Imagine an artificial intelligence model that not only has the ability to surpass traditional computing, but also achieves more efficient performance at a lower cost. This is not science fiction, DeepSeek-V2[1], the world’s most powerful open source MoE model is here. DeepSeek-V2 is a powerful mixture of experts (MoE) language model with the characteristics of economical training and efficient inference. It consists of 236B parameters, 21B of which are used to activate each marker. Compared with DeepSeek67B, DeepSeek-V2 has stronger performance, while saving 42.5% of training costs, reducing KV cache by 93.3%, and increasing the maximum generation throughput to 5.76 times. DeepSeek is a company exploring general artificial intelligence

Earlier this month, researchers from MIT and other institutions proposed a very promising alternative to MLP - KAN. KAN outperforms MLP in terms of accuracy and interpretability. And it can outperform MLP running with a larger number of parameters with a very small number of parameters. For example, the authors stated that they used KAN to reproduce DeepMind's results with a smaller network and a higher degree of automation. Specifically, DeepMind's MLP has about 300,000 parameters, while KAN only has about 200 parameters. KAN has a strong mathematical foundation like MLP. MLP is based on the universal approximation theorem, while KAN is based on the Kolmogorov-Arnold representation theorem. As shown in the figure below, KAN has

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.

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

Written above & the author’s personal understanding: This paper is dedicated to solving the key challenges of current multi-modal large language models (MLLMs) in autonomous driving applications, that is, the problem of extending MLLMs from 2D understanding to 3D space. This expansion is particularly important as autonomous vehicles (AVs) need to make accurate decisions about 3D environments. 3D spatial understanding is critical for AVs because it directly impacts the vehicle’s ability to make informed decisions, predict future states, and interact safely with the environment. Current multi-modal large language models (such as LLaVA-1.5) can often only handle lower resolution image inputs (e.g.) due to resolution limitations of the visual encoder, limitations of LLM sequence length. However, autonomous driving applications require

In order to align large language models (LLMs) with human values ??and intentions, it is critical to learn human feedback to ensure that they are useful, honest, and harmless. In terms of aligning LLM, an effective method is reinforcement learning based on human feedback (RLHF). Although the results of the RLHF method are excellent, there are some optimization challenges involved. This involves training a reward model and then optimizing a policy model to maximize that reward. Recently, some researchers have explored simpler offline algorithms, one of which is direct preference optimization (DPO). DPO learns the policy model directly based on preference data by parameterizing the reward function in RLHF, thus eliminating the need for an explicit reward model. This method is simple and stable

The benchmark YOLO series of target detection systems has once again received a major upgrade. Since the release of YOLOv9 in February this year, the baton of the YOLO (YouOnlyLookOnce) series has been passed to the hands of researchers at Tsinghua University. Last weekend, the news of the launch of YOLOv10 attracted the attention of the AI ??community. It is considered a breakthrough framework in the field of computer vision and is known for its real-time end-to-end object detection capabilities, continuing the legacy of the YOLO series by providing a powerful solution that combines efficiency and accuracy. Paper address: https://arxiv.org/pdf/2405.14458 Project address: https://github.com/THU-MIG/yo

French AI unicorn MistralAI, which is targeting OpenAI, has made a new move: Codestral, the first large code model, was born. As an open generative AI model designed specifically for code generation tasks, Codestral helps developers write and interact with code by sharing instructions and completion API endpoints. Codestral's proficiency in coding and English allows software developers to design advanced AI applications. The parameter size of Codestral is 22B, it complies with the new MistralAINon-ProductionLicense, and can be used for research and testing purposes, but commercial use is prohibited. Currently, the model is available for download on HuggingFace. download link