Unverified50% confidenceFactExact time
The study uses frozen pathology foundation model representations from UNI2-h and CONCH for feature extraction without fine-tuning.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe frozen representations of pathology foundation models contain information for predicting rare joint molecular phenotypes, supporting such tasks without fine-tuning.74% similarUnverifiedA frozen model refers to a model whose weight parameters all remain unchanged during the inference phase, with no fine-tuning, adapter training, or online learning performed.65% similarUnverifiedAll comparative experiments in the study share the same frozen 7B-parameter backbone model, with the only difference being the content placed in the context.64% similarUnverifiedThe core of model distillation lies in the application of the temperature softmax function, which softens the probability distribution through the temperature parameter T to reveal similarity relationships between classes56% similarUnverifiedApproaches that fall between frozen embeddings and full fine-tuning include fine-tuning only the last few layers, using parameter-efficient fine-tuning methods such as LoRA, or employing an adapter architecture.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983421API
curl https://kongchang.com/api/v1/knowledge/claims/983421MCP
get_claim(id=983421)