MOSS-TTS Technical Report

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal pattern capture capabilities, they also incur inherent inconsistencies that severely compromise representation. In this paper, we perform dual consistency optimization via Stable Spike to mitigate this problem, thereby improving the recognition performance of SNNs. With the hardware-friendly ``AND" bit operation, we efficiently decouple the stable spike skeleton from the multi-timestep spike maps, thereby capturing critical semantics while reducing inconsistencies from variable noise spikes. Enforcing the unstable spike maps to converge to the stable spike skeleton significantly improves the inherent consistency across timesteps. Furthermore, we inject amplitude-aware spike noise into the stable spike skeleton to diversify the representations while preserving consistent semantics. The SNN is encouraged to produce perturbation-consistent predictions, thereby contributing to generalization. Extensive experiments across multiple architectures and datasets validate the effectiveness and versatility of our method. In particular, our method significantly advances neuromorphic object recognition under ultra-low latency, improving accuracy by up to 8.33\%. This will help unlock the full power consumption and speed potential of SNNs.

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates, creating a fundamental bottleneck. We present MOSS-Speech, a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance. Our approach combines a modality-based layer-splitting architecture with a frozen pre-training strategy, preserving the reasoning and knowledge of pretrained text LLMs while adding native speech capabilities. Experiments show that our model achieves state-of-the-art results in spoken question answering and delivers comparable speech-to-speech performance relative to existing text-guided systems, while still maintaining competitive text performance. By narrowing the gap between text-guided and direct speech generation, our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.

SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data

Poor sitting posture is a critical yet often overlooked factor contributing to long-term musculoskeletal disorders and physiological dysfunctions. Existing sitting posture monitoring systems, although leveraging visual, IMU, or pressure-based modalities, often suffer from coarse-grained recognition and lack the semantic expressiveness necessary for personalized feedback. In this paper, we propose \textbf{SitLLM}, a lightweight multimodal framework that integrates flexible pressure sensing with large language models (LLMs) to enable fine-grained posture understanding and personalized health-oriented response generation. SitLLM comprises three key components: (1) a \textit{Gaussian-Robust Sensor Embedding Module} that partitions pressure maps into spatial patches and injects local noise perturbations for robust feature extraction; (2) a \textit{Prompt-Driven Cross-Modal Alignment Module} that reprograms sensor embeddings into the LLM's semantic space via multi-head cross-attention using the pre-trained vocabulary embeddings; and (3) a \textit{Multi-Context Prompt Module} that fuses feature-level, structure-level, statistical-level, and semantic-level contextual information to guide instruction comprehension.

Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction

Spatial proteomics maps protein distributions in tissues, providing transformative insights for life sciences. However, current sequencing-based technologies suffer from low spatial resolution, and substantial inter-tissue variability in protein expression further compromises the performance of existing molecular data prediction methods. In this work, we introduce the novel task of spatial super-resolution for sequencing-based spatial proteomics (seq-SP) and, to the best of our knowledge, propose the first deep learning model for this task--Neural Proteomics Fields (NPF). NPF formulates seq-SP as a protein reconstruction problem in continuous space by training a dedicated network for each tissue. The model comprises a Spatial Modeling Module, which learns tissue-specific protein spatial distributions, and a Morphology Modeling Module, which extracts tissue-specific morphological features. Furthermore, to facilitate rigorous evaluation, we establish an open-source benchmark dataset, Pseudo-Visium SP, for this task. Experimental results demonstrate that NPF achieves state-of-the-art performance with fewer learnable parameters, underscoring its potential for advancing spatial proteomics research. Our code and dataset are publicly available at https://github.com/Bokai-Zhao/NPF.

Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images

Foundation models have demonstrated remarkable potential in medical domain. However, their application to complex cardiovascular diagnostics remains underexplored. In this paper, we present Cardiac-CLIP, a multi-modal foundation model designed for 3D cardiac CT images. Cardiac-CLIP is developed through a two-stage pre-training strategy. The first stage employs a 3D masked autoencoder (MAE) to perform self-supervised representation learning from large-scale unlabeled volumetric data, enabling the visual encoder to capture rich anatomical and contextual features. In the second stage, contrastive learning is introduced to align visual and textual representations, facilitating cross-modal understanding. To support the pre-training, we collect 16641 real clinical CT scans, supplemented by 114k publicly available data. Meanwhile, we standardize free-text radiology reports into unified templates and construct the pathology vectors according to diagnostic attributes, based on which the soft-label matrix is generated to supervise the contrastive learning process. On the other hand, to comprehensively evaluate the effectiveness of Cardiac-CLIP, we collect 6,722 real-clinical data from 12 independent institutions, along with the open-source data to construct the evaluation dataset. Specifically, Cardiac-CLIP is comprehensively evaluated across multiple tasks, including cardiovascular abnormality classification, information retrieval and clinical analysis. Experimental results demonstrate that Cardiac-CLIP achieves state-of-the-art performance across various downstream tasks in both internal and external data. Particularly, Cardiac-CLIP exhibits great effectiveness in supporting complex clinical tasks such as the prospective prediction of acute coronary syndrome, which is notoriously difficult in real-world scenarios.

MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network

Medical image segmentation methods generally assume that the process from medical image to segmentation is unbiased, and use neural networks to establish conditional probability models to complete the segmentation task. This assumption does not consider confusion factors, which can affect medical images, such as complex anatomical variations and imaging modality limitations. Confusion factors obfuscate the relevance and causality of medical image segmentation, leading to unsatisfactory segmentation results. To address this issue, we propose a multi-causal aware modeling backdoor-intervention optimization (MAMBO-NET) network for medical image segmentation. Drawing insights from causal inference, MAMBO-NET utilizes self-modeling with multi-Gaussian distributions to fit the confusion factors and introduce causal intervention into the segmentation process. Moreover, we design appropriate posterior probability constraints to effectively train the distributions of confusion factors. For the distributions to effectively guide the segmentation and mitigate and eliminate the Impact of confusion factors on the segmentation, we introduce classical backdoor intervention techniques and analyze their feasibility in the segmentation task. To evaluate the effectiveness of our approach, we conducted extensive experiments on five medical image datasets. The results demonstrate that our method significantly reduces the influence of confusion factors, leading to enhanced segmentation accuracy.

CP-UNet: Contour-based Probabilistic Model for Medical Ultrasound Images Segmentation

Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, which guides the segmentation network to enhance its focus on contour during decoding. We design a novel down-sampling module to enable the contour probability distribution modeling and encoding stages to acquire global-local features. Furthermore, the Gaussian Mixture Model utilizes optimized features to model the contour distribution, capturing the uncertainty of lesion boundaries. Extensive experiments with several state-of-the-art deep learning segmentation methods on three ultrasound image datasets show that our method performs better on breast and thyroid lesions segmentation.