Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
Fuente:
arXiv
Saved in:
| Main Authors: | Qiu, Jason, Meurer, Zachary, Thomas, Xavier, Ghadiyaram, Deepti |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
by: Chen, Tianle, et al.
Published: (2026)
by: Chen, Tianle, et al.
Published: (2026)
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
by: Thomas, Xavier, et al.
Published: (2025)
by: Thomas, Xavier, et al.
Published: (2025)
$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models
by: Kim, Dahye, et al.
Published: (2024)
by: Kim, Dahye, et al.
Published: (2024)
Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
by: Kim, Dahye, et al.
Published: (2025)
by: Kim, Dahye, et al.
Published: (2025)
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
by: Thomas, Xavier, et al.
Published: (2025)
by: Thomas, Xavier, et al.
Published: (2025)
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
by: Saichandran, Ketan Suhaas, et al.
Published: (2025)
by: Saichandran, Ketan Suhaas, et al.
Published: (2025)
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
by: Chen, Tianle, et al.
Published: (2025)
by: Chen, Tianle, et al.
Published: (2025)
DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
by: Kim, Dahye, et al.
Published: (2026)
by: Kim, Dahye, et al.
Published: (2026)
Improving Physical Object State Representation in Text-to-Image Generative Systems
by: Chen, Tianle, et al.
Published: (2025)
by: Chen, Tianle, et al.
Published: (2025)
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
by: Ikechukwu, Nicholas, et al.
Published: (2026)
by: Ikechukwu, Nicholas, et al.
Published: (2026)
FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
by: Lim, Youngsun, et al.
Published: (2026)
by: Lim, Youngsun, et al.
Published: (2026)
TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
by: Stergiou, Alexandros
Published: (2025)
by: Stergiou, Alexandros
Published: (2025)
Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary
by: Tasnim, Nazia, et al.
Published: (2026)
by: Tasnim, Nazia, et al.
Published: (2026)
Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs
by: Tasnim, Nazia, et al.
Published: (2025)
by: Tasnim, Nazia, et al.
Published: (2025)
Learning Geometric Invariance for Gait Recognition
by: Wang, Zengbin, et al.
Published: (2026)
by: Wang, Zengbin, et al.
Published: (2026)
Swift Sampling: Selecting Temporal Surprises via Taylor Series
by: Kim, Dahye, et al.
Published: (2026)
by: Kim, Dahye, et al.
Published: (2026)
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
by: Ramaswamy, Vikram V., et al.
Published: (2023)
by: Ramaswamy, Vikram V., et al.
Published: (2023)
VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
by: Zhang, Zaiwei, et al.
Published: (2024)
by: Zhang, Zaiwei, et al.
Published: (2024)
Semantic-Enriched Latent Visual Reasoning
by: Xu, Tianrun, et al.
Published: (2026)
by: Xu, Tianrun, et al.
Published: (2026)
PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
by: Zhou, Weijie, et al.
Published: (2025)
by: Zhou, Weijie, et al.
Published: (2025)
Do Image-Text Metrics Respect Semantic Invariances?
by: Agarwal, Amit, et al.
Published: (2026)
by: Agarwal, Amit, et al.
Published: (2026)
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
by: Zhang, Yiming, et al.
Published: (2026)
by: Zhang, Yiming, et al.
Published: (2026)
Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
by: Wang, Wentao, et al.
Published: (2025)
by: Wang, Wentao, et al.
Published: (2025)
Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
by: Tang, Yolo Y., et al.
Published: (2025)
by: Tang, Yolo Y., et al.
Published: (2025)
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
by: Zhang, Di, et al.
Published: (2024)
by: Zhang, Di, et al.
Published: (2024)
Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
by: Bao, Wentao, et al.
Published: (2024)
by: Bao, Wentao, et al.
Published: (2024)
Does VLM Classification Benefit from LLM Description Semantics?
by: Ma, Pingchuan, et al.
Published: (2024)
by: Ma, Pingchuan, et al.
Published: (2024)
Visually Prompted Benchmarks Are Surprisingly Fragile
by: Feng, Haiwen, et al.
Published: (2025)
by: Feng, Haiwen, et al.
Published: (2025)
GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder
by: Cho, Seunghyuk, et al.
Published: (2025)
by: Cho, Seunghyuk, et al.
Published: (2025)
SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
by: Lin, Jiawen, et al.
Published: (2025)
by: Lin, Jiawen, et al.
Published: (2025)
CogVLM: Visual Expert for Pretrained Language Models
by: Wang, Weihan, et al.
Published: (2023)
by: Wang, Weihan, et al.
Published: (2023)
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
by: Huang, Chen, et al.
Published: (2026)
by: Huang, Chen, et al.
Published: (2026)
VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)
by: Xu, Runsen, et al.
Published: (2024)
Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
by: Kakda, Mohit, et al.
Published: (2026)
by: Kakda, Mohit, et al.
Published: (2026)
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
by: Wen, Jiawen, et al.
Published: (2026)
by: Wen, Jiawen, et al.
Published: (2026)
TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos
by: Fateh, Fawad Javed, et al.
Published: (2024)
by: Fateh, Fawad Javed, et al.
Published: (2024)
PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Models
by: Li, Yuliang, et al.
Published: (2026)
by: Li, Yuliang, et al.
Published: (2026)
Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?
by: Kuchibhotla, Hari Chandana, et al.
Published: (2024)
by: Kuchibhotla, Hari Chandana, et al.
Published: (2024)
PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
by: Chang, Zewei, et al.
Published: (2025)
by: Chang, Zewei, et al.
Published: (2025)
MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding
by: Xie, Rongchang, et al.
Published: (2024)
by: Xie, Rongchang, et al.
Published: (2024)
Similar Items
-
A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
by: Chen, Tianle, et al.
Published: (2026) -
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
by: Thomas, Xavier, et al.
Published: (2025) -
$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models
by: Kim, Dahye, et al.
Published: (2024) -
Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
by: Kim, Dahye, et al.
Published: (2025) -
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
by: Thomas, Xavier, et al.
Published: (2025)