The b2n task for VQA, added brief description for each sample. Setting on 4-shot
Kaze Sama
kaze-desu
AI & ML interests
MLLM, Domain Generalization
Recent Activity
upvoted a paper about 2 hours ago
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning upvoted a paper 2 months ago
ICA Lens: Interpreting Language Models Without Training Another Dictionary updated a dataset 7 months ago
kaze-desu/spatial-trainset-3kOrganizations
None yet