Imagen de Portada

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Hui, Lu, Shiyin, Wang, Huanyu, Chen, Qing-Guo, Xu, Zhao, Luo, Weihua, Zhang, Kaifu, Li, Ming
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Ovis: Structural Embedding Alignment for Multimodal Large Language Model
por: Lu, Shiyin, et al.
Publicado: (2024)

Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images
por: Yang, Wenhao, et al.
Publicado: (2025)

Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
por: Wang, Yibo, et al.
Publicado: (2026)

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
por: Fu, Minghao, et al.
Publicado: (2025)

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
por: Fu, Minghao, et al.
Publicado: (2025)

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance
por: Fu, Minghao, et al.
Publicado: (2025)

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images
por: Hu, JiaKui, et al.
Publicado: (2025)

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
por: Zhang, Shaojie, et al.
Publicado: (2025)

Multimodal Tabular Reasoning with Privileged Structured Information
por: Jiang, Jun-Peng, et al.
Publicado: (2025)

From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding
por: Sun, Guangyu, et al.
Publicado: (2025)

Evaluating Image Caption via Cycle-consistent Text-to-Image Generation
por: Cui, Tianyu, et al.
Publicado: (2025)

Parrot: Multilingual Visual Instruction Tuning
por: Sun, Hai-Long, et al.
Publicado: (2024)

Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
por: Yang, Wenhao, et al.
Publicado: (2026)

LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
por: Kim, Jihwan, et al.
Publicado: (2026)

Frame-Voyager: Learning to Query Frames for Video Large Language Models
por: Yu, Sicheng, et al.
Publicado: (2024)

Wings: Learning Multimodal LLMs without Text-only Forgetting
por: Zhang, Yi-Kai, et al.
Publicado: (2024)

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation
por: Zhu, Tianyi, et al.
Publicado: (2024)

PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm
por: Chang, Tianyu, et al.
Publicado: (2024)

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
por: Wang, Yibo, et al.
Publicado: (2026)

UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation
por: Duan, Lunhao, et al.
Publicado: (2024)

ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation
por: Yang, Shaoshu, et al.
Publicado: (2024)

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
por: Han, Kai, et al.
Publicado: (2024)

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
por: Zhao, Shanshan, et al.
Publicado: (2025)

Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning
por: Xu, Huali, et al.
Publicado: (2024)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
por: Song, Baiyang, et al.
Publicado: (2026)

Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction
por: Liu, Zheyuan, et al.
Publicado: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
por: Chen, Wang, et al.
Publicado: (2026)

Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
por: Gao, Sensen, et al.
Publicado: (2025)

Weight Group-wise Post-Training Quantization for Medical Foundation Model
por: Chen, Yineng, et al.
Publicado: (2026)

Think-Clip-Sample: Slow-Fast Frame Selection for Video Understanding
por: Tan, Wenhui, et al.
Publicado: (2026)

EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection
por: Qu, Huaizhi, et al.
Publicado: (2025)

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs
por: Sun, Bowen, et al.
Publicado: (2025)

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
por: Feng, X., et al.
Publicado: (2026)

FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis
por: Tan, Jiangtong, et al.
Publicado: (2025)

Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
por: Ghazanfari, Sara, et al.
Publicado: (2025)

Training-Free Image Editing with Visual Context Integration and Concept Alignment
por: Song, Rui, et al.
Publicado: (2026)

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
por: Chen, Wang, et al.
Publicado: (2026)

SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models
por: Wang, Yibo, et al.
Publicado: (2025)

Layer-wise Noise Guided Selective Wavelet Reconstruction for Robust Medical Image Segmentation
por: Lu, Yuting, et al.
Publicado: (2025)

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
por: Chung, Hyungjin, et al.
Publicado: (2025)