1 16 81

Mert Erbak PRO

merterbak

AI & ML interests

Currently NLP and Image Processing

Recent Activity

reacted to singhsidhukuldeep's post with 🚀 5 days ago

Exciting breakthrough in AI: AirRAG - A Novel Approach to Retrieval Augmented Generation! Researchers from Alibaba Cloud have developed a groundbreaking framework that significantly improves how AI systems reason and retrieve information. AirRAG introduces five fundamental reasoning actions that work together to create more accurate and comprehensive responses. >> Key Technical Innovations: - Implements Monte Carlo Tree Search (MCTS) for exploring diverse reasoning paths - Utilizes five core actions: System Analysis, Direct Answer, Retrieval-Answer, Query Transformation, and Summary-Answer - Features self-consistency verification and process-supervised reward modeling - Achieves superior performance across complex QA datasets like HotpotQA, MuSiQue, and 2WikiMultiHopQA >> Under the Hood: The system expands solution spaces through tree-based search, allowing for multiple reasoning paths to be explored simultaneously. The framework implements computationally optimal strategies, applying more resources to key actions while maintaining efficiency. >> Results Speak Volumes: - Outperforms existing RAG methods by over 10% on average - Shows remarkable scalability with increasing inference computation - Demonstrates exceptional flexibility in integrating with other advanced technologies This research represents a significant step forward in making AI systems more capable of complex reasoning tasks. The team's innovative approach combines human-like reasoning with advanced computational techniques, setting new benchmarks in the field.

liked a Space 5 days ago

deepseek-ai/Janus-Pro-7B

liked a model 5 days ago

deepseek-ai/Janus-Pro-1B

View all activity

Organizations

merterbak's activity

upvoted a collection about 1 month ago

Google's Gemma models family

Collection

243 items • Updated Dec 13, 2024 • 83

upvoted an article 2 months ago

Article

Use Models from the Hugging Face Hub in LM Studio

•

Nov 28, 2024

• 136

upvoted a paper 3 months ago

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Paper • 2411.06176 • Published Nov 9, 2024 • 45

upvoted 4 papers 6 months ago

upvoted an article 6 months ago

Article

Inference for PROs

Sep 22, 2023

• 52

upvoted 4 papers 7 months ago

HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale

Paper • 2406.19280 • Published Jun 27, 2024 • 62

X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance

Paper • 2303.15764 • Published Mar 28, 2023 • 2

DETRs Beat YOLOs on Real-time Object Detection

Paper • 2304.08069 • Published Apr 17, 2023 • 13

Attention Is All You Need

Paper • 1706.03762 • Published Jun 12, 2017 • 49

upvoted 3 papers 9 months ago

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

Paper • 2405.10314 • Published May 16, 2024 • 46

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15, 2024 • 88

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published May 16, 2024 • 130

upvoted a paper 11 months ago

Gemma: Open Models Based on Gemini Research and Technology

Paper • 2403.08295 • Published Mar 13, 2024 • 48