Search arXiv⌕ Search

arXiv subjects

Bowen Zhu

Publications and source records attributed to Bowen Zhu.

At least 19 recordsLinked to original sources
arXiv2026

Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch

Recent breakthroughs in artificial-intelligence-assisted mathematics show that open-ended machine search can outperform human mathematicians, yet transferring this paradigm to physics requires refactoring the research workflow. We introduce Simjecture, an open-source framework in which language-model agents pursue human-defined physical conjectures. The framework tackles two central challenges in this transfer: first, because physics is empirical and no model is final, it structures inquiry around counterexample-driven falsification and prospective hypothesis repair; second, because physical theories must interact with the real world, it uses computational physics as an executable testbed while separating the qualification of numerical instruments from scientific claim review so solvers and diagnostics can be adapted within a recorded investigation. We apply the framework in an 82.6 h investigation to tackle the long-standing problem of radiated energy exceeding the imploding-shell kinetic energy in a Z-pinch. The investigation reveals competing effects of energy conversion, retention, and release timing. Stronger coherent helical deformation increases resistive conversion while reducing radiation and increasing retained energy. A broader trailing-plasma profile delays the later radiation maximum and recovers much of its early bolometric deficit, with a spectral response that changes during the pulse. These results provide new insight into energy conversion in high-energy-density plasma physics and demonstrate a new paradigm for physics research.

cs.AI↗
arXiv2026

CIVER: Causal Intervention Verification for Reliable Code Review

Code review is essential for maintaining software repositories by identifying defects, improving code quality, and supporting reliable software evolution. With the growing adoption of LLM-based coding agents, an increasing number of code contributions and repository changes are generated by these agents. Consequently, LLM-based code review agents are becoming increasingly prevalent to evaluate these contributions and maintain software quality. However, LLM reviewers often generate lengthy reviews containing numerous potential issues, many of which are false positives or lack sufficient evidence. These unreliable reviews can mislead developers and downstream coding agents, motivating the need to distinguish actionable findings from unsupported claims. We propose CIVER, a causal intervention-based framework that identifies the core issues underlying code-review findings and distinguishes genuine defects from false positives. CIVER integrates three modules: a review module assesses findings, an intervention module generates repair-oriented perturbations, and a verifier module scores review reliability. Through joint optimization via expert iteration, the three modules identify genuine defects by responding to targeted repairs while remaining stable under unrelated changes. Extensive experiments on SWE-Review-Bench demonstrate that CIVER correctly identifies 77% of genuine defects through targeted repairs. Cross-project and downstream repair evaluations further demonstrate that CIVER generalizes across repositories and improves coding agents' task success rates, highlighting its effectiveness for reliable automated code review.

cs.SE↗
arXiv2026

Skill Dreaming: Evolving Repository Skills through Pull Request Streams

Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framework that learns from PR streams to guide continuous repository development and maintenance. Given a repository and its PR history, Skill Dreaming builds a repository-specific skill library by extracting executable knowledge from validated PRs and continuously refines the skills as new PR information becomes available. These skills guide coding agents not only in implementing requested features but also in maintaining associated tests, documentation, compatibility, and repository conventions. By integrating PR analysis, skill management, code execution, and continuous integration, Skill Dreaming provides an end-to-end workflow for applying learned skills to repository changes and incorporating subsequent PR outcomes into future skill updates.

cs.AI↗
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

Software World Models: From Consequence Prediction to Decision Value

A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests after every agent action is impractical, so the agent must predict these failures before executing them. Existing software world models predict the agent's own observations, while static change-impact analysis only identifies where a change may propagate. We instead introduce the Software World Model (SWM), which models the broader system affected by a code change and predicts its blast set: the components that the change will break. SWM follows three stages: explore, learn, and act. Explore executes candidate changes from restored system states, prioritizing regions where observed failures contradict the dependency graph. Learn fine-tunes a language model on these execution outcomes to predict downstream breakage. Act converts sampled predictions into per-consumer break probabilities for change ranking, proactive migration, and deciding when another execution is worth its cost. On held-out synthetic systems, SWM improves blast-set F1 from 0.431 for static reachability to $0.571\pm0.037$, more than halves ranking regret, and improves migration return at all nine evaluation checkpoints. The two methods are complementary: reachability is stronger on dependencies represented in the graph, while SWM recovers failures caused by couplings the graph misses. Experiments on held-out real libraries further show that predicting structured failure outcomes, rather than only scalar risk, is important for downstream decision quality.

cs.LG↗
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

StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents

Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observation is appended to the context and the context grows with each one. History-based maintenance is a common remedy, which masks or summarizes old observations, or prunes what a model reads as useless, and bounds the context at little cost. However, it decides from the text of the history alone and sees nothing of how the code is connected. Since a coding agent edits code many times over a single task, and each write can change what code elsewhere means, such maintenance may keep records a write has falsified, drop ones that still hold, and miss code the agent needs next. To overcome these challenges, this paper proposes StateTape, a novel and scalable framework that rewrites a coding agent's context as the repository changes rather than as the context grows. The key idea of StateTape is to model the repository as a symbol-level code graph, whose dependencies and language rules expose which symbols a write can affect. Upon this graph, a tape marks the symbols each write changed, which turns staleness from an inference about text into an observation of the agent's writes. We propose a per-write procedure in which the tape nominates the records a write could have falsified while a small manager model settles what the write log cannot, and further provide a theoretical analysis and TraceBench, a benchmark that labels what an agent is holding against what is actually needed. Empirically, we demonstrate that StateTape can effectively clear falsified records and retrieve what is needed, and thus achieve a higher resolve rate in all experiments spanned by six coding agents and three edit-heavy benchmarks with little computational overhead.

cs.AI↗
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

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

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↗