Researchers propose a new framework for managing experiences in self-evolving agents. The Tree-of-Experience (ToE) framework organizes experience into...
Researchers have developed a new model called Factorized Inverse Decision Model (FIDM) to better understand how people make decisions. Unlike previous...
Researchers have developed a new family of AI models called Mint-Agent, designed to excel in financial tasks. These models are built around three pill...
Large language models (LLMs) used in code generation often 'hallucinate', inventing non-existent libraries that can mislead developers and expose syst...
Researchers have developed a new framework for automatically assigning and ordering International Classification of Diseases (ICD) codes in clinical n...
Researchers have investigated the effectiveness of knowledge distillation for CLIP-style models in visual question answering tasks. They found that st...
Researchers have created a benchmark to evaluate the safety of code generated by large language models in real-world tasks. The benchmark, called SUSV...
Researchers propose a method called PonderTTT for adaptive compute allocation in large language models. This approach uses self-supervised reconstruct...
Researchers have developed a new approach to translating natural language questions into SQL queries, called Text-to-SQL. They fine-tuned a large lang...
Researchers have proposed a new attention mechanism called STS that efficiently reduces the computational cost of processing large language models. Th...
Researchers have developed a method to audit the safety of Large Language Models (LLMs) without requiring access to user prompts or model internals. T...
Researchers have found that large language models (LLMs) can 'remember' and reproduce specific code logic from their training data in ways that tradit...