Bạn có thể thích
🚀 PaddleOCR-VL is here! Introducing PaddleOCR-VL (0.9B) — the ultra-compact Vision-Language model that reaches SOTA accuracy across text, tables, formulas, charts & handwriting. Breaking the limits of document parsing!🌍 Powered by: • NaViT dynamic vision encoder • ERNIE…
PaddleOCR-VL-0.9B is mind blowing and it supports 109 languages! Check it out on HF demo:
Making fun with the new APPS from @runwayml, i'm testing "add dialogue" with onomatopoeia, and it's working very well !! So fun !
Special Thanks to @GauzillaPro and Yoshiharu (Josh) S. as well to make this into reality! 🙌🤩
Reality — Captured. Progress — Tracked. With @XGRIDS2023 #handheldscanners + #3DGS, #AEC teams can document, compare & verify progress with photorealistic precision. Find out more: heliguy.com/blogs/posts/xg… #aec #survey
ByteDance just released Sa2VA on Hugging Face The first unified model for dense grounded understanding of images and videos. Combines SAM2 with LLaVA for SOTA segmentation and visual QA.
We are excited to release the technical report for RAG-Anything 🚀: All-in-One RAG Framework. ⭐ RAG-Anything has now reached over 8.3k stars on Github! Thanks to the valuable feedback and comments from the open-source community! ------------------------------------------ I.…
Finally, a production-ready backend for Agents that actually works! xpander is a plug-and-play backend for Agents that manages memory, tools, states, version control, guardrails, and more. Works with any framework, like CrewAI, Agno, Langchain, etc. Fully self-hostable!
Super excited to introduce ✨ AnyUp: Universal Feature Upsampling 🔎 Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining. SOTA feature upsampling results while being feature-agnostic at inference time.
Facebook just dropped HoneyBee, a massive new dataset for vision-language reasoning, on Hugging Face! It contains 2.5M high-quality examples with chain-of-thought solutions, pushing VLM performance to new SOTA.
Open-sourcing retrieve-dspy! 💻🚀 While developing Search Mode for Weaviate's Query Agent, we dove into the literature. It was amazing, and overwhelming, to see how many different takes on Compound Retrieval Systems there are! 📚 From perspectives on Reranking, such as to…
You need SeCs? New Segmentation model that purportedly outperforms SAM 2 has arrived, and with Comfy nodes to boot! I won't be testing this, but this seems like a very useful model to have around. github.com/9nate-drake/Co…
Example of us using AI to track cartel activity from grainy videos posted on Telegram
MuseSteamer just leveled up! Our video generation model now supports real-time interactive long-form video generation. It breaks the traditional 10-second limit, creating videos of any length with greater speed and control—enabling users to pause, rewrite storylines, or extend…
I'm currently making a tutorial for training qwen-image-edit-2509 LoRA on <24GB of VRAM. The fact that it can put this QR code on her shirt accurately enough to scan in 1,000 steps is mind boggling. I love this model.
terminal-based SSH connection manager with search and edit features
Meta just did the unthinkable. They figured out how to train AI agents without rewards, human demos, or supervision and it actually works better than both. It’s called 'Early Experience', and it quietly kills the two biggest pain points in agent training: → Human…
spec-driven workflow for AI coding assistants, no API keys needed
For those that think this is hype: no it's not. I invented a little training/eval set last night. Model score is about 50% with my own optimized prompt. GEPA takes that to 70% with auto="light" optimization. I imagine this can go to 90% with heavy optimization. Insane…
One of the awesome features of the SuperSplat Editor is that it can render high quality videos of your 3D Gaussian Splats. #PlayCanvas #OpenSource
Spatial representations are central to world models🌍 SuperDec is an extremely compact 3D scene representation (replacing millions of Gaussians with just a few hundred primitives) ideal for abstract reasoning and planning in 3D ➡️super-dec.github.io ✨Oral @ICCVConference
Are photorealistic representations all we need? In SuperDec, we turn millions of points into compact and modular abstractions made of just a few superquadrics!🧩 Try our code and get a compact representation of your favorite scene!🚀 👾: github.com/elisabettafede…
United States Xu hướng
- 1. John Bolton 66.3K posts
- 2. #NationalBreadDay N/A
- 3. Asheville 5,170 posts
- 4. Ace Frehley 2,006 posts
- 5. Putin 185K posts
- 6. #KonamiWorldSeriesSweepstakes 1,999 posts
- 7. Mitch 50.8K posts
- 8. Steelers 25.7K posts
- 9. Curt Cignetti 5,724 posts
- 10. Term 201K posts
- 11. Andrade 12K posts
- 12. #2025MAMAVOTE 1.69M posts
- 13. Espionage Act 10.1K posts
- 14. Carter Hart 4,318 posts
- 15. Former Trump 22.6K posts
- 16. AJ Green 1,217 posts
- 17. Dairy Bird N/A
- 18. Nissan 5,175 posts
- 19. Good for Indiana N/A
- 20. Noah Fant N/A
Something went wrong.
Something went wrong.