Image de couverture de livre

CyberV: Cybernetics for Test-time Scaling in Video Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Meng, Jiahao, Sun, Shuyang, Tan, Yue, Qi, Lu, Tong, Yunhai, Li, Xiangtai, Wen, Longyin
Format:	Preprint
Publié:	2025
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

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
par: Shi, Qingyu, et autres
Publié: (2025)

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
par: Meng, Jiahao, et autres
Publié: (2025)

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
par: Yuan, Haobo, et autres
Publié: (2025)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
par: Meng, Jiahao, et autres
Publié: (2026)

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
par: Wang, Chaoyang, et autres
Publié: (2024)

DreamRelation: Bridging Customization and Relation Generation
par: Shi, Qingyu, et autres
Publié: (2024)

Conditional Panoramic Image Generation via Masked Autoregressive Modeling
par: Wang, Chaoyang, et autres
Publié: (2025)

Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
par: Xu, Lu, et autres
Publié: (2024)

LLAVADI: What Matters For Multimodal Large Language Models Distillation
par: Xu, Shilin, et autres
Publié: (2024)

MotionBooth: Motion-Aware Customized Text-to-Video Generation
par: Wu, Jianzong, et autres
Publié: (2024)

VG4D: Vision-Language Model Goes 4D Video Recognition
par: Deng, Zhichao, et autres
Publié: (2024)

Explore In-Context Segmentation via Latent Diffusion Models
par: Wang, Chaoyang, et autres
Publié: (2024)

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
par: Wu, Jianzong, et autres
Publié: (2024)

DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
par: Xu, Shilin, et autres
Publié: (2023)

Vidi: Large Multimodal Models for Video Understanding and Editing
par: Vidi Team, et autres
Publié: (2025)

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
par: Zhou, Yikang, et autres
Publié: (2025)

Video Prediction Transformers without Recurrence or Convolution
par: Tang, Yujin, et autres
Publié: (2024)

One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration
par: Wang, Chaoyang, et autres
Publié: (2026)

Dense360: Dense Understanding from Omnidirectional Panoramas
par: Zhou, Yikang, et autres
Publié: (2025)

Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs
par: Yao, Yue, et autres
Publié: (2025)

Towards Language-Driven Video Inpainting via Multimodal Large Language Models
par: Wu, Jianzong, et autres
Publié: (2024)

Unified Dense Prediction of Video Diffusion
par: Yang, Lehan, et autres
Publié: (2025)

Generative Classifier for Domain Generalization
par: Long, Shaocong, et autres
Publié: (2025)

RecTok: Reconstruction Distillation along Rectified Flow
par: Shi, Qingyu, et autres
Publié: (2025)

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
par: Li, Jiachen, et autres
Publié: (2024)

AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
par: Xue, Zhucun, et autres
Publié: (2025)

DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
par: Qi, Mengshi, et autres
Publié: (2025)

Edit3K: Universal Representation Learning for Video Editing Components
par: Gu, Xin, et autres
Publié: (2024)

Accurate and Fast Compressed Video Captioning
par: Shen, Yaojie, et autres
Publié: (2023)

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
par: Chen, Guo, et autres
Publié: (2024)

EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation
par: Li, Bingxuan, et autres
Publié: (2025)

V-CORE: Temporally Consistent Video Understanding for Video-LLM
par: Kang, Zhengjian, et autres
Publié: (2026)

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
par: Xu, Shilin, et autres
Publié: (2024)

VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing
par: Deng, Andong, et autres
Publié: (2026)

D-Attn: Decomposed Attention for Large Vision-and-Language Models
par: Kuo, Chia-Wen, et autres
Publié: (2025)

BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
par: Wen, Haiquan, et autres
Publié: (2025)

PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
par: Li, Xiangtai, et autres
Publié: (2023)

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
par: Wang, Haochen, et autres
Publié: (2025)

Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
par: Wu, Jianzong, et autres
Publié: (2025)

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
par: Feng, Haoran, et autres
Publié: (2025)