arXiv subjects

Jiachen Zheng

Publications and source records attributed to Jiachen Zheng.

4 recordsLinked to original sources

arXiv2026

Turbulent infall onto class 0 disks as cause of CAI brief condensation episode in the solar system

Calcium-aluminum-rich inclusions (CAIs) in carbonaceous chondritic meteorites are the oldest relics in the solar system. Notably, their radiogenic age feature a brief (100 kyr) condensation episode. In contrast, the reservoirs of the short-lived isotopes in CAIs, presumably supernovae or asymptotic giant stars, pollutes star-forming regions in giant molecular cloud complexes (GMC) over much longer (Myr) duration. Through a series of numerical simulations, we show here the possibility that, within an extended region (2$\sim$3 AU), nearly all ``pre-solar'' CAI-loaded grains in the infall clouds were sublimated and re-condensed during the early ($ \lesssim 10^5$ yr) infall and formation of class-0 disks. We adopt a set of initial conditions from a previous hydrodynamic simulation of the collapse of GMC and the formation of young stellar clusters. We analyze the evolution of the disk's thermal distribution and dynamical structure resulting from the interaction between circumstellar disks and infalling gas. Our follow-up simulations, with much higher resolution, show significant and rapid changes in the disk orientation and morphology due to the dynamic infall of external streamers. Warps and global spiral density waves commonly appear. They lead to intense dissipation which heats the gas to sufficiently high temperature to sublimate prior-generation CAIs. This solid-to-gas phase transition is followed by subsequent cooling and re-condensation. The CAI contained in the meteorites today could be the relics of the last episode of major infall onto class 0 disks.

astro-ph.EP↗

arXiv2025

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

We introduce Metis, a foundation model for unified speech generation. Unlike previous task-specific or multi-task models, Metis follows a pre-training and fine-tuning paradigm. It is pre-trained on large-scale unlabeled speech data using masked generative modeling and then fine-tuned to adapt to diverse speech generation tasks. Specifically, 1) Metis utilizes two discrete speech representations: SSL tokens derived from speech self-supervised learning (SSL) features, and acoustic tokens directly quantized from waveforms. 2) Metis performs masked generative pre-training on SSL tokens, utilizing 300K hours of diverse speech data, without any additional condition. 3) Through fine-tuning with task-specific conditions, Metis achieves efficient adaptation to various speech generation tasks while supporting multimodal input, even when using limited data and trainable parameters. Experiments demonstrate that Metis can serve as a foundation model for unified speech generation: Metis outperforms state-of-the-art task-specific or multi-task systems across five speech generation tasks, including zero-shot text-to-speech, voice conversion, target speaker extraction, speech enhancement, and lip-to-speech, even with fewer than 20M trainable parameters or 300 times less training data. Audio samples are are available at https://metis-demo.github.io/.

cs.SD↗

arXiv2024

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the mask-and-predict learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. Experiments with 100K hours of in-the-wild speech demonstrate that MaskGCT outperforms the current state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility. Audio samples are available at https://maskgct.github.io/. We release our code and model checkpoints at https://github.com/open-mmlab/Amphion/blob/main/models/tts/maskgct.

cs.SD↗

arXiv2024

On Diffusion Process in SE(3)-invariant Space

Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold. However, due to the non-trivial geometry, we still lack a comprehensive understanding of the diffusion mechanism within such SE(3)-invariant space. This study addresses this gap by mathematically delineating the diffusion mechanism under SE(3)-invariance, via zooming into the interaction behavior between coordinates and the inter-point distance manifold through the lens of differential geometry. Upon this analysis, we propose accurate and projection-free diffusion SDE and ODE accordingly. Such formulations enable enhancing the performance and the speed of generation pathways; meanwhile offering valuable insights into other systems incorporating SE(3)-invariance.

cs.LG↗