Hugging Face's logo
Alan Dao's picture
2 7 9

Alan Dao

alandao
Shamus's profile picture emreckartal's profile picture vinhnx90's profile picture
·
https://about.alandao.net

AI & ML interests

None yet

Recent Activity

upvoted a paper 13 days ago
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
replied to tianchez's post 14 days ago
Introducing VLM-R1! GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks? The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task). https://github.com/om-ai-lab/VLM-R1
authored a paper 17 days ago
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
View all activity

Organizations

Jan's profile picture Cortex's profile picture Homebrew Research's profile picture

alandao's activity

upvoted a paper 13 days ago
replied to tianchez's post 14 days ago
authored a paper 17 days ago
updated a model 2 months ago
upvoted a paper 2 months ago
updated 2 models 4 months ago
liked a model 4 months ago
upvoted a collection 4 months ago
commented a paper 5 months ago
upvoted a paper 5 months ago
authored a paper 5 months ago
upvoted a collection 5 months ago
updated a model 5 months ago
updated a collection 5 months ago
reacted to reach-vb's post with 😎 5 months ago
view post
Post
5536
Multimodal Ichigo Llama 3.1 - Real Time Voice AI 🔥

> WhisperSpeech X Llama 3.1 8B
> Trained on 50K hours of speech (7 languages)
> Continually trained on 45hrs 10x A1000s
> MLS -> WhisperVQ tokens -> Llama 3.1
> Instruction tuned on 1.89M samples
> 70% speech, 20% transcription, 10% text
> Apache 2.0 licensed ⚡

Architecture:
> WhisperSpeech/ VQ for Semantic Tokens
> Llama 3.1 8B Instruct for Text backbone
> Early fusion (Chameleon)

I'm super bullish on HomeBrew/ Jan and early fusion, audio and text, multimodal models!

(P.S. Play with the demo on Hugging Face: jan-hq/Ichigo-llama3.1-s-instruct)
liked a Space 7 months ago
liked a dataset 7 months ago