Unverified50% confidenceFactExact time
TAPES pretrains with a joint likelihood parameterized by shared discrete latent variables to explicitly model the conditional co-occurrence relationships among prediction targets.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn TAPES's discrete latent variable model, given the value of the latent variable, the prediction targets are conditionally independent; after marginalizing out the latent variable, a conditional co-occurrence structure emerges among the targets.79% similarUnverifiedTAPES is a task-aligned joint predictive pretraining framework for transaction sequences.78% similarUnverifiedParameter merging generally refers to fusing the weights of multiple independently trained models into one model via averaging, task arithmetic, Fisher weighting, or similar methods.77% similarUnverifiedSelecting the already-trained model whose parameters are closest to a specific trade-off point to approximate that point is a method with some effectiveness.76% similarUnverifiedMerging the parameters of multiple trained models to generate new trade-off combinations has been shown to be helpful.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133840API
curl https://kongchang.com/api/v1/knowledge/claims/1133840MCP
get_claim(id=1133840)