Imagen de Portada

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Zhe, Wen, Hao, Hao, Aiming, Song, Bingze, Wu, Meiqi, Wu, Jiahong, Chu, Xiangxiang, Lu, Sheng, Wang, Haoqian
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Artifact-Aware Evaluation for High-Quality Video Generation
por: Zhu, Chen, et al.
Publicado: (2026)

VMBench: A Benchmark for Perception-Aligned Video Motion Generation
por: Ling, Xinran, et al.
Publicado: (2025)

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints
por: Wu, Meiqi, et al.
Publicado: (2025)

Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V
por: Wu, Meiqi, et al.
Publicado: (2026)

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
por: Mao, Fangyuan, et al.
Publicado: (2025)

Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning
por: Chen, Chubin, et al.
Publicado: (2025)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
por: Zhao, Chenxi, et al.
Publicado: (2026)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
por: Ma, Xiaoxiao, et al.
Publicado: (2026)

Ranking-aware Reinforcement Learning for Ordinal Ranking
por: Hao, Aiming, et al.
Publicado: (2026)

ConceptWeaver: Weaving Disentangled Concepts with Flow
por: Chen, Jintao, et al.
Publicado: (2026)

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
por: Wu, Meiqi, et al.
Publicado: (2026)

MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
por: Yang, Kaixing, et al.
Publicado: (2025)

Towards Fine-Grained Human Motion Video Captioning
por: Song, Guorui, et al.
Publicado: (2025)

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
por: Lu, Hao, et al.
Publicado: (2025)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
por: Ouyang, Kun, et al.
Publicado: (2025)

Omni-Video: Democratizing Unified Video Understanding and Generation
por: Tan, Zhiyu, et al.
Publicado: (2025)

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
por: Fang, Bo, et al.
Publicado: (2025)

CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management
por: Wang, Chao, et al.
Publicado: (2026)

Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
por: Chen, Chubin, et al.
Publicado: (2025)

E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
por: Liu, Xianjie, et al.
Publicado: (2026)

There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
por: Lei, Jiachen, et al.
Publicado: (2025)

LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling
por: Li, Huaqiu, et al.
Publicado: (2025)

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
por: Poppi, Tobia, et al.
Publicado: (2026)

VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMs
por: Zheng, Naishan, et al.
Publicado: (2025)

Video-R1: Reinforcing Video Reasoning in MLLMs
por: Feng, Kaituo, et al.
Publicado: (2025)

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding
por: Cai, Yuxuan, et al.
Publicado: (2025)

TransAnimate: Taming Layer Diffusion to Generate RGBA Video
por: Chen, Xuewei, et al.
Publicado: (2025)

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
por: Li, Zongxia, et al.
Publicado: (2025)

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
por: Liu, Yuanxin, et al.
Publicado: (2025)

Video-CoE: Reinforcing Video Event Prediction via Chain of Events
por: Su, Qile, et al.
Publicado: (2026)

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
por: Yang, Ruoliu, et al.
Publicado: (2026)

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
por: Yang, Yuxiao, et al.
Publicado: (2025)

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
por: He, Yuping, et al.
Publicado: (2025)

VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking
por: Meng, Desen, et al.
Publicado: (2025)

DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
por: Wang, Weitao, et al.
Publicado: (2025)

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
por: Guan, Kaisi, et al.
Publicado: (2025)

VUDG: A Dataset for Video Understanding Domain Generalization
por: Wang, Ziyi, et al.
Publicado: (2025)

Towards Universal Soccer Video Understanding
por: Rao, Jiayuan, et al.
Publicado: (2024)

Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
por: Wu, Jianzong, et al.
Publicado: (2025)

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
por: Wang, Ziyue, et al.
Publicado: (2026)