| GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI | Nov 21, 2024 | Decision MakingLanguage Modeling | CodeCode Available | 2 |
| FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression | Nov 21, 2024 | Visual Question Answering | —Unverified | 0 |
| Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset | Nov 21, 2024 | Question AnsweringVisual Grounding | CodeCode Available | 0 |
| Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance | Nov 21, 2024 | Visual Question Answering | —Unverified | 0 |
| Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training | Nov 20, 2024 | Contrastive Learningimage-classification | —Unverified | 0 |
| Teaching VLMs to Localize Specific Objects from In-context Examples | Nov 20, 2024 | ObjectObject Tracking | CodeCode Available | 1 |
| LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement | Nov 20, 2024 | Autonomous DrivingComputational Efficiency | —Unverified | 0 |
| Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model | Nov 19, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| A Survey of Medical Vision-and-Language Applications and Their Techniques | Nov 19, 2024 | Decision MakingDiagnostic | CodeCode Available | 1 |
| CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs | Nov 19, 2024 | HallucinationLanguage Modeling | —Unverified | 0 |
| Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts | Nov 18, 2024 | BenchmarkingMultimodal Large Language Model | CodeCode Available | 0 |
| MC-LLaVA: Multi-Concept Personalized Vision-Language Model | Nov 18, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry | Nov 17, 2024 | Question AnsweringScene Understanding | —Unverified | 0 |
| Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning | Nov 17, 2024 | Image CaptioningLanguage Modeling | CodeCode Available | 0 |
| BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation | Nov 17, 2024 | Action Recognitionbackdoor defense | CodeCode Available | 1 |
| Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering | Nov 17, 2024 | HallucinationIn-Context Learning | CodeCode Available | 0 |
| A Comprehensive Survey on Visual Question Answering Datasets and Algorithms | Nov 17, 2024 | DiagnosticMiscellaneous | —Unverified | 0 |
| Large Vision-Language Models for Remote Sensing Visual Question Answering | Nov 16, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Everything is a Video: Unifying Modalities through Next-Frame Prediction | Nov 15, 2024 | Caption GenerationCross-Modal Retrieval | —Unverified | 0 |
| AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference | Nov 15, 2024 | QuantizationQuestion Answering | —Unverified | 0 |
| LLaVA-CoT: Let Vision Language Models Reason Step-by-Step | Nov 15, 2024 | Logical ReasoningMultimodal Reasoning | CodeCode Available | 7 |
| Visual question answering based evaluation metrics for text-to-image generation | Nov 15, 2024 | Image GenerationImage Manipulation | —Unverified | 0 |
| JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation | Nov 12, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 11 |
| SparrowVQE: Visual Question Explanation for Course Content Understanding | Nov 12, 2024 | Question AnsweringVisual Question Answering | CodeCode Available | 0 |
| Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent | Nov 8, 2024 | Autonomous DrivingLanguage Modeling | —Unverified | 0 |
