Recent progress in (multimodal) large language models ((M)LLMs) has shifted focus from pre-training to inference-time compute scaling and post-training optimization, driven by concerns over limited high-quality real-world data. However, these strategies alone are insufficient for advancing model capabilities. We hypothesize that effective model improvement requires a strong synergy among pre-training, inference-time compute scaling, and post-training optimization. In this paper, we validate this hypothesis in the context of multimodal pre-training for foundation MLLM construction. We introduce Self-Improving cognition (SIcog), a self-learning framework for constructing next-generation foundation MLLMs by imparting multimodal knowledge and enhancing their systematic cognitive capabilities through multimodal pre-training with self-generated data. Specifically, we introduce Chain-of-Description, a step-by-step visual understanding method to improve comprehensive perception, and integrate structured chain-of-thought (CoT) reasoning to support in-depth multimodal reasoning. SIcog first equips a base model with systematic perception and reasoning using minimal external supervision. The enhanced model then generates candidate image captions and CoT-style reasoning responses for unlabeled images and image-question pairs across diverse tasks, which are curated through a self-consistency mechanism. These curated samples are subsequently used for large-scale multimodal pre-training, completing a self-learning cycle that strengthens the model's cognitive foundation. Extensive experiments demonstrate that SIcog produces next-generation foundation MLLMs with substantially improved multimodal cognition, outperforming prevailing pre-training approaches. These findings empirically establish SIcog as a promising framework for realizing a complete self-improving paradigm.
We propose a novel approach for captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally dense bounding boxes. We introduce the following contributions. First, we present a large-scale automatic annotation method that aggregates captions grounded with bounding boxes across individual frames into temporally dense and consistent bounding box annotations. We apply this approach on the HowTo100M dataset to construct a large-scale pre-training dataset, named HowToGround1M. We also introduce a Grounded Video Caption Generation model, dubbed GROVE, and pre-train the model on HowToGround1M. Second, we introduce a new dataset, called iGround, of 3500 videos with manually annotated captions and dense spatio-temporally grounded bounding boxes. This allows us to measure progress on this challenging problem, as well as to fine-tune our model on this small-scale but high-quality data. Third, we demonstrate that our approach achieves state-of-the-art results on the proposed iGround dataset compared to a number of baselines, as well as on the VidSTG and ActivityNet-Entities datasets. We perform extensive ablations that demonstrate the importance of pre-training using our automatically annotated HowToGround1M dataset followed by fine-tuning on the manually annotated iGround dataset and validate the key technical contributions of our model.
Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential benefits of text-based semantic information. To address this issue, we first construct three text-enhanced multi-modal object ReID benchmarks. To be specific, we propose a standardized multi-modal caption generation pipeline for structured and concise text annotations with Multi-modal Large Language Models (MLLMs). Besides, current methods often directly aggregate multi-modal information without selecting representative local features, leading to redundancy and high complexity. To address the above issues, we introduce IDEA, a novel feature learning framework comprising the Inverted Multi-modal Feature Extractor (IMFE) and Cooperative Deformable Aggregation (CDA). The IMFE utilizes Modal Prefixes and an InverseNet to integrate multi-modal information with semantic guidance from inverted text. The CDA adaptively generates sampling positions, enabling the model to focus on the interplay between global features and discriminative local features. With the constructed benchmarks and the proposed modules, our framework can generate more robust multi-modal features under complex scenarios. Extensive experiments on three multi-modal object ReID benchmarks demonstrate the effectiveness of our proposed method.
Situational awareness applications rely heavily on real-time processing of visual and textual data to provide actionable insights. Vision language models (VLMs) have become essential tools for interpreting complex environments by connecting visual inputs with natural language descriptions. However, these models often face computational challenges, especially when required to perform efficiently in real environments. This research presents a novel vision language model (VLM) framework that leverages frequency domain transformations and low-rank adaptation (LoRA) to enhance feature extraction, scalability, and efficiency. Unlike traditional VLMs, which rely solely on spatial-domain representations, our approach incorporates Discrete Fourier Transform (DFT) based low-rank features while retaining pretrained spatial weights, enabling robust performance in noisy or low visibility scenarios. We evaluated the proposed model on caption generation and Visual Question Answering (VQA) tasks using benchmark datasets with varying levels of Gaussian noise. Quantitative results demonstrate that our model achieves evaluation metrics comparable to state-of-the-art VLMs, such as CLIP ViT-L/14 and SigLIP. Qualitative analysis further reveals that our model provides more detailed and contextually relevant responses, particularly for real-world images captured by a RealSense camera mounted on an Unmanned Ground Vehicle (UGV).
Large multimodal models (LMMs) have shown remarkable performance in video understanding tasks and can even process videos longer than one hour. However, despite their ability to handle long inputs, generating outputs with corresponding levels of richness remains a challenge. In this paper, we explore the issue of long outputs in LMMs using video captioning as a proxy task, and we find that open-source LMMs struggle to consistently generate outputs exceeding about 300 words. Through controlled experiments, we find that the scarcity of paired examples with long-captions during training is the primary factor limiting the model's output length. However, manually annotating long-caption examples is time-consuming and expensive. To address this, we propose the LongCaption-Agent, a framework that synthesizes long caption data by aggregating multi-level descriptions. Using LongCaption-Agent, we curated a new long-caption dataset, LongCaption-10K. We also develop LongCaption-Bench, a benchmark designed to comprehensively evaluate the quality of long captions generated by LMMs. By incorporating LongCaption-10K into training, we enable LMMs to generate captions exceeding 1,000 words, while maintaining high output quality. In LongCaption-Bench, our 8B parameter model achieved state-of-the-art performance, even surpassing larger proprietary models. We will release the dataset and code after publication.
Recent advances in visual language models (VLMs) have significantly improved image captioning, but extending these gains to video understanding remains challenging due to the scarcity of fine-grained video captioning datasets. To bridge this gap, we propose a novel zero-shot video captioning approach that combines frame-level scene graphs from a video to obtain intermediate representations for caption generation. Our method first generates frame-level captions using an image VLM, converts them into scene graphs, and consolidates these graphs to produce comprehensive video-level descriptions. To achieve this, we leverage a lightweight graph-to-text model trained solely on text corpora, eliminating the need for video captioning annotations. Experiments on the MSR-VTT and ActivityNet Captions datasets show that our approach outperforms zero-shot video captioning baselines, demonstrating that aggregating frame-level scene graphs yields rich video understanding without requiring large-scale paired data or high inference cost.
The integration of artificial intelligence in medical imaging has shown tremendous potential, yet the relationship between pre-trained knowledge and performance in cross-modality learning remains unclear. This study investigates how explicitly injecting medical knowledge into the learning process affects the performance of cross-modality classification, focusing on Chest X-ray (CXR) images. We introduce a novel Set Theory-based knowledge injection framework that generates captions for CXR images with controllable knowledge granularity. Using this framework, we fine-tune CLIP model on captions with varying levels of medical information. We evaluate the model's performance through zero-shot classification on the CheXpert dataset, a benchmark for CXR classification. Our results demonstrate that injecting fine-grained medical knowledge substantially improves classification accuracy, achieving 72.5\% compared to 49.9\% when using human-generated captions. This highlights the crucial role of domain-specific knowledge in medical cross-modality learning. Furthermore, we explore the influence of knowledge density and the use of domain-specific Large Language Models (LLMs) for caption generation, finding that denser knowledge and specialized LLMs contribute to enhanced performance. This research advances medical image analysis by demonstrating the effectiveness of knowledge injection for improving automated CXR classification, paving the way for more accurate and reliable diagnostic tools.
Remote sensing image captioning aims to generate descriptive text from remote sensing images, typically employing an encoder-decoder framework. In this setup, a convolutional neural network (CNN) extracts feature representations from the input image, which then guide the decoder in a sequence-to-sequence caption generation process. Although much research has focused on refining the decoder, the quality of image representations from the encoder remains crucial for accurate captioning. This paper introduces a novel approach that integrates features from two distinct CNN based encoders, capturing complementary information to enhance caption generation. Additionally, we propose a weighted averaging technique to combine the outputs of all GRUs in the stacked decoder. Furthermore, a comparison-based beam search strategy is incorporated to refine caption selection. The results demonstrate that our fusion-based approach, along with the enhanced stacked decoder, significantly outperforms both the transformer-based state-of-the-art model and other LSTM-based baselines.
Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://github.com/iSEE-Laboratory/LLMDet.
Since the SCICAP datasets launch in 2021, the research community has made significant progress in generating captions for scientific figures in scholarly articles. In 2023, the first SCICAP Challenge took place, inviting global teams to use an expanded SCICAP dataset to develop models for captioning diverse figure types across various academic fields. At the same time, text generation models advanced quickly, with many powerful pre-trained large multimodal models (LMMs) emerging that showed impressive capabilities in various vision-and-language tasks. This paper presents an overview of the first SCICAP Challenge and details the performance of various models on its data, capturing a snapshot of the fields state. We found that professional editors overwhelmingly preferred figure captions generated by GPT-4V over those from all other models and even the original captions written by authors. Following this key finding, we conducted detailed analyses to answer this question: Have advanced LMMs solved the task of generating captions for scientific figures?
Multi-modal transformers are rapidly gaining attention in video captioning tasks. Existing multi-modal video captioning methods typically extract a fixed number of frames, which raises critical challenges. When a limited number of frames are extracted, important frames with essential information for caption generation may be missed. Conversely, extracting an excessive number of frames includes consecutive frames, potentially causing redundancy in visual tokens extracted from consecutive video frames. To extract an appropriate number of frames for each video, this paper proposes the first model-agnostic module selection framework in video captioning that has two main functions: (1) selecting a caption generation module with an appropriate size based on visual tokens extracted from video frames, and (2) constructing subsets of visual tokens for the selected caption generation module. Furthermore, we propose a new adaptive attention masking scheme that enhances attention on important visual tokens. Our experiments on three different benchmark datasets demonstrate that the proposed framework significantly improves the performance of three recent video captioning models.
Vision language models have achieved impressive results across various fields. However, adoption in remote sensing remains limited, largely due to the scarcity of paired image-text data. To bridge this gap, synthetic caption generation has gained interest, traditionally relying on rule-based methods that use metadata or bounding boxes. While these approaches provide some description, they often lack the depth needed to capture complex wide-area scenes. Large language models (LLMs) offer a promising alternative for generating more descriptive captions, yet they can produce generic outputs and are prone to hallucination. In this paper, we propose a new method to enhance vision-language datasets for remote sensing by integrating maps as external data sources, enabling the generation of detailed, context-rich captions. Additionally, we present methods to measure and mitigate hallucinations in LLM-generated text. We introduce fMoW-mm, a multimodal dataset incorporating satellite imagery, maps, metadata, and text annotations. We demonstrate its effectiveness for automatic target recognition in few-shot settings, achieving superior performance compared to other vision-language remote sensing datasets.
Figures and their captions play a key role in scientific publications. However, despite their importance, many captions in published papers are poorly crafted, largely due to a lack of attention by paper authors. While prior AI research has explored caption generation, it has mainly focused on reader-centered use cases, where users evaluate generated captions rather than actively integrating them into their writing. This paper addresses this gap by investigating how paper authors incorporate AI-generated captions into their writing process through a user study involving 18 participants. Each participant rewrote captions for two figures from their own recently published work, using captions generated by state-of-the-art AI models as a resource. By analyzing video recordings of the writing process through interaction analysis, we observed that participants often began by copying and refining AI-generated captions. Paper writers favored longer, detail-rich captions that integrated textual and visual elements but found current AI models less effective for complex figures. These findings highlight the nuanced and diverse nature of figure caption composition, revealing design opportunities for AI systems to better support the challenges of academic writing.
Scientific figure captioning is a complex task that requires generating contextually appropriate descriptions of visual content. However, existing methods often fall short by utilizing incomplete information, treating the task solely as either an image-to-text or text summarization problem. This limitation hinders the generation of high-quality captions that fully capture the necessary details. Moreover, existing data sourced from arXiv papers contain low-quality captions, posing significant challenges for training large language models (LLMs). In this paper, we introduce a framework called Multi-LLM Collaborative Figure Caption Generation (MLBCAP) to address these challenges by leveraging specialized LLMs for distinct sub-tasks. Our approach unfolds in three key modules: (Quality Assessment) We utilize multimodal LLMs to assess the quality of training data, enabling the filtration of low-quality captions. (Diverse Caption Generation) We then employ a strategy of fine-tuning/prompting multiple LLMs on the captioning task to generate candidate captions. (Judgment) Lastly, we prompt a prominent LLM to select the highest quality caption from the candidates, followed by refining any remaining inaccuracies. Human evaluations demonstrate that informative captions produced by our approach rank better than human-written captions, highlighting its effectiveness. Our code is available at https://github.com/teamreboott/MLBCAP
The automatic generation of representative natural language descriptions for observable patterns in time series data enhances interpretability, simplifies analysis and increases cross-domain utility of temporal data. While pre-trained foundation models have made considerable progress in natural language processing (NLP) and computer vision (CV), their application to time series analysis has been hindered by data scarcity. Although several large language model (LLM)-based methods have been proposed for time series forecasting, time series captioning is under-explored in the context of LLMs. In this paper, we introduce TSLM, a novel time series language model designed specifically for time series captioning. TSLM operates as an encoder-decoder model, leveraging both text prompts and time series data representations to capture subtle temporal patterns across multiple phases and generate precise textual descriptions of time series inputs. TSLM addresses the data scarcity problem in time series captioning by first leveraging an in-context prompting synthetic data generation, and second denoising the generated data via a novel cross-modal dense retrieval scoring applied to time series-caption pairs. Experimental findings on various time series captioning datasets demonstrate that TSLM outperforms existing state-of-the-art approaches from multiple data modalities by a significant margin.
Recently, zero-shot image captioning has gained increasing attention, where only text data is available for training. The remarkable progress in text-to-image diffusion model presents the potential to resolve this task by employing synthetic image-caption pairs generated by this pre-trained prior. Nonetheless, the defective details in the salient regions of the synthetic images introduce semantic misalignment between the synthetic image and text, leading to compromised results. To address this challenge, we propose a novel Patch-wise Cross-modal feature Mix-up (PCM) mechanism to adaptively mitigate the unfaithful contents in a fine-grained manner during training, which can be integrated into most of encoder-decoder frameworks, introducing our PCM-Net. Specifically, for each input image, salient visual concepts in the image are first detected considering the image-text similarity in CLIP space. Next, the patch-wise visual features of the input image are selectively fused with the textual features of the salient visual concepts, leading to a mixed-up feature map with less defective content. Finally, a visual-semantic encoder is exploited to refine the derived feature map, which is further incorporated into the sentence decoder for caption generation. Additionally, to facilitate the model training with synthetic data, a novel CLIP-weighted cross-entropy loss is devised to prioritize the high-quality image-text pairs over the low-quality counterparts. Extensive experiments on MSCOCO and Flickr30k datasets demonstrate the superiority of our PCM-Net compared with state-of-the-art VLMs-based approaches. It is noteworthy that our PCM-Net ranks first in both in-domain and cross-domain zero-shot image captioning. The synthetic dataset SynthImgCap and code are available at https://jianjieluo.github.io/SynthImgCap.
Multimodal large language models (MLLMs) have significantly advanced tasks like caption generation and visual question answering by integrating visual and textual data. However, they sometimes produce misleading or hallucinate content due to discrepancies between their pre-training data and real user prompts. Existing approaches using Direct Preference Optimization (DPO) in vision-language tasks often rely on strong models like GPT-4 or CLIP to determine positive and negative responses. Here, we propose a new framework in generating synthetic data using a reward model as a proxy of human preference for effective multimodal alignment with DPO training. The resulting DPO dataset ranges from 2K to 9K image-text pairs, was evaluated on LLaVA-v1.5-7B, where our approach demonstrated substantial improvements in both the trustworthiness and reasoning capabilities of the base model across multiple hallucination and vision-language benchmark. The experiment results indicate that integrating selected synthetic data, such as from generative and rewards models can effectively reduce reliance on human-annotated data while enhancing MLLMs' alignment capability, offering a scalable solution for safer deployment.
Scalable learning of humanoid robots is crucial for their deployment in real-world applications. While traditional approaches primarily rely on reinforcement learning or teleoperation to achieve whole-body control, they are often limited by the diversity of simulated environments and the high costs of demonstration collection. In contrast, human videos are ubiquitous and present an untapped source of semantic and motion information that could significantly enhance the generalization capabilities of humanoid robots. This paper introduces Humanoid-X, a large-scale dataset of over 20 million humanoid robot poses with corresponding text-based motion descriptions, designed to leverage this abundant data. Humanoid-X is curated through a comprehensive pipeline: data mining from the Internet, video caption generation, motion retargeting of humans to humanoid robots, and policy learning for real-world deployment. With Humanoid-X, we further train a large humanoid model, UH-1, which takes text instructions as input and outputs corresponding actions to control a humanoid robot. Extensive simulated and real-world experiments validate that our scalable training approach leads to superior generalization in text-based humanoid control, marking a significant step toward adaptable, real-world-ready humanoid robots.
The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tasks. CapAgent automatically transforms user-provided simple instructions into detailed, professional instructions, enabling precise and context-aware caption generation. By leveraging multimodal large language models (MLLMs) and external tools such as object detection tool and search engines, the system ensures that captions adhere to specified guidelines, including sentiment, keywords, focus, and formatting. CapAgent transparently controls each step of the captioning process, and showcases its reasoning and tool usage at every step, fostering user trust and engagement. The project code is available at https://github.com/xin-ran-w/CapAgent.
Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on raw captions or parsed objects, which fail to capture the full semantic richness of the data. In this paper, we propose Dive Into Retrieval (DIR), a method designed to enhance both the image-to-text retrieval process and the utilization of retrieved text to achieve a more comprehensive understanding of the visual content. Our approach introduces two key innovations: (1) diffusion-guided retrieval enhancement, where a pretrained diffusion model guides image feature learning by reconstructing noisy images, allowing the model to capture more comprehensive and fine-grained visual information beyond standard annotated captions; and (2) a high-quality retrieval database, which provides comprehensive semantic information to enhance caption generation, especially in out-of-domain scenarios. Extensive experiments demonstrate that DIR not only maintains competitive in-domain performance but also significantly improves out-of-domain generalization, all without increasing inference costs.