English
Related papers

Related papers: Variational Best-of-N Alignment

200 papers

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

Computation and Language · Computer Science 2021-09-10 Chunting Zhou , Daniel Levy , Xian Li , Marjan Ghazvininejad , Graham Neubig

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Haoxian Chen , Yucheng Guo , Genta Indra Winata , Tingting Ou , Ziyu Huang , David D. Yao , Wenpin Tang

Derivative Free Optimization is known to be an efficient and robust method to tackle the black-box optimization problem. When it comes to noisy functions, classical comparison-based algorithms are slower than gradient-based algorithms. For…

Optimization and Control · Mathematics 2016-04-29 Marie-Liesse Cauwet , Olivier Teytaud

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Machine Learning · Computer Science 2022-11-15 Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic generators. A natural alternative is noise-space optimization, but existing…

Machine Learning · Computer Science 2026-05-14 Jeongsol Kim , Hongeun Kim , Jian Wang , Jong Chul Ye

Neural networks (NN) have been recently applied together with evolutionary algorithms (EAs) to solve dynamic optimization problems. The applied NN estimates the position of the next optimum based on the previous time best solutions. After…

Neural and Evolutionary Computing · Computer Science 2020-02-03 Maryam Hasani-Shoreh , Renato Hermoza Aragonés , Frank Neumann

Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…

Computation and Language · Computer Science 2025-11-11 Yichen Wang , Chenghao Yang , Tenghao Huang , Muhao Chen , Jonathan May , Mina Lee

Mixture models are widely used in Bayesian statistics and machine learning, in particular in computational biology, natural language processing and many other fields. Variational inference, a technique for approximating intractable…

Statistics Theory · Mathematics 2020-08-03 Badr-Eddine Chérief-Abdellatif , Pierre Alquier

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

Robotics · Computer Science 2024-03-12 Evan Ellis , Gaurav R. Ghosal , Stuart J. Russell , Anca Dragan , Erdem Bıyık

While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability. Thus the underlying foundation model should be eventually…

Machine Learning · Computer Science 2025-02-19 Daiki Chijiwa , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito , Susumu Takeuchi

We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided decoding in large language models. GSI combines soft best-of-$n$ test-time scaling with a reward model $r(x,y)$ and speculative samples from a…

Machine Learning · Computer Science 2026-04-28 Jonathan Geuter , Youssef Mroueh , David Alvarez-Melis

Distributional alignment enables large language models (LLMs) to predict how a target population distributes its responses across answer options, rather than collapsing disagreement into a single consensus answer. However, existing…

Machine Learning · Computer Science 2026-03-17 Viet-Thanh Pham , Lizhen Qu , Zhuang Li , Gholamreza Haffari

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that…

Machine Learning · Computer Science 2019-12-02 Dang Nguyen , Sunil Gupta , Santu Rana , Alistair Shilton , Svetha Venkatesh

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…

Robotics · Computer Science 2024-05-17 Yuwei Zeng , Yao Mu , Lin Shao

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…

Computer Vision and Pattern Recognition · Computer Science 2023-02-17 André Susano Pinto , Alexander Kolesnikov , Yuge Shi , Lucas Beyer , Xiaohua Zhai

Diffusion alignment adapts pretrained diffusion models to sample from reward-tilted distributions along the denoising trajectory. This process naturally admits a Sequential Monte Carlo (SMC) interpretation, where the denoising model acts as…

Machine Learning · Computer Science 2026-02-13 Zijing Ou , Jacob Si , Junyi Zhu , Ondrej Bohdal , Mete Ozay , Taha Ceritli , Yingzhen Li

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various…

Computation and Language · Computer Science 2024-04-30 Shanghaoran Quan

Guiding the policy of multi-agent reinforcement learning to align with human common sense is a difficult problem, largely due to the complexity of modeling common sense as a reward, especially in complex and long-horizon multi-agent tasks.…

Artificial Intelligence · Computer Science 2025-02-20 Hao Ma , Shijie Wang , Zhiqiang Pu , Siyao Zhao , Xiaolin Ai

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Computation and Language · Computer Science 2026-05-11 Arash Ahmadi , Sarah Sharif , Yaser , Banad

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

Computation and Language · Computer Science 2024-10-28 Alizée Pace , Jonathan Mallinson , Eric Malmi , Sebastian Krause , Aliaksei Severyn