BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Junjie Zhang

Junjie Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
cond-mat.str-elMachine Learningcond-mat.mtrl-scicond-mat.supr-conComputer VisionDistributed, Parallel, and Cluster Computingeess.SPNetworking and Internet ArchitectureRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
9topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

12 published item(s)

preprint2026arXiv

BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training

Modern Large Foundation Model (LFM) training has transformed the data pipeline from a static ingestion layer into a dynamic component that must co-evolve with the training process. Existing systems are ill-equipped: colocated dataloaders offer no failure isolation, while message queue-based disaggregated dataloaders operate on a record/offset abstraction that cannot express the batch-level semantics required by distributed training. We present BatchWeave, an object-store-native training data plane for distributed LFM training. BatchWeave uses versioned manifests and conditional object writes to coordinate batch publication, recovery, and lifecycle management. First, it introduces the Transactional Global Batch (TGB), which builds on versioned-manifest ACID storage semantics and extends them with training-specific consistency, including atomic all-rank batch visibility, a globally ordered step sequence, checkpoint-aligned lifecycle management, and end-to-end exactly-once recovery. Second, it realizes recovery and retention directly in the storage layer, by durably persisting producer state through the commit protocol and tying reclamation to distributed checkpoint state. Third, its Decentralized Adaptive Commit (DAC) algorithm sustains stable ingestion throughput as the manifest grows, without any inter-producer communication. Evaluations on large-scale multimodal pre-training and SFT workloads using 64 GPUs show that BatchWeave outperforms colocated dataloader throughput while providing full failure isolation, outperforms Apache Kafka in ingestion throughput, and achieves lower consumer read latency than Kafka.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Observation of correlated plasmons in low-valence nickelates

The discovery of nickelate superconductors has opened a new arena for studying the behavior of correlated electron liquids that give rise to unconventional superconductivity. While critical information about a material's charge dynamics is encoded in its plasmons, collective modes of the electron gas, these excitations have not yet been observed in nickelate materials. Here, we use resonant inelastic x-ray scattering (RIXS) to detect plasmons in the metallic, low-valence nickelate Pr4Ni3O8. Although qualitatively similar to those in cuprates, the nickelate plasmons are more heavily damped and have a lower velocity than those in a cuprate at comparable doping, which we attribute to reduced electronic hopping and enhanced screening of the long-range Coulomb interactions. Furthermore, the plasmons in Pr4Ni3O8 soften with increasing temperature, in contrast to the cuprate, where plasmons remain at nearly fixed energy but become more strongly damped. Taken together, these results reveal a distinct charge-screening landscape in nickelates and place quantitative constraints on analogies to cuprates.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain coverage, while scalar scores further impose an information bottleneck, offering insufficient semantic bandwidth to improve intermediate decisions. Alternative language-critique approaches, which rely on frozen or external critics, provide richer textual feedback but lack the scalability needed for sustained policy improvement. In this work, we propose language-driven stepwise trajectory redirection, termed as STRIDE, a novel training framework that shifts process supervision from scalar rewards to learnable stepwise language feedback. Specifically, we co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations, while delivering sustained policy improvement through jointly aligned verifier training. The verifier's stepwise language critiques explicitly localize and explain failures, enabling the generator to redirect reasoning trajectories at intermediate steps toward alternative decisions. The trajectory redirection design guarantees harmless policy improvement, even under noisy or suboptimal verifier feedback. Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines, as well as achieving breakthroughs on zero-pass-rate problems where scalar methods yield no learning signal in our ablation studies, demonstrating the effectiveness of learnable stepwise language feedback for enhancing LLM reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Centimeter-level Positioning by Instantaneous Lidar-aided GNSS Ambiguity Resolution

High-precision vehicle positioning is key to the implementation of modern driving systems in urban environments. Global Navigation Satellite System (GNSS) carrier phase measurements can provide millimeter- to centimeter-level positioning, provided that the integer ambiguities are correctly resolved. Abundant code measurements are often used to facilitate integer ambiguity resolution (IAR), however, they suffer from signal blockage and multipath in urban canyons. In this contribution, a lidar-aided instantaneous ambiguity resolution method is proposed. Lidar measurements, in the form of 3D keypoints, are generated by a learning-based point cloud registration method using a pre-built HD map and integrated with GNSS observations in a mixed measurement model to produce precise float solutions, which in turn increase the ambiguity success rate. Closed-form expressions of the ambiguity variance matrix and the associated Ambiguity Dilution of Precision (ADOP) are developed to provide a priori evaluation of such lidar-aided ambiguity resolution performance. Both analytical and experimental results show that the proposed method enables successful instantaneous IAR with limited GNSS satellites and frequencies, leading to centimeter-level vehicle positioning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Electronic structure and correlations in planar trilayer nickelate Pr4Ni3O8

The recent discovery of superconductivity in hole-doped planar nickelates R1-xSrNiO2 (R=Pr,Nd) raises the foundational question of how the electronic structure and electronic correlations of these Ni1+ compounds compare to those of the Cu2+ cuprate superconductors. Here, we present an Angle-Resolved Photoemission Spectroscopy (ARPES) study of the trilayer nickelate Pr4Ni3O8, revealing an electronic structure and Fermi surface very similar to that of the hole-doped cuprates but with a few critical differences. Specifically, the main portions of the Fermi surface are extremely similar to that of the bilayer cuprates, with an additional piece that can accommodate additional hole doping. We find that the electronic correlations are about twice as strong in the nickelates and are almost k-independent, indicating that they originate from a local effect-likely the Mott interaction, whereas the cuprate interactions are somewhat less local. Nevertheless, the nickelates still demonstrate an approximately linear in energy and linear in temperature scattering rate. Understanding the similarities and differences between these two related families of strongly-correlated novel superconductors is an important challenge.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Strong Superexchange in a $d^{9-δ}$ Nickelate Revealed by Resonant Inelastic X-Ray Scattering

The discovery of superconductivity in a $d^{9-δ}$ nickelate has inspired disparate theoretical perspectives regarding the essential physics of this class of materials. A key issue is the magnitude of the magnetic superexchange, which relates to whether cuprate-like high-temperature nickelate superconductivity could be realized. We address this question using Ni L-edge and O K-edge spectroscopy of the reduced trilayer nickelate $d^{9-1/3}$ La4Ni3O8 and associated theoretical modeling. A magnon energy scale of ~80 meV resulting from a nearest-neighbor magnetic exchange of $J = 69(4)4$ meV is observed, proving that $d^{9-δ}$ nickelates can host a large superexchange. This value, along with that of the Ni-O hybridization estimated from our O K-edge data, implies that trilayer nickelates represent an intermediate case between the infinite-layer nickelates and the cuprates, and suggests that they represent a promising route towards higher-temperature nickelate superconductivity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

CFR-RL: Traffic Engineering with Reinforcement Learning in SDN

Traditional Traffic Engineering (TE) solutions can achieve the optimal or near-optimal performance by rerouting as many flows as possible. However, they do not usually consider the negative impact, such as packet out of order, when frequently rerouting flows in the network. To mitigate the impact of network disturbance, one promising TE solution is forwarding the majority of traffic flows using Equal-Cost Multi-Path (ECMP) and selectively rerouting a few critical flows using Software-Defined Networking (SDN) to balance link utilization of the network. However, critical flow rerouting is not trivial because the solution space for critical flow selection is enormous. Moreover, it is impossible to design a heuristic algorithm for this problem based on fixed and simple rules, since rule-based heuristics are unable to adapt to the changes of the traffic matrix and network dynamics. In this paper, we propose CFR-RL (Critical Flow Rerouting-Reinforcement Learning), a Reinforcement Learning-based scheme that learns a policy to select critical flows for each given traffic matrix automatically. CFR-RL then reroutes these selected critical flows to balance link utilization of the network by formulating and solving a simple Linear Programming (LP) problem. Extensive evaluations show that CFR-RL achieves near-optimal performance by rerouting only 10%-21.3% of total traffic.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DSP: A Differential Spatial Prediction Scheme for Comprehensive real industrial datasets

Inverse Distance Weighted models (IDW) have been widely used for predicting and modeling multidimensional space in multimodal industrial processes. However, the more complex the structure of multidimensional space, the lower the performance of IDW models, and real industrial datasets tend to have more complex spatial structure. To solve this problem, a new framework for spatial prediction and modeling based on deep reinforcement learning network is proposed. In the proposed framework, the internal relationship between state and action is enhanced by reusing the state values in the Q network, and the convergence rate and stability of the deep reinforcement learning network are improved. The improved deep reinforcement learning network is then used to search for and learn the hyperparameters of each sample point in the inverse distance weighted model. These hyperparameters can reflect the spatial structure of the current industrial dataset to some extent. Then a spatial distribution of hyperparameters is constructed based on the learned hyperparameters. Each interpolation point obtains corresponding hyperparameters from the hyperparametric spatial distribution and brings them into the classical IDW models for prediction, thus achieving differential spatial prediction and modeling. The simulation results show that the proposed framework is suitable for real industrial datasets with complex spatial structure characteristics and is more accurate than current IDW models in spatial prediction.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

High oxygen pressure floating zone growth and crystal structure of the layered nickelates R$_4$Ni$_3$O$_{10}$ (R=La, Pr)

Single crystals of the metallic Ruddlesden-Popper trilayer nickelates R$_4$Ni$_3$O$_{10}$ (R=La, Pr) were successfully grown using an optical-image floating zone furnace under oxygen pressure (pO$_2$) of 20 bar for La$_4$Ni$_3$O$_{10}$ and 140 bar for Pr$_4$Ni$_3$O$_{10}$. A combination of synchrotron and laboratory x-ray single crystal diffraction, high-resolution synchrotron x-ray powder diffraction and measurements of physical properties revealed that R$_4$Ni$_3$O$_{10}$ (R=La, Pr) crystallizes in the monoclinic $P$2$_1$/$a$ (Z=2) space group at room temperature, and that a metastable orthorhombic phase ($Bmab$) can be trapped by post-growth rapid cooling. Both La$_4$Ni$_3$O$_{10}$ and Pr$_4$Ni$_3$O$_{10}$ crystals undergo a metal-to-metal transition (MMT) below room temperature. In the case of Pr$_4$Ni$_3$O$_{10}$, the MMT is found at ~157.6 K. For La$_4$Ni$_3$O$_{10}$, the MMT depends on the lattice symmetry: 147.5 K for $Bmab$ vs. 138.6 K for $P$2$_1$/$a$. Lattice anomalies were found at the MMT that, when considered together with the pronounced dependence of the transition temperature on subtle structural differences between $Bmab$ and $P$2$_1$/$a$ phases, demonstrates a not insignificant coupling between electronic and lattice degrees of freedom in these trilayer nickelates.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Spin dynamics and a nearly continuous magnetic phase transition in an entropy-stabilized oxide antiferromagnet

The magnetic order and the spin dynamics in the antiferromagnetic entropy-stabilized oxide (Mg$_{0.2}$Co$_{0.2}$Ni$_{0.2}$Cu$_{0.2}$Zn$_{0.2}$)O (MgO-ESO) have been studied using muon spin relaxation ($μ$SR) and inelastic neutron scattering. We find that antiferromagnetic order develops gradually in the sample volume as it is cooled below 140 K, becoming fully ordered around 100 K. The spin dynamics show a critical slowing down in the vicinity of the transition, and the magnetic order parameter grows continuously in the ordered state. These results indicate that the antiferromagnetic transition is continuous but proceeds with a Gaussian distribution of ordering temperatures. The magnetic contribution to the specific heat determined from inelastic neutron scattering likewise shows a broad feature centered around 120 K. High-resolution inelastic neutron scattering further reveals an initially gapped spectrum at low temperature which sees an increase in a quasielastic contribution upon heating until the ordering temperature.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions

Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge for learning a deep neural network, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training. On the other hand, oversampling tail classes makes the network prone to over-fitting, since head class samples are often consequently under-represented. To resolve this dilemma, in this paper, we propose a simple-yet-effective auxiliary learning approach. The key idea is to split a network into a classifier part and a feature extractor part, and then employ different training strategies for each part. Specifically, to promote the awareness of tail-classes, a class-balanced sampling scheme is utilised for training both the classifier and the feature extractor. For the feature extractor, we also introduce an auxiliary training task, which is to train a classifier under the regular random sampling scheme. In this way, the feature extractor is jointly trained from both sampling strategies and thus can take advantage of all training data and avoid the over-fitting issue. Apart from this basic auxiliary task, we further explore the benefit of using self-supervised learning as the auxiliary task. Without using any bells and whistles, our model achieves superior performance over the state-of-the-art solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning

The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervision. Inspired by this learning process, we propose a simple yet effective model for the Few-Shot Fine-Grained (FSFG) recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning. The proposed method, named Pairwise Alignment Bilinear Network (PABN), is an end-to-end deep neural network. Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric. In order to match base image features with query image features, we design feature alignment losses before the proposed pairwise bilinear pooling. Experiment results on four fine-grained classification datasets and one generic few-shot dataset demonstrate that the proposed model outperforms both the state-ofthe-art few-shot fine-grained and general few-shot methods.

0 citations0 reviewsNo code linkedOpen access