Unverified50% confidenceFactExact time
A sequence of 6 tokens fed into an encoder with d_model = 512 forms a 6×512 matrix.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe typical form of a modular arithmetic task is to give a modulus p (usually a prime such as 97 or 113) and have the model learn operations of the form (a+b) mod p, with inputs as one-hot encoded integers.59% similarUnverifiedC51用51个等距原子离散化Q值分布支撑集，网络对每个动作输出51维softmax向量，训练目标为最小化预测分布与目标分布间的KL散度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.57% similarUnverifiedThe team performed one epoch of fine-tuning on 477,642 synthetic reasoning trajectories distilled from GLM-5.2, covering 22,000 curated problems spanning 16 competitive programming contest systems.57% similarUnverifiedModel batching improves hardware utilization by concatenating multiple independent inference requests into the same tensor matrix and feeding them into the GPU at once to complete matrix multiplication.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106229API
curl https://kongchang.com/api/v1/knowledge/claims/1106229MCP
get_claim(id=1106229)