Source author record

Wenzhe Cai

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

ResearcherUnclaimed source record

Catalog footprint

What is connected

3works
2topics
4close collaborators

Actions

Connect this record

Log in to claim

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

3 published item(s)

preprint2026arXiv

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the rigorous functional semantics and safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are not only realistic but also functionally valid and safe for complex experimental workflows.

preprint2022arXiv

Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation

Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different morphology). Thus some scene graph generation methods are trapped into most frequent relation predictions caused by capricious visual features and trivial dataset annotations. Therefore, recent works emphasized the "unbiased" approaches to balance predictions for a more informative scene graph. However, human's quick and accurate judgments over relations between numerous objects should be attributed to "bias" (i.e., experience and linguistic knowledge) rather than pure vision. To enhance the model capability, inspired by the "cognitive bias" mechanism, we propose a novel 3-paradigms framework that simulates how humans incorporate the label linguistic features as guidance of vision-based representations to better mine hidden relation patterns and alleviate noisy visual propagation. Our framework is model-agnostic to any scene graph model. Comprehensive experiments prove our framework outperforms baseline modules in several metrics with minimum parameters increment and achieves new SOTA performance on Visual Genome dataset.

preprint2022arXiv

Interface inter-atomic electron-transition induced photon emission in contact-electrification

Contact electrification (CE) (or triboelectrification) is the phenomena where charges are produced through physical contact between two materials. Here we report the atomic featured photon emission spectra during CE between two solid materials. Photon emission provides the evidence that electron transfer takes place at the interface from an atom in one material to another atom in the other material during CE. This process is the contact electrification induced interface photon emission spectroscopy (CEIIPES). It naturally paves a way to a spectroscopy corresponding to the CE at an interface, which might impact our understanding of the interaction between solids, liquids, and gases. The physics presented here could be expanded to Auger electron excitation, x-ray emission, and electron emission in CE for general cases, which remain to be explored. This could lead to a general field that may be termed as contact electrification induced interface spectroscopy (CEIIS).