paper-with-me

Papers

Dual-objective Language Models: Training Efficiency Without Overfitting

2025-12-16 · David Samuel, Lucas Georges Gabriel Charpentier arxiv

This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular approach, partly because of its training efficiency; however, that comes at the cost of sensitivity to overfitting. On the other hand, masked-diffusion models are less efficient to train while being more resilient to overfitting. In this work, we demonstrate that dual-objective training achieves the best of both worlds. To derive the optimal balance between both objectives, we train and evaluate 50 language models under varying levels of data repetition. We show that it is optimal to combine both objectives under all evaluated settings and that the optimal balance is similar whether targeting autoregressive or masked-diffusion downstream performance.

📄 PDF Abstract BibTeX arXiv:2512.14549

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FilFL: Client Filtering for Optimized Client Participation in Federated Learning

2023-02-13 · Fares Fourati, Salma Kharrat, Vaneet Aggarwal, Mohamed-Slim Alouini 외

Federated learning, an emerging machine learning paradigm, enables clients to collaboratively train a model without exchanging local data. Clients participating in the training process significantly impact the convergenc…

Federated Learning

EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning

2025-05-05 · Lingxiao Kong, Cong Yang, Susanne Neufang, Oya Deniz Beyan 외

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including complex objective balancing, low…

Ensemble LearningLarge Language ModelMulti-Objective Reinforcement LearningReinforcement Learning (RL)

A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning

2023-12-27 · Hanlin Gu, Xinyuan Zhao, Gongxi Zhu, Yuxing Han 외

Federated learning (FL) enables multiple clients to collaboratively learn a shared model without sharing their individual data. Concerns about utility, privacy, and training efficiency in FL have garnered significant res…

Federated Learning

Duality Models: An Embarrassingly Simple One-step Generation Paradigm

2026-02-04 · Peng Sun, Xinyi Shang, Tao Lin, Zhiqiang Shen arxiv

Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ along…

DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training

2022-03-17 · Findings (ACL) 2022 5 · Luyang Huang, guocheng niu, Jiachen Liu, Xinyan Xiao 외

Due to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we prop…

DenoisingImage CaptioningImage GenerationText Generation+2