English
Related papers

Related papers: Alignment-Aware Decoding

200 papers

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

Auditory attention decoding (AAD) is a technique used to identify and amplify the talker that a listener is focused on in a noisy environment. This is done by comparing the listener's brainwaves to a representation of all the sound sources…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-14 Cong Han , Vishal Choudhari , Yinghao Aaron Li , Nima Mesgarani

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang

Recent direct preference alignment algorithms (DPA), such as DPO, have shown great promise in aligning large language models to human preferences. While this has motivated the development of many new variants of the original DPO loss,…

Computation and Language · Computer Science 2025-03-28 Kyle Richardson , Vivek Srikumar , Ashish Sabharwal

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Machine Learning · Computer Science 2026-05-18 Xiaoqiang Lin , Arun Verma , Zhongxiang Dai , Daniela Rus , See-Kiong Ng , Bryan Kian Hsiang Low

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…

Machine Learning · Computer Science 2024-08-21 Qingsong Zhao , Yi Wang , Shuguang Dou , Chen Gong , Yin Wang , Cairong Zhao

Direct Alignment Algorithms (DAAs) such as Direct Preference Optimization (DPO) have emerged as alternatives to the standard Reinforcement Learning from Human Feedback (RLHF) for aligning large language models (LLMs) with human values.…

Machine Learning · Computer Science 2025-06-12 Phuc Minh Nguyen , Ngoc-Hieu Nguyen , Duy H. M. Nguyen , Anji Liu , An Mai , Binh T. Nguyen , Daniel Sonntag , Khoa D. Doan

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

Machine Learning · Computer Science 2022-01-07 Kowshik Thopalli , Jayaraman J Thiagarajan , Rushil Anirudh , Pavan K Turaga

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…

Machine Learning · Computer Science 2026-01-01 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly…

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning…

Machine Learning · Computer Science 2026-02-24 Wendi Li , Sharon Li

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Machine Learning · Computer Science 2025-09-09 Thanh Thi Nguyen , Campbell Wilson , Janis Dalins

Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existing methods for semantic classification typically employ…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Kangjun Liu , Ke Chen , Kui Jia , Yaowei Wang

Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program. This technique is considered as the de-facto standard for computing the differentiation in many machine learning and…

Programming Languages · Computer Science 2022-12-21 Amir Shaikhha , Mathieu Huot , Shabnam Ghasemirad , Andrew Fitzgibbon , Simon Peyton Jones , Dimitrios Vytiniotis

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

Computation and Language · Computer Science 2025-10-16 Hao Wang , Linlong Xu , Heng Liu , Yangyang Liu , Xiaohu Zhao , Bo Zeng , Liangying Shao , Longyue Wang , Weihua Luo , Kaifu Zhang

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Machine Learning · Computer Science 2026-05-27 Austin Wang , Jiaqi Han , Stefano Ermon , Yisong Yue

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Computation and Language · Computer Science 2025-06-10 Javier Marín

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless. As an initial foray in…

End-to-end architectures in autonomous driving (AD) face a significant challenge in interpretability, impeding human-AI trust. Human-friendly natural language has been explored for tasks such as driving explanation and 3D captioning.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Kairui Ding , Boyuan Chen , Yuchen Su , Huan-ang Gao , Bu Jin , Chonghao Sima , Wuqiang Zhang , Xiaohui Li , Paul Barsch , Hongyang Li , Hao Zhao

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in…

Artificial Intelligence · Computer Science 2026-01-30 Sangyun Chung , Se Yeon Kim , Youngchae Chee , Yong Man Ro