Vikram Jha

invincible-jha

https://www.linkedin.com/in/invinciblejha/

AI & ML interests

Have developed vocal biomarkers for rapid Covid-19 screening using smartphones & basic phones using AI & have developed novel drug candidates for Covid-19 & other diseases using AI. 13+ Years Exp. in AI. Currently into R&D of advanced Agentic AI frameworks and systems

Recent Activity

upvoted a paper about 6 hours ago

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

upvoted a paper about 6 hours ago

Kimi k1.5: Scaling Reinforcement Learning with LLMs

reacted to Kseniase's post with 🚀 about 6 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

View all activity

Organizations

invincible-jha's activity

upvoted 2 papers about 6 hours ago

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

Paper • 2501.13106 • Published 5 days ago • 70

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published 6 days ago • 65

reacted to Kseniase's post with 🚀 about 6 hours ago

Post

1888

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. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (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. FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces (2501.12909)

3. Improving Video Generation with Human Feedback (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. DiffuEraser: A Diffusion Model for Video Inpainting (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. Taming Teacher Forcing for Masked Autoregressive Video Generation (2501.12389)

6. Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise (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. Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (2501.12375)