BuiDoan's picture

26 6

BuiDoan

BuiDoan

·

AI & ML interests

None yet

Recent Activity

reacted to Kseniase's post with 🔥 4 days 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

reacted to tianchez's post with 👍 4 days ago

Introducing VLM-R1! GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks? The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task). https://github.com/om-ai-lab/VLM-R1

updated a collection 6 days ago

View all activity

Organizations

Collections 4

models

None public yet

datasets

None public yet