Blog

Our technical team members share their work in agent science and other fields on the forefront of AI.

August 7, 2024
August 7, 2024

Exploring the Functional Roles of Transformer Layers

A new paper, "Transformer Layers as Painters," co-written by Emergence researchers and Sakana AI, investigates the internal workings of transformers, focusing on how the removal or reorganization of information impacts pretrained models.

August 7, 2024
Exploring the Functional Roles of Transformer Layers
September 8, 2024
A new paper, "Transformer Layers as Painters," co-written by Emergence researchers and Sakana AI, investigates the internal workings of transformers, focusing on how the removal or reorganization of information impacts pretrained models.
July 11, 2024
Our Agent-E SOTA Results on the WebVoyager Benchmark
September 8, 2024
We evaluated our Agent-E with the WebVoyager benchmark.
July 8, 2024
Reliable Synthetic Data Generat­­­ion
September 8, 2024
As we’ve seen the rapidly rising impact of LLMs, we’ve also seen the growing importance of “synthetic data,” generated instructional raw text used to train LLMs.
Search Publications
Filter By

Categories

Showing 0 results of 0 publications.
Tag
close icon
August 21, 2024
October 9, 2024
Building Innate Knowledge into Modality-Agnostic AI Systems
A new paper explores how to encode specific innate knowledge into AI systems that are agnostic to the sensory modality of their inputs.
Insights
August 7, 2024
September 8, 2024
Exploring the Functional Roles of Transformer Layers
A new paper, "Transformer Layers as Painters," co-written by Emergence researchers and Sakana AI, investigates the internal workings of transformers, focusing on how the removal or reorganization of information impacts pretrained models.
Engineering
July 11, 2024
September 8, 2024
Our Agent-E SOTA Results on the WebVoyager Benchmark
We evaluated our Agent-E with the WebVoyager benchmark.
Product
July 8, 2024
September 8, 2024
Reliable Synthetic Data Generat­­­ion
As we’ve seen the rapidly rising impact of LLMs, we’ve also seen the growing importance of “synthetic data,” generated instructional raw text used to train LLMs.
Engineering
July 5, 2024
September 8, 2024
The Emergence of Emergence
Emergence is a compelling phenomenon observable both in natural systems and in engineered designs, where complex behaviors and patterns arise from simple interactions.
Insights
May 20, 2024
September 8, 2024
Beyond What Comes Next
In this post, we consider how to make language models better, not just faster, inspired by several papers.
Insights
May 14, 2024
September 8, 2024
Achieving Self-Improvement in Agentic Systems with Skill Harvesting
Skill harvesting allows agentic systems to self-reflect, autonomously developing more specialized skills.
April 15, 2024
September 8, 2024
MathViz-E - Agent Tool Control
At Emergence, we’ve always believed that the next significant advancement in workflow automation will come from the planning, selection, and use of multiple external tools by artificial intelligence.
Engineering
March 28, 2024
September 8, 2024
Distilling the Web for Multi-Agent Automation
Our everyday interactions with computers are filled with slow and repetitive tasks.
Engineering
Product
March 17, 2024
September 8, 2024
Introducing Emergence
The pivotal advancement in the ability of computers to understand language and develop functional world models has profoundly reset the landscape in computing.
Insights
Engineering
Product
March 19, 2024
September 8, 2024
Self-Improving Agents
Self-improving agents have varying objectives, and the issue of aligning them with human values is critical.
Product
March 20, 2024
September 8, 2024
Building Narrow Self Improving Agents
A number of enterprise workflows involving language- and tool-control tasks can be augmented with LLM- and LVM-powered agents.
Product
Engineering
March 18, 2024
September 8, 2024
The Anatomy of Agents
The concept of a software agent can be traced back to the model Hewitt, et al.
Product
Insights
April 3, 2024
September 8, 2024
Emergence’s Appropriateness Evaluation Model
The high accuracy and precision of our model represent a new achievement in reliably identifying unsuitable prompts and biased datasets.
Product
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.