Cover Image

Physics Knowledge in Frontier Models: A Diagnostic Study of Failure Modes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bagdonaviciute, Ieva, Vineet, Vibhav
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Navigating Hallucinations for Reasoning of Unintentional Activities
by: Grover, Shresth, et al.
Published: (2024)

HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding
by: Azad, Shehreen, et al.
Published: (2025)

StreamReady: Learning What to Answer and When in Long Streaming Videos
by: Azad, Shehreen, et al.
Published: (2026)

A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning
by: Kumar, Akash, et al.
Published: (2025)

OmViD: Omni-supervised active learning for video action detection
by: Rana, Aayush, et al.
Published: (2025)

Understanding Depth and Height Perception in Large Visual-Language Models
by: Azad, Shehreen, et al.
Published: (2024)

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
by: Modi, Rajat, et al.
Published: (2024)

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
by: Grover, Shresth, et al.
Published: (2025)

PEEKABOO: Interactive Video Generation via Masked-Diffusion
by: Jain, Yash, et al.
Published: (2023)

Robustness Analysis on Foundational Segmentation Models
by: Schiappa, Madeline Chantry, et al.
Published: (2023)

Grounding Task Assistance with Multimodal Cues from a Single Demonstration
by: Sarch, Gabriel, et al.
Published: (2025)

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames
by: Ravi, Sahithya, et al.
Published: (2025)

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
by: Wang, Jiayu, et al.
Published: (2024)

OS-Marathon: Benchmarking Computer-Use Agents on Long-Horizon Repetitive Tasks
by: Wu, Jing, et al.
Published: (2026)

Simplifying Knowledge Transfer in Pretrained Models
by: Jain, Siddharth, et al.
Published: (2025)

PRIME: Prioritizing Interpretability in Failure Mode Extraction
by: Rezaei, Keivan, et al.
Published: (2023)

Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment
by: Zhang, Yue, et al.
Published: (2025)

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
by: Hayes, Kevin David, et al.
Published: (2025)

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
by: Zhao, Brian Nlong, et al.
Published: (2023)

A Study of Failure Modes in Two-Stage Human-Object Interaction Detection
by: Wang, Lemeng, et al.
Published: (2026)

MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
by: Joshi, Siddharth, et al.
Published: (2025)

More Images, More Problems? A Controlled Analysis of VLM Failure Modes
by: Das, Anurag, et al.
Published: (2026)

Discovering Failure Modes in Vision-Language Models using RL
by: Jain, Kanishk, et al.
Published: (2026)

How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders
by: Tang, Yiming, et al.
Published: (2025)

Scanner-Agnostic MRI Harmonization via SSIM-Guided Disentanglement
by: Caldera, Luca, et al.
Published: (2025)

Understanding the Failure Modes of Out-of-Distribution Generalization
by: Nagarajan, Vaishnavh, et al.
Published: (2020)

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction
by: Agarwal, Aishwarya, et al.
Published: (2024)

Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
by: Shao, Jie, et al.
Published: (2025)

WorldBench: Disambiguating Physics for Diagnostic Evaluation of World Models
by: Upadhyay, Rishi, et al.
Published: (2026)

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models
by: Moayeri, Mazda, et al.
Published: (2024)

Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation
by: Peddi, Rohith, et al.
Published: (2024)

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
by: Balakrishnan, Ravikumar, et al.
Published: (2026)

PLUTO-4: Frontier Pathology Foundation Models
by: Padigela, Harshith, et al.
Published: (2025)

NVILA: Efficient Frontier Visual Language Models
by: Liu, Zhijian, et al.
Published: (2024)

Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data
by: Sharma, Yash Kumar, et al.
Published: (2025)

Fara-7B: An Efficient Agentic Model for Computer Use
by: Awadallah, Ahmed, et al.
Published: (2025)

Advancing Egocentric Video Question Answering with Multimodal Large Language Models
by: Patel, Alkesh, et al.
Published: (2025)

A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding
by: Zhang, Yue, et al.
Published: (2026)

FoundBioNet: A Foundation-Based Model for IDH Genotyping of Glioma from Multi-Parametric MRI
by: Farahani, Somayeh, et al.
Published: (2025)

AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
by: Basappa, Aahana, et al.
Published: (2026)