mlsanityData to 14 Oct 2026

MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models

arXiv 2510.19457 ↗First posted 22 Oct 2025cs.CLcited by 7

On the map: Multimodal LLMs / vision-language models → Image editing and quality assessment

Abstract (arXiv)

Large Multimodal Models (LMMs) encode rich factual knowledge via cross-modal pre-training, yet their static representations struggle to maintain an accurate understanding of time-sensitive factual knowledge. Existing benchmarks remain constrained by static designs, inadequately evaluating LMMs' ability to understand time-sensitive knowledge. To address this gap, we propose MINED, a comprehensive benchmark that evaluates temporal awareness along 6 key dimensions and 11 challenging tasks: cognition, awareness, trustworthiness, understanding, reasoning, and robustness. MINED is constructed from Wikipedia by two professional annotators, containing 2,104 time-sensitive knowledge samples spanning six knowledge types. Evaluating 15 widely used LMMs on MINED shows that Gemini-2.5-Pro achieves the highest average CEM score of 63.07, while most open-source LMMs still lack time understanding ability. Meanwhile, LMMs perform best on organization knowledge, whereas their performance is weakest on sport. To address these challenges, we investigate the feasibility of updating time-sensitive knowledge in LMMs through knowledge editing methods and observe that LMMs can effectively update knowledge via knowledge editing methods in single editing scenarios.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 45 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

38 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency19 Jun
  2. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark12 Mar
  3. 2024MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing18 Feb

Other references · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  7. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  8. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  9. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  10. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  11. 2021Fast Model Editing at Scalecited by 498
  12. 2022Memory-Based Model Editing at Scalecited by 447
23 more
  1. 2024mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Modelscited by 291
  2. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 285
  3. 2022RealTime QA: What's the Answer Right Now?cited by 244
  4. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
  5. 2021A Dataset for Answering Time-Sensitive Questionscited by 154
  6. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  7. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 121
  8. 2025PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selectioncited by 61
  9. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 51
  10. 2025CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Processcited by 51
  11. 2023Can We Edit Multimodal Large Language Models?cited by 44
  12. 2023Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Modelscited by 37
  13. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 34
  14. 2024DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMscited by 24
  15. 2025Seeking and Updating with Live Visual Knowledgecited by 24
  16. 2024Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understandingcited by 23
  17. 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledgecited by 23
  18. 2025Benchmarking Multimodal Knowledge Conflict for Large Multimodal Modelscited by 19
  19. 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solvingcited by 19
  20. 2024UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorizationcited by 17
  21. 2023MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Modelscited by 15
  22. 2024EvoWiki: Evaluating LLMs on Evolving Knowledgecited by 13
  23. 2022Spatial-Temporal Graph Convolutional Gated Recurrent Network for Traffic Forecastingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026OPD-V: Visual On-Policy Self-Distillation with Modality Balancecited by 8
  2. 2026ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoningcited by 6
  3. 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledgecited by 5
  4. 2026From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Searchcited by 5
  5. 2026Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Rankingcited by 3
  6. 2026Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guaranteescited by 1
  7. 2026AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Researchcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
  2. 2025Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
  3. 2026MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
  4. 2025KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
  5. 2025Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
  6. 2026Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos
  7. 2024Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
  8. 2026RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World