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.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
TRACE (Temporal Audit and Condition-aware Evaluation) is a new benchmark and evaluation framework for streaming video understanding that explicitly records when evidence becomes valid, how visual history is maintained, and how responses are triggered. It combines temporally audited visual tasks, evidence timing, instruction-dependent trigger annotations, a unified causal Core–Adapter protocol, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. Using 1,240 records from 517 videos, TRACE evaluated eight publicly available models in eight configurations, revealing that similar QA accuracy can hide significant differences in completion, answer validity, generation workload, and proactive performance metrics such as response delay, false alarms, and missed target windows.
arXiv:2602.10639v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) have achieved strong performance on video understanding tasks, yet existing benchmarks evaluate only what m...
arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
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:2606. 02522v1 Announce Type: cross Abstract: Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.
arXiv:2606. 18586v1 Announce Type: cross Abstract: Physical events are not understood by their names alone, but by the causal state changes that compose them.