English
Related papers

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

200 papers

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture…

Artificial Intelligence · Computer Science 2026-05-19 Zaiyi Zheng , Guanghui Min , Yaochen Zhu , Liang Wu , Liangjie Hong , Chen Chen , Jundong Li

Stochastic compositional optimization arises in many important machine learning tasks such as value function evaluation in reinforcement learning and portfolio management. The objective function is the composition of two expectations of…

Machine Learning · Statistics 2020-01-28 Huizhuo Yuan , Xiangru Lian , Ji Liu

Sequential Convex Programming (SCP) has recently seen a surge of interest as a tool for trajectory optimization. However, most available methods lack rigorous performance guarantees and they are often tailored to specific optimal control…

Optimization and Control · Mathematics 2019-03-04 Riccardo Bonalli , Abhishek Cauligi , Andrew Bylard , Marco Pavone

Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems that may exceed their own capabilities? Existing approaches…

Artificial Intelligence · Computer Science 2026-05-28 William Overman , Mohsen Bayati

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Machine Learning · Computer Science 2026-05-15 Matias Alvo , Daniel Russo , Yash Kanoria

Robotic systems operating in real-world environments inevitably encounter unobserved dynamics shifts during continuous execution, including changes in actuation, mass distribution, or contact conditions. When such shifts occur mid-episode,…

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Machine Learning · Computer Science 2025-10-07 Yoonjeon Kim , Doohyuk Jang , Eunho Yang

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Cryptography and Security · Computer Science 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

Hierarchical Instruction Following (HIF) refers to the problem of prompting large language models with a priority-ordered stack of instructions. Standard methods like RLHF and DPO typically fail in this problem since they mainly optimize…

Machine Learning · Computer Science 2026-03-18 Keru Chen , Jun Luo , Sen Lin , Yingbin Liang , Alvaro Velasquez , Nathaniel Bastian , Shaofeng Zou

Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations --…

Computation and Language · Computer Science 2025-05-12 Julia Shuieh , Prasann Singhal , Apaar Shanker , John Heyer , George Pu , Samuel Denton

Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We recast self-correction as a closed-loop feedback-control…

Artificial Intelligence · Computer Science 2026-05-05 Aofan Liu , Jingxiang Meng

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently…

Machine Learning · Computer Science 2026-02-13 Li He , Qiang Qu , He Zhao , Stephen Wan , Dadong Wang , Lina Yao , Tongliang Liu

Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…

Robotics · Computer Science 2025-02-26 Zhiyuan Zhou , Pranav Atreya , Abraham Lee , Homer Walke , Oier Mees , Sergey Levine

Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc…

Computation and Language · Computer Science 2024-10-15 Mingye Zhu , Yi Liu , Quan Wang , Junbo Guo , Zhendong Mao

We consider a smoothed online convex optimization (SOCO) problem with predictions, where the learner has access to a finite lookahead window of time-varying stage costs, but suffers a switching cost for changing its actions at each stage.…

Optimization and Control · Mathematics 2023-10-16 Spandan Senapati , Ashwin Shenai , Ketan Rajawat

Applications abound in which optimization problems must be repeatedly solved, each time with new (but similar) data. Analytic optimization algorithms can be hand-designed to provably solve these problems in an iterative fashion. On one…

Optimization and Control · Mathematics 2022-09-28 Howard Heaton , Xiaohan Chen , Zhangyang Wang , Wotao Yin

Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe…

Recursive self-modification is increasingly central in AutoML, neural architecture search, and adaptive optimization, yet no existing framework ensures that such changes are made safely. Godel machines offer a principled safeguard by…

Machine Learning · Computer Science 2025-10-14 Xuening Wu , Shenqin Yin , Yanlan Kang , Xinhang Zhang , Qianya Xu , Zeping Chen , Wenqiang Zhang

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…

Computation and Language · Computer Science 2025-08-27 Peng Ding , Wen Sun , Dailin Li , Wei Zou , Jiaming Wang , Jiajun Chen , Shujian Huang

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here, we focus on two prevalent methods used to align these…

Computation and Language · Computer Science 2023-10-26 Gabriel Mukobi , Peter Chatain , Su Fong , Robert Windesheim , Gitta Kutyniok , Kush Bhatia , Silas Alberti