LLMS

Multi-Hop Reasoning Limitations in Large Language Models

By

–

02 December 2024 18h46

Evaluating Latent Multi-Hop Reasoning in Large Language Models Investigates whether LLMs can combine factual knowledge across multiple hops without relying on pretraining shortcuts. Problem:
LLMs struggle with latent multi-hop reasoning due to reliance on pretraining

Enhancing LLM Reasoning with Separate Critique Model

By

–

02 December 2024 18h46

Enhancing LLM Reasoning Improving LLM reasoning by using a separate "critique" model to provide feedback during both training and testing. Problem:
LLMs struggle with complex reasoning and self-correction, especially on challenging tasks where performance plateaus. Method:

LLM-Powered GUI Agents: Automation Survey and Insights

By

–

02 December 2024 18h46

Large Language Model-Brained GUI Agents: A Survey A comprehensive survey exploring how large language models can be used to create AI agents that interact with graphical user interfaces through natural language. Problem:
GUI automation lacks flexibility, requiring complex

ShowUI: Lightweight Vision-Language Model for GUI Automation

By

–

02 December 2024 18h46

ShowUI A lightweight vision-language model for efficient GUI automation that achieves SOTA performance while using fewer parameters and less training data. Problem:
GUI automation relying on APIs and metadata struggles with real-world visual scenarios requiring efficient,

Critic-V: External Feedback Framework for Vision-Language Models

By

–

02 December 2024 18h46

Critic-V A framework using an external critic model to refine vision-language model outputs through feedback. Problem: Vision-language models struggle with errors like hallucinations and irrelevant reasoning due to lack of external feedback. Method: Combines a Reasoner that

→ View original post on X — @reach_vb

Try llms-txt: New Tool for Language Models

By

@reach_vb

–

02 December 2024 17h59

You should try it on `llms-txt`: Would love to hear feedback!

→ View original post on X — @testingcatalog

Hume lance des outils de création de voix

By

@testingcatalog

–

02 December 2024 17h55

Hume just launched its Voice Creation tools on the Hume Platform!

There you can create, configure and test Hume voices with different LLM models and configs 👀 https://t.co/hBY7qZQR6R pic.twitter.com/pOerNdh4HU
— 🚨 AI News | TestingCatalog (@testingcatalog) 2 décembre 2024

Hume just launched its Voice Creation tools on the Hume Platform! There you can create, configure and test Hume voices with different LLM models and configs

→ View original post on X — @aymericroucher

Adobe’s Code-Generating Agent Tops GAIA Leaderboard

By

@aymericroucher

–

02 December 2024 17h54

𝗔𝗱𝗼𝗯𝗲'𝘀 𝗰𝗼𝗱𝗲-𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝘁𝗵𝗲 𝘁𝗼𝗽 𝗼𝗳 𝗚𝗔𝗜𝗔 𝗹𝗲𝗮𝗱𝗲𝗿𝗯𝗼𝗮𝗿𝗱 – and they cite "Roucher, 2024" in the paper! Reminder: Broadly defined, an "Agent" is a system where a LLM is augmented with the ability to run

→ View original post on X — @reach_vb

Execute SQL Queries with AI in Your Browser Today

By

@reach_vb

–

02 December 2024 15h17

you can just do things – ask AI to create your SQL queries and execute them right in your browser! 🔥

let your creativity guide you – powered by @Alibaba_Qwen 2.5 coder 32b ⚡

available on all 254,746 public datasets on the hub!

go check it out today! 🤗 pic.twitter.com/YYIiNaSFJK
— Vaibhav (VB) Srivastav (@reach_vb) 2 décembre 2024

you can just do things – ask AI to create your SQL queries and execute them right in your browser! let your creativity guide you – powered by @Alibaba_Qwen 2.5 coder 32b available on all 254,746 public datasets on the hub! go check it out today!