Verified75% confidenceFactExact time
EAGLE's core innovation is training a lightweight autoregressive head that takes the target model's hidden states as input features to predict the feature representation of the next token, rather than directly predicting the token itself.
3
Sources
75%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe EAGLE series does not use an independent small model as the drafter; instead, it reuses the main model's feature representations to train a lightweight autoregressive head, naturally aligning the drafter's distribution with the main model's to achieve a higher hit rate.74% similarUnverifiedEagle uses feature vectors from the intermediate layers of the target model as input for next-token prediction.74% similarUnverifiedEAGLE uses the target model's feature layers for autoregressive draft generation, making predictions in feature space rather than token space, and can usually achieve a higher acceptance rate.70% similarUnverifiedEAGLE's innovation lies in reusing the feature representations of the main model's last layer to drive the draft head, allowing draft generation to share the semantic space with the main model and thereby improving the token acceptance rate.69% similarVerifiedA surrogate model is a lightweight approximate model (such as a Gaussian process or neural network) trained with relatively few simulation samples, used to quickly predict the impact of design parameter changes on metrics such as power, area, and gain, thereby guiding the location of the next sampling point.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/869681API
curl https://kongchang.com/api/v1/knowledge/claims/869681MCP
get_claim(id=869681)