AdaMTP is proposed, an adaptive training paradigm that dynamically aligns the prediction horizon with the intrinsic predictability of the sequence, and consistently outperforms standard MTP in both task performance and inference speedup.
Abstract
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several future tokens in parallel to enrich its supervision signal and accelerate inference. However, existing training frameworks adopt a rigid, fixed-length prediction horizon, disregarding the highly non-uniform information density of natural language and code. Forcing the auxiliary heads to predict across high-entropy semantic boundaries injects noisy, conflicting training signals; because these heads share the backbone's latent representations, the resulting gradients backpropagate and interfere with the model's core capabilities. We propose AdaMTP, an adaptive training paradigm that dynamically aligns the prediction horizon with the intrinsic predictability of the sequence. At its core, an entropy-based segmentation algorithm leverages the base model to detect sudden surges in uncertainty as semantic boundaries, partitioning sequences into variable-length groups. Each token is assigned an adaptive prediction depth, and a dynamically masked MTP objective suppresses the loss for predictions that cross these boundaries, attenuating the noisy gradients that degrade the backbone. Across mathematical reasoning, code generation, and general benchmarks on three backbones (Llama-3.1-8B, Qwen-2.5-7B, Gemma-3-12B), AdaMTP consistently outperforms standard MTP in both task performance and inference speedup.
Hierarchical Latent Prediction (HiLP) is introduced, which introduces an auxiliary higher-level abstract latent to help reduce the error accumulation effect in latent-space rollouts and can lead to longer-horizon coherent belief state representation.
Changyan Shi, Tim Pearce, Manan Tomar et al.· 0 citations
A statistical framework connecting token prediction with representation geometry, encoder approximation, and downstream performance is developed, introducing a self-consistency principle showing that repeated applications of a shared representation block can progressively refine the contextual representation without introducing additional block parameters.
The experimental results show that even 130M-parameter models benefit from including the MTP task in the pre-training objective, and hold even under severe data constraints, as demonstrated on both zero-shot benchmarks and downstream tasks.
Pretrained language models (PLMs) have established state-of-the-art performance across diverse natural language understanding (NLU) tasks. This study reveals that seman-tic-rich explanations of lexical units can effectively guide PLM learning processes. We propose a novel language understanding enhancement method with token interpretation (LUETI) that addresses two critical limitations in conventional PLMs: Incomplete token semantics caused by isolated contextual learning and insufficient semantic encoding in embedding matrices. LUETI operates through dual mechanisms, augmenting token represen-tations by integrating hidden states with corresponding token interpretations and refining embedding spaces using interpretation-derived semantic vectors for token prediction. LUETI, which is implemented as a plug-in module for standard architectures, demonstrates significant improvements on BERT and GLM, achieving average performance gains of 3.36% and 4.87% respectively on the SuperGLUE benchmark with equivalent parameters and training data. Note that LUETI-equipped models attain comparable performance to baseline PLMs using only 60% of pretraining data. Findings establish token interpretation as a computationally efficient but semantically powerful enhancement strategy for language model pretraining.
Tianyi Chen, Yashen Wang, Huan Chang et al.· IEEE/CAA Journal of Automati...· 0 citations
We aim to improve frozen DINOv3 dense-prediction models under distribution shift by adding inference computation inside the visual backbone, without changing model weights, task adapters, or prediction heads. The challenge is that repeated transformer-block computation must refine dense features without disrupting the pairwise patch relations that DINOv3 uses to preserve spatial structure. We introduce GramLoop, a training-free framework that replays a short transformer window and controls each replay through final-layer cosine-Gram consistency. Each proposal is propagated through the frozen suffix, measured against the standard DINOv3 trajectory, and accepted through a patchwise gate at the replay-window endpoint. Across object detection and semantic segmentation under corruptions, perturbations, and natural shifts, GramLoop improves all five shifted benchmarks over the paired DINOv3 baseline. On COCO-O, it improves mAP by +0.252 and Effective Robustness by +0.250, while preserving clean ADE20K performance. Code will be released at https://github.com/cheyan9/GramLoop.
Yang Chen, Can-Yu Shen, Xin-Zhe Rao et al.· 0 citations
This work proposes NONTP, extending NTP's signal coverage along both dimensions through two auxiliary objectives, and analyses each component contributes independently, with gradient conflict analyzed as a direction for future work.
Changhao Li, Shuli Wang, Junwei Yin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
