Papers with Code paper Oct 5

Learning to Learn a Language

We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic prior. Given a prefix of real ...

Papers with Code paper Oct 5

What Matters for Latent Reasoning with Flow Matching

Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought must meet five requirements:...

Papers with Code paper Oct 5

Empirical Variational Autoencoder

We present Empirical Variational Autoencoder, a general generative framework for continuous-valued (i.e., non-vector-quantized) sequences. EVA is based on the evidence lower bound ...