32 citations · 44 across the 14 of their papers we have counts for
14 papers
AI Infrastructure in Space: How Far Can We Go?
Qing Li, Qiyang Zhang, Daliang Xu +10
Satellites are becoming programmable computing platforms capable of running increasingly demanding AI workloads. This shift raises a systems problem: how can AI services remain dep…
Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization
Xuan Han, Yihao Zhao, Mingyu You
Subject Customization is a foundational task in modern image generation. By providing a few reference images and a text prompt, users can generate images of a specific object in an…
Improving Text-Instance Alignment Of Foreground Conditioned Out-Painting Via Customized Concept Embedding
Yihao Zhao, Xuan Han, Bin He +1
To showcase products, merchants often incur substantial costs creating high-quality display images. Foreground Conditioned Outpainting (FCO) meets this demand, allowing users to cr…
ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning
Bangjun Xiao, Yihao Zhao, Xiangwei Deng +9
Agentic reinforcement learning (RL) has emerged as a transformative workload in cloud clusters, enabling large language models (LLMs) to solve complex problems through interactions…
MiMo-V2-Flash Technical Report
Core Team, Bangjun Xiao, Bingquan Xia +123
We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-…
MiMo-Audio: Audio Language Models are Few-Shot Learners
Core Team, Dong Zhang, Gang Wang +97
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with…
Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology
Yatai Ji, Zhengqiu Zhu, Yong Zhao +7
Aerial Visual Object Search (AVOS) tasks in urban environments require Unmanned Aerial Vehicles (UAVs) to autonomously search for and identify target objects using visual and textu…
SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference
Yihao Zhao, Jiadun Chen, Peng Sun +3
Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due t…
TG-LMM: Enhancing Medical Image Segmentation Accuracy through Text-Guided Large Multi-Modal Model
Yihao Zhao, Enhao Zhong, Cuiyun Yuan +5
We propose TG-LMM (Text-Guided Large Multi-Modal Model), a novel approach that leverages textual descriptions of organs to enhance segmentation accuracy in medical images. Existing…
Quality assurance of organs-at-risk delineation in radiotherapy
Yihao Zhao, Cuiyun Yuan, Ying Liang +6
The delineation of tumor target and organs-at-risk is critical in the radiotherapy treatment planning. Automatic segmentation can be used to reduce the physician workload and impro…
A Survey of Resource-efficient LLM and Multimodal Foundation Models
Mengwei Xu, Wangsong Yin, Dongqi Cai +15
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine lear…
MuxFlow: Efficient and Safe GPU Sharing in Large-Scale Production Deep Learning Clusters
Yihao Zhao, Xin Liu, Shufan Liu +5
Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicat…
Unpaired Image-to-Image Translation using Adversarial Consistency Loss
Yihao Zhao, Ruihai Wu, Hao Dong
Unpaired image-to-image translation is a class of vision problems whose goal is to find the mapping between different image domains using unpaired training data. Cycle-consistency…
DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
Guanqi Zhan, Yihao Zhao, Bingchan Zhao +3
Recent studies have shown how disentangling images into content and feature spaces can provide controllable image translation/ manipulation. In this paper, we propose a framework t…