arXiv subjects

Kai Sun

Publications and source records attributed to Kai Sun.

At least 19 recordsLinked to original sources

arXiv2026

From Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis

Designing power electronics converters traditionally requires intensive human expertise across topology sizing, commercial component selection, circuit simulation verification, and schematic drafting. While Large Language Models (LLMs) show promise in electronic design automation (EDA), applying standalone LLMs directly to board-level power electronics schematic synthesis suffers from severe engineering hallucinations, including inaccurate analytical sizing, fabricated or mismatched component part numbers, violated voltage derating margins, and broken topological connectivity. In this paper, we propose a Bounded Dual-Loop Automated Schematic Synthesis Framework that translates natural language specifications into verified, editable KiCad schematics and manufacturing deliverables. Our workflow integrates six stages across three functional columns: (1) requirement parsing and knowledge-driven power stage synthesis covering non-isolated (Buck, Boost) and isolated/resonant (Flyback, DAB, half-bridge LLC) topologies; (2) contract- and evidence-coordinated component selection grounded in distributor APIs and OEM datasheets, coupled with closed-loop ngspice transient verification and stress feedback; and (3) modular control hardware integration and multi-format deliverable generation featuring native KiCad netlist round-trip verification. End-to-end case studies on a 24-36V to 12V,2A Buck converter (29 positions, 83 verified terminals) and an isolated 48V to 24V, 0.5A, Dual-Active Bridge (DAB) converter (87 positions, 341 verified terminals), alongside comparative evaluations against a Vanilla LLM baseline, demonstrate that our framework improves component verification coverage from 22.2 to 98.6, nominal value consistency from 0 to 97.7, and SPICE simulation pass rates from 0 to 100.

cs.AI↗

arXiv2026

Label Ensemble Perspective for Reduced-Complexity Graph Node Classification under Label Noise

Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by \emph{label noise}, that is, a small amount of incorrectly labeled nodes can substantially misguide model training. Mainstream solutions define node classification with label noise (NCLN) as a reliable labeling task, often introducing node similarity with quadratic computational complexity to more accurately assess label reliability. To this end, in this paper, we introduce the Label Ensemble Graph Neural Network (LEGNN), a lower complexity method for robust GNNs training against label noise. LEGNN reframes NCLN as a label ensemble task, gathering informative multiple labels instead of constructing a single reliable label, avoiding high-complexity computations for reliability assessment. Specifically, LEGNN conducts a two-step process: bootstrapping neighboring contexts and robust learning with gathered multiple labels. In the former step, we apply random neighbor masks for each node and gather the predicted labels as a high-probability label set. This mitigates the impact of inaccurately labeled neighbors and diversifies the label set. In the latter step, we utilize a partial label learning based strategy to aggregate the high-probability label information for model training. Additionally, we symmetrically gather a low-probability label set to counteract potential noise from the high-probability label set. Extensive experiments on six datasets demonstrate that LEGNN achieves strong classification performance while maintaining computational efficiency. Moreover, it exhibits good scalability on datasets with over one hundred thousand nodes and one million edges.

cs.LG↗

arXiv2026

MemoProAgent: Toward Memory-Driven Proactive Assistance

As assistants move from reactive answering toward proactive intervention, memory changes role: it no longer only supplies the answer to a query, it determines whether and when to speak at all. Prior work in this setting hands the system the relevant fact in context; we study the regime that makes the problem hard, where the evidence justifying an intervention must be mined from a long-horizon personal memory. We introduce MemoProBench, a benchmark for memory-driven proactive assistance (MPA), pairing egocentric video with year-long, distractor-rich user memories (~618K tokens on average), human-verified trigger windows, and a protocol that scores content and timing jointly. Every baseline we evaluate performs poorly (at most 15%), including frontier models given summarized or retrieval-augmented memory. A controlled study explains why: with oracle evidence delivered inside the trigger window GPT-5.3-Chat reaches 96%; letting it choose the timing drops it to 38%, and replacing oracle evidence with retrieval drops it to 15%. Content and timing are separately necessary, and missing either is catastrophic. Guided by this, we build MemoProAgent with a plug-and-play harness that surfaces memory from a graph-organized store and gates it down to what is worth interrupting for, plus a lightweight RL stage that curbs early and repeated firing. Without any training, MemoProAgent lifts strict accuracy from below 10% to 37.5% on Qwen3.8-27B and 38% on GPT-5.3-Chat; RL post-training reaches 42.4%.

cs.CL↗

arXiv2026

Agentic Swarms Discover Enhanchment of Fractional Chern Insulator Gaps Beyond Ideal Quantum Geometry

Can artificial intelligence (AI) move beyond solving well-defined problems to contribute to open-ended discovery in fundamental physics? Could AI propose what to explore, identify unexpected phenomena, and uncover their mechanisms? We address this using MOSAIC (Multi-agent Open-ended Scientific Analysis and Investigation through Collaboration), a collaborative swarm of AI agents (Claude Opus 5.5), to tackle a longstanding bottleneck: the small energy gaps limiting the robustness of fractional topological order and the study of anyons at higher temperatures. Rather than prescribing a model, we ask frontier models (GPT-6 Astra) to propose a theoretical framework, which MOSAIC explores through diverse strategies and rapid exchange of ideas. This reveals a striking finding: although ideal quantum geometry is considered favorable for fractional states, departing from this limit can dramatically enhance their robustness, with many-body gaps more than an order of magnitude larger than in the ideal case. Without centralized coordination, the agents explored autonomously, combined findings across agents, and formed insights from individual runs, outperforming isolated agents with the same tools. AI-assisted theoretical analysis further develops simplified models with an analytical gap enhancement factor that is unbounded within the single-band approximation. Remarkably, AI identifies the real-space quantum metric, rather than the momentum-space one, as the key quantity governing the many-body gap, revealing how flat-band wavefunctions shape two-electron interactions and yielding an index computable from single-particle wavefunctions without many-body ED to guide gap optimization. Our study demonstrates how collaborative AI agents can integrate exploration, discovery of unexpected physics, and theoretical understanding, opening new possibilities for AI-driven research in fundamental physics.

cond-mat.str-el↗

arXiv2026

A Chiral Superlattice Route to Spin-Split Topological Antiferromagnetism

The interplay between chirality and magnetism is a profound topic, spanning particle physics, condensed matter, chemistry and origin of life. In this paper, we study this interplay in the new antiferromagnet (AFM) UOTe, and we report a chiral superlattice route to spin-split topological phenomena from collinear antiferromagnetism. Pristine UOTe is a collinear AFM without Berry curvature or spin-split bands. However, we identify the spontaneous formation of a chiral superlattice in UOTe, which can be viewed as frozen chiral phonons at finite wave vector. When electrons move through the chiral superlattice, their orbital Bloch wavefunction and quantum geometry are modulated by the strong chiral superlattice potential, generating large Berry curvature in the chiral superlattice, which we detect by the nonlinear Hall effect. At 150 K, the chiral superlattice induced Berry curvature couples to the collinear AFM order, generating a giant anomalous Hall angle ~0.14 abruptly near $T_N$ that is among the largest in bulk magnets. Moreover, our spin Hanle precession measurement shows that the chiral superlattice also generates spin-polarized current from the collinear AFM, a long-standing goal in spintronics. We shed light on the supermodulation formation mechanism based on chemical ion size and physical interlayer-intralayer energy competitions, using which we propose a design principle to discover similar bond-mismatch superlattices, providing a chiral superlattice pathway through real space engineering of quantum geometry.

cond-mat.mes-hall↗

arXiv2026

Three Machines Suffice for Local Hardening of Electromechanical Oscillations

The single-degree-of-freedom swing equation with sinusoidal coupling is locally softening: its oscillation frequency decreases with oscillation level near a stable equilibrium. Nonlinear modal interaction, however, can reverse this trend in multimachine systems. This letter gives a necessary-and-sufficient condition for strict leading-order local hardening, measured with respect to canonical action, in two symmetric three-machine operating-point families with equal or opposite power injections at the equal-inertia machines. An exact two-coordinate reduction expresses the condition in terms of a squared modal-frequency ratio and a dimensionless nonlinear coupling measure. The proof retains the induced mean shift and second harmonic and shows that the companion modal family remains locally softening. The criterion recovers both an equal-inertia hardening example and an exact large-inertia threshold. Coherent aggregation recovers the two-machine softening law, whereas the infinite-bus limit retains two dynamic rotor angles and permits hardening. An exact coherent-group extension preserves the selected periodic family, frequency, and canonical action for every finite machine count greater than two. Thus, three finite-inertia machines are the minimum permitting local hardening in the stated undamped, lossless classical model.

eess.SY↗

arXiv2026

When Should Agents Check External State? Budgeting Observations for Stored Intentions

Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition currently holds. Checking it may require web access, multi-step tool use, and paid calls. Existing systems decide when intentions require attention, but do not allocate the resulting observations under a shared budget. We introduce the first resource-allocation formulation for the external observations required by stored intentions under a shared episode budget. BudgetPM offers two policy variants that share a hard-budget executor. BudgetPM-Static uses a lightweight Logistic scorer to learn whether a check improves the current decision. BudgetPM-Sequential distills full-episode hindsight schedules into a lightweight policy that decides when to spend or reserve capacity using only pre-query information at deployment. We evaluate BudgetPM against two public memory-agent systems, five matched controls, and four hand-designed monitoring or budget-adaptation rules. Across two benchmarks and three backbones, BudgetPM-Static outperforms adapted Mem0 and PMA workflows. On PM-Bench, its Logistic scorer reaches competitive quality--cost operating points alongside higher-capacity scorers and retains 99.9--100\% of unconstrained quality with 42--54\% fewer observations. Under severe scarcity and the same hard caps, BudgetPM-Sequential exceeds the strongest tested natural monitoring schedule by 1.92--2.58 Set F1 points. It reaches the same Set F1 and on-time recall with 16--33\% fewer observations. Matched attribution, exact-cost analysis, and a fixed-budget load intervention link this gain to competition between present and future opportunities. These results yield a demand--capacity design rule: local gating works when capacity covers demand, while future-aware supervision adds value when observations compete across time.

cs.AI↗

arXiv2026

SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and membrane potentials. Existing post-training quantization (PTQ) methods provide them without retraining and, like those for ANNs, minimize numerical errors such as the mean squared error (MSE). In an SNN, however, a quantization error reaches later layers only through the spikes it flips. We find that errors of equal MSE can cause very different accuracy losses, whereas errors that flip the same fraction of spikes cause the same loss. We therefore propose SpikeQ, a spike-guided PTQ framework. For weights, we select the level of each weight by simulating the downstream neurons and minimizing their spike errors. For membrane potentials, most existing methods quantize the state after the reset, whereas neuromorphic chips compare the threshold with the membrane potential stored at a fixed bit width. We target this pre-fire quantization and build a reset-aware grid that places the threshold on a rounding boundary, so rounding never flips the spike at the current time step. We evaluate SpikeQ on seven benchmarks of image classification, semantic segmentation, and object detection. With 2-bit pre-fire membrane potentials, every existing grid collapses, whereas SpikeQ retains most of the full-precision accuracy. With both at 4 bits, the models stay within 2.59 points of full precision, shrink their memory footprint 7.8--7.9 times, and use 6.4--6.9 times less energy.

cs.NE↗

arXiv2026

PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models

Multimodal Retrieval-Augmented Generation (MM-RAG) augments visual question answering (VQA) with external knowledge, but many systems rely on modular pipelines that separate visual grounding, query construction, and answer generation. This separation can propagate errors from intermediate detections, masks, or captions into retrieval while adding latency and limiting coordination with ongoing reasoning. These limitations are especially consequential for egocentric images, where questions often concern small, off-center, or long-tail entities that global retrieval can overlook. We propose PixSearch, an end-to-end segmenting Large Multimodal Model (LMM) that unifies region-level visual grounding with retrieval-augmented reasoning. During autoregressive generation, PixSearch learns when to retrieve, how to route queries across text, whole-image, and region-level retrieval, and how to crop the target entity as a visual query using a jointly trained mask decoder. A two-stage supervised fine-tuning regimen with search-interleaved supervision teaches retrieval triggering, query selection, and evidence-grounded answer generation while preserving segmentation ability. On egocentric and entity-centric VQA benchmarks, PixSearch achieves an 18.3% relative accuracy gain on CRAG-MM over whole-image retrieval, with particularly strong gains on egocentric images, while remaining competitive on broader VQA and text-only QA tasks. It also reduces inference latency by 36.4% compared with a cached GroundedSAM-LLaVA pipeline.

cs.CV↗

arXiv2026

An Agentic AI System for Multi-Framework Communication Coding

Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensive, inconsistent, and difficult to scale. Existing approaches based on large language models typically rely on single-task models that lack adaptability, interpretability, and reliability, especially when applied across various communication frameworks and clinical domains. In this study, we developed a Multi-framework Structured Agentic AI system for Clinical Communication (MOSAIC), built on a LangGraph-based architecture that orchestrates four core agents, including a Plan Agent for codebook selection and workflow planning, an Update Agent for maintaining up-to-date retrieval databases, a set of Annotation Agents that applies codebook-guided retrieval-augmented generation (RAG) with dynamic few-shot prompting, and a Verification Agent that provides consistency checks and feedback. To evaluate performance, we compared MOSAIC outputs against gold-standard annotations created by trained human coders. We developed and evaluated MOSAIC using 26 gold standard annotated transcripts for training and 50 transcripts for testing, spanning rheumatology and OB/GYN domains. On the test set, MOSAIC achieved an overall F1 score of 0.928. Performance was highest in the Rheumatology subset (F1 = 0.962) and strongest for Patient Behavior (e.g., patients asking questions, expressing preferences, or showing assertiveness). Ablations revealed that MOSAIC outperforms baseline benchmarking.

cs.CL↗

arXiv2026

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

Despite rapid progress in automating scientific research, generating promising and well grounded research solutions remains a central challenge. We isolate research ideation as a standalone task and build our solution on the intuition that a challenge in one field can often be addressed by a mechanism that solved an analogous challenge in another. Accordingly, we introduce IdeaScientist, which decomposes ideation into gap finding, innovation, and report writing, and trains each role with reinforcement learning. These roles identify limitations in related work, draw solution intuitions from analogous problem settings, and develop those intuitions into complete research proposals. To facilitate discovery of insights across domains, we construct the Svalbard Idea Vault, a corpus of 2.77M decomposed research ideas for retrieval, training, and temporally controlled evaluation. Our evaluation restricts access to literature available before a cutoff date and assesses how closely proposed directions align with those later explored in 15K papers authored by human researchers. On Qwen3.6-27B, IdeaScientist outperforms the strongest open-source autoresearch baseline by 14.0%, driven mainly by gains in novelty. On this 27B open backbone, IdeaScientist even outperforms Claude Code SDK with Claude-4.8-Opus and Codex SDK with GPT-5.4, by up to 5.9%.

cs.CL↗

arXiv2026

Topological Fermi-polaron Polaritons with Electrically Invertible Topology

Topological polaritons provide a route to engineer optical Chern bands, but realizing large gaps or efficient electrical tunability remains challenging because time-reversal-symmetry breaking in semiconductor polariton systems is typically limited by weak Zeeman splittings. Here, we demonstrate a topological Bose-Fermi mixture --- Fermi-polaron polaritons ---where large gaps and electrically invertible topology emerge from the interplay of Fermi-polaron many-body interactions, photonic symmetry, and strong light--matter coupling. Using a gate-controlled monolayer transition-metal dichalcogenide integrated with a symmetry-engineered photonic crystal, we create Fermi-polaron polaritons with topological band structures. The direct coupling between band topology and gate-tunable many-body interactions provides a mechanism for amplified time-reversal-symmetry breaking beyond bare Zeeman splitting and enables electrical inversion of topological gaps, Berry curvature, and Chern numbers. These results establish an electrically reconfigurable platform for interaction-driven topological states and programmable topological photonics.

physics.optics↗

arXiv2026

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessing raw clips for every query becomes computationally prohibitive. Memory systems offer a scalable alternative by compacting videos into text representations, but often fail on practical benchmarks: either the memory does not preserve key evidence, or the retriever fails to locate relevant entries due to retrieval competition in growing search spaces. To address these challenges, we introduce MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader. Without training or query-time video access, MemLife improves over the strongest training-free baseline by 4.6--12.0% across four long-horizon benchmarks. To further improve memory quality, we propose MemOpt, a reinforcement learning framework that optimizes the memory writer to produce faithful, informative, and retrievable memories. MemOpt consistently improves MemLife by 2.7--5.0% across different video and question distributions, with gains that generalize across writer and reader backbones and memory systems.

cs.CV↗

arXiv2026

Identifiability Limits of Forced Oscillation Sources in Power Systems

Whether a forced-oscillation source can be uniquely localized depends jointly on the available measurements and the candidate intervention dictionary. This paper considers a single unknown constant-amplitude sinusoid acting through one of physical intervention channels. Because its amplitude and phase are unknown, each candidate harmonic response is observable only up to a nonzero complex scalar and therefore defines a projective ray in measurement space. A necessary-and-sufficient condition is derived for exact localization, together with a weighted nearest-ray locator and a deterministic recovery bound based on projective separation. The paper proposes a framework distinguishing four mechanisms of source localization failure: mechanism mismatch, feature-projection loss, structural nonidentifiability, and poor conditioning or model error. Numerical studies on the Kundur two-area system illustrate well-separated recovery, mechanism-dependent terminal decisions, measurement-induced ambiguity, and the sensitivity of nearly collinear signatures to model perturbations. Then, IEEE--NASPI Contest models are used to further examine broad candidate dictionaries, terminal-feature source coverage, and ambiguity removal through measurement augmentation. The results show that correctly locating the source bus does not by itself establish unique identification of the internal forcing channel or robustness to measurement and model uncertainty.

eess.SY↗

arXiv2026

Nonlinear Participation Factor-based Power System Model Reduction Addressing Near-Resonance Conditions

This paper proposes an adaptive model reduction approach based on nonlinear participation factors (NPFs) which determines the most effective selection of unimportant generators in a power system to be linearized to accelerate time-domain simulation for the entire system. The method enables a dynamic transition between the full-order model, and a hybrid reduced model. It uses modal energies to rank system modes under contingencies, and computes NPFs for highly energized modes based on Normal Form theory. To accelerate the computation of NPFs and make it achievable online, a tensor contraction technique is introduced. The proposed approach is tested on a 48-machine, 140-bus NPCC system using both partitioned and unpartitioned strategies. It demonstrates significant simulation speedup while preserving better accuracy than a linear participation factor-based method if the nonlinear behaviors of the system cannot be ignored, especially when a near-resonance condition is presented.

eess.SY↗

arXiv2026

Reduced-Order Model Characterization of Nonlinear Sustained Oscillations

Nonlinear sustained oscillations involving inverter-based resources can happen when device and network interactions produce an attracting limit cycle around an unstable equilibrium. A damping controller must then describe nonlinear dynamics over the region between the two invariant sets, where a local equilibrium linearization can be insufficient. In this paper, a controlled phase--isostable model is first developed on a two-dimensional invariant manifold connecting the equilibrium and the limit cycle. Dynamics on this surface are represented by phase and isostable coordinates, while physical states and control inputs are related to these coordinates through nonlinear reconstruction and response functions. The required functions are computed from connecting trajectories and periodic-orbit data. A control strategy is then designed to provide extra damping while limiting phase distortion. Case studies on a two-area system and an IEEE 39-bus system demonstrate more effective oscillation damping than the compared equilibrium-linearized designs under the same conditions.

eess.SY↗

arXiv2026

Isostable-Based Nonlinear Model Reduction for Power System Oscillations

Power systems are often represented by high-dimensional dynamic models, making nonlinear control design computationally expensive and limiting its practical application. Oscillation analysis and damping control therefore commonly rely on linearized models, which do not capture the nonlinear oscillatory behavior induced by large disturbances. This paper proposes an isostable-based model reduction method for nonlinear modal analysis of power systems. The method constructs an invariant manifold associated with a selected oscillatory mode and uses isostable coordinates to describe the mode with only two real state variables. The isostable formulation gives linear autonomous modal dynamics, with nonlinear state reconstruction and input response computed on the modal manifold. An optimal damping control problem is then formulated directly in the reduced coordinates. Case studies on the IEEE 39-bus system demonstrate the accuracy of the proposed model in describing nonlinear oscillations and show improved damping compared with control designed using a linear reduced model.

eess.SY↗

arXiv2026

N-Body Dynamics as a Mechanism for Mean Motion Resonance Formation in the Post-Gas Era

Mean motion resonances (MMRs) are traditionally thought to form during the gas-rich phase of protoplanetary disks via disk-driven migration. Whether MMRs can form solely through collisional damping after disk dispersal has not been systematically investigated. To study MMR formation in the post-gas-disk era, we perform a large suite of N-body simulations, each containing 10,000 planetesimals around an M-dwarf star and evolving over 10 Myr. We compare two groups of simulations that differ only in their initial mass distributions. Each group consists of 10 runs with statistically identical initial planetesimal orbital distributions, generated using different random seeds. One group adopts a uniform planetesimal mass distribution, whereas the other features a bimodal distribution with massive embryos embedded in a swarm of smaller planetesimals. At 1 Myr, 40% of systems (8/20) exhibit near-resonant period ratios, but this fraction drops to 25% (5/20) by 10 Myr as higher-order commensurabilities dissolve. Resonant-angle tracking shows that all persistent systems have circulating resonant angles at 10 Myr, although one system undergoes a transient libration phase between about 2 and 7 Myr before returning to circulation. These results demonstrate that collisional merging can drive MMR formation even without a gas disk, although in this scenario near-resonant configurations are strongly favored over true resonances. Furthermore, this mechanism produces similar MMR fractions in both groups, suggesting that MMR formation is insensitive to the initial mass distribution, although the latter may modulate the formation pathway to a limited extent.

astro-ph.EP↗