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

Yin Yu

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

ResearcherUnclaimed source record
Computer VisionArtificial IntelligenceComputation and Languageeess.SYInformation RetrievalMachine LearningMultiagent Systemsphysics.flu-dynphysics.opticsSystems and Control

Catalog footprint

What is connected

6works
10topics
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

DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models

PromptReps showed that an autoregressive language model can be used directly as a retriever by prompting it to generate dense and sparse representations of a query or passage. Extending this to multiple representatives is inefficient for autoregressive models, since tokens must be generated sequentially, and prior multi-token variants did not reliably improve over single-token decoding. We show that the bottleneck is sequential generation, not the multi-token idea itself. DiffRetriever is a representative-token retriever for diffusion language models: it appends K masked positions to the prompt and reads all K in a single bidirectional forward pass. Across in-domain and out-of-domain evaluation, multi-token DiffRetriever substantially improves over single-token on every diffusion backbone we test, while autoregressive multi-token is flat or negative and pays a latency cost that scales with K where diffusion does not. After supervised fine-tuning, DiffRetriever on Dream is the strongest BEIR-7 retriever in our comparison, ahead of PromptReps, the encoder-style DiffEmbed baseline on the same diffusion backbones, and the contrastively fine-tuned single-vector RepLLaMA. A per-query oracle on the frozen base model exceeds contrastive fine-tuning at the same fixed budget, pointing to adaptive budget selection as future work. Code is available at https://github.com/ielab/diffretriever.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Expanding the Latent Space of StyleGAN for Real Face Editing

Recently, a surge of face editing techniques have been proposed to employ the pretrained StyleGAN for semantic manipulation. To successfully edit a real image, one must first convert the input image into StyleGAN's latent variables. However, it is still challenging to find latent variables, which have the capacity for preserving the appearance of the input subject (e.g., identity, lighting, hairstyles) as well as enabling meaningful manipulations. In this paper, we present a method to expand the latent space of StyleGAN with additional content features to break down the trade-off between low-distortion and high-editability. Specifically, we proposed a two-branch model, where the style branch first tackles the entanglement issue by the sparse manipulation of latent codes, and the content branch then mitigates the distortion issue by leveraging the content and appearance details from the input image. We confirm the effectiveness of our method using extensive qualitative and quantitative experiments on real face editing and reconstruction tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generating Topological Structure of Floorplans from Room Attributes

Analysis of indoor spaces requires topological information. In this paper, we propose to extract topological information from room attributes using what we call Iterative and adaptive graph Topology Learning (ITL). ITL progressively predicts multiple relations between rooms; at each iteration, it improves node embeddings, which in turn facilitates generation of a better topological graph structure. This notion of iterative improvement of node embeddings and topological graph structure is in the same spirit as \cite{chen2020iterative}. However, while \cite{chen2020iterative} computes the adjacency matrix based on node similarity, we learn the graph metric using a relational decoder to extract room correlations. Experiments using a new challenging indoor dataset validate our proposed method. Qualitative and quantitative evaluation for layout topology prediction and floorplan generation applications also demonstrate the effectiveness of ITL.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

PIDGeuN: Graph Neural Network-Enabled Transient Dynamics Prediction of Networked Microgrids Through Full-Field Measurement

A Physics-Informed Dynamic Graph Neural Network (PIDGeuN) is presented to accurately, efficiently and robustly predict the nonlinear transient dynamics of microgrids in the presence of disturbances. The graph-based architecture of PIDGeuN provides a natural representation of the microgrid topology. Using only the state information that is practically measurable, PIDGeuN employs a time delay embedding formulation to fully reproduce the system dynamics, avoiding the dependency of conventional methods on internal dynamic states such as controllers. Based on a judiciously designed message passing mechanism, the PIDGeuN incorporates two physics-informed techniques to improve its prediction performance, including a physics-data-infusion approach to determining the inter-dependencies between buses, and a loss term to respect the known physical law of the power system, i.e., the Kirchhoff's law, to ensure the feasibility of the model prediction. Extensive tests show that PIDGeuN can provide accurate and robust prediction of transient dynamics for nonlinear microgrids over a long-term time period. Therefore, the PIDGeuN offers a potent tool for the modeling of large scale networked microgrids (NMs), with potential applications to predictive or preventive control in real time applications for the stable and resilient operations of NMs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety critical applications of c-MARL, such as traffic management, power management and unmanned aerial vehicle control, it is crucial to test the robustness of c-MARL algorithm before it was deployed in reality. Existing adversarial attacks for MARL could be used for testing, but is limited to one robustness aspects (e.g., reward, state, action), while c-MARL model could be attacked from any aspect. To overcome the challenge, we propose MARLSafe, the first robustness testing framework for c-MARL algorithms. First, motivated by Markov Decision Process (MDP), MARLSafe consider the robustness of c-MARL algorithms comprehensively from three aspects, namely state robustness, action robustness and reward robustness. Any c-MARL algorithm must simultaneously satisfy these robustness aspects to be considered secure. Second, due to the scarceness of c-MARL attack, we propose c-MARL attacks as robustness testing algorithms from multiple aspects. Experiments on \textit{SMAC} environment reveals that many state-of-the-art c-MARL algorithms are of low robustness in all aspect, pointing out the urgent need to test and enhance robustness of c-MARL algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Rayleigh-Brillouin scattering in SF$_6$ in the kinetic regime

Rayleigh-Brillouin spectral profiles are measured with a laser-based scatterometry setup for a 90 degrees scattering angle at a high signal-to-noise ratio (r.m.s. noise below 0.15 \% w.r.t. peak intensity) in sulphur-hexafluoride gas for pressures in the range 0.2 -- 5 bar and for a wavelength of $λ=403.0$ nm. The high quality data are compared to a number of light scattering models in order to address the effects of rotational and vibrational relaxation. While the vibrational relaxation rate is so slow that vibration degrees of freedom remain frozen, rotations relax on time scales comparable to those of the density fluctuations. Therefore, the heat capacity, the thermal conductivity and the bulk viscosity are all frequency-dependent transport coefficients. This is relevant for the Tenti model that depends on the values chosen for these transport coefficients. This is not the case for the other two models considered: a kinetic model based on rough-sphere interactions, and a model based on fluctuating hydrodynamics. The deviations with the experiment are similar between the three different models, except for the hydrodynamic model at pressures $p \lesssim 2\;{\rm bar}$. As all models are in line with the ideal gas law, we hypothesize the presence of real gas effects in the measured spectra.

0 citations0 reviewsNo code linkedOpen access