🦸🏻#9: Does AI Remember? The Role of Memory in Agentic Workflows
•
2
Ksenia Se
Kseniase
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
12 minutes ago
TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and
Compression in LLMs
upvoted
a
paper
14 minutes ago
Diverse Preference Optimization
upvoted
a
paper
36 minutes ago
WARP: An Efficient Engine for Multi-Vector Retrieval
Articles
Organizations
Posts
8
Post
713
8 Free Sources on Reinforcement Learning
With the phenomenon of DeepSeek-R1's top reasoning capabilities, we all saw the true power of RL. At its core, RL is a type of machine learning where a model/agent learns to make decisions by interacting with an environment to maximize a reward. RL learns through trial and error, receiving feedback in the form of rewards or penalties.
Here's a list of free sources that will help you dive into RL and how to use it:
1. "Reinforcement Learning: An Introduction" book by Richard S. Sutton and Andrew G. Barto -> https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf
2. Hugging Face Deep Reinforcement Learning Course -> https://huggingface.co./learn/deep-rl-course/unit0/introduction
You'll learn how to train agents in unique environments, using best libraries, share your results, compete in challenges, and earn a certificate.
3. OpenAI Spinning Up in Deep RL -> https://spinningup.openai.com/en/latest/index.html
A comprehensive overview of RL with many useful resources
4. "Reinforcement Learning and Optimal Control" books, video lectures and course material by Dimitri P. Bertsekas from ASU -> https://web.mit.edu/dimitrib/www/RLbook.html
Explores approximate Dynamic Programming (DP) and RL with key concepts and methods like rollout, tree search, and neural network training for RL and more.
5. RL Course by David Silver (Google DeepMind) -> https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPeb
Many recommend these video lectures as a good foundation
6. RL theory seminars -> https://sites.google.com/view/rltheoryseminars/home?authuser=0
Provides virtual seminars from different experts about RL advancements
7. "Reinforcement Learning Specialization" (a 4-course series on Coursera) -> https://www.coursera.org/learn/fundament
8. Concepts: RLHF, RLAIF, RLEF, RLCF -> https://www.turingpost.com/p/rl-f
Our flashcards easily explain what are these four RL approaches with different feedback
With the phenomenon of DeepSeek-R1's top reasoning capabilities, we all saw the true power of RL. At its core, RL is a type of machine learning where a model/agent learns to make decisions by interacting with an environment to maximize a reward. RL learns through trial and error, receiving feedback in the form of rewards or penalties.
Here's a list of free sources that will help you dive into RL and how to use it:
1. "Reinforcement Learning: An Introduction" book by Richard S. Sutton and Andrew G. Barto -> https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf
2. Hugging Face Deep Reinforcement Learning Course -> https://huggingface.co./learn/deep-rl-course/unit0/introduction
You'll learn how to train agents in unique environments, using best libraries, share your results, compete in challenges, and earn a certificate.
3. OpenAI Spinning Up in Deep RL -> https://spinningup.openai.com/en/latest/index.html
A comprehensive overview of RL with many useful resources
4. "Reinforcement Learning and Optimal Control" books, video lectures and course material by Dimitri P. Bertsekas from ASU -> https://web.mit.edu/dimitrib/www/RLbook.html
Explores approximate Dynamic Programming (DP) and RL with key concepts and methods like rollout, tree search, and neural network training for RL and more.
5. RL Course by David Silver (Google DeepMind) -> https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPeb
Many recommend these video lectures as a good foundation
6. RL theory seminars -> https://sites.google.com/view/rltheoryseminars/home?authuser=0
Provides virtual seminars from different experts about RL advancements
7. "Reinforcement Learning Specialization" (a 4-course series on Coursera) -> https://www.coursera.org/learn/fundament
8. Concepts: RLHF, RLAIF, RLEF, RLCF -> https://www.turingpost.com/p/rl-f
Our flashcards easily explain what are these four RL approaches with different feedback
Post
2924
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)
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)
Collections
1
-
Exploring the Best Practices of Query Expansion with Large Language Models
Paper • 2401.06311 • Published • 1 -
Robust Prompt Optimization for Large Language Models Against Distribution Shifts
Paper • 2305.13954 • Published • 1 -
Optimizing Query Generation for Enhanced Document Retrieval in RAG
Paper • 2407.12325 • Published • 1 -
Multi-Aspect Reviewed-Item Retrieval via LLM Query Decomposition and Aspect Fusion
Paper • 2408.00878 • Published • 1
models
None public yet
datasets
None public yet