Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
Paper • 2511.19418 • Published • 29 •
4
KeyKy
kangyang
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval new activity about 2 months ago
google/gemma-4-12B:ValueError: Cannot use apply_chat_template because this processor does not have a chat template. new activity about 2 months ago
google/gemma-4-12B:ValueError: Cannot use apply_chat_template because this processor does not have a chat template.Organizations
None yet
ValueError: Cannot use apply_chat_template because this processor does not have a chat template.
#3 opened about 2 months ago
by kangyang
repeat input_ids.size(1) in dim1
1
#3 opened 4 months ago
by kangyang
GLM-4.6V-Flash 也需要用Glm4vMoeForConditionalGeneration初始化吗
2
#10 opened 8 months ago
by kangyang
commented a
paper 8 months ago