English
Related papers

Related papers: Harmony in Divergence: Towards Fast, Accurate, and…

200 papers

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Artificial Intelligence · Computer Science 2026-04-14 Shaocong Ma , Peiran Yu , Heng Huang

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

We propose the intermediate direct preference optimization (DPO) method to calculate the DPO loss at selected intermediate layers as an auxiliary loss for finetuning large language models (LLMs). The conventional DPO method fine-tunes a…

Computation and Language · Computer Science 2024-08-07 Atsushi Kojima

Zeroth-order (ZO) method has been shown to be a powerful method for solving the optimization problem where explicit expression of the gradients is difficult or infeasible to obtain. Recently, due to the practical value of the constrained…

Optimization and Control · Mathematics 2024-09-04 Wanli Shi , Hongchang Gao , Bin Gu

Zeroth-order (ZO) optimization is widely used to handle challenging tasks, such as query-based black-box adversarial attacks and reinforcement learning. Various attempts have been made to integrate prior information into the gradient…

Machine Learning · Statistics 2021-11-09 Shuyu Cheng , Guoqiang Wu , Jun Zhu

First-order optimization methods, such as SGD and Adam, are widely used for training large-scale deep neural networks due to their computational efficiency and robust performance. However, relying solely on gradient information, these…

Machine Learning · Computer Science 2025-07-29 Yue Hu , Zanxia Cao , Yingchao Liu

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Machine Learning · Computer Science 2026-02-13 Yihan Du , Seo Taek Kong , R. Srikant

As distributed optimization scales to meet the demands of Large Language Model (LLM) training, hardware failures become increasingly non-negligible. Existing fault-tolerant training methods often introduce significant computational or…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-21 Rizhen Hu , Yutong He , Ran Yan , Mou Sun , Binghang Yuan , Kun Yuan

Rank-based zeroth-order (ZO) optimization -- which relies only on the ordering of function evaluations -- offers strong robustness to noise and monotone transformations, and underlies many successful algorithms such as CMA-ES, natural…

Machine Learning · Computer Science 2025-12-19 Haishan Ye

In this letter, we first propose a \underline{Z}eroth-\underline{O}rder c\underline{O}ordinate \underline{M}ethod~(ZOOM) to solve the stochastic optimization problem over a decentralized network with only zeroth-order~(ZO) oracle feedback…

Optimization and Control · Mathematics 2022-10-11 Shengjun Zhang , Tan Shen , Hongwei Sun , Yunlong Dong , Dong Xie , Heng Zhang

The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task…

Machine Learning · Computer Science 2026-03-31 Mayank Jha

Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects can be fragile: lightweight post-alignment manipulations,…

Artificial Intelligence · Computer Science 2026-05-29 Zhihao Liu , Yifan Wu , Jian Lou , Di Wang , Yuxi Zhou , Yuke Hu

Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on…

Machine Learning · Computer Science 2025-08-19 Manning Zhu , Songtao Guo , Pengzhan Zhou , Yansong Ning , Chang Han , Dewen Qiao

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

Artificial Intelligence · Computer Science 2024-10-25 Yibo Miao , Bofei Gao , Shanghaoran Quan , Junyang Lin , Daoguang Zan , Jiaheng Liu , Jian Yang , Tianyu Liu , Zhijie Deng

Instruction-following is particularly crucial for large language models (LLMs) to support diverse user requests. While existing work has made progress in aligning LLMs with human preferences, evaluating their capabilities on instruction…

Artificial Intelligence · Computer Science 2024-07-08 Zihui Gu , Xingwu Sun , Fengzong Lian , Zhanhui Kang , Cheng-Zhong Xu , Ju Fan

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

Artificial Intelligence · Computer Science 2024-10-23 Pietro Bernardelle , Gianluca Demartini

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models…

Artificial Intelligence · Computer Science 2025-09-24 Xia Jiang , Yaoxin Wu , Minshuo Li , Zhiguang Cao , Yingqian Zhang

We consider the problem of minimizing a high-dimensional objective function, which may include a regularization term, using (possibly noisy) evaluations of the function. Such optimization is also called derivative-free, zeroth-order, or…

Optimization and Control · Mathematics 2023-03-20 HanQin Cai , Daniel Mckenzie , Wotao Yin , Zhenliang Zhang

Recent research explores optimization using large language models (LLMs) by either iteratively seeking next-step solutions from LLMs or directly prompting LLMs for an optimizer. However, these approaches exhibit inherent limitations,…

Optimization and Control · Mathematics 2024-03-06 Zeyuan Ma , Hongshu Guo , Jiacheng Chen , Guojun Peng , Zhiguang Cao , Yining Ma , Yue-Jiao Gong

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

Machine Learning · Computer Science 2026-05-25 Miria Feng , Mert Pilanci