AI
Are LLMs becoming similarly creative? Evidence from three years of models
Researchers analyzed three years of Large Language Model (LLM) performance on open-ended tasks. They...
AI
Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark
Researchers have developed a new framework for evaluating the quality of specifications in artificia...
AI
Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI
Researchers have developed a method using agentic AI to speed up simulations in project scheduling. ...
AI
In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
Researchers propose a new framework for lifelong learning in neural models, inspired by how animals ...
AI
Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)
Researchers at George Washington University have developed a system to automatic...
AI
When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models
Researchers have developed a framework called UniLang that allows large language...
AI
CVSD-Reg: Cross-Modal Visual Semantic Prior Distillation for Robust LiDAR Registration
Researchers have developed a new method for registering LiDAR point clouds calle...
AI
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Researchers have proposed a new method for training autoregressive diffusion vid...