17 citations · 45 across the 14 of their papers we have counts for
3 papers · 1 filter
Language Self-Play For Data-Free Training
Jakub Grudzien Kuba, Mengting Gu, Qi Ma +3
Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fund…
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat +2
In cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Analogously, Large Language Models (L…
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert, Sainbayar Sukhbaatar, DiJia Su +4
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decisio…