arXiv Computer Vision October 19, 2026 By Jingfeng Chen, Jiawen Qian, Wendi Deng, Yinuo Guo, Jiaqi Yu, Sicong Leng, Raghuveer Thirukovalluru, Bhuwan Dhingra

LDDR: Linear-DPP Dynamic-Resolution Frame Sampling for Video MLLMs

Read the original on arXiv Computer Vision →

LDDR (Linear DPP Dynamic Resolution) is a training‑free, budget‑aware video frame sampling framework designed for multimodal large language models (MLLMs). It uses query‑aware Determinantal Point Process (DPP) selection in a task‑conditioned feature space, achieving a 3× runtime speedup over standard DPP baselines. By assigning a non‑uniform token budget—allocating more tokens to informative, non‑redundant frames and downscaling or pruning less useful ones—LDDR improves performance by 2.5 points in low‑budget settings and 1.6 points in high‑budget scenarios across four video benchmarks and multiple MLLM families.

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 Computer Vision.

arXiv Computer Vision

Oct 1

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

arXiv:2608.05707v2 Announce Type: replace Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows....

By Wang Chen, Yu Chen, Xiang Wang, Shuai Li, Jinfa Huang, Xiawu Zheng

multimodal benchmarks

arXiv Computation and Language

Sep 15

MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding

arXiv:2609.15408v1 Announce Type: cross Abstract: Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computatio...

By Hongchang Shi, Jinpeng Hu, Ao Wang, Wenzheng Zhou, Hui Ma, Feng Li, Zenglin Shi

llms multimodal benchmarks

Hugging Face Trending Papers

Aug 6

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density.

benchmarks

arXiv Computer Vision

Oct 2

FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering

arXiv:2610.00573v1 Announce Type: new Abstract: Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant fram...

By Haifeng Huang, Biyin Xu, Chunsheng Xin, Yang Li

llms nlp multimodal benchmarks

arXiv AI

Jul 29

Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

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

llms multimodal benchmarks safety

arXiv AI

Sep 16

VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs

arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates co...

By Haoyu Guo, Yuan Feng, Junlin Lv, Mingjun Xiao, S Kevin Zhou, Xike Xie

llms multimodal