{"total":21,"rows":[{"id":"2602.11858","title":"Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception","created":"2026-02-12","cited_by_count":50,"area":"mllm"},{"id":"2604.12012","title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","created":"2026-04-13","cited_by_count":13,"area":"mllm"},{"id":"2602.02537","title":"WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models","created":"2026-01-28","cited_by_count":8,"area":"mllm"},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2510.13364","title":"Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity","created":"2025-10-15","cited_by_count":1,"area":"mllm"},{"id":"2511.20770","title":"Text-Guided Semantic Image Encoder","created":"2025-11-25","cited_by_count":1,"area":"mllm"},{"id":"2511.23170","title":"PowerCLIP: Powerset Alignment for Contrastive Pre-Training","created":"2025-11-28","cited_by_count":1,"area":"mllm"},{"id":"2512.12107","title":"EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography","created":"2025-12-13","cited_by_count":1,"area":"mllm"},{"id":"2605.12650","title":"CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2601.10305","title":"DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset","created":"2026-01-15","cited_by_count":0,"area":"mllm"},{"id":"2603.27759","title":"When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models","created":"2026-03-29","cited_by_count":0,"area":"mllm"},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2605.13178","title":"CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.18029","title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2606.04613","title":"Beyond Symmetric Alignment: Spectral Diagnostics of Modality Imbalance in Vision-Language Models in the Medical Domain","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.29888","title":"Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.00684","title":"AdaBoosting Text Prompts for Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.28211","title":"Scaling Vision-Language Models Is Not Enough to Mitigate Bias","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.25653","title":"Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2609.07823","title":"SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2610.05413","title":"A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models","created":"2026-10-04","cited_by_count":0,"area":"mllm"}],"next_cursor":null}