Unverified50% confidenceFactExact time
Dynamic absorption activation dynamically skips unnecessary neuron activation paths based on input during the inference phase, reducing FLOP consumption through sparse computation
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
Unverified等变神经网络的等变性使输出随输入的旋转或平移变换而以相同方式变换，这种归纳偏置提高了样本效率69% similarUnverifiedThe Skill caching mechanism reduces token consumption by reusing learned skills to skip reasoning from scratch, thereby reducing the number of reasoning rounds and context length.69% similarUnverifiedThe weakening of pattern separation ability during aging tilts the balance toward pattern completion, which is the neurocomputational basis for memory confusion.68% similarUnverifiedPruning is the process of identifying and removing neural network weights or entire channels that contribute minimally to the output, thereby reducing the model's structure.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963241API
curl https://kongchang.com/api/v1/knowledge/claims/963241MCP
get_claim(id=963241)