arXiv subjects

Biao Zhao

Publications and source records attributed to Biao Zhao.

13 recordsLinked to original sources

arXiv2026

Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage

Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most methods train agents at a single fixed difficulty throughout the entire run. We term this static-difficulty regime environmental meta-stationarity and show that it caps policy generalization and steers learning toward shallow local optima. To break this regime, we propose CL-MARL, a dynamic curriculum learning framework that adapts opponent strength online from win-rate signals, advancing or regressing the task as agents master it. Its scheduler, FlexDiff, fuses momentum-based trend estimation with sliding-window dual-curve monitoring of training and evaluation returns, yielding stable difficulty transitions without manual tuning. Because a moving curriculum amplifies non-stationarity and sparsifies global rewards, we introduce the Counterfactual Group Relative Policy Advantage (CGRPA), which extends GRPO-style group-relative optimization with counterfactual baselines to disentangle each agent's contribution under shifting team dynamics. On the StarCraft Multi-Agent Challenge (SMAC), CL-MARL attains a 40% mean win rate on the super-hard maps with an average episode return of 17.85, exceeding the QMIX, OW-QMIX, DER, EMC, and MARR baselines by +2.94 on average, while reaching its peak win rate roughly 1.28faster on 8m_vs_9m and 1.42 faster on 3s5z_vs_3s6z than the strongest baseline. The implementation is publicly available at https://github.com/NICE-HKU/CL2MARL-SMAC.

cs.AI↗

arXiv2025

Charge-Unified Semiconductor Switching Theory

Semiconductors and their downstream applications sustain the electronic, information, energy and industrial systems underpinning modern society. Improving their sustainability is therefore an urgent global priority, particularly as global electricity generation is projected to increase more than 2.5 fold by 2050. Yet, since the invention of the transistor in 1947, a unified, global view of circuit elements as media for charge redistribution and transfer one that reveals switching inertia and the dynamical nature of switching while connecting microscopic and macroscopic domains across the semiconductor value chain through a common theoretical language has remained absent. Switching consequently lacks a unified mechanistic account of its physical origins and spatiotemporal evolution, with fundamental disconnects between charge- and energy-conservation frameworks, among carrier dynamic mechanisms and across equivalent-circuit formalisms. These limitations fragment research domains and impede sustainability gains, particularly those requiring cross-domain causal information. Here, we present Charge-Unified Semiconductor Switching Theory (CUSST), a general theory that unifies circuit elements through a charge-mediated view, reveals switching inertia and the dynamical nature of switching, bridges these long-standing disconnects and establishes a unified conceptual, mechanistic, formal and analytical framework. Through these unifications, CUSST provides an unusually simple representation of otherwise fragmented switching phenomena. It establishes a unified micro-macro spatiotemporal view of switching, generalizes circuit theory, extends the application of conservation laws and provides a foundation for developing new theoretical systems.

eess.SY↗

arXiv2025

Measurement of the Temperature Dependence of the Refractive Index of CdZnTe

We have been developing a CdZnTe immersion grating for a compact high-dispersion mid-infrared spectrometer (wavelength range 10--18 $μ$m, spectral resolution $R = λ/Δλ> 25,000$, operating temperature $T < 20$ K). Using an immersion grating, the spectrometer size can be reduced to $1/n$ ($n$: refractive index) compared to conventional diffraction gratings. CdZnTe is promising as a material for immersion gratings for the wavelength range. However, the refractive index $n$ of CdZnTe has not been measured at $T < 20$ K. We have been developing a system to precisely measure $n$ at cryogenic temperatures ($T \sim 10$ K) in the mid-infrared wavelength range. As the first result, this paper reports the temperature dependence of $n$ of CdZnTe at the wavelength of 10.68 $μ$m. This system employs the minimum deviation method. The refractive index $n$ of CdZnTe is measured at temperatures of $ T = 12.57, 22.47, 50.59, 70.57, \text{ and } 298 \, \text{K} $. We find that $n$ of CdZnTe at $λ=$ 10.68 $μ$m is $2.6371 \pm 0.0022$ at $12.57 \pm 0.14$ K, and the average temperature dependence of $n$ between 12.57 $\pm$ 0.14 K and 70.57 $\pm$ 0.23 K is $Δn/ΔT = (5.8 \pm 0.3) \times 10^{-5}$ K$^{-1}$.

astro-ph.IM↗

arXiv2025

Mid-Infrared Imaging Spectroscopy of N2O Solid Simulating the haze of trans-Neptunian objects

\ Nitrous oxide (N$_2$O) ice is likely to exist in trans-Neptunian objects such as Pluto and Triton, potentially formed through ultraviolet (UV) radiation from the Sun or cosmic ray irradiation of N$_2$ and CO ices. However, the mid-infrared spectral characteristics of N$_2$O ice in higher temperature regions (90-110 K), changes in mid-infrared spectra during UV irradiation, and the chemical network of nitrogen oxide (N$_x$O$_y$) ices remain insufficiently understood. This study aims to elucidate these aspects through in-situ mid-infrared spectral measurements of cryogenic particles using two-dimensional imaging Fourier transform infrared spectroscopy. Spectroscopic imaging confirmed strong absorption at 7.75 $μ$m (N$_2$O $ν_1$ vibrational mode), with weaker vibrational modes observed at 8.60 $μ$m (N$_2$O 2$ν_2$), 7.27 $μ$m (N$_2$O torsion), and 5.29 $μ$m (N$_2$O $ν_1$+$ν_2$). Annealing experiments simulating high-temperature conditions demonstrated that all vibrational modes irreversibly intensified with increasing temperature, indicating progressive crystallization. New spectral features appeared at approximately 12 $μ$m and 14 $μ$m at the condensed sample. N$_2$O ice was exposed to ultraviolet radiation (190-340 nm) using a D$_2$ lamp for 8.5 hours to investigate spectral changes during UV irradiation. After 60-90 minutes of irradiation, all N$_2$O vibrational modes disappeared, while absorption intensities of various nitrogen oxides, including NO, NO$_2$, N$_2$O$_3$, and O$_3$ increased. Beyond 180 minutes, vibrational modes of multiple nitrogen oxide ices exhibited intensity variations across different wavelengths, corresponding to other species such as cis-(NO)$_2$, N$_2$O$_4$, and N$_2$O$_5$.

astro-ph.EP↗

arXiv2025

A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives

With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex multi-agent cooperative task scenarios. Multi-agent cooperative decision-making involves multiple agents working together to complete established tasks and achieve specific objectives. These techniques are widely applicable in real-world scenarios such as autonomous driving, drone navigation, disaster rescue, and simulated military confrontations. This paper begins with a comprehensive survey of the leading simulation environments and platforms used for multi-agent cooperative decision-making. Specifically, we provide an in-depth analysis for these simulation environments from various perspectives, including task formats, reward allocation, and the underlying technologies employed. Subsequently, we provide a comprehensive overview of the mainstream intelligent decision-making approaches, algorithms and models for multi-agent systems (MAS). Theseapproaches can be broadly categorized into five types: rule-based (primarily fuzzy logic), game theory-based, evolutionary algorithms-based, deep multi-agent reinforcement learning (MARL)-based, and large language models(LLMs)reasoning-based. Given the significant advantages of MARL andLLMs-baseddecision-making methods over the traditional rule, game theory, and evolutionary algorithms, this paper focuses on these multi-agent methods utilizing MARL and LLMs-based techniques. We provide an in-depth discussion of these approaches, highlighting their methodology taxonomies, advantages, and drawbacks. Further, several prominent research directions in the future and potential challenges of multi-agent cooperative decision-making are also detailed.

cs.MA↗

arXiv2024

Hierarchical Multi-Relational Graph Representation Learning for Large-Scale Prediction of Drug-Drug Interactions

Most existing methods for predicting drug-drug interactions (DDI) predominantly concentrate on capturing the explicit relationships among drugs, overlooking the valuable implicit correlations present between drug pairs (DPs), which leads to weak predictions. To address this issue, this paper introduces a hierarchical multi-relational graph representation learning (HMGRL) approach. Within the framework of HMGRL, we leverage a wealth of drug-related heterogeneous data sources to construct heterogeneous graphs, where nodes represent drugs and edges denote clear and various associations. The relational graph convolutional network (RGCN) is employed to capture diverse explicit relationships between drugs from these heterogeneous graphs. Additionally, a multi-view differentiable spectral clustering (MVDSC) module is developed to capture multiple valuable implicit correlations between DPs. Within the MVDSC, we utilize multiple DP features to construct graphs, where nodes represent DPs and edges denote different implicit correlations. Subsequently, multiple DP representations are generated through graph cutting, each emphasizing distinct implicit correlations. The graph-cutting strategy enables our HMGRL to identify strongly connected communities of graphs, thereby reducing the fusion of irrelevant features. By combining every representation view of a DP, we create high-level DP representations for predicting DDIs. Two genuine datasets spanning three distinct tasks are adopted to gauge the efficacy of our HMGRL. Experimental outcomes unequivocally indicate that HMGRL surpasses several leading-edge methods in performance.

cs.LG↗

arXiv2023

On the $C_4$-isolation number of a graph

Let $C_k$ be the cycle of length $k$. For any graph $G$, a subset $D \subseteq V(G)$ is a $C_k$-isolating set of $G$ if the graph obtained from $G$ by deleting the closed neighbourhood of $D$ contains no $C_k$ as a subgraph. The $C_k$-isolation number of $G$, denoted by $ι(G,C_k)$, is the cardinality of a smallest $C_k$-isolating set of $G$. Borg (2020) and Borg et al. (2022) proved that if $G \ncong C_3$ is a connected graph of order $n$ and size $m$, then $ι(G,C_3) \leq \frac{n}{4}$ and $ι(G,C_3) \leq \frac{m+1}{5}$. Very recently, Bartolo, Borg and Scicluna showed that if $G$ is a connected graph of order $n$ that is not one of the determined nine graphs, then $ι(G,C_4) \leq \frac{n}{5}$. In this paper, we prove that if $G \ncong C_4$ is a connected graph of size $m$, then $ι(G,C_4) \leq \frac{m+1}{6}$, and we characterize the graphs that attain the bound. Moreover, we conjecture that if $G \ncong C_k$ is a connected graph of size $m$, then $ι(G,C_k) \leq \frac{m+1}{k+2}$.

math.CO↗

arXiv2023

Relation-aware graph structure embedding with co-contrastive learning for drug-drug interaction prediction

Relation-aware graph structure embedding is promising for predicting multi-relational drug-drug interactions (DDIs). Typically, most existing methods begin by constructing a multi-relational DDI graph and then learning relation-aware graph structure embeddings (RaGSEs) of drugs from the DDI graph. Nevertheless, most existing approaches are usually limited in learning RaGSEs of new drugs, leading to serious over-fitting when the test DDIs involve such drugs. To alleviate this issue, we propose a novel DDI prediction method based on relation-aware graph structure embedding with co-contrastive learning, RaGSECo. The proposed RaGSECo constructs two heterogeneous drug graphs: a multi-relational DDI graph and a multi-attribute drug-drug similarity (DDS) graph. The two graphs are used respectively for learning and propagating the RaGSEs of drugs, aiming to ensure all drugs, including new ones, can possess effective RaGSEs. Additionally, we present a novel co-contrastive learning module to learn drug-pairs (DPs) representations. This mechanism learns DP representations from two distinct views (interaction and similarity views) and encourages these views to supervise each other collaboratively to obtain more discriminative DP representations. We evaluate the effectiveness of our RaGSECo on three different tasks using two real datasets. The experimental results demonstrate that RaGSECo outperforms existing state-of-the-art prediction methods.

cs.LG↗

arXiv2023

ChatAgri: Exploring Potentials of ChatGPT on Cross-linguistic Agricultural Text Classification

In the era of sustainable smart agriculture, a massive amount of agricultural news text is being posted on the Internet, in which massive agricultural knowledge has been accumulated. In this context, it is urgent to explore effective text classification techniques for users to access the required agricultural knowledge with high efficiency. Mainstream deep learning approaches employing fine-tuning strategies on pre-trained language models (PLMs), have demonstrated remarkable performance gains over the past few years. Nonetheless, these methods still face many drawbacks that are complex to solve, including: 1. Limited agricultural training data due to the expensive-cost and labour-intensive annotation; 2. Poor domain transferability, especially of cross-linguistic ability; 3. Complex and expensive large models deployment.Inspired by the extraordinary success brought by the recent ChatGPT (e.g. GPT-3.5, GPT-4), in this work, we systematically investigate and explore the capability and utilization of ChatGPT applying to the agricultural informatization field. ....(shown in article).... Code has been released on Github https://github.com/albert-jin/agricultural_textual_classification_ChatGPT.

cs.CL↗

arXiv2022

Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning

Knowledge Graph Question Answering (KGQA) aims to answer user-questions from a knowledge graph (KG) by identifying the reasoning relations between topic entity and answer. As a complex branch task of KGQA, multi-hop KGQA requires reasoning over the multi-hop relational chain preserved in KG to arrive at the right answer. Despite recent successes, the existing works on answering multi-hop complex questions still face the following challenges: i) The absence of an explicit relational chain order reflected in user-question stems from a misunderstanding of a user's intentions. ii) Incorrectly capturing relational types on weak supervision of which dataset lacks intermediate reasoning chain annotations due to expensive labeling cost. iii) Failing to consider implicit relations between the topic entity and the answer implied in structured KG because of limited neighborhoods size constraint in subgraph retrieval-based algorithms.To address these issues in multi-hop KGQA, we propose a novel model herein, namely Relational Chain based Embedded KGQA (Rce-KGQA), which simultaneously utilizes the explicit relational chain revealed in natural language question and the implicit relational chain stored in structured KG. Our extensive empirical study on three open-domain benchmarks proves that our method significantly outperforms the state-of-the-art counterparts like GraftNet, PullNet and EmbedKGQA. Comprehensive ablation experiments also verify the effectiveness of our method on the multi-hop KGQA task. We have made our model's source code available at github: https://github.com/albert-jin/Rce-KGQA.

cs.CL↗

arXiv2022

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompose this problem into two sub-problems: the visual representation and the sparse reward. To address them, a novel framework IAMMIR combining the self-supervised representation learning with the intrinsic motivation is presented. For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired. For sparse rewards, a new type of intrinsic reward is designed, the Momentum Memory Intrinsic Reward (MMIR). It utilizes the difference of the outputs from the current model (online network) and the historical model (target network) to present the agent's state familiarity. Our method is evaluated on the visual navigation task with sparse rewards in Vizdoom. Experiments demonstrate that our method achieves the state of the art performance in sample efficiency, at least 2 times faster than the existing methods reaching 100% success rate.

cs.AI↗

arXiv2017

A Resilient Image Matching Method with an Affine Invariant Feature Detector and Descriptor

Image feature matching is to seek, localize and identify the similarities across the images. The matched local features between different images can indicate the similarities of their content. Resilience of image feature matching to large view point changes is challenging for a lot of applications such as 3D object reconstruction, object recognition and navigation, etc, which need accurate and robust feature matching from quite different view points. In this paper we propose a novel image feature matching algorithm, integrating our previous proposed Affine Invariant Feature Detector (AIFD) and new proposed Affine Invariant Feature Descriptor (AIFDd). Both stages of this new proposed algorithm can provide sufficient resilience to view point changes. With systematic experiments, we can prove that the proposed method of feature detector and descriptor outperforms other state-of-the-art feature matching algorithms especially on view points robustness. It also performs well under other conditions such as the change of illumination, rotation and compression, etc.

cs.CV↗

arXiv2017

Feedback vertex number of Sierpiński-type graphs

The feedback vertex number $τ(G)$ of a graph $G$ is the minimum number of vertices that can be deleted from $G$ such that the resultant graph does not contain a cycle. We show that $τ(S_p^n)=p^{n-1}(p-2)$ for the Sierpiński graph $S_p^n$ with $p\geq 2$ and $n\geq 1$. The generalized Sierpiński triangle graph $\hat{S_p^n}$ is obtained by contracting all non-clique edges from the Sierpiński graph $S_p^{n+1}$. We prove that $τ(\hat{S}_3^n)=\frac {3^n+1} 2=\frac{|V(\hat{S}_3^n)|} 3$, and give an upper bound for $τ(\hat{S}_p^n)$ for the case when $p\geq 4$.

math.CO↗