MarCos modifies transformers to perform continuous multi-step reasoning by mapping thought-level continuous states directly to next-thought distributions, achieving substantial wall-clock speedups on math problems.
The training batch size is 256, and both training phases run for 10 epochs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Thinking by Markov Chain of Continuous Thoughts
MarCos modifies transformers to perform continuous multi-step reasoning by mapping thought-level continuous states directly to next-thought distributions, achieving substantial wall-clock speedups on math problems.