English
Related papers

Related papers: SAHOO: Safeguarded Alignment for High-Order Optimi…

200 papers

Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Mingzhe Zheng , Weijie Kong , Yue Wu , Dengyang Jiang , Yue Ma , Xuanhua He , Bin Lin , Kaixiong Gong , Zhao Zhong , Liefeng Bo , Qifeng Chen , Harry Yang

Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Benjamin Yu , Jackie Liu , Justin Cui

Continuous optimization has significantly advanced causal discovery, yet existing methods (e.g., NOTEARS) generally guarantee only asymptotic convergence to a stationary point. This often yields dense weighted matrices that require…

Machine Learning · Computer Science 2026-01-27 Rui Wu , Yongjun Li

The predict-then-optimize (PTO) framework is indispensable for addressing practical stochastic decision-making tasks. It consists of two crucial steps: initially predicting unknown parameters of an optimization model and subsequently…

Systems and Control · Electrical Eng. & Systems 2024-11-20 Jixian Liu , Tao Xu , Jianping He , Chongrong Fang

Recursive QAOA (RQAOA) solves combinatorial optimization problems by using shallow quantum circuits to estimate pairwise correlations and recursively eliminate variables until a classical solver can handle the residual instance. Each…

Quantum Physics · Physics 2026-05-27 Euimin Lee , Shiho Kim

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Meng Lou , Hanzhong Guo , Linwei Chen , Yizhou Yu

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from…

Machine Learning · Computer Science 2026-03-19 Ziyan Wang , Zheng Wang , Xingwei Qu , Qi Cheng , Jie Fu , Shengpu Tang , Minjia Zhang , Xiaoming Huo

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization…

Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Tu Zheng , Shuai Zhao , Yang Liu , Zili Liu , Deng Cai

Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable…

Machine Learning · Computer Science 2026-03-24 Hongjun Wang , Wei Liu , Weibo Gu , Xing Sun , Kai Han

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL…

Robotics · Computer Science 2025-06-04 Yifan Sun , Feihan Li , Weiye Zhao , Rui Chen , Tianhao Wei , Changliu Liu

Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to…

Machine Learning · Computer Science 2021-05-20 Riccardo Poiani , Andrea Tirinzoni , Marcello Restelli

Abnormal Human Behavior Detection (AHBD) under special scenarios is becoming increasingly crucial. While YOLO-based detection methods excel in real-time tasks, they remain hindered by challenges including small objects, task conflicts, and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xinyi Yin , Wenbo Yuan , Xuecheng Wu , Liangyu Fu , Danlei Huang

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Wei Hua , Dingkang Liang , Jingyu Li , Xiaolong Liu , Zhikang Zou , Xiaoqing Ye , Xiang Bai

In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems…

Machine Learning · Computer Science 2021-06-01 Tengyu Xu , Yingbin Liang , Guanghui Lan

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

Artificial Intelligence · Computer Science 2025-09-23 Mohammad Beigi , Ying Shen , Parshin Shojaee , Qifan Wang , Zichao Wang , Chandan Reddy , Ming Jin , Lifu Huang

The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a…

Machine Learning · Computer Science 2024-11-05 Jonathan Pirnay , Dominik G. Grimm

This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding…

Machine Learning · Computer Science 2022-09-12 Frank Röder , Manfred Eppe , Stefan Wermter

Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications. However, current algorithms still struggle for efficient policy updates with hard constraint…

Machine Learning · Computer Science 2022-06-20 Linrui Zhang , Li Shen , Long Yang , Shixiang Chen , Bo Yuan , Xueqian Wang , Dacheng Tao