Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction

This paper addresses the challenges posed by the unstructured nature and high-dimensional semantic complexity of electronic health record texts. A deep learning method based on attention mechanisms is proposed to achieve unified modeling for information extraction and multi-label disease prediction. The study is conducted on the MIMIC-IV dataset. A Transformer-based architecture is used to perform representation learning over clinical text. Multi-layer self-attention mechanisms are employed to capture key medical entities and their contextual relationships. A Sigmoid-based multi-label classifier is then applied to predict multiple disease labels. The model incorporates a context-aware semantic alignment mechanism, enhancing its representational capacity in typical medical scenarios such as label co-occurrence and sparse information. To comprehensively evaluate model performance, a series of experiments were conducted, including baseline comparisons, hyperparameter sensitivity analysis, data perturbation studies, and noise injection tests. Results demonstrate that the proposed method consistently outperforms representative existing approaches across multiple performance metrics. The model maintains strong generalization under varying data scales, interference levels, and model depth configurations. The framework developed in this study offers an efficient algorithmic foundation for processing real-world clinical texts and presents practical significance for multi-label medical text modeling tasks.

Learning an Ensemble Token from Task-driven Priors in Facial Analysis

Facial analysis exhibits task-specific feature variations. While Convolutional Neural Networks (CNNs) have enabled the fine-grained representation of spatial information, Vision Transformers (ViTs) have facilitated the representation of semantic information at the patch level. Although the generalization of conventional methodologies has advanced visual interpretability, there remains paucity of research that preserves the unified feature representation on single task learning during the training process. In this work, we introduce ET-Fuser, a novel methodology for learning ensemble token by leveraging attention mechanisms based on task priors derived from pre-trained models for facial analysis. Specifically, we propose a robust prior unification learning method that generates a ensemble token within a self-attention mechanism, which shares the mutual information along the pre-trained encoders. This ensemble token approach offers high efficiency with negligible computational cost. Our results show improvements across a variety of facial analysis, with statistically significant enhancements observed in the feature representations.

SWinMamba: Serpentine Window State Space Model for Vascular Segmentation

Vascular segmentation in medical images is crucial for disease diagnosis and surgical navigation. However, the segmented vascular structure is often discontinuous due to its slender nature and inadequate prior modeling. In this paper, we propose a novel Serpentine Window Mamba (SWinMamba) to achieve accurate vascular segmentation. The proposed SWinMamba innovatively models the continuity of slender vascular structures by incorporating serpentine window sequences into bidirectional state space models. The serpentine window sequences enable efficient feature capturing by adaptively guiding global visual context modeling to the vascular structure. Specifically, the Serpentine Window Tokenizer (SWToken) adaptively splits the input image using overlapping serpentine window sequences, enabling flexible receptive fields (RFs) for vascular structure modeling. The Bidirectional Aggregation Module (BAM) integrates coherent local features in the RFs for vascular continuity representation. In addition, dual-domain learning with Spatial-Frequency Fusion Unit (SFFU) is designed to enhance the feature representation of vascular structure. Extensive experiments on three challenging datasets demonstrate that the proposed SWinMamba achieves superior performance with complete and connected vessels.

Proof of a perfect platonic representation hypothesis

In this note, we elaborate on and explain in detail the proof given by Ziyin et al. (2025) of the "perfect" Platonic Representation Hypothesis (PRH) for the embedded deep linear network model (EDLN). We show that if trained with SGD, two EDLNs with different widths and depths and trained on different data will become Perfectly Platonic, meaning that every possible pair of layers will learn the same representation up to a rotation. Because most of the global minima of the loss function are not Platonic, that SGD only finds the perfectly Platonic solution is rather extraordinary. The proof also suggests at least six ways the PRH can be broken. We also show that in the EDLN model, the emergence of the Platonic representations is due to the same reason as the emergence of progressive sharpening. This implies that these two seemingly unrelated phenomena in deep learning can, surprisingly, have a common cause. Overall, the theory and proof highlight the importance of understanding emergent "entropic forces" due to the irreversibility of SGD training and their role in representation learning. The goal of this note is to be instructive and avoid lengthy technical details.

ShapeEmbed: a self-supervised learning framework for 2D contour quantification

The shape of objects is an important source of visual information in a wide range of applications. One of the core challenges of shape quantification is to ensure that the extracted measurements remain invariant to transformations that preserve an object's intrinsic geometry, such as changing its size, orientation, and position in the image. In this work, we introduce ShapeEmbed, a self-supervised representation learning framework designed to encode the contour of objects in 2D images, represented as a Euclidean distance matrix, into a shape descriptor that is invariant to translation, scaling, rotation, reflection, and point indexing. Our approach overcomes the limitations of traditional shape descriptors while improving upon existing state-of-the-art autoencoder-based approaches. We demonstrate that the descriptors learned by our framework outperform their competitors in shape classification tasks on natural and biological images. We envision our approach to be of particular relevance to biological imaging applications.

LANet: A Lane Boundaries-Aware Approach For Robust Trajectory Prediction

Accurate motion forecasting is critical for safe and efficient autonomous driving, enabling vehicles to predict future trajectories and make informed decisions in complex traffic scenarios. Most of the current designs of motion prediction models are based on the major representation of lane centerlines, which limits their capability to capture critical road environments and traffic rules and constraints. In this work, we propose an enhanced motion forecasting model informed by multiple vector map elements, including lane boundaries and road edges, that facilitates a richer and more complete representation of driving environments. An effective feature fusion strategy is developed to merge information in different vector map components, where the model learns holistic information on road structures and their interactions with agents. Since encoding more information about the road environment increases memory usage and is computationally expensive, we developed an effective pruning mechanism that filters the most relevant map connections to the target agent, ensuring computational efficiency while maintaining essential spatial and semantic relationships for accurate trajectory prediction. Overcoming the limitations of lane centerline-based models, our method provides a more informative and efficient representation of the driving environment and advances the state of the art for autonomous vehicle motion forecasting. We verify our approach with extensive experiments on the Argoverse 2 motion forecasting dataset, where our method maintains competitiveness on AV2 while achieving improved performance. Index Terms-Autonomous driving, trajectory prediction, vector map elements, road topology, connection pruning, Argoverse 2.

TriVLA: A Unified Triple-System-Based Unified Vision-Language-Action Model for General Robot Control

Recent advancements in vision-language models (VLMs) for common-sense reasoning have led to the development of vision-language-action (VLA) models, enabling robots to perform generalized manipulation. Although existing autoregressive VLA methods design a specific architecture like dual-system to leverage large-scale pretrained knowledge, they tend to capture static information, often neglecting the dynamic aspects vital for embodied tasks. To this end, we propose TriVLA, a unified Vision-Language-Action model with a triple-system architecture for general robot control. The vision-language module (System 2) interprets the environment through vision and language instructions. The dynamics perception module (System 3) inherently produces visual representations that encompass both current static information and predicted future dynamics, thereby providing valuable guidance for policy learning. TriVLA utilizes pre-trained VLM model and fine-tunes pre-trained video foundation model on robot datasets along with internet human manipulation data. The subsequent policy learning module (System 1) generates fluid motor actions in real time. Experimental evaluation demonstrates that TriVLA operates at approximately 36 Hz and surpasses state-of-the-art imitation learning baselines on standard simulation benchmarks as well as challenging real-world manipulation tasks.

Distributional Soft Actor-Critic with Diffusion Policy

Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy representations. A multimodal distributional policy iteration framework that can converge to the optimal policy was established by introducing policy entropy and value distribution function. A diffusion value network that can accurately characterize the distribution of multi peaks was constructed by generating a set of reward samples through reverse sampling using a diffusion model. Based on this, a distributional reinforcement learning algorithm with dual diffusion of the value network and the policy network was derived. MuJoCo testing tasks demonstrate that the proposed algorithm not only learns multimodal policy, but also achieves state-of-the-art (SOTA) performance in all 9 control tasks, with significant suppression of estimation bias and total average return improvement of over 10\% compared to existing mainstream algorithms. The results of real vehicle testing show that DSAC-D can accurately characterize the multimodal distribution of different driving styles, and the diffusion policy network can characterize multimodal trajectories.

Surrogate Modeling via Factorization Machine and Ising Model with Enhanced Higher-Order Interaction Learning

Recently, a surrogate model was proposed that employs a factorization machine to approximate the underlying input-output mapping of the original system, with quantum annealing used to optimize the resulting surrogate function. Inspired by this approach, we propose an enhanced surrogate model that incorporates additional slack variables into both the factorization machine and its associated Ising representation thereby unifying what was by design a two-step process into a single, integrated step. During the training phase, the slack variables are iteratively updated, enabling the model to account for higher-order feature interactions. We apply the proposed method to the task of predicting drug combination effects. Experimental results indicate that the introduction of slack variables leads to a notable improvement of performance. Our algorithm offers a promising approach for building efficient surrogate models that exploit potential quantum advantages.

MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement

With the advent of new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform state-of-the-art models in single-channel speech enhancement, automatic speech recognition, and self-supervised audio representation learning. However, prior research has demonstrated that sequence models like LSTM and Mamba tend to overfit to the training set. To address this issue, previous works have shown that adding self-attention to LSTMs substantially improves generalization performance for single-channel speech enhancement. Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement. In this paper, we propose a novel hybrid architecture, MambAttention, which combines Mamba and shared time- and frequency-multi-head attention modules for generalizable single-channel speech enhancement. To train our model, we introduce VoiceBank+Demand Extended (VB-DemandEx), a dataset inspired by VoiceBank+Demand but with more challenging noise types and lower signal-to-noise ratios. Trained on VB-DemandEx, our proposed MambAttention model significantly outperforms existing state-of-the-art LSTM-, xLSTM-, Mamba-, and Conformer-based systems of similar complexity across all reported metrics on two out-of-domain datasets: DNS 2020 and EARS-WHAM_v2, while matching their performance on the in-domain dataset VB-DemandEx. Ablation studies highlight the role of weight sharing between the time- and frequency-multi-head attention modules for generalization performance. Finally, we explore integrating the shared time- and frequency-multi-head attention modules with LSTM and xLSTM, which yields a notable performance improvement on the out-of-domain datasets. However, our MambAttention model remains superior on both out-of-domain datasets across all reported evaluation metrics.