Unverified50% confidenceFactExact time
In FS's deterministic strategy, the lower bound f_min may remain unchanged for an extended period, preventing the FOCAL set from expanding and causing the search to fall into an inefficient plateau.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExpanding the minimum-f node advances the lower bound f_min, thereby enlarging the FOCAL set and allowing more nodes that may lead to feasible solutions to enter the candidate range.72% similarUnverified稀疏激活架构下推理阶段的FLOPs与激活参数规模线性相关而非与总参数规模相关，从而降低单次推理的计算资源消耗和延迟65% similarUnverifiedThe residual structure makes F=0 the default option—as long as the F(x) weights are close to zero, the residual block degenerates into an identity mapping, thereby resolving the optimization difficulty of SGD in learning identity mappings.64% similarUnverifiedExcessively thorough SFT may harm the exploration space for subsequent RL, and a perfectly converged SFT model is not necessarily the best starting point for RL.63% similarUnverifiedProbabilistic Focal Search (PFS) follows the heuristic-guided selection of FS with probability p, and with probability 1-p expands the node with the minimum f value in the OPEN list.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916289API
curl https://kongchang.com/api/v1/knowledge/claims/916289MCP
get_claim(id=916289)