Collage: Decomposable Rapid Prototyping for Information Extraction on Scientific PDFs

Recent years in NLP have seen the continued development of domain-specific information extraction tools for scientific documents, alongside the release of increasingly multimodal pretrained transformer models. While the opportunity for scientists outside of NLP to evaluate and apply such systems to their own domains has never been clearer, these models are difficult to compare: they accept different input formats, are often black-box and give little insight into processing failures, and rarely handle PDF documents, the most common format of scientific publication. In this work, we present Collage, a tool designed for rapid prototyping, visualization, and evaluation of different information extraction models on scientific PDFs. Collage allows the use and evaluation of any HuggingFace token classifier, several LLMs, and multiple other task-specific models out of the box, and provides extensible software interfaces to accelerate experimentation with new models. Further, we enable both developers and users of NLP-based tools to inspect, debug, and better understand modeling pipelines by providing granular views of intermediate states of processing. We demonstrate our system in the context of information extraction to assist with literature review in materials science.

PViT: Prior-augmented Vision Transformer for Out-of-distribution Detection

Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for image Out-of-Distribution (OOD) detection, we introduce a novel and generic framework named Prior-augmented Vision Transformer (PViT). PViT identifies OOD samples by quantifying the divergence between the predicted class logits and the prior logits obtained from pre-trained models. Unlike existing state-of-the-art OOD detection methods, PViT shapes the decision boundary between ID and OOD by utilizing the proposed prior guide confidence, without requiring additional data modeling, generation methods, or structural modifications. Extensive experiments on the large-scale ImageNet benchmark demonstrate that PViT significantly outperforms existing state-of-the-art OOD detection methods. Additionally, through comprehensive analyses, ablation studies, and discussions, we show how PViT can strategically address specific challenges in managing large vision models, paving the way for new advancements in OOD detection.

MorphoSeg: An Uncertainty-Aware Deep Learning Method for Biomedical Segmentation of Complex Cellular Morphologies

Deep learning has revolutionized medical and biological imaging, particularly in segmentation tasks. However, segmenting biological cells remains challenging due to the high variability and complexity of cell shapes. Addressing this challenge requires high-quality datasets that accurately represent the diverse morphologies found in biological cells. Existing cell segmentation datasets are often limited by their focus on regular and uniform shapes. In this paper, we introduce a novel benchmark dataset of Ntera-2 (NT2) cells, a pluripotent carcinoma cell line, exhibiting diverse morphologies across multiple stages of differentiation, capturing the intricate and heterogeneous cellular structures that complicate segmentation tasks. To address these challenges, we propose an uncertainty-aware deep learning framework for complex cellular morphology segmentation (MorphoSeg) by incorporating sampling of virtual outliers from low-likelihood regions during training. Our comprehensive experimental evaluations against state-of-the-art baselines demonstrate that MorphoSeg significantly enhances segmentation accuracy, achieving up to a 7.74% increase in the Dice Similarity Coefficient (DSC) and a 28.36% reduction in the Hausdorff Distance. These findings highlight the effectiveness of our dataset and methodology in advancing cell segmentation capabilities, especially for complex and variable cell morphologies. The dataset and source code is publicly available at https://github.com/RanchoGoose/MorphoSeg.

Gaussian Representation for Deformable Image Registration

Deformable image registration (DIR) is a fundamental task in radiotherapy, with existing methods often struggling to balance computational efficiency, registration accuracy, and speed effectively. We introduce a novel DIR approach employing parametric 3D Gaussian control points achieving a better tradeoff. It provides an explicit and flexible representation for spatial deformation fields between 3D volumetric medical images, producing a displacement vector field (DVF) across all volumetric positions. The movement of individual voxels is derived using linear blend skinning (LBS) through localized interpolation of transformations associated with neighboring Gaussians. This interpolation strategy not only simplifies the determination of voxel motions but also acts as an effective regularization technique. Our approach incorporates a unified optimization process through backpropagation, enabling iterative learning of both the parameters of the 3D Gaussians and their transformations. Additionally, the density of Gaussians is adjusted adaptively during the learning phase to accommodate varying degrees of motion complexity. We validated our approach on the 4D-CT lung DIR-Lab and cardiac ACDC datasets, achieving an average target registration error (TRE) of 1.06 mm within a much-improved processing time of 2.43 seconds for the DIR-Lab dataset over existing methods, demonstrating significant advancements in both accuracy and efficiency.

On the Sequence Evaluation based on Stochastic Processes

Modeling and analyzing long sequences of text is an essential task for Natural Language Processing. Success in capturing long text dynamics using neural language models will facilitate many downstream tasks such as coherence evaluation, text generation, machine translation and so on. This paper presents a novel approach to model sequences through a stochastic process. We introduce a likelihood-based training objective for the text encoder and design a more thorough measurement (score) for long text evaluation compared to the previous approach. The proposed training objective effectively preserves the sequence coherence, while the new score comprehensively captures both temporal and spatial dependencies. Theoretical properties of our new score show its advantages in sequence evaluation. Experimental results show superior performance in various sequence evaluation tasks, including global and local discrimination within and between documents of different lengths. We also demonstrate the encoder achieves competitive results on discriminating human and AI written text.

BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence

Measuring the coherence of text is a vital aspect of evaluating the quality of written content. Recent advancements in neural coherence modeling have demonstrated their efficacy in capturing entity coreference and discourse relations, thereby enhancing coherence evaluation. However, many existing methods heavily depend on static embeddings or focus narrowly on nearby context, constraining their capacity to measure the overarching coherence of long texts. In this paper, we posit that coherent texts inherently manifest a sequential and cohesive interplay among sentences, effectively conveying the central theme, purpose, or standpoint. To explore this abstract relationship, we introduce the "BBScore," a novel reference-free metric grounded in Brownian bridge theory for assessing text coherence. Our findings showcase that when synergized with a simple additional classification component, this metric attains a performance level comparable to state-of-the-art techniques on standard artificial discrimination tasks. We also establish in downstream tasks that this metric effectively differentiates between human-written documents and text generated by large language models under a specific domain. Furthermore, we illustrate the efficacy of this approach in detecting written styles attributed to diverse large language models, underscoring its potential for generalizability. In summary, we present a novel Brownian bridge coherence metric capable of measuring both local and global text coherence, while circumventing the need for end-to-end model training. This flexibility allows for its application in various downstream tasks.

Out-of-distribution Object Detection through Bayesian Uncertainty Estimation

The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to uncertainty in the results. In this paper, we propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Unlike other uncertainty-modeling methods that either require huge computational costs to infer the weight distributions or rely on model training through synthetic outlier data, our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions based on pre-trained networks. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets as the ID datasets and evaluated on COCO2017 dataset as the OOD dataset.

MRET: Multi-resolution Transformer for Video Quality Assessment

No-reference video quality assessment (NR-VQA) for user generated content (UGC) is crucial for understanding and improving visual experience. Unlike video recognition tasks, VQA tasks are sensitive to changes in input resolution. Since large amounts of UGC videos nowadays are 720p or above, the fixed and relatively small input used in conventional NR-VQA methods results in missing high-frequency details for many videos. In this paper, we propose a novel Transformer-based NR-VQA framework that preserves the high-resolution quality information. With the multi-resolution input representation and a novel multi-resolution patch sampling mechanism, our method enables a comprehensive view of both the global video composition and local high-resolution details. The proposed approach can effectively aggregate quality information across different granularities in spatial and temporal dimensions, making the model robust to input resolution variations. Our method achieves state-of-the-art performance on large-scale UGC VQA datasets LSVQ and LSVQ-1080p, and on KoNViD-1k and LIVE-VQC without fine-tuning.

MACC: Cross-Layer Multi-Agent Congestion Control with Deep Reinforcement Learning

Congestion Control (CC), as the core networking task to efficiently utilize network capacity, received great attention and widely used in various Internet communication applications such as 5G, Internet-of-Things, UAN, and more. Various CC algorithms have been proposed both on network and transport layers such as Active Queue Management (AQM) algorithm and Transmission Control Protocol (TCP) congestion control mechanism. But it is hard to model dynamic AQM/TCP system and cooperate two algorithms to obtain excellent performance under different communication scenarios. In this paper, we explore the performance of multi-agent reinforcement learning-based cross-layer congestion control algorithms and present cooperation performance of two agents, known as MACC (Multi-agent Congestion Control). We implement MACC in NS3. The simulation results show that our scheme outperforms other congestion control combination in terms of throughput and delay, etc. Not only does it proves that networking protocols based on multi-agent deep reinforcement learning is efficient for communication managing, but also verifies that networking area can be used as new playground for machine learning algorithms.

Exploring Semantic Relationships for Unpaired Image Captioning

Recently, image captioning has aroused great interest in both academic and industrial worlds. Most existing systems are built upon large-scale datasets consisting of image-sentence pairs, which, however, are time-consuming to construct. In addition, even for the most advanced image captioning systems, it is still difficult to realize deep image understanding. In this work, we achieve unpaired image captioning by bridging the vision and the language domains with high-level semantic information. The motivation stems from the fact that the semantic concepts with the same modality can be extracted from both images and descriptions. To further improve the quality of captions generated by the model, we propose the Semantic Relationship Explorer, which explores the relationships between semantic concepts for better understanding of the image. Extensive experiments on MSCOCO dataset show that we can generate desirable captions without paired datasets. Furthermore, the proposed approach boosts five strong baselines under the paired setting, where the most significant improvement in CIDEr score reaches 8%, demonstrating that it is effective and generalizes well to a wide range of models.