AutoCode: A New AI Framework that Lets LLMs Create and Verify Competitive Programming Problems, Mirroring the Workflow of Human Problem Setters
10 月 19, 2025admin NUAI,Committee,新闻,Uncategorized(0)Are your LLM code benchmarks actually rejecting wrong-complexity solutions and interactive-protocol violations, or are they...
Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification
9 月 23, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2309.11895v4 Announce Type: replace-cross Abstract: Standard fine-tuning of pre-trained audio models couples representation learning with...
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
6 月 3, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.01365v1 Announce Type: cross Abstract: Voice Activity Detection (VAD) plays a key role in speech...
Attention Basin: Why Contextual Position Matters in Large Language Models
8 月 8, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.05128v1 Announce Type: new Abstract: The performance of Large Language Models (LLMs) is significantly sensitive...
AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR
6 月 18, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.14190v1 Announce Type: new Abstract: Developing code-switched ASR systems is challenging due to language ambiguity...
AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
6 月 18, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.13992v1 Announce Type: cross Abstract: Large language models (LLMs) have advanced the automation of data...
Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
11 月 20, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2507.18224v4 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) based on large language models (LLMs) have...
Ask Good Questions for Large Language Models
8 月 20, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.14025v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have significantly improved...
As AI safety concerns mount, three pioneers make the case for staying open
8 月 12, 2026admin NUAI,Committee,新闻,Uncategorized(0)At Ai4, three of the world’s most respected AI experts — Geoffrey Hinton, Fei-Fei Li...
