Kyle's picture

Kyle PRO

iky1e

·

https://ikyle.me

kylehowells

AI & ML interests

None yet

Recent Activity

liked a model about 10 hours ago

canopylabs/3b-es_it-ft-research_release

liked a model about 11 hours ago

canopylabs/3b-es_it-pretrain-research_release

liked a Space about 11 hours ago

freddyaboulton/really-fast-whisper

View all activity

Organizations

None yet

iky1e's activity

upvoted 2 articles about 11 hours ago

Article

Vision Language Models (Better, Faster, Stronger)

By

and 4 others •

5 days ago

• 288

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

1 day ago

• 68

upvoted an article about 12 hours ago

Article

Blazingly fast whisper transcriptions with Inference Endpoints

By

and 5 others •

4 days ago

• 56

upvoted 2 collections 1 day ago

Idefics 3 + SmolVLM

4 items • Updated Nov 26, 2024 • 2

NariLabs Dia-1.5B

4 items • Updated 20 days ago • 5

upvoted an article 8 days ago

Article

Finally, a Replacement for BERT: Introducing ModernBERT

By

and 14 others •

Dec 19, 2024

• 629

upvoted 4 collections 9 days ago

Kokoro TTS

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers amazing quality. • 4 items • Updated Feb 28 • 6

Parakeet

Nvidia's ASR models, now in MLX! • 9 items • Updated 10 days ago • 3

LLaMA-Omni

12 items • Updated about 1 month ago • 16

Parakeet

NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. • 11 items • Updated 4 days ago • 24

upvoted an article 14 days ago

Article

The 4 Things Qwen-3's Chat Template Teaches Us

By

•

17 days ago

• 38

upvoted a collection 16 days ago

Mellum

Series of code models by JetBrains • 4 items • Updated 16 days ago • 21

upvoted a paper 17 days ago

Towards Understanding Camera Motions in Any Video

Paper • 2504.15376 • Published 25 days ago • 155

upvoted a collection 17 days ago

3D Modelization

51 items • Updated 2 days ago • 11

upvoted a paper 17 days ago

3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models

Paper • 2504.17414 • Published 22 days ago • 17

upvoted a collection 18 days ago

Qwen3

39 items • Updated 4 days ago • 633

upvoted a paper 19 days ago

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published about 1 month ago • 28

upvoted a paper 22 days ago

Describe Anything: Detailed Localized Image and Video Captioning

Paper • 2504.16072 • Published 24 days ago • 61

upvoted a collection 22 days ago

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated 7 days ago • 49

upvoted a paper 24 days ago

SoundStorm: Efficient Parallel Audio Generation

Paper • 2305.09636 • Published May 16, 2023 • 12