MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
มิถุนายน 3, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2604.08782v3 Announce Type: replace Abstract: Large language models (LLMs) suffer significant performance degradation when user...
MSCoRe: A Benchmark for Multi-Stage Collaborative Reasoning in LLM Agents
กันยายน 23, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2509.17628v1 Announce Type: new Abstract: Large Language Models (LLMs) have excelled in question-answering (QA) tasks...
Moving toward LessOps with VMware-to-cloud migrations
พฤศจิกายน 28, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)Today’s IT leaders face competing mandates to do more (“make us an ‘AI-first’ enterprise—yesterday”) with...
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
ตุลาคม 13, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2510.08804v1 Announce Type: new Abstract: We present MOSAIC, a multi-agent Large Language Model (LLM) framework...
MoonshotAI Released Checkpoint-Engine: A Simple Middleware to Update Model Weights in LLM Inference Engines, Effective for Reinforcement Learning
กันยายน 16, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)MoonshotAI has open-sourced checkpoint-engine, a lightweight middleware aimed at solving one of the key bottlenecks...
Moonshot AI’s Kimi K2 outperforms GPT-4 in key benchmarks — and it’s free
กรกฎาคม 12, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)Chinese AI startup Moonshot releases open-source Kimi K2 model that outperforms OpenAI and Anthropic on...
Moonshot AI Researchers Introduce Seer: An Online Context Learning System for Fast Synchronous Reinforcement Learning RL Rollouts
พฤศจิกายน 23, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)How do you keep reinforcement learning for large reasoning models from stalling on a few...
Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6
มิถุนายน 13, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)This week, Moonshot AI released Kimi K2.7-Code. It is a coding-focused, agentic model. The model...
Moonshot AI Releases Kimi K2: A Trillion-Parameter MoE Model Focused on Long Context, Code, Reasoning, and Agentic Behavior
กรกฎาคม 12, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)Kimi K2, launched by Moonshot AI in July 2025, is a purpose-built, open-source Mixture-of-Experts (MoE)...
