GoT-R1

New GoT-R1 Multimodal Model Released: Making AI Drawing Smarter, the New Era of Image Generation!

Recently, a research team from the University of Hong Kong, The Chinese University of Hong Kong, and SenseTime has released a remarkable new framework - GoT-R1. This innovative multimodal large model significantly enhances AI's semantic and spatial reasoning capabilities in visual generation tasks by introducing reinforcement learning (RL), successfully generating high-fidelity and semantically consistent images from complex text prompts. This advancement marks another leap forward in image generation technology.Currently, although existing multimodal large models have made significant progress in generating images based on text prompts, they still face many challenges when handling instructions involving precise spatial relationships and complex combinations.

6/26/2025 5:01:43 PM

AI在线

全新 GoT-R1 多模态模型发布：让 AI 画图更聪明，图像生成新纪元！

近日，来自香港大学、香港中文大学以及商汤科技的研究团队发布了一个令人瞩目的新框架 ——GoT-R1。这一全新的多模态大模型通过引入强化学习（RL），在视觉生成任务中显著提升了 AI 的语义和空间推理能力，成功应对复杂的文本提示生成高保真、语义一致的图像。这一进展标志着图像生成技术的又一次飞跃。

6/26/2025 1:00:48 PM

AI在线

资讯热榜

AI Hacker Rises to Power! XBOW's Autonomous AI Tool Dominates HackerOne, Revealing Thousands of Vulnerabilities and Intimidating the Cybersecurity Industry 我国首个发电行业大模型“擎源”发布，模型参数达千亿级别告别复杂SQL！用Spring AI + DeepSeek构建自然语言查询系统 Vibemotion AI Released! One-Click Generation of Dynamic Videos, Zero-Barrier Creation Triggers a Visual Revolution Hengbot 推出 Sirius 机器狗：集成 OpenAI，可跳舞、踢足球未来已来！Hengbot发布 Sirius 机器狗，能跳舞会踢球，还有AI陪聊豆包AI编程重磅升级！零代码小白也能轻松打造专属网页，实时编辑超省心！ Gartner 预测：市场冷静后，2027 年底超 40% 智能体（代理）AI 项目将被取消

标签云

人工智能 AI OpenAI AIGC 模型 ChatGPT DeepSeek AI绘画谷歌数据机器人大模型 Midjourney 用户智能开源微软 Meta GPT 学习图像技术 Gemini AI创作马斯克论文代码 Anthropic 英伟达算法 Stable Diffusion 芯片智能体训练开发者生成式蛋白质腾讯苹果神经网络 3D 研究生成 Claude AI新词机器学习计算 LLM Sora AI设计 AI for Science AI视频 GPU 人形机器人 xAI 华为百度搜索大语言模型场景 Agent 字节跳动预测深度学习伟达大型语言模型 Transformer 工具视觉 RAG 神器推荐模态 Copilot 亚马逊具身智能文本 LLaMA 算力驾驶 API