English
Related papers

Related papers: Zero-Order Optimization for LLM Fine-Tuning via Le…

200 papers

Policy gradient (PG) algorithms have been widely used in reinforcement learning (RL). However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample…

Machine Learning · Computer Science 2021-07-06 Hao Sun , Ziping Xu , Yuhang Song , Meng Fang , Jiechao Xiong , Bo Dai , Bolei Zhou

Zeroth-order optimization (ZOO) is an important framework for stochastic optimization when gradients are unavailable or expensive to compute. A potential limitation of existing ZOO methods is the bias inherent in most gradient estimators…

Machine Learning · Computer Science 2025-10-24 Shaocong Ma , Heng Huang

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…

Machine Learning · Computer Science 2026-05-07 Xinyu Wang , Changzhi Sun , Yuanbin Wu , Xiaoling Wang

Zeroth-order (ZO) optimization has emerged as a promising alternative to gradient-based backpropagation methods, particularly for black-box optimization and large language model (LLM) fine-tuning. However, ZO methods often suffer from slow…

Machine Learning · Computer Science 2025-05-26 Sihwan Park , Jihun Yun , SungYub Kim , Souvik Kundu , Eunho Yang

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its…

Machine Learning · Computer Science 2025-10-21 Kangqi Ni , Zhen Tan , Zijie Liu , Pingzhi Li , Tianlong Chen

Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other domains. Yet, deploying LLM-driven planning in the physical world demands strict adherence to…

Robotics · Computer Science 2026-05-27 Yunhao Yang , Junyuan Hong , Gabriel Jacob Perin , Zhiwen Fan , Li Yin , Zhangyang Wang , Ufuk Topcu

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Machine Learning · Computer Science 2026-05-12 Minmin Zhang , Sina Aghaei , Soroush Saghafian

Reasoning over procedural sequences, where the order of steps directly impacts outcomes, is a critical capability for large language models (LLMs). In this work, we study the task of reconstructing globally ordered sequences from shuffled…

Computation and Language · Computer Science 2025-11-18 Adrita Anika , Md Messal Monem Miah

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Knowledge distillation (KD) has been a predominant method for compressing Large Language Models (LLMs). In this paper, we first revisit KD and Low-Rank Adaption (LoRA) and demonstrate that they follow the same paradigm. Inspired by this…

Computation and Language · Computer Science 2025-02-26 Runming Yang , Taiqiang Wu , Jiahao Wang , Pengfei Hu , Yik-Chung Wu , Ngai Wong , Yujiu Yang

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet general knowledge is often insufficient for specific…

Machine Learning · Computer Science 2025-10-01 Xue Yan , Zijing Ou , Mengyue Yang , Yan Song , Haifeng Zhang , Yingzhen Li , Jun Wang

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Machine Learning · Computer Science 2025-04-04 Abhay Kumar , Louis Owen , Nilabhra Roy Chowdhury , Fabian Güra

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Recent studies have demonstrated the great potential of Large Language Models (LLMs) serving as zero-shot relevance rankers. The typical approach involves making comparisons between pairs or lists of documents. Although effective, these…

Information Retrieval · Computer Science 2023-11-06 Weiwei Sun , Zheng Chen , Xinyu Ma , Lingyong Yan , Shuaiqiang Wang , Pengjie Ren , Zhumin Chen , Dawei Yin , Zhaochun Ren

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similarity to the original lead compound. Despite recent advances,…

Machine Learning · Computer Science 2025-09-29 Ziqing Wang , Yibo Wen , William Pattie , Xiao Luo , Weimin Wu , Jerry Yao-Chieh Hu , Abhishek Pandey , Han Liu , Kaize Ding

Large language models (LLMs) have recently been proposed as general-purpose agents for experimental design, with claims that they can perform in-context experimental design. We evaluate this hypothesis using both open- and closed-source…

Machine Learning · Computer Science 2025-09-29 Rushil Gupta , Jason Hartford , Bang Liu

Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation models, achieving stronger performance than heuristic rules.…

Computation and Language · Computer Science 2025-10-15 Zeyu Yang , Satoshi Nakamura

Zeroth-order (ZO) optimization with ordinal feedback has emerged as a fundamental problem in modern machine learning systems, particularly in human-in-the-loop settings such as reinforcement learning from human feedback, preference…

Optimization and Control · Mathematics 2025-12-23 Haishan Ye

Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely on heuristically hand-crafted metrics, potentially leading…

Machine Learning · Computer Science 2025-07-04 Yuan Gao , Zujing Liu , Weizhong Zhang , Bo Du , Gui-Song Xia

Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While data selection has been widely studied, the strategic data organization for enhanced…

Artificial Intelligence · Computer Science 2026-05-29 Yalun Dai , Yangyu Huang , Tongshen Yang , Yonghan Wang , Xin Zhang , Wenshan Wu , Qihao Zhao , Hao Li , Yuanyuan Gao , Kim-Hui Yap , Scarlett Li