Article
🌁#87: Why DeepResearch Should Be Your New Hire
By
•
•
2Ksenia Se
Kseniase
AI & ML interests
None yet
Recent Activity
upvoted
an
article
about 20 hours ago
🌁#87: Why DeepResearch Should Be Your New Hire
published
an
article
about 22 hours ago
🌁#87: Why DeepResearch Should Be Your New Hire
replied to
their
post
1 day ago
8 New Types of RAG
RAG techniques continuously evolve to enhance LLM response accuracy by retrieving relevant external data during generation. To keep up with current AI trends, new RAG types incorporate deep step-by-step reasoning, tree search, citations, multimodality and other effective techniques.
Here's a list of 8 latest RAG advancements:
1. DeepRAG -> https://huggingface.co/papers/2502.01142
Models retrieval-augmented reasoning as a Markov Decision Process, enabling strategic retrieval. It dynamically decides when to retrieve external knowledge and when rely on parametric reasoning.
2. RealRAG -> https://huggingface.co/papers/2502.00848
Enhances novel object generation by retrieving real-world images and using self-reflective contrastive learning to fill knowledge gap, improve realism and reduce distortions.
3. Chain-of-Retrieval Augmented Generation (CoRAG) -> https://huggingface.co/papers/2501.14342
Retrieves information step-by-step and adjusts it, also deciding how much compute power to use at test time. If needed it reformulates queries.
4. VideoRAG -> https://huggingface.co/papers/2501.05874
Enables unlimited-length video processing, using dual-channel architecture that integrates graph-based textual grounding and multi-modal context encoding.
5. CFT-RAG -> https://huggingface.co/papers/2501.15098
A tree-RAG acceleration method uses an improved Cuckoo Filter to optimize entity localization, enabling faster retrieval.
6. Contextualized Graph RAG (CG-RAG) -> https://huggingface.co/papers/2501.15067
Uses Lexical-Semantic Graph Retrieval (LeSeGR) to integrate sparse and dense signals within graph structure and capture citation relationships
7. GFM-RAG -> https://huggingface.co/papers/2502.01113
A graph foundation model that uses a graph neural network to refine query-knowledge connections
8. URAG -> https://huggingface.co/papers/2501.16276
A hybrid system combining rule-based and RAG methods to improve lightweight LLMs for educational chatbots
Organizations
Kseniase's activity
published
an
article
about 22 hours ago
published
an
article
5 days ago
Article
What is test-time compute and how to scale it?
By
and 1 other
•
•
16
published
an
article
8 days ago
Article
🌁#86: Four Freedoms of truly open AI
By
and 1 other
•
•
5
published
an
article
15 days ago
Article
🦸🏻#6: The Role of Profiling in Agentic Workflows
By
•
•
3
published
an
article
19 days ago
Article
**Topic 24: What is Cosmos World Foundation Model Platform?**
By
and 1 other
•
•
6
published
an
article
22 days ago
Article
🌁#84: Could Program Synthesis Unlock AGI?
By
•
•
4
published
an
article
25 days ago
Article
Topic 23: What is LLM Inference, it's challenges and solutions for it
By
•
•
5
published
an
article
about 1 month ago
Article
🌁#82: AI and ML in Real Life
By
•
•
16
published
an
article
about 1 month ago
Article
AI in 2025: A Combinatorial Explosion of Possibilities, but NOT AGI
By
•
•
3
published
an
article
about 2 months ago
Article
🦸🏻#2: Your Go-To Vocabulary to Navigate the World of AI Agents and Agentic Workflows
By
•
•
10
published
an
article
about 2 months ago
Article
🦸🏻#1: Open-endedness and AI Agents – A Path from Generative to Creative AI?
By
•
•
7