paper-with-me

홈 › Papers

Advancing Sequential Numerical Prediction in Autoregressive Models

2025-05-19 · Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. This paper introduces Numerical Token Integrity Loss (NTIL) to address this gap. NTIL operates at two levels: (1) token-level, where it extends the Earth Mover's Distance (EMD) to preserve ordinal relationships between numerical values, and (2) sequence-level, where it penalizes the overall discrepancy between the predicted and actual sequences. This dual approach improves numerical prediction and integrates effectively with LLMs/MLLMs. Extensive experiments show significant performance improvements with NTIL.

📄 PDF Abstract BibTeX arXiv:2505.13077

Code (1)

xfey/ntil 공식 구현 pytorch

Tasks

Prediction

Similar Papers 제목 키워드 기반

Visual Self-Refinement for Autoregressive Models

2025-10-01 · Jiamian Wang, Ziqi Zhou, Chaithanya Kumar Mummadi, Sohail Dianat 외 arxiv

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token predicti…

Comparative Study of Neural Surrogate Architectures for Autoregressive Prediction of Internal Battery States

2026-06-18 · Gihyun Lee, Thorben Menne, Simon Olma, Jakob Hilgert 외 arxiv

The Doyle-Fuller-Newman (DFN) model resolves internal electrochemical states in lithium-ion batteries with high fidelity. However, the numerical solution of its governing equations is computationally prohibitive for real…

Autoregressive Generation Strategies for Top-K Sequential Recommendations

2024-09-26 · Anna Volodkevich, Danil Gusak, Anton Klenitskiy, Alexey Vasilev

The goal of modern sequential recommender systems is often formulated in terms of next-item prediction. In this paper, we explore the applicability of generative transformer-based models for the Top-K sequential recommen…

Recommendation SystemsSequential Recommendation

Implicit Stacked Autoregressive Model for Video Prediction

2023-03-14 · Minseok Seo, Hakjin Lee, Doyi Kim, Junghoon Seo

Future frame prediction has been approached through two primary methods: autoregressive and non-autoregressive. Autoregressive methods rely on the Markov assumption and can achieve high accuracy in the early stages of pr…

modelPredictionVideo PredictionWeather Forecasting

On the Efficient Marginalization of Probabilistic Sequence Models

2024-03-06 · Alex Boyd

Real-world data often exhibits sequential dependence, across diverse domains such as human behavior, medicine, finance, and climate modeling. Probabilistic methods capture the inherent uncertainty associated with predict…

Point Processes