Unverified50% confidenceBenchmarkExact time
A learnable permutation-invariant graph context aggregation mechanism (implemented with weighted averaging and Set2Set) achieved the largest improvement, about 0.9 percentage points, on the CVRP100 to CVRP20 transfer.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAmong the nine combinations that include unseen sizes (CVRP35, CVRP75, CVRP200), eight achieved improvements, with a maximum gain of 3.2%.72% similarUnverifiedRMSProp replaces accumulation with an exponential moving average, solving AdaGrad's vanishing learning rate problem.67% similarUnverified在从50%到92%的准确率提升中，REPL贡献最大（直接从50%跳至74%），随后领域知识注入、模糊搜索、公式追踪、系统prompt优化和bug修复层层累积66% similarUnverifiedImage preprocessing often has the highest return on investment, and sometimes this single step alone can improve OCR accuracy by 10–20 percentage points.65% similarUnverifiedIn the setting with condition number 100, when the factors are generated before the readout scaling, RC-DS raises the average sparse factor recovery rate from 0.506 to 0.913, against a baseline of centered logit training under the same budget.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079405API
curl https://kongchang.com/api/v1/knowledge/claims/1079405MCP
get_claim(id=1079405)