Sajad Norouzi

Yonggan Fu, Lexington Whalen, Abhinav Garg et al.

We introduce Nemotron-Labs-Diffusion, a tri-mode language model (LM) that unifies AR, diffusion, and self-speculation decoding within a single architecture. Trained with a joint AR-diffusion objective, Nemotron-Labs-Diffusion can switch modes to sustain high throughput across deployment settings and concurrency levels. Our study shows that (1) AR and diffusion objectives are complementary: diffusion improves lookahead planning, while AR provides left-to-right linguistic priors. (2) In self-speculation mode, diffusion drafts while AR verifies, outperforming multi-token prediction (MTP) methods in both acceptance rate and real-device efficiency. (3) A speed-of-light analysis further demonstrates diffusion's long-term potential, with up to 76.5% more tokens per forward pass than self-speculation under an optimal sampler. Scaling to 3B, 8B, and 14B parameters, our Nemotron-Labs-Diffusion family, including base, instruct, and vision-language models, consistently outperforms state-of-the-art open-source AR and diffusion LMs in both accuracy and speed. For example, Nemotron-Labs-Diffusion-8B decodes 6x more tokens per forward than Qwen3-8B with comparable accuracy, translating to 4x higher throughput on SPEED-Bench with SGLang on a GB200 GPU.

Sajad Norouzi, Rasa Hosseinzadeh, Felipe Perez et al.

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease the number of required steps to reach a certain translation quality. The distilled model enjoys the computational benefits of early iterations while preserving the enhancements from several iterative steps. DiMS relies on two models namely student and teacher. The student is optimized to predict the output of the teacher after multiple decoding steps while the teacher follows the student via a slow-moving average. The moving average keeps the teacher's knowledge updated and enhances the quality of the labels provided by the teacher. During inference, the student is used for translation and no additional computation is added. We verify the effectiveness of DiMS on various models obtaining 7.8 and 12.9 BLEU points improvements in single-step translation accuracy on distilled and raw versions of WMT'14 De-En.

Sajad Norouzi, Keyi Tang, Yanshuai Cao

Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks. As a result, models for this application usually need additional prior knowledge to be built into the architecture or algorithm. The increased dependency on human experts hinders automation and raises the development and maintenance costs in practice. This work investigates whether a generic transformer-based seq2seq model can achieve competitive performance with minimal code-generation-specific inductive bias design. By exploiting a relatively sizeable monolingual corpus of the target programming language, which is cheap to mine from the web, we achieved 81.03% exact match accuracy on Django and 32.57 BLEU score on CoNaLa. Both are SOTA to the best of our knowledge. This positive evidence highlights a potentially easier path toward building accurate semantic parsers in practice.

Sajad Norouzi, David J. Fleet, Mohammad Norouzi

We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models. Exemplar VAE is a variant of VAE with a non-parametric prior in the latent space based on a Parzen window estimator. To sample from it, one first draws a random exemplar from a training set, then stochastically transforms that exemplar into a latent code and a new observation. We propose retrieval augmented training (RAT) as a way to speed up Exemplar VAE training by using approximate nearest neighbor search in the latent space to define a lower bound on log marginal likelihood. To enhance generalization, model parameters are learned using exemplar leave-one-out and subsampling. Experiments demonstrate the effectiveness of Exemplar VAEs on density estimation and representation learning. Importantly, generative data augmentation using Exemplar VAEs on permutation invariant MNIST and Fashion MNIST reduces classification error from 1.17% to 0.69% and from 8.56% to 8.16%.