TunyTrinh's profile picture. AI Engineer

Tuan Trinh Anh

@TunyTrinh

AI Engineer

Tuan Trinh Anh reposted

Most multi-drone systems struggle with one thing: coordination under real-world constraints. A new paper in Science Robotics from TU Delft proposes a model-based approach that lets multiple quadrotors jointly move and orient a cable-suspended load. BUT: without relying on…


Tuan Trinh Anh reposted

Even with full-batch gradients, DL optimizers defy classical optimization theory, as they operate at the *edge of stability.* With @alex_damian_, we introduce "central flows": a theoretical tool to analyze these dynamics that makes accurate quantitative predictions on real NNs.


Tuan Trinh Anh reposted

Stop chunking first. Start embedding first. 𝗟𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴 improves retrieval quality of your RAG system: First, let’s do a quick chunking refresher: 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the basics we all started with) • Token Chunking - split by token count •…


Tuan Trinh Anh reposted

China has just unveiled a mosquito-sized spy drone, an ultra-quiet, radar-evading UAV engineered for indoor surveillance. Designed to mimic an insect, it can be controlled directly from a smartphone.

From Mr. Nobody

Tuan Trinh Anh reposted

Turn PDF files into clean, LLM-ready data! Dolphin is an open source document parsing framework that converts PDFs into structured formats like Markdown, HTML, LaTeX, and JSON. 100% Open Source

Sumanth_077's tweet image. Turn PDF files into clean, LLM-ready data!

Dolphin is an open source document parsing framework that converts PDFs into structured formats like Markdown, HTML, LaTeX, and JSON.

100% Open Source

Tuan Trinh Anh reposted

CVPR 2025 papers pt. 3 - EdgeTAM EdgeTAM lets you run high-quality video object segmentation and tracking at up to 16 FPS right on an iPhone 15 Pro Max more papers: github.com/SkalskiP/top-c… ↓ more


Tuan Trinh Anh reposted

Hierarchical Reasoning Model This is one of the most interesting ideas on reasoning I've read in the past couple of months. It uses a recurrent architecture for impressive hierarchical reasoning. Here are my notes:

omarsar0's tweet image. Hierarchical Reasoning Model

This is one of the most interesting ideas on reasoning I've read in the past couple of months.

It uses a recurrent architecture for impressive hierarchical reasoning. 

Here are my notes:

Tuan Trinh Anh reposted

GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats github.com/DengKaiCQ/Giga…

rsasaki0109's tweet image. GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
github.com/DengKaiCQ/Giga…
rsasaki0109's tweet image. GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
github.com/DengKaiCQ/Giga…
rsasaki0109's tweet image. GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
github.com/DengKaiCQ/Giga…

Tuan Trinh Anh reposted

Today @Shopify is open sourcing the tool we use for optimizing glTF 3D models. 🔧 Tweak compression settings per texture ⚡ See changes immediately 🧰 Mesh compression options 🌐 Hosted online & free 👇 Check the thread for details


Tuan Trinh Anh reposted

Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research🧵

shawshank_v's tweet image. Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research🧵

Tuan Trinh Anh reposted

Advanced anti-UAV techniques are needed due to the rising threat of drone intrusion or air defence system saturation. Object tracking in thermal infrared (TIR) videos could solve this problem for all-weather surveillance. Today, I am demonstrating my Anti-UAV Tracking result.


Tuan Trinh Anh reposted

9 techniques you should know to master AI: - RAG (like Multimodal and Agentic RAG) - Knowledge distillation - Prompt optimization - GRPO - Mixture-of-Experts (MoE) - Chains-of-... : Chain-of-Agents and Chain-of-RAG - Methods reducing memory use, e.g. LightThinker, MLA - Advanced…

TheTuringPost's tweet image. 9 techniques you should know to master AI:

- RAG (like Multimodal and Agentic RAG)
- Knowledge distillation
- Prompt optimization
- GRPO
- Mixture-of-Experts (MoE)
- Chains-of-... : Chain-of-Agents and Chain-of-RAG
- Methods reducing memory use, e.g. LightThinker, MLA
- Advanced…
TheTuringPost's tweet image. 9 techniques you should know to master AI:

- RAG (like Multimodal and Agentic RAG)
- Knowledge distillation
- Prompt optimization
- GRPO
- Mixture-of-Experts (MoE)
- Chains-of-... : Chain-of-Agents and Chain-of-RAG
- Methods reducing memory use, e.g. LightThinker, MLA
- Advanced…
TheTuringPost's tweet image. 9 techniques you should know to master AI:

- RAG (like Multimodal and Agentic RAG)
- Knowledge distillation
- Prompt optimization
- GRPO
- Mixture-of-Experts (MoE)
- Chains-of-... : Chain-of-Agents and Chain-of-RAG
- Methods reducing memory use, e.g. LightThinker, MLA
- Advanced…

Tuan Trinh Anh reposted

Video generation is powerful but too slow for real-world robotic tasks. How can we enable both video and action generation while ensuring real-time policy inference? Check out our work on the Unified Video Action Model (UVA) to find out! unified-video-action-model.github.io (1/7)


Tuan Trinh Anh reposted

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering Contributions: • We reformulate video stabilization as a novel 3D grounded scheme of local reconstruction and rendering. This approach is naturally robust to diverse camera…


Tuan Trinh Anh reposted

Efficient Cross-Modality Insulator Augmentation for Multi-Domain Insulator Defect Detection in UAV Images mdpi.com/1424-8220/24/2… #transmissionlineinspection

Sensors_MDPI's tweet image. Efficient   Cross-Modality Insulator Augmentation for Multi-Domain Insulator Defect   Detection in UAV Images 
mdpi.com/1424-8220/24/2…
#transmissionlineinspection

Tuan Trinh Anh reposted

DUSt3R-like models work for scientific imaging too! Our ICCV’25 paper “CryoFastAR” shows that a geometric foundation model can do feed-forward ab initio cryo-EM reconstruction—10× faster and state-of-the-art quality on noisy particle images! #ICCV2025 #CryoEM 📎Paper:…

zhiwen_fan_'s tweet image. DUSt3R-like models work for scientific imaging too! Our ICCV’25 paper “CryoFastAR” shows that a geometric foundation model can do feed-forward ab initio cryo-EM reconstruction—10× faster and state-of-the-art quality on noisy particle images! #ICCV2025 #CryoEM

📎Paper:…

Tuan Trinh Anh reposted

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.


Tuan Trinh Anh reposted

Engineers from the California Institute of Technology developed "Neural-Fly," an algorithm that helps drones navigate real-world weather conditions and adapt to it in real time, according to Reuters cnn.it/3m5WBQE


United States Trends

Loading...

Something went wrong.


Something went wrong.