#多模态

Posts connected by this tag.

2 postsView all tags →

From Single-Frame Vision to Real-Time Video Conversation: The Multimodal Architecture Paths of DeepSeek, MiniCPM, and MiniMax

2026-08-25

TechnologyLearning Note

/

/

/

/

From DeepSeek visual primitives and MiniMax-M3 image TTFT to how MiniCPM-o sustains local video understanding and full-duplex speech interaction.

3346 words

|

17 minutes

Cover Image of the Post

Single Image Does Not Equal Multiple Images: Why VLMs Hallucinate More with Multiple Images, and a Two-Stage Fix

2026-02-08

TechnologyLearning Note

/

/

/

An investigation into why web and API results diverge during multi-image analysis, from Lost in the Middle to a two-stage approach based on per-image pre-summaries.

2061 words

|

10 minutes

Cover Image of the Post