Patryk Binkowski

ismu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a collection 15 days ago

LayerSkip

Collection

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 18 days ago • 43

upvoted 2 collections 4 months ago

BigVGAN

Collection

BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input. • 11 items • Updated Oct 1 • 10

LLaVa-Interleave

Collection

LLaVa models that extends the model capabilities to Multi-image, Multi-frame (videos), Multi-patch (single-image) scenarios. • 3 items • Updated Jul 10 • 14

upvoted a paper over 1 year ago

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Paper • 2307.02486 • Published Jul 5, 2023 • 80