BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Jin Zhu

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

ResearcherUnclaimed source record
hep-exhep-phMachine LearningArtificial IntelligenceComputation and LanguageComputer Visioneess.IVmath.STMethodology

Catalog footprint

What is connected

6works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

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.

Published work

6 published item(s)

preprint2026arXiv

Perturbation is All You Need for Extrapolating Language Models

We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we propose a perturbation-based procedure that first transforms the prefix into a semantic neighbor and then conditions on this perturbed variant for next-token prediction. This yields a hierarchical model with a pre-post-additive noise structure. Within this framework, we develop a rigorous theory of extrapolability, namely, the capacity of a model class to make reliable predictions for token sequences that lie outside the empirical support of the training corpus. We evaluate the finite-sample performance of the proposed procedure using both synthetic and real-world language data. Results show that the proposed method consistently improves out-of-support prediction while maintaining competitive in-support performance, demonstrating that perturbation offers a practical route to language modeling.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Segmenting Human-LLM Co-authored Text via Change Point Detection

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an entire passage; however, this is insufficient for human--LLM co-authored text, where the objective is to localize specific segments authored by humans or LLMs. To bridge this gap, we propose algorithms to segment text into human- and LLM-authored pieces. Our key observation is that such a segmentation task is conceptually similar to classical change point detection in time-series analysis. Leveraging this analogy, we adapt change point detection to LLM-generated text detection, develop a weighted algorithm and a generalized algorithm to accommodate heterogeneous detection score variability, and establish the minimax optimality of our procedure. Empirically, we demonstrate the strong performance of our approach against a wide range of existing baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Arbitrary Scale Super-Resolution for Brain MRI Images

Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves high storage and energy costs as every integer scale factor involves a separate neural network. A recent paper has proposed a novel meta-learning technique that uses a Weight Prediction Network to enable Super-Resolution on arbitrary scale factors using only a single neural network. In this paper, we propose a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images. By using this network to perform arbitrary scale magnifications on images from the Multimodal Brain Tumor Segmentation Challenge (BraTS) dataset, we demonstrate that it is able to outperform traditional interpolation methods by up to 20$\%$ on SSIM scores whilst retaining generalisability on brain MRI images. We show that performance across scales is not compromised, and that it is able to achieve competitive results with other state-of-the-art methods such as EDSR whilst being fifty times smaller than them. Combining efficiency, performance, and generalisability, this can hopefully become a new foundation for tackling Super-Resolution on medical images. Check out the webapp here: https://metasrgan.herokuapp.com/ Check out the github tutorial here: https://github.com/pancakewaffles/metasrgan-tutorial

0 citations0 reviewsNo code linkedOpen access
preprint2006arXiv

Study of $B\to K^* ρ, K^*ω$ Decays with Polarization in Perturbative QCD Approach

The $B \to K^{*}ρ$, $ K^{*}ω$ decays are useful to determine the CKM angle $ϕ_3=γ$. Their polarization fractions are also interesting since the polarization puzzle of the $B\to ϕK^*$ decay. We study these decays in the perturbative QCD approach based on $k_T$ factorization. After calculating of the non-factorizable and annihilation type contributions, in addition to the conventional factorizable contributions, we find that the contributions from the annihilation diagrams are crucial. They give dominant contribution to the strong phases and suppress the longitudinal polarizations. Our results agree with the current existing data. We also predict a sizable direct CP asymmetries in $B^+ \to K^{*+}ρ^0$, $B^0 \to K^{*+}ρ^-$, and $B^+ \to K^{*+}ω$ decays, which can be tested by the oncoming measurements in the B factory experiments.

0 citations0 reviewsNo code linkedOpen access
preprint2005arXiv

$B^0 \to ϕϕ$ Decay in Perturbative QCD Approach

The rare decay $B^0 \to ϕϕ$ can occur only via penguin annihilation topology in the standard model. We calculate this channel in the perturbative QCD approach. The predicted branching ratio is very small at ($10^{-8}$). We also give the polarization fractions, which shows that the transverse polarization contribution is comparable to the longitudinal one, due to a big transverse contribution from factorizable diagrams. The small branching ratio in SM, makes it sensitive to any new physics contributions.

0 citations0 reviewsNo code linkedOpen access
preprint2005arXiv

B_s \to ρ(ω) K^* with Perturbative QCD approach

$B_s \to ρ(ω) K^{\ast}$ are useful to determine the $B_s$ distribution amplitude, as well as constrain the CKM phase angle $α$. We study these decays within the Perturbative QCD (PQCD) picture. In this approach, we calculate factorizable, non-factorizable, as well as annihilation diagrams. We find the branching ratio for $B_s \to ρ^+ K^{*-}$ is big to order $10^{-5}$, we also find there's large direct CP violation in $B_s(\bar B_s) \to ρ^0(ω) \bar K^{*0}(K^{*0})$. Our predictions are consistent with those from other methods and current experiments.

0 citations0 reviewsNo code linkedOpen access