Recently, the decentralized baseband processing (DBP) paradigm and relevant detection methods have been proposed to enable extremely large-scale massive multiple-input multiple-output technology. Under the DBP architecture, base station antennas are divided into several independent clusters, each connected to a local computing fabric. However, current detection methods tailored to DBP only consider ideal white Gaussian noise scenarios, while in practice, the noise is often colored due to interference from neighboring cells. Moreover, in the DBP architecture, linear minimum mean-square error (LMMSE) detection methods rely on the estimation of the noise covariance matrix through averaging distributedly stored noise samples. This presents a significant challenge for decentralized LMMSE-based equalizer design. To address this issue, this paper proposes decentralized LMMSE equalization methods under colored noise scenarios for both star and daisy chain DBP architectures. Specifically, we first propose two decentralized equalizers for the star DBP architecture based on dimensionality reduction techniques. Then, we derive an optimal decentralized equalizer using the block coordinate descent (BCD) method for the daisy chain DBP architecture with a bandwidth reduction enhancement scheme based on decentralized low-rank decomposition. Finally, simulation results demonstrate that our proposed methods can achieve excellent detection performance while requiring much less communication bandwidth.
Large Language Models (LLMs) present immense potential in the medical field, yet concerns over data privacy, regulatory compliance, and model stability restrict their widespread adoption. Although the distillation of high-performing closed-source LLMs has proven effective for general tasks, their application in healthcare is limited due to reduced domain knowledge and remnants of alignment behavior hindering clinical tasks. To address these challenges, we propose Dialogue-Based Knowledge Encoding (DBKE). DBKE enhances models' implicit knowledge base and primes them for conversational recall, augmenting their conversational capabilities and enabling a soft alignment for subsequent use cases. By transforming dense academic source text into synthetic dialogue, DBKE broadens the model's knowledge base and enables a soft alignment that guides downstream behaviours. We present Clinical Camel, an open-source, healthcare-focused conversational model, to showcase the effectiveness of DBKE. Clinical Camel outperforms GPT-3.5 on the United States Medical Licensing Examination (USMLE) Step 1 and Step 3 with scores of 53.2 % and 58.2 %, respectively, compared to GPT-3.5's scores of 36.1 % and 55.7 %. Clinical Camel adeptly handles multi-stage clinical case problems, provides adaptive counseling, and generates clinical notes. However, it is prone to hallucinations, which pose a significant obstacle in safety-critical settings. The performance of Clinical Camel underscores the importance of continued research and development of open-source models for the safe and effective integration of LLMs in healthcare settings.
Sensitivity to severe occlusion and large view angles limits the usage scenarios of the existing monocular 3D dense face alignment methods. The state-of-the-art 3DMM-based method, directly regresses the model's coefficients, underutilizing the low-level 2D spatial and semantic information, which can actually offer cues for face shape and orientation. In this work, we demonstrate how modeling 3D facial geometry in image and model space jointly can solve the occlusion and view angle problems. Instead of predicting the whole face directly, we regress image space features in the visible facial region by dense prediction first. Subsequently, we predict our model's coefficients based on the regressed feature of the visible regions, leveraging the prior knowledge of whole face geometry from the morphable models to complete the invisible regions. We further propose a fusion network that combines the advantages of both the image and model space predictions to achieve high robustness and accuracy in unconstrained scenarios. Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method. Comprehensive evaluations demonstrate the superior performance of our method compared with the state-of-the-art methods. On the 3D dense face alignment task, we achieve 3.80% NME on the AFLW2000-3D dataset, which outperforms the state-of-the-art method by 5.5%. Code is available at https://github.com/lhyfst/DSFNet.
The personalized dialogue explores the consistent relationship between dialogue generation and personality. Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue histories. However, sparse structured persona attributes are explicit but uninformative, dense persona texts contain rich persona descriptions with much noise, and dialogue history query is both noisy and uninformative for persona modeling. In this work, we combine the advantages of the three resources to obtain a richer and more accurate persona. We design a Contrastive Latent Variable-based model (CLV) that clusters the dense persona descriptions into sparse categories, which are combined with the history query to generate personalized responses. Experimental results on Chinese and English datasets demonstrate our model's superiority in personalization.
This paper addresses the emerging task of recognizing multiple retinal diseases from wide-field (WF) and ultra-wide-field (UWF) fundus images. For an effective reuse of existing labeled color fundus photo (CFP) data, we propose Cross-domain Collaborative Learning (CdCL). Inspired by the success of fixed-ratio based mixup in unsupervised domain adaptation, we re-purpose this strategy for the current task. Due to the intrinsic disparity between the field-of-view of CFP and WF/UWF images, a scale bias naturally exists in a mixup sample that the anatomic structure from a CFP image will be considerably larger than its WF/UWF counterpart. The CdCL method resolves the issue by Scale-bias Correction, which employs Transformers for producing scale-invariant features. As demonstrated by extensive experiments on multiple datasets covering both WF and UWF images, the proposed method compares favorably against a number of competitive baselines.
This paper describes our submission to the MEDIQA-Chat 2023 shared task for automatic clinical note generation from doctor-patient conversations. We report results for two approaches: the first fine-tunes a pre-trained language model (PLM) on the shared task data, and the second uses few-shot in-context learning (ICL) with a large language model (LLM). Both achieve high performance as measured by automatic metrics (e.g. ROUGE, BERTScore) and ranked second and first, respectively, of all submissions to the shared task. Expert human scrutiny indicates that notes generated via the ICL-based approach with GPT-4 are preferred about as often as human-written notes, making it a promising path toward automated note generation from doctor-patient conversations.
Segment anything model (SAM) has revolutionized natural image segmentation, but its performance on medical images is limited. This work presents MedSAM, the first attempt at extending the success of SAM to medical images, with the goal of creating a universal tool for the segmentation of various medical targets. Specifically, we first curate a large-scale medical image dataset, encompassing over 200,000 masks across 11 different modalities. Then, we develop a simple fine-tuning method to adapt SAM to general medical image segmentation. Comprehensive experiments on 21 3D segmentation tasks and 9 2D segmentation tasks demonstrate that MedSAM outperforms the default SAM model with an average Dice Similarity Coefficient (DSC) of 22.5% and 17.6% on 3D and 2D segmentation tasks, respectively. The code and trained model are publicly available at \url{https://github.com/bowang-lab/MedSAM}.
Over the past few decades, fiber-optic time synchronization (FOTS) has provided fundamental support for the efficient operation of modern society. Looking toward the future beyond fifth-generation/sixth-generation (B5G/6G) scenarios and very large radio telescope arrays, developing high-precision, low-complexity and scalable FOTS technology is crucial for building a large-scale time synchronization network. However, the traditional two-way FOTS method needs a data layer to exchange time delay information. This increases the complexity of system and makes it impossible to realize multiple-access time synchronization. In this paper, a time reversal enabled FOTS method is proposed. It measures the clock difference between two locations without involving a data layer, which can reduce the complexity of the system. Moreover, it can also achieve multiple-access time synchronization along the fiber link. Tests over a 230 km fiber link have been carried out to demonstrate the high performance of the proposed method.
Based on the variational method, we propose a novel paradigm that provides a unified framework of training neural operators and solving partial differential equations (PDEs) with the variational form, which we refer to as the variational operator learning (VOL). We first derive the functional approximation of the system from the node solution prediction given by neural operators, and then conduct the variational operation by automatic differentiation, constructing a forward-backward propagation loop to derive the residual of the linear system. One or several update steps of the steepest decent method (SD) and the conjugate gradient method (CG) are provided in every iteration as a cheap yet effective update for training the neural operators. Experimental results show the proposed VOL can learn a variety of solution operators in PDEs of the steady heat transfer and the variable stiffness elasticity with satisfactory results and small error. The proposed VOL achieves nearly label-free training. Only five to ten labels are used for the output distribution-shift session in all experiments. Generalization benefits of the VOL are investigated and discussed.
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e.g., emotion status) and cognitive factors (e.g., cause of the emotion). Besides concerning emotion status in early work, the latest approaches study emotion causes in empathetic dialogue. These approaches focus on understanding and duplicating emotion causes in the context to show empathy for the speaker. However, instead of only repeating the contextual causes, the real empathic response often demonstrate a logical and emotion-centered transition from the causes in the context to those in the responses. In this work, we propose an emotion cause transition graph to explicitly model the natural transition of emotion causes between two adjacent turns in empathetic dialogue. With this graph, the concept words of the emotion causes in the next turn can be predicted and used by a specifically designed concept-aware decoder to generate the empathic response. Automatic and human experimental results on the benchmark dataset demonstrate that our method produces more empathetic, coherent, informative, and specific responses than existing models.