Image de couverture de livre

Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vani, Sameep, Jena, Shreyas, Patel, Maitreya, Baral, Chitta, Aditya, Somak, Yang, Yezhou
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

$λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
par: Patel, Maitreya, et autres
Publié: (2024)

Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?
par: Sampat, Shailaja Keyur, et autres
Publié: (2024)

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
par: Patel, Maitreya, et autres
Publié: (2023)

AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models
par: Malaviya, Vatsal, et autres
Publié: (2025)

RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
par: Pathiraja, Bimsara, et autres
Publié: (2025)

TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
par: Patel, Maitreya, et autres
Publié: (2024)

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
par: Kusumba, Abhiram, et autres
Publié: (2025)

TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark
par: Fallah, Forouzan, et autres
Publié: (2025)

VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
par: Yilmaz, Nilay, et autres
Publié: (2025)

ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions
par: Sampat, Shailaja Keyur, et autres
Publié: (2024)

Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
par: Cheng, Sheng, et autres
Publié: (2024)

On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
par: Chatterjee, Agneet, et autres
Publié: (2024)

Dual Caption Preference Optimization for Diffusion Models
par: Saeidi, Amir, et autres
Publié: (2025)

Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images
par: Luo, Yiran, et autres
Publié: (2024)

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models
par: Chatterjee, Agneet, et autres
Publié: (2024)

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
par: Kim, Changhoon, et autres
Publié: (2023)

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
par: Patel, Maitreya, et autres
Publié: (2024)

VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
par: Patel, Maitreya, et autres
Publié: (2026)

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
par: Chatterjee, Agneet, et autres
Publié: (2025)

Chimera: Compositional Image Generation using Part-based Concepting
par: Singh, Shivam, et autres
Publié: (2025)

Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations
par: Liu, Xiangrui, et autres
Publié: (2025)

MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations
par: Yilmaz, Nilay, et autres
Publié: (2026)

VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks
par: Sampat, Shailaja Keyur, et autres
Publié: (2024)

MMTABREAL: Real-World Benchmark for Multimodal Table Understanding
par: Titiya, Prasham, et autres
Publié: (2025)

GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
par: Siingh, Shikhhar, et autres
Publié: (2025)

Lost in Translation? Translation Errors and Challenges for Fair Assessment of Text-to-Image Models on Multilingual Concepts
par: Saxon, Michael, et autres
Publié: (2024)

Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
par: Rasekh, Ali, et autres
Publié: (2025)

Getting it Right: Improving Spatial Consistency in Text-to-Image Models
par: Chatterjee, Agneet, et autres
Publié: (2024)

Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding
par: Chatterjee, Dibyadip, et autres
Publié: (2025)

SKoPe3D: A Synthetic Dataset for Vehicle Keypoint Perception in 3D from Traffic Monitoring Cameras
par: Pahadia, Himanshu, et autres
Publié: (2023)

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
par: Sun, Yiming, et autres
Publié: (2025)

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs
par: Anvekar, Tejas, et autres
Publié: (2025)

Harnessing Object Grounding for Time-Sensitive Video Understanding
par: Wu, Tz-Ying, et autres
Publié: (2025)

CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models
par: Suin, Maitreya, et autres
Publié: (2024)

SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
par: Chanda, Kaustav, et autres
Publié: (2025)

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
par: Wang, Shaobo, et autres
Publié: (2025)

Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
par: Li, Haoxin, et autres
Publié: (2025)

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
par: Jiang, Songtao, et autres
Publié: (2026)

TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos
par: Fateh, Fawad Javed, et autres
Publié: (2024)

IFSENet : Harnessing Sparse Iterations for Interactive Few-shot Segmentation Excellence
par: Chandgothia, Shreyas, et autres
Publié: (2024)