English
Related papers

Related papers: SAHOO: Safeguarded Alignment for High-Order Optimi…

200 papers

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

The growing prevalence of drift and shocks in modern decision environments exposes a gap between classical optimization theory and real-world practice. Standard models assume fixed objectives, yet organizations from hospitals to power grids…

Computational Finance · Quantitative Finance 2025-09-18 JINHO CHA

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

Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not…

Optimization and Control · Mathematics 2021-12-13 Yafei Wang , Bo Pan , Wei Tu , Peng Liu , Bei Jiang , Chao Gao , Wei Lu , Shangling Jui , Linglong Kong

Achieving top-notch performance in Intelligent Transportation detection is a critical research area. However, many challenges still need to be addressed when it comes to detecting in a cross-domain scenario. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Tong Xiang , Hongxia Zhao , Fenghua Zhu , Yuanyuan Chen , Yisheng Lv

Self-adaptation has been proposed as a mechanism to counter complexity in control problems of technical systems. A major driver behind self-adaptation is the idea to transfer traditional design-time decisions to runtime and into the…

Multiagent Systems · Computer Science 2019-05-13 Stefan Rudolph , Sven Tomforde , Jörg Hähner

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Computation and Language · Computer Science 2024-11-15 Somanshu Singla , Zhen Wang , Tianyang Liu , Abdullah Ashfaq , Zhiting Hu , Eric P. Xing

Bayesian Optimization (BO) is a class of surrogate-based, sample-efficient algorithms for optimizing black-box problems with small evaluation budgets. The BO pipeline itself is highly configurable with many different design choices…

Machine Learning · Computer Science 2023-07-03 Carolin Benjamins , Elena Raponi , Anja Jankovic , Carola Doerr , Marius Lindauer

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has…

Computation and Language · Computer Science 2025-03-31 Xuying Li , Zhuo Li , Yuji Kosuga , Victor Bian

A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only…

Computation and Language · Computer Science 2022-04-15 Utku Norman , Tanvi Dinkar , Barbara Bruno , Chloé Clavel

Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that…

Machine Learning · Computer Science 2026-05-26 Wenlong Deng , Jiaji Huang , Kaan Ozkara , Yushu Li , Christos Thrampoulidis , Xiaoxiao Li , Youngsuk Park

Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning extended time horizons. While learning-based Rolling Horizon Optimization~(RHO) has emerged as…

Machine Learning · Computer Science 2026-04-14 Yujie Li , Jiuniu Wang , Mugen Peng , Guangzuo Li , Wenjia Xu

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on…

Optimization and Control · Mathematics 2021-07-05 Tianlong Chen , Xiaohan Chen , Wuyang Chen , Howard Heaton , Jialin Liu , Zhangyang Wang , Wotao Yin

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Machine Learning · Computer Science 2026-05-07 Etienne Gauthier , Francis Bach , Michael I. Jordan

Randomized smoothing is a recently proposed defense against adversarial attacks that has achieved SOTA provable robustness against $\ell_2$ perturbations. A number of publications have extended the guarantees to other metrics, such as…

Machine Learning · Computer Science 2020-10-15 Jeet Mohapatra , Ching-Yun Ko , Tsui-Wei Weng , Pin-Yu Chen , Sijia Liu , Luca Daniel

Autoregressive scientific forecasters often enforce physical or structural constraints by repairing each predicted state before feeding it back into the model. However, it remains unclear when stronger physical rule enforcement becomes…

Machine Learning · Computer Science 2026-05-12 Bum Jun Kim

Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Yuming Zhang , Dongzhi Guan , Shouxin Zhang , Junhao Su , Yunzhi Han , Jiabin Liu

Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software,…

Artificial Intelligence · Computer Science 2015-02-24 Roman V. Yampolskiy

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers…

Computation and Language · Computer Science 2026-01-12 Xueyun Tian , Minghua Ma , Bingbing Xu , Nuoyan Lyu , Wei Li , Heng Dong , Zheng Chu , Yuanzhuo Wang , Huawei Shen

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Artificial Intelligence · Computer Science 2026-05-12 Dongcheng Zhang , Yi Zhang , Yuxin Chen , An Zhang , Xiang Wang , Chaochao Lu