Searcharxiv⌕ Search

arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 55 records · Page 3Linked to original sources
arXiv2026

Close Shortcut Wins Long: Seeking Diverse and Stable Generators for Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) preserves privacy by transferring knowledge without real data access. However, existing generator-based DFKD methods suffer from over-reliance on teacher preferences and pattern collapse, exhibiting "generative shortcut learning" in the frequency domain: dependent on specific frequency components and frequency positions, resulting in inconsistent synthetic image quality and class diversity. In this paper, we propose a CSWL framework aimed at introducing insights from the frequency domain perspective to improve generator diversity and training stability to Close the phenomenon of Shortcut learning to Win in the Longer term. To address the issue of generative shortcut learning, we introduce frequency-domain augmentation at the feature level, encouraging the generator to attend to the full frequency spectrum and thereby suppress shortcut learning behavior. To tackle training instability, we propose a Cross-Stage Frequency Reconstruction (CSFR) auxiliary task, which implicitly constructs an Exponential Moving Average (EMA) mechanism to promote long-term optimization and stability. Extensive experiments, including downstream tasks and various image recognition datasets at multiple resolutions, validate the effectiveness of CSWL in improving both diversity and stability from the frequency view.

cs.CV↗
arXiv2026

Diffractive Sail H-Reversal Trajectory: Theoretical Feasibility, Design Strategies, and Applications

With the growing threat of near-Earth asteroid, planetary defense serves as a vital shield against catastrophic disasters. Kinetic impact utilizing an angular momentum reversal (H-reversal) trajectory of a solar sail is a highly advantageous defense approach. However, traditional reflective sails (RS) are constrained during these maneuvers by attitude-thrust coupling and a degradation of solar radiation pressure utilization at the high cone angles required for transverse acceleration. To enhance impact performance and simplify control, this paper proposes an H-reversal impact scheme utilizing a Sun-facing diffractive sail (SFDS) under a one-stage diffraction angle θd strategy and a two-stage θd strategy. The feasible parameter spaces for both strategies were mapped using the hodograph method. Tailored trajectory design methods were established for both strategies based on the feasibility analysis. Apophis impact scenario was considered, and the corresponding trajectories were constructed. Simulations demonstrate that the one-stage θd SFDS outperforms RS through a 21% increase in the impact velocity and a 35% decrease in the mission duration. Furthermore, the proposed two-stage θd strategy yields an additional 9km/s gain in impact velocity. By utilizing SFDS H-reversal trajectories, this research establishes an emergency planetary defense framework characterized by rapid response and high kinetic energy.

astro-ph.EP↗
arXiv2026

Efficient production of $^{229m,g}$Th via neutron capture in VUV-transparent crystals

The low-lying isomeric state of $^{229m}$Th, owing to its unique nuclear energy structure, has been widely regarded as one of the most promising candidates for the development of a nuclear clock. However, the limited availability of suitable $^{229}$Th sources with sufficiently high activity remains a major challenge for experimental investigations of the $^{229m}$Th isomer. We propose a neutron-capture-based approach for the in-situ production of $^{229m,g}$Th by doping $^{228}$Ra into crystal hosts, where $^{229m,g}$Th is generated through neutron-capture reactions followed by a sequence of radioactive decay processes. We systematically investigate the background contributions associated with the three doped crystal hosts, namely CaF$_2$, SrF$_2$, and LiF, and evaluate their impact on the detection and identification of $^{229m}$Th. Under a neutron flux of $10^{15}\ \mathrm{n/cm^{2}/s}$ and a $^{228}$Ra doping concentration of $10^{19}\ \mathrm{cm^{-3}}$, the proposed method is capable of producing on the order of $10^{12}$ $^{229}$Th and $^{229m}$Th nuclei within only 1 s of irradiation, with a signal-to-noise ratios as high as $10^5$. In addition, the influences of detector wavelength resolution and post-irradiation measurement time on the detectability of the $^{229m}$Th signal are systematically analyzed, and the corresponding optimal measurement conditions are identified. Furthermore, the spatial distribution of neutron-produced $^{229}$Th within the crystal is investigated, providing practical guidance for optimizing crystal geometry and illumination configuration in future continuous-wave VUV absorption spectroscopy experiments. These results suggest that the proposed scheme provides a promising alternative pathway for the production and detection of $^{229\mathrm{m,g}}$Th, which may facilitate future studies toward the realization of nuclear-clock-based technologies.

nucl-ex↗
arXiv2026

When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge

LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and factuality, and these outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations between trust and truth judgment. We then apply stress tests by changing only source cues of identical QA between Human and AI. Source attribution shifts not only trust scores but also truth verdicts and logit-derived correct-side probabilities. Results show that current LLM-as-Judge protocols should not treat trust scores as independent evidence for truth judgments.

cs.AI↗
arXiv2026

Diffractive-Sail Single-Impulse Reachable Set for Interplanetary Transfer Design

Interest in planetary exploration has renewed, and the design of interplanetary transfers has attracted remarkable attention. This paper considers the interplanetary transfer design using a diffractive sail. Considering a nonzero departure hyperbolic excess velocity, the interplanetary transfer problem is transformed into the problem of computing single-impulse reachable sets. Then, based on previous work, a complementary computational method for reachable sets under arbitrary dynamics is proposed using differential algebra combined with adaptive grid refinement. The adaptive grid refinement considers two types of merit scores that reveal dynamical properties and the truncation error of the differential algebra propagation. The proposed method is applied to compute the diffractive-sail reachable sets, and the results verify the effectiveness of the method and merit scores. Finally, a preliminary design of the interplanetary transfers, specified as the Earth-Mars transfers, is performed based on the diffractive-sail reachable sets. The design results are presented. The effects of the corresponding parameters, including transfer time, diffractive angle, and type of diffractive sails, on transfer characteristics are analyzed, providing further insight into parameter selection for interplanetary transfer design.

astro-ph.EP↗
arXiv2026

Inflation on the lattice: scalar Gauss-Bonnet single field inflation

We use lattice methods to study inflation in the scalar Gauss-Bonnet (SGB) gravity theory. We focus on the ultra-slow-roll scenario with the peak frequency falls into the PTA band. In the parameter range we consider, we find that the lattice results exceed the perturbative predictions, which differs from the case in Einstein gravity. We further find that lattice corrections become significant when the peak of the primordial curvature spectrum reaches $\sim 10^{-2}$. We calculate the energy density spectra of second-order scalar induced gravitational waves (SIGWs) using the primordial power spectra obtained from both the lattice method and the traditional perturbative method, and analyze the SGB model in light of current pulsar timing array (PTA) observations. Our results indicate that lattice corrections enhance the ability of the SGB model to dominate the PTA observations.

astro-ph.CO↗
arXiv2026

Multimodal Adaptive Control for Safe Robotic Craniotomy Under Partial Observability

Autonomous robotic craniotomy requires continuous regulation of tool-tissue interactions to mitigate mechanical overload and thermal damage while maintaining surgical efficiency. However, this process is inherently partially observable due to unknown, time-varying tissue properties and the inability to directly measure cutting temperatures under physical occlusion. To address these challenges, we propose RL-MACRO, a cybernetic closed-loop intelligence framework that couples multimodal perception, adaptive decision-making, and robotic execution. This framework empowers the surgical robot to autonomously perceive inaccessible states from partial sensory feedback and dynamically optimize its behaviors under uncertain environment. A CNN-LSTM observer first fuses force and sound feedback to reconstruct the hidden temperature state (R^2=0.939, MAE = 1.717 deg C). This reconstructed temperature, alongside multi-sensor features, forms the belief state for an offline Implicit Q-Learning (IQL) policy. A novel dual-head Actor dynamically coordinates the feed rate, spindle speed, and cutting depth to optimize efficiency within strict safety bounds. These decisions are seamlessly translated into spatial motions via online trajectory re-planning and velocity servoing. Experiments on bovine ribs and six ex vivo goat skulls validate the system's robust perception, adaptive recovery from force/temperature excursions, and smooth execution on irregular surfaces, establishing a data-driven cybernetic paradigm for safe and efficient autonomous bone cutting.

cs.RO↗
arXiv2026

LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering

Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, but answering research questions from papers requires more than fluent generation. A reliable system must identify the relevant papers, locate the concrete evidence that supports the answer, and produce a response that is faithful to that evidence. We present LitTraceQA, a benchmark for literature-grounded question answering over scientific papers. Given a research question and a metadata pool of papers, a system must return three connected outputs: canonical paper identifiers, supporting evidence locations, and answers in one or more requested formats, including free-form text, multiple-choice answers, and structured tables. LitTraceQA targets evidence types common in scientific reading: tables, figures, text spans, equations or algorithms, and citation contexts. The public development split contains 55 examples, including 26 hidden-source single-paper questions and 29 multi-paper questions, and provides gold papers, evidence annotations, and answers for local validation. We also analyze a larger final annotation collection with 4,978 unique-question records over 4,859 unique gold papers. By evaluating paper retrieval, evidence grounding, and answer accuracy separately, LitTraceQA provides a testbed for scientific QA systems that produce verifiable answers rather than unsupported summaries.

cs.CL↗
arXiv2026

MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation

While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core challenges: authentic narrative logic, spatiotemporal text-video alignment conflicts, and the "copy-paste" dilemma prevalent in Subject-to-Video (S2V) generation. To bridge this gap, we introduce MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation. Sourced from over 3,000 movies, MuSS explicitly supports both complex montage transitions and subject-centric narratives. To construct this dataset, we pioneer a progressive captioning pipeline that eliminates contextual conflicts by ensuring local shot-level accuracy before enforcing global narrative coherence. Crucially, we implement a cross-shot matching mechanism to fundamentally eradicate the S2V copy-paste shortcut. Alongside the dataset, we propose the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency. Extensive experiments demonstrate that while current baselines struggle with continuous narrative logic or degenerate into trivial 2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation.

cs.CV↗
arXiv2026

Two-Horizon Sector Thermodynamics as a Diagnostic for the Bi-Hair Organization of NUT Charge

After decades without a fully self-consistent thermodynamic formulation, recent proposals for Lorentzian Taub-NUT spacetime have yielded several inequivalent descriptions, each satisfying its own first law and Smarr relation, leaving unresolved which formulation is physically preferred. In this Letter we introduce a two-horizon diagnostic whose sector temperatures are fixed by harmonic mean relations before the thermodynamic variables are chosen. For uncharged Taub-NUT, the sum sector closes with the mass and NUT charge, whereas, within the restricted homogeneous class examined here, the difference sector requires the thermodynamic secondary hair $J_n=mn$. This result supports a bi-hair thermodynamic organization of the NUT parameter through $N=n$ and $J_n=mn$. Furthermore, this two-horizon framework offers a new route toward addressing similar thermodynamic nonuniqueness in other two-horizon systems when the first law and Smarr relation alone do not identify a physically preferred formulation.

gr-qc↗
arXiv2026

Wafer-scale monolithic integration of Ce:YIG films and magneto-optical isolators on silicon

Silicon integrated cerium doped yttrium iron garnet (Ce:YIG) thin films are promising candidates for integrated nonreciprocal photonic devices, cryogenic photonic modulators and optical computing applications. However, previously reported Ce:YIG thin film on silicon is limited to milimeter sizes. Wafer-scale integration and non-destructive characterization of high quality Ce:YIG thin films on silicon has been elusive. Here, we report growth of 4-inch wafer-scale Ce:YIG thin films on silicon substrates by radio-frequency magnetron sputtering. Strong Faraday effect of 2318 deg/cm, low propagation loss of 80 dB/cm and excellent thickness uniformity of 3.5% is demonstrated across the 4-inch silicon wafer. Furthermore, a custom designed wafer-scale, non-destructive magneto-ellipsometry was established to characterize the film thickness, optical constants and magneto-optical constants across the wafer. Wafer-scale integration of ring resonator type magneto-optical isolators are also demonstrated. Our work demonstrates a step forward toward wafer-scale heterogeneous integration and characterization of magneto-optical thin films on silicon, providing material candidates for non-reciprocal photonic device arrays, magneto-optical in-memory computing networks and integrated magneto-optic magnetometers.

physics.optics↗
arXiv2026

Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents

Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reasoning states into text. Vision Wormhole realizes this approach by translating visual features into a universal latent representation that can be consumed by another model, but every message is transported as a dense tensor of the same size regardless of its content. A fixed-capacity dense tensor therefore need not have a fixed effective information density: some messages may use only a small fraction of the available representational degrees of freedom. This observation suggests that the communication channel may be substantially compressible. We study its redundancy by fitting a post-hoc sparse autoencoder to frozen Vision Wormhole activations and measuring reconstruction, downstream utility, feature reuse, and token-level interventions across nine reasoning benchmarks. Relative to the original float32 transport, a uint16-index/float16-value sparse payload with k=4 active coefficients per token reduces the transmitted bytes by 128x. In a single-run evaluation, the seven-task non-AIME mean accuracy changes from 49.85% to 49.77%. The fitted 4096-element dictionary uses only 50 features, and task-level active sets have a mean pairwise Jaccard similarity of 0.906. These measurements establish strong post-hoc compressibility relative to the original transport, but do not yet isolate the incremental contribution of sparse coding from position selection, reduced precision, low-rank structure, or SAE optimization effects. The results motivate matched-payload comparisons and communication mechanisms whose payload adapts to the information used by each message.

cs.AI↗
arXiv2026

C2C-Explorer: An Exploration Framework for Chip-to-Chip Interconnect Architectures in LLM Cloud Computing Systems

The scaling-up of large language models (LLMs) necessitates computing systems to have multi-processor-chip architectures, elevating the importance of chip-to-chip (C2C) communication. However, designing efficient C2C hardware architectures for LLM workloads faces three key challenges: generating realistic LLM-specific C2C traffic, accurately simulating hardware-level communication at scale, and efficiently exploring the exponentially large C2C design space. We propose C2C-Explorer, an adaptive Bayesian DSE framework that integrates a LLM-workload-driven traffic generator, a scalable interconnect simulator (switch/full-mesh, up to 512 chips), and a metric-guided evaluator into a workload-to-hardware optimization pipeline, enabling systematic C2C architectural co-design under realistic LLM workloads. Validated against FPGA-based C2C prototypes, the C2C simulator achieves 2.46-8.23% end-to-end timing error across diverse traffic patterns. Its hybrid cycle and event model further accelerates large-scale simulation by up to 7.8$\times$ over a pure cycle-accurate baseline. Applied to a 32-XPU DeepSeek-R1-671B inference workload, C2C-Explorer identifies configurations that improve goodput by 44.1% and reduce memory by 98.4%. C2C-Explorer is open-source and available at https://github.com/Selinaee/C2C-Explorer.

cs.DC↗
arXiv2026

TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution

Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empirical analysis reveals inherent topology quality limitations in real-world MAGs, including noisy interactions, missing connections, and task-agnostic relational structures. A single graph derived from generic relationships is therefore unlikely to be universally optimal for diverse downstream tasks. To address this challenge, we propose Task-aware Modality and Topology co-Evolution (TMTE), a novel MGL framework that jointly and iteratively optimizes graph topology and multimodal representations toward the target task. TMTE is motivated by the bidirectional coupling between modality and topology: multimodal attributes induce relational structures, while graph topology shapes modality representations. Concretely, TMTE casts topology evolution as multi-perspective metric learning over modality embeddings with an anchor-based approximation, and formulates modality evolution as smoothness-regularized fusion with cross-modal alignment, yielding a closed-loop task-aware co-evolution process. Extensive experiments on 9 MAG datasets and 1 non-graph multimodal dataset across 6 graph-centric and modality-centric tasks show that TMTE consistently achieves state-of-the-art performance. Our code is available at https://anonymous.4open.science/r/TMTE-1873.

cs.LG↗
arXiv2026

GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking

Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which frequency bands carry the perturbation. Although such perturbations can elicit unsafe responses, repeatedly applying a universal perturbation across diverse inputs may also degrade utility on normal tasks, leaving a conspicuous behavioral footprint that may expose the attack to users or automated monitoring systems and thereby compromise its stealthiness. To determine whether full-band perturbation is necessary, we vary coverage from partial-band to full-band. Jailbreak Success Rate (JSR) varies non-monotonically, while utility degradation grows with coverage. This mismatch shows that selected bands can yield stronger attacks with less utility degradation than full-band perturbations. Based on this observation, we propose GRM, a utility-aware, frequency-selective jailbreak framework that ranks Mel bands by the ratio between jailbreak contribution and transcript sensitivity, confines a universal perturbation to selected bands, and regularizes deviations from the intended request semantics. Experiments on four ALLMs show that GRM achieves an average JSR of 88.46\% while substantially reducing utility degradation across benign transcription and response tasks relative to baselines. Our code is available at \href{https://github.com/159753Fetter/GRM}{this repository}. Warning: This paper contains potentially sensitive content.

cs.SD↗
arXiv2026

DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training

Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification. However, unlike agent tasks, coding agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution of independent change indistinguishable. Existing RLVR methods mostly leverage the outcome reward or step-level reward, which fails to dive into a code diff and makes unique properties of coding actions invisible to training. In this paper, we propose Diff-in-Diff Policy Optimization (DiDPO), a critic-free RL method that constructs fine-grained credit units directly from the structure of code diffs. DiDPO organizes multi-turn coding interactions into multiple thought--action steps and discovers code diffs across sampled trajectories. It then selects anchors by aggregating highly similar sub-diffs split from each whole diff by our ``groupability score'', which provides the splitting schema that optimally balances the semantic scope of anchors and the group mass they may form. Finally these anchors form advantage groups and project the diff-level advantage back to individual response tokens. Experiments on long-horizon coding and reasoning benchmarks show that DiDPO significantly outperforms strong agentic RL baselines. On Qwen2.5-7B-Coder, DiDPO exceeds comparable methods by over 10\% and narrows the gap with far larger models, offering a principled framework for fine-grained credit assignment in coding agent training. We also open-source verl-code, an agentic rl codebase that supports various RL methods and coding benchmarks.

cs.AI↗
arXiv2026

Three-Body Earth-Moon Transfers with Different Departure/Arrival Orbital Altitudes: New Phenomenon and Diffusion Model-Augmented Construction

Construction of Earth-Moon transfers is the basis of missions to explore the Moon and cislunar space. The traditional grid search method suffers from a relatively low convergence rate and computational efficiency, mainly focusing on the distribution of transfer characteristic parameters. Moreover, when constructing transfers with different departure/arrival orbital altitudes, the process of grid search and trajectory correction should be repeated with a low convergence rate and computational efficiency. To address these limitations of the traditional grid search method, this paper is devoted to exploring an effective way to augment the grid search method. Bi-impulsive Earth-Moon transfers from a circular Earth parking orbit to a circular Moon target orbit in the Earth-Moon planar circular restricted three-body problem are considered in this paper. Firstly, the transfers are constructed, and the corresponding solution space is explored in terms of construction parameters, including departure phase angle at the Earth parking orbit, initial-to-circular velocity ratio, and time of flight. An interesting phenomenon about the discontinuous behavior of the time-of-flight distribution with respect to departure phase angle is identified. This phenomenon is further used to train a diffusion model, which aims to augment the traditional grid search method and generate high-quality initial guesses for transfers with different departure/arrival orbital altitudes. The construction results of the proposed method are presented and analyzed. The proposed diffusion model-augmented grid search method improves the convergence rate by 47.34-56.25% and saves the wall-clock time by 39.39-40.52% over the traditional grid search method relatively, while ensuring comparable transfer characteristics.

math.OC↗
arXiv2026

Optimal Measurement of Drone Swarm in RSS-based Passive Localization with Region Constraints

Passive geolocation by multiple unmanned aerial vehicles (UAVs) covers a wide range of military and civilian applications including rescue, wild life tracking and electronic warfare. The sensor-target geometry is known to significantly affect the localization precision. The existing sensor placement strategies mainly work on the cases without any constraints on the sensors locations. However, UAVs cannot fly/hover simply in arbitrary region due to realistic constraints, such as the geographical limitations, the security issues, and the max flying speed. In this paper, optimal geometrical configurations of UAVs in received signal strength (RSS)-based localization under region constraints are investigated. Employing the D-optimal criteria, i.e., minimizing the determinate of Fisher information matrix (FIM), such optimal problem is formulated. Based on the rigorous algebra and geometrical derivations, optimal and also closed form configurations of UAVs under different flying states are proposed. Finally, the effectiveness and practicality of the proposed configurations are demonstrated by simulation examples.

eess.SP↗