Tue Apr 11 2023
Mon Apr 10 2023

OpenAGI: When LLM Meets Domain Experts

Large Language Models (LLMs)
Artificial General Intelligence (AGI)
Reinforcement Learning (RL)
Multi-task problem-solving
Improving AI performance over time through RLTF
Developing AI models that use multiple domain-specific models to solve complex tasks

OpenAGI is an open-source AGI research platform that uses Large Language Models (LLMs) to select, synthesize, and execute various domain-specific expert models to solve complex tasks. It also proposes a Reinforcement Learning from Task Feedback (RLTF) mechanism to provide feedback to improve LLM's task-solving ability, enabling a feedback loop for self-improving AI.

Businesses can use OpenAGI to develop and implement AI models that can solve complex tasks by harnessing multiple domain-specific models. RLTF can be used to improve the performance of AI models over time.

Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention

Local attention modules
Convolution operations
Vision Transformer models
Implementing advanced Vision Transformer models
Efficient and flexible local feature learning and dynamic feature selection

Slide-Transformer is a local attention module that allows for local feature learning and dynamic feature selection using common convolution operations. It is an efficient and flexible way to implement the local attention paradigm, and is compatible with various hardware devices. It achieves consistently improved performance on comprehensive benchmarks for advanced Vision Transformer models.

Businesses can use Slide-Transformer to implement advanced Vision Transformer models that allow for efficient and flexible local feature learning and dynamic feature selection.

Inference with Reference: Lossless Acceleration of Large Language Models

Inference with references
Large Language Models (LLMs)
Speeding up inference of Large Language Models
Practical generation scenarios with significant overlap between in-context reference and outputs

LLMA is an LLM accelerator that losslessly speeds up Large Language Model (LLM) inference with references. It achieves over 2x speed-up for LLMs with identical generation results as greedy decoding in practical generation scenarios where significant overlap between in-context reference and outputs exists (e.g., search engines and multi-turn conversations).

Businesses can use LLMA to speed up inference of Large Language Models when there is significant overlap between the reference and the outputs, such as in search engines and multi-turn conversations.

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

Artificial intelligence
Computer vision
Natural language processing
Image classification
Semantic segmentation
Object detection

This work proposes POMP, a prompt pre-training method for vision-language models. Once pre-trained, the prompt can be directly plugged into a variety of visual recognition tasks to boost recognition performances in a zero-shot manner.

POMP improves recognition performances on 21 downstream datasets for image classification, semantic segmentation, and object detection.

WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus

Artificial intelligence
Natural language processing
Web mining
Factual article generation
Evidence retrieval

This paper introduces a new NLP task called WebBrain, which generates short factual articles from queries by mining supporting evidence from the web. The authors construct a large-scale dataset WebBrain-Raw by extracting English wiki articles and their references.

ReGen, a new framework for generation, outperforms all baselines in both automatic and human evaluations in enhancing factualness.

Sun Apr 09 2023
Thu Apr 06 2023
Wed Apr 05 2023
Tue Apr 04 2023