R1-VL

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 ?

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)

? Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Latest Advances on System-2 Reasoning

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.