderek/qwen2_5_vl_3b_GEOQA_8K_hf
Image-to-Text
•
4B
•
Updated
•
3
zhehuderek/llama-2-7b-chinese
Text Generation
•
7B
•
Updated
•
3
zhehuderek/llama-3.1-8b-chinese-sft
Text Generation
•
8B
•
Updated
•
3
datasets
8
zhehuderek/humor_understanding_combined
Viewer
•
Updated
•
4.89k
•
13
•
1
zhehuderek/humor_understanding_nyt
Viewer
•
Updated
•
2.69k
•
6
zhehuderek/comparative_reasoning_mllm_compbench
Viewer
•
Updated
•
21.8k
•
65
zhehuderek/humor_understanding_deepeval
Viewer
•
Updated
•
2.96k
•
7
zhehuderek/textual_decisionmaking_data
Viewer
•
Updated
•
11k
•
15
•
1
zhehuderek/YESBUT_Benchmark_V2
Viewer
•
Updated
•
1.26k
•
50
•
1
zhehuderek/YESBUT_Benchmark
Viewer
•
Updated
•
348
•
45
•
1
zhehuderek/VIVA_Benchmark_EMNLP24
Viewer
•
Updated
•
1.24k
•
14