DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization
octobre 22, 2025admin NUAI,Committee,Actualités,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
août 14, 2025admin NUAI,Committee,Actualités,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
novembre 4, 2025admin NUAI,Committee,Actualités,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
janvier 19, 2026admin NUAI,Committee,Actualités,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
août 1, 2026admin NUAI,Committee,Actualités,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
janvier 4, 2026admin NUAI,Committee,Actualités,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
juin 27, 2026admin NUAI,Committee,Actualités,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
mai 30, 2025admin NUAI,Committee,Actualités,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
janvier 15, 2026admin NUAI,Committee,Actualités,Uncategorized(0)Transformers use attention and Mixture-of-Experts to scale computation, but they still lack a native way...
