multimodal AI - aitoearn

Baidu ERNIE

Only 3B Active Parameters, Stronger Multimodal Understanding and Reasoning — Baidu ERNIE-4.5-VL-28B-A3B-Thinking Officially Open-Sourced

PaddlePaddle — ERNIE-4.5-VL-28B-A3B-Thinking Release Date: November 11, 2025 Location: Zhejiang --- Overview Baidu has officially open-sourced its new ERNIE-4.5-VL-28B-A3B-Thinking multimodal deep-thinking model — a leading performer in document & chart understanding, cross-disciplinary reasoning, general visual reasoning, and cross-modal problem-solving. With only 3B activated parameters, it delivers capabilities comparable to top-tier

NVIDIA

Flexing Muscles While Building Walls: NVIDIA Launches OmniVinci, Outperforms Qwen2.5-Omni but Faces “Fake Open Source” Criticism

NVIDIA OmniVinci: A Breakthrough in Multimodal AI NVIDIA has unveiled OmniVinci, a large language model designed for multimodal understanding and reasoning — capable of processing text, visual, audio, and even robotic data inputs. Led by the NVIDIA Research team, the project explores human-like perception: integrating and interpreting information across multiple data

LLM optimization

Today’s Open Source (2025-11-3): Kuaishou and Nanjing University Lab Co-Develop HiPO for Hybrid Strategy Optimization in LLM Dynamic Inference, Dual-Mode Switching Balances Accuracy and Efficiency

🏆 Foundational Models ① Project: HiPO HiPO-8B is a novel reinforcement learning framework based on Hybrid Policy Optimization, enabling dynamic reasoning capabilities in large language models (LLMs). Key Highlights: * Developed by KwaiKAT team at Kuaishou in collaboration with NJU-LINK Laboratory (Nanjing University) and ARiSE Laboratory. * Features “think-on” and “think-off” mode switching to

LongCat-Flash

LongCat-Flash-Omni Released and Open-Sourced: Ushering in the Era of Real-Time All-Modal Interaction

LongCat-Flash-Omni — Next-Generation Open-Source Full-Modality Model Overview Since September 1, Meituan launched the LongCat-Flash series, beginning with LongCat-Flash-Chat and LongCat-Flash-Thinking, quickly gaining attention in the developer community. Today, the series expands with a new flagship addition: LongCat-Flash-Omni. Highlights: * Efficient Shortcut-Connected MoE architecture (including zero-computation experts) * Highly efficient multimodal perception modules * Speech

Meituan AI

Meituan’s New Standalone App — You Can’t Order Food, Only AI

Meituan’s “Food Delivery Speed” Approach to AI Models Meituan appears to be embracing a “fast and stable” AI development mantra — rapidly releasing new models while maintaining high performance. Over the past two months, multiple models have been launched, and the momentum continues. --- Introducing LongCat‑Flash‑Omni The newest

AI Models

LeCun’s Prediction Comes True: 790-Year Long Video Trains the Strongest Open-Source “World Model”

The Third Scaling Paradigm in AI Emu3.5 Ushers in a Native Multimodal World New Intelligence Report Editor: Peach Sleepy --- Executive Summary The third scaling paradigm in AI is here — Emu3.5. With 34 billion parameters, trained on the equivalent of 790 years of long-form video, this native multimodal

Emu3.5

Zhipu Wujie·Emu3.5 Released, Launching “Next-State Prediction”! Wang Zhongyuan: Could Open the Third Scaling Paradigm

WuJie·Emu3.5 — The Next Leap in Multimodal World Models Introduction In October 2024, the Beijing Academy of Artificial Intelligence (BAAI) released the world’s first natively multimodal world model — WuJie·Emu3. This groundbreaking model is based entirely on next-token prediction, avoiding diffusion or composite methods, and achieves a unified

Emu3.5

The World Model Gets Open-Source Base Emu3.5 — Achieves Multimodal SOTA, Outperforms Nano Banana

Wujie·Emu3.5 — The Latest Open‑Source Native Multimodal World Model The Beijing Academy of Artificial Intelligence (BAAI) has officially unveiled Wujie·Emu3.5 — a groundbreaking open-source world model that masters images, text, and video in a single architecture. It can draw, edit, teach with illustrated tutorials, and now, generate

world models

Zhiyuan Wujie · Emu3.5 Reshapes the World Model Landscape: Introducing the First Multimodal Scaling Paradigm for Next-Gen AI Understanding

Once Again, Pushing the Limits of World Models A new benchmark has been set in the race for world models. The Beijing Academy of Artificial Intelligence (BAAI) has announced its large-scale multimodal world model — Wujie·Emu3.5. It not only simulates complex, dynamic physical realities with remarkable realism, but also

PaddleOCR-VL

Wenxin 4.5’s Most Powerful Derivative Model PaddleOCR-VL: How to Push Document Parsing Limits with 0.9B Parameters

PaddleOCR-VL: Next-Generation Multimodal Document Parsing 2025-10-27 · Shanghai --- Click the blue text to follow us We have officially launched PaddleOCR-VL, a next-generation multimodal document parsing solution supporting 109 languages. With only 0.9B parameters, it sets new records across multiple authoritative benchmarks. Testing — both public and internal — shows industry-leading performance

multimodal AI

Relentless Pursuit of "Text Intelligence": The Next Frontier in Multimodal Research

Everywhere We Look, Text Holds Hidden Challenges — Time to Talk About Multimodal Text Intelligence AI in Medical Diagnosis — A Growing Trend Recently, we reported on a striking phenomenon: more and more people are consulting AI for medical advice, especially when the cause of illness is unclear. Some even claim AI

AI image editing

Google’s Top AI Surpassed by HKUST Open Source? The Image Editing Powerhouse Making Overseas Creators Shout “King Bomb”

Driving Multimodal AI Toward True Generalized Creation Introduction — The "Photoshop is Dead" Moment In recent months, "Photoshop is dead" has become a hot topic in the AI creator community. The explosive growth of image editing and generation models is challenging professional creative software’s long-standing dominance.