Researcher profile

Zijian Zhao

Zijian Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Machine Learning Artificial Intelligence Emerging Technologies Computation and Language Multimedia astro-ph.IM eess.AS eess.SP Hardware Architecture Multiagent Systems physics.app-ph physics.ins-det

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

9works

0followers

12topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

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

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

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.

preprint2026arXiv

Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning

Music-inspired Automatic Stage Lighting Control (ASLC) has gained increasing attention in recent years due to the substantial time and financial costs associated with hiring and training professional lighting engineers. However, existing methods suffer from several notable limitations: the low interpretability of rule-based approaches, the restriction to single-primary-light control in music-to-color-space methods, and the limited transferability of music-to-controlling-parameter frameworks. To address these gaps, we propose SeqLight, a hierarchical deep learning framework that maps music to multi-light Hue-Saturation-Value (HSV) space. Our approach first customizes SkipBART, an end-to-end single primary light generation model, to predict the full light color distribution for each frame, followed by hybrid Imitation Learning (IL) techniques to derive an effective decomposition strategy that distributes the global color distribution among individual lights. Notably, the light decomposition module can be trained under varying venue-specific lighting configurations using only mixed light data and no professional demonstrations, thereby flexibly adapting across diverse venues. In this stage, we formulate the light decomposition task as a Goal-Conditioned Markov Decision Process (GCMDP), construct an expert demonstration set inspired by Hindsight Experience Replay (HER), and introduce a three-phase IL training pipeline, achieving strong generalization capability. To validate our IL solution for the proposed GCMDP, we conduct a series of quantitative analysis and human study. The code and trained models are provided at https://github.com/RS2002/SeqLight .

preprint2025arXiv

Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?

Stage lighting is a vital component in live music performances, shaping an engaging experience for both musicians and audiences. In recent years, Automatic Stage Lighting Control (ASLC) has attracted growing interest due to the high costs of hiring or training professional lighting engineers. However, most existing ASLC solutions only classify music into limited categories and map them to predefined light patterns, resulting in formulaic and monotonous outcomes that lack rationality. To address this gap, this paper presents Skip-BART, an end-to-end model that directly learns from experienced lighting engineers and predict vivid, human-like stage lighting. To the best of our knowledge, this is the first work to conceptualize ASLC as a generative task rather than merely a classification problem. Our method adapts the BART model to take audio music as input and produce light hue and value (intensity) as output, incorporating a novel skip connection mechanism to enhance the relationship between music and light within the frame grid. To address the lack of available datasets, we create the first stage lighting dataset, along with several pre-training and transfer learning techniques to improve model training with limited data. We validate our method through both quantitative analysis and an human evaluation, demonstrating that Skip-BART outperforms conventional rule-based methods across all evaluation metrics and shows only a limited gap compared to real lighting engineers. To support further research, we have made our self-collected dataset, code, and trained model parameters available at https://github.com/RS2002/Skip-BART .

preprint2025arXiv

Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?

On-demand ride-sharing platforms, such as Uber and Lyft, face the intricate real-time challenge of bundling and matching passengers-each with distinct origins and destinations-to available vehicles, all while navigating significant system uncertainties. Due to the extensive observation space arising from the large number of drivers and orders, order dispatching, though fundamentally a centralized task, is often addressed using Multi-Agent Reinforcement Learning (MARL). However, independent MARL methods fail to capture global information and exhibit poor cooperation among workers, while Centralized Training Decentralized Execution (CTDE) MARL methods suffer from the curse of dimensionality. To overcome these challenges, we propose Triple-BERT, a centralized Single Agent Reinforcement Learning (MARL) method designed specifically for large-scale order dispatching on ride-sharing platforms. Built on a variant TD3, our approach addresses the vast action space through an action decomposition strategy that breaks down the joint action probability into individual driver action probabilities. To handle the extensive observation space, we introduce a novel BERT-based network, where parameter reuse mitigates parameter growth as the number of drivers and orders increases, and the attention mechanism effectively captures the complex relationships among the large pool of driver and orders. We validate our method using a real-world ride-hailing dataset from Manhattan. Triple-BERT achieves approximately an 11.95% improvement over current state-of-the-art methods, with a 4.26% increase in served orders and a 22.25% reduction in pickup times. Our code, trained model parameters, and processed data are publicly available at the repository https://github.com/RS2002/Triple-BERT .

preprint2022arXiv

An Ultra-Compact Single FeFET Binary and Multi-Bit Associative Search Engine

Content addressable memory (CAM) is widely used in associative search tasks for its highly parallel pattern matching capability. To accommodate the increasingly complex and data-intensive pattern matching tasks, it is critical to keep improving the CAM density to enhance the performance and area efficiency. In this work, we demonstrate: i) a novel ultra-compact 1FeFET CAM design that enables parallel associative search and in-memory hamming distance calculation; ii) a multi-bit CAM for exact search using the same CAM cell; iii) compact device designs that integrate the series resistor current limiter into the intrinsic FeFET structure to turn the 1FeFET1R into an effective 1FeFET cell; iv) a successful 2-step search operation and a sufficient sensing margin of the proposed binary and multi-bit 1FeFET1R CAM array with sizes of practical interests in both experiments and simulations, given the existing unoptimized FeFET device variation; v) 89.9x speedup and 66.5x energy efficiency improvement over the state-of-the art alignment tools on GPU in accelerating genome pattern matching applications through the hyperdimensional computing paradigm.

preprint2022arXiv

CMOS-Compatible Ising Machines built using Bistable Latches Coupled through Ferroelectric Transistor Arrays

Realizing compact and scalable Ising machines that are compatible with CMOS-process technology is crucial to the effectiveness and practicality of using such hardware platforms for accelerating computationally intractable problems. Besides the need for realizing compact Ising spins, the implementation of the coupling network, which describes the spin interaction, is also a potential bottleneck in the scalability of such platforms. Therefore, in this work, we propose an Ising machine platform that exploits the novel behavior of compact bi-stable CMOS-latches (cross-coupled inverters) as classical Ising spins interacting through highly scalable and CMOS-process compatible ferroelectric-HfO2-based Ferroelectric FETs (FeFETs) which act as coupling elements. We experimentally demonstrate the prototype building blocks of this system, and evaluate the behavior of the scaled system using simulations. We project that the proposed architecture can compute Ising solutions with an efficiency of ~1.04 x 10^8 solutions/W/second. Our work not only provides a pathway to realizing CMOS-compatible designs but also to overcoming their scaling challenges.

preprint2022arXiv

Hardware Functional Obfuscation With Ferroelectric Active Interconnects

Camouflaging gate techniques are typically used in hardware security to prevent reverse engineering. Layout level camouflaging by adding dummy contacts ensures some level of protection against extracting the correct netlist. Threshold voltage manipulation for multi-functional logic with identical layouts has also been introduced for functional obfuscation. All these techniques are implemented at the expense of circuit-complexity and with significant area, energy, and delay penalty. In this paper, we propose an efficient hardware encryption technique with minimal complexity and overheads based on ferroelectric field-effect transistor (FeFET) active interconnects. The active interconnect provides run-time reconfigurable inverter-buffer logic by utilizing the threshold voltage programmability of the FeFETs. Our method utilizes only two FeFETs and an inverter to realize the masking function compared to recent reconfigurable logic gate implementations using several FeFETs and complex differential logic. We fabricate the proposed circuit and demonstrate the functionality. Judicious placement of the proposed logic in the IC makes it acts as a hardware encryption key and enables encoding and decoding of the functional output without affecting the critical path timing delay. Also, we achieve comparable encryption probability with a limited number of encryption units. In addition, we show a peripheral programming scheme for reconfigurable logic by reusing the existing scan chain logic, hence obviating the need for specialized programming logic and circuitry for keybit distribution. Our analysis shows an average encryption probability of 97.43% with an increase of 2.24%/ 3.67% delay for the most critical path/ sum of 100 critical paths delay for ISCAS85 benchmarks.

preprint2021arXiv

Performance of a focal plane detector for soft X-ray imaging spectroscopy based on back-illuminated sCMOS

Spectroscopy focusing array (SFA) and Polarimetry focusing array (PFA) are the two major payloads of enhanced X-ray Timing and Polarimetry mission (eXTP). Nested Wolter-\RNum{1} X-ray mirror module is implemented in SFA and PFA to achive high effective area. When evaluating the properties of the mirror module, the alignment of the optical axis of the X-ray mirror module and a quasi-parallel X-ray beam is a prerequisite to ensure the accuracy of the results. Hence, to assist the alignment of the X-ray mirror module, an X-ray focal plane detector is designed based on the back-illuminated scientific Complementary Metal-Oxide-Semiconductor Transistor (sCMOS) sensor GSENSE6060BSI, one of the largest detection areas, is produced by \textit{Gpixel Inc}. Then the characteristics of readout noise, dark current, and split-pixel event properties of the detector are studied with the self-developed multi-target fluorescence X-ray source in a 100 m long X-ray test facility. The energy calibration is carried out with the single-pixel event and the energy non-linearity of the detector is also obtained. Eventually, the simulation of the eXTP mirror module based on the optical model is conducted and the alignment test of the Wolter-\RNum{1} X-ray mirror module designed for \textit{EP/FXT} (Einstein Probe/Follow-up X-ray Telescope) with "Burkert test" method is shown.

preprint2020arXiv

Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding

Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SLU module. To address this issue, word confusion networks (WCNs) have been used to encode the input for SLU, which contain richer information than 1-best or n-best hypotheses list. To further eliminate ambiguity, the last system act of dialogue context is also utilized as additional input. In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly. It can integrate both structural information and ASR posterior probabilities of WCNs in the BERT architecture. Experiments on DSTC2, a benchmark of SLU, show that the proposed method is effective and can outperform previous state-of-the-art models significantly.

preprint2020arXiv

Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding

Traditional slot filling in natural language understanding (NLU) predicts a one-hot vector for each word. This form of label representation lacks semantic correlation modelling, which leads to severe data sparsity problem, especially when adapting an NLU model to a new domain. To address this issue, a novel label embedding based slot filling framework is proposed in this paper. Here, distributed label embedding is constructed for each slot using prior knowledge. Three encoding methods are investigated to incorporate different kinds of prior knowledge about slots: atomic concepts, slot descriptions, and slot exemplars. The proposed label embeddings tend to share text patterns and reuses data with different slot labels. This makes it useful for adaptive NLU with limited data. Also, since label embedding is independent of NLU model, it is compatible with almost all deep learning based slot filling models. The proposed approaches are evaluated on three datasets. Experiments on single domain and domain adaptation tasks show that label embedding achieves significant performance improvement over traditional one-hot label representation as well as advanced zero-shot approaches.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint