arXiv subjects

Jiaxin Pan

Publications and source records attributed to Jiaxin Pan.

18 recordsLinked to original sources

arXiv2026

Weighted Ces\`aro type operators on the weighted Bergman spaces in the unit ball

In this paper, we study weighted Ces\`aro type operators \[ \mathcal C_{\mu,\beta}^{\xi}:A_{\alpha}^{p}(\mathbb B_n) \longrightarrow A_{\alpha}^{q}(\mathbb B_n) \] induced by measures on $[0,1)$, and obtain boundedness characterizations throughout the range $0<p,q\le\infty$. We first extend the corresponding results on the unit disk to the unit ball in the range $1\le p\le q<\infty$. By means of atomic decomposition, we further treat the case $0<p<1$ and $p\le q<\infty$, thereby obtaining a complete characterization for $0<p\le q<\infty$. The latter result is new even in one dimension. For the range $0<q<p\le\infty$, we characterize the boundedness in terms of an integral condition involving the tail function of the inducing measure. This result is also new even on the unit disk. Finally, we characterize the boundedness of the corresponding operators when the target space is $H^\infty(\mathbb B_n)$.

math.FA↗

arXiv2026

FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs

Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are already known at training time, restricting each model to a single graph and vocabulary. We propose FITTER, the first fully-inductive structural model for temporal knowledge graph link prediction that supports cross-domain transfer: the inference graph may contain entirely unseen entities, relation names, and timestamps drawn from a different domain. FITTER represents each predicate by its interaction patterns with others and time through encodings of relative rather than absolute ordering; message-passing fuses local and global temporal context to produce vocabulary-agnostic embeddings. We prove the temporal encoding is time-shift invariant and evaluate FITTER on cross-domain, cross-graph transfer over six temporal knowledge graph benchmarks of diverse domains, granularities, and time spans. FITTER consistently outperforms inductive baselines without retraining, indicating that vocabulary-agnostic structural learning is a viable foundation for inference over the heterogeneous knowledge graphs of the Semantic Web.

cs.AI↗

arXiv2026

GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations. Extending this transferability to temporal knowledge graphs (TKGs) remains challenging: existing temporal models tie their parameters to dataset-specific entities, relations, or timestamps and are not designed to transfer to TKGs with disjoint vocabularies. We propose GRATE (Gated Rotary Attention for Temporal Encoding), an entity-side message function that adds no learnable parameters and encodes time through relative time differences by rotating each edge message according to its time gap to the query and applying a query-conditioned gate to select temporally relevant signals. GRATE integrates into NBFNet-style KG foundation models while preserving structural transferability. Existing TKG benchmarks evaluate within shared train/test vocabularies and cannot directly test cross-dataset temporal transfer; we therefore construct GDELTIndT and WIKIIndT, inductive transfer benchmark suites with disjoint entities, relations, and timestamps spanning both interpolation and extrapolation. Across these benchmarks and held-out forecasting datasets, a single jointly pretrained GRATE checkpoint improves over the static base model in most settings.

cs.AI↗

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2025

Coupled-wire construction of non-Abelian higher-order topological phases

Non-Abelian topological charges (NATCs), characterized by their noncommutative algebra, offer a framework for describing multigap topological phases beyond conventional Abelian invariants. While higher-order topological phases (HOTPs) host boundary states at corners or hinges, their characterization has largely relied on Abelian invariants such as winding and Chern numbers. Here, we propose a coupled-wire scheme of constructing non-Abelian HOTPs and analyze a non-Abelian second-order topological insulator as its minimal model. The resulting Hamiltonian supports hybridized corner modes, protected by parity-time-reversal plus sublattice symmetries and described by a topological vector that unites a non-Abelian quaternion charge with an Abelian winding number. Corner states emerge only when both invariants are nontrivial, whereas weak topological edge states of non-Abelian origins arise when the quaternion charge is nontrivial, enriching the bulk-edge-corner correspondence. The system further exhibits both non-Abelian and Abelian topological phase transitions, providing a unified platform that bridges these two distinct topological classes. Our work extends the understanding of HOTPs into non-Abelian regimes and suggests feasible experimental realizations in synthetic quantum systems, such as photonic or acoustic metamaterials.

cond-mat.mes-hall↗

arXiv2025

Floquet non-Abelian topological charges and edge states

Non-Abelian topological insulators are characterized by matrix-valued, non-commuting topological charges with regard to more than one energy gap. Their descriptions go beyond the conventional topological band theory, in which an additive integer is endowed separately with each (degenerate group of) energy band(s). In this work, we reveal that Floquet (time-periodic) driving could not only enrich the topology and phase transitions of non-Abelian topological matter, but also induce bulk-edge correspondence unique to nonequilibrium setups. Using a one-dimensional (1D), three-band model as an illustrative example, we demonstrate that Floquet driving could reshuffle the phase diagram of the non-driven system, yielding both gapped and gapless Floquet band structures with non-Abelian topological charges. Moreover, by dynamically tuning the anomalous Floquet $π$-quasienergy gap, non-Abelian topological transitions inaccessible to static systems could arise, leading to much more complicated relations between non-Abelian topological charges and Floquet edge states. These discoveries put forth the periodic driving as a powerful scheme of engineering non-Abelian topological phases (NATPs) and incubating unique non-Abelian band topology beyond equilibrium.

cond-mat.mes-hall↗

arXiv2025

Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning

Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods typically use snapshot graphs to encode temporal evolution. We introduce a full-history graph that instantiates one node for every entity at every time step and separates two edge sets: (i) intra-time-step edges that capture relations within a single frame and (ii) inter-time-step edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-time-step edges, a multi-head temporal-attention module attends over an entity's inter-time-step history, and a fusion module combines the two messages after every layer. Evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6\% (vs. 74.1\%) and raising Elliptic++ illicit-class F1 to 88.1\% (vs. 60.4\%). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.

cs.AI↗

arXiv2025

Floquet Möbius topological insulators

Möbius topological insulators have dispersive edge bands with Möbius twists in momentum space, which are protected by the combination of chiral and $Z_2$-projective translational symmetries. In this work, we reveal a unique type of Möbius topological insulator, whose edge bands could twist around the quasienergy $π$ of a periodically driven system and are thus of Floquet origin. By applying time-periodic quenches to an experimentally realized Möbius insulator model, we obtain interconnected Möbius edge bands around zero and $π$ quasienergies, which can coexist with a gapped or gapless bulk. These Möbius bands are topologically characterized by a pair of generalized winding numbers, which are integer-quantized due to an emergent chiral symmetry at a high-symmetry point in momentum space. Numerical investigations of the quasienergy and entanglement spectra provide consistent evidence for the presence of such Möbius topological phases. A protocol based on the adiabatic switching of edge-band populations is further introduced to dynamically characterize the topology of Floquet Möbius edge bands. Our findings thus extend the scope of Möbius topological phases to nonequilibrium settings and unveil a unique class of Möbius-twisted topological edge states without static counterparts.

cond-mat.mes-hall↗

arXiv2025

Towards Foundation Model on Temporal Knowledge Graph Reasoning

Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t). Existing Temporal Knowledge Graph Embedding (TKGE) models perform link prediction tasks in transductive or semi-inductive settings, which means the entities, relations, and temporal information in the test graph are fully or partially observed during training. Such reliance on seen elements during inference limits the models' ability to transfer to new domains and generalize to real-world scenarios. A central limitation is the difficulty in learning representations for entities, relations, and timestamps that are transferable and not tied to dataset-specific vocabularies. To overcome these limitations, we introduce the first fully-inductive approach to temporal knowledge graph link prediction. Our model employs sinusoidal positional encodings to capture fine-grained temporal patterns and generates adaptive entity and relation representations using message passing conditioned on both local and global temporal contexts. Our model design is agnostic to temporal granularity and time span, effectively addressing temporal discrepancies across TKGs and facilitating time-aware structural information transfer. As a pretrained, scalable, and transferable model, POSTRA demonstrates strong zero-shot performance on unseen temporal knowledge graphs, effectively generalizing to novel entities, relations, and timestamps. Extensive theoretical analysis and empirical results show that a single pretrained model can improve zero-shot performance on various inductive temporal reasoning scenarios, marking a significant step toward a foundation model for temporal KGs.

cs.AI↗

arXiv2025

Gapless higher-order topology and corner states in Floquet systems

Higher-order topological phases (HOTPs) possess localized and symmetry-protected eigenmodes at corners and along hinges in two and three dimensional lattices. The numbers of these topological boundary modes will undergo quantized changes at the critical points between different HOTPs. In this work, we reveal unique higher-order topology induced by time-periodic driving at the critical points of topological phase transitions, which has no equilibrium counterparts and also goes beyond the description of gapped topological matter. Using an alternately coupled Creutz ladder and its Floquet-driven descendants as illustrative examples, we analytically characterize and numerically demonstrate the zero and $π$ corner modes that could emerge at the critical points between different Floquet HOTPs. Moreover, we propose a unified scheme of bulk-corner correspondence for both gapless and gapped Floquet HOTPs protected by chiral symmetry in two dimensions. Our work reveals the possibility of corner modes surviving topological transitions in Floquet systems and initializes the study of higher-order Floquet topology at quantum criticality.

quant-ph↗

arXiv2024

Enriching Ontologies with Disjointness Axioms using Large Language Models

Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this study, we explore the potential of Large Language Models (LLMs) to enrich ontologies by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs, using prompt engineering to elicit this knowledge for classifying ontological disjointness. We validate our methodology on the DBpedia ontology, focusing on open-source LLMs. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjoint class relationships, thus streamlining the process of ontology completion without extensive manual input. For comprehensive disjointness enrichment, we propose a process that takes logical relationships between disjointness and subclass statements into account in order to maintain satisfiability and reduce the number of calls to the LLM. This work provides a foundation for future applications of LLMs in automated ontology enhancement and offers insights into optimizing LLM performance through strategic prompt design. Our code is publicly available on GitHub at https://github.com/n28div/llm-disjointness.

cs.AI↗

arXiv2023

HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces

Temporal knowledge graphs represent temporal facts $(s,p,o,τ)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $τ$, where $τ$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.

cs.AI↗

arXiv2023

Robust Autonomous Vehicle Pursuit without Expert Steering Labels

In this work, we present a learning method for lateral and longitudinal motion control of an ego-vehicle for vehicle pursuit. The car being controlled does not have a pre-defined route, rather it reactively adapts to follow a target vehicle while maintaining a safety distance. To train our model, we do not rely on steering labels recorded from an expert driver but effectively leverage a classical controller as an offline label generation tool. In addition, we account for the errors in the predicted control values, which can lead to a loss of tracking and catastrophic crashes of the controlled vehicle. To this end, we propose an effective data augmentation approach, which allows to train a network capable of handling different views of the target vehicle. During the pursuit, the target vehicle is firstly localized using a Convolutional Neural Network. The network takes a single RGB image along with cars' velocities and estimates the target vehicle's pose with respect to the ego-vehicle. This information is then fed to a Multi-Layer Perceptron, which regresses the control commands for the ego-vehicle, namely throttle and steering angle. We extensively validate our approach using the CARLA simulator on a wide range of terrains. Our method demonstrates real-time performance and robustness to different scenarios including unseen trajectories and high route completion. The project page containing code and multimedia can be publicly accessed here: https://changyaozhou.github.io/Autonomous-Vehicle-Pursuit/.

cs.RO↗

arXiv2021

Mention-centered Graph Neural Network for Document-level Relation Extraction

Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches either leverage syntactic trees to construct document-level graphs or aggregate inference information from different sentences. In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. Adopting aggressive linking strategy, intermediate relations are reasoned on the document-level graphs by mention convolution. We further notice the generalization problem of NA instances, which is caused by incomplete annotation and worsened by fully-connected mention pairs. An improved ranking loss is proposed to attend this problem. Experiments show the connections between different mentions are crucial to document-level relation extraction, which enables the model to extract more meaningful higher-level compositional relations.

cs.CL↗

arXiv2020

RDSGAN: Rank-based Distant Supervision Relation Extraction with Generative Adversarial Framework

Distant supervision has been widely used for relation extraction but suffers from noise labeling problem. Neural network models are proposed to denoise with attention mechanism but cannot eliminate noisy data due to its non-zero weights. Hard decision is proposed to remove wrongly-labeled instances from the positive set though causes loss of useful information contained in removed instances. In this paper, we propose a novel generative neural framework named RDSGAN (Rank-based Distant Supervision GAN) which automatically generates valid instances for distant supervision relation extraction. Our framework combines soft attention and hard decision to learn the distribution of true positive instances via adversarial training and selects valid instances conforming to the distribution via rank-based distant supervision, which addresses the false positive problem. Experimental results show the superiority of our framework over strong baselines.

cs.CL↗

arXiv2020

Non-Hermitian Floquet second order topological insulators in periodically quenched lattices

Higher-order topological phases are characterized by protected states localized at the corners or hinges of the system. By applying time-periodic quenches to a two-dimensional lattice with balanced gain and loss, we obtain a rich variety of non-Hermitian Floquet second order topological insulating phases. Each of the phases is characterized by a pair of integer topological invariants, which predict the numbers of Floquet corner modes at zero and $π$ quasienergies. We establish the topological phase diagram of the model, and find a series of non-Hermiticity induced transitions between different Floquet second order topological phases. We further generalize the mean chiral displacement to two-dimensional non-Hermitian systems, and use it to extract the topological invariants of our model dynamically. This work thus extend the study of higher-order topological matter to more generic nonequilibrium settings, in which the interplay between Floquet engineering and non-Hermiticity yields fascinating new phases.

cond-mat.mes-hall↗

arXiv2020

Non-Hermitian Floquet topological phases in the double-kicked rotor

Dynamical kicking systems possess rich topological structures. In this work, we study Floquet states of matter in a non-Hermitian extension of double kicked rotor model. Under the on-resonance condition, we find various non-Hermitian Floquet topological phases, with each being characterized by a pair of topological winding numbers. A generalized mean chiral displacement is introduced to detect these winding numbers dynamically in two symmetric time frames. Furthermore, by mapping the system to a periodically quenched lattice model, we obtain the topological edge states and unravel the bulk-edge correspondence of the non-Hermitian double kicked rotor. These results uncover the richness of Floquet topological states in non-Hermitian dynamical kicking systems.

quant-ph↗

arXiv2019

Coupled-wire construction of static and Floquet second-order topological insulators

Second-order topological insulators (SOTI) exhibit protected gapless boundary states at their hinges or corners. In this paper, we propose a generic means to construct SOTIs in static and Floquet systems by coupling one-dimensional topological insulator wires along a second dimension through dimerized hopping amplitudes. The Hamiltonian of such SOTIs admits a Kronecker sum structure, making it possible for obtaining its features by analyzing two constituent one-dimensional lattice Hamiltonians defined separately in two orthogonal dimensions. The resulting topological corner states do not rely on any delicate spatial symmetries, but are solely protected by the chiral symmetry of the system. We further utilize our idea to construct Floquet SOTIs, whose number of topological corner states is arbitrarily tunable via changing the hopping amplitudes of the system. Finally, we propose to detect the topological invariants of static and Floquet SOTIs constructed following our approach in experiments by measuring the mean chiral displacements of wavepackets.

cond-mat.mes-hall↗