{"total":55,"rows":[{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183,"area":"lr"},{"id":"2502.11501","title":"Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?","created":"2025-02-17","cited_by_count":76,"area":"mllm"},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2504.13169","title":"Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling","created":"2025-04-17","cited_by_count":33,"area":"mllm"},{"id":"2505.10610","title":"MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly","created":"2025-05-15","cited_by_count":29,"area":"mllm"},{"id":"2504.17447","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","created":"2025-04-24","cited_by_count":27,"area":"mllm"},{"id":"2507.02001","title":"Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames","created":"2025-07-01","cited_by_count":27,"area":"lr"},{"id":"2411.16740","title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","created":"2024-11-23","cited_by_count":17,"area":"mllm"},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2601.16973","title":"VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents","created":"2026-01-23","cited_by_count":11,"area":"mllm"},{"id":"2510.09733","title":"VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2511.00162","title":"ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2601.07812","title":"More Images, More Problems? A Controlled Analysis of VLM Failure Modes","created":"2026-01-12","cited_by_count":9,"area":"mllm"},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2505.18153","title":"REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2506.16024","title":"From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2512.08511","title":"Thinking with Images via Self-Calling Agent","created":"2025-12-09","cited_by_count":4,"area":"lr"},{"id":"2504.18406","title":"HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2601.14127","title":"The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning","created":"2026-01-20","cited_by_count":3,"area":"lr"},{"id":"2412.12735","title":"GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models","created":"2024-12-17","cited_by_count":2,"area":"mllm"},{"id":"2508.17334","title":"Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs","created":"2025-08-24","cited_by_count":2,"area":"mllm"},{"id":"2509.24253","title":"MRAG-Suite: A Diagnostic Evaluation Platform for Visual Retrieval-Augmented Generation","created":"2025-09-29","cited_by_count":2,"area":"rag"},{"id":"2512.19675","title":"Multimodal LLMs for Historical Dataset Construction from Archival Image Scans: German Patents (1877-1918)","created":"2025-12-22","cited_by_count":2,"area":"mllm"},{"id":"2512.21576","title":"Towards Long-window Anchoring in Vision-Language Model Distillation","created":"2025-12-25","cited_by_count":2,"area":"mllm"},{"id":"2604.18573","title":"T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2605.28806","title":"Personal Visual Memory from Explicit and Implicit Evidence","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2609.12818","title":"Online Video Agent Harness for Long Video Understanding","created":"2026-09-11","cited_by_count":2,"area":"agents"},{"id":"2604.15280","title":"Why Do Vision Language Models Struggle To Recognize Human Emotions?","created":"2026-04-16","cited_by_count":1,"area":"mllm"},{"id":"2605.13277","title":"Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation","created":"2026-05-13","cited_by_count":1,"area":"rag"},{"id":"2605.13831","title":"Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context","created":"2026-05-13","cited_by_count":1,"area":"mllm"},{"id":"2607.08497","title":"Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2505.05635","title":"Neural Catalog: Scaling Species Recognition with Catalog of Life-Augmented Generation","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2511.03768","title":"What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2603.04676","title":"Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks","created":"2026-03-04","cited_by_count":0,"area":"lr"},{"id":"2603.16245","title":"How to Utilize Complementary Vision-Text Information for 2D Structure Understanding","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.09687","title":"Grid2Matrix: Revealing Digital Agnosia in Vision-Language Models","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2606.05275","title":"Personal AI Agent for Camera Roll VQA","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11853","title":"Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning","created":"2026-06-10","cited_by_count":0,"area":"mllm"},{"id":"2606.25343","title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2607.28627","title":"ReToken: One Token to Improve Vision-Language Models for Visual Retrieval","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.18532","title":"StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long Videos","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.30653","title":"Fine-Grained Multi Image Object Hallucination Benchmark","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.03206","title":"Learning to Zoom Efficiently with a Contrastive Curriculum","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.05518","title":"CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.17921","title":"Collaborative Memory for Multi-Agent VLM Systems","created":"2026-09-15","cited_by_count":0,"area":"mllm"},{"id":"2609.29735","title":"C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31706","title":"Can't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level","created":"2026-09-20","cited_by_count":0,"area":"mllm"},{"id":"2609.34480","title":"When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38368","title":"Composition, Not Conversation: VLMs Lose the Scene, Not the Thread","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.38743","title":"Learning to Route in Visual Space via Multi-Step Embedding Retrieval","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.18858","title":"Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.19611","title":"What Breaks in Multi-Image Schema Application? Factorial Oracle Interventions Reveal an Instance-Information Bottleneck","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}