The establishment of static digital humans and the integration with spinal models

Adolescent idiopathic scoliosis (AIS), a prevalent spinal deformity, significantly affects individuals' health and quality of life. Conventional imaging techniques, such as X - rays, computed tomography (CT), and magnetic resonance imaging (MRI), offer static views of the spine. However, they are restricted in capturing the dynamic changes of the spine and its interactions with overall body motion. Therefore, developing new techniques to address these limitations has become extremely important. Dynamic digital human modeling represents a major breakthrough in digital medicine. It enables a three - dimensional (3D) view of the spine as it changes during daily activities, assisting clinicians in detecting deformities that might be missed in static imaging. Although dynamic modeling holds great potential, constructing an accurate static digital human model is a crucial initial step for high - precision simulations. In this study, our focus is on constructing an accurate static digital human model integrating the spine, which is vital for subsequent dynamic digital human research on AIS. First, we generate human point - cloud data by combining the 3D Gaussian method with the Skinned Multi - Person Linear (SMPL) model from the patient's multi - view images. Then, we fit a standard skeletal model to the generated human model. Next, we align the real spine model reconstructed from CT images with the standard skeletal model. We validated the resulting personalized spine model using X - ray data from six AIS patients, with Cobb angles (used to measure the severity of scoliosis) as evaluation metrics. The results indicate that the model's error was within 1 degree of the actual measurements. This study presents an important method for constructing digital humans.

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Diffusion Transformer Autoregressive Modeling (DiTAR), a patch-based autoregressive framework combining a language model with a diffusion transformer. This approach significantly enhances the efficacy of autoregressive models for continuous tokens and reduces computational demands. DiTAR utilizes a divide-and-conquer strategy for patch generation, where the language model processes aggregated patch embeddings and the diffusion transformer subsequently generates the next patch based on the output of the language model. For inference, we propose defining temperature as the time point of introducing noise during the reverse diffusion ODE to balance diversity and determinism. We also show in the extensive scaling analysis that DiTAR has superb scalability. In zero-shot speech generation, DiTAR achieves state-of-the-art performance in robustness, speaker similarity, and naturalness.

Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

Triangle meshes are fundamental to 3D applications, enabling efficient modification and rasterization while maintaining compatibility with standard rendering pipelines. However, current automatic mesh generation methods typically rely on intermediate representations that lack the continuous surface quality inherent to meshes. Converting these representations into meshes produces dense, suboptimal outputs. Although recent autoregressive approaches demonstrate promise in directly modeling mesh vertices and faces, they are constrained by the limitation in face count, scalability, and structural fidelity. To address these challenges, we propose Nautilus, a locality-aware autoencoder for artist-like mesh generation that leverages the local properties of manifold meshes to achieve structural fidelity and efficient representation. Our approach introduces a novel tokenization algorithm that preserves face proximity relationships and compresses sequence length through locally shared vertices and edges, enabling the generation of meshes with an unprecedented scale of up to 5,000 faces. Furthermore, we develop a Dual-stream Point Conditioner that provides multi-scale geometric guidance, ensuring global consistency and local structural fidelity by capturing fine-grained geometric features. Extensive experiments demonstrate that Nautilus significantly outperforms state-of-the-art methods in both fidelity and scalability. The project page will be released to https://nautilusmeshgen.github.io.

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

LongViTU: Instruction Tuning for Long-Form Video Understanding

This paper introduce LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We developed a systematic approach that organizes videos into a hierarchical tree structure and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.); and 3) explicit timestamp labels for relevant events. LongViTU also serves as a benchmark for instruction following in long-form and streaming video understanding. We evaluate the open-source state-of-the-art long video understanding model, LongVU, and the commercial model, Gemini-1.5-Pro, on our benchmark. They achieve GPT-4 scores of 49.9 and 52.3, respectively, underscoring the substantial challenge posed by our benchmark. Further supervised fine-tuning (SFT) on LongVU led to performance improvements of 12.0% on our benchmark, 2.2% on the in-distribution (ID) benchmark EgoSchema, 1.0%, 2.2% and 1.2% on the out-of-distribution (OOD) benchmarks VideoMME (Long), WorldQA and OpenEQA, respectively. These outcomes demonstrate LongViTU's high data quality and robust OOD generalizability.

Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding

Multi-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used applications. Compared with the traditional multi-modal conversations, MMC requires stronger character-centered understanding abilities as there are many interlocutors appearing in both the visual and textual context. To facilitate the study of this problem, we present Friends-MMC in this paper, an MMC dataset that contains 24,000+ unique utterances paired with video context. To explore the character-centered understanding of the dialogue, we also annotate the speaker of each utterance, the names and bounding bboxes of faces that appear in the video. Based on this Friends-MMC dataset, we further study two fundamental MMC tasks: conversation speaker identification and conversation response prediction, both of which have the multi-party nature with the video or image as visual context. For conversation speaker identification, we demonstrate the inefficiencies of existing methods such as pre-trained models, and propose a simple yet effective baseline method that leverages an optimization solver to utilize the context of two modalities to achieve better performance. For conversation response prediction, we fine-tune generative dialogue models on Friend-MMC, and analyze the benefits of speaker information. The code and dataset is publicly available at https://github.com/yellow-binary-tree/Friends-MMC and thus we call for more attention on modeling speaker information when understanding conversations.

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

Pushing Rendering Boundaries: Hard Gaussian Splatting

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to reduce rendering loss. However, this average operation smooths the positional gradients from different viewpoints and rendering errors from different pixels, hindering the growth and optimization of many defective Gaussians. This leads to strong spurious artifacts in some areas. To address this problem, we propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians that fill the gaps of classical Gaussian Splatting on 3D scenes, thus achieving superior NVS results. In detail, we present positional gradient driven HGS, which leverages multi-view significant positional gradients to uncover hard Gaussians. Moreover, we propose rendering error guided HGS, which identifies noticeable pixel rendering errors and potentially over-large Gaussians to jointly mine hard Gaussians. By growing and optimizing these hard Gaussians, our method helps to resolve blurring and needle-like artifacts. Experiments on various datasets demonstrate that our method achieves state-of-the-art rendering quality while maintaining real-time efficiency.

SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation

Full-duplex multimodal large language models (LLMs) provide a unified framework for addressing diverse speech understanding and generation tasks, enabling more natural and seamless human-machine conversations. Unlike traditional modularised conversational AI systems, which separate speech recognition, understanding, and text-to-speech generation into distinct components, multimodal LLMs operate as single end-to-end models. This streamlined design eliminates error propagation across components and fully leverages the rich non-verbal information embedded in input speech signals. We introduce SALMONN-omni, a codec-free, full-duplex speech understanding and generation model capable of simultaneously listening to its own generated speech and background sounds while speaking. To support this capability, we propose a novel duplex spoken dialogue framework incorporating a ``thinking'' mechanism that facilitates asynchronous text and speech generation relying on embeddings instead of codecs (quantized speech and audio tokens). Experimental results demonstrate SALMONN-omni's versatility across a broad range of streaming speech tasks, including speech recognition, speech enhancement, and spoken question answering. Additionally, SALMONN-omni excels at managing turn-taking, barge-in, and echo cancellation scenarios, establishing its potential as a robust prototype for full-duplex conversational AI systems. To the best of our knowledge, SALMONN-omni is the first codec-free model of its kind. A full technical report along with model checkpoints will be released soon.

Edge-Assisted Accelerated Cooperative Sensing for CAVs: Task Placement and Resource Allocation

In this paper, we propose a novel road side unit (RSU)-assisted cooperative sensing scheme for connected autonomous vehicles (CAVs), with the objective to reduce completion time of sensing tasks. Specifically, LiDAR sensing data of both RSU and CAVs are selectively fused to improve sensing accuracy, and computing resources therein are cooperatively utilized to process tasks in real time. To this end, for each task, we decide whether to compute it at the CAV or at the RSU and allocate resources accordingly. We first formulate a joint task placement and resource allocation problem for minimizing the total task completion time while satisfying sensing accuracy constraint. We then decouple the problem into two subproblems and propose a two-layer algorithm to solve them. The outer layer first makes task placement decision based on the Gibbs sampling theory, while the inner layer makes spectrum and computing resource allocation decisions via greedy-based and convex optimization subroutines, respectively. Simulation results based on the autonomous driving simulator CARLA demonstrate the effectiveness of the proposed scheme in reducing total task completion time, comparing to benchmark schemes.