{"total":23,"rows":[{"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":"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":"2411.16740","title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","created":"2024-11-23","cited_by_count":17,"area":"mllm"},{"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":"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":"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":"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":"2604.15280","title":"Why Do Vision Language Models Struggle To Recognize Human Emotions?","created":"2026-04-16","cited_by_count":1,"area":"mllm"},{"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":"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":"2608.30653","title":"Fine-Grained Multi Image Object Hallucination Benchmark","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"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":"2609.31706","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":"2609.38368","title":"Composition, Not Conversation: VLMs Lose the Scene, Not the Thread","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"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}