Sign in Subscribe

Topic

machine learning

A collection of 13 issues

Tessera Protocol Enables AI Knowledge Transfer Across Architectures

The Tessera protocol is a new open-source initiative designed to facilitate AI-to-AI knowledge transfer across different architectures. It uses an activation-based approach, encoding learned knowledge into self-describing tokens that can be decoded by a receiving model via a Universal Hub Space

Framework Assesses AI Decisions in AutoML Pipelines

A new framework evaluates AI agent decisions within AutoML pipelines, addressing the complexities of multi-stage decision-making in automated machine learning systems. The Evaluation Agent (EA) assesses intermediate decisions along four dimensions: decision validity, reasoning consistency, mode

New Method Detects and Mitigates Reward Hacking in AI Models

Researchers have developed IR$^3$, a framework using Contrastive Inverse Reinforcement Learning (C-IRL) to detect and mitigate reward hacking in large language models. IR$^3$ reconstructs reward functions, identifies hacking signatures, and applies mitigation strategies to enhance AI alignment