{"total":63,"rows":[{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2404.15127","title":"GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration","created":"2024-04-23","cited_by_count":34,"area":null},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2410.22376","title":"Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance","created":"2024-10-29","cited_by_count":30,"area":"diffusion"},{"id":"2502.12521","title":"Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights","created":"2025-02-18","cited_by_count":30,"area":"lr"},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2410.19294","title":"Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting","created":"2024-10-25","cited_by_count":26,"area":"mllm"},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2505.20612","title":"Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models","created":"2025-05-27","cited_by_count":20,"area":"mllm"},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2406.11148","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","created":"2024-06-17","cited_by_count":15,"area":"rag"},{"id":"2409.12969","title":"Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models","created":"2024-09-02","cited_by_count":15,"area":"mllm"},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2405.15668","title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models","created":"2024-05-24","cited_by_count":10,"area":"mllm"},{"id":"2503.12821","title":"From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration","created":"2025-03-17","cited_by_count":8,"area":"mllm"},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"id":"2510.16596","title":"SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense","created":"2025-10-18","cited_by_count":7,"area":"mllm"},{"id":"2502.19295","title":"Complex LLM Planning via Automated Heuristics Discovery","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2503.00359","title":"Solving Instance Detection from an Open-World Perspective","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2607.13125","title":"Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget","created":"2026-07-14","cited_by_count":6,"area":"agents"},{"id":"2505.07496","title":"DocVXQA: Context-Aware Visual Explanations for Document Question Answering","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2604.05117","title":"Watch Before You Answer: Learning from Visually Grounded Post-Training","created":"2026-04-06","cited_by_count":5,"area":"mllm"},{"id":"2410.03955","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2502.02885","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2506.22908","title":"Attention to the Burstiness in Visual Prompt Tuning!","created":"2025-06-28","cited_by_count":4,"area":null},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2410.01180","title":"UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2512.04238","title":"6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models","created":"2025-12-03","cited_by_count":3,"area":"mllm"},{"id":"2602.11743","title":"Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation","created":"2026-02-12","cited_by_count":3,"area":"mllm"},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.22939","title":"Learnability-Informed Fine-Tuning of Diffusion Language Models","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2506.01724","title":"Active Learning via Vision-Language Model Adaptation with Open Data","created":"2025-06-02","cited_by_count":2,"area":"mllm"},{"id":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2510.15508","title":"Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2504.05059","title":"MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2508.17417","title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","created":"2025-08-24","cited_by_count":1,"area":"mllm"},{"id":"2602.00813","title":"Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-01-31","cited_by_count":1,"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":"2506.02914","title":"AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2506.09740","title":"ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models","created":"2025-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2507.08000","title":"Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models","created":"2025-07-10","cited_by_count":0,"area":"mllm"},{"id":"2508.08701","title":"SafeFix: Targeted Model Repair via Controlled Image Generation","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2512.10244","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.15748","title":"Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors","created":"2025-12-10","cited_by_count":0,"area":"mllm"},{"id":"2512.24826","title":"Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.19385","title":"Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.27932","title":"Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training","created":"2026-04-30","cited_by_count":0,"area":"mllm"},{"id":"2605.01295","title":"Autonomous Drift Learning in Data Streams: A Unified Perspective","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2608.05424","title":"Invisible Shortcuts: Why Vision Encoders Know Your Camera","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.29358","title":"Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models","created":"2026-09-24","cited_by_count":0,"area":"mllm"}],"next_cursor":null}