Author name cluster

Jiacheng Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

OmniScale: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Qianli Ma
Yaowei Zheng
Zhelun Shi
Zhongkai Zhao
Bin Jia
Ziyue Huang
Zhiqi Lin
Youjie Li

Recent advances in large language models (LLMs) have driven impressive progress in omni-modal understanding and generation. However, training omni-modal LLMs remains a significant challenge due to the heterogeneous model architectures required to process diverse modalities, necessitating sophisticated system design for efficient large-scale training. Existing frameworks typically entangle model definition with parallel logic, incurring limited scalability and substantial engineering overhead for end-to-end omni-modal training. We present OmniScale, a modular and efficient training framework to accelerate the development of omni-modal LLMs. OmniScale introduces model-centric distributed recipes that decouples communication from computation, enabling efficient 3D parallelism on omni-modal LLMs. OmniScale also features a flexible configuration interface supporting seamless integration of new modalities with minimal code change. Using OmniScale, a omni-modal mixture-of-experts (MoE) model with 30B parameters can be trained with over 2,800 tokens/sec/GPU throughput and scale to 160K context lengths via 3D parallelism on 128 GPUs, showcasing its superior efficiency and scalability for training large omni-modal LLMs.

PDF Details DOI

JBHI Journal 2026 Journal Article

TriCSART: Semi-Supervised Medical Image Segmentation with Triple-Level Contrastive Learning and Selective Active Re-Training

Shujian Gao
Yuan Wang
Jiacheng Yang
Mengwen Ye
Weifan Liu
Zekuan Yu

Semi-supervised medical image segmentation has garnered significant attention due to challenges of limited medical data accessibility and expensive annotation costs. However, existing studies face two critical challenges: 1) while contrastive learning has demonstrated potential in semi-supervised frameworks, prior implementations lack hierarchical modeling, failing to comprehensively integrate contrastive mechanisms across intra-, inter-, and memorybankdimensions; 2)conventional pseudo-labeling strategies inadequately address quality assessment, potentially propagating annotation biases through continual error accumulation. To address these issues, this paper introduces a Triple-Level Contrastive (TLC) Learning and Selective Active Re-Training (SART) strategy for medical image analysis. The proposed method adopts a teacher–student architecture with two main components: the TLC module and the SART module. The TLC module establishes multilevel semantic consistency across different views through three distinct, complementary loss functions, simultaneously enhancing inter-class discriminability and intra-class compactness. To further mitigate sample quality imbalance, the SART module introduces a metric-driven evaluation mechanism to automatically identify salient samples. Finally, these selected unlabeled samples are integrated with labeled data for re-training guided by calculated curriculum scores. Extensive experiments are conducted on five diverse bench marks, including four public datasets and one private CBCT dataset. The results demonstrate that our approach achieves state-of-the-art performance, consistently outperforming other semi-supervised segmentation strategies. Ablation studies further confirm the efficacy of each proposed component.

Details DOI

ICML Conference 2025 Conference Paper

TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories

Honghua Dong
Jiacheng Yang
Xun Deng
Yuhe Jiang
Gennady Pekhimenko
Fan Long
Xujie Si

Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have shown promise in code understanding, their type inference capabilities remain underexplored. We introduce TypyBench, a benchmark designed to evaluate LLMs’ type inference across entire Python repositories. TypyBench features two novel metrics: TypeSim, which captures nuanced semantic relationships between predicted and ground truth types, and TypeCheck, which assesses type consistency across codebases. Our evaluation of various LLMs on a curated dataset of 50 high-quality Python repositories reveals that, although LLMs achieve decent TypeSim scores, they struggle with complex nested types and exhibit significant type consistency errors. These findings suggest that future research should shift focus from improving type similarity to addressing repository-level consistency. TypyBench provides a foundation for this new direction, offering insights into model performance across different type complexities and usage contexts. Our code and data are available at https: //github. com/typybench/typybench

Details

AAAI Conference 2020 Conference Paper

Towards Making the Most of BERT in Neural Machine Translation

Jiacheng Yang
Mingxuan Wang
Hao Zhou
Chengqi Zhao
Weinan Zhang
Yong Yu
Lei Li

GPT-2 and BERT demonstrate the effectiveness of using pretrained language models (LMs) on various natural language processing tasks. However, LM ﬁne-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In this work, we introduce a concerted training framework (CTNMT) that is the key to integrate the pre-trained LMs to neural machine translation (NMT). Our proposed CTNMT consists of three techniques: a) asymptotic distillation to ensure that the NMT model can retain the previous pre-trained knowledge; b) a dynamic switching gate to avoid catastrophic forgetting of pre-trained knowledge; and c) a strategy to adjust the learning paces according to a scheduled policy. Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pretraining aided NMT by 1. 4 BLEU score. While for the large WMT14 English-French task with 40 millions of sentencepairs, our base model still signiﬁcantly improves upon the state-of-the-art Transformer big model by more than 1 BLEU score.

PDF Details

NeurIPS Conference 2019 Conference Paper

Park: An Open Platform for Learning-Augmented Computer Systems

Hongzi Mao
Parimarjan Negi
Akshay Narayan
Hanrui Wang
Jiacheng Yang
Haonan Wang
Ryan Marcus
ravichandra addanki

We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems. Using RL for improving the performance of systems has a lot of potential, but is also in many ways very different from, for example, using RL for games. Thus, in this work we first discuss the unique challenges RL for systems has, and then propose Park an open extensible platform, which makes it easier for ML researchers to work on systems problems. Currently, Park consists of 12 real world system-centric optimization problems with one common easy to use interface. Finally, we present the performance of existing RL approaches over those 12 problems and outline potential areas of future work.

PDF Details

AAAI Conference 2018 System Paper

MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence

Lianmin Zheng
Jiacheng Yang
Han Cai
Ming Zhou
Weinan Zhang
Jun Wang
Yong Yu

We introduce MAgent, a platform to support research and development of many-agent reinforcement learning. Unlike previous research platforms on single or multi-agent reinforcement learning, MAgent focuses on supporting the tasks and the applications that require hundreds to millions of agents. Within the interactions among a population of agents, it enables not only the study of learning algorithms for agents’ optimal polices, but more importantly, the observation and understanding of individual agent’s behaviors and social phenomena emerging from the AI society, including communication languages, leaderships, altruism. MAgent is highly scalable and can host up to one million agents on a single GPU server. MAgent also provides ﬂexible conﬁgurations for AI researchers to design their customized environments and agents. In this demo, we present three environments designed on MAgent and show emerged collective intelligence by learning from scratch.

PDF Details

ICML Conference 2018 Conference Paper

Path-Level Network Transformation for Efficient Architecture Search

Han Cai
Jiacheng Yang
Weinan Zhang 0001
Song Han 0003
Yong Yu 0001

We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that can only perform layer-level architecture modifications, such as adding (pruning) filters or inserting (removing) a layer, which fails to change the topology of connection paths. Our proposed path-level transformation operations enable the meta-controller to modify the path topology of the given network while keeping the merits of reusing weights, and thus allow efficiently designing effective structures with complex path topologies like Inception models. We further propose a bidirectional tree-structured reinforcement learning meta-controller to explore a simple yet highly expressive tree-structured architecture space that can be viewed as a generalization of multi-branch architectures. We experimented on the image classification datasets with limited computational resources (about 200 GPU-hours), where we observed improved parameter efficiency and better test results (97. 70% test accuracy on CIFAR-10 with 14. 3M parameters and 74. 6% top-1 accuracy on ImageNet in the mobile setting), demonstrating the effectiveness and transferability of our designed architectures.

Details