Five things you need to know about AI
junio 9, 2026admin NUAI,Committee,Noticias,Uncategorized(0)At SXSW London last week I gave a talk called “Five things you need to...
FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning
enero 31, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2601.21682v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate impressive capabilities across diverse tasks...
Fish Audio Releases Fish Audio S2: A New Generation of Expressive Text-to-Speech (TTS) with Absurdly Controllable Emotion
marzo 11, 2026admin NUAI,Committee,Noticias,Uncategorized(0)The landscape of Text-to-Speech (TTS) is moving away from modular pipelines toward integrated Large Audio...
FireRedTeam Releases FireRed-OCR-2B Utilizing GRPO to Solve Structural Hallucinations in Tables and LaTeX for Software Developers
marzo 2, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Document digitization has long been a multi-stage problem: first detect the layout, then extract the...
FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design
junio 17, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.13066v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However...
Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
agosto 27, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2409.08846v3 Announce Type: replace-cross Abstract: Backdoor-based fingerprinting has emerged as an effective technique for tracing...
FineWeb2: One Pipeline to Scale Them All — Adapting Pre-Training Data Processing to Every Language
junio 27, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.20920v1 Announce Type: new Abstract: Pre-training state-of-the-art large language models (LLMs) requires vast amounts of...
Fine-tuning vs. in-context learning: New research guides better LLM customization for real-world tasks
mayo 10, 2025admin NUAI,Committee,Noticias,Uncategorized(0)By combining fine-tuning and in-context learning, you get LLMs that can learn tasks that would...
Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3
agosto 15, 2026admin NUAI,Committee,Noticias,Uncategorized(0)In this tutorial, we implement an end-to-end supervised fine-tuning pipeline for the XYZ-Aquila-SFT dataset, Hugging...
