English
Related papers

Related papers: Option-Order Randomisation Reveals a Distributiona…

200 papers

We explore the probabilistic foundations of shared control in complex dynamic environments. In order to do this, we formulate shared control as a random process and describe the joint distribution that governs its behavior. For…

Robotics · Computer Science 2015-08-10 Pete Trautman

We study a $d$-dimensional random walk with exponentially distributed increments conditioned so that the components stay ordered (in the sense of Doob). We find explicitly a positive harmonic function $h$ for the killed process and then…

Probability · Mathematics 2023-09-06 Denis Denisov , Will FitzGerald

Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B)…

Machine Learning · Computer Science 2026-03-05 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of…

Computation and Language · Computer Science 2024-08-16 Aiwei Liu , Haoping Bai , Zhiyun Lu , Xiang Kong , Simon Wang , Jiulong Shan , Meng Cao , Lijie Wen

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Zhou Jiang , Yandong Wen , Zhen Liu

Recent advancements in LLMs have revolutionized motion generation models in embodied applications. While LLM-type auto-regressive motion generation models benefit from training scalability, there remains a discrepancy between their token…

Artificial Intelligence · Computer Science 2025-03-27 Ran Tian , Kratarth Goel

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…

Artificial Intelligence · Computer Science 2026-01-09 Fady Rezk , Yuangang Pan , Chuan-Sheng Foo , Xun Xu , Nancy Chen , Henry Gouk , Timothy Hospedales

Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and…

Machine Learning · Computer Science 2026-03-19 Benjamin Hudson , Laurent Charlin , Emma Frejinger

Safety-aligned LLMs go through refusal training to reject harmful requests, but whether these mechanisms remain effective under emotionally charged stimuli is unexplored. We introduce FreakOut-LLM, a framework investigating whether…

Cryptography and Security · Computer Science 2026-04-08 Daniel Kuznetsov , Ofir Cohen , Karin Shistik , Rami Puzis , Asaf Shabtai

Automated matching engines execute millions of orders per session, yet systematic asymmetries in latency, order size, and market access compound into persistent execution disparities that erode participant trust. We formulate provably fair…

Computer Science and Game Theory · Computer Science 2026-04-09 Zehua Cheng , Zhipeng Wang , Wei Dai , Wenhu Zhang , Vadzim Mahilny , David Shi , Elena Jia , Jiahao Sun

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static…

Machine Learning · Computer Science 2026-03-18 Zeyu Zhang , Xiangxiang Dai , Ziyi Han , Xutong Liu , John C. S. Lui

We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation,…

Machine Learning · Computer Science 2024-11-12 Zichen Liu , Changyu Chen , Chao Du , Wee Sun Lee , Min Lin

This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Xiaoyu Yang , En Yu , Wei Duan , Jie Lu

We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward model. SPO optimizes model outputs directly over a…

Machine Learning · Computer Science 2024-10-07 Arsalan Sharifnassab , Saber Salehkaleybar , Sina Ghiassian , Surya Kanoria , Dale Schuurmans

Diffusion language models (DLMs) have recently emerged as competitive alternatives to autoregressive (AR) language models, yet differences in their activation dynamics remain poorly understood. We characterize these dynamics in LLaDA-8B and…

Machine Learning · Computer Science 2026-05-12 Alexander Conzelmann , Albert Catalan-Tatjer , Shiwei Liu

In this paper, we address the problem of robust stability for uncertain sampled-data systems controlled by a discrete-time disturbance observer (DT-DOB). Unlike most of previous works that rely on the small-gain theorem, our approach is to…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Gyunghoon Park , Chanhwa Lee , Youngjun Joo , Hyungbo Shim

Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, and alignment. Using pairs of preferred and dispreferred…

Computation and Language · Computer Science 2024-07-04 Arka Pal , Deep Karkhanis , Samuel Dooley , Manley Roberts , Siddartha Naidu , Colin White

Exchangeability-based martingale diagnostics have been used to question Bayesian explanations of transformer in-context learning. We show that these violations are compatible with Bayesian/MDL behavior once we account for a basic…

Machine Learning · Statistics 2026-02-24 Leon Chlon , Zein Khamis , Maggie Chlon , Mahdi El Zein , MarcAntonio M. Awada

We study the probability distribution of entanglement in the Quantum Symmetric Simple Exclusion Process, a model of fermions hopping with random Brownian amplitudes between neighboring sites. We consider a protocol where the system is…

Statistical Mechanics · Physics 2021-07-30 Denis Bernard , Lorenzo Piroli