Just saw a talk by @AlonHalevy about using a **timeline** based data-structure to do RAG. Really useful for querying over personal events Need to dive into this more! Am always excited to see novel data-structures Repo here: https://
github.com/facebookresear
ch/personal-timeline/tree/main
…
MACHINE LEARNING
-
Timeline-Based Data Structure for Personal Event RAG Queries
By
–
-
AI Conversational Agents Training Children’s Curiosity Learning
By
–
Designing artificial conversational agents to train children's curiosity during learning, a proof of concept through the Kids Ask project https://
bit.ly/3Qv3njj #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Three Steps for Building Responsible AI Infrastructure
By
–
3 Steps To Creating The Infrastructure For Responsible AI
#AI #AIio #BigData #ML #NLU #Futureofwork @CRudinschi @AntonioSelas @alexjc @RobotLaunch @karpathy @andyjankowski @bobgourley @CadeMetz http://
ow.ly/gSWA30swTtO -
AI Robot Wingman Transforms Aerial Combat Operations
By
–
#AI Brings the Robot Wingman to Aerial Combat https://
nytimes.com/2023/08/27/us/
politics/ai-air-force.html?smid=tw-share
… -
Rethinking Backdoor Attacks in AI Systems
By
–
Rethinking Backdoor Attacks https://
bit.ly/45j81oJ #AI #MachineLearning #DeepLearning #LLMs #DataScience -
LLMs training on self-generated text as machine learning inbreeding
By
–
LLMs generating new text that they will then use to further train LLMs is the machine learning version of inbreeding.
-
Language-to-Rewards System for Robotic Skill Synthesis
By
–
10/ Language to Rewards for Robotic Skill Synthesis – proposes a new language-to-reward system that utilizes LLMs to define optimizable reward parameters to achieve a variety of robotic tasks.https://t.co/8ztl4MMyjS
— DAIR.AI (@dair_ai) 27 août 202310/ Language to Rewards for Robotic Skill Synthesis – proposes a new language-to-reward system that utilizes LLMs to define optimizable reward parameters to achieve a variety of robotic tasks.
-
Survey of LLM-Based Autonomous Agents and Applications
By
–
7/ A Survey on LLM-based Autonomous Agents – presents a survey of LLM-based autonomous agents; delivers a systematic review of the field and a summary of various applications of LLM-based AI agents in domains like social science and engineering.
-
Prompt2Model: Automated Small Model Training Pipeline
By
–
8/ Prompt2Model – takes a prompt describing a task and trains a small model that is conducive to deployment; the pipeline automatically collects and synthesizes knowledge through three channels: dataset retrieval, dataset generation, and model retrieval.
-
Giraffe: Extended Context Length LLMs from Llama Base Models
By
–
5/ Giraffe – new models that are fine-tuned from base Llama and Llama 2; extends the context length to 4K, 16K, and 32K; explores the space of expanding context lengths in LLMs so it also includes insights useful for practitioners and researchers.