12 papers
Intern-S2-Preview: Scientific Agentic Foundation Model
Lei Bai, Jiaqi Cao, Chiyu Chen +121
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sus…
AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
Qitan Lv, Hong Wang, Zhongkai Hao +5
Pre-training neural operators on diverse partial differential equation (PDE) datasets has emerged as a promising direction for building general-purpose surrogate models in scientif…
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, Dongsheng Zhu, Lin Zhu +174
We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancem…
STEP: Scientific Time-Series Encoder Pretraining via Cross-Domain Distillation
Chen Zhang, Liwei Liu, Jun Tao +6
Scientific time series are central to scientific AI but are typically sparse, highly heterogeneous, and limited in scale, making unified representation learning particularly challe…
SemanticVocoder: Bridging Audio Generation and Audio Understanding via Semantic Latents
Zeyu Xie, Chenxing Li, Qiao Jin +6
Recent audio generation models typically rely on Variational Autoencoders (VAEs) and perform generation within the VAE latent space. Although VAEs excel at compression and reconstr…
HoliAntiSpoof: Audio LLM for Holistic Speech Anti-Spoofing
Xuenan Xu, Yiming Ren, Liwei Liu +5
Recent advances in speech synthesis and editing have made speech spoofing increasingly challenging. However, most existing methods treat spoofing as binary classification, overlook…
MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
Ye Tao, Wen Wu, Chao Zhang +3
Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally li…
HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding
Qitan Lv, Tianyu Liu, Wen Wu +4
Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily…
Bayesian Speech Synthesizers Can Learn from Multiple Teachers
Ziyang Zhang, Yifan Gao, Xuenan Xu +3
Text-to-speech (TTS) is a "one-to-many" problem: one text can be spoken in many valid ways, so its realizations form a distribution whose spread depends on the input. Most TTS mode…
SciTS: Scientific Time Series Understanding and Generation with LLMs
Wen Wu, Ziyang Zhang, Liwei Liu +12
The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents u…
Can Audio Large Language Models Verify Speaker Identity?
Yiming Ren, Xuenan Xu, Baoxiang Li +2
This paper investigates adapting Audio Large Language Models (ALLMs) for speaker verification (SV). We reformulate SV as an audio question-answering task and conduct comprehensive…
Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training
Wenbo Li, Guohao Li, Zhibin Lan +5
Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backb…