{"total":58,"rows":[{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2406.11776","title":"Improving Multi-Agent Debate with Sparse Communication Topology","created":"2024-06-17","cited_by_count":107,"area":"lr"},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105,"area":"lr"},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63,"area":"driving"},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2312.01261","title":"TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models","created":"2023-12-03","cited_by_count":52,"area":null},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51,"area":null},{"id":"2311.11315","title":"TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems","created":"2023-11-19","cited_by_count":39,"area":"agents"},{"id":"2506.21215","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","created":"2025-06-26","cited_by_count":38,"area":"lr"},{"id":"2410.00193","title":"Do Vision-Language Models Really Understand Visual Language?","created":"2024-09-30","cited_by_count":32,"area":"mllm"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2503.13792","title":"Identifying and Mitigating Position Bias of Multi-image Vision-Language Models","created":"2025-03-18","cited_by_count":25,"area":"mllm"},{"id":"2503.14853","title":"Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection","created":"2025-03-19","cited_by_count":21,"area":"mllm"},{"id":"2401.06781","title":"PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2405.03272","title":"WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning","created":"2024-05-06","cited_by_count":16,"area":"wm"},{"id":"2311.17091","title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","created":"2023-11-28","cited_by_count":13,"area":"mllm"},{"id":"2502.16641","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","created":"2025-02-23","cited_by_count":13,"area":"rag"},{"id":"2311.16492","title":"VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2511.00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis","created":"2025-11-02","cited_by_count":12,"area":null},{"id":"2311.17331","title":"Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering","created":"2023-11-29","cited_by_count":11,"area":"lr"},{"id":"2505.10118","title":"Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering","created":"2025-05-15","cited_by_count":11,"area":"inference"},{"id":"2406.09838","title":"ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis","created":"2024-06-14","cited_by_count":10,"area":"mllm"},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2503.00723","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","created":"2025-03-02","cited_by_count":9,"area":"mllm"},{"id":"2412.07030","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","created":"2024-12-09","cited_by_count":7,"area":"synth"},{"id":"2501.13368","title":"MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2404.13947","title":"Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering","created":"2024-04-22","cited_by_count":5,"area":"mllm"},{"id":"2412.03002","title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?","created":"2024-12-04","cited_by_count":5,"area":"mllm"},{"id":"2412.11026","title":"SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation","created":"2024-12-15","cited_by_count":5,"area":"lr"},{"id":"2505.22112","title":"Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2403.11373","title":"Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration","created":"2024-03-17","cited_by_count":4,"area":"mllm"},{"id":"2506.12299","title":"QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2507.03123","title":"Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations","created":"2025-07-03","cited_by_count":4,"area":"mllm"},{"id":"2510.10285","title":"Reallocating Attention Across Layers to Reduce Multimodal Hallucination","created":"2025-10-11","cited_by_count":4,"area":"lr"},{"id":"2406.12746","title":"Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2410.07824","title":"Exploring Foundation Models in Remote Sensing Image Change Detection: A Comprehensive Survey","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2406.03721","title":"Attribute-Aware Implicit Modality Alignment for Text Attribute Person Search","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2505.22396","title":"Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2508.10016","title":"Training-Free Multimodal Large Language Model Orchestration","created":"2025-08-06","cited_by_count":2,"area":"mllm"},{"id":"2509.17116","title":"MCTS-EP: Empowering Embodied Planning with Online Preference Optimization","created":"2025-09-21","cited_by_count":2,"area":"alignment"},{"id":"2509.26594","title":"Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2601.22228","title":"Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2506.23502","title":"LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching","created":"2025-06-30","cited_by_count":1,"area":"mllm"},{"id":"2601.02764","title":"Netflix Artwork Personalization via LLM Post-training","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2604.09201","title":"CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2501.10011","title":"Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions","created":"2025-01-17","cited_by_count":0,"area":"mllm"},{"id":"2505.10453","title":"Vision language models have difficulty recognizing virtual objects","created":"2025-05-15","cited_by_count":0,"area":"mllm"},{"id":"2507.21584","title":"TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs","created":"2025-07-29","cited_by_count":0,"area":"mllm"},{"id":"2510.03376","title":"Visual Language Model as a Judge for Object Detection in Industrial Diagrams","created":"2025-10-03","cited_by_count":0,"area":"mllm"},{"id":"2512.03335","title":"Step-by-step Layered Design Generation","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.06769","title":"Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding","created":"2025-12-07","cited_by_count":0,"area":"mllm"},{"id":"2512.18411","title":"AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning","created":"2025-12-20","cited_by_count":0,"area":"mllm"},{"id":"2603.12217","title":"Real-World Point Tracking with Verifier-Guided Pseudo-Labeling","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.06824","title":"Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"id":"2608.12724","title":"MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning","created":"2026-08-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}