Cover Image

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Eltahir, Mohamed, Ayash, Lama, Habibullah, Ali, Hussain, Tanveer, Khan, Naeemullah
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VideoAtlas: Navigating Long-Form Video in Logarithmic Compute
by: Eltahir, Mohamed, et al.
Published: (2026)

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers
by: Eltahir, Mohamed, et al.
Published: (2025)

PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training
by: Altuuaim, Sattam, et al.
Published: (2026)

GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids
by: Eltahir, Mohamed, et al.
Published: (2026)

Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric
by: Eltahir, Mohamed, et al.
Published: (2025)

AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks
by: Eltahir, Mohamed, et al.
Published: (2025)

A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs
by: Vaishnav, Mohit, et al.
Published: (2025)

Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
by: Liu, Zhining, et al.
Published: (2025)

Stateful Token Reduction for Long-Video Hybrid VLMs
by: Jiang, Jindong, et al.
Published: (2026)

Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMs
by: Ballout, Mohamad, et al.
Published: (2025)

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
by: Cheng, Junhao, et al.
Published: (2026)

Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization
by: Khan, Anas Anwarul Haq, et al.
Published: (2025)

TAPS : Frustratingly Simple Test Time Active Learning for VLMs
by: Sarkar, Dhruv, et al.
Published: (2025)

Adaptive Image Restoration for Video Surveillance: A Real-Time Approach
by: Amin, Muhammad Awais, et al.
Published: (2025)

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
by: Cai, Zhaolin, et al.
Published: (2025)

Probing Visual Language Priors in VLMs
by: Luo, Tiange, et al.
Published: (2024)

Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards
by: Gambashidze, Alexander, et al.
Published: (2025)

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
by: Gavrikov, Paul, et al.
Published: (2025)

Shaking the Fake: Detecting Deepfake Videos in Real Time via Active Probes
by: Xie, Zhixin, et al.
Published: (2024)

FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos
by: Li, Zhaolun, et al.
Published: (2025)

Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
by: Jha, Saurav, et al.
Published: (2025)

Linear Scaling Video VLMs for Long Video Understanding
by: Eyzaguirre, Cristobal, et al.
Published: (2026)

Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection
by: Harari, Daniel, et al.
Published: (2025)

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
by: Liang, Jiarong, et al.
Published: (2026)

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks
by: Zhou, Ting, et al.
Published: (2024)

Video-T1: Test-Time Scaling for Video Generation
by: Liu, Fangfu, et al.
Published: (2025)

Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
by: Chang, Chun-Peng, et al.
Published: (2026)

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
by: Lin, Kuanwei, et al.
Published: (2026)

PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning
by: Ma'sum, M. Anwar, et al.
Published: (2025)

PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning
by: Ma'sum, Muhammad Anwar, et al.
Published: (2024)

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

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
by: Pan, Junwen, et al.
Published: (2025)

TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
by: Guo, Chaohong, et al.
Published: (2025)

Adaptive Hybrid Optimizer based Framework for Lumpy Skin Disease Identification
by: Ubaidullah, et al.
Published: (2026)

Probing Visual Planning in Image Editing Models
by: Zhou, Zhimu, et al.
Published: (2026)

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

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
by: Tan, Shanwen, et al.
Published: (2026)

Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
by: Sun, Xiaoxiao, et al.
Published: (2026)

Prior2Posterior: Model Prior Correction for Long-Tailed Learning
by: Bhat, S Divakar, et al.
Published: (2024)

Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality
by: Toibazar, Daulet, et al.
Published: (2025)