Source author record

Chenwei Xu

Chenwei Xu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence Machine Learning Information Retrieval physics.acc-ph

Catalog footprint

What is connected

3works

4topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Attention Sinks and Outliers in Attention Residuals

We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also exacerbate attention sinks, activation outliers, and the resulting degradation in inference stability and quantization robustness. OASIS addresses this issue by introducing a Softmax1-based null space and coupling token-level null evidence to depth routing through an inter-layer null signal, thereby reducing sink-dominated routing and improving structural robustness. Theoretically, we show that the dual-normalization design of AttnResidual intensifies sink formation and quantization brittleness. Experimentally, we compare OASIS against five baselines on three real-world datasets and observe consistent improvements in both attention sink and post-quantization performance. Notably, OASIS achieves an average reduction of 9.26% in maximum infinity norm and 2.60% in average kurtosis across the evaluated settings, while lowering perplexity by 75.85% under W8A8 and improving GSM8K Pass@1 by 12.42% under W4A4.

preprint2023arXiv

Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e

We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron Conversion Experiment (Mu2e) at Fermi National Accelerator Laboratory (Fermilab). Our primary objective is to regulate the spill process to ensure a consistent intensity profile, with the ultimate goal of creating an automated controller capable of providing real-time feedback and calibration of the Spill Regulation System (SRS) parameters on a millisecond timescale. We treat the Mu2e accelerator system as a Markov Decision Process suitable for Reinforcement Learning (RL), utilizing PPO to reduce bias and enhance training stability. A key innovation in our approach is the integration of a neuralized Proportional-Integral-Derivative (PID) controller into the policy function, resulting in a significant improvement in the Spill Duty Factor (SDF) by 13.6%, surpassing the performance of the current PID controller baseline by an additional 1.6%. This paper presents the preliminary offline results based on a differentiable simulator of the Mu2e accelerator. It paves the groundwork for real-time implementations and applications, representing a crucial step towards automated proton beam intensity control for the Mu2e experiment.

preprint2022arXiv

Person-job fit estimation from candidate profile and related recruitment history with co-attention neural networks

Existing online recruitment platforms depend on automatic ways of conducting the person-job fit, whose goal is matching appropriate job seekers with job positions. Intuitively, the previous successful recruitment records contain important information, which should be helpful for the current person-job fit. Existing studies on person-job fit, however, mainly focus on calculating the similarity between the candidate resumes and the job postings on the basis of their contents, without taking the recruiters' experience (i.e., historical successful recruitment records) into consideration. In this paper, we propose a novel neural network approach for person-job fit, which estimates person-job fit from candidate profile and related recruitment history with co-attention neural networks (named PJFCANN). Specifically, given a target resume-job post pair, PJFCANN generates local semantic representations through co-attention neural networks and global experience representations via graph neural networks. The final matching degree is calculated by combining these two representations. In this way, the historical successful recruitment records are introduced to enrich the features of resumes and job postings and strengthen the current matching process. Extensive experiments conducted on a large-scale recruitment dataset verify the effectiveness of PJFCANN compared with several state-of-the-art baselines. The codes are released at: https://github.com/CCIIPLab/PJFCANN.