Unverified50% confidenceFactExact time
The net delta short tilt disappears entirely under GBM training and is weaker under SABR or hybrid training.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedunsloth.tile_mlp(model) can reduce MLP activation memory during training.67% similarUnverifiedZhipu did not retrain the model base, but retained GLM-5.2's base and only expanded and reinforced it during the post-training phase.61% similarUnverifiedIn real models trained on the same data, the correlation between BPB and downstream task performance is weak.60% similarUnverifiedGCD does not require retraining the model, and its deployment cost is far lower than that of adversarial training-type solutions.60% similarUnverifiedThe model did not use any pretrained weights during training.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153146API
curl https://kongchang.com/api/v1/knowledge/claims/1153146MCP
get_claim(id=1153146)