arXiv subjects

Bowen Zhu

Publications and source records attributed to Bowen Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Development of A Novel Compton Camera for MeV Gamma-Ray Measurement in Space

The astrophysical gamma rays in the MeV energy region have not yet been well-explored due to the limitation of detection technology in the past decades, and the famous gamma-ray "MeV gap" exists. Opening the window of MeV gamma-ray is not only critical for the gamma astronomy but also essential for rich frontier researches in astro-particle physics, such as detecting light dark matter, probing the primordial black hole and better understanding of nucleosynthesis. As a pilot experiment of the project for dark matter detection in space at Shanghai Jiao Tong University, a three-layer Compton camera with the energy resolution better than 4% and position resolution of ~2 mm is developed utilizing the novel scintillators. Here we show the design, detailed calibration and validation results of the novel Compton camera, and demonstrate its good ability of MeV gamma-ray source imaging for the upcoming in-orbit mission.

hep-ex↗

arXiv2026

MegaMem: A Retrieval Solution for Ultra-Large Context Windows

Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge is to keep hundreds of millions of tokens searchable while passing only bounded source evidence to the answer model. We introduce MegaMem, a source-resolved dual-view retrieval system that separates semantic access from generation evidence. Distilled records and detailed evidence are searched with original and transformed queries; every distilled hit resolves to an immutable source ID before reciprocal-rank fusion, deduplication, and cross-encoder reranking; and only the highest-ranked detailed evidence within a fixed budget supports generation. Post-answer attribution then identifies which loaded sources support the fixed answer. We evaluate MegaMem on EnterpriseRAG-Bench, which contains more than 500,000 heterogeneous enterprise documents and approximately 650M tokens. MegaMem improves Overall from 68.22 to 82.26 and reaches 86.50 Correctness. These results show that MegaMem supports ultra-large persistent memory while preserving strong answer accuracy under a bounded generation context. By separating searchable memory scale from answer-context size, MegaMem provides a practical path toward accurate retrieval over memories ranging from hundreds of millions to one billion tokens. Our code is available at https://github.com/ xfab-xinyuansong/MegaMem.git.

cs.AI↗

arXiv2026

MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data

Enterprise repositories are large, heteroge- neous, and continuously updated, making re- trieval difficult when efficient access, source- faithful evidence, and cross-query adaptation must be supported together. Enterprise mem- ory extends retrieval beyond the model con- text, but existing systems do not jointly address collection-specific hierarchy construction, low- cost routing, detailed evidence loading, and workload-aware memory updates at this scale. We introduce MEMONDEMAND, short for On- Demand Memory, a memory management sys- tem with three coordinated mechanisms: a dy- namic multi-level hierarchy that determines the abstraction structure and depth for each col- lection, dual memory at every hierarchy level that separates distilled routing from detailed evidence, and on-demand memory promotion that updates node priority under a bounded active-state budget. On EnterpriseRAG-Bench, MEMONDEMAND outperforms the strongest published LB#1 result at every evaluated scale from 10M tokens through the complete 618M- token collection, with gains of 12.23% at 10M and 4.66% at 618M. Results on FinanceBench, HotpotQA, and FRAMES further show strong performance across financial, multi-hop, and fact-retrieval settings. Together, these results establish MEMONDEMAND as an accurate, ef- ficient, and scalable memory solution for very large enterprise repositories across data scales, domains, and evidence requirements. Our code is available at https://github.com/ xfab-xinyuansong/MemOnDemand.git.

cs.AI↗

arXiv2026

Integrated 3D fully kinetic simulation of field-reversed-configuration formation with embedded coils

We present an integrated, three-dimensional, fully kinetic particle-in-cell simulation of field-reversed-configuration (FRC) formation at the device scale. To our knowledge, this is the first fully kinetic model of whole-device FRC formation. The model embeds the drive coils directly inside the computational domain as physical conductors, advancing them self-consistently with the plasma on a single explicit grid and coupling them in closed loop to an external circuit. We apply this unified framework to the Yingguang-1 $θ$-pinch. Unlike the magnetohydrodynamic and hybrid models used previously, our framework advances the electrons as kinetic particles rather than a fluid, capturing fast magnetic reconnection and electron heating from first principles. The simulation reproduces the complete formation sequence, from reversed-bias lock-in through reconnection to the emergence of a closed-flux FRC, reaching a peak ion density ${\sim}2.2\times10^{22}\,\mathrm{m^{-3}}$ consistent with experiment. The compressed core is electron-dominated, with $T_e\approx1.7\,$keV exceeding $T_i\approx1.2\,$keV, and is pinched to a separatrix radius $r_s\approx1\,$cm, several times below the equilibrium-inferred value, indicating that the plasma never relaxes to a pressure-balanced equilibrium within the microsecond pulse. The model further reproduces a non-axisymmetric, four-fold ($m=4$) deformation of the compressed column, matching the square cross-section recorded by the experiment's end-on framing camera, a feature beyond the reach of the two-dimensional models previously applied to this device. Running on modest GPU hardware, this work brings integrated, first-principles kinetic modeling of fusion-relevant FRCs within reach.

physics.plasm-ph↗

arXiv2026

A Lightweight MPC Bidding Framework for Brand Auction Ads

Brand advertising plays a critical role in building long-term consumer awareness and loyalty, making it a key objective for advertisers across digital platforms. Although real-time bidding has been extensively studied, there is limited literature on algorithms specifically tailored for brand auction ads that fully leverage their unique characteristics. In this paper, we propose a lightweight Model Predictive Control (MPC) framework designed for brand advertising campaigns, exploiting the inherent attributes of brand ads -- such as stable user engagement patterns and fast feedback loops -- to simplify modeling and improve efficiency. Our approach utilizes online isotonic regression to construct monotonic bid-to-spend and bid-to-conversion models directly from streaming data, eliminating the need for complex machine learning models. The algorithm operates fully online with low computational overhead, making it highly practical for real-world deployment. Simulation results demonstrate that our approach significantly improves spend efficiency and cost control compared to baseline strategies, providing a scalable and easily implementable solution for modern brand advertising platforms.

cs.GT↗

arXiv2026

Otters++: A Time-to-first-spike Based Energy Efficient Optical Spiking Transformer

Spiking neural networks (SNNs) are promising for energy-efficient inference, and time-to-first-spike (TTFS) coding is especially attractive because each neuron fires at most once. In practice, however, this benefit is often reduced by the cost of computing a temporal decay term and multiplying it by the synaptic weight. We address this issue by turning a physical hardware "bug," the natural signal decay in optoelectronic devices, into the main computation of TTFS, named Otters++. Specifically, we use the measured decay of a custom In$_2$O$_3$ optoelectronic synapse to directly realize the TTFS temporal term, removing the need for explicit digital decay computation. To scale this idea to Transformer models, we establish a layer-wise functional equivalence between the Otters++ and a quantized neural network (QNN), and develop a hybrid training method that uses device-faithful SNN computation in the forward pass and QNN straight-through gradients through the equivalent QNN path in the backward pass, together with model distillation. This avoids differentiation through discrete first-spike events and reduces the over-sparsity problem in direct TTFS-SNN training. We further make training aware of measured device noise by sampling run-to-run variation, and refine the system-level energy model by accounting for device sharing and multi-hop communication. On GLUE dataset, Otters++ improves the average score to 84.17\% while maintaining a clear energy advantage over prior spiking Transformer baselines. These results show that physically grounded TTFS computing can be efficient, trainable, and robust under realistic hardware effects.

cs.AI↗

arXiv2026

Multimodal Representation Learning Conditioned on Semantic Relations

Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While effective for general-purpose representation learning, such models typically produce a single embedding per sample that is reused across different semantic relations and contexts. However, in many real-world applications, relevance between samples is inherently relation-dependent, with different semantic relations emphasizing different aspects of multimodal data. In this work, we propose Relation-Conditioned Multimodal Learning (RCML), a framework that treats semantic relations as explicit conditions of multimodal representation learning. Rather than producing relation-agnostic embeddings, RCML learns representations conditioned on natural-language relation descriptions, allowing the same sample to be represented differently under different relational contexts. The framework constructs relation-aware training pairs, introduces a relation-conditioned module to adapt embeddings to relation semantics, and employs a unified contrastive objective to jointly model cross-modal alignment and relation-induced inter-sample structure. Experiments on multiple datasets show that RCML consistently outperforms strong baselines on retrieval and classification tasks in zero-shot, fine-tuned, and out-of-domain settings, highlighting the effectiveness of leveraging semantic relations to guide multimodal representation learning.

cs.LG↗

arXiv2026

SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents

Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and cost: injecting coarse skills can introduce irrelevant or misleading context, while rewriting entire skills is expensive and often unnecessary. We propose SkillLens, a hierarchical skill-evolution framework that organizes skills into a four-layer graph of policies, strategies, procedures, and primitives, and retrieves them at mixed granularity. Given a task, SkillLens first retrieves semantically relevant skill seeds, expands them through degree-corrected random walk over the skill graph, and then uses a verifier to decide whether each visited unit should be accepted, decomposed, rewritten, or skipped. This enables the agent to reuse compatible subskills directly while adapting only locally mismatched components. To improve the system over time, SkillLens further refines multi-granularity skills and verifier in order to improve its routing decisions. We provide theoretical analysis showing that mixed-granularity adaptation incurs sublinear cost under sparse mismatch assumptions and that the evolutionary update rule monotonically improves the validation objective until a local optimum. Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill-based baselines, achieving up to a 6.31 percentage-point Acc@1 gain for bug localization and raising agent success rate from 45.00% to 51.31%.

cs.AI↗

arXiv2026

LARGER: Lexically Anchored Repository Graph Exploration and Retrieval

Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch generation to test writing and codebase question answering. Existing agents navigate repositories primarily through lexical search, often missing structural relations such as imports, call chains, type hierarchies, and code-test links. Graph-based retrieval can recover such dependencies, but existing approaches often require separate graph tools or traversal stages that fragment the agent's interaction loop. We formalize repository context localization as Lexically Anchored Structural Localization, where success depends on turning lexical matches into high-precision structural entry points and exposing the most useful confidence-filtered local neighborhoods within the agent's existing search loop. We introduce LARGER (Lexically Anchored Repository Graph Exploration and Retrieval), a lexically anchored active-set retrieval framework that starts from lexical matches, aligns them to graph anchors, and performs confidence-filtered local expansion within the agent's existing search loop. LARGER integrates directly into existing CLI coding agents without requiring external graph databases or specialized graph interfaces. Across four benchmarks spanning localization, test generation, and codebase understanding, LARGER improves file-level Acc@5 on LocBench by +13.9 points with tuned hyperparameters and still gains +11.8 points with fixed hyperparameters over the strongest baseline, while delivering consistent gains on MuLocBench, SWE-Atlas Test Writing, and SWE-Atlas Codebase QA.

cs.IR↗

arXiv2026

GEMM-GS: Accelerating 3D Gaussian Splatting on Tensor Cores with GEMM-Compatible Blending

Neural Radiance Fields (NeRF) enables 3D scene reconstruction from several 2D images but incurs high rendering latency via its point-sampling design. 3D Gaussian Splatting (3DGS) improves on NeRF with explicit scene representation and an optimized pipeline yet still fails to meet practical real-time demands. Existing acceleration works overlook the evolving Tensor Cores of modern GPUs because 3DGS pipeline lacks General Matrix Multiplication (GEMM) operations. This paper proposes GEMM-GS, an acceleration approach utilizing tensor cores on GPUs via GEMM-friendly blending transformation. It equivalently reformulates the 3DGS blending process into a GEMM-compatible form to utilize Tensor Cores. A high-performance CUDA kernel is designed, integrating a three-stage double-buffered pipeline that overlaps computation and memory access. Extensive experiments show that GEMM-GS achieves $1.42\times$ speedup over vanilla 3DGS and provides an additional $1.47\times$ speedup on average when combining with existing acceleration approaches. Code is released at https://github.com/shieldforever/GEMM-GS.

cs.AR↗

arXiv2026

Scalable Solar-Blind Imaging Enabled by Single-Crystalline Beta-Ga2O3 Membranes on Silicon Backplanes

Ultrawide-bandgap semiconductors are attractive for solar-blind ultraviolet (UV) detection owing to their intrinsically low noise and high spectral selectivity, yet their deployment in large-area, high-density electronic imaging systems remains limited by a fundamental trade-off between material quality, device speed, and compatibility with high-density planar silicon readout circuits. Here, we report a membrane-enabled integration platform based on transferable single-crystalline beta-Ga2O3 that overcomes these constraints at the system level. By exploiting the weak interplanar bonding of beta-Ga2O3 (100) plane, we obtain wafer-scale freestanding single-crystalline membranes that enable vertically integrated photodiodes with sub-microsecond, non-persistent photoresponse and high UV-visible rejection. Crucially, we introduce a stitching-based membrane assembly strategy that decouples array resolution from the size of the source single-crystalline substrate, allowing high-resolution photodetector arrays to be integrated onto silicon thin-film-transistor backplanes. The modular assembled active-matrix UV imaging arrays exhibit uniform solar-blind response without image lag, in stark contrast to arrays based on amorphous or polycrystalline films. Beyond beta-Ga2O3, this membrane-enabled and stitching-based modular integration strategy provides a general route toward high-speed, high-resolution electronic imaging systems using transferable single-crystalline semiconductors.

cond-mat.mtrl-sci↗

arXiv2025

Flexible mm-Wave Frequency and High-Speed Arbitrary IQ Signal Synthesis by a Photonic System on Chip

Photonics-assisted millimeter-wave bands and terahertz signal generation offer significant advantages over traditional electronic methods by leveraging the inherent benefits of optical components, including broad bandwidth, low power consumption, and minimal insertion loss. This work utilizes a silicon photonic chip in conjunction with a reconfigurable optical frequency comb to demonstrate the synthesis of signals in the millimeter-wave range. The implemented photonic system performs on-chip filtering and modulation, producing high-bandwidth single frequency, multi-frequency, and vector signals suitable for arbitrary IQ signal construction. These results highlight the flexible and reconfigurable capabilities of the proposed approach, providing new perspectives for applications in radio-over-fiber systems and beyond.

physics.optics↗

arXiv2025

Efficient Symbolic Computation via Hash Consing

Symbolic computation systems suffer from memory inefficiencies due to redundant storage of structurally identical subexpressions, commonly known as expression swell, which degrades performance in both classical computer algebra and emerging AI-driven mathematical reasoning tools. In this paper, we present the first integration of hash consing into JuliaSymbolics, a high-performance symbolic toolkit in Julia, by employing a global weak-reference hash table that canonicalizes expressions and eliminates duplication. This approach reduces memory consumption and accelerates key operations such as differentiation, simplification, and code generation, while seamlessly integrating with Julia's metaprogramming and just-in-time compilation infrastructure. Benchmark evaluations across different computational domains reveal substantial improvements: symbolic computations are accelerated by up to 3.2 times, memory usage is reduced by up to 2 times, code generation is up to 5 times faster, function compilation up to 10 times faster, and numerical evaluation up to 100 times faster for larger models. While certain workloads with fewer duplicate unknown-variable expressions show more modest gains or even slight overhead in initial computation stages, downstream processing consistently benefits significantly. These findings underscore the importance of hash consing in scaling symbolic computation and pave the way for future work integrating hash consing with e-graphs for enhanced equivalence-aware expression sharing in AI-driven pipelines.

cs.PL↗

arXiv2025

Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding

Spiking neural networks (SNNs) promise high energy efficiency, particularly with time-to-first-spike (TTFS) encoding, which maximizes sparsity by emitting at most one spike per neuron. However, such energy advantage is often unrealized because inference requires evaluating a temporal decay function and subsequent multiplication with the synaptic weights. This paper challenges this costly approach by repurposing a physical hardware `bug', namely, the natural signal decay in optoelectronic devices, as the core computation of TTFS. We fabricated a custom indium oxide optoelectronic synapse, showing how its natural physical decay directly implements the required temporal function. By treating the device's analog output as the fused product of the synaptic weight and temporal decay, optoelectronic synaptic TTFS (named Otters) eliminates these expensive digital operations. To use the Otters paradigm in complex architectures like the transformer, which are challenging to train directly due to the sparsity issue, we introduce a novel quantized neural network-to-SNN conversion algorithm. This complete hardware-software co-design enables our model to achieve state-of-the-art accuracy across seven GLUE benchmark datasets and demonstrates a 1.77$\times$ improvement in energy efficiency over previous leading SNNs, based on a comprehensive analysis of compute, data movement, and memory access costs using energy measurements from a commercial 22nm process. Our work thus establishes a new paradigm for energy-efficient SNNs, translating fundamental device physics directly into powerful computational primitives. All codes and data are open source.

cs.LG↗

arXiv2025

ASDR: Exploiting Adaptive Sampling and Data Reuse for CIM-based Instant Neural Rendering

Neural Radiance Fields (NeRF) offer significant promise for generating photorealistic images and videos. However, existing mainstream neural rendering models often fall short in meeting the demands for immediacy and power efficiency in practical applications. Specifically, these models frequently exhibit irregular access patterns and substantial computational overhead, leading to undesirable inference latency and high power consumption. Computing-in-memory (CIM), an emerging computational paradigm, has the potential to address these access bottlenecks and reduce the power consumption associated with model execution. To bridge the gap between model performance and real-world scene requirements, we propose an algorithm-architecture co-design approach, abbreviated as ASDR, a CIM-based accelerator supporting efficient neural rendering. At the algorithmic level, we propose two rendering optimization schemes: (1) Dynamic sampling by online sensing of the rendering difficulty of different pixels, thus reducing access memory and computational overhead. (2) Reducing MLP overhead by decoupling and approximating the volume rendering of color and density. At the architecture level, we design an efficient ReRAM-based CIM architecture with efficient data mapping and reuse microarchitecture. Experiments demonstrate that our design can achieve up to $9.55\times$ and $69.75\times$ speedup over state-of-the-art NeRF accelerators and Xavier NX GPU in graphics rendering tasks with only $0.1$ PSNR loss.

cs.AR↗

arXiv2025

Spatial-Wavelength Multiplexing Reliable Photonic Integrated General-Purpose Analog Computing System

In the "post-Moore era", the growing challenges in traditional computing have driven renewed interest in analog computing, leading to various proposals for the development of general-purpose analog computing (GPAC) systems. In this work, we present a GPAC prototype featuring a silicon photonic chip designed for fully optical analog computation. This system leverages on-chip multi-channel architectures to enable parallel processing and utilizes wavelength-division multiplexing to significantly enhance computational capacity. In addition, we have developed an error-correction algorithm to monitor processing operations in real time, ensuring the reliability of computational results. Experimentally, we demonstrate the system's capability to solve ordinary differential equations and its applications in communications, microwave photonics, and image processing. The chip's energy efficiency is evaluated to reach up to 227 tera-operations per second per watt. Through this research, we provide a novel hardware framework and innovative directions for analog photonic computing.

physics.optics↗

arXiv2025

On a perturbation analysis of Higham squared maximum Gaussian elimination growth matrices

Gaussian elimination is the most popular technique for solving a dense linear system. Large errors in this procedure can occur in floating point arithmetic when the matrix's growth factor is large. In the study of numerical linear algebra, it is often valuable to study and characterize the worst case examples. To this end, in their 1989 paper, Higham and Higham characterized the complete set of real n by n matrices that achieves the maximum growth factor under partial pivoting. Left undone is a sensitivity analysis for these matrices under perturbations. The growth factor of these and nearby matrices is the subject of this work. Through theoretical insights and empirical results, we illustrate the high sensitivity of the growth factor of these matrices to perturbations and show how subtle changes can be strategically applied to matrix entries to significantly reduce the growth.

math.NA↗

arXiv2025

Ultralow-pressure mechanical-motion switching of ferroelectric polarization

Ferroelectric polarization switching, achieved by mechanical forces, enables the storage of stress information in ferroelectrics, and holds promise for human-interfacing applications. The prevailing mechanical approach is locally induced flexoelectricity with large strain gradients. However, this approach usually requires huge mechanical pressures, which greatly impedes device applications. Here, we report an approach of using triboelectric effect to mechanically, reversibly switch ferroelectric polarization across α-In2Se3 ferroelectric memristors. Through contact electrification and electrostatic induction effects, triboelectric units are used to sensitively detect mechanical forces and generate electrical voltage pulses to trigger α-In2Se3 resistance switching. We realize multilevel resistance states under different mechanical forces, by which a neuromorphic stress system is demonstrated. Strikingly, we achieve the reversal of α-In2Se3 ferroelectric polarization with a record-low mechanical pressure of ~ 10 kPa, and even with tactile touches. Our work provides a fundamental but pragmatic strategy for creating mechanical-tactile ferroelectric memory devices.

cond-mat.mtrl-sci↗