{"total":25,"rows":[{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2403.02910","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","created":"2024-03-05","cited_by_count":57,"area":"mllm"},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19,"area":"mllm"},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2501.00958","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","created":"2025-01-01","cited_by_count":9,"area":"mllm"},{"id":"2509.14977","title":"EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence","created":"2025-09-18","cited_by_count":5,"area":"mllm"},{"id":"2505.23759","title":"Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"id":"2505.07675","title":"Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization","created":"2025-05-12","cited_by_count":1,"area":"mllm"},{"id":"2505.18053","title":"FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation","created":"2025-05-23","cited_by_count":1,"area":"mllm"},{"id":"2602.07849","title":"LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge","created":"2026-02-08","cited_by_count":1,"area":"mllm"},{"id":"2604.01179","title":"A ROS 2 Wrapper for Florence-2: Multi-Mode Local Vision-Language Inference for Robotic Systems","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2410.10879","title":"Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency","created":"2024-10-09","cited_by_count":0,"area":"mllm"},{"id":"2412.03871","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","created":"2024-12-05","cited_by_count":0,"area":"mllm"},{"id":"2506.00910","title":"PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models","created":"2025-06-01","cited_by_count":0,"area":"mllm"},{"id":"2506.19288","title":"Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"id":"2508.04028","title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval","created":"2025-08-06","cited_by_count":0,"area":"mllm"},{"id":"2510.19559","title":"A Matter of Time: Revealing the Structure of Time in Vision-Language Models","created":"2025-10-22","cited_by_count":0,"area":"mllm"},{"id":"2511.17886","title":"When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA","created":"2025-11-22","cited_by_count":0,"area":"mllm"},{"id":"2602.12659","title":"IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models","created":"2026-02-13","cited_by_count":0,"area":"mllm"},{"id":"2603.00136","title":"TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings","created":"2026-02-24","cited_by_count":0,"area":"mllm"},{"id":"2603.05421","title":"DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression","created":"2026-03-05","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":"2607.28211","title":"Scaling Vision-Language Models Is Not Enough to Mitigate Bias","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2609.05782","title":"Distilling Vision-Language Models for On-Device Fire Understanding","created":"2026-09-05","cited_by_count":0,"area":"mllm"}],"next_cursor":null}