Advertising on the Telegram channel «Data Science | Machine Learning for Researchers»

🚀 LunaProxy - The Most Cost-effective Residential Proxy Exclusive Benefits for Members of This Group: 💥 Residential Proxy: As low as $0.77 / GB. Use the discount code [lunapro30] when placing an order and save 30% immediately. ✔️ Over 200 million pure IPs | No charge for invalid ones | Success rate > 99.9% 💥 Unlimited Traffic Proxy: Enjoy a discount of up to 72%, only $79 / day. ✔️ Unlimited traffic | Unlimited concurrency | Bandwidth of over 100Gbps | Customized services | Save 90% of the cost when collecting AI/LLM data Join the Luna Affiliate Program and earn a 10% commission. There is no upper limit for the commission, and you can withdraw it at any time. 👉 Take action now: https://www.lunaproxy.com/?ls=data&lk=?01

فرصة عمل عن بعد 🧑‍💻 لا يتطلب اي مؤهل او خبره الشركه تقدم تدريب كامل ✨ ساعات العمل مرنه  ⏰ يتم التسجيل ثم التواصل معك لحضور لقاء تعريفي بالعمل والشركه https://forms.gle/hqUZXu7u4uLjEDPv8

🌼 SOTA Textured 3D-Guided VTON 🌼 👉 #ALIBABA unveils 3DV-TON, a novel diffusion model for HQ and temporally consistent video. Generating animatable textured 3D meshes as explicit frame-level guidance, alleviating the issue of models over-focusing on appearance fidelity at the expense of motion coherence. Code & benchmark to be released 💙 👉 Review: https://t.ly/0tjdC 👉 Paper: https://lnkd.in/dFseYSXz 👉 Project: https://lnkd.in/djtqzrzs 👉 Repo: TBA #AI #3DReconstruction #DiffusionModels #VirtualTryOn #ComputerVision #DeepLearning #VideoSynthesis https://t.me/DataScienceT 🔗

This channels is for Programmers, Coders, Software Engineers. 0️⃣ Python 1️⃣ Data Science 2️⃣ Machine Learning 3️⃣ Data Visualization 4️⃣ Artificial Intelligence 5️⃣ Data Analysis 6️⃣ Statistics 7️⃣ Deep Learning 8️⃣ programming Languages ✅ https://t.me/addlist/8_rRW2scgfRhOTc0 ✅ https://t.me/Codeprogrammer

NVIDIA introduces Describe Anything Model (DAM) a new state-of-the-art model designed to generate rich, detailed descriptions for specific regions in images and videos. Users can mark these regions using points, boxes, scribbles, or masks. DAM sets a new benchmark in multimodal understanding, with open-source code under the Apache license, a dedicated dataset, and a live demo available on Hugging Face. Explore more below: Paper: https://lnkd.in/dZh82xtV Project Page: https://lnkd.in/dcv9V2ZF GitHub Repo: https://lnkd.in/dJB9Ehtb Hugging Face Demo: https://lnkd.in/dXDb2MWU Review: https://t.ly/la4JD

#NVIDIA #DescribeAnything #ComputerVision #MultimodalAI #DeepLearning #ArtificialIntelligence #MachineLearning #OpenSource #HuggingFace #GenerativeAI #VisualUnderstanding #Python #AIresearch https://t.me/DataScienceT ✅

Follow me on linkedin (important for you) https://www.linkedin.com/in/hussein-sheikho-4a8187246

Liquid: Language Models are Scalable Multi-modal Generators

5 Dec 2024 · Junfeng Wu, Yi Jiang, Chuofan Ma, Yuliang Liu, Hengshuang Zhao, Zehuan Yuan, Song Bai, Xiang Bai · We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared feature space for both vision and language. Unlike previous multimodal large language model (MLLM), Liquid achieves this integration using a single large language model (LLM), eliminating the need for external pretrained visual embeddings such as CLIP. For the first time, Liquid uncovers a scaling law that performance drop unavoidably brought by the unified training of visual and language tasks diminishes as the model size increases. Furthermore, the unified token space enables visual generation and comprehension tasks to mutually enhance each other, effectively removing the typical interference seen in earlier models. We show that existing LLMs can serve as strong foundations for Liquid, saving 100x in training costs while outperforming Chameleon in multimodal capabilities and maintaining language performance comparable to mainstream LLMs like LLAMA2. Liquid also outperforms models like SD v2.1 and SD-XL (FID of 5.47 on MJHQ-30K), excelling in both vision-language and text-only tasks. This work demonstrates that LLMs such as LLAMA3.2 and GEMMA2 are powerful multimodal generators, offering a scalable solution for enhancing both vision-language understanding and generation. The code and models will be released at https://github.com/FoundationVision/Liquid.

Paper: https://arxiv.org/pdf/2412.04332v2.pdf Code: https://github.com/foundationvision/liquid https://t.me/DataScienceT 🖕

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

14 Apr 2025 · Xingjian Leng, Jaskirat Singh, Yunzhong Hou, Zhenchang Xing, Saining Xie, Liang Zheng · In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Traditional deep-learning wisdom dictates that end-to-end training is often preferable when possible. However, for latent diffusion transformers, it is observed that end-to-end training both VAE and diffusion-model using standard diffusion-loss is ineffective, even causing a degradation in final performance. We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process. Despite its simplicity, the proposed training recipe (REPA-E) shows remarkable performance; speeding up diffusion model training by over 17x and 45x over REPA and vanilla training recipes, respectively. Interestingly, we observe that end-to-end tuning with REPA-E also improves the VAE itself; leading to improved latent space structure and downstream generation performance. In terms of final performance, our approach sets a new state-of-the-art; achieving FID of 1.26 and 1.83 with and without classifier-free guidance on ImageNet 256 x 256. Code is available at https://end2end-diffusion.github.io.

Paper: https://arxiv.org/pdf/2504.10483v1.pdf Code: https://github.com/End2End-Diffusion/REPA-E Dataset: ImageNet https://t.me/DataScienceT ✅

📢 5-Day Generative AI Intensive Course with #Google is now available as a self-paced Learn Guide! Access whitepapers, podcasts, code labs, & recorded livestreams. Additionally, there is a bonus assignment for you! https://www.kaggle.com/learn-guide/5-day-genai

#GenerativeAI #GoogleAI #AICourse #SelfPacedLearning #MachineLearning #DeepLearning #Kaggle #AICommunity #TechEducation #AIforEveryone

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

🔥 General Attention-Based Object Detection 🔥 👉 GATE3D is a novel framework designed specifically for generalized monocular 3D object detection via weak supervision. GATE3D effectively bridges domain gaps by employing consistency losses between 2D and 3D predictions. 👉 Review: https://t.ly/O7wqH 👉 Paper: https://lnkd.in/dc5VTUj9 👉 Project: https://lnkd.in/dzrt-qQV #3DObjectDetection #Monocular3D #DeepLearning #WeakSupervision #ComputerVision #AI #MachineLearning #GATE3D ⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟