{"total":55,"rows":[{"id":"2506.04133","title":"TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems","created":"2025-06-04","cited_by_count":59,"area":"agents"},{"id":"2504.10191","title":"Localized Cultural Knowledge is Conserved and Controllable in Large Language Models","created":"2025-04-14","cited_by_count":20,"area":"wm"},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2508.07414","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","created":"2025-08-10","cited_by_count":16,"area":"mllm"},{"id":"2502.08779","title":"BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models","created":"2025-02-12","cited_by_count":11,"area":"mllm"},{"id":"2502.14865","title":"Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts","created":"2025-02-20","cited_by_count":11,"area":null},{"id":"2511.05681","title":"Culture in Action: Evaluating Text-to-Image Models through Social Activities","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2502.11361","title":"VLDBench Evaluating Multimodal Disinformation with Regulatory Alignment","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2503.16423","title":"GAEA: A Geolocation Aware Conversational Assistant","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2506.07032","title":"A Culturally-diverse Multilingual Multimodal Video Benchmark & Model","created":"2025-06-08","cited_by_count":5,"area":"mllm"},{"id":"2510.06371","title":"OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.08608","title":"MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2503.18484","title":"Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning","created":"2025-03-24","cited_by_count":4,"area":"mllm"},{"id":"2505.24456","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2507.22752","title":"CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2508.02241","title":"Isolating Culture Neurons in Multilingual Large Language Models","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2509.04438","title":"The Telephone Game: Evaluating Semantic Drift in Unified Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2503.10427","title":"VisTW: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan","created":"2025-03-13","cited_by_count":3,"area":"mllm"},{"id":"2505.15075","title":"Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs","created":"2025-05-21","cited_by_count":3,"area":"mllm"},{"id":"2510.01247","title":"Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2511.17004","title":"Vision Language Models are Confused Tourists","created":"2025-11-21","cited_by_count":3,"area":"mllm"},{"id":"2511.22787","title":"World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models","created":"2025-11-27","cited_by_count":3,"area":"mllm"},{"id":"2504.11108","title":"Benchmarking Vision Language Models on German Factual Data","created":"2025-04-15","cited_by_count":2,"area":"mllm"},{"id":"2509.07994","title":"STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2510.00041","title":"Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness","created":"2025-09-27","cited_by_count":2,"area":"mllm"},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2601.05699","title":"Afri-MCQA: Multimodal Cultural Question Answering for African Languages","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.05965","title":"Learning to Share: Selective Memory for Efficient Parallel Agentic Systems","created":"2026-02-05","cited_by_count":2,"area":"agents"},{"id":"2608.27135","title":"Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2505.16566","title":"ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2507.07274","title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","created":"2025-07-09","cited_by_count":1,"area":"mllm"},{"id":"2509.22123","title":"Multilingual Vision-Language Models, A Survey","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2510.03762","title":"Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2510.21849","title":"TowerVision: Understanding and Improving Multilinguality in Vision-Language Models","created":"2025-10-22","cited_by_count":1,"area":"mllm"},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2602.18788","title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.06484","title":"ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.08970","title":"An Effective Router for Vision-Language Model Selection","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2412.16188","title":"A Decade of Deep Learning: A Survey on The Magnificent Seven","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2602.12659","title":"IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models","created":"2026-02-13","cited_by_count":0,"area":"mllm"},{"id":"2603.24826","title":"Synthetic Rewriting as a Quality Multiplier: Evidence from Portuguese Continued Pretraining","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.26742","title":"Do Multilingual VLMs Reason Equally? A Cross-Lingual Visual Reasoning Audit for Indian Languages","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2604.14448","title":"MARCA: A Checklist-Based Benchmark for Multilingual Web Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.15613","title":"Toward LLMs Beyond English-Centric Development","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.30685","title":"How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.30788","title":"XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.09648","title":"ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.17188","title":"Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2606.19727","title":"NRITYAM: Language Models Meet Art and Heritage of Dance","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2606.20770","title":"Beyond 'One Language, One Script': Quantifying Orthographic Bias in Multilingual VLMs with PuMVR","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.00724","title":"MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.18361","title":"Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.30739","title":"SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}