Conditional text-to-image generation has seen countless recent improvements in terms of quality, diversity and fidelity. Nevertheless, most state-of-the-art models require numerous inference steps to produce faithful generations, resulting in performance bottlenecks for end-user applications. In this paper we introduce Paella, a novel text-to-image model requiring less than 10 steps to sample high-fidelity images, using a speed-optimized architecture allowing to sample a single image in less than 500 ms, while having 573M parameters. The model operates on a compressed & quantized latent space, it is conditioned on CLIP embeddings and uses an improved sampling function over previous works. Aside from text-conditional image generation, our model is able to do latent space interpolation and image manipulations such as inpainting, outpainting, and structural editing. We release all of our code and pretrained models at https://github.com/dome272/Paella
The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a dividing-and-conquering strategy, which involves: 1) developing a point-cloud detector that can learn a general representation for localizing various objects, and 2) connecting textual and point-cloud representations to enable the detector to classify novel object categories based on text prompting. Specifically, we resort to rich image pre-trained models, by which the point-cloud detector learns localizing objects under the supervision of predicted 2D bounding boxes from 2D pre-trained detectors. Moreover, we propose a novel de-biased triplet cross-modal contrastive learning to connect the modalities of image, point-cloud and text, thereby enabling the point-cloud detector to benefit from vision-language pre-trained models,i.e.,CLIP. The novel use of image and vision-language pre-trained models for point-cloud detectors allows for open-vocabulary 3D object detection without the need for 3D annotations. Experiments demonstrate that the proposed method improves at least 3.03 points and 7.47 points over a wide range of baselines on the ScanNet and SUN RGB-D datasets, respectively. Furthermore, we provide a comprehensive analysis to explain why our approach works.
Language is one of the primary means by which we describe the 3D world around us. While rapid progress has been made in text-to-2D-image synthesis, similar progress in text-to-3D-shape synthesis has been hindered by the lack of paired (text, shape) data. Moreover, extant methods for text-to-shape generation have limited shape diversity and fidelity. We introduce TextCraft, a method to address these limitations by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs for training. TextCraft achieves this by using CLIP and using a multi-resolution approach by first generating in a low-dimensional latent space and then upscaling to a higher resolution, improving the fidelity of the generated shape. To improve shape diversity, we use a discrete latent space which is modelled using a bidirectional transformer conditioned on the interchangeable image-text embedding space induced by CLIP. Moreover, we present a novel variant of classifier-free guidance, which further improves the accuracy-diversity trade-off. Finally, we perform extensive experiments that demonstrate that TextCraft outperforms state-of-the-art baselines.
Simultaneous localization and mapping (SLAM) is a critical technology that enables autonomous robots to be aware of their surrounding environment. With the development of deep learning, SLAM systems can achieve a higher level of perception of the environment, including the semantic and text levels. However, current works are limited in their ability to achieve a natural-language level of perception of the world. To address this limitation, we propose LP-SLAM, the first language-perceptive SLAM system that leverages large language models (LLMs). LP-SLAM has two major features: (a) it can detect text in the scene and determine whether it represents a landmark to be stored during the tracking and mapping phase, and (b) it can understand natural language input from humans and provide guidance based on the generated map. We illustrated three usages of the LLM in the system including text cluster, landmark judgment, and natural language navigation. Our proposed system represents an advancement in the field of LLMs based SLAM and opens up new possibilities for autonomous robots to interact with their environment in a more natural and intuitive way.
Ground-air negotiation via speech communication is a vital prerequisite for ensuring safety and efficiency in air traffic control (ATC) operations. However, with the increase in traffic flow, incorrect instructions caused by human factors bring a great threat to ATC safety. Existing flight trajectory prediction (FTP) approaches primarily rely on the flight status of historical trajectory, leading to significant delays in the prediction of real-time maneuvering instruction, which is not conducive to conflict detection. A major reason is that spoken instructions and flight trajectories are presented in different modalities in the current air traffic control (ATC) system, bringing great challenges to considering the maneuvering instruction in the FTP tasks. In this paper, a spoken instruction-aware FTP framework, called SIA-FTP, is innovatively proposed to support high-maneuvering FTP tasks by incorporating instant spoken instruction. To address the modality gap and minimize the data requirements, a 3-stage learning paradigm is proposed to implement the SIA-FTP framework in a progressive manner, including trajectory-based FTP pretraining, intent-oriented instruction embedding learning, and multi-modal finetuning. Specifically, the FTP model and the instruction embedding with maneuvering semantics are pre-trained using volumes of well-resourced trajectory and text data in the 1st and 2nd stages. In succession, a multi-modal fusion strategy is proposed to incorporate the pre-trained instruction embedding into the FTP model and integrate the two pre-trained networks into a joint model. Finally, the joint model is finetuned using the limited trajectory-instruction data to enhance the FTP performance within maneuvering instruction scenarios. The experimental results demonstrated that the proposed framework presents an impressive performance improvement in high-maneuvering scenarios.
Within the text analysis and processing fields, generated text attacks have been made easier to create than ever before. To combat these attacks open sourcing models and datasets have become a major trend to create automated detection algorithms in defense of authenticity. For this purpose, synthetic text detection has become an increasingly viable topic of research. This review is written for the purpose of creating a snapshot of the state of current literature and easing the barrier to entry for future authors. Towards that goal, we identified few research trends and challenges in this field.
The extraction of structured clinical information from free-text radiology reports in the form of radiology graphs has been demonstrated to be a valuable approach for evaluating the clinical correctness of report-generation methods. However, the direct generation of radiology graphs from chest X-ray (CXR) images has not been attempted. To address this gap, we propose a novel approach called Prior-RadGraphFormer that utilizes a transformer model with prior knowledge in the form of a probabilistic knowledge graph (PKG) to generate radiology graphs directly from CXR images. The PKG models the statistical relationship between radiology entities, including anatomical structures and medical observations. This additional contextual information enhances the accuracy of entity and relation extraction. The generated radiology graphs can be applied to various downstream tasks, such as free-text or structured reports generation and multi-label classification of pathologies. Our approach represents a promising method for generating radiology graphs directly from CXR images, and has significant potential for improving medical image analysis and clinical decision-making.
A wave of new task-based virtual assistants has been fueled by increasingly powerful large language models, such as GPT-4. These conversational agents can be customized to serve customer-specific use cases, but ensuring that agent-generated text conforms to designer-specified rules included in prompt instructions alone is challenging. Therefore, chatbot designers often use another model, called a guardrail model, to verify that the agent output aligns with their rules and constraints. We explore using a distillation approach to guardrail models to monitor the output of the first model using training data from GPT-4. We find two crucial steps to our CONSCENDI process: scenario-augmented generation and contrastive training examples. When generating conversational data, we generate a set of rule-breaking scenarios, which enumerate a diverse set of high-level ways a rule can be violated. This scenario-guided approach produces a diverse training set of rule-violating conversations, and it provides chatbot designers greater control over the classification process. We also prompt GPT-4 to also generate contrastive examples by altering conversations with violations into acceptable conversations. This set of borderline, contrastive examples enables the distilled model to learn finer-grained distinctions between what is acceptable and what is not. We find that CONSCENDI results in guardrail models that improve over baselines.
Medical coding is the task of assigning medical codes to clinical free-text documentation. Healthcare professionals manually assign such codes to track patient diagnoses and treatments. Automated medical coding can considerably alleviate this administrative burden. In this paper, we reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. In previous work, the macro F1 score has been calculated sub-optimally, and our correction doubles it. We contribute a revised model comparison using stratified sampling and identical experimental setups, including hyperparameters and decision boundary tuning. We analyze prediction errors to validate and falsify assumptions of previous works. The analysis confirms that all models struggle with rare codes, while long documents only have a negligible impact. Finally, we present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models. We release our code, model parameters, and new MIMIC-III and MIMIC-IV training and evaluation pipelines to accommodate fair future comparisons.
Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision helped building document-focused pre-training methods, leveraging a multimodal understanding of the document text, layout and image modalities. However, these breakthroughs also led to the emergence of a new DocKIE subtask of extractive document Question Answering (DocQA), as part of the Machine Reading Comprehension (MRC) research field. In this work, we compare the Question Answering approach with the classical token classification approach for document key information extraction. We designed experiments to benchmark five different experimental setups : raw performances, robustness to noisy environment, capacity to extract long entities, fine-tuning speed on Few-Shot Learning and finally Zero-Shot Learning. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach, while the QA approach could be a good alternative for noisy environment or long entities use-cases.