Cover Image

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zhen, Jian, Ping, Guo, Zhongbin, Zhang, Zuming, Li, Chengzhi, Deng, Yonghong, Zhang, Xinyue, Lu, Wenpeng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
by: Deng, Yonghong, et al.
Published: (2026)

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
by: Guo, Zhongbin, et al.
Published: (2026)

TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models
by: Guo, Zhongbin, et al.
Published: (2025)

Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
by: Li, Chengzhi, et al.
Published: (2025)

Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression
by: Guo, Zhongbin, et al.
Published: (2025)

LISA-3D: Lifting Language-Image Segmentation to 3D via Multi-View Consistency
by: Guo, Zhongbin, et al.
Published: (2025)

HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?
by: Zhang, Yusen, et al.
Published: (2025)

How Do VLAs Effectively Inherit from VLMs?
by: Zhang, Chuheng, et al.
Published: (2025)

Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT
by: Wang, Jiacheng, et al.
Published: (2026)

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding
by: Ye, Junyi, et al.
Published: (2024)

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
by: Cui, Chenhang, et al.
Published: (2026)

Understanding and Rectifying Safety Perception Distortion in VLMs
by: Zou, Xiaohan, et al.
Published: (2025)

Optimizing Fire Suppression Strategies for Lithium‐Ion Battery Thermal Runaway: A Comparative Study of Foam‐Based Extinguishing Protocols
by: Zhongbin Fei, et al.
Published: (2026)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
by: Berman, Shmuel, et al.
Published: (2025)

Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations
by: Liang, Chen, et al.
Published: (2026)

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

SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
by: Zhang, Jianshu, et al.
Published: (2026)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
by: Jiang, Yukun, et al.
Published: (2026)

How Well Do LLMs Understand Tunisian Arabic?
by: Mahdi, Mohamed
Published: (2025)

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
by: Liu, Zhining, et al.
Published: (2026)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

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

Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
by: Kuo, Shang-Jui Ray, et al.
Published: (2026)

Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?
by: Balepur, Nishant, et al.
Published: (2024)

Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation
by: Zhou, Ziya, et al.
Published: (2024)

On the Perception Bottleneck of VLMs for Chart Understanding
by: Liu, Junteng, et al.
Published: (2025)

A Separation Principle for Conditional Mean-Field Type Linear Quadratic Optimal Control Problem
by: Guo, Zhongbin, et al.
Published: (2025)

Some interesting number theory problems
by: Zhang, Wenpeng
Published: (2025)

A century problem related to the Legendre symbol modulo p
by: Zhang, Wenpeng
Published: (2025)

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs
by: Zhang, Yuyou, et al.
Published: (2025)

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2025)

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
by: Chen, Zejian, et al.
Published: (2026)

For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
by: Deng, Wenlong, et al.
Published: (2025)

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning
by: Zhang, Xuanyu, et al.
Published: (2025)

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs
by: Li, Weiming, et al.
Published: (2025)

Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
by: Huang, Feiyang, et al.
Published: (2026)

A Stable SBP-SAT FDTD Subgridding Method Without Region Split
by: Wang, Yuhui, et al.
Published: (2026)

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
by: Zhong, Chengzhi, et al.
Published: (2024)

How Do LLMs Perform Two-Hop Reasoning in Context?
by: Guo, Tianyu, et al.
Published: (2025)

How Well Do Multi-modal LLMs Interpret CT Scans? An Auto-Evaluation Framework for Analyses
by: Zhu, Qingqing, et al.
Published: (2024)