STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
décembre 1, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.24693v2 Announce Type: replace-cross Abstract: Despite rapid progress in Multi-modal Large Language Models and Large...
Stanford Researchers Introduce TRACE: A Capability-Targeted Agentic Training System That Turns Recurrent Agent Failures Into Synthetic RL Environment
juillet 13, 2026admin NUAI,Committee,Actualités,Uncategorized(0)Agentic LLMs often fail the same way, again and again. A Stanford research team traced...
Stand Up for Research, Innovation, and Education
octobre 25, 2025admin NUAI,Committee,Actualités,Uncategorized(0)Right now, MIT alumni and friends are voicing their support for: America’s scientific and technological...
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
mars 6, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2603.04759v1 Announce Type: new Abstract: The limited context window of contemporary large language models (LLMs)...
Stable Signer: Hierarchical Sign Language Generative Model
décembre 4, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2512.04048v1 Announce Type: cross Abstract: Sign Language Production (SLP) is the process of converting the...
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
mai 18, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2507.15778v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective...
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
mai 29, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2605.23440v4 Announce Type: replace Abstract: Joint Entity and Relation Extraction (JERE) is highly sensitive to...
SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
mai 12, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2411.11053v5 Announce Type: replace Abstract: Large language models demonstrate exceptional performance in simple code generation...
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
décembre 3, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2512.02807v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences typically relies...
