Unverified50% confidenceFactExact time
U-Space projects the state of each token onto a set of orthogonal basis vectors to obtain an interpretable uncertainty map.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe U-Space framework is used to reveal when and why uncertainty arises in language models, and can provide an interpretable model certainty signal through a single forward inference.66% similarUnverifiedThe Jacobian Lens projects high-dimensional hidden states back into a readable vocabulary probability distribution by computing the Jacobian matrix of each layer's activations with respect to the word embedding space.65% similarUnverifiedThe context window refers to the total number of tokens a model can see in a single inference, including input and output; the computational cost of the attention mechanism grows quadratically with sequence length.59% similarUnverifiedLatent space reasoning allows the model to complete thinking in a continuous vector space composed of hidden states, only decoding the result into text at the final stage.59% similarUnverifiedEach token is converted into a d_model-dimensional vector by looking up the Embedding Table, and N tokens form an N × d_model input matrix.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065666API
curl https://kongchang.com/api/v1/knowledge/claims/1065666MCP
get_claim(id=1065666)