Nous Research Releases Contrastive Neuron Attribution (CNA): Sparse MLP Circuit Steering Without SAE Training or Weight Modification
พฤษภาคม 23, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)Instruction-tuned language models refuse harmful requests. But which part of the model is actually responsible...
Nous Research Releases ‘Hermes Agent’ to Fix AI Forgetfulness with Multi-Level Memory and Dedicated Remote Terminal Access Support
กุมภาพันธ์ 26, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)In the current AI landscape, we’ve become accustomed to the ‘ephemeral agent’—a brilliant but forgetful...
Nous Research Proposes Lighthouse Attention: A Training-Only Selection-Based Hierarchical Attention That Delivers 1.4–1.7× Pretraining Speedup at Long Context
พฤษภาคม 17, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)Training large language models on long sequences has a well-known problem: attention is expensive. The...
Not Just Understanding, But Evolving: The All-New Self-Evolving JiuwenClaw Makes Its Debut
มีนาคม 28, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)Over the past year, AI agents have evolved from merely answering questions to attempting to...
Not everything needs an LLM: A framework for evaluating when AI makes sense
พฤษภาคม 4, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)The answer to ‘What customer needs requires an AI solution?’ isn’t always ‘Yes.’ LLMs are...
Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
มิถุนายน 6, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2410.12872v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently emerged as promising tools...
Not All Needles Are Found: How Fact Distribution and Don’t Make It Up Prompts Shape Literal Extraction, Logical Inference, and Hallucination Risks in Long-Context LLMs
มกราคม 6, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2601.02023v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support very long input contexts...
Non-Collaborative User Simulators for Tool Agents
ธันวาคม 9, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2509.23124v3 Announce Type: replace Abstract: Tool agents interact with users through multi-turn dialogues to accomplish...
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining
กรกฎาคม 21, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2507.14119v1 Announce Type: cross Abstract: Recent advances in generative modeling enable image editing assistants that...
