DeepSeek-R1
DeepSeek-R1 is a reasoning model trained via large-scale reinforcement learning (RL) without the need for supervised fine-tuning (SFT). It demonstrates remarkable performance in reasoning tasks, including self-verification and reflection. The model addresses challenges such as endless repetition and poor readability, and achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
Podrobný úvod
DeepSeek-R1 is an advanced reasoning model that leverages large-scale reinforcement learning to achieve significant performance in reasoning tasks. It incorporates cold-start data before RL to enhance reasoning capabilities and address issues like repetition and readability. DeepSeek-R1 is designed to provide high accuracy in reasoning tasks and is suitable for a wide range of applications.
VíceUmělá inteligence
DeepSeek-VL2
DeepSeek-VL2 is an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models designed for advanced multimodal understanding. It demonstrates superior capabilities across various tasks, including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. The model series includes three variants with 1 billion, 2.8 billion, and 4.5 billion activated parameters respectively.
Yuna AI | Mental Health Companion
Yuna AI is a mental health companion app that offers AI-guided self-therapy based on Cognitive Behavioral Therapy (CBT). It helps users reduce stress, control overthinking, and unlock their best selves.
AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
Discover an innovative approach to mobile UI agents with a cutting-edge solution from Tsinghua University that leverages the power of Small Language Models (SLMs) to automate tasks on-device. Our method addresses the privacy and cost concerns associated with large language models (LLMs) by offering a domain-specific, compact model trained with high-quality data. This breakthrough transforms the UI task automation challenge into a code generation problem, efficiently tackled by an SLM and executed with an on-device code interpreter. Our document-centered strategy automatically constructs detailed API documentation for each app, creating diverse task samples to guide the agent in learning to generate accurate and efficient scripts for unseen tasks. Experience the future of mobile UI interactions with our solution, boasting significantly higher success rates, lower latency, and reduced token consumption compared to state-of-the-art mobile UI agents. Stay ahead with our open-source code, set to revolutionize the field.