Cover Image

Hidden in plain sight: VLMs overlook their visual representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Stephanie, Bonnen, Tyler, Guillory, Devin, Darrell, Trevor
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
by: Qin, Yiming, et al.
Published: (2025)

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
by: Franco, Luca, et al.
Published: (2023)

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
by: Yu, Junwei, et al.
Published: (2025)

Reconstruction Alignment Improves Unified Multimodal Models
by: Xie, Ji, et al.
Published: (2025)

Compositional Chain-of-Thought Prompting for Large Multimodal Models
by: Mitra, Chancharik, et al.
Published: (2023)

REOrdering Patches Improves Vision Models
by: Kutscher, Declan, et al.
Published: (2025)

Visual Lexicon: Rich Image Features in Language Space
by: Wang, XuDong, et al.
Published: (2024)

InstanceDiffusion: Instance-level Control for Image Generation
by: Wang, Xudong, et al.
Published: (2024)

Lifting Embodied World Models for Planning and Control
by: Wang, Alex N., et al.
Published: (2026)

Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding
by: Chen, Tianyu, et al.
Published: (2025)

TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering
by: Shang, Chuyi, et al.
Published: (2024)

Navigation World Models
by: Bar, Amir, et al.
Published: (2024)

Rethinking VLMs and LLMs for Image Classification
by: Cooper, Avi, et al.
Published: (2024)

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
by: Li, Shuo, et al.
Published: (2024)

Self-supervised video pretraining yields robust and more human-aligned visual representations
by: Parthasarathy, Nikhil, et al.
Published: (2022)

CARES: Context-Aware Resolution Selector for VLMs
by: Kimhi, Moshe, et al.
Published: (2025)

DASH: Detection and Assessment of Systematic Hallucinations of VLMs
by: Augustin, Maximilian, et al.
Published: (2025)

Retrieval-Augmented VLMs for Multimodal Melanoma Diagnosis
by: Moon, Jihyun, et al.
Published: (2025)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
by: Huang, Brandon, et al.
Published: (2024)

Video Action Differencing
by: Burgess, James, et al.
Published: (2025)

Shape-Guided Diffusion with Inside-Outside Attention
by: Park, Dong Huk, et al.
Published: (2022)

Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight
by: Ding, Xi, et al.
Published: (2024)

DEAL: Disentangle and Localize Concept-level Explanations for VLMs
by: Li, Tang, et al.
Published: (2024)

PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor
by: Goel, Vidit, et al.
Published: (2023)

IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs
by: Faraz, Ali, et al.
Published: (2025)

Do We Need Large VLMs for Spotting Soccer Actions?
by: Chakraborty, Ritabrata, et al.
Published: (2025)

ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs
by: Burgess, James, et al.
Published: (2026)

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
by: Zhang, Jianrui, et al.
Published: (2026)

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation
by: Chen, Weixin, et al.
Published: (2026)

Stochastic positional embeddings improve masked image modeling
by: Bar, Amir, et al.
Published: (2023)

Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint
by: Lee, Heekyung, et al.
Published: (2025)

Analyzing The Language of Visual Tokens
by: Chan, David M., et al.
Published: (2024)

Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs
by: Izadi, Amirmohammad, et al.
Published: (2025)

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
by: Li, Kevin Y., et al.
Published: (2024)

COVR:Collaborative Optimization of VLMs and RL Agent for Visual-Based Control
by: Xia, Canming, et al.
Published: (2026)

Reinforcing VLMs to Use Tools for Detailed Visual Reasoning Under Resource Constraints
by: Kumar, Sunil, et al.
Published: (2025)

Right this way: Can VLMs Guide Us to See More to Answer Questions?
by: Liu, Li, et al.
Published: (2024)

ALOHa: A New Measure for Hallucination in Captioning Models
by: Petryk, Suzanne, et al.
Published: (2024)

Whole-Body Conditioned Egocentric Video Prediction
by: Bai, Yutong, et al.
Published: (2025)

VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
by: Kim, Minkyu, et al.
Published: (2026)