Technology peripherals
AI
SenseTime and Tsinghua University generalist AI agents unlock 100% of Minecraft! 2 days of training on a single CPU to create a redstone circuit from scratch
SenseTime and Tsinghua University generalist AI agents unlock 100% of Minecraft! 2 days of training on a single CPU to create a redstone circuit from scratch
In the development process of AI, there is a very interesting but contrary to common sense phenomenon——
"Some tasks that are relatively difficult for humans, such as playing chess, It is relatively easy for AI to achieve. However, in the open world, interacting with the environment, planning and making decisions, which are relatively simple things for humans, AI faces huge challenges."
And this is the Moravec Paradox.
However, now GITM has successfully broken this paradox limitation, made breakthroughs in complex and real-world-like environments, and is able to survive, explore and create like humans!
In the best-selling game "Minecraft" that closely simulates the real world, jointly developed by SenseTime The general AI agent Ghost in the Minecraft (GITM) jointly proposed by researchers from Tsinghua University, Shanghai Artificial Intelligence Laboratory and other institutions can not only play "Minecraft", but also performs better than all previous agents.
##Project homepage: https://github.com/OpenGVLab/GITM
Survive, explore and create like humansThis research is an important step towards artificial general intelligence (AGI).
#Extensive mission coverage
GITM achieved 100% mission coverage on all technical challenges in the main world in "Minecraft" (successfully unlocked 262 items in the complete technology tree), while the sum of all previous agents was only Can cover 30%. (In the past, all agent methods, including OpenAI and DeepMind, only unlocked a total of 78)
High Mission success rate
#On the most watched "Get Diamonds" mission, GITM achieved a success rate of 67.5%, compared to the current best result (OpenAI VPT) An increase of 47.5%.
The training efficiency of GITM has also reached new heights. The number of environment interaction steps is only one ten thousandth of that of existing methods, and training on a single CPU node can be completed in 2 days, which is far lower than the 6480 GPU days required by OpenAI VPT or the 17 GPU days required by DeepMind DreamerV3.
GITM can handle various terrains, environments, day and night scenes, and even monsters.
GITM can be further applied In the more complex tasks of "Minecraft", such as shelters, farmland, iron golems needed for survival, redstone circuits needed to create automated equipment, nether portals needed to enter the netherworld, etc.
These tasks demonstrate the powerful capabilities and scalability of GITM, allowing the agent to play in "Minecraft" Survive, develop and explore a more advanced world in the medium to long term.
General Artificial Intelligence Breakthrough Accelerates the AI Industrialization Revolution
The purpose of developing an AI agent GITM that overcomes all technical challenges in "Minecraft" is to build an autonomous A general artificial intelligence direction for learning and mastering entire real-world skills.
GITM breaks the traditional RL-based architecture and adopts a new paradigm of large language model (LLM) as the core of the agent.
This innovation also helps accelerate the research goal of artificial general intelligence (AGI) Realize and develop intelligent agents that can perceive, understand and interact like humans in an open world environment, and bring huge breakthroughs and progress to industries such as robotics and autonomous driving, effectively solving complex environments and various long tails in the real world. issues to promote the industrial implementation of AI technology on a larger scale.
##「Ghost in the Minecraft」（GITM）
Benefit With the strategic layout of "big models and big computing power" to promote the development of AGI (general artificial intelligence) and the full-stack large model R&D system, SenseTime has been able to develop rapidly in the field of multi-modal and multi-task general large models, with "every day" "New SenseNova" large-scale model system is the core, continuously helping innovative technologies to be quickly applied in fields such as smart cars, smart life, smart business, and smart cities, and continuously improving industrial intelligence.
Today, the success of GITM will push the ability of applications such as autonomous driving to handle complex tasks to a higher level and break higher technical ceilings.
The above is the detailed content of SenseTime and Tsinghua University generalist AI agents unlock 100% of Minecraft! 2 days of training on a single CPU to create a redstone circuit from scratch. For more information, please follow other related articles on the PHP Chinese website!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
1387
52
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
No OpenAI data required, join the list of large code models! UIUC releases StarCoder-15B-Instruct
Jun 13, 2024 pm 01:59 PM
At the forefront of software technology, UIUC Zhang Lingming's group, together with researchers from the BigCode organization, recently announced the StarCoder2-15B-Instruct large code model. This innovative achievement achieved a significant breakthrough in code generation tasks, successfully surpassing CodeLlama-70B-Instruct and reaching the top of the code generation performance list. The unique feature of StarCoder2-15B-Instruct is its pure self-alignment strategy. The entire training process is open, transparent, and completely autonomous and controllable. The model generates thousands of instructions via StarCoder2-15B in response to fine-tuning the StarCoder-15B base model without relying on expensive manual annotation.
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
Yolov10: Detailed explanation, deployment and application all in one place!
Jun 07, 2024 pm 12:05 PM
1. Introduction Over the past few years, YOLOs have become the dominant paradigm in the field of real-time object detection due to its effective balance between computational cost and detection performance. Researchers have explored YOLO's architectural design, optimization goals, data expansion strategies, etc., and have made significant progress. At the same time, relying on non-maximum suppression (NMS) for post-processing hinders end-to-end deployment of YOLO and adversely affects inference latency. In YOLOs, the design of various components lacks comprehensive and thorough inspection, resulting in significant computational redundancy and limiting the capabilities of the model. It offers suboptimal efficiency, and relatively large potential for performance improvement. In this work, the goal is to further improve the performance efficiency boundary of YOLO from both post-processing and model architecture. to this end
SOTA performance, Xiamen multi-modal protein-ligand affinity prediction AI method, combines molecular surface information for the first time
Jul 17, 2024 pm 06:37 PM
Editor | KX In the field of drug research and development, accurately and effectively predicting the binding affinity of proteins and ligands is crucial for drug screening and optimization. However, current studies do not take into account the important role of molecular surface information in protein-ligand interactions. Based on this, researchers from Xiamen University proposed a novel multi-modal feature extraction (MFE) framework, which for the first time combines information on protein surface, 3D structure and sequence, and uses a cross-attention mechanism to compare different modalities. feature alignment. Experimental results demonstrate that this method achieves state-of-the-art performance in predicting protein-ligand binding affinities. Furthermore, ablation studies demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within this framework. Related research begins with "S
SK Hynix will display new AI-related products on August 6: 12-layer HBM3E, 321-high NAND, etc.
Aug 01, 2024 pm 09:40 PM
According to news from this site on August 1, SK Hynix released a blog post today (August 1), announcing that it will attend the Global Semiconductor Memory Summit FMS2024 to be held in Santa Clara, California, USA from August 6 to 8, showcasing many new technologies. generation product. Introduction to the Future Memory and Storage Summit (FutureMemoryandStorage), formerly the Flash Memory Summit (FlashMemorySummit) mainly for NAND suppliers, in the context of increasing attention to artificial intelligence technology, this year was renamed the Future Memory and Storage Summit (FutureMemoryandStorage) to invite DRAM and storage vendors and many more players. New product SK hynix launched last year
