English
Related papers

Related papers: Bicoptor 2.0: Addressing Challenges in Probabilist…

200 papers

Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has explored improved estimators of advantages and normalization,…

Machine Learning · Computer Science 2026-02-24 Philipp Becker , Niklas Freymuth , Serge Thilges , Fabian Otto , Gerhard Neumann

Existing learning-based video compression methods still face challenges related to inaccurate motion estimates and inadequate motion compensation structures. These issues result in compression errors and a suboptimal rate-distortion…

Image and Video Processing · Electrical Eng. & Systems 2025-03-13 Md baharul Islam , Afsana Ahsan Jeny

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

The ubiquitous use of machine learning algorithms brings new challenges to traditional database problems such as incremental view update. Much effort is being put in better understanding and debugging machine learning models, as well as in…

Machine Learning · Computer Science 2020-02-28 Yinjun Wu , Val Tannen , Susan B. Davidson

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Machine Learning · Computer Science 2025-10-28 Junkang Wu , Kexin Huang , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Machine Learning · Computer Science 2026-02-13 Yihan Du , Seo Taek Kong , R. Srikant

Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This challenge is particularly acute in advanced networked systems,…

Machine Learning · Computer Science 2025-11-18 Shaojie Bai , Mohammad Sadegh Talebi , Chengcheng Zhao , Peng Cheng , Jiming Chen

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in…

Computation and Language · Computer Science 2026-03-02 Shuichiro Haruta , Kazunori Matsumoto , Zhi Li , Yanan Wang , Mori Kurokawa

With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…

Machine Learning · Computer Science 2022-02-22 Fei Zheng , Chaochao Chen , Xiaolin Zheng , Mingjie Zhu

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…

Computation and Language · Computer Science 2026-03-26 Rahul Singhal , Pradyumna Tambwekar , Karime Maamari

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction…

Machine Learning · Computer Science 2023-05-24 Chengbin Xuan , Feng Zhang , Faliang Yin , Hak-Keung Lam

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

Machine Learning · Computer Science 2026-02-18 Chang Liu , Yunfan Li , Lin F. Yang

We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety analysis of robotic perception and control systems with deep…

Robotics · Computer Science 2021-04-02 Joseph A. Vincent , Mac Schwager

The rising volume of datasets has made training machine learning (ML) models a major computational cost in the enterprise. Given the iterative nature of model and parameter tuning, many analysts use a small sample of their entire data…

Machine Learning · Computer Science 2018-12-31 Yongjoo Park , Jingyi Qing , Xiaoyang Shen , Barzan Mozafari

The recent success of deep neural networks (DNNs) for function approximation in reinforcement learning has triggered the development of Deep Reinforcement Learning (DRL) algorithms in various fields, such as robotics, computer games,…

Machine Learning · Computer Science 2023-07-19 Dor Livne , Kobi Cohen

Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is hampered by the inherent limitations in autoregressive token…

Machine Learning · Computer Science 2024-02-22 Shuzhang Zhong , Zebin Yang , Meng Li , Ruihao Gong , Runsheng Wang , Ru Huang

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Machine Learning · Computer Science 2024-08-08 Shashank Gupta , Harrie Oosterhuis , Maarten de Rijke

In B5G edge networks, end-to-end low-latency and high-reliability transmissions between edge computing nodes and terminal devices are essential. This paper investigates the queue-aware coding scheduling transmission of randomly arriving…

Networking and Internet Architecture · Computer Science 2024-02-02 Zhongfu Guo , Xinsheng Ji , Wei You , Mingyan Xu , Yu Zhao , Zhimo Cheng , Deqiang Zhou