AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction

arXiv:2608.00434 · cs.CL, cs.AI · Submitted 2026-08-01 · Read on arXiv

Ziqiang Cui, Han Shi, Bowei He, Yu Pan, Peiyang Liu, Shengyin Sun, Yankai Chen, Haoli Bai, Yichun Yin, Xue Liu, Chen Ma

cs.CL, cs.AI

Submitted: 2026-08-01

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Multi-Token Prediction — 16× in this paper
• Benchmark — 11× in this paper · explained in 2 episodes
• Core — 9× in this paper · explained in 2 episodes
• Pruning — 7× in this paper · explained in 4 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Speculative Decoding — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Transformers — 5× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Knowledge Distillation — 3× in this paper · explained in 15 episodes
• Latent Representation — 3× in this paper · explained in 2 episodes
• Latent Representations — 3× in this paper · explained in 3 episodes
• Quantization — 3× in this paper · explained in 15 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Papers — 2× in this paper · explained in 3 episodes
• Training Objective — 2× in this paper · explained in 3 episodes
• Conditional Independence — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 12 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 3 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes
• Latent Reasoning — 1× in this paper · explained in 3 episodes
• Next-Token Prediction — 1× in this paper
• Overfitting — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 13 episodes

Sources

• Program Synthesis with Large Language Models
• Large Concept Models: Language Modeling in a Sentence Representation Space
• Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction
• Measuring Mathematical Problem Solving With the MATH Dataset
• Accelerating Large Language Model Decoding with Speculative Sampling
• Distilling the Knowledge in a Neural Network
• Evaluating Large Language Models Trained on Code
• Generating Long Sequences with Sparse Transformers
• Training Verifiers to Solve Math Word Problems
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• SqueezeLLM: Dense-and-Sparse Quantization
• Multi-Token Prediction Needs Registers
• Better & Faster Large Language Models via Multi-token Prediction
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
• MiniLLM: On-Policy Distillation of Large Language Models
• Measuring Massive Multitask Language Understanding
• DeepSeek-V3 Technical Report
• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering