1 23 140

Mert Erbak PRO

merterbak

AI & ML interests

NLP and Image Processing

Recent Activity

liked a Space about 6 hours ago

nvidia/describe-anything-model-demo

updated a model about 12 hours ago

merterbak/Mistral-Small-3.1-24B-Instruct-2503-GGUF

reacted to their post with 🔥 about 22 hours ago

FlowReasoner is a new system that builds a custom set of small AI agents for every user question. Unlike search based methods it uses reasoning driven optimization with external execution feedback. ✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖 ✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡 ✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning. https://huggingface.co/papers/2504.15257 Code: https://github.com/sail-sg/flowreasoner

View all activity

Organizations

merterbak's activity

upvoted a paper 1 day ago

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 7 days ago • 45

upvoted a paper 5 days ago

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Paper • 2504.16078 • Published 6 days ago • 19

upvoted an article 14 days ago

Article

Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖

14 days ago

• 40

upvoted an article 23 days ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

23 days ago

• 141

upvoted a collection 23 days ago

Llama 4

Collection

Llama 4 release • 10 items • Updated 23 days ago • 456

upvoted a paper about 1 month ago

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Paper • 2503.15265 • Published Mar 19 • 47

upvoted a paper about 2 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 391

upvoted a collection 4 months ago

Google's Gemma models family

Collection

279 items • Updated 10 days ago • 175

upvoted a paper 6 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 • 46

upvoted 4 papers 8 months ago

upvoted an article 9 months ago

Article

Inference for PROs

Sep 22, 2023

• 54

upvoted 4 papers 10 months ago

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

Paper • 2406.19280 • Published Jun 27, 2024 • 65

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 • 60

upvoted a paper 11 months ago

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

Paper • 2405.10314 • Published May 16, 2024 • 49