Image de couverture de livre

Symbolic Grounding Reveals Representational Bottlenecks in Abstract Visual Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vaishnav, Mohit, Tammet, Tanel
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language 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

A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs
par: Vaishnav, Mohit, et autres
Publié: (2025)

Beyond the Linear Separability Ceiling: Aligning Representations in VLMs
par: Vompa, Enrico, et autres
Publié: (2025)

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
par: Prasad, Archiki, et autres
Publié: (2023)

VGR: Visual Grounded Reasoning
par: Wang, Jiacong, et autres
Publié: (2025)

On Data Synthesis and Post-training for Visual Abstract Reasoning
par: Zhu, Ke, et autres
Publié: (2025)

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation
par: Yu, Shoubin, et autres
Publié: (2025)

ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities
par: Zhu, Chenming, et autres
Publié: (2024)

Visual Grounding Methods for VQA are Working for the Wrong Reasons!
par: Shrestha, Robik, et autres
Publié: (2020)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
par: Ghosh, Sreyan, et autres
Publié: (2024)

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
par: Wang, Haochen, et autres
Publié: (2025)

DRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
par: Iyengar, Anirudh Iyengar Kaniyar Narayana, et autres
Publié: (2026)

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
par: Acuna, David, et autres
Publié: (2025)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
par: Tartaglini, Alexa R., et autres
Publié: (2025)

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
par: Wang, Ziyang, et autres
Publié: (2024)

KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding
par: Ma, Xinyu, et autres
Publié: (2025)

Seeing Culture: A Benchmark for Visual Reasoning and Grounding
par: Satar, Burak, et autres
Publié: (2025)

Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding
par: Sun, Shenghuan, et autres
Publié: (2024)

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
par: Fu, Xingyu, et autres
Publié: (2023)

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
par: Yu, Shoubin, et autres
Publié: (2026)

Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding
par: Kawasaki, Haruka, et autres
Publié: (2026)

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
par: Li, Zejun, et autres
Publié: (2024)

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
par: Yu, Shoubin, et autres
Publié: (2024)

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
par: Lee, Daeun, et autres
Publié: (2026)

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
par: Yu, Zhuoran, et autres
Publié: (2025)

Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
par: Li, Aiden Yiliu, et autres
Publié: (2025)

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
par: Lee, Daeun, et autres
Publié: (2025)

The Scaling Properties of Implicit Deductive Reasoning in Transformers
par: Vompa, Enrico, et autres
Publié: (2026)

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
par: Yan, Hao, et autres
Publié: (2025)

Efficient Adaptation For Remote Sensing Visual Grounding
par: Moughnieh, Hasan, et autres
Publié: (2025)

The Role of Entropy in Visual Grounding: Analysis and Optimization
par: Li, Shuo, et autres
Publié: (2025)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
par: Pothiraj, Atin, et autres
Publié: (2025)

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
par: Yu, Shoubin, et autres
Publié: (2025)

Unbiased Visual Reasoning with Controlled Visual Inputs
par: Li, Zhaonan, et autres
Publié: (2025)

Multimodal Fact-Level Attribution for Verifiable Reasoning
par: Wan, David, et autres
Publié: (2026)

Error-Driven Scene Editing for 3D Grounding in Large Language Models
par: Zhang, Yue, et autres
Publié: (2025)

TimeRefine: Temporal Grounding with Time Refining Video LLM
par: Wang, Xizi, et autres
Publié: (2024)

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
par: Li, You, et autres
Publié: (2025)

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
par: Yu, Shoubin, et autres
Publié: (2026)

Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models
par: Siddique, Md. Abu Bakor, et autres
Publié: (2026)

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
par: Wu, Qianhui, et autres
Publié: (2025)