{"list":"other","total":96,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2403.06764","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","created":"2024-03-11","cited_by_count":642},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2410.04417","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","created":"2024-10-06","cited_by_count":391},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2410.05160","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","created":"2024-10-07","cited_by_count":228},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"2103.15316","title":"Whitening Sentence Representations for Better Semantics and Faster Retrieval","created":"2021-03-29","cited_by_count":202},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"id":"2412.16855","title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs","created":"2024-12-22","cited_by_count":170},{"id":"2411.02571","title":"MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs","created":"2024-11-04","cited_by_count":161},{"id":"2412.01818","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","created":"2024-12-02","cited_by_count":157},{"id":"2402.12451","title":"The Revolution of Multimodal Large Language Models: A Survey","created":"2024-02-19","cited_by_count":137},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"2409.10197","title":"Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models","created":"2024-09-16","cited_by_count":126},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125},{"id":"2507.04590","title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","created":"2025-07-07","cited_by_count":116},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114},{"id":"2406.11251","title":"Unifying Multimodal Retrieval via Document Screenshot Embedding","created":"2024-06-17","cited_by_count":110},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105},{"id":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101},{"id":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80},{"id":"2310.18340","title":"UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web","created":"2023-10-22","cited_by_count":78},{"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},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76},{"id":"2505.17166","title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval","created":"2025-05-22","cited_by_count":61},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59},{"id":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43},{"id":"2410.04780","title":"Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality","created":"2024-10-07","cited_by_count":42},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42},{"id":"2308.14263","title":"Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions","created":"2023-08-28","cited_by_count":40},{"id":"2410.04509","title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","created":"2024-10-06","cited_by_count":37},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35},{"id":"2310.15556","title":"TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction","created":"2023-10-24","cited_by_count":34},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34},{"id":"2402.19348","title":"Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook","created":"2024-02-29","cited_by_count":33},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33},{"id":"2405.19504","title":"MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings","created":"2024-05-29","cited_by_count":32},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31},{"id":"2402.19014","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","created":"2024-02-29","cited_by_count":30},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30},{"id":"2502.11051","title":"MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models","created":"2025-02-16","cited_by_count":30},{"id":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29},{"id":"2507.05513","title":"Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model","created":"2025-07-07","cited_by_count":27},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26},{"id":"2506.04997","title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings","created":"2025-06-05","cited_by_count":26},{"id":"2409.14683","title":"Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling","created":"2024-09-23","cited_by_count":25},{"id":"2503.18132","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","created":"2025-03-23","cited_by_count":24},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17},{"id":"2501.17788","title":"WARP: An Efficient Engine for Multi-Vector Retrieval","created":"2025-01-29","cited_by_count":17},{"id":"2407.20243","title":"Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions","created":"2024-07-17","cited_by_count":16},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14},{"id":"2403.14374","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","created":"2024-03-21","cited_by_count":13},{"id":"2504.01818","title":"Efficient Constant-Space Multi-Vector Retrieval","created":"2025-04-02","cited_by_count":12},{"id":"2507.14067","title":"VLA-Mark: A cross modal watermark for large vision-language alignment model","created":"2025-07-18","cited_by_count":12},{"id":"2304.12702","title":"A Static Pruning Study on Sparse Neural Retrievers","created":"2023-04-25","cited_by_count":11},{"id":"2412.01380","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","created":"2024-12-02","cited_by_count":11},{"id":"2505.05666","title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","created":"2025-05-08","cited_by_count":11},{"id":"2404.14241","title":"UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation","created":"2024-04-22","cited_by_count":10},{"id":"2408.11366","title":"GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding","created":"2024-08-21","cited_by_count":10},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8},{"id":"2404.00684","title":"Generative Retrieval as Multi-Vector Dense Retrieval","created":"2024-03-31","cited_by_count":8},{"id":"2502.11431","title":"Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval","created":"2025-02-17","cited_by_count":8},{"id":"2403.13291","title":"An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models","created":"2024-03-20","cited_by_count":7},{"id":"2406.16069","title":"FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models","created":"2024-06-23","cited_by_count":7},{"id":"2505.13965","title":"CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring","created":"2025-05-20","cited_by_count":7},{"id":"2406.17968","title":"Efficient Document Ranking with Learnable Late Interactions","created":"2024-06-25","cited_by_count":6},{"id":"2411.17299","title":"2D Matryoshka Training for Information Retrieval","created":"2024-11-26","cited_by_count":6},{"id":"2505.01457","title":"A Multi-Granularity Retrieval Framework for Visually-Rich Documents","created":"2025-05-01","cited_by_count":6},{"id":"2505.14406","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","created":"2025-05-20","cited_by_count":3},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2},{"id":"2508.13901","title":"Multimodal Data Storage and Retrieval for Embodied AI: A Survey","created":"2025-08-19","cited_by_count":2},{"id":"2509.08216","title":"Vector embedding of multi-modal texts: a tool for discovery?","created":"2025-09-10","cited_by_count":2}],"next_cursor":null}