English
Related papers

Related papers: Optimas: Optimizing Compound AI Systems with Globa…

200 papers

Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment…

Machine Learning · Computer Science 2026-03-09 Xiangwen Wang , Yibo Jacky Zhang , Zhoujie Ding , Katherine Tsai , Haolun Wu , Sanmi Koyejo

Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they…

Information Retrieval · Computer Science 2025-04-17 Harrie Oosterhuis , Rolf Jagerman , Zhen Qin , Xuanhui Wang

Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal coordination, particularly when sparse task rewards provide insufficient grounding for coordinated…

Machine Learning · Computer Science 2026-04-07 Dogan Urgun , Gokhan Gungor

Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces…

Machine Learning · Computer Science 2021-04-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , Keren Zhu , David Z. Pan

Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy…

Machine Learning · Computer Science 2024-06-21 Ahmed M. Ahmed , Rafael Rafailov , Stepan Sharkov , Xuechen Li , Sanmi Koyejo

Huge neural network models have shown unprecedented performance in real-world applications. However, due to memory constraints, model parallelism must be utilized to host large models that would otherwise not fit into the memory of a single…

Machine Learning · Computer Science 2021-04-13 Qifan Xu , Shenggui Li , Chaoyu Gong , Yang You

Stochastic variance reduced optimization methods are known to be globally convergent while they suffer from slow local convergence, especially when moderate or high accuracy is needed. To alleviate this problem, we propose an optimization…

Optimization and Control · Mathematics 2021-11-15 Hamed Sadeghi , Pontus Giselsson

Static feature exclusion strategies often fail to prevent bias when hidden dependencies influence the model predictions. To address this issue, we explore a reinforcement learning (RL) framework that integrates bias mitigation and automated…

Machine Learning · Computer Science 2025-10-14 Sudip Khadka , L. S. Paudel

Training large language models (LLMs) is constrained by memory requirements, with activations accounting for a substantial fraction of the total footprint. Existing approaches reduce memory using low-rank weight parameterizations or…

Machine Learning · Computer Science 2026-04-13 Sakshi Choudhary , Utkarsh Saxena , Kaushik Roy

This work presents a unified framework that combines global approximations with locally built models to handle challenging nonconvex and nonsmooth composite optimization problems, including cases involving extended real-valued functions. We…

Optimization and Control · Mathematics 2026-02-19 Welington de Oliveira , Johannes O. Royset

Multimodal large language models (MLLMs) have extended the success of large language models (LLMs) to multiple data types, such as image, text and audio, achieving significant performance in various domains, including multimodal…

Computation and Language · Computer Science 2025-06-03 Weiqi Feng , Yangrui Chen , Shaoyu Wang , Yanghua Peng , Haibin Lin , Minlan Yu

Federated learning (FL) has emerged as a widely adopted training paradigm for privacy-preserving machine learning. While the SGD-based FL algorithms have demonstrated considerable success in the past, there is a growing trend towards…

Machine Learning · Computer Science 2024-07-29 Yujia Wang , Shiqiang Wang , Songtao Lu , Jinghui Chen

In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired task. To solve this,…

Computation and Language · Computer Science 2025-04-30 Yash Jain , Vishal Chowdhary

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Computation and Language · Computer Science 2025-01-09 Shujun Liu , Xiaoyu Shen , Yuhang Lai , Siyuan Wang , Shengbin Yue , Zengfeng Huang , Xuanjing Huang , Zhongyu Wei

We study vehicle dispatching in autonomous mobility on demand (AMoD) systems, where a central operator assigns vehicles to customer requests or rejects these with the aim of maximizing its total profit. Recent approaches use multi-agent…

Machine Learning · Computer Science 2024-05-21 Heiko Hoppe , Tobias Enders , Quentin Cappart , Maximilian Schiffer

Effectively aligning Large Language Models (LLMs) with human-centric values while preventing the degradation of abilities acquired through Pre-training and Supervised Fine-tuning (SFT) poses a central challenge in Reinforcement Learning…

Computation and Language · Computer Science 2024-05-29 Keming Lu , Bowen Yu , Fei Huang , Yang Fan , Runji Lin , Chang Zhou

Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward models are used to approximately model human preferences.…

Machine Learning · Computer Science 2024-03-12 Thomas Coste , Usman Anwar , Robert Kirk , David Krueger

Compound AI Systems (CAIS) are an emerging paradigm that integrates large language models (LLMs) with external components, including retrievers, agents, tools, and orchestrators, to overcome the limitations of standalone models in tasks…

Multiagent Systems · Computer Science 2026-05-11 Jiayi Chen , Junyi Ye , Guiling Wang

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Computation and Language · Computer Science 2024-10-24 Rui Yang , Ruomeng Ding , Yong Lin , Huan Zhang , Tong Zhang

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…

Machine Learning · Computer Science 2026-05-07 Xiyan Fu , Wei Liu