Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
Paper • 2609.26637 • Published • 23
Mika Hoshino
mikaevange
·
AI & ML interests
Multimodal learning, vision-language models, image captioning, cross-modal retrieval
Recent Activity
liked a dataset about 18 hours ago
multimodal-reasoning-lab/Robot-Planning liked a model about 18 hours ago
multimodal-reasoning-lab/Anole-Zebra-CoT liked a model about 18 hours ago
era-temporary/eb_alfred_sft_single_step_reasoning_dataset_success_episodes_multimodal-lr1e-5-full-e1-bs-16Organizations
None yet