# Multi-Token Prediction Needs Registers

arXiv: https://arxiv.org/abs/2505.10518 · HTML: https://mlsanity.com/paper/2505.10518/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 58 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 30 of 45)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)

## Built on by (most cited first, 16 of 16)

- [Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential](https://mlsanity.com/paper/2507.11851/) (2025)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries](https://mlsanity.com/paper/2510.14751/) (2025)
- [Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling](https://mlsanity.com/paper/2509.01649/) (2025)
- [The State-Prediction Separation Hypothesis](https://mlsanity.com/paper/2607.01218/) (2026)
- [Mirai: Autoregressive Visual Generation Needs Foresight](https://mlsanity.com/paper/2601.14671/) (2026)
- [Efficient Document Parsing via Parallel Token Prediction](https://mlsanity.com/paper/2603.15206/) (2026)
- [Thinking into the Future: Latent Lookahead Training for Transformers](https://mlsanity.com/paper/2603.20219/) (2026)
- [MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration](https://mlsanity.com/paper/2604.14889/) (2026)
- [Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction](https://mlsanity.com/paper/2605.19975/) (2026)
- [Enhancing Audio Reasoning via Semantic Summary Prediction](https://mlsanity.com/paper/2609.20849/) (2026)
- [Temporal Guidance for Large Language Models](https://mlsanity.com/paper/2601.21744/) (2026)
- [Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models](https://mlsanity.com/paper/2602.14386/) (2026)
- [Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing](https://mlsanity.com/paper/2603.17942/) (2026)
- [How Transformers Learn to Plan via Multi-Token Prediction](https://mlsanity.com/paper/2604.11912/) (2026)
- [EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment](https://mlsanity.com/paper/2608.14011/) (2026)

## Abstract (arXiv)

Multi-token prediction has emerged as a promising objective for improving language model pretraining, but its benefits have not consistently generalized to other settings such as fine-tuning. In this paper, we propose MuToR, a simple and effective approach to multi-token prediction that interleaves learnable register tokens into the input sequence, each tasked with predicting future targets. Compared to existing methods, MuToR offers several key advantages: it introduces only a negligible number of additional parameters, requires no architectural changes--ensuring compatibility with off-the-shelf pretrained language models--and remains aligned with the next-token pretraining objective, making it especially well-suited for supervised fine-tuning. Moreover, it naturally supports scalable prediction horizons. We demonstrate the effectiveness and versatility of MuToR across a range of use cases, including supervised fine-tuning, parameter-efficient fine-tuning (PEFT), and pretraining, on challenging generative tasks in both language and vision domains. Our code will be available at: https://github.com/nasosger/MuToR.