Unverified50% confidenceBenchmarkExact time
On reasoning and tool-use benchmarks, FSPO achieved the highest average accuracy within a 5-hour training budget, about 4 percentage points higher on average than the strongest baseline.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedEmsyAI was trained for 15,000 steps using FP16 mixed precision, with validation perplexity converging to 5.8671% similarUnverifiedGradient checkpointing and mixed-precision training (FP16/BF16) are common memory-reduction measures.68% similarUnverifiedGLM-5.3的智能体编程准确率随投入词元增加而提升：低投入约24.7，高投入31.5，最大投入34.766% similarUnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平66% similarUnverified在混合精度Adam训练中，单个参数的完整训练状态高达18字节（FP16权重2字节、FP32主权重4字节、一阶矩4字节、二阶矩4字节，加梯度）64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037326API
curl https://kongchang.com/api/v1/knowledge/claims/1037326MCP
get_claim(id=1037326)