Image de couverture de livre

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ahn, Daechul, Choi, Yura, Kim, San, Yu, Youngjae, Kang, Dongyeop, Choi, Jonghyun
Format:	Preprint
Publié:	2024
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

Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
par: Ahn, Daechul, et autres
Publié: (2024)

What Happens When: Learning Temporal Orders of Events in Videos
par: Ahn, Daechul, et autres
Publié: (2025)

AVC-DPO: Aligned Video Captioning via Direct Preference Optimization
par: Tang, Jiyang, et autres
Publié: (2025)

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
par: Huang, Qihan, et autres
Publié: (2024)

VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving
par: Xu, Zhefan, et autres
Publié: (2026)

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
par: Shang, Shuyao, et autres
Publié: (2025)

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
par: Jia, Hongrui, et autres
Publié: (2024)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
par: Wu, Ziyi, et autres
Publié: (2025)

When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO
par: Zhang, Lingfan, et autres
Publié: (2025)

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
par: Huang, Haojian, et autres
Publié: (2025)

mDPO: Conditional Preference Optimization for Multimodal Large Language Models
par: Wang, Fei, et autres
Publié: (2024)

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment
par: Park, Jonghyun, et autres
Publié: (2025)

$ϕ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models
par: Truong, Thanh-Dat, et autres
Publié: (2026)

DeDPO: Debiased Direct Preference Optimization for Diffusion Models
par: Pham, Khiem, et autres
Publié: (2026)

SEE-DPO: Self Entropy Enhanced Direct Preference Optimization
par: Shekhar, Shivanshu, et autres
Publié: (2024)

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
par: Liu, Runtao, et autres
Publié: (2024)

RealDPO: Real or Not Real, that is the Preference
par: Cheng, Guo, et autres
Publié: (2025)

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
par: Yang, Zhihe, et autres
Publié: (2025)

Becoming Experienced Judges: Selective Test-Time Learning for Evaluators
par: Jwa, Seungyeon, et autres
Publié: (2025)

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
par: Zhou, Dewei, et autres
Publié: (2025)

SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning
par: Cheng, Xin, et autres
Publié: (2026)

S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models
par: Shukla, Nitish, et autres
Publié: (2026)

BalancedDPO: Adaptive Multi-Metric Alignment
par: Tamboli, Dipesh, et autres
Publié: (2025)

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
par: Li, Zejian, et autres
Publié: (2025)

PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection
par: Wang, Peiyao, et autres
Publié: (2025)

HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment
par: Jiang, Lifan, et autres
Publié: (2025)

CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
par: Ouali, Yassine, et autres
Publié: (2024)

Region-Normalized DPO for Medical Image Segmentation under Noisy Judges
par: Kalisch, Hamza, et autres
Publié: (2026)

Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
par: Rao, Abinav, et autres
Publié: (2026)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
par: Liu, Ziyu, et autres
Publié: (2024)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
par: Kim, Taeheon, et autres
Publié: (2025)

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models
par: Kim, Jisoo, et autres
Publié: (2025)

HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images
par: Yang, Yilin, et autres
Publié: (2026)

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
par: Ayupov, Shamil, et autres
Publié: (2025)

Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
par: Du, Jie, et autres
Publié: (2025)

DPO Learning with LLMs-Judge Signal for Computer Use Agents
par: Luo, Man, et autres
Publié: (2025)

Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
par: Ahn, Daechul, et autres
Publié: (2025)

InpaintDPO: Mitigating Spatial Relationship Hallucinations in Foreground-conditioned Inpainting via Diverse Preference Optimization
par: Li, Qirui, et autres
Publié: (2025)

DEVIAS: Learning Disentangled Video Representations of Action and Scene
par: Bae, Kyungho, et autres
Publié: (2023)

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
par: Xie, Yuxi, et autres
Publié: (2024)