RITS

Tag: genai

  • Wan2.2: Alibaba’s Open‑Source Breakthrough in AI Video Generation

    The Wan2.2 project (hosted at Wan‑Video/Wan2.2) marks another leap forward in large‑scale, open, consumer‑accessible video generative models developed by the Wan‑AI team at Alibaba Cloud (GitHub). Released on July 28, 2025, this upgrade offers major technical advancements over the previous Wan2.1 version (Hugging Face). Key points The Wan-AI team at Alibaba Cloud released Wan2.2 on […]

  • Alibaba Unveils Qwen3‑Coder: A New Era for Agentic Code Generation

    Alibaba Cloud has officially launched Qwen3‑Coder, marking a significant leap in open‑source AI code models. Here’s why it matters: Key points Alibaba Cloud launched Qwen3-Coder, and its flagship variant Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts model with 480 billion total parameters and 35 billion active per pass. The model has a native context window of 256K tokens […]

  • AI Wins Gold at 2025 International Mathematical Olympiad

    In an unprecedented milestone for artificial intelligence, Google’s Gemini Deep Think and a new experimental OpenAI model both achieved gold medal scores at the 66th International Mathematical Olympiad (IMO), held July 2025 in Queensland, Australia. This marks the first time AI systems have reached this level in the prestigious high-school competition (Reuters). Key points Google’s Gemini Deep Think […]

  • OmniSVG Weights Released!

    Exciting news from the AI graphic design community: the developers behind OmniSVG have officially released the pre‑trained model weights on Hugging Face 🎉. Key points The developers behind OmniSVG officially released the model’s pre-trained weights on Hugging Face. OmniSVG was first introduced in a research paper (arXiv 2504.06263) by Yiying Yang et al. in April 2025. […]

  • Alibaba‑backed Moonshot Unveils Kimi K2: A High‑Performance, Cost‑Effective Rival to ChatGPT and Claude

    Chinese AI startup Moonshot AI, backed by Alibaba, has released Kimi K2, a powerful open‑source language model designed to compete directly with market leaders like OpenAI’s ChatGPT and Anthropic’s Claude Opus 4 (Reuters). Key points Chinese AI startup Moonshot AI, backed by Alibaba, has released Kimi K2, an open-source language model designed to compete with OpenAI’s ChatGPT and […]

  • Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation with MultiTalk

    Modern generative AI has made impressive strides in creating lifelike talking-head and full-body videos from single-speaker audio, but when multiple people converse, existing solutions often falter—mixing up who’s speaking or failing to follow a direction. Enter MultiTalk, a new framework designed specifically for multi-person, audio-driven video generation. Key points MultiTalk is a framework for multi-person, […]

  • Introducing MagentaRT: Google’s Open-Weights Real-Time Music Generation Model

    Today, Google’s Magenta team unveiled Magenta RealTime (MagentaRT), an 800-million-parameter autoregressive transformer model designed to generate high-fidelity, 48 kHz stereo music in real time with low latency and full user control (magenta.withgoogle.com). Licensed permissively (with some bespoke terms), MagentaRT is the open-weights counterpart to Google’s proprietary Lyria RealTime model and aims to eventually run locally […]

  • Introducing V-JEPA 2: Meta’s Self-Supervised Video World Model for Understanding, Prediction, and Planning

    Meta’s FAIR research team has just released V-JEPA 2, a cutting-edge world model trained on large-scale video data that enables AI agents to understand, predict, and even plan in the physical world. Building on the original JEPA (Joint Embedding Predictive Architecture) framework, V-JEPA 2 is pretrained on over 1 million hours of internet video and […]

  • Seaweed APT2: Real-Time Interactive Video Generation with Autoregressive Adversarial Post-Training

    Seaweed APT2 is a groundbreaking streaming video generation model designed for real-time interactive applications. Building on its predecessor (APT1), APT2 employs an autoregressive adversarial post-training paradigm that allows it to generate continuous video frames with minimal latency. At its core, the model produces a single latent frame—equivalent to four video frames—using only one network forward […]

  • Tencent Hunyuan3D: A One-Stop AI 3D Content Creation Platform

    Tencent’s Hunyuan3D platform (https://3d-models.hunyuan.tencent.com/) brings the power of generative AI to every step of the 3D-asset pipeline. Whether you’re a game designer, filmmaker, product modeller, or hobbyist creator, Hunyuan3D offers a suite of tools that let you go from concept to production–ready models in seconds. Key points Tencent’s Hunyuan3D is a platform that applies generative […]