Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

Recently, speech generation models have made significant progress by using large-scale training data. However, the research community struggle to produce highly spontaneous and human-like speech due to the lack of large-scale, diverse, and spontaneous speech data. This paper presents \textit{Emilia}, the first multilingual speech generation dataset from in-the-wild speech data, and Emilia-Pipe, the first open-source preprocessing pipeline designed to transform in-the-wild speech data into high-quality training data with annotations for speech generation. Emilia starts with over 101k hours of speech in six languages and features diverse speech with varied speaking styles. To facilitate the scale-up of Emilia, the open-source pipeline Emilia-Pipe can process one hour of raw speech data ready for model training in a few mins, which enables the research community to collaborate on large-scale speech generation research. Experimental results validate the effectiveness of Emilia. Demos are available at: https://emilia-dataset.github.io/Emilia-Demo-Page/.

A Contrastive Learning Based Convolutional Neural Network for ERP Brain-Computer Interfaces

ERP-based EEG detection is gaining increasing attention in the field of brain-computer interfaces. However, due to the complexity of ERP signal components, their low signal-to-noise ratio, and significant inter-subject variability, cross-subject ERP signal detection has been challenging. The continuous advancement in deep learning has greatly contributed to addressing this issue. This brief proposes a contrastive learning training framework and an Inception module to extract multi-scale temporal and spatial features, representing the subject-invariant components of ERP signals. Specifically, a base encoder integrated with a linear Inception module and a nonlinear projector is used to project the raw data into latent space. By maximizing signal similarity under different targets, the inter-subject EEG signal differences in latent space are minimized. The extracted spatiotemporal features are then used for ERP target detection. The proposed algorithm achieved the best AUC performance in single-trial binary classification tasks on the P300 dataset and showed significant optimization in speller decoding tasks compared to existing algorithms.

WcDT: World-centric Diffusion Transformer for Traffic Scene Generation

In this paper, we introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models (a.k.a., diffusion models) and transformers. Our proposed framework, termed the "World-Centric Diffusion Transformer" (WcDT), optimizes the entire trajectory generation process, from feature extraction to model inference. To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks. Then, the latent features, historical trajectories, HD map features, and historical traffic signal information are fused with various transformer-based encoders. The encoded traffic scenes are then decoded by a trajectory decoder to generate multimodal future trajectories. Comprehensive experimental results show that the proposed approach exhibits superior performance in generating both realistic and diverse trajectories, showing its potential for integration into automatic driving simulation systems.

The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis

Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an important indicator of the current training state for large language models. However, this principle only focuses on the model's compression properties on the training data, resulting in an inconsistency with the ability improvements on the downstream tasks. Some follow-up works attempted to extend the scaling-law to more complex metrics (such as hyperparameters), but still lacked a comprehensive analysis of the dynamic differences among various capabilities during pretraining. To address the aforementioned limitations, this paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. Through this analysis, we confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes, up to 67 billion parameters. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints. This initiative offers valuable resources to the research community and facilitates the verification and exploration of LLM pretraining by open-source researchers. Besides, we provide empirical summaries, including performance comparisons of different models and capabilities, and tuition of key metrics for different training phases. Based on these findings, we provide a more user-friendly strategy for evaluating the optimization state, offering guidance for establishing a stable pretraining process.

Annolid: Annotate, Segment, and Track Anything You Need

Annolid is a deep learning-based software package designed for the segmentation, labeling, and tracking of research targets within video files, focusing primarily on animal behavior analysis. Based on state-of-the-art instance segmentation methods, Annolid now harnesses the Cutie video object segmentation model to achieve resilient, markerless tracking of multiple animals from single annotated frames, even in environments in which they may be partially or entirely concealed by environmental features or by one another. Our integration of Segment Anything and Grounding-DINO strategies additionally enables the automatic masking and segmentation of recognizable animals and objects by text command, removing the need for manual annotation. Annolid's comprehensive approach to object segmentation flexibly accommodates a broad spectrum of behavior analysis applications, enabling the classification of diverse behavioral states such as freezing, digging, pup huddling, and social interactions in addition to the tracking of animals and their body parts.

EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting

Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots. However, existing SLAM (Simultaneous Localization and Mapping) methods often struggle to achieve both complete high-quality surgical field reconstruction and efficient computation, restricting their intraoperative applications among endoscopic surgeries. In this paper, we introduce EndoGSLAM, an efficient SLAM approach for endoscopic surgeries, which integrates streamlined Gaussian representation and differentiable rasterization to facilitate over 100 fps rendering speed during online camera tracking and tissue reconstructing. Extensive experiments show that EndoGSLAM achieves a better trade-off between intraoperative availability and reconstruction quality than traditional or neural SLAM approaches, showing tremendous potential for endoscopic surgeries. The project page is at https://EndoGSLAM.loping151.com

A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation

In online video platforms, reading or writing comments on interesting videos has become an essential part of the video watching experience. However, existing video recommender systems mainly model users' interaction behaviors with videos, lacking consideration of comments in user behavior modeling. In this paper, we propose a novel recommendation approach called LSVCR by leveraging user interaction histories with both videos and comments, so as to jointly conduct personalized video and comment recommendation. Specifically, our approach consists of two key components, namely sequential recommendation (SR) model and supplemental large language model (LLM) recommender. The SR model serves as the primary recommendation backbone (retained in deployment) of our approach, allowing for efficient user preference modeling. Meanwhile, we leverage the LLM recommender as a supplemental component (discarded in deployment) to better capture underlying user preferences from heterogeneous interaction behaviors. In order to integrate the merits of the SR model and the supplemental LLM recommender, we design a twostage training paradigm. The first stage is personalized preference alignment, which aims to align the preference representations from both components, thereby enhancing the semantics of the SR model. The second stage is recommendation-oriented fine-tuning, in which the alignment-enhanced SR model is fine-tuned according to specific objectives. Extensive experiments in both video and comment recommendation tasks demonstrate the effectiveness of LSVCR. Additionally, online A/B testing on the KuaiShou platform verifies the actual benefits brought by our approach. In particular, we achieve a significant overall gain of 4.13% in comment watch time.

From Chaos to Clarity: Time Series Anomaly Detection in Astronomical Observations

With the development of astronomical facilities, large-scale time series data observed by these facilities is being collected. Analyzing anomalies in these astronomical observations is crucial for uncovering potential celestial events and physical phenomena, thus advancing the scientific research process. However, existing time series anomaly detection methods fall short in tackling the unique characteristics of astronomical observations where each star is inherently independent but interfered by random concurrent noise, resulting in a high rate of false alarms. To overcome the challenges, we propose AERO, a novel two-stage framework tailored for unsupervised anomaly detection in astronomical observations. In the first stage, we employ a Transformer-based encoder-decoder architecture to learn the normal temporal patterns on each variate (i.e., star) in alignment with the characteristic of variate independence. In the second stage, we enhance the graph neural network with a window-wise graph structure learning to tackle the occurrence of concurrent noise characterized by spatial and temporal randomness. In this way, AERO is not only capable of distinguishing normal temporal patterns from potential anomalies but also effectively differentiating concurrent noise, thus decreasing the number of false alarms. We conducted extensive experiments on three synthetic datasets and three real-world datasets. The results demonstrate that AERO outperforms the compared baselines. Notably, compared to the state-of-the-art model, AERO improves the F1-score by up to 8.76% and 2.63% on synthetic and real-world datasets respectively.

GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting

Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D information, leading to two significant challenges: 1) Difficulty in building multi-view consistency as images for matching are too few; 2) Partially omitted or highly compressed object information as view coverage is insufficient. To tackle these challenges, we propose GaussianObject, a framework to represent and render the 3D object with Gaussian splatting, that achieves high rendering quality with only 4 input images. We first introduce techniques of visual hull and floater elimination which explicitly inject structure priors into the initial optimization process for helping build multi-view consistency, yielding a coarse 3D Gaussian representation. Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined. We design a self-generating strategy to obtain image pairs for training the repair model. Our GaussianObject is evaluated on several challenging datasets, including MipNeRF360, OmniObject3D, and OpenIllumination, achieving strong reconstruction results from only 4 views and significantly outperforming previous state-of-the-art methods.

EndoGaussian: Gaussian Splatting for Deformable Surgical Scene Reconstruction

Reconstructing deformable tissues from endoscopic stereo videos is essential in many downstream surgical applications. However, existing methods suffer from slow inference speed, which greatly limits their practical use. In this paper, we introduce EndoGaussian, a real-time surgical scene reconstruction framework that builds on 3D Gaussian Splatting. Our framework represents dynamic surgical scenes as canonical Gaussians and a time-dependent deformation field, which predicts Gaussian deformations at novel timestamps. Due to the efficient Gaussian representation and parallel rendering pipeline, our framework significantly accelerates the rendering speed compared to previous methods. In addition, we design the deformation field as the combination of a lightweight encoding voxel and an extremely tiny MLP, allowing for efficient Gaussian tracking with a minor rendering burden. Furthermore, we design a holistic Gaussian initialization method to fully leverage the surface distribution prior, achieved by searching informative points from across the input image sequence. Experiments on public endoscope datasets demonstrate that our method can achieve real-time rendering speed (195 FPS real-time, 100$\times$ gain) while maintaining the state-of-the-art reconstruction quality (35.925 PSNR) and the fastest training speed (within 2 min/scene), showing significant promise for intraoperative surgery applications. Code is available at: \url{https://yifliu3.github.io/EndoGaussian/}.