Kyle's picture

Kyle PRO

iky1e

·

https://ikyle.me

kylehowells

AI & ML interests

None yet

Recent Activity

liked a model about 3 hours ago

Qwen/Qwen2.5-0.5B

upvoted a collection about 3 hours ago

upvoted a collection about 7 hours ago

Marian COMET (Metrics and QE)

View all activity

Organizations

None yet

iky1e's activity

upvoted a collection about 3 hours ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated Nov 28, 2024 • 474

upvoted a collection about 7 hours ago

Marian COMET (Metrics and QE)

COMET models converted into Marian by Microsoft Translate Team! • 10 items • Updated May 28, 2024 • 1

upvoted a paper about 7 hours ago

xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection

Paper • 2310.10482 • Published Oct 16, 2023 • 2

upvoted a paper about 9 hours ago

Beyond English-Centric Multilingual Machine Translation

Paper • 2010.11125 • Published Oct 21, 2020 • 1

upvoted a collection about 13 hours ago

MT5 release

The MT5 release follows the T5 family, but is pretrained on multilingual data. The update UMT5 models are pretrained on an updated corpus. • 10 items • Updated Dec 13, 2024 • 18

upvoted 2 papers about 20 hours ago

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Paper • 2406.07476 • Published Jun 11, 2024 • 34

VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Paper • 2501.13106 • Published 2 days ago • 61

upvoted a collection about 20 hours ago

VideoLLaMA3

Frontier Multimodal Foundation Models for Video Understanding • 13 items • Updated about 10 hours ago • 7

upvoted a collection about 22 hours ago

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 1 day ago • 18

upvoted a collection 1 day ago

Video Understanding & Segmentation

4 items • Updated about 13 hours ago • 1

upvoted an article 1 day ago

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

2 days ago

• 63

upvoted 4 collections 1 day ago

SmolVLM 256M & 500M

Collection for models & demos for even smoller SmolVLM release • 12 items • Updated 1 day ago • 42

X-ALMA

12 items • Updated Oct 5, 2024 • 4

ALMA

6 items • Updated Jun 11, 2024 • 1

Tower

Model weights and SFT data for Tower. • 11 items • Updated Nov 15, 2024 • 28

upvoted a paper 2 days ago

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Paper • 2501.12375 • Published 3 days ago • 18

upvoted 3 papers 3 days ago

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Paper • 2501.09781 • Published 8 days ago • 20

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published 8 days ago • 95

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong

Paper • 2501.09775 • Published 9 days ago • 26

upvoted a collection 3 days ago

Shuttle 3 Diffusion

3 items • Updated 3 days ago • 2