Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
The Topological Trouble With Transformers
Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu
Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tr…
cs.LG2025
Can foundation models actively gather information in interactive environments to test hypotheses?
Danny P. Sawyer, Nan Rosemary Ke, Hubert Soyer +9
Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments, a requirement for many real-world challenges. We evaluated these…