Imagen de Portada

Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sharma, Shivam, Nagaonkar, Sankalp, Choithani, Ashish, Trivedi, Ashutosh
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
por: Nagaonkar, Sankalp, et al.
Publicado: (2025)

BadScan: An Architectural Backdoor Attack on Visual State Space Models
por: Deshmukh, Om Suhas, et al.
Publicado: (2024)

SceneGPT: A Language Model for 3D Scene Understanding
por: Chandhok, Shivam
Publicado: (2024)

TM-PATHVQA:90000+ Textless Multilingual Questions for Medical Visual Question Answering
por: Rajkhowa, Tonmoy, et al.
Publicado: (2024)

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
por: Zhang, Jialiang, et al.
Publicado: (2026)

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
por: Kang, Hyolim, et al.
Publicado: (2025)

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
por: Qi, Zhangyang, et al.
Publicado: (2025)

Do Vision-Language Foundational models show Robust Visual Perception?
por: Chandhok, Shivam, et al.
Publicado: (2024)

Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
por: Chen, Seng Nam, et al.
Publicado: (2026)

Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
por: Lee, Jonathan, et al.
Publicado: (2025)

Streaming Long Video Understanding with Large Language Models
por: Qian, Rui, et al.
Publicado: (2024)

StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
por: Hu, Yuhang, et al.
Publicado: (2025)

Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models
por: Berman, Nimrod, et al.
Publicado: (2025)

Do Vision--Language Models Understand 3D Scenes or Just Catalogue Objects?
por: Maheshwari, Animesh, et al.
Publicado: (2026)

Vision-Language Models Do Not Understand Negation
por: Alhamoud, Kumail, et al.
Publicado: (2025)

Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
por: Bharadwaj, Siddhant, et al.
Publicado: (2026)

IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
por: Liu, Parker, et al.
Publicado: (2025)

ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models
por: Darabi, Nastaran, et al.
Publicado: (2026)

Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models
por: Pham, Tan-Hanh, et al.
Publicado: (2025)

RLM: A Vision-Language Model Approach for Radar Scene Understanding
por: Mishra, Pushkal, et al.
Publicado: (2025)

Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning
por: Liang, Dayong, et al.
Publicado: (2025)

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
por: Makarov, Vladislav, et al.
Publicado: (2026)

Do Vision-Language Models Really Understand Visual Language?
por: Hou, Yifan, et al.
Publicado: (2024)

Do Vision-Language Models Understand Compound Nouns?
por: Kumar, Sonal, et al.
Publicado: (2024)

Do Vision-Language Models Understand Visual Persuasiveness?
por: Park, Gyuwon
Publicado: (2025)

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
por: Li, Yue, et al.
Publicado: (2025)

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
por: Ma, Ke, et al.
Publicado: (2026)

Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
por: Addepalli, Sravanti, et al.
Publicado: (2023)

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
por: Gholami, Mohsen, et al.
Publicado: (2025)

Embodied Scene Understanding for Vision Language Models via MetaVQA
por: Wang, Weizhen, et al.
Publicado: (2025)

VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding
por: Kim, Younggun, et al.
Publicado: (2025)

On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning
por: Kim, Geewook, et al.
Publicado: (2024)

Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models
por: Wang, Yuqing, et al.
Publicado: (2023)

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
por: Jeon, Yerim, et al.
Publicado: (2025)

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
por: Kim, Joowon, et al.
Publicado: (2026)

The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding
por: Rosenberg, Gillian, et al.
Publicado: (2026)

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
por: Chen, Yangyi, et al.
Publicado: (2023)

FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning
por: Chen, Haodong, et al.
Publicado: (2025)

StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding
por: Tang, Guowei, et al.
Publicado: (2026)

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
por: Feng, Zhiyuan, et al.
Publicado: (2025)