Tue Apr 04 2023
Mon Apr 03 2023

Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data

Chat modeling
Natural Language Processing
Customer service chat bots

Proposes a pipeline that can automatically generate a high-quality multi-turn chat corpus by leveraging ChatGPT to engage in a conversation with itself

Can improve customer service chat bots and enable businesses to create their own chat models for customer interactions

Vision Transformers with Mixed-Resolution Tokenization

Vision Transformers
Computer vision
Image recognition tasks

Introduces a novel image tokenization scheme for Vision Transformers, improving accuracy gains on image classification while controlling computational budget

Can improve image recognition tasks and enable businesses to process images more efficiently

Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos

Text-to-image models
Computer vision
Digital character creation

Presents a two-stage training scheme for obtaining pose-controllable character videos using pre-trained text-to-image models and easily obtained datasets

Can improve digital character creation for businesses in various industries, including gaming and entertainment

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

motion generation
AI for creative applications
machine learning for motion generation
3D human motion generation
creative industry
text-driven motion generation

ReMoDiffuse proposes a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process for diverse motion generation

ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation which is crucial for the creative industry, providing a better balance between text-motion consistency and motion quality

LLMMaps - A Visual Metaphor for Stratified Evaluation of Large Language Models

language models
natural language processing
evaluation of language models
natural language processing
question and answer datasets
stratified evaluation

LLMMaps proposes a novel visualization technique that enables users to evaluate Large Language Models' (LLMs) performance with respect to question and answer (Q&A) datasets

LLMMaps provides detailed insights into LLMs' knowledge capabilities in different subfields, revealing subfields where hallucinations are more likely to occur and guiding their further development

Sun Apr 02 2023
Fri Mar 31 2023
Thu Mar 30 2023
Wed Mar 29 2023