498 citations · 636 across the 19 of their papers we have counts for
20 papers
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5
Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is…
P^2O: Joint Policy and Prompt Optimization
Xinyu Lu, Kaiqi Zhang, Jinglin Yang +6
Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but is suffer from advantage collapse: when all rollouts of a query receive iden…
Shifting the Sweet Spot: High-Performance Matrix-Free Method for High-Order Elasticity
Dali Chang, Chong Zhang, Kaiqi Zhang +3
MFEM is a widely used finite-element library, but its native linear-elasticity Partial Assembly (PA) path still applies an contraction in the element operator, leaving…
Relative-Absolute Fusion: Rethinking Feature Extraction in Image-Based Iterative Method Selection for Solving Sparse Linear Systems
Kaiqi Zhang, Mingguan Yang, Dali Chang +4
Iterative method selection is crucial for solving sparse linear systems because these methods inherently lack robustness. Though image-based selection approaches have shown promise…
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning
Kaiqi Zhang, Jing Zhao, Rui Chen
Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full…
TALEC: Teach Your LLM to Evaluate in Specific Domain with In-house Criteria by Criteria Division and Zero-shot Plus Few-shot
Kaiqi Zhang, Shuai Yuan, Honghan Zhao
With the rapid development of large language models (LLM), the evaluation of LLM becomes increasingly important. Measuring text generation tasks such as summarization and article c…
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
Dan Qiao, Kaiqi Zhang, Esha Singh +2
We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK)…
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Zixuan Zhang, Kaiqi Zhang, Minshuo Chen +4
Convolutional residual neural networks (ConvResNets), though overparameterized, can achieve remarkable prediction performance in practice, which cannot be well explained by convent…
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
Kaiqi Zhang, Ming Yin, Yu-Xiang Wang
Quantized neural networks have drawn a lot of attention as they reduce the space and computational complexity during the inference. Moreover, there has been folklore that quantizat…
Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?
Kaiqi Zhang, Yu-Xiang Wang
We study the theory of neural network (NN) from the lens of classical nonparametric regression problems with a focus on NN's ability to adaptively estimate functions with heterogen…
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration
Yao Chen, Cole Hawkins, Kaiqi Zhang +2
The deep neural network (DNN) based AI applications on the edge require both low-cost computing platforms and high-quality services. However, the limited memory, computing resource…
On-FPGA Training with Ultra Memory Reduction: A Low-Precision Tensor Method
Kaiqi Zhang, Cole Hawkins, Xiyuan Zhang +2
Various hardware accelerators have been developed for energy-efficient and real-time inference of neural networks on edge devices. However, most training is done on high-performanc…
Sparse Tucker Tensor Decomposition on a Hybrid FPGA-CPU Platform
Weiyun Jiang, Kaiqi Zhang, Colin Yu Lin +2
Recommendation systems, social network analysis, medical imaging, and data mining often involve processing sparse high-dimensional data. Such high-dimensional data are naturally re…
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev +3
Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability an…
Tucker Tensor Decomposition on FPGA
Kaiqi Zhang, Xiyuan Zhang, Zheng Zhang
Tensor computation has emerged as a powerful mathematical tool for solving high-dimensional and/or extreme-scale problems in science and engineering. The last decade has witnessed…
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
Shaokai Ye, Tianyun Zhang, Kaiqi Zhang +6
Many model compression techniques of Deep Neural Networks (DNNs) have been investigated, including weight pruning, weight clustering and quantization, etc. Weight pruning leverages…
Progressive Weight Pruning of Deep Neural Networks using ADMM
Shaokai Ye, Tianyun Zhang, Kaiqi Zhang +10
Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices…
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs
Tianyun Zhang, Shaokai Ye, Kaiqi Zhang +8
Weight pruning methods of DNNs have been demonstrated to achieve a good model pruning rate without loss of accuracy, thereby alleviating the significant computation/storage require…
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
Tianyun Zhang, Shaokai Ye, Kaiqi Zhang +4
Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarante…