DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization
10月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2510.18257v1 Announce Type: new Abstract: Prompt Optimization has emerged as a crucial approach due to...
DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments
8月 14, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2506.00739v3 Announce Type: replace Abstract: Large language model (LLM) agents have shown impressive capabilities in...
DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
11月 4, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2511.01192v1 Announce Type: new Abstract: Detecting machine-generated text (MGT) has emerged as a critical challenge...
DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation
1月 19, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2512.17776v2 Announce Type: replace Abstract: As large language models advance, deep research systems capable of...
DeepSeek Upgrades DeepSeek-V4-Flash-0731 with Major Agentic and Coding Gains
8月 1, 2026admin NUAI,Committee,ニュース,Uncategorized(0)DeepSeek published DeepSeek-V4-Flash-0731 on Hugging Face and moved the official V4-Flash API into public beta...
DeepSeek Researchers Apply a 1967 Matrix Normalization Algorithm to Fix Instability in Hyper Connections
1月 4, 2026admin NUAI,Committee,ニュース,Uncategorized(0)DeepSeek researchers are trying to solve a precise issue in large language model training. Residual...
DeepSeek Releases DSpark, a Speculative Decoding Framework That Accelerates DeepSeek-V4 Per-User Generation 60–85% Over MTP-1
6月 27, 2026admin NUAI,Committee,ニュース,Uncategorized(0)DeepSeek released DSpark, a speculative decoding framework, with open-source checkpoints and training code. It is...
DeepSeek R1-0528 arrives in powerful open source challenge to OpenAI o3 and Google Gemini 2.5 Pro
5月 30, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Additionally, the model’s hallucination rate has been reduced, contributing to more reliable and consistent output.Read...
DeepSeek AI Researchers Introduce Engram: A Conditional Memory Axis For Sparse LLMs
1月 15, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Transformers use attention and Mixture-of-Experts to scale computation, but they still lack a native way...
