Multimodal Large Language Models

2 papers touch this idea.

Papers

AIs that play card games fail because they forget what they saw, not because they choose badly

Teaching image-reading AI to stop and run code when the math gets hard

Related concepts

Ideas that show up alongside Multimodal Large Language Models.

Adaptive Interleaved Reasoning Benchmark Design Closed-Loop Policy Evaluation Code-Augmented Reasoning Data Curation And Filtering Fine-Tuning On Policy Rollouts Memory And Observation Recall Non-Markov Games Numerical Computation Reinforcement Learning Spatial Reasoning Tool-Use In AI