An official website of the United States government
The ability to compare objects, scenes, or situations is crucial for effective decision-making and problem-solving in everyday life. For instance, comparing the freshness of apples enables better choices during grocery shopping, while comparing sofa designs helps optimize the aesthetics of our living space. Despite its significance, the comparative capability is largely unexplored in artificial general intelligence (AGI). In this paper, we introduce MLLM-COMPBENCH, a benchmark designed to evaluate the comparative reasoning capability of multimodal large language models (MLLMs). MLLM-COMPBENCH mines and pairs images through visually oriented questions covering eight dimensions of relative comparison: visual attribute, existence, state, emotion, temporality, spatiality, quantity, and quality. We curate a collection of around 40K image pairs using metadata from diverse vision datasets and CLIP similarity scores. These image pairs span a broad array of visual domains, including animals, fashion, sports, and both outdoor and indoor scenes. The questions are carefully crafted to discern relative characteristics between two images and are labeled by human annotators for accuracy and relevance. We use MLLM-COMPBENCH to evaluate recent MLLMs, including GPT-4V(ision), Gemini-Pro, and LLaVA-1.6. Our results reveal notable shortcomings in their comparative abilities. We believe MLLM-COMPBENCH not only sheds light on these limitations but also establishes a solid foundation for future enhancements in the comparative capability of MLLMs.
more »
« less
This content will become publicly available on August 11, 2026
Improving Multimodal Large Language Models Using Continual Learning
Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often significantly decreases performance on natural language understanding and generation tasks, compared to the original LLM. This study investigates this issue using the LLaVA MLLM, treating the integration as a continual learning problem. We evaluate five continual learning methods to mitigate forgetting and identify a technique that enhances visual understanding while minimizing linguistic performance loss. Our approach reduces linguistic performance degradation by up to 15% over the LLaVA recipe, while maintaining high multimodal accuracy. We also demonstrate the robustness of our method through continual learning on a sequence of vision-language tasks, effectively preserving linguistic skills while acquiring new multimodal capabilities.
more »
« less
- PAR ID:
- 10644274
- Publisher / Repository:
- Proc. Conference on Lifelong Learning Agents (CoLLAs)
- Date Published:
- Subject(s) / Keyword(s):
- Continual learning multi-modal AI visual question answering vision-language model large language model
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple vision experts. This study provides an extensive exploration of the design space for MLLMs using a mixture of vision encoders and resolutions. Our findings reveal several underlying principles common to various existing strategies, leading to a streamlined yet effective design approach. We discover that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies. We additionally introduce Pre-Alignment to bridge the gap between vision-focused encoders and language tokens, enhancing model coherence. The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.more » « less
-
High-resolution Vision-Language Models (VLMs) are widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate an excessive number of visual tokens due to the need to encode multiple partitions of a high-resolution image input. Processing such a large number of visual tokens poses significant computational challenges, particularly for resource-constrained commodity GPUs. To address this challenge, we propose High-Resolution Early Dropping (HiRED), a plug-and-play token-dropping method designed to operate within a fixed token budget. HiRED leverages the attention of CLS token in the vision transformer (ViT) to assess the visual content of the image partitions and allocate an optimal token budget for each partition accordingly. The most informative visual tokens from each partition within the allocated budget are then selected and passed to the subsequent Large Language Model (LLM). We showed that HiRED achieves superior accuracy and performance, compared to existing token-dropping methods. Empirically, HiRED-20% (i.e., a 20% token budget) on LLaVA-Next-7B achieves a 4.7x increase in token generation throughput, reduces response latency by 78%, and saves 14% of GPU memory for single inference on an NVIDIA TESLA P40 (24 GB). For larger batch sizes (e.g., 4), HiRED-20% prevents out-of-memory errors by cutting memory usage by 30%, while preserving throughput and latency benefits.more » « less
-
Abstract Engineering design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision-language models (VLMs), such as GPT-4V, enabling AI to impact many more types of tasks. Our work presents a comprehensive evaluation of VLMs across a spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks. Specifically in this paper, we assess the capabilities of two VLMs, GPT-4V and LLaVA 1.6 34B, in design tasks such as sketch similarity analysis, CAD generation, topology optimization, manufacturability assessment, and engineering textbook problems. Through this structured evaluation, we not only explore VLMs’ proficiency in handling complex design challenges but also identify their limitations in complex engineering design applications. Our research establishes a foundation for future assessments of vision language models. It also contributes a set of benchmark testing datasets, with more than 1000 queries, for ongoing advancements and applications in this field.more » « less
-
Faggioli, G; Ferro, N; Galuščáková, P; de, A (Ed.)This working note documents the participation of CS_Morgan in the ImageCLEFmedical 2024 Caption subtasks, focusing on Caption Prediction and Concept Detection challenges. The primary objectives included training, validating, and testing multimodal Artificial Intelligence (AI) models intended to automate the process of generating captions and identifying multi-concepts of radiology images. The dataset used is a subset of the Radiology Objects in COntext version 2 (ROCOv2) dataset and contains image-caption pairs and corresponding Unified Medical Language System (UMLS) concepts. To address the caption prediction challenge, different variants of the Large Language and Vision Assistant (LLaVA) models were experimented with, tailoring them for the medical domain. Additionally, a lightweight Large Multimodal Model (LMM), and MoonDream2, a small Vision Language Model (VLM), were explored. The former is the instruct variant of the Image-aware Decoder Enhanced à la Flamingo with Interleaved Cross-attentionS (IDEFICS) 9B obtained through quantization. Besides LMMs, conventional encoder-decoder models like Vision Generative Pre-trained Transformer 2 (visionGPT2) and Convolutional Neural Network-Transformer (CNN-Transformer) architectures were considered. Consequently, this enabled 10 submissions for the caption prediction task, with the first submission of LLaVA 1.6 on the Mistral 7B weights securing the 2nd position among the participants. This model was adapted using 40.1M parameters and achieved the best performance on the test data across the performance metrics of BERTScore (0.628059), ROUGE (0.250801), BLEU-1 (0.209298), BLEURT (0.317385), METEOR (0.092682), CIDEr (0.245029), and RefCLIPScore (0.815534). For the concept detection task, our single submission based on the ConvMixer architecture—a hybrid approach leveraging CNN and Transformer advantages—ranked 9th with an F1-score of 0.107645. Overall, the evaluations on the test data for the caption prediction task submissions suggest that LMMs, quantized LMMs, and small VLMs, when adapted and selectively fine-tuned using fewer parameters, have ample potential for understanding medical concepts present in images.more » « less
