🌁#85: Curiosity, Open Source, and Timing: The Formula Behind DeepSeek’s Phenomenal Success
•
3
Ksenia Se
Kseniase
AI & ML interests
None yet
Recent Activity
upvoted
an
article
about 5 hours ago
🌁#85: Curiosity, Open Source, and Timing: The Formula Behind DeepSeek’s Phenomenal Success
upvoted
a
paper
about 7 hours ago
Evolution and The Knightian Blindspot of Machine Learning
reacted
to
their
post
with 👍
about 8 hours ago
7 Open-source Methods to Improve Video Generation and Understanding
AI community is making great strides toward achieving the full potential of multimodality in video generation and understanding. Last week studies showed that working with videos is now one of the main focuses for improving AI models. Another highlight of the week is that open source, once again, proves its value. For those who were impressed by DeepSeek-R1, we’re with you!
Today, we’re combining these two key focuses and bringing you a list of open-source methods for better video generation and understanding:
1. VideoLLaMA 3 model: Excels in various video and image tasks thanks to vision-centric training approach. https://huggingface.co/papers/2501.13106
2. FILMAGENT framework assigns roles to multiple AI agents, like a director, screenwriter, actor, and cinematographer, to automate the filmmaking process in 3D virtual environments. https://huggingface.co/papers/2501.12909
3. https://huggingface.co/papers/2501.13918 proposes a new VideoReward Model and approach that uses human feedback to refine video generation models.
4. DiffuEraser video inpainting model, based on stable diffusion, is designed to fill in missing areas with detailed, realistic content and to ensure consistent structures across frames. https://huggingface.co/papers/2501.10018
5. MAGI is a hybrid video gen model that combines masked and casual modeling. Its key innovation, Complete Teacher Forcing (CTF), conditions masked frames on fully visible frames. https://huggingface.co/papers/2501.12389
6. https://huggingface.co/papers/2501.08331 proposes motion control, allowing users to guide how objects or the camera move in generated videos. Its noise warping algorithm replaces random noise in videos with structured noise based on motion info.
7. Video Depth Anything model estimates depth consistently in super-long videos (several minutes or more) without sacrificing quality or speed. https://huggingface.co/papers/2501.12375
Articles
Organizations
Kseniase's activity
upvoted
an
article
about 5 hours ago
Article
🌁#85: Curiosity, Open Source, and Timing: The Formula Behind DeepSeek’s Phenomenal Success
By
•
•
3
upvoted
a
paper
about 7 hours ago
upvoted
a
paper
about 13 hours ago
upvoted
a
paper
about 14 hours ago
upvoted
an
article
1 day ago
Article
🦸🏻#5: Building Blocks of Agentic Systems
By
•
•
3
upvoted
a
paper
1 day ago
upvoted
a
paper
2 days ago
upvoted
an
article
4 days ago
Article
**Topic 24: What is Cosmos World Foundation Model Platform?**
By
•
•
6
upvoted
an
article
6 days ago
Article
🌁#84: Could Program Synthesis Unlock AGI?
By
•
•
4
upvoted
a
paper
7 days ago
upvoted
an
article
9 days ago
Article
Topic 23: What is LLM Inference, it's challenges and solutions for it
By
•
•
5
upvoted
2
articles
14 days ago
Article
🌁#83: GAN is back
By
•
•
7Article
🅰️ℹ️ 1️⃣0️⃣1️⃣ **What is HtmlRAG, Multimodal RAG and Agentic RAG?**
By
•
•
7
upvoted
2
papers
14 days ago
upvoted
an
article
17 days ago
Article
🦸🏻#2: Your Go-To Vocabulary to Navigate the World of AI Agents and Agentic Workflows
By
•
•
10
upvoted
an
article
20 days ago
Article
🌁#82: AI and ML in Real Life
By
•
•
15
upvoted
a
paper
about 2 months ago
upvoted
a
collection
10 months ago