Searcharxiv⌕ Search

arXiv subjects

Ziyu Wang

Publications and source records attributed to Ziyu Wang.

At least 19 recordsLinked to original sources

AI-Assisted Analysis of CMS Open Data: Prompt J/psi Cross-Section Measurements in pp and Peripheral PbPb Collisions at sqrt(S)= 7 TeV and sqrt(sNN) = 2.76 TeV

We investigate the use of an artificial-intelligence (AI) coding agent, supervised by human physicists, for collider physics analyses using CMS Open Data. OpenAI Codex performs dimuon event selection, two-dimensional invariant-mass and decay-length fits, Monte Carlo detector simulations, and systematic uncertainty evaluation after acquiring physics and experimental knowledge from published studies and external references, with human review at each stage. The workflow is tested on two CMS datasets, with custom full-detector simulations used to determine acceptance and reconstruction efficiencies. In proton-proton collisions at sqrt(s) = 7 TeV, prompt J/psi differential cross sections are measured versus transverse momentum and rapidity. The ratios of remeasured to published CMS cross sections have a mean of 1.000 and an RMS spread of 0.215 across 39 bins. In peripheral (50-100% centrality) PbPb collisions at sqrt(s_NN) = 2.76 TeV, the corresponding prompt J/psi fiducial cross-section ratios have a mean of 1.158 and an RMS spread of 0.225 across six intervals. We identify agent failure modes and demonstrate the importance of structured human review in ensuring reliable results.

hep-ex↗

A full-wave ICRH solver with full kinetic accuracy using only first order differential equations

Accurate full-wave computation of ion cyclotron resonance heating (ICRH) typically requires solving the computationally demanding integro-differential dielectric tensor of the hot plasma. Based on the method in [Phys. Plasmas 32, 082110 (2025)], we develop BO-FW1D, a 1D frequency domain finite difference full-wave solver which generates full kinetic, accurate and efficient simulations utilizing a fluid plasma model. To accurately convert the conductivity tensor in phase space into a first-order differential equation, we introduce a mathematically rigorous framework using pseudodifferential operator theory based on Kohn-Nirenberg ordering. Benchmarks with an all-orders 1D full-wave solver show high consistency in critical kinetic effects and electric-field distributions, while substantial computational acceleration is achieved. This work could lay the foundation for developing full-wave solvers that combine full kinetic accuracy with high computational efficiency.

physics.plasm-ph↗

Simplify, Agree, Distill: Label-Free Self-Distillation with Stepping Stones

Can a language model teach itself to reason without labels? On-policy self-distillation (OPSD) uses the model as its own teacher, but strengthens that teacher with a ground-truth solution. The natural label-free substitute, voting over the model's attempts, fails precisely on hard problems: attempts disagree, and their most common answer is often wrong. We propose STONE, a label-free alternative that moves agreement to easier related problems. The model writes these stepping stones, keeps those it solves consistently, and shows the teacher their worked solutions, with final answers removed; the student sees only the original problem. No step reads a label, and inference needs no extra context or model calls. Across five math benchmarks, the proposed method achieves the highest average accuracy for Qwen3-4B and Qwen3-8B in thinking mode. Without thinking mode, it gains 13.2 and 22.7 points, 2.5 and 2.7 times the gains of OPSD with ground-truth solutions.

cs.LG↗

Can Music Generation Models Tap Along? Evaluating Generative Approaches to Beat Tracking

Existing studies have shown that music generative models can generate synchronized tracks that play alongside an input song. Can we extend this capability to develop a generative approach to beat tracking? To answer this question, we equip a pretrained MusicGen model with an audio-conditioning adapter to generate percussion tracks synchronized with the input music, from which we extract the beat positions. We train separate models with percussion targets of varying rhythmic complexity and compare them with two other generative models and conventional beat trackers. On GTZAN, our model achieves performance close to state-of-the-art beat trackers. Our model also demonstrates greater robustness: it shows the smallest drop in F-measure when drums are removed from the input at inference time. In certain genres, such as metal and disco, our model is also less likely to be misled by strong onsets or to miss beats with weak onsets. These results suggest that percussion generation has the potential to become a viable approach to beat tracking, and that its output is not merely a sequence of beat positions but an audible percussion track.

cs.SD↗

Rethinking Adaptive Routing on Dragonfly

The Dragonfly topology is widely deployed in leading supercomputers, where adaptive routing is crucial for high-performance interconnection. Despite years of research, a dilemma remains: state-of-the-art adaptive routing algorithms achieve excellent performance but demand hardware budgets far beyond what real router chips can afford -- prohibitive buffers, logically dependent floating-point operations, or exhaustive path-set traversals -- whereas realizable algorithms deliver unsatisfactory performance. Furthermore, existing algorithms fail to exploit the abundant almost-minimal paths in Dragonfly: when only the local channels of a minimal path are congested, they reroute packets to significantly longer global non-minimal paths, wasting global bandwidth and increasing latency. To address both limitations, we analyze intra-group path contention and propose the Decoupled Incremental Adaptive Routing (DIAR) algorithm, which decouples routing into global path selection at the source and incremental local detours onto almost-minimal paths, guaranteeing deadlock freedom without additional virtual channels, escape rings, or turn models. Requiring only a few comparators, shifters, adders, and multiplexers, DIAR reduces buffer overhead by up to four orders of magnitude compared with state-of-the-art algorithms, while achieving comparable or superior performance across all evaluated scenarios: relative to the strongest realizable adaptive routing algorithm in each scenario, DIAR improves saturation throughput by up to 30.0% across synthetic traffic patterns and improves performance by up to 34.9% (13.2% on average) across HPC workloads.

cs.NI↗

AuthGateBench: Benchmarking LLMs as Authorization Gate

Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large language model (LLM). Such systems, adopted in tools like Claude Code and Codex, remain vulnerable to failure modes such as scope escalation, where the agent takes actions exceeding what the user authorized. Existing benchmarks focus mainly on malicious requests, evaluating refusal under an implicit policy. We introduce AuthGateBench, the first policy-guided benchmark for authorization gating under benign requests. We implement a novel pipeline where an LLM generates contrast pairs with identical action and trajectory but differing request, flipping the label between block and allow. This allows us to assess whether models reason over context rather than the action alone. We further examine whether auxiliary environment signals can help models make better decisions. The resulting benchmark comprises 1,400 instances spanning five failure modes drawn from real-world Claude Code incidents. Evaluations show accuracy degrades unevenly across failure modes as models over-rely on internal safety alignment, and models still block most actions even when explicitly authorized, revealing unstable rather than deterministic decisions; retrospectively retrieved environment signals, however, substantially improve authorization accuracy.

cs.AI↗

MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control

A cover song re-renders an existing piece, most commonly by preserving its tonal content -- melody and chord progression -- while reshaping other musical attributes. This suggests a natural formulation for generative cover synthesis with pretrained music language models: explicitly control tonal content, while specifying lyrics and style through text. Existing approaches condition on frame-level features, tightly coupling generation to the reference's timing and structure, and limiting flexibility such as tempo variation, structural rearrangement, or partial conditioning. To this end, we present MuLaCover, a cover generation model that conditions a pretrained text-to-song foundation model on an editable symbolic lead sheet. Our design enables alignment-free control: generated outputs preserve the tonal signature of the source without frame-level alignment, allowing flexible timing, structure, and segment-level generation. We further introduce a training curriculum with partially mismatched audio-symbolic pairs, improving diversity and robustness. We evaluate MuLaCover with objective metrics, standard subjective ratings, and in-depth expert interviews that provide fine-grained diagnostic insights. Experiments show that MuLaCover achieves state-of-the-art performance among open-source systems and is competitive with leading commercial models such as Suno-v5.5. Audio samples and code are available at our project page: https://mulalabs.ai/mulacover/

cs.SD↗

MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA

Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into a frozen E5 text embedding space. This enables a dense retrieval path that accepts a waveform without a query transcript. Retrieved passages and speech-linked textual metadata support answer generation with entity alternatives, diagnostic contrasts, relation heuristics, and bounded retrieval refinement. ASR-less refers to the initial speech retrieval interface; lexical retrieval, string-based entity correction, and the text generator require textual inputs. The deterministic speech embedding does not constitute a calibrated model of acoustic uncertainty. Reported retrieval results reach 87.6 Recall@10 for the speech-only retriever and 90.4 for the hybrid configuration, compared with 81.0 for transcript-first dense retrieval. Medical QA and ablations provide descriptive system comparisons, with input-provenance and evaluation limitations stated explicitly. We distinguish controlled synthetic acoustic tests from real clinical speech, qualify component attribution, and specify the remaining comparisons needed to assess speech-only QA and clinical generalization.

cs.CL↗

Network-Aware Progressive Replacement Sequence Planning for Laser-Enhanced BeiDou Navigation Constellations

The early satellites of the third-generation BeiDou Navigation Satellite System (BDS-3) are approaching the end of their design lifetime, making progressive constellation replacement an inevitable engineering task. Meanwhile, laser inter-satellite links (LISLs) offer high-precision time transfer, ranging, and high-rate data forwarding, providing a promising upgrade path for future BeiDou satellites. This paper investigates the replacement-sequence planning problem for progressively replacing legacy microwave satellites with laser-enabled satellites from a networking perspective. Since practical replacement decisions remain constrained by legacy satellite lifetime, on-orbit condition, laser satellite manufacturing readiness, and launch scheduling, networking information is used as an auxiliary criterion in the actual engineering replacement process. An integer linear programming model is developed to evaluate the network value of intermediate laser--microwave hybrid states. Based on this common state evaluator, two complementary planning methods are developed. A priority-aware exact method supports round-wise network-assisted launch decisions, while a visibility-guided adaptive large-neighborhood search is used for full-sequence planning and provides a full-horizon network-oriented near-optimal reference. Simulations using the actual BDS-3 constellation show that stronger network participation leads to earlier and larger ground-connected laser subnetworks, fewer microwave-dependent satellites, better coordination between laser-backbone growth and high-rate ground access, and improved residual microwave-layer performance. These results provide a quantitative basis for incorporating network performance as an auxiliary criterion in future BeiDou replacement planning.

eess.SY↗

Half-Slot Link Scheduling for Open GNSS with $x$-Tx $y$-Rx Multibeam Phased Array Antennas

Global Navigation Satellite Systems (GNSSs) are evolving from closed navigation constellations toward open space infrastructure capable of serving extensive spacecraft users. This evolution requires the constellation to support navigation ranging, telemetry (TM) return, and telecommand (TC) delivery for users while preserving its own ranging and communication functions.Existing phased-array payloads onboard BeiDou satellites provide one transmit (Tx) beam and one receive (Rx) beam. Such a configuration was designed mainly for intra-constellation operation, and can become a resource bottleneck when a large number of users share the same link opportunities. Upgrading GNSS satellites to phased-array terminals with $x$-Tx and $y$-Rx beams is therefore a natural enhancement. This paper develops a staged dynamic half-slot link scheduling framework (SDHSS) for open GNSS with $x$-Tx $y$-Rx multibeam phased-array antennas. The framework models navigation, TM, and TC as three different services, reserves the essential ranging and ground-access opportunities required by the GNSS constellation, and then allocates the remaining half-slot beam resources according to current service demand. To support multibeam concurrency, feasible links are selected through dynamic service-layer ordering and beam-copy matching. Simulations based on a BeiDou constellation show that the proposed method protects GNSS baseline operation and provides stronger external navigation, TM, and TC performance than fair contact planning. The results further show that additional Tx and Rx beams can be effectively converted into multi-service capability. This work establishes a link-scheduling approach for extending GNSS from constellation-internal operation to large-scale spacecraft service support.

eess.SY↗

CoSec: Benchmarking Agent Security in Communities

LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships. Agents must complete legitimate tasks and prevent unauthorized disclosure of protected information. Existing evaluations do not fully examine these risks in agent systems. We introduce \textbf{CoSec}, an executable benchmark for evaluating privacy and authorization enforcement in LLM agent systems operating within and across communities. CoSec contains 208 canonical scenarios spanning fixed and evolving boundaries, protected information belonging to the agent owner or other participants, and attacks through dialogue, environmental content, persistent memory, and composed workflows. CoSec executes complete agent systems with persistent sessions, memory, files and tools. It verifies information flows against the active authorization state using execution traces and artifacts. Across harness and model configurations, agents frequently complete benign tasks but violate privacy and authorization boundaries. Privacy behavior varies across harnesses, attack surfaces, and community states, revealing how memory, files, tools, and workflows can carry protected information beyond its authorized scope. These findings show that task utility does not imply privacy or authorization compliance and that authorization in community settings remains an unresolved security challenge for persistent LLM agents.

cs.CR↗

FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence

Large language models can now generate complex, multi-step mathematical proofs, but reliably determining their correctness and localizing early logical errors remains a critical challenge. Existing evaluation approaches largely depend on model-based natural-language judgments, which often overlook local reasoning gaps. While formal theorem provers like Lean offer a path to rigorous verification, using them to evaluate informal text requires solving locality and semantic mismatches: a prover might bypass a local flaw by proving an overly broad target, or validate an auto-formalized statement that drifts from the original mathematical intent. To address this, we introduce FaithSieve, a Lean-assisted framework for fine-grained evaluation of natural-language mathematical proofs. FaithSieve decomposes coarse proof steps into local reasoning units, extracts typed proof obligations, and verifies them through a formal evaluation agent. Formal validation is gated by semantic alignment scoring, so Lean evidence is incorporated only when the formal statement faithfully preserves the context, objects, and logical form of the original claim. We construct two expert-verified datasets, ProofLoc-Olympiad and ProofLoc-University, to benchmark first-error localization. On the 350-problem Olympiad dataset, FaithSieve using a GPT-5.4 backbone achieves 81.43% exact first-error accuracy, outperforming the direct-judging baseline of 72.29%. Furthermore, on the 200-problem ProofLoc-University benchmark spanning six advanced domains, FaithSieve reaches 84.5% exact accuracy, compared to 75.0% for the direct judge. Our work demonstrates that decomposing proofs into fine-grained units and grounding them with faithful formal evidence significantly improves reliable evaluation of natural-language reasoning.

cs.AI↗

Note-Level Temporal Grounding of Musical Concepts in Large Audio-Language Models

Large audio-language models (LALMs) demonstrate growing music-understanding capabilities, but whether their responses are grounded in acoustic evidence remains unclear. Musical language often involves abstract concepts whose acoustic evidence is difficult to define and evaluate precisely. We introduce MusicGroundingBench, a controlled benchmark of algorithmically generated piano audio with exact symbolic alignment, comprising three-note and two-bar settings. We evaluate two complementary capabilities: grounding, which localizes the acoustic evidence for a musical query, and understanding, which answers questions about the same excerpts. Our experiments show that cross-modal fine-tuning enables models to learn each capability, but adding grounding supervision does not consistently improve understanding across backbones. We further test whether understanding requires listening through audio-ablation controls that remove or replace the input audio, and use attention analysis to examine whether grounding supervision shifts attention toward note boundaries. Meanwhile, the two evaluated LALMs show limited zero-shot grounding even for basic musical concepts, highlighting grounded music understanding as an important open challenge.

cs.SD↗

Do Music Generative Models Understand Musical Qualities? Automatic Music Evaluation with Model-Intrinsic Signals

Current music generative models can produce high-quality music, but does this ability imply that they ``understand'' the musical qualities of their outputs, and is that understanding aligned with human evaluation? Previous attempts to use the likelihood of a generative model to evaluate music, an approach commonly used in text, have proven unsuccessful, leading researchers to rely on standalone supervised music evaluation models. In this paper, we answer this question affirmatively: we show that a model's intrinsic signals---derived from its hidden representations and predictions---are strongly correlated with human ratings. In particular, we study MusicGen and consider three types of features: (1) prediction loss, (2) prediction entropy, and (3) concepts extracted from the model using a sparse autoencoder (SAE). Using these features, we train a lightweight prediction model to estimate subjective ratings. We evaluate these features both individually and in combination. We hypothesize that these signals parallel the listening process: the temporal and frequency-domain structure of loss and entropy reflects listeners' expectation and surprise, while gradient directions in SAE latent space predict perceived quality. Experiments on five human-evaluation benchmarks spanning continuous ratings and pairwise preferences confirm this hypothesis, with SAE latents carrying most of the predictive signal.

cs.SD↗

TempCloze: Can Video-LLMs Identify the Missing Middle?

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

cs.CV↗

Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems

Ensuring the reliability of deep learning-based image retrieval systems is a software engineering challenge. This paper presents a dual contribution: (1) a literature review of augmentation and generation techniques which resulted in the identification of 50 techniques which we organized into a ten-category taxonomy, and (2) a large-scale empirical study that evaluates these techniques as test generators for embedding-based image retrieval systems. Augmented images are embedded using Amazon Titan and OpenCLIP, and evaluated across four analytical dimensions: (1) embedding-space similarity, (2) embedding uncertainty measured via four estimators, (3) semantic realism scored by LLaVA, and (4) retrieval failure rate. Experiments are performed on three datasets: CIFAR-10, ImageNet-1K, and a dataset from an industrial partner (March Networks). Across all evaluated datasets and embedding models, and under the single severity level tested for each technique, weather simulation and SaSPA are the image augmentation/generation techniques that produce the highest embedding uncertainty and failure rates while maintaining a favorable balance between performance stability, visual realism, and augmentation effectiveness. The results we discuss are configuration-specific and may shift under milder or stronger perturbation settings. In contrast, GAN-based augmentation techniques are among the lowest in realism, indicating the presence of synthetic artifacts and perceptual inconsistencies that reduce their suitability to produce realistic test inputs. Overall, our findings provide practical guidelines for selecting augmentation techniques that maximize test diversity while preserving realistic image characteristics, thereby enabling the construction of comprehensive and effective test suites for image retrieval systems while reducing the cost of manual data labeling through the use of metamorphic testing.

cs.SE↗

PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation

LLM agents have achieved strong performance on general software engineering tasks, yet struggle with domain-specific code generation. We identify the root cause as the agent's lack of tacit knowledge, including domain-specific business rules, interface contracts, and operational conventions that developers internalize through practice but never document. This knowledge is deeply buried beneath the domain code, dispersed across code entities and their dependency relations, and invisible to the agent that lacks it. These properties make tacit knowledge inherently difficult to retrieve or learn. In this work, we propose PRAXIS, a framework that enables agents to systematically extract, represent, and reuse tacit knowledge for domain code generation. PRAXIS acquires tacit knowledge by simulating human development workflows within the target codebase, distills it into structured units organized on the code dependency graph, and proactively surfaces it to the agent at the point of code interaction. Extensive experiments demonstrate that PRAXIS outperforms state-of-the-art agents equipped with powerful agentic search capabilities, as well as experience-based and skill-based methods. The approach integrates seamlessly into various agent frameworks and LLMs with consistent performance improvements, and supports continual evolution with performance steadily scaling as practice accumulates.

cs.SE↗

Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping

What is music style? Though often described using text labels such as "swing," "classical," or "emotional," the real style remains implicit and hidden in concrete music examples. In this paper, we introduce a cross-modal framework that learns implicit music styles from raw audio and applies them to symbolic music generation. Inspired by BLIP-2, our model leverages a Querying Transformer (Q-Former) to extract style representations from a large, pre-trained audio language model (LM), and further applies them to condition a symbolic LM for generating piano arrangements. We adopt a two-stage training strategy: contrastive learning to align auditory style with symbolic expression, followed by generative modeling for music arrangement. Our model generates piano performances jointly conditioned on a lead sheet (content) and a reference audio example (style), enabling controllable and stylistically faithful arrangement. Experiments demonstrate the effectiveness of our approach in piano cover generation, style transfer, and audio-to-MIDI retrieval, achieving substantial improvements in style-aware alignment and music quality.

cs.SD↗