Papers

Filtered to interpretability · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

84 upvotes · 12 AUG 2026 · Mengru Wang, Junfeng Fang, Shuofei Qiao et al.

This paper introduces Mechanist, a system that uses AI to discover the underlying mechanisms of intelligence, allowing for better understanding and control of AI models. Practitioners might care because Mechanist can identify safety risks and improve model performance.

AImechanistic discoveryinterpretabilitycausal reasoningscientific instrumentationagent-based systems