TESS 2: A Large-Scale Generalist Diffusion Language Model

We introduce TESS 2, a general instructionfollowing diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exceeds strong autoregressive (AR) models.We train TESS 2 by first adapting an AR model via continued pretraining with the usual cross-entropy as diffusion loss, and then performing further instruction tuning.We find that adaptation training as well as the choice of the base model is crucial for training good instruction-following diffusion models.Furthermore, we propose reward guidance, a novel and modular inference-time guidance procedure to align model outputs without needing to train the underlying model.Finally, we show that TESS 2 further improves with increased inference-time compute, highlighting the utility of diffusion LMs in having fine-grained controllability over the amount of compute used at inference time.Code and models are available at https://github.com/hamishivi/tess-2.