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

Yiming Huang

Yiming Huang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageArtificial Intelligenceastro-ph.IMComputer Visioncond-mat.dis-nncond-mat.mes-hallhep-exHuman-Computer InteractionMachine LearningMultimediaNeurons and Cognitionphysics.opticsRoboticsSoftware Engineering

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
14topics
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

9 published item(s)

preprint2026arXiv

BOOKMARKS: Efficient Active Storyline Memory for Role-playing

Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling) mainly rely on recurrent summarization, whose compression inevitably discards important details. To address this issue, we propose a search-based memory framework called BOOKMARKS, which actively initializes, maintains, and updates task-relevant pieces of bookmarks for the current task (e.g., character acting). A bookmark is structured as the answer to a question at a specific point in the storyline. For each current task, BOOKMARKS selects reusable existing bookmarks or initializes new ones (at storyline beginning) with useful questions. These bookmarks are then synchronized to the current story point, with their answers updated accordingly, so they can be efficiently reused in future grounding rounds. Compared with recurrent summarization, BOOKMARKS offers (1) active grounding for capturing task-specific details and (2) passive updating to avoid unnecessary computation. In implementation, BOOKMARKS supports concept, behavior, and state searches, each powered by an efficient synchronization method. BOOKMARKS significantly outperforms RPA memory baselines on 85 characters from 16 artifacts, demonstrating the effectiveness of search-based memory for RPAs.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, capable of tackling complex tasks during inference. However, the extent to which LLMs can be utilized for code checking or debugging through test case generation remains largely unexplored. We investigate this problem from the perspective of competition-level programming (CP) programs and propose TCGBench, a Benchmark for (LLM generation of) Test Case Generators. This benchmark comprises two tasks, aimed at studying the capabilities of LLMs in (1) generating valid test case generators for a given CP problem, and further (2) generating targeted test case generators that expose bugs in human-written code. Experimental results indicate that while state-of-the-art LLMs can generate valid test case generators in most cases, most LLMs struggle to generate targeted test cases that reveal flaws in human code effectively. Especially, even advanced reasoning models (e.g., o3-mini) fall significantly short of human performance in the task of generating targeted generators. Furthermore, we construct a high-quality, manually curated dataset of instructions for generating targeted generators. Analysis demonstrates that the performance of LLMs can be enhanced with the aid of this dataset, by both prompting and fine-tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios

Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at \href{https://github.com/DA-Open/DV-World}{this project page}.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting

In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream tasks and advancing surgical outcomes. However, existing methods primarily focus on visual reconstruction, lacking physics-based descriptions of the scene required for realistic simulation. We propose a unified framework that achieves physics-aware reconstruction and physical simulation of endoscopic scenes through Multi-modal Large Language Models (MLLMs)-guided Gaussian Splatting. Our approach utilizes 4D Gaussian Splatting (4DGS) integrated with pre-trained segmentation and depth estimation to represent deformable tissues and tools. To achieve automatic inference of physical properties, we introduce an object-wise material field that initializes material parameters via MLLM and refines them through a differentiable Material Point Method (MPM) under joint supervision from rendered images and optical flow. Validated on both open-source and in-house datasets, our framework achieves superior simulation fidelity and physical accuracy compared to state-of-the-art methods, underscoring its potential to advance robot-assisted surgical applications.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow

Automation in data analysis has been a long-time pursuit. Current agentic LLM shows a promising solution towards it. Like DeepAnalyze, DataSage, and Datawise. They are all powerful agentic frameworks for automatic fine-grained analysis and are powered by LLM-based agentic tool calling ability. However, what about powered by a preset AutoML-like workflow? If we traverse all possible exploration, like Xn itself`s statistics, Xn1-Xn2 relationships, Xn to all other, and finally explain? Our Explanova is such an attempt: Cheaper due to a Local Small LLM.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CATCH: Chasing All Transients Constellation Hunters Space Mission

In time-domain astronomy, a substantial number of transients will be discovered by multi-wavelength and multi-messenger observatories, posing a great challenge for follow-up capabilities. We have thus proposed an intelligent X-ray constellation, the Chasing All Transients Constellation Hunters (CATCH) space mission. Consisting of 126 micro-satellites in three types, CATCH will have the capability to perform follow-up observations for a large number of different types of transients simultaneously. Each satellite in the constellation will carry lightweight X-ray optics and use a deployable mast to increase the focal length. The combination of different optics and detector systems enables different types of satellites to have multiform observation capabilities, including timing, spectroscopy, imaging, and polarization. Controlled by the intelligent system, different satellites can cooperate to perform uninterrupted monitoring, all-sky follow-up observations, and scanning observations with a flexible field of view (FOV) and multi-dimensional observations. Therefore, CATCH will be a powerful mission to study the dynamic universe. Here, we present the current design of the spacecraft, optics, detector system, constellation configuration and observing modes, as well as the development plan.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Change in structural brain network abnormalities after traumatic brain injury determines post-injury recovery

The trajectory of an individual's recovery after traumatic brain injury (TBI) is heterogeneous, with complete recovery in some cases but persistent disability in others. We hypothesized that changes in structural brain network abnormalities guide the trajectory of an individual's recovery post-injury. Our objective was to characterize the variability in recovery post-TBI by identifying a putative neuroimaging biomarker of traumatic axonal injury (TAI) in individuals with mild TBI. We analyzed 70 T1-weighted and diffusion MRIs longitudinally collected from 35 individuals during the subacute and chronic post-injury periods. Each individual underwent longitudinal blood work to characterize blood protein biomarkers of axonal and glial injury and assessment of post-injury recovery in the subacute and chronic periods. By comparing the MRI data of individual cases with 35 controls, we estimated the longitudinal change in structural brain network abnormalities. We validated this proxy measure of TAI with independent measures of acute intracranial injury estimated from head CT and blood protein biomarkers. Post-injury structural network abnormality was significantly higher than controls in both subacute and chronic periods, associated with an acute CT lesion and subacute blood levels of glial fibrillary acid protein (r=0.5, p=0.008) and neurofilament light (r=0.41, p=0.02). Longitudinal change in abnormality associated with change in functional outcome status (r=-0.51, p=0.003) and post-concussive symptoms (BSI: r=0.46, p=0.03; RPQ:r = 0.46, p=0.02). Brain regions that most closely mapped onto symptom change over time corresponded to structural network hubs or areas susceptible to neurotrauma. Structural network abnormalities might be a biomarker of TAI. Assessing changes in brain network abnormality might enable better patient stratification for monitoring recovery after neurotrauma.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Reproducible Evaluations for Flying Drone Controllers in Virtual Environments

Research attention on natural user interfaces (NUIs) for drone flights are rising. Nevertheless, NUIs are highly diversified, and primarily evaluated by different physical environments leading to hard-to-compare performance between such solutions. We propose a virtual environment, namely VRFlightSim, enabling comparative evaluations with enriched drone flight details to address this issue. We first replicated a state-of-the-art (SOTA) interface and designed two tasks (crossing and pointing) in our virtual environment. Then, two user studies with 13 participants demonstrate the necessity of VRFlightSim and further highlight the potential of open-data interface designs.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Invariance principle for wave propagation inside inhomogeneously disordered materials

Disorder is more the rule than the exception in natural and synthetic materials. Nonetheless, wave propagation within inhomogeneously disordered materials has received scant attention. We combine microwave experiments and theory to find the spatial variation of generic wave propagation quantities in inhomogeneously disordered materials. We demonstrate that wave statistics within samples of any dimension are independent of the detailed structure of a material and depend only on the net strengths of distributed scattering and reflection between the observation point and each of the boundaries.

0 citations0 reviewsNo code linkedOpen access