Kyle's picture

Kyle PRO

iky1e

·

https://ikyle.me

kylehowells

AI & ML interests

None yet

Recent Activity

updated a collection about 21 hours ago

updated a collection about 21 hours ago

liked a model about 21 hours ago

BSC-LT/salamandra-7b-instruct

View all activity

Organizations

upvoted a paper 1 day ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 8 days ago • 132

upvoted a paper 6 days ago

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

Paper • 2606.18558 • Published 8 days ago • 50

upvoted a collection 8 days ago

FunctionGemma

3 items • Updated Mar 12 • 41

upvoted a paper 12 days ago

MiniMax Sparse Attention

Paper • 2606.13392 • Published 14 days ago • 145

upvoted 3 collections 13 days ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 36 items • Updated 10 days ago • 222

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 106 items • Updated 7 days ago • 727

Gemma 4

88 items • Updated 21 days ago • 146

upvoted an article 13 days ago

Article

Introducing North Mini Code: Cohere’s First Model For Developers

CohereLabs

•

15 days ago

• 74

upvoted 2 collections 14 days ago

DiffusionGemma

1 item • Updated 14 days ago • 52

DiffusionGemma

8 items • Updated 14 days ago • 16

upvoted a paper 14 days ago

Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models

Paper • 2606.11167 • Published 15 days ago • 5

upvoted a collection 14 days ago

Interactivity Alignment

Full-duplex speech models post-trained with reinforcement learning for improved conversational interactivity. • 4 items • Updated 15 days ago • 6

upvoted a collection 16 days ago

Ideogram 4

8 items • Updated 20 days ago • 64

upvoted a paper 20 days ago

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition

Paper • 2312.17279 • Published Dec 27, 2023 • 4

upvoted an article 20 days ago

Article

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

nvidia

•

21 days ago

• 64

upvoted 2 collections 20 days ago

CoreML Speech Models

Speech AI models for Apple Neural Engine via CoreML. iOS/macOS ready. ASR, TTS, VAD, diarization. • 28 items • Updated 2 days ago • 4

MLX Speech Models

Speech AI models for Apple Silicon via MLX. ASR, TTS, VAD, diarization, speaker embedding. • 57 items • Updated 3 days ago • 5

upvoted a paper 22 days ago

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Paper • 2605.26368 • Published May 25 • 4

upvoted a collection 22 days ago

📟 PaGeR

Panorama Geometry Reconstruction • 7 items • Updated 29 days ago • 3

upvoted a paper 27 days ago

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

Paper • 2605.28763 • Published 29 days ago • 14