Researchers from the National University of Singapore Introduce ‘Thinkless,’ an Adaptive Framework that Reduces Unnecessary Reasoning by up to 90% Using DeGRPO
5 月 23, 2025admin NUAI,Committee,新闻,Uncategorized(0)The effectiveness of language models relies on their ability to simulate human-like step-by-step deduction. However...
Researchers at UT Austin Introduce Panda: A Foundation Model for Nonlinear Dynamics Pretrained on 20,000 Chaotic ODE Discovered via Evolutionary Search
5 月 27, 2025admin NUAI,Committee,新闻,Uncategorized(0)Chaotic systems, such as fluid dynamics or brain activity, are highly sensitive to initial conditions...
Research on the Integration of Embodied Intelligence and Reinforcement Learning in Textual Domains
10 月 2, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2510.01076v1 Announce Type: new Abstract: This article addresses embodied intelligence and reinforcement learning integration in...
Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
9 月 8, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2509.04770v1 Announce Type: new Abstract: Accurately answering complex questions has consistently been a significant challenge...
Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing
6 月 10, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.07086v1 Announce Type: new Abstract: Multi-modal affective computing aims to automatically recognize and interpret human...
Repositioning retail for the AI era
6 月 25, 2026admin NUAI,Committee,新闻,Uncategorized(0)Artificial intelligence is rapidly reshaping retail, but not in the ways consumers might immediately notice...
RePo: Language Models with Context Re-Positioning
12 月 17, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.14391v1 Announce Type: cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs);...
REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities
6 月 17, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2503.13102v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have introduced the...
Rep2Text: Decoding Full Text from a Single LLM Token Representation
11 月 11, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2511.06571v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress across diverse...
