Sleeping
🌍
AnySearch
Search from anywhere using RAG
Mohamed Hisham Abdelzaher
MH0386
AI & ML interests
None yet
Recent Activity
updated
a Space
19 days ago
MH0386/AnySearch
upvoted
an
article
about 1 month ago
Use Models from the Hugging Face Hub in LM Studio
reacted
to
Symbol-LLM's
post
with 🚀
about 2 months ago
🚀 Excited to introduce a new member of the OS-Copilot family: OS-Atlas - an open-sourced foundational action model for GUI agents
📘 Paper: https://huggingface.co/papers/2410.23218
🔗 Website: https://osatlas.github.io
😇 TL;DR: OS-Atlas offers:
1. State-of-the-Art GUI Grounding: Helps GUI agents accurately locate GUI elements.
2. Strong OOD Performance and Cross-platform Compatibility: Excels in out-of-domain agentic tasks across MacOS, Windows, Linux, Android, and Web.
3. Complete Infrastructure for GUI Data Synthesis:
You can easily build your own OS agent upon it!
Organizations
MH0386's activity
updated
a
Space
19 days ago
upvoted
an
article
about 1 month ago
Article
Use Models from the Hugging Face Hub in LM Studio
By
•
•
127
reacted to
Symbol-LLM's
post with 🚀
about 2 months ago
Post
2163
🚀 Excited to introduce a new member of the OS-Copilot family: OS-Atlas - an open-sourced foundational action model for GUI agents
📘 Paper: OS-ATLAS: A Foundation Action Model for Generalist GUI Agents (2410.23218)
🔗 Website: https://osatlas.github.io
😇 TL;DR: OS-Atlas offers:
1. State-of-the-Art GUI Grounding: Helps GUI agents accurately locate GUI elements.
2. Strong OOD Performance and Cross-platform Compatibility: Excels in out-of-domain agentic tasks across MacOS, Windows, Linux, Android, and Web.
3. Complete Infrastructure for GUI Data Synthesis:
You can easily build your own OS agent upon it!
📘 Paper: OS-ATLAS: A Foundation Action Model for Generalist GUI Agents (2410.23218)
🔗 Website: https://osatlas.github.io
😇 TL;DR: OS-Atlas offers:
1. State-of-the-Art GUI Grounding: Helps GUI agents accurately locate GUI elements.
2. Strong OOD Performance and Cross-platform Compatibility: Excels in out-of-domain agentic tasks across MacOS, Windows, Linux, Android, and Web.
3. Complete Infrastructure for GUI Data Synthesis:
You can easily build your own OS agent upon it!
liked
a
Space
2 months ago
liked
a
model
3 months ago
updated
a
dataset
3 months ago
upvoted
an
article
3 months ago
Article
Introducing Community Tools on HuggingChat
•
34
updated
a
dataset
4 months ago
updated
a
Space
4 months ago
liked
a
model
5 months ago
liked
a
model
6 months ago
upvoted
a
collection
7 months ago
updated
a
collection
8 months ago
updated
a
model
8 months ago
liked
a
model
8 months ago
upvoted
a
collection
8 months ago
updated
a
model
9 months ago
liked
a
model
9 months ago
upvoted
an
article
9 months ago
Article
Welcome Llama 3 - Meta's new open LLM
•
281
reacted to
Jaward's
post with 👍
9 months ago
Post
3271
Let's breakdown the technical details in Microsoft's mind blowing Lifelike audio-driven talking faces framework - VASA and model VASA-1:
Summary of Summaries
- The paper introduces VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) from a single image and speech audio.
- Core innovations include a diffusion-based model for holistic generation of facial dynamics and head movements in an expressive, disentangled face latent space developed using video data..
- VASA-1 Generates high-quality 512x512 videos at up to 40 FPS with low latency.
- Supports real-time generation of lifelike, emotive talking faces.
Summary of Overall Framework:
- VASA generates facial dynamics and head motion in latent space, conditioned on audio and other signals
- Instead of directly generating video frames, it generates holistic facial dynamics and head motion in a latent space, conditioned on audio and optional signals.
- To achieve this, the framework uses a face encoder-decoder to extract appearance and identity features and train a Diffusion Transformer model to generate motion latent codes.
Technical Method Details:
Expressive and Disentangled Face Latent Space Construction:
- Based on 3D-AID face reenactment framework
- Decomposes face into 3D appearance volume, identity code, head pose,
and facial dynamics latents
- Uses encoders to extract these latent factors from face images.
- Applies additional losses to improve disentanglement:
- Pairwise head pose and facial dynamics transfer loss
- Face identity similarity loss for cross-identity pose/dynamics transfer
Holistic Facial Dynamics Generation with Diffusion Transformer:
- Represents all facial movements (lip, expression, gaze, etc.) as a single
latent sequence
- Applies a Diffusion Transformer model to generate the facial dynamics sequence.
- Diffusion Transformer trained with simplified denoising score matching objective.
Summary of Summaries
- The paper introduces VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) from a single image and speech audio.
- Core innovations include a diffusion-based model for holistic generation of facial dynamics and head movements in an expressive, disentangled face latent space developed using video data..
- VASA-1 Generates high-quality 512x512 videos at up to 40 FPS with low latency.
- Supports real-time generation of lifelike, emotive talking faces.
Summary of Overall Framework:
- VASA generates facial dynamics and head motion in latent space, conditioned on audio and other signals
- Instead of directly generating video frames, it generates holistic facial dynamics and head motion in a latent space, conditioned on audio and optional signals.
- To achieve this, the framework uses a face encoder-decoder to extract appearance and identity features and train a Diffusion Transformer model to generate motion latent codes.
Technical Method Details:
Expressive and Disentangled Face Latent Space Construction:
- Based on 3D-AID face reenactment framework
- Decomposes face into 3D appearance volume, identity code, head pose,
and facial dynamics latents
- Uses encoders to extract these latent factors from face images.
- Applies additional losses to improve disentanglement:
- Pairwise head pose and facial dynamics transfer loss
- Face identity similarity loss for cross-identity pose/dynamics transfer
Holistic Facial Dynamics Generation with Diffusion Transformer:
- Represents all facial movements (lip, expression, gaze, etc.) as a single
latent sequence
- Applies a Diffusion Transformer model to generate the facial dynamics sequence.
- Diffusion Transformer trained with simplified denoising score matching objective.
- 12 replies