10 1 20

Makar Vlasov

Makar7

AI & ML interests

None yet

Recent Activity

reacted to merve's post with 👍 1 day ago

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥 D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩 > Collection with all checkpoints and demo https://huggingface.co/collections/ustc-community/d-fine-68109b427cbe6ee36b4e7352 Notebooks: > Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb > Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb > Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩 Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️ D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩 Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️ this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

reacted to samihalawa's post with 🔥 2 days ago

HELLO GUYS 🚀 Just released my first MCP: VUDA – Visual UI Debug Agent Ever been stuck debugging buttons that don’t work? Broken flows? Inconsistent UI behavior? VUDA sees it, clicks it, fixes it. An automated visual debug agent that inspects, validates, and repairs your UI — like magic 🧠✨ Better that any other playwright / puppeteer. 🔧 Install now via Smithery: npx -y @smithery/cli@latest install @samihalawa/visual-ui-debug-agent-mcp --client cursor ⸻ Want a shorter alt for social media too?

liked a Space 8 days ago

Qwen/Qwen3-Demo

View all activity

Organizations

None yet

Makar7's activity

reacted to merve's post with 👍 1 day ago

Post

5518

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

reacted to samihalawa's post with 🔥 2 days ago

Post

3354

HELLO GUYS 🚀 Just released my first MCP: VUDA – Visual UI Debug Agent
Ever been stuck debugging buttons that don’t work? Broken flows? Inconsistent UI behavior?

VUDA sees it, clicks it, fixes it.
An automated visual debug agent that inspects, validates, and repairs your UI — like magic 🧠✨ Better that any other playwright / puppeteer.

🔧 Install now via Smithery:

npx -y @smithery /cli@latest install @samihalawa /visual-ui-debug-agent-mcp --client cursor

⸻

Want a shorter alt for social media too?

liked a Space 8 days ago

473

Qwen3 Demo

📊

Generate responses to your messages

liked a model 8 days ago

Qwen/Qwen3-30B-A3B

Text Generation • Updated 8 days ago • 108k • • 481

liked a model 9 days ago

Qwen/Qwen3-235B-A22B

Text Generation • Updated 7 days ago • 53.6k • • 738

reacted to merterbak's post with 🚀🔥 9 days ago

Post

4789

Qwen 3 models released🔥
It offers 2 MoE and 6 dense models with following parameter sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B(MoE), 32B, and 235B(MoE).
Models: Qwen/qwen3-67dd247413f0e2e4f653967f
Blog: https://qwenlm.github.io/blog/qwen3/
Demo: Qwen/Qwen3-Demo
GitHub: https://github.com/QwenLM/Qwen3

✅ Pre-trained 119 languages(36 trillion tokens) and dialects with strong translation and instruction following abilities. (Qwen2.5 was pre-trained on 18 trillion tokens.)
✅Qwen3 dense models match the performance of larger Qwen2.5 models. For example, Qwen3-1.7B/4B/8B/14B/32B perform like Qwen2.5-3B/7B/14B/32B/72B.
✅ Three stage done while pretraining:
• Stage 1: General language learning and knowledge building.
• Stage 2: Reasoning boost with STEM, coding, and logic skills.
• Stage 3: Long context training
✅ It supports MCP in the model
✅ Strong agent skills
✅ Supports seamless between thinking mode (for hard tasks like math and coding) and non-thinking mode (for fast chatting) inside chat template.
✅ Better human alignment for creative writing, roleplay, multi-turn conversations, and following detailed instructions.

reacted to etemiz's post with 👍 16 days ago

Post

2269

Llama 4 Maverick got worse scores than Llama 3.1 405B in human alignment.

I used CPU for inferencing from this size of a model (402B), and it ran fast. Being a mixture of experts it may be useful for CPU inference and having a big context useful for RAG. For beneficial answers there are other alternatives.

Still it managed to beat Grok 3. I had so much expectations for Grok 3 because X is holding more beneficial ideas in my opinion.

It got worse health scores compared to 3.1 and better bitcoin scores. I could post some comparisons of answers between the two. With which model should I publish comparisons? Llama 3.1 or Grok 3 or something else?

https://sheet.zohopublic.com/sheet/published/mz41j09cc640a29ba47729fed784a263c1d08

reacted to Kseniase's post with 👍 17 days ago

Post

7016

11 new types of RAG

RAG is evolving fast, keeping pace with cutting-edge AI trends. Today it becomes more agentic and smarter at navigating complex structures like hypergraphs.

Here are 11 latest RAG types:

1. InstructRAG -> InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning (2504.13032)
Combines RAG with a multi-agent framework, using a graph-based structure, an RL agent to expand task coverage, and a meta-learning agent for better generalization

2. CoRAG (Collaborative RAG) -> CoRAG: Collaborative Retrieval-Augmented Generation (2504.01883)
A collaborative framework that extends RAG to settings where clients train a shared model using a joint passage store

3. ReaRAG -> ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation (2503.21729)
It uses a Thought-Action-Observation loop to decide at each step whether to retrieve information or finalize an answer, reducing unnecessary reasoning and errors

4. MCTS-RAG -> MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search (2503.20757)
Combines RAG with Monte Carlo Tree Search (MCTS) to help small LMs handle complex, knowledge-heavy tasks

5. Typed-RAG - > Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering (2503.15879)
Improves answers on open-ended questions by identifying question types (a debate, personal experience, or comparison) and breaking it down into simpler parts

6. MADAM-RAG -> Retrieval-Augmented Generation with Conflicting Evidence (2504.13079)
A multi-agent system where models debate answers over multiple rounds and an aggregator filters noise and misinformation

7. HM-RAG -> HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation (2504.12330)
A hierarchical multi-agent RAG framework that uses 3 agents: one to split queries, one to retrieve across multiple data types (text, graphs and web), and one to merge and refine answers

8. CDF-RAG -> CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (2504.12560)
Works with causal graphs and enables multi-hop causal reasoning, refining queries. It validates responses against causal pathways

To explore what is Causal AI, read our article: https://www.turingpost.com/p/causalai

Subscribe to the Turing Post: https://www.turingpost.com/subscribe

Read further 👇

1 reply

reacted to aiqtech's post with 🔥 17 days ago

Post

4367

🌐 AI Token Visualization Tool with Perfect Multilingual Support

Hello! Today I'm introducing my Token Visualization Tool with comprehensive multilingual support. This web-based application allows you to see how various Large Language Models (LLMs) tokenize text.

aiqtech/LLM-Token-Visual

✨ Key Features

🤖 Multiple LLM Tokenizers: Support for Llama 4, Mistral, Gemma, Deepseek, QWQ, BERT, and more
🔄 Custom Model Support: Use any tokenizer available on HuggingFace
📊 Detailed Token Statistics: Analyze total tokens, unique tokens, compression ratio, and more
🌈 Visual Token Representation: Each token assigned a unique color for visual distinction
📂 File Analysis Support: Upload and analyze large files

🌏 Powerful Multilingual Support
The most significant advantage of this tool is its perfect support for all languages:

📝 Asian languages including Korean, Chinese, and Japanese fully supported
🔤 RTL (right-to-left) languages like Arabic and Hebrew supported
🈺 Special characters and emoji tokenization visualization
🧩 Compare tokenization differences between languages
💬 Mixed multilingual text processing analysis

🚀 How It Works

Select your desired tokenizer model (predefined or HuggingFace model ID)
Input multilingual text or upload a file for analysis
Click 'Analyze Text' to see the tokenized results
Visually understand how the model breaks down various languages with color-coded tokens

💡 Benefits of Multilingual Processing
Understanding multilingual text tokenization patterns helps you:

Optimize prompts that mix multiple languages
Compare token efficiency across languages (e.g., English vs. Korean vs. Chinese token usage)
Predict token usage for internationalization (i18n) applications
Optimize costs for multilingual AI services

🛠️ Technology Stack

Backend: Flask (Python)
Frontend: HTML, CSS, JavaScript (jQuery)
Tokenizers: 🤗 Transformers library

27 replies

replied to openfree's post 19 days ago

Using a translator:
Thank you for answering. I just don't like using translators because they can distort the meaning of my texts.
I fully support you with your project. I hope there will be some improvements in the future. Sorry if my first comment looked like an advertisement.
I also met a person on the Pikabu website who, as I understand it, is creating an application for a phone with the same idea of making any neural network reasoning (I haven't met him since). I gave Vinci KPU as an example because it was (before your project was released) the only implementation I found on the Internet that left the concept stage or some internal tests.

replied to openfree's post 19 days ago

Мне непонятно, почему мой прошлый комментарий был скрыт из-за того, что он, типа, не по теме.

Я просто в комментарии сказал, что то, как работает ThinkFlow, использует тот же замысел, что и Vinci KPU от Maisa AI.
Вы же не будете отрицать то, что они появились намного раньше с этой идеей? В пустоте не появляется конкуренция. Я просто показал, с чем можно сравнить ThinkFlow.

Идея-то одна и та же: сделать из любой нерассуждающей LLM-модели рассуждающую, используя запрограммированный отдельный механизм для создания рассуждений.

replied to openfree's post 19 days ago

This comment has been hidden

reacted to prithivMLmods's post with 👍 22 days ago

Post

2549

Try out the demo for Multimodal OCR featuring the implementation of models including RolmOCR and Qwen2VL OCR. The use case showcases image-text-to-text conversion and video understanding support for the RolmOCR model ! 🚀

🤗Multimodal OCR Space : prithivMLmods/Multimodal-OCR

📦The models implemented in this Space are:
+ Qwen2VL OCR : prithivMLmods/Qwen2-VL-OCR-2B-Instruct [ or ]
+ Qwen2VL OCR2 : prithivMLmods/Qwen2-VL-OCR2-2B-Instruct
+ RolmOCR : reducto/RolmOCR

Qwen2VL OCR supports only image-text-to-text in the space.

reacted to AdinaY's post with ❤️ 24 days ago

Post

3288

🔥 New reasoning models from the Chinese community, by Skywork 天工-昆仑万维

Skywork/skywork-or1-67fa1bcb41b436ef2def76b9

✨Skywork OR1-Math-7B > Optimized for math reasoning
✨Skywork-OR1-7B-preview > Excels in math & coding
✨Skywork-OR1-32B-preview > Matches Deepseek-R1 on math (AIME24/25) and coding (LiveCodeBench)

Released under the Apache 2.0 license 🥳
Final version coming in 2 weeks!

reacted to AdinaY's post with 🔥 26 days ago

Post

3273

Shanghai AI Lab - OpenGV team just released InternVL3 🔥

OpenGVLab/internvl3-67f7f690be79c2fe9d74fe9d

✨ 1/2/8/9/14/38/28B with MIT license
✨ Stronger perception & reasoning vs InternVL 2.5
✨ Native Multimodal Pre-Training for even better language performance

1 reply

New activity in yandex/YandexGPT-5-Lite-8B-instruct 27 days ago

Она всё же Алиса.

#4 opened about 1 month ago by

Makar7

reacted to merterbak's post with ❤️🔥 27 days ago

Post

4743

Qwen 3 can launch very soon. 👀

https://github.com/ggml-org/llama.cpp/pull/12828

3 replies

reacted to fdaudens's post with 🤯 28 days ago

Post

4109

🎨 Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow.

@OmniSVG

2 replies