T
traeai
Sign in

概念

Test-Time Scaling

别名:测试时扩展、TTS

在推理阶段动态分配更多计算资源以提升模型输出的技术范式。

已跟踪 2 条高相关材料

TraeAI 观察

相关材料

已收录 2 条与 Test-Time Scaling 相关的内容,按评分排序。

Databricks 图标

Databricks' Instructed-Retriever-1 cuts search latency by 3x and TTFT to ~2s via parallel test-time scaling without quality loss. The unified model handles query generation and reranking in parallel using multi-pivot groupwise reranking, achieving Pareto-optimal recall-precision tradeoffs for enterprise RAG systems.

入选理由:Instructed-Retriever-1使搜索延迟降低3倍以上,TTFT降至约2秒,无需重新配置。

FeaturedArticle#RAG#Test-Time Scaling#Instructed-Retriever-1#Databricks#Retrieval英文
// LLMs Improving LLMs //

Interesting progress the past of couple of weeks around self-improving AI...

// LLMs Improving LLMs //

elvis(@omarsar0)289 字 (约 2 分钟)
87

The AutoTTS framework enables LLMs to autonomously search test-time scaling strategies, discovering controllers superior to human-designed ones in just $39.9 and 160 minutes, achieving better accuracy-cost Pareto frontiers on math reasoning tasks.

入选理由:AutoTTS将测试时扩展策略搜索成本降至39.9美元和160分钟,显著低于传统人工调参。

FeaturedTweet#LLM#AutoTTS#AI agent#test-time scaling#arXiv paper英文

跨材料问答 · Test-Time Scaling

回答基于:Test-Time Scaling 相关 2 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.