paper-with-me

Papers

Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models

2026-02-11 · Sethuraman T, Savya Khosla, Aditi Tiwari, Vidya Ganesh, Rakshana Jayaprakash, Aditya Jain, Vignesh Srinivasakumar, Onkar Kishor Susladkar, Srinidhi Sunkara, Aditya Shanmugham, Rakesh Vaideeswaran, Abbaas Alif Mohamed Nishar, Simon Jenni, Derek Hoiem arxiv

This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a diagnostic benchmark that probes fundamental weaknesses of contemporary VidLMs through five controlled stress tests; assessing temporal expectation bias, reliance on language-only shortcuts, video sycophancy, camera motion sensitivity, and robustness to spatiotemporal occlusion. We test leading open- and closed-source VidLMs and find that these models confidently describe reversed scenes as forward, answer questions while neglecting video content, agree with false claims, struggle with basic camera motion, and fail to aggregate temporal information amidst simple spatiotemporal masking. Humans, on the other hand, succeed at these tasks with ease. Alongside our benchmark, we provide a data pipeline that automatically generates diagnostic examples for our stress tests, enabling broader and more scalable evaluation. We will release our benchmark and code to support future research.

📄 PDF Abstract BibTeX arXiv:2602.11244

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks

2020-02-14 · LREC 2020 5 · Carlos Aspillaga, Andrés Carvallo, Vladimir Araujo

There has been significant progress in recent years in the field of Natural Language Processing thanks to the introduction of the Transformer architecture. Current state-of-the-art models, via a large number of parameter…

Natural Language InferenceNatural Language UnderstandingQuestion Answering

Sim-to-Real Gentle Manipulation of Deformable and Fragile Objects with Stress-Guided Reinforcement Learning

2025-10-29 · Kei Ikemura, Yifei Dong, David Blanco-Mulero, Alberta Longhini 외 arxiv

Robotic manipulation of deformable and fragile objects presents significant challenges, as excessive stress can lead to irreversible damage to the object. While existing solutions rely on accurate object models or specia…

Reinforcement Learning

Stress Test Evaluation for Natural Language Inference

2018-06-02 · COLING 2018 8 · Aakanksha Naik, Abhilasha Ravichander, Norman Sadeh, Carolyn Rose 외

Natural language inference (NLI) is the task of determining if a natural language hypothesis can be inferred from a given premise in a justifiable manner. NLI was proposed as a benchmark task for natural language underst…

Natural Language InferenceNatural Language UnderstandingSentence

Notes on Correlation Stress Tests

2025-03-20 · Piotr Chmielowski

This note outlines an approach to stress testing of covariance of financial time series, in the context of financial risk management. It discusses how the geodesic distance between covariance matrices implies a notion of…

ManagementTime Series

When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems

2026-05-04 · Jose Manuel de la Chica, Juan Manuel Vera, Jairo Rodríguez arxiv

Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether per…