Unverified50% confidenceFactExact time
TAPES is a task-aligned joint predictive pretraining framework for transaction sequences.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTAPES pretrains with a joint likelihood parameterized by shared discrete latent variables to explicitly model the conditional co-occurrence relationships among prediction targets.78% similarUnverifiedScheduled Sampling is a compromise approach to mitigating exposure bias, gradually introducing the model's own predictions as input during the later stages of training.70% similarUnverifiedThis study published on arXiv proposes a new proposition called Alignment Forecasting: predicting before training begins whether a given fine-tuning dataset will significantly exacerbate specific misalignment behaviors.69% similarUnverifiedThe framework uses a flow matching model during training to learn the joint distribution of adjacent axial slice triplets.68% similarUnverifiedTabPFN的预训练使用由结构因果模型和贝叶斯网络等概率生成模型采样得到的合成数据集66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133831API
curl https://kongchang.com/api/v1/knowledge/claims/1133831MCP
get_claim(id=1133831)