{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2501.05874","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","created":"2025-01-10","cited_by_count":57},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40},{"id":"2406.16620","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","created":"2024-06-24","cited_by_count":34},{"id":"2507.00008","title":"DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning","created":"2025-06-12","cited_by_count":31},{"id":"2510.14032","title":"Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding","created":"2025-10-15","cited_by_count":31},{"id":"2312.14871","title":"BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction","created":"2023-12-22","cited_by_count":30},{"id":"2409.20365","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","created":"2024-09-30","cited_by_count":29},{"id":"2406.11668","title":"\"Not Aligned\" is Not \"Malicious\": Being Careful about Hallucinations of Large Language Models' Jailbreak","created":"2024-06-17","cited_by_count":25},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21},{"id":"2503.19602","title":"Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking","created":"2025-03-25","cited_by_count":20},{"id":"2402.07140","title":"Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?","created":"2024-02-11","cited_by_count":16},{"id":"2410.02684","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","created":"2024-10-03","cited_by_count":16},{"id":"2507.04504","title":"Unveiling the Potential of Diffusion Large Language Model in Controllable Generation","created":"2025-07-06","cited_by_count":15},{"id":"2405.19996","title":"DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild","created":"2024-05-30","cited_by_count":14},{"id":"2504.14597","title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","created":"2025-04-20","cited_by_count":13},{"id":"2508.18722","title":"VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft","created":"2025-08-26","cited_by_count":13},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12},{"id":"2503.23768","title":"Texture or Semantics? Vision-Language Models Get Lost in Font Recognition","created":"2025-03-31","cited_by_count":11},{"id":"2506.09518","title":"HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene","created":"2025-06-11","cited_by_count":11},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10},{"id":"2510.04560","title":"ContextNav: Towards Agentic Multimodal In-Context Learning","created":"2025-10-06","cited_by_count":10},{"id":"2508.10264","title":"MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs","created":"2025-08-14","cited_by_count":9},{"id":"2509.21749","title":"Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models","created":"2025-09-26","cited_by_count":9},{"id":"2602.00181","title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","created":"2026-01-30","cited_by_count":9},{"id":"2506.21600","title":"Structured Attention Matters to Multimodal LLMs in Document Understanding","created":"2025-06-19","cited_by_count":8},{"id":"2509.06461","title":"Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning","created":"2025-09-08","cited_by_count":8},{"id":"2408.09449","title":"From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification","created":"2024-08-18","cited_by_count":7},{"id":"2410.15180","title":"HACSurv: A Hierarchical Copula-Based Approach for Survival Analysis with Dependent Competing Risks","created":"2024-10-19","cited_by_count":7},{"id":"2506.07600","title":"SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding","created":"2025-06-09","cited_by_count":7},{"id":"2508.03343","title":"WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval","created":"2025-08-05","cited_by_count":7},{"id":"2407.07638","title":"Tuning Vision-Language Models with Candidate Labels by Prompt Alignment","created":"2024-07-10","cited_by_count":6},{"id":"2410.20016","title":"Vulnerability of LLMs to Vertically Aligned Text Manipulations","created":"2024-10-26","cited_by_count":6},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6},{"id":"2512.23483","title":"TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding","created":"2025-12-29","cited_by_count":6},{"id":"2601.12906","title":"Gated Differentiable Working Memory for Long-Context Language Modeling","created":"2026-01-19","cited_by_count":6},{"id":"2509.19994","title":"Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models","created":"2025-09-24","cited_by_count":5},{"id":"2509.24566","title":"TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models","created":"2025-09-29","cited_by_count":5},{"id":"2603.12989","title":"Test-Time Attention Purification for Backdoored Large Vision Language Models","created":"2026-03-13","cited_by_count":5},{"id":"2504.10967","title":"An Efficient and Mixed Heterogeneous Model for Image Restoration","created":"2025-04-15","cited_by_count":4},{"id":"2410.20021","title":"Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization","created":"2024-10-26","cited_by_count":3},{"id":"2411.16217","title":"Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding","created":"2024-11-25","cited_by_count":2},{"id":"2510.02732","title":"From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting","created":"2025-10-03","cited_by_count":1}],"next_cursor":null}