Kyle PRO

iky1e's activity

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

upvoted 2 papers 2 days ago

Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities

Paper • 2505.08699 • Published May 13, 2025 • 4

Self-Speculative Decoding for LLM-based ASR with CTC Encoder Drafts

Paper • 2603.11243 • Published Mar 11 • 2

upvoted 2 articles 2 days ago

view article

Article

A Deepdive into Aya Expanse: Advancing the Frontier of Multilinguality

• 
• 
• +2

johndang-cohere, shivalikasingh, dsouzadaniel, ArashAhmadian

•

Oct 24, 2024

• 65

view article

Article

Universal Assisted Generation: Faster Decoding with Any Assistant Model

• 
• 
• +6

danielkorat, orenpereg, mber, jmamou, joaogante, lewtun, Nadav-Timor, moshew

•

Oct 29, 2024

• 62

liked a model 2 days ago

nvidia/speakerverification_en_titanet_large

Updated Nov 14, 2023 • 121k • 125

upvoted 2 articles 3 days ago

view article

Article

Security incident disclosure — July 2026

• 

system

•

8 days ago

• 536

view article

Article

Be Ready Before the Attack: A Practical Guide to Self-Hosting an Open Model for Cyber Defense

• 

jeffboudier

•

3 days ago

• 14

upvoted a paper 5 days ago

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Paper • 2408.13912 • Published Aug 25, 2024 • 2

liked 4 models 9 days ago

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 4B • Updated 5 days ago • 576k • • 967

prism-ml/Bonsai-27B-gguf

Text Generation • 4B • Updated 6 days ago • 1.91M • 611

prism-ml/Ternary-Bonsai-27B-mlx-2bit

Text Generation • 3B • Updated 9 days ago • 27.6k • 142

prism-ml/Bonsai-27B-mlx-1bit

Text Generation • 2B • Updated 9 days ago • 34.3k • 168

liked a Space 9 days ago

Running

Featured

297

Bonsai 27B WebGPU Kernels

🌳

297

Run a 1-bit 27B LLM locally in your browser on WebGPU

upvoted a collection 9 days ago

Bonsai 27B

Collection

10 items • Updated 9 days ago • 193

updated a collection 9 days ago

Text to Image

Collection

25 items • Updated 9 days ago

liked 2 models 9 days ago

fal/ideogram-v4-instant

Text-to-Image • 9B • Updated 9 days ago • • 31

fal/ideogram-v4-fast

Text-to-Image • 9B • Updated 9 days ago • • 25

upvoted a paper 9 days ago

UniSE: A Unified Framework for Decoder-only Autoregressive LM-based Speech Enhancement

Paper • 2510.20441 • Published Oct 23, 2025 • 2

upvoted an article 9 days ago

view article

Article

Native-speed vLLM transformers modeling backend

• 
• 

hmellor, lysandre

•

16 days ago

• 58

liked a model 9 days ago

QuarkAudio/QuarkAudio-UniSE

Updated Dec 25, 2025 • 36