XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion

Nuclear fusion is one of the most promising ways for humans to obtain infinite energy. Currently, with the rapid development of artificial intelligence, the mission of nuclear fusion has also entered a critical period of its development. How to let more people to understand nuclear fusion and join in its research is one of the effective means to accelerate the implementation of fusion. This paper proposes the first large model in the field of nuclear fusion, XiHeFusion, which is obtained through supervised fine-tuning based on the open-source large model Qwen2.5-14B. We have collected multi-source knowledge about nuclear fusion tasks to support the training of this model, including the common crawl, eBooks, arXiv, dissertation, etc. After the model has mastered the knowledge of the nuclear fusion field, we further used the chain of thought to enhance its logical reasoning ability, making XiHeFusion able to provide more accurate and logical answers. In addition, we propose a test questionnaire containing 180+ questions to assess the conversational ability of this science popularization large model. Extensive experimental results show that our nuclear fusion dialogue model, XiHeFusion, can perform well in answering science popularization knowledge. The pre-trained XiHeFusion model is released on https://github.com/Event-AHU/XiHeFusion.

Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning

Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.

Continual SFT Matches Multimodal RLHF with Negative Supervision

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multimodal RLHF lies in its negative supervision, the logit of the rejected responses. We thus propose a novel negative supervised finetuning (nSFT) approach that fully excavates these information resided. Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with a simple SFT loss. This is more memory efficient than multimodal RLHF where 2 (e.g., DPO) or 4 (e.g., PPO) large VLMs are strictly required. The effectiveness of nSFT is rigorously proved by comparing it with various multimodal RLHF approaches, across different dataset sources, base VLMs and evaluation metrics. Besides, fruitful of ablations are provided to support our hypothesis. We hope this paper will stimulate further research to properly align large vision language models.

Improving Multi-modal Large Language Model through Boosting Vision Capabilities

We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}.

Automated Quantification of Hyperreflective Foci in SD-OCT With Diabetic Retinopathy

The presence of hyperreflective foci (HFs) is related to retinal disease progression, and the quantity has proven to be a prognostic factor of visual and anatomical outcome in various retinal diseases. However, lack of efficient quantitative tools for evaluating the HFs has deprived ophthalmologist of assessing the volume of HFs. For this reason, we propose an automated quantification algorithm to segment and quantify HFs in spectral domain optical coherence tomography (SD-OCT). The proposed algorithm consists of two parallel processes namely: region of interest (ROI) generation and HFs estimation. To generate the ROI, we use morphological reconstruction to obtain the reconstructed image and histogram constructed for data distributions and clustering. In parallel, we estimate the HFs by extracting the extremal regions from the connected regions obtained from a component tree. Finally, both the ROI and the HFs estimation process are merged to obtain the segmented HFs. The proposed algorithm was tested on 40 3D SD-OCT volumes from 40 patients diagnosed with non-proliferative diabetic retinopathy (NPDR), proliferative diabetic retinopathy (PDR), and diabetic macular edema (DME). The average dice similarity coefficient (DSC) and correlation coefficient (r) are 69.70%, 0.99 for NPDR, 70.31%, 0.99 for PDR, and 71.30%, 0.99 for DME, respectively. The proposed algorithm can provide ophthalmologist with good HFs quantitative information, such as volume, size, and location of the HFs.

OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer

Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-vocabulary detector with strong performance and low latency. Building upon OVLW-DETR, we provide an end-to-end training recipe that transferring knowledge from vision-language model (VLM) to object detector with simple alignment. We align detector with the text encoder from VLM by replacing the fixed classification layer weights in detector with the class-name embeddings extracted from the text encoder. Without additional fusing module, OVLW-DETR is flexible and deployment friendly, making it easier to implement and modulate. improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time open-vocabulary detectors on standard Zero-Shot LVIS benchmark. Source code and pre-trained models are available at [https://github.com/Atten4Vis/LW-DETR].

Test-Time Generative Augmentation for Medical Image Segmentation

In this paper, we propose a novel approach to enhance medical image segmentation during test time. Instead of employing hand-crafted transforms or functions on the input test image to create multiple views for test-time augmentation, we advocate for the utilization of an advanced domain-fine-tuned generative model (GM), e.g., stable diffusion (SD), for test-time augmentation. Given that the GM has been trained to comprehend and encapsulate comprehensive domain data knowledge, it is superior than segmentation models in terms of representing the data characteristics and distribution. Hence, by integrating the GM into test-time augmentation, we can effectively generate multiple views of a given test sample, aligning with the content and appearance characteristics of the sample and the related local data distribution. This approach renders the augmentation process more adaptable and resilient compared to conventional handcrafted transforms. Comprehensive experiments conducted across three medical image segmentation tasks (nine datasets) demonstrate the efficacy and versatility of the proposed TTGA in enhancing segmentation outcomes. Moreover, TTGA significantly improves pixel-wise error estimation, thereby facilitating the deployment of a more reliable segmentation system. Code will be released at: https://github.com/maxiao0234/TTGA.

LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR).

Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models

Optical coherence tomography (OCT) image analysis plays an important role in the field of ophthalmology. Current successful analysis models rely on available large datasets, which can be challenging to be obtained for certain tasks. The use of deep generative models to create realistic data emerges as a promising approach. However, due to limitations in hardware resources, it is still difficulty to synthesize high-resolution OCT volumes. In this paper, we introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way. First, we propose non-holistic autoencoders to efficiently build a bidirectional mapping between high-resolution volume space and low-resolution latent space. In tandem with autoencoders, we propose cascaded diffusion processes to synthesize high-resolution OCT volumes with a global-to-local refinement process, amortizing the memory and computational demands. Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods. Moreover, performance gains on two down-stream fine-grained segmentation tasks demonstrate the benefit of the proposed method in training deep learning models for medical imaging tasks. The code is public available at: https://github.com/nicetomeetu21/CA-LDM.

Adaptive Fuzzy C-Means with Graph Embedding

Fuzzy clustering algorithms can be roughly categorized into two main groups: Fuzzy C-Means (FCM) based methods and mixture model based methods. However, for almost all existing FCM based methods, how to automatically selecting proper membership degree hyper-parameter values remains a challenging and unsolved problem. Mixture model based methods, while circumventing the difficulty of manually adjusting membership degree hyper-parameters inherent in FCM based methods, often have a preference for specific distributions, such as the Gaussian distribution. In this paper, we propose a novel FCM based clustering model that is capable of automatically learning an appropriate membership degree hyper-parameter value and handling data with non-Gaussian clusters. Moreover, by removing the graph embedding regularization, the proposed FCM model can degenerate into the simplified generalized Gaussian mixture model. Therefore, the proposed FCM model can be also seen as the generalized Gaussian mixture model with graph embedding. Extensive experiments are conducted on both synthetic and real-world datasets to demonstrate the effectiveness of the proposed model.