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

Yongcai Wang

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

ResearcherUnclaimed source record
Artificial IntelligenceComputer VisionHuman-Computer InteractionInformation Theorymath.ITNetworking and Internet Architecture

Catalog footprint

What is connected

5works
6topics
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

5 published item(s)

preprint2026arXiv

BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception

Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DecisionLLM: Large Language Models for Long Sequence Decision Exploration

Long-sequence decision-making, which is usually addressed through reinforcement learning (RL), is a critical component for optimizing strategic operations in dynamic environments, such as real-time bidding in computational advertising. The Decision Transformer (DT) introduced a powerful paradigm by framing RL as an autoregressive sequence modeling problem. Concurrently, Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning and planning tasks. This inspires us whether LLMs, which share the same Transformer foundation, but operate at a much larger scale, can unlock new levels of performance in long-horizon sequential decision-making problem. This work investigates the application of LLMs to offline decision making tasks. A fundamental challenge in this domain is the LLMs' inherent inability to interpret continuous values, as they lack a native understanding of numerical magnitude and order when values are represented as text strings. To address this, we propose treating trajectories as a distinct modality. By learning to align trajectory data with natural language task descriptions, our model can autoregressively predict future decisions within a cohesive framework we term DecisionLLM. We establish a set of scaling laws governing this paradigm, demonstrating that performance hinges on three factors: model scale, data volume, and data quality. In offline experimental benchmarks and bidding scenarios, DecisionLLM achieves strong performance. Specifically, DecisionLLM-3B outperforms the traditional Decision Transformer (DT) by 69.4 on Maze2D umaze-v1 and by 0.085 on AuctionNet. It extends the AIGB paradigm and points to promising directions for future exploration in online bidding.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Featured Trajectory Generation for TrackPuzzle

Indoor route graph learning is critically important for autonomous indoor navigation. A key problem for crowd-sourcing indoor route graph learning is featured trajectory generation. In this paper, a system is provided to generate featured trajectories by crowd-sourcing smartphone data. Firstly, we propose a more accurate PDR algorithm for the generation of trajectory motion data. This algorithm uses ADAPTIV as the step counting method and uses the step estimation algorithm o make the trajectory more accurate in length. Next, the barometer is used to segment the tracks of different floors, and the track floors are obtained by WiFi feature clustering. Finally, by finding the turning point as the feature point of the trajectory, the vertices and edges of the trajectory are extracted to reduce the noise of the long straight trajectory.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Hybrid Radio-map for Noise Tolerant Wireless Indoor Localization

In wireless networks, radio-map based locating techniques are commonly used to cope the complex fading feature of radio signal, in which a radio-map is built by calibrating received signal strength (RSS) signatures at training locations in the offline phase. However, in severe hostile environments, such as in ship cabins where severe shadowing, blocking and multi-path fading effects are posed by ubiquitous metallic architecture, even radio-map cannot capture the dynamics of RSS. In this paper, we introduced multiple feature radio-map location method for severely noisy environments. We proposed to add low variance signature into radio map. Since the low variance signatures are generally expensive to obtain, we focus on the scenario when the low variance signatures are sparse. We studied efficient construction of multi-feature radio-map in offline phase, and proposed feasible region narrowing down and particle based algorithm for online tracking. Simulation results show the remarkably performance improvement in terms of positioning accuracy and robustness against RSS noises than the traditional radio-map method.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Locating Multiple Ultrasound Targets in Chorus

Ranging by Time of Arrival (TOA) of Narrow-band ultrasound (NBU) has been widely used by many locating systems for its characteristics of low cost and high accuracy. However, because it is hard to support code division multiple access in narrowband signal, to track multiple targets, existing NBU-based locating systems generally need to assign exclusive time slot to each target to avoid the signal conflicts. Because the propagation speed of ultrasound is slow in air, dividing exclusive time slots on a single channel causes the location updating rate for each target rather low, leading to unsatisfied tracking performances as the number of targets increases. In this paper, we investigated a new multiple target locating method using NBU, called UltraChorus, which is to locate multiple targets while allowing them sending NBU signals simultaneously, i.e., in chorus mode. It can dramatically increase the location updating rate. In particular, we investigated by both experiments and theoretical analysis on the necessary and sufficient conditions for resolving the conflicts of multiple NBU signals on a single channel, which is referred as the conditions for chorus ranging and chorus locating. To tackle the difficulty caused by the anonymity of the measured distances, we further developed consistent position generation algorithm and probabilistic particle filter algorithm}to label the distances by sources, to generate reasonable location estimations, and to disambiguate the motion trajectories of the multiple concurrent targets based on the anonymous distance measurements. Extensive evaluations by both simulation and testbed were carried out, which verified the effectiveness of our proposed theories and algorithms.

0 citations0 reviewsNo code linkedOpen access