arXiv Computer Vision
VideoSTF: Stress-Testing Output Repetition in Video Large Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 18
Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models
The paper introduces REVEAL, a diagnostic benchmark that stresses Video‑Language Models (VidLMs) on five controlled probes—camera‑motion sensitivity, cross‑frame integration, video sycophancy, language‑only shortcuts, and temporal expectation bias—to assess how well these models encode and use visual evidence. Experiments on 12 VidLMs reveal systematic failures: some visual signals are never reliably encoded, while others are overridden by model priors, leading to performance below chance on several probes that humans solve with high accuracy. Mechanistic probes further pinpoint where and why visual evidence is lost, demonstrating that under assertive prompts a model’s output becomes nearly invariant to real versus random video input, rendering visual evidence causally inert.
arXiv AI
Jul 16
Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks
arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
arXiv Machine Learning
Sep 22
TempCore: Are Video QA Benchmarks Temporally Grounded?
arXiv:2509.01167v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current...
arXiv Computer Vision
3d ago
RESUME: Recurrent State Updates from Motion and Residual Signals for Efficient Video Language Modeling
arXiv:2609.39563v1 Announce Type: new Abstract: Existing video language models encode sampled RGB frames independently, so a long video must either exhaust the token budget or drop the changes betwee...
arXiv AI
Aug 7
The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
arXiv:2608. 06361v1 Announce Type: new Abstract: Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate.
arXiv Machine Learning
Jun 9
Echo-Memory: A Controlled Study of Memory in Action World Models
arXiv:2606. 09803v1 Announce Type: cross Abstract: We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models.