Image de couverture de livre

SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Melany, Yu, Yuhang, Weng, Diwang, Chen, Jinwei, Dong, Wei
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

L2SR: Learning to Sample and Reconstruct for Accelerated MRI via Reinforcement Learning
par: Yang, Pu, et autres
Publié: (2022)

Unified Reinforcement and Imitation Learning for Vision-Language Models
par: Lee, Byung-Kwan, et autres
Publié: (2025)

High-Quality Live Video Streaming via Transcoding Time Prediction and Preset Selection
par: Shahre-Babak, Zahra Nabizadeh, et autres
Publié: (2023)

HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection
par: Weng, Zekang, et autres
Publié: (2025)

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
par: Zheng, Xiaoji, et autres
Publié: (2025)

Resonance4D: Frequency-Domain Motion Supervision for Preset-Free Physical Parameter Learning in 4D Dynamic Physical Scene Simulation
par: Zhang, Changshe, et autres
Publié: (2026)

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
par: Zheng, Kaiwen, et autres
Publié: (2025)

Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability
par: Weng, Juanjuan, et autres
Publié: (2024)

Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning
par: Yang, Kuo, et autres
Publié: (2024)

Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
par: Liu, Yuhong, et autres
Publié: (2025)

Sampling Control for Imbalanced Calibration in Semi-Supervised Learning
par: Tian, Senmao, et autres
Publié: (2025)

Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
par: Wang, Feng, et autres
Publié: (2025)

Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
par: Shao, Qian, et autres
Publié: (2024)

TinySR: Pruning Diffusion for Real-World Image Super-Resolution
par: Dong, Linwei, et autres
Publié: (2025)

DARIL: When Imitation Learning outperforms Reinforcement Learning in Surgical Action Planning
par: Boels, Maxence, et autres
Publié: (2025)

What's the Move? Hybrid Imitation Learning via Salient Points
par: Sundaresan, Priya, et autres
Publié: (2024)

OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
par: Zhang, Guohui, et autres
Publié: (2026)

Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics
par: Gao, Zhirui, et autres
Publié: (2024)

EgoMimic: Scaling Imitation Learning via Egocentric Video
par: Kareer, Simar, et autres
Publié: (2024)

MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI
par: Lu, Zhengyi, et autres
Publié: (2026)

Impact of Strategic Sampling and Supervision Policies on Semi-supervised Learning
par: Roy, Shuvendu, et autres
Publié: (2022)

Active Self-Semi-Supervised Learning for Few Labeled Samples
par: Wen, Ziting, et autres
Publié: (2022)

VILP: Imitation Learning with Latent Video Planning
par: Xu, Zhengtong, et autres
Publié: (2025)

Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization
par: Li, Yuhang, et autres
Publié: (2024)

Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
par: Wang, Peiyu, et autres
Publié: (2025)

SCR2-ST: Combine Single Cell with Spatial Transcriptomics for Efficient Active Sampling via Reinforcement Learning
par: Zhu, Junchao, et autres
Publié: (2025)

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
par: Xing, Long, et autres
Publié: (2025)

LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion
par: Xue, Clara, et autres
Publié: (2026)

Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
par: Li, Weijia, et autres
Publié: (2024)

Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning
par: Tan, Qida, et autres
Publié: (2026)

Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight
par: Xing, Jiaxu, et autres
Publié: (2024)

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
par: Zheng, Ziwei, et autres
Publié: (2025)

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
par: Su, Zhaochen, et autres
Publié: (2025)

FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
par: Ma, Yeyao, et autres
Publié: (2026)

Controlling Neural Style Transfer with Deep Reinforcement Learning
par: Feng, Chengming, et autres
Publié: (2023)

Universal Semi-Supervised Learning for Medical Image Classification
par: Ju, Lie, et autres
Publié: (2023)

Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning
par: Jiang, Zhaohui, et autres
Publié: (2024)

Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning
par: Li, Xueheng, et autres
Publié: (2026)

PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning
par: Wang, Yijian, et autres
Publié: (2026)

Automated Schizophrenia Detection from Handwriting Samples via Transfer Learning Convolutional Neural Networks
par: Castro, Rafael, et autres
Publié: (2024)