conftrace_

mixing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vq-vae (1) alignment (1) chain-of-thoughts (1) on-policy data (1) hybrid representation (1) off-policy data (1) latent token (1) reasoning trace (1) language model (1) preference learning (1)

Papers

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning ICML 2025 Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning ICML 2025