DementiaCare-Bench is a new video benchmark designed to evaluate video-language models (VLMs) on understanding behavioral and psychological symptoms of dementia (BPSD). It contains 56 caregiver training videos, 94 clips across nine BPSD categories, and 2023 questions that are grounded in transcript spans and labeled by their visual demand. The benchmark reveals that most VLMs perform well on questions answerable by language alone but struggle with those requiring ordered frames, and a lightweight LoRA fine‑tune (DemCare‑VLM) can improve video dependence.
arXiv:2608. 13113v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks.
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:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
EgoMemReason is a new benchmark for week‑long egocentric video understanding that focuses on memory‑driven reasoning rather than simple perception tasks. It tests three memory types—entity, event, and behavior—across 500 questions, each requiring evidence from an average of 5.1 video segments and 25.9 hours of backtracking. Evaluation of 17 models shows that even the best achieves only 39.6% accuracy, highlighting the difficulty of long‑horizon memory in multimodal systems.
arXiv:2608. 07435v1 Announce Type: cross Abstract: Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify.
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
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:2608. 14015v1 Announce Type: cross Abstract: Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time.
The paper introduces PACE, a factor-guided, progressive framework for acquiring evidence in long-video question answering. PACE first indexes clip-level descriptions using question-derived factors, then refines evidence retrieval with contrastive cues derived from candidate answers. On the MMR‑V dataset, PACE achieves 42.6% accuracy and recovers 66.9% of annotated cues, outperforming direct inference and prior agentic baselines, and shows consistent improvements across several long-video benchmarks.
Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7--8B models now reach 37--38% on InfiniBench's global appearance task, which asks exactly that.
arXiv:2607. 01751v1 Announce Type: cross Abstract: Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time.
arXiv:2606. 16353v1 Announce Type: cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.