Unverified50% confidenceBenchmarkExact time
In the seed 3 experiment, the PPO policy trained on normal data only achieved a nominal MAE of 0.0177 and a stress MAE of 0.1166; the 5% stress policy achieved a nominal MAE of 0.0296 and a stress MAE of 0.0654; the 10% stress policy achieved a nominal MAE of 0.0501 and a stress MAE of 0.0555.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPhi-3-mini（3.8B参数）在部分基准测试上超越了Mixtral 8x7B等更大的混合专家模型62% similarUnverifiedPhi-3 是微软推出的小模型，mini 版本仅 38 亿参数，通过高质量合成数据训练在多项基准上逼近更大模型。59% similarUnverifiedOn 12 synthetic incident report extraction tasks, using Ollama to run llama3.1:8b locally with temperature=0 and a fixed seed, the single-call condition field accuracy was 30/36 (83.3%), and the three-step pipeline (planner, executor, reviewer) condition was 33/36 (91.7%).58% similarUnverified千问3.6的35B MOE模型每次只激活其中3B的参数58% similarUnverifiedSmall models of the same scale such as Phi-3-mini, Gemma-2B, and Qwen1.5-1.8B, after training on high-quality data, can achieve performance close to larger models on specific tasks.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109978API
curl https://kongchang.com/api/v1/knowledge/claims/1109978MCP
get_claim(id=1109978)