Adding a next-latent prediction loss to next-token training makes transformer hidden states more predictive of future tokens and improves planning/reasoning on small benchmarks.
Ilya Loshchilov and Frank Hutter
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Next-Latent Prediction Transformers Learn Compact World Models
Adding a next-latent prediction loss to next-token training makes transformer hidden states more predictive of future tokens and improves planning/reasoning on small benchmarks.