Publications (16)
DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
Debin Meng, Jiaming Yang, Zefang Zong +4
The paper introduces DataClawEval, a benchmark that tests autonomous LLM agents on end-to-end data engineering tasks across multiple production-grade SQL and Spark engines using de…
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
Tri Dao, Beidi Chen, Kaizhao Liang +4
Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefi…
Task-Oriented Communications for 3D Scene Representation: Balancing Timeliness and Fidelity
Xiangmin Xu, Zhen Meng, Kan Chen +4
Real-time Three-dimensional (3D) scene representation is a foundational element that supports a broad spectrum of cutting-edge applications, including digital manufacturing, Virtua…
Federated Adversarial Learning: A Framework with Convergence Analysis
Xiaoxiao Li, Zhao Song, Jiaming Yang
Federated learning (FL) is a trending training paradigm to utilize decentralized training data. FL allows clients to update model parameters locally for several epochs, then share…
Precision Neural Network Quantization via Learnable Adaptive Modules
Wenqiang Zhou, Zhendong Yu, Xinyu Liu +5
Quantization Aware Training (QAT) is a neural network quantization technique that compresses model size and improves operational efficiency while effectively maintaining model perf…
Do Pathology Vision-Language Models Truly See Pathology?
Chengyang Zhang, Wenchuan Zhang, Bo Li +10
Pathology vision-language models (VLMs) have recently progressed rapidly and are commonly evaluated by answer accuracy on pathology VQA benchmarks. However, we dig into current eva…
Task-Oriented Edge-Assisted Cross-System Design for Real-Time Human-Robot Interaction in Industrial Metaverse
Kan Chen, Zhen Meng, Xiangmin Xu +3
Real-time human-device interaction in industrial Metaverse faces challenges such as high computational load, limited bandwidth, and strict latency. This paper proposes a task-orien…
Scalable Exact Densest P-Partite Subgraph Search in Heterogeneous Information Networks
Jiadong Xie, Jiaming Yang, Kangfei Zhao +1
Heterogeneous information networks (HINs) model typed entities and typed relations, where dense cross-type structures can reveal cohesive semantic patterns such as prolific author-…
Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning
MichaÅ DereziÅski, Christopher Musco, Jiaming Yang
We present a new class of preconditioned iterative methods for solving linear systems of the form . Our methods are based on constructing a low-rank Nyström approximation…
Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
Pratik Rathore, Zachary Frangella, Jiaming Yang +2
Kernel ridge regression (KRR) is a fundamental computational tool, appearing in problems that range from computational chemistry to health analytics, with a particular interest due…
Solving Dense Linear Systems Faster Than via Preconditioning
MichaÅ DereziÅski, Jiaming Yang
We give a stochastic optimization algorithm that solves a dense real-valued linear system , returning such that in time:…
Randomized Kaczmarz Methods with Beyond-Krylov Convergence
MichaÅ DereziÅski, Deanna Needell, Elizaveta Rebrova +1
Randomized Kaczmarz methods form a family of linear system solvers which converge by repeatedly projecting their iterates onto randomly sampled equations. While effective in some c…
HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
Yongyi Yang, Jiaming Yang, Wei Hu +1
As a variant of Graph Neural Networks (GNNs), Unfolded GNNs offer enhanced interpretability and flexibility over traditional designs. Nevertheless, they still suffer from scalabili…
Task-Oriented Edge-Assisted Cooperative Data Compression, Communications and Computing for UGV-Enhanced Warehouse Logistics
Jiaming Yang, Zhen Meng, Xiangmin Xu +3
This paper explores the growing need for task-oriented communications in warehouse logistics, where traditional communication Key Performance Indicators (KPIs)-such as latency, rel…
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
Jinfeng Zhou, Zhuang Chen, Dazhen Wan +14
In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters. Our CharacterGLM is designed for generating Chara…
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
Jiaming Yang, Chenwei Tang, Liangli Zhen +1
Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies…