English
Related papers

Related papers: Test-Time Alignment via Hypothesis Reweighting

200 papers

A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve…

Machine Learning · Computer Science 2024-02-28 Zihao Li , Xiang Ji , Minshuo Chen , Mengdi Wang

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the…

Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable…

Machine Learning · Computer Science 2022-05-30 Dominique Mercier , Andreas Dengel , Sheraz Ahmed

Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback (RLHF), are typically cast as optimizing a tradeoff between…

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly…

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang

Pairwise comparisons are a well-known method for modelling of the subjective preferences of a decision maker. A popular implementation of the method is based on solving an eigenvalue problem for M - the matrix of pairwise comparisons. This…

Discrete Mathematics · Computer Science 2015-09-25 Konrad Kułakowski

The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…

Machine Learning · Computer Science 2025-04-29 Amogh Joshi , Adarsh Kumar Kosta , Kaushik Roy

In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from…

Machine Learning · Computer Science 2024-08-09 Heewoong Choi , Sangwon Jung , Hongjoon Ahn , Taesup Moon

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot…

Computation and Language · Computer Science 2024-10-29 Yuchen Zhuang , Haotian Sun , Yue Yu , Rushi Qiang , Qifan Wang , Chao Zhang , Bo Dai

Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Huan Liu , Julia Qi , Zhenhao Li , Mohammad Hassanpour , Yang Wang , Konstantinos Plataniotis , Yuanhao Yu

Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm for sparse reward functions. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in the episode. Virtual…

Machine Learning · Computer Science 2021-03-09 Binyamin Manela , Armin Biess

We study hypothesis testing over a heterogeneous population of strategic agents with private information. Any single test applied uniformly across the population yields statistical error that is sub-optimal relative to the performance of an…

Computer Science and Game Theory · Computer Science 2025-10-27 Flora C. Shi , Martin J. Wainwright , Stephen Bates

Reinforcement learning from human feedback (RLHF) with reward models has advanced alignment of generative models to human aesthetic and perceptual preferences. However, jointly optimizing multiple rewards often incurs an alignment tax,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chieh-Yun Chen , Zhonghao Wang , Qi Chen , Zhifan Ye , Min Shi , Yue Zhao , Yinan Zhao , Hui Qu , Wei-An Lin , Yiru Shen , Ajinkya Kale , Irfan Essa , Humphrey Shi

Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as…

Computation and Language · Computer Science 2025-06-09 Michael J Ryan , Omar Shaikh , Aditri Bhagirath , Daniel Frees , William Held , Diyi Yang

In this paper, we propose Hard Person Identity Mining (HPIM) that attempts to refine the hard example mining to improve the exploration efficacy in person re-identification. It is motivated by following observation: the more attributes some…

Computer Vision and Pattern Recognition · Computer Science 2019-08-07 Xiao Wang , Ziliang Chen , Rui Yang , Bin Luo , Jin Tang

Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals who have diverse viewpoints that may conflict with each…

Machine Learning · Computer Science 2024-03-11 Huiying Zhong , Zhun Deng , Weijie J. Su , Zhiwei Steven Wu , Linjun Zhang

In many clinical contexts, estimating effects of treatment in time-to-event data is complicated not only by confounding, censoring, and heterogeneity, but also by the presence of a cured subpopulation in which the event of interest never…

Methodology · Statistics 2026-02-06 Yuqi Li , Quinn Lanners , Matthew M. Engelhard

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…

Machine Learning · Computer Science 2026-02-04 Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Computation and Language · Computer Science 2025-11-03 Fenia Christopoulou , Ronald Cardenas , Gerasimos Lampouras , Haitham Bou-Ammar , Jun Wang
‹ Prev 1 4 5 6 7 8 10 Next ›