Image de couverture de livre

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Donghu, Lee, Hojoon, Lee, Kyungmin, Hwang, Dongyoon, Choo, Jaegul
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence 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

Do's and Don'ts: Learning Desirable Skills with Instruction Videos
par: Kim, Hyunseung, et autres
Publié: (2024)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
par: Hwang, Dongyoon, et autres
Publié: (2024)

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
par: Hwang, Dongyoon, et autres
Publié: (2025)

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
par: Lee, Hojoon, et autres
Publié: (2024)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
par: Lee, Hojoon, et autres
Publié: (2024)

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
par: Yoon, Jaesik, et autres
Publié: (2023)

Hyperspherical Normalization for Scalable Deep Reinforcement Learning
par: Lee, Hojoon, et autres
Publié: (2025)

The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
par: Schneider, Moritz, et autres
Publié: (2024)

Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning
par: Kim, Kyungsoo, et autres
Publié: (2025)

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
par: Kim, Gahyeon, et autres
Publié: (2025)

AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
par: Kim, Gahyeon, et autres
Publié: (2024)

Skip-and-Play: Depth-Driven Pose-Preserved Image Generation for Any Objects
par: Jo, Kyungmin, et autres
Publié: (2024)

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
par: Kim, Jeongho, et autres
Publié: (2024)

RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation
par: Kim, Minwoo, et autres
Publié: (2025)

RL makes MLLMs see better than SFT
par: Song, Junha, et autres
Publié: (2025)

Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modeling
par: Kim, Jaehyeok, et autres
Publié: (2024)

Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
par: Verma, Sahil, et autres
Publié: (2023)

Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision
par: Kim, Jinhee, et autres
Publié: (2024)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
par: Oh, Changdae, et autres
Publié: (2023)

Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention
par: Park, Jeonghoon, et autres
Publié: (2025)

Dataset Distillation for Pre-Trained Self-Supervised Vision Models
par: Cazenavette, George, et autres
Publié: (2025)

SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
par: Lee, Jaeseong, et autres
Publié: (2024)

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
par: Lee, Byung-Kwan, et autres
Publié: (2025)

Pre-Training Meta-Rule Selection Policy for Visual Generative Abductive Learning
par: Jin, Yu, et autres
Publié: (2025)

PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask
par: Kim, Jeongho, et autres
Publié: (2024)

What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
par: Farid, Karim, et autres
Publié: (2025)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
par: Lee, Dongyeun, et autres
Publié: (2025)

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
par: Kang, Seongjae, et autres
Publié: (2025)

Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
par: Park, Jihwan, et autres
Publié: (2025)

Training-Free Restoration of Pruned Neural Networks
par: Lee, Keonho, et autres
Publié: (2025)

Rethinking Multi-domain Generalization with A General Learning Objective
par: Tan, Zhaorui, et autres
Publié: (2024)

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
par: Karnik, Sathwik, et autres
Publié: (2026)

TexAvatars : Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars
par: Lee, Jaeseong, et autres
Publié: (2025)

Training Diffusion Models with Reinforcement Learning
par: Black, Kevin, et autres
Publié: (2023)

Pre-training Vision Transformers with Formula-driven Supervised Learning
par: Kataoka, Hirokatsu, et autres
Publié: (2022)

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
par: Kim, Jinyeong, et autres
Publié: (2025)

Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model
par: Chen, Yi-Chia, et autres
Publié: (2024)

Training-free Detection of AI-generated images via Cropping Robustness
par: Choi, Sungik, et autres
Publié: (2025)

Reinforcement Learning for Unsupervised Video Summarization with Reward Generator Training
par: Abbasi, Mehryar, et autres
Publié: (2024)

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
par: Zhang, Gengwei, et autres
Publié: (2026)