🏢 Stanford University
BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
·4247 words·20 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Stanford University
BoxingGym: A new benchmark rigorously evaluates AI agents’ ability to design experiments and discover scientific models, revealing current LLMs’ limitations and highlighting fertile research avenues.
Whisper-GPT: A Hybrid Representation Audio Large Language Model
·1640 words·8 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Speech and Audio
Audio Generation
🏢 Stanford University
Whisper-GPT, a hybrid audio LLM, improves music/speech generation by combining audio waveforms and text.
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
·3186 words·15 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Stanford University
FiVA dataset and its adaptation framework enable unprecedented fine-grained control over visual attributes in text-to-image generation, empowering users to craft highly customized images.
SegBook: A Simple Baseline and Cookbook for Volumetric Medical Image Segmentation
·2952 words·14 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Segmentation
🏢 Stanford University
SegBook: a large-scale benchmark, reveals that fine-tuning full-body CT pre-trained models significantly improves performance on various downstream medical image segmentation tasks, particularly for s…
RedPajama: an Open Dataset for Training Large Language Models
·7625 words·36 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Stanford University
RedPajama, two massive open-source datasets, are released for training LLMs, improving transparency and facilitating the development of high-performing open-source models.