paper-with-me

홈 › Papers

Interactive Training: Feedback-Driven Neural Network Optimization

2025-10-02 · Wentao Zhang, Yang Young Lu, Yuntian Deng arxiv

Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an open-source framework that enables real-time, feedback-driven intervention during neural network training by human experts or automated AI agents. At its core, Interactive Training uses a control server to mediate communication between users or agents and the ongoing training process, allowing users to dynamically adjust optimizer hyperparameters, training data, and model checkpoints. Through three case studies, we demonstrate that Interactive Training achieves superior training stability, reduced sensitivity to initial hyperparameters, and improved adaptability to evolving user needs, paving the way toward a future training paradigm where AI agents autonomously monitor training logs, proactively resolve instabilities, and optimize training dynamics.

📄 PDF Abstract BibTeX arXiv:2510.02297

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization

2025-11-11 · Zhen Yang, Wenyi Hong, Mingde Xu, Xinyue Fan 외 arxiv

UI-to-code aims to translate UI screenshots into executable front-end code. Despite progress with vision-language models (VLMs), most existing methods formulate UI-to-code as a single-pass generation, which mismatches re…

Reinforcement LearningCode Generation

Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation

2026-02-28 · Yafei Zhang, Shuaitian Song, Huafeng Li, Shujuan Wang 외 arxiv

In real-world vision systems,haze removal is required not only to enhance image visibility but also to meet the specific needs of diverse downstream tasks.To address this challenge,we propose a novel adaptive dynamic deh…

HF4Rec: Human-Like Feedback-Driven Optimization Framework for Explainable Recommendation

2025-04-19 · Jiakai Tang, Jingsen Zhang, Zihang Tian, Xueyang Feng 외

Recent advancements in explainable recommendation have greatly bolstered user experience by elucidating the decision-making rationale. However, the existing methods actually fail to provide effective feedback signals for…

Explainable RecommendationLogical Reasoning

Improving Interactive In-Context Learning from Natural Language Feedback

2026-02-17 · Martin Klissarov, Jonathan Cook, Diego Antognini, Hao Sun 외 arxiv

Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavil…

Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search

2026-07-01 · Binglin Ji, Anindya Sarkar, Hengchang Lu, Jens Sjölund 외 arxiv

While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution. These approaches struggle when preferences a…