Cover Image

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xiaodong, Huang, Jinfa, Yuan, Li, Peng, Peixi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos
by: Wang, Xiaodong, et al.
Published: (2025)

LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model
by: Wang, Xiaodong, et al.
Published: (2025)

Is Micro-expression Ethnic Leaning?
by: Khor, Huai-Qian, et al.
Published: (2025)

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
by: Wang, Xiaodong, et al.
Published: (2026)

LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
by: Cheng, Yu, et al.
Published: (2025)

InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
by: Lu, Yunhong, et al.
Published: (2025)

ViPO: Visual Preference Optimization at Scale
by: Li, Ming, et al.
Published: (2026)

SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning
by: Dang, Jisheng, et al.
Published: (2025)

Lean Unet: A Compact Model for Image Segmentation
by: Hassler, Ture, et al.
Published: (2025)

FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis
by: Chen, Shijie, et al.
Published: (2025)

LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
by: Wu, Jiamin, et al.
Published: (2024)

LeanStereo: A Leaner Backbone based Stereo Network
by: Rahim, Rafia, et al.
Published: (2025)

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
by: Wan, Zhongwei, et al.
Published: (2024)

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
by: Cao, Meng, et al.
Published: (2024)

Identity-Preserving Text-to-Video Generation by Frequency Decomposition
by: Yuan, Shenghai, et al.
Published: (2024)

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
by: Yuan, Shenghai, et al.
Published: (2024)

Lean classical-quantum hybrid neural network model for image classification
by: Liu, Ao, et al.
Published: (2024)

Data-Driven Abdominal Phenotypes of Type 2 Diabetes in Lean, Overweight, and Obese Cohorts
by: Remedios, Lucas W., et al.
Published: (2025)

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
by: Yan, Ziang, et al.
Published: (2024)

Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
by: Zhu, Jingyuan, et al.
Published: (2026)

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
by: Huang, Haoyu, et al.
Published: (2026)

ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints
by: Huang, Kaili, et al.
Published: (2026)

Discriminator-Free Direct Preference Optimization for Video Diffusion
by: Cheng, Haoran, et al.
Published: (2025)

Lean Learning Beyond Clouds: Efficient Discrepancy-Conditioned Optical-SAR Fusion for Semantic Segmentation
by: Meng, Chenxing, et al.
Published: (2026)

LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
by: Yuan, Jianhao, et al.
Published: (2025)

VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment
by: Kulkarni, Yogesh, et al.
Published: (2025)

HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment
by: Jiang, Lifan, et al.
Published: (2025)

McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical Reasoning
by: Yang, Qiushi, et al.
Published: (2025)

AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
by: He, Dailan, et al.
Published: (2026)

AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization
by: Lu, Jinda, et al.
Published: (2025)

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
by: Jiang, Songtao, et al.
Published: (2024)

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
by: Huang, Zhenpeng, et al.
Published: (2026)

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
by: Yuan, Shenghai, et al.
Published: (2025)

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach
by: Li, Hebei, et al.
Published: (2025)

Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
by: Huang, Yangru, et al.
Published: (2019)

OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
by: Zhang, Jiacheng, et al.
Published: (2024)

From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models
by: Cai, Zefan, et al.
Published: (2025)

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization
by: Zhu, Kangyu, et al.
Published: (2024)

ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
by: Yuan, Shenghai, et al.
Published: (2024)

MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization
by: Pappa, Massimiliano, et al.
Published: (2024)