[KongchangAI]
Unverified50% confidenceFactExact time

The main experiments are based on Qwen3-1.7B and 4B configurations, with visual capacity fixed at 0.4B parameters, plus a scale ladder of backbone models from 0.6B to 6.4B.

1
Sources
50%
Confidence
Long-term
Relevance
11/15/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1173179
API
curl https://kongchang.com/api/v1/knowledge/claims/1173179
MCP
get_claim(id=1173179)