01:26:35

o3 (Part 1): Generating data from multiple sampling for self-improvement + Path Ahead

08:29

AgentJo CV Generator: Generate your CV by searching for your profile on the web!

12:07

AgentJo FinTech Demo: Extract Data from Web Pages, Answer with Citation, Multi-step Agentic RAG

01:52:00

Can LLMs be used in self-driving? CoMAL: Collaborative Multi-Agent LLM for Mixed Autonomy Traffic

01:31:47

From TaskGen to AgentJo: Creating My Life Dream of Fast Learning and Adaptable Agents

01:27:48

Tian Yu X John: Discussing Practical Gen AI Tips for Image Prompting

01:28:56

Jiafei Duan: Uncovering the 'Right' Representations for Multimodal LLMs for Robotics

11:54

TaskGen Tutorial 6: Conversation Wrapper

20:05

TaskGen Tutorial 5: External Functions & CodeGen

14:22

TaskGen Tutorial 4: Hierarchical Agents

14:06

TaskGen Tutorial 3: Memory

18:19

TaskGen Tutorial 2: Shared Variables and Global Context

01:29:53

Beyond Strawberry: gpt-o1 - Is LLM alone sufficient for reasoning?

22:33

TaskGen Tutorial 1: Agents and Equipped Functions

32:55

TaskGen Tutorial 0: StrictJSON

01:28:15

LLM-Modulo: Using Critics and Verifiers to Improve Grounding of a Plan - Explanation + Improvements

01:39:49

Agentic Systems for Production: Tips and Tricks

40:08

alphaXiv - Share Ideas, Build Collective Understanding, Interact with ANY open sourced paper authors

01:39:32

TaskGen Overview: Open-Sourced LLM Agentic Framework - Task-Based, Memory-Infused, StrictJSON

01:55:09

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

01:49:08

NeoPlanner - Continually Learning Planning Agent for Large Environments guided by LLMs

02:03:48

Intelligence = Sampling + Filtering

01:28:17

Michael Hodel: Reverse Engineering the Abstraction and Reasoning Corpus

01:17:55

TaskGen Conversational Class v2: JARVIS, Psychology Counsellor, Sherlock Holmes Shop Assistant

01:37:57

CodeAct: Code As Action Space of LLM Agents - Pros and Cons

01:27:17

TaskGen Conversation with Dynamic Memory - Math Quizbot, Escape Room Solver, Psychology Counsellor

01:18:29

Integrate ANY Python Function, CodeGen, CrewAI tool, LangChain tool with TaskGen! - v2.3.0

44:38

Empirical - Open Source LLM Evaluation UI

01:54:55

TaskGen Ask Me Anything #1

01:30:01

StrictJSON (LLM Output Parser) Ask Me Anything #1

11:22

Tutorial #14: Write latex papers with LLMs such as Llama 3!

02:10:13

SORA Deep Dive: Predict patches from text, images or video

01:47:56

OpenAI CLIP Embeddings: Walkthrough + Insights

01:46:47

TaskGen - LLM Agentic Framework that Does More, Talks Less: Shared Variables, Memory, Global Context

02:00:36

CRADLE (Part 2): An AI that can play Red Dead Dedemption 2. Reflection, Memory, Task-based Planning

01:37:39

CRADLE (Part 1) - AI that plays Red Dead Redemption 2. Towards General Computer Control and AGI

01:51:37

TaskGen - A Task-based Agentic Framework using StrictJSON at the core

02:05:11

SymbolicAI / ExtensityAI Paper Overview (Part 2) - Evaluation Benchmark Discussion!

01:32:22

SymbolicAI / ExtensityAI Paper Overview (Part 1) - Key Philosophy Behind the Design - Symbols

01:15:20

Embeddings Walkthrough (Part 2): Context-Dependent Embeddings, Shifting Embedding Space

01:37:30

Embeddings Walkthrough (Part 1) - Bag of Words to word2vec to Transformer contextual embeddings

01:33:16

V* - Better than GPT-4V? Iterative Context Refining for Visual Question Answer!

02:01:20

AutoGen: A Multi-Agent Framework - Overview and Improvements

01:41:05

AppAgent: Using GPT-4V to Navigate a Smartphone!

15:21

Tutorial #13: StrictJSON, my first Python Package! - Get LLMs to output into a working JSON!

04:08

"Are you smarter than an LLM?" game speedrun

11:19

Is Gemini better than GPT4? Self-created benchmark - Fact Retrieval/Checking, Coding, Tool Use

02:31:50

Learning, Fast and Slow: 10 Years Plan - Memory Soup, Hier. Planning, Emotions, Knowledge Sharing

47:02

Tutorial #12: Use ChatGPT and off-the-shelf RAG on Terminal/Command Prompt/Shell - SymbolicAI

01:50:16

JARVIS-1: Multi-modal (Text + Image) Memory + Decision Making with LLMs in MineCraft!

47:21

Tutorial #11: Virtual Persona from Documents, Multi-Agent Chat, Text-to-Speech to hear your Personas

01:49:33

A Roadmap for AI: Past, Present and Future (Part 3) - Multi-Agent, Multiple Sampling and Filtering

13:39

Learning, Fast and Slow: My Landmark Idea for fast, adaptable agents (ICDL 2023 Best Paper Finalist)

01:39:52

A Roadmap for AI: Past, Present and Future (Part 2) - Fixed vs Flexible, Memory Soup vs Hierarchy

34:02

AI & Education: Education when AI tools are smarter than us - Discussion with Kuang Wen (Part 2)

57:04

AI & Education: RAG Question-Answer, Test Question Generator, Autograder by Kuang Wen! (Part 1)

01:31:09

A Roadmap for AI: Past, Present and Future (Part 1) - Expert Systems, Supervised, Unsupervised

07:08

Tutorial #10: StrictJSON v2 (StrictText): Handle any output - quotation marks or backslash!

01:25:18

ChatDev: Can LLM Agents really replace a software company?

02:05:10

LLMs and Robotics: An Overview by Daniel Tan!