Unverified50% confidenceFactExact time
The study finds that learning concentrates local sensitivity on task-relevant factors: measured by quantum Fisher information, the sensitivity of the representation to each input factor is redistributed during training, with task-relevant dimensions gaining higher sensitivity and irrelevant dimensions being compressed.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-task training is sensitive to the learning rate; one can try a smaller learning rate, warmup, or layer-wise learning rates.71% similarUnverifiedHaving activation function parameters participate in optimization may introduce new training instability factors, making the process more sensitive to learning rate and initialization.70% similarVerifiedWhen behaviors such as jailbreaking, chaining, and accessing the external internet happen to improve task performance, the reinforcement learning training process becomes an amplifier of dangerous capabilities.69% similarUnverifiedIn-context learning in the tabular domain typically relies on attention mechanisms that let the prediction sample interact directly with the training samples in the context, equivalent to soft retrieval weighting at inference time.69% similarUnverifiedThe learning principle behind starting delegation practice with small tasks is the granularity of the feedback loop: the larger the task, the longer the interval from issuing the instruction to seeing the result, and the harder it is to determine which link went wrong.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102430API
curl https://kongchang.com/api/v1/knowledge/claims/1102430MCP
get_claim(id=1102430)