| Emu3: Next-Token Prediction is All You Need | Sep 27, 2024 | All | CodeCode Available | 3 |
| Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations | Sep 27, 2024 | Chart Question AnsweringQuestion Answering | —Unverified | 0 |
| Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE | Sep 26, 2024 | image-classificationImage Classification | CodeCode Available | 1 |
| Robotic Environmental State Recognition with Pre-Trained Vision-Language Models and Black-Box Optimization | Sep 26, 2024 | Image to textImage-to-Text Retrieval | —Unverified | 0 |
| DARE: Diverse Visual Question Answering with Robustness Evaluation | Sep 26, 2024 | image-classificationImage Classification | —Unverified | 0 |
| ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue | Sep 26, 2024 | Medical Visual Question AnsweringQuestion Answering | —Unverified | 0 |
| A Unified Hallucination Mitigation Framework for Large Vision-Language Models | Sep 24, 2024 | HallucinationQuestion Answering | CodeCode Available | 0 |
| MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models | Sep 23, 2024 | Medical Visual Question AnsweringQuestion Answering | CodeCode Available | 1 |
| Phantom of Latent for Large Language and Vision Models | Sep 23, 2024 | Visual Question Answering | CodeCode Available | 2 |
| Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation | Sep 23, 2024 | Multiple-choiceQuestion Answering | —Unverified | 0 |
| Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP | Sep 23, 2024 | Image GenerationQuestion Answering | —Unverified | 0 |
| @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology | Sep 21, 2024 | BenchmarkingDepth Estimation | —Unverified | 0 |
| Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering | Sep 19, 2024 | HallucinationHallucination Evaluation | CodeCode Available | 1 |
| Vision Language Models Can Parse Floor Plan Maps | Sep 19, 2024 | Image CaptioningQuestion Answering | —Unverified | 0 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | Sep 18, 2024 | Natural Language Visual Grounding | CodeCode Available | 11 |
| Sparks of Artificial General Intelligence(AGI) in Semiconductor Material Science: Early Explorations into the Next Frontier of Generative AI-Assisted Electron Micrograph Analysis | Sep 17, 2024 | In-Context LearningQuestion Answering | —Unverified | 0 |
| Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs | Sep 17, 2024 | Question AnsweringToken Reduction | CodeCode Available | 1 |
| OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities | Sep 17, 2024 | cross-modal alignmentQuestion Answering | —Unverified | 0 |
| CAST: Cross-modal Alignment Similarity Test for Vision Language Models | Sep 17, 2024 | cross-modal alignmentQuestion Answering | CodeCode Available | 0 |
| NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training | Sep 15, 2024 | Contrastive Learningcross-modal alignment | —Unverified | 0 |
| Explore the Hallucination on Low-level Perception for MLLMs | Sep 15, 2024 | HallucinationQuestion Answering | —Unverified | 0 |
| One missing piece in Vision and Language: A Survey on Comics Understanding | Sep 14, 2024 | document understandingimage-classification | CodeCode Available | 2 |
| Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types | Sep 14, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering | Sep 11, 2024 | Question AnsweringVisual Question Answering | —Unverified | 0 |
| Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks | Sep 11, 2024 | Image CaptioningQuestion Answering | CodeCode Available | 0 |
