What do you think of the humanoid robots? Are they still in the early stage of investment bubbles?

In this blog, we will give you a brief introduction to AgentBoard, an open source AI agent visualization toolkit which can be used the same way as Tensorboard, which helps visaulize Tensors data during model training. AgentBoard aims to visualize key elements and information of AI Agents running loops in development and production stages of real-world scenarios. It provides easy logging APIs in python and can help log multiple data types such as text (prompt), tools use (function calling of LLM API), image, audio and video. With organized logging schemas, agentboard will visualize the agent-loop (PLAN -> ACT -> REFLECT -> REACT etc ), RAG (Retrieval Augumented Generation), Autonomous Agents running, Multi-Agents orchestration, etc. The rest of the blog will cover the basic data types usage, visualization of Agent Loop, Chat History, Tool Use, Functions Calling, RAG, etc.

AI agent research have attracted a lot of attention with the rapid development of Large Language Model (LLM) and Reasoning (RL or CoT Chain of Thought) technology. Generative AI Agents use LLM to plan, act and reflect on the memories from the environment as well as the interactions from other agents, just like the environment in Stanford's Generative Agents paper "Generative Agents: Interactive Simulacra of Human Behavior". The simulation environment usually consists of a environment (Such as A Small Town) and multiple AI Agents taking actions to make plans and achieve goals. Before making plans and taking actions, agents will retrieve related information from memories, which is a list of descriptions of the timestamp and exact events, such as "2023-02-03 Someone is watching a movie...". During multi-agents simulation, each agent will have its own timeline and their actions are usually asynchronous. In this blog, we will give a review of the tools of AI Agents Visualization, especially in the situation where there are multiple agents with asynchronous actions during the simulation.

In this blog, we will introduce the DeepNLP Equation workspace, which helps users better manage, edit, share and display their equations. In the platform, users can manage their equations and latex code in a personal workspace, which enables users to create new equations (with latex code, personal tags), edit and save equations. It also creates a URL of your equation, which can be shared to the collaborators. In the following sections, we will give you the step by step instructions on how to create, edit and share an equation. Once you finish add the equation, you can copy the latex code of your equation to clipboard and paste the code to your preferred latex file system, e.g. Overleaf, etc.

In this blog, we will summarize the latex code of most popular formulas and equations for Financial Engineering Formula and Equation part I-Forwards, Puts, and Calls. We will cover important topics including Forwards, Put-Call Parity, Calls and Puts with Different Strikes, Calls and Puts Arbitrage, Call and Put Price Bounds, Varying Times to Expiration, Early Exercise for American Options, etc.

In this blog, we will summarize the latex code of most popular formulas and equations for Financial Engineering Formula and Equation Monte-Carlo Simulations and Interest Rate Models. We will cover important topics including Monte-Carlo Simulations, Bonds and Interest Rates, Black-Derman-Toy (BDT) model and Cox-Ingersoll-Ross (CIR) model.

In this blog, we will summarize the latex code of most popular formulas and equations for Financial Engineering Formula and Equation part I-Forwards, Puts, and Calls. We will cover important topics including Forwards, Put-Call Parity, Calls and Puts with Different Strikes, Calls and Puts Arbitrage, Call and Put Price Bounds, Varying Times to Expiration, Early Exercise for American Options, etc.

In this blog, we will summarize the latex code of most popular formulas and equations for Financial Engineering Formula and Equation Monte-Carlo Simulations and Interest Rate Models. We will cover important topics including Monte-Carlo Simulations, Bonds and Interest Rates, Black-Derman-Toy (BDT) model and Cox-Ingersoll-Ross (CIR) model.

The 20 useful tricks to tell if Coach Bags are Real or Fake. This guidance is applied to most lines of Coach bags, including COACH RACHEL PHONE CROSSBODY BAG, COACH REVERSIBLE CITY TOTE BAG, COACH PRAIRIE SATCHEL BAG, COACH MARLON HOBO BAG, COACH DREAMER IN COLORBLOCK WITH WHIPSTITCH BAG, COACH DRAWSTRING CARRYALL BAG, COACH TOWN BUCKET BAG, COACH ROWAN SATCHEL BAG, COACH Mollie Bucket Bag, COACH Val Duffle BAG, COACH Gallery Tote BAG, COACH Mini Klare CROSSBODY BAG, etc. You can also visit the official website of Coach (https://www.coach.com) and apply the information from this tutorial to help you check important details of the authentification of Coach bags. The easiest way to tell if a Coach bag is real or fake is to judge by its appearance. You can check the Coach logo and the sign of horse and carriage, the leather plate, the serial number and coach story patch, text on the washing labels and origin of manufacturing, metal zipper, and the paper tag with bar code, etc.

We are seeing more applications of robotaxi and self-driving vehicles worldwide. Many large companies such as Waymo, Tesla and Baidu are accelerating their speed of robotaxi deployment in multiple cities. Some human drivers especially cab drivers worry that they will lose their jobs due to AI. They argue that the lower operating cost and AI can work technically 24 hours a day without any rest like human will have more competing advantage than humans. What do you think?

In this blog, we will give you a brief introduction of most recent progress in On-Device Recommendation (Edge Recommendation) in real-world applications. Mobile AI systems and applications have been more popular due to increasing number of mobile devices and technology developments in deep learning based methods, e.g. model compression, distillation and so on. In recent years, on-device recommendations have enpowered many Mobile Apps to better respond to users' most real-time behaviors on mobile deivces, including clicks, scroll-donwns, likes, and many others. We will introduce three applications, including EdgeRec in Taobao, searchbar background words reranking in Alipay, search result reranking in Meituan-Dianping, short-video recommendation in KuaiShou, TfLite Implementation of Tensorflow, etc.

In this blog, we will summarize the latex code of most fundamental equations of reinforcement learning (RL). This blog will cover many topics, including Bellman Equation, Markov Decision Process(MDP), Partial Observable Markov Decision Process(POMDP), DQN, A3C, etc.

We are seeing more applications of robotaxi and self-driving vehicles worldwide. Many large companies such as Waymo, Tesla and Baidu are accelerating their speed of robotaxi deployment in multiple cities. Some human drivers especially cab drivers worry that they will lose their jobs due to AI. They argue that the lower operating cost and AI can work technically 24 hours a day without any rest like human will have more competing advantage than humans. What do you think?

We are seeing more applications of robotaxi and self-driving vehicles worldwide. Many large companies such as Waymo, Tesla and Baidu are accelerating their speed of robotaxi deployment in multiple cities. Some human drivers especially cab drivers worry that they will lose their jobs due to AI. They argue that the lower operating cost and AI can work technically 24 hours a day without any rest like human will have more competing advantage than humans. What do you think?

In this post, we will talk about some real-world applications of deep candidates generation (vector-retrieval) models in the matching stage of recommendation scenario. Commercial recommendation system will recommend tens of millions of items to each user. And the recommendation process usually consists of two stages: The first stage is the candidate generation(matching) stage, a few hundred candidates are selected from the pool of all candidate items. The second stage is the ranking stage in which hundreds of items are ranked and sorted by the ranking score. Then the top rated items are displayed to users.