TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
By Baiqi Li, Kangyi Zhao, Ce Zhang, Chancharik Mitra, Jean de Dieu Nyandwi, Gedas Bertasius
TAME is a CLIP‑based framework for Text‑Video Retrieval that incorporates temporal modeling through three key innovations: sparse Mixture‑of‑Experts layers with frame‑consistent routing, Frame‑Temporal tokens that aggregate cross‑frame information, and a Cross‑Temporal Interaction and Aggregation module for refining frame‑wise similarities. These components enable the model to capture both local visual patterns and long‑range temporal dependencies, leading to consistent performance gains over CLIP‑based baselines on multiple TVR benchmarks, including a 4.0 R@1 improvement on MSR‑VTT. The code is publicly available on GitHub.
By Uicheol Jung, Juyoung Hong, Hojung Kwon, Yukyung Choi
TAME introduces a Temporal-Aware Mixture-of-Experts framework for Text-Video Retrieval that enhances CLIP-based models by incorporating frame-level structure and temporal relations. It adds sparse Mixture-of-Experts layers with frame-consistent routing, Frame-Temporal tokens for global cross-frame aggregation, and a Cross-Temporal Interaction and Aggregation module to refine sentence-video similarities. Experiments on multiple TVR benchmarks show consistent performance gains, such as a 4.0 R@1 improvement on MSR‑VTT over CLIP4Clip.
FastBench is a new benchmark that tests streaming Video‑Large‑Language Models (VLMs) on high‑dynamic real‑world video streams, where events occur rapidly and cannot be captured by sparse 1–2 FPS sampling. The benchmark uses a trajectory‑grounded pipeline that generates QA pairs from high‑FPS clips, filters questions answerable at 2 FPS, verifies answers with SAM3 and CoTracker3 trajectories, and incorporates three rounds of human inspection, yielding 306 QA pairs across eight domains and multiple temporal scopes. Experiments show that even the strongest model, Gemini‑3.5‑Flash, achieves only 50.7 % accuracy, and that denser sampling improves performance but saturates when history is compressed; a training‑free baseline, ProactiveFrame, outperforms uniform sampling but still falls short of oracle‑guided focusing.
By Yuxuan Hu, Weikang Shi, Yang Bo, Xudong Lu, Xintong Guo, Shuhan Li, Yuyang He, Huankang Guan, Peiwen Sun, Yunqiao Yang, Wenbo Li, Rui Liu, Hongsheng Li
arXiv:2606. 06853v1 Announce Type: cross Abstract: The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding.
By Yifan Xu, Chao Zhang, Ruifei Ma, Fei Gao, Zhifei Yang, Jiaxing Qi, Zhipeng Chen
arXiv:2607. 24794v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding.
By Linghao Meng, Qiankun Li, Junyuan Mao, Pujin Liao, Zhicheng He, Enbo Zhang, Kun Wang, Yang Liu, Huazhu Fu, Yueming Jin
arXiv:2608.27871v1 Announce Type: new
Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruc...
By Ziling Huang, Shin'ichi Satoh
StreamPI introduces a streaming multimodal temporal modeling framework that enhances Vision‑Language‑Action models by adding temporal reasoning without extra parameters. It anchors each visual observation and language instruction pair as a temporal unit, using bidirectional attention for cross‑modal fusion and causal attention for autoregressive streaming inference. The method employs random‑interval streaming training to improve robustness and leverages the LLM backbone’s length extrapolation to inherit pretrained weights, achieving superior performance over pi0.5 on real‑robot and simulation tasks.
By Zhe Liu, Jinghua Hou, Yuxiang Lu, Zhenya Yang, Xianzhe Fan, Junwei Luo, Junyi Li, Ruihua Han, Zhi Hou, Hengshuang Zhao
arXiv:2606. 05702v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored.
By Haoyu Zhou, Qing Qing, Caichong Li, Qixin Zhang, Yongcheng Jing, Ziqi Xu, Juncheng Hu, Xikun Zhang, Renqiang Luo
VETO (Video Efficient Token Optimization for Vision Language Models) is a plug‑in that reduces the quadratic cost of visual tokens in long‑video inference by applying dual‑axis compression: an intra‑frame compressor merges semantically similar tokens within each frame, and an inter‑frame compressor merges temporally redundant frames. By first compressing spatial dimensions, VETO lowers the cost of subsequent global temporal matching, surpassing single‑axis methods and achieving up to 45% faster inference on models such as LLaVA‑OneVision‑7B while maintaining or improving accuracy. The approach is universally applicable across LLaVA‑OneVision, InternVL‑2.5, and LongVA, preserving or enhancing zero‑shot accuracy even under extreme token budgets.
By Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen, Winston H. Hsu
The paper introduces structured video prompting, a training‑free inference‑time technique that augments input videos with lightweight spatial and temporal structure to provide explicit anchors for evidence organization. By applying this method to two video benchmarks and two open video‑language models, the authors demonstrate performance improvements across several tasks, with gains varying by model and task. The study suggests that failures in video‑language models stem not only from reasoning capacity but also from how video evidence is presented during inference.
By Sadegh Mohammadian
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.
By Xiaolin Liu, Yilun Zhu, Xiangyu Zhao, Xuehui Wang, Yan Li, Xin Li, Haoyu Cao, Xing Sun, Shaofeng Zhang, Xu Yang, Zhihang Zhong, Xue Yang