Unverified50% confidenceFactExact time
In the transductive paradigm, computation is evenly distributed across each output token; in the inductive paradigm, the model can invest large amounts of computation in reasoning tokens while the final answer tokens are relatively lightweight.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedInference-time computation improves output quality by allocating more computational resources during the inference stage while keeping model parameters fixed.76% similarUnverifiedFor a model to truly generalize modular arithmetic tasks, it needs to implicitly discover periodic representations such as the discrete Fourier transform, rather than memorizing the answer for every pair of inputs.75% similarUnverifiedEach output token requires a full autoregressive inference computation, and the cost grows linearly or even super-linearly with length.75% similarUnverifiedEach model invocation consumes both input tokens (prompts and context) and output tokens (the model's generated response), with the two typically priced separately.74% similarUnverifiedIn the Bayesian framework, the prior plays the role of regularization, and adding a regularization term is essentially equivalent to introducing a certain prior distribution for the parameters.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995964API
curl https://kongchang.com/api/v1/knowledge/claims/995964MCP
get_claim(id=995964)