Papers

Dynamic multi-mode resource-constrained project scheduling requires decisions to be made under precedence constraints, limited resources, multiple execution modes, and uncertain activity durations. Genetic programming (GP) can automatically evolve heuristic rules for such problems, but its simulation-based fitness evaluation is computationally expensive. This study investigates phenotypic characterisation (PC) in surrogate-assisted GP to evolve higher-quality scheduling heuristics under a fixed budget of full simulation-based fitness evaluations. A key question is how GP individuals should be encoded into phenotypic characterisations to support effective fitness estimation. To answer this question, three PC encoding schemes with different levels of information richness are designed: priority-value encoding, which preserves raw rule outputs; rank encoding, which captures candidate ordering; and binary encoding, which represents final scheduling decisions. These encodings are combined with different distance metrics to measure behavioural similarity between GP individuals. The experimental results show that binary encoding with Euclidean distance provides the most effective and robust surrogate guidance. Further analyses show that surrogate estimation accuracy alone does not fully explain the performance differences. The PC representation also determines how effectively phenotypically redundant offspring are removed and how much behavioural diversity is retained after preselection. Ablation experiments further demonstrate that duplicate removal and surrogate preselection provide complementary benefits, with their combination producing the largest improvement. These findings highlight that effective surrogate-assisted GP depends not only on identifying promising offspring, but also on controlling redundancy and preserving useful diversity during evolutionary search.

Large language model (LLM)-based database migration is often treated as direct code transformation, although enterprise Oracle systems contain heterogeneous SQL and PL/SQL artifacts with different dependencies, execution order, complexity, and validation needs. This paper proposes a hybrid dependency-aware framework that identifies migration tasks, builds a cross-file dependency graph, condenses cyclic dependencies, and uses task specifications to generate specialized migration agents at runtime. The deterministic path combines ANTLR-based parsing with typed dependency extraction, while an LLM fallback is invoked only for units that cannot be parsed reliably. On a corpus of 116 Oracle files, the pipeline produced 1,037 units with zero coverage gaps and 1,271 AST-derived dependencies. The fallback processed 165 parse-error units, recovered 496 additional validated dependencies, eliminated unresolved-dependency units, and increased resolved internal edges from 446 to 527. The graph contained four dependency-respecting phases, while cycle handling was validated separately using Tarjan SCC condensation. A complementary experiment on 1,006 PL/SQL files regenerated 623 scripts (~62%), of which 380 (~61%) executed successfully in PostgreSQL 16. Tables achieved about 85% regeneration success, whereas no query regenerations succeeded under the evaluated specification-mediated baseline, and procedural objects remained strongly dependent on schema context. These results motivate dependency-aware context delivery, task-specific validation, and differentiated agent routing. The paper also formalizes task-to-agent mapping, introduces monitoring and diagnostics for execution feedback, and defines a controlled comparison of monolithic, static-decomposition, dependency-aware, and dynamically orchestrated migration strategies.

Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmarks such as BrowseComp-Plus shows that well-configured lexical retrieval can surface high-quality evidence, yet agents may still fail to connect documents carrying evidence to the gold documents. We identify a deep research agent's first retrieval move as an important design decision for this setting. We introduce Question's Gambit, a first-move retrieval module that decomposes the question into a set of clues, reformulates them into complementary searches, consolidates the retrieved results, and reranks the candidate pool before the agent begins its iterative search-and-reasoning process. This produces an opening context designed to support both clue aggregation and final-answer verification. We further evaluate on MultiHop-RAG to test whether these benefits transfer beyond BrowseComp-Plus to a more conventional multi-hop question structure. Experiments on BrowseComp-Plus show that Question's Gambit improves retrieval recall and downstream agent accuracy over strong baselines, improving answer accuracy from 83.1% to 90.5% with gpt-5.5 over Pi-Serini, the strongest reported agentic baseline. Our results confirm that effective agentic deep research depends not only on the tools available inside the loop, but also on the quality of the first move. We published our implementation publicly at https://github.com/radinhamidi/Question-s-Gambit.

We present an automated pipeline that converts NCERT textbooks into interactive video explanations that respond directly to user queries. A user uploads a PDF and asks a question; the system then generates a video-based explanation as output, handling both text and visual elements from the PDF for multi-modal retrieval and response generation. The pipeline combines a Retrieval-Augmented Generation (RAG) model with generative multimedia components. The RAG stage is optimized for the structure of NCERT textbooks and performs best on content from those books. Given a user query, the RAG model retrieves relevant content from the PDF and generates a multi-scene script containing narrative explanations and structured visual prompts aligned with the textbook's explanatory style. These prompts are passed to a Stable Diffusion module, implemented layer by layer for interpretability and control, which generates contextually relevant images. The images are then processed by DynamiCrafter to produce animated sequences. Finally, a Google Text-to-Speech module generates synchronized narration, aligning speech with the visual scenes through time-based control. The result is a coherent video explanation integrating animation, narration, and textbook-aligned visuals, transforming static educational material into an engaging learning experience. By combining multi-modal document retrieval, generative visual models, animation frameworks, and speech synthesis, this pipeline demonstrates a scalable approach to delivering interactive, personalized digital education content.

We revisit a multiterminal lossy source coding problem named successive refinement and derive the rate-distortion-perception region under the strong-sense perfect perception constraint in the presence of unlimited common randomness. Specifically, in successive refinement, one aims to compress a source sequence and allows two distinct decoders to recover the source sequence at different distortion levels. By imposing the strong-sense perfect perception constraint, our results refine the previous result by analyzing the impact of the perceptual quality. Our achievability proof is inspired by output constrained lossy source coding and our converse proof adapts the proof steps of the standard successive refinement problem. Furthermore, we provide a numerical example of the Bernoulli source to illustrate our result and show that the Bernoulli source under Hamming distortion is successively refinable even with the strong-sense perfect perception constraint.

Many engineering building blocks behave as multi-port linear time-invariant systems. RF cavities, photonic devices, and superconducting quantum chips, despite their different underlying physics, all share a common mathematical structure for their port-level response. Each entry of the response matrix is a sum of contributions from a small number of intrinsic resonant modes, the pole-residue form. A model capable of predicting such responses for arbitrary geometries and arbitrary port configurations, while simultaneously extracting the underlying eigenmode structure, could therefore offer a design principle potentially applicable across all these domains. We propose a neural framework that learns this modal decomposition end-to-end, supervised only by system-level observables and without supervising the modal parameters themselves. The architecture decomposes into a port-independent pole predictor and two port-dependent coupling predictors whose outputs are combined entry-wise, separating intrinsic from port-dependent features. This factorization yields a single trained model that generalizes to port counts unseen during training, whereas direct regression needs a separate model for each port count, with an output size that grows as $\mathcal{O}(N^2)$. Although the modal parameters are never supervised, the freely parameterized poles converge to the physical resonances, in agreement with poles extracted by the AAA rational approximation algorithm. We instantiate the framework in radio-frequency electromagnetic surrogate modeling. A model trained only on 2-port data accurately predicts $N$-port responses unseen during training.

Agent benchmarks evaluate policy compliance but assume each policy determines a unique correct action. Natural-language policies can violate this assumption through silence, ambiguity, or contradiction, admitting multiple defensible readings that a single gold trajectory cannot capture. Auditing two $\tau^2$-bench domains, we develop a taxonomy of such policy loopholes and show that affected tasks produce unreliable scores: they lower scores across different models in different ways and make every model less consistent across repeated trials. A cross-domain comparison reveals that exploitability requires both policy ambiguity and tool permissiveness: when policy complexity exceeds what tools can enforce, agents resolve gaps inconsistently and scores become unreliable. Policy specification quality sets the ceiling on evaluation quality. Benchmark developers should audit policies before collecting gold annotations.

Natural language prompts and skills serve as the strategic backbone of LLM-based agents. Recent advances in prompt and skill optimization have achieved notable gains, yet all existing methods optimize a single text template—missing the synergy among multiple complementary strategies. We propose MOSCOPT, a text-native, parameter-free algorithm that jointly optimizes a pool of $N$ skills and a gating skill $G$ that dynamically selects $K$ skills per step. To effectively optimize the skills, we build the EditAdam with internally maintained dual states. Through the three-phase interleaved updates with EditAdam, the system monotonically improves without gradient or parameter tuning. Extensive experiments and detailed ablations across 5 benchmarks and 3 target LLMs demonstrate that MOSCOPT consistently outperforms all baselines, and confirm that both the mixture-of-skills architecture with selective activation and the collective evolution with three-phase interleaving are essential to its superior performance. Code is released https://github.com/zhangzhenyu13/SummerClaw/tree/master/summerclaw/agent_trainer/algorithms/moscopt.

This paper addresses the angle-based formation tracking problem for a class of heterogeneous planar underactuated agents subject to disturbances. A representative example is a group of underactuated surface vessels (USVs) operating in the surge-sway-yaw plane, in which each vessel has three degrees of freedom but only two independent control inputs, which are surge force and yaw moment. The desired formation is characterized by a set of longitudinal offset points, referred to as hand points, together with prescribed angular constraints among triplets of these points. The formation tracking problem is studied on a leader-follower interaction graph, assuming the leader moves at constant velocity. Under the assumption that relative velocity measurements are available, the first control law achieves asymptotic formation tracking with internal stability guarantees. Moreover, a second algorithm that does not rely on relative velocity information is introduced, which successfully drives the followers' hand points to their desired configuration. Numerical simulations involving USVs are presented to validate the effectiveness of the proposed approaches.

Graph property testing asks whether a massive graph satisfies a given property, or is far from doing so, using only a sublinear number of queries to the graph. Since property testers typically inspect only a small, randomly sampled portion of the input, they appear naturally compatible with differential privacy and privacy amplification by subsampling. Despite this, few results link these two fields. We initiate a systematic study of differentially private graph property testing with the goal of designing efficient testers with formal privacy guarantees in the dense and bounded-degree graph models. We develop new privacy amplification theorems for several widely used graph-sampling procedures such as induced subgraph sampling, random walks and k-disc sampling. We then leverage these privacy amplification techniques to design a private canonical tester in the dense graph model, as well as private bipartiteness testers and subgraph freeness testers in the dense and bounded-degree graph models. Finally, using the new privacy amplification theorem for k-disc sampling, we prove that every property of hyperfinite graphs is privately testable. The resulting query complexities of our private testers are comparable to those of their non-private counterparts.

The tensor rank of $n\times 2$-with-$2\times m$ matrix multiplication is at least $\left\lceil \frac{24m+2}{5} \right\rceil$ if $m\ge n=3$ and at least $(n+2)m+n-3$ if $m\ge n\ge 4$, over arbitrary fields. This result matches the Hopcroft-Kerr upper bound for $n=3$ and $m\le 6$.

Compressed sensing (CS) reconstructs images from highly limited measurements, but existing deep unfolding methods are typically driven by first-order optimization and weakly exploit the optimization states generated during reconstruction. To address these limitations, we propose a Newton deep unfolding network (NDU-Net), which, to the best of our knowledge, is the first deep unfolding framework that leverages second-order optimization for CS reconstruction. Specifically, NDU-Net introduces a Newton update (NU) module to estimate Newton-type update directions and generate optimization states that characterize the current reconstruction process. Furthermore, a Newton-guided multi-scale prior (MP) module is designed to incorporate these optimization states into multi-scale feature restoration, thereby enabling the learned prior to adapt to the current reconstruction stage. Experimental results under different CS ratios confirm that our proposed NDU-Net achieves promising reconstruction performance and exhibits enhanced robustness. Our code is available at https://github.com/xianchaoxiu/DNU-Net.

What must a neural system be capable of to implement language? Current research annotates stimuli with linguistic variables and tests which electrodes, voxels, or language-model layers predict neural activity. Yet predictive success leaves mechanisms under-constrained. Here, we show that algebraic properties of language specify invariants that mechanisms must preserve: non-associative hierarchical grouping, commutativity, recursive closure, access to substructures, and structured workspace transitions. We term this the Neural Admissibility Program (NAP). Syntactic structure building is analyzed algebraically, with candidate mechanisms offered for each requirement: content-addressable workspace memory, graph-structured transient dynamics scheduling structure-building operations (e.g. stable heteroclinic channels), and a phase-coupled sealing operation recording grouping. Simulations show that a corrected Marcolli-Berwick entropy-optimized binding gate preserves grouping only within a narrow commitment band. As an alternative, we propose a novel neural binding operation we term 'Meld': two constituent populations converge through shared synapses, integrate sublinearly, and saturate. Meld is, to our knowledge, the closest neurally plausible composition law to syntactic Merge. It preserves every NAP invariant, uses known cortical operations, and recovers hierarchical structure at every tested depth and temperature. It predicts that effective population dimensionality separates alternative bracketings and that the composite depends on constituent disagreement. Importantly, the laws decoding bracketing most accurately are a priori inadmissible, showing that decoding accuracy alone cannot adjudicate between mechanisms. By specifying how neural dynamics can remain faithful to linguistic structure, the NAP changes the criterion by which neural implementations of cognition are evaluated.

Real-time pedestrian detection in driving scenes is constrained by three coupled failure modes: tiny targets lose discriminative evidence, occlusion weakens geometric support, and weather or illumination changes distort appearance statistics. We formulate the detector through a unified contour-guided spectral routing view rather than treating frequency processing, attention, and boundary reasoning as independent add-ons. The detector routes information in a prescribed order: spatial evidence is first augmented with global spectral context, deep representations then exchange spatial and spectral cues, and cross-scale fusion is finally conditioned on boundary–semantic disagreement. This ordering yields a compact representation pipeline in which low-frequency context stabilizes global structure while high-frequency evidence protects small-object contours. We further retain a wavelet-subband training transformation that perturbs low- and high-frequency coefficients independently, targeting appearance shifts caused by fog, rain, snow, and low illumination. The formulation exposes a single routing variable at each stage and distinguishes reusable signal transforms from the task-specific policy that decides where each signal is injected. On CityPersons, the proposed detector obtains 70.4 AP$_{50}$ and 44.2 AP$_{50:95}$, compared with 68.1 and 42.2 for RT-DETR, while the full wavelet-augmented configuration reaches 71.1 and 44.6.

Cryptanalytic model extraction aims to reconstruct a functionally equivalent model through black-box interactions with the victim model. Under the fundamental assumption that the network architecture is completely known, existing attacks achieve the goal by recovering the model parameters. In this paper, we explore whether this assumption can be removed practically. Focusing on ReLU fully connected networks, which are widely studied in this field, we propose a guess-and-determine framework that jointly recovers the network architecture (including network depth and hidden-layer dimensions) and the model parameters. This framework is based on a simple yet effective high-level idea: after designing a parameter recovery attack under the known-architecture assumption, we can analyze the architecture-sensitive traces observed during parameter recovery to recover the network architecture. We identify two such traces in differential extraction attacks: (i) a zero suffix in the merged weight vectors produced by signature recovery, whose length reveals the hidden layer dimension; and (ii) an equality pattern in the preimage-based sign recovery, which occurs only under the true hidden layer dimension. These two signals give rise to two routes for network architecture recovery. For the second-to-last layer, we further propose two methods, one for identifying it, and one for recovering its dimension. Practical end-to-end attacks are implemented on a wide range of ReLU neural networks, including both expansive and non-expansive networks. To the best of our knowledge, this is the first time the feasibility of achieving functionally equivalent extraction on deep neural networks, after removing the known-architecture assumption, has been demonstrated in practice.

Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background contexts. Achieving this objective requires jointly satisfying three coupled requirements: foreground preservation to retain target integrity, semantic compatibility to select plausible concealment contexts, and appearance assimilation to reduce visual discrepancies. Recent approaches predominantly rely on task-specific training on camouflage datasets to address these requirements, incurring substantial computational cost and limiting generalization beyond the training domain. To address these limitations, we formulate training-free CIG as a concealment-oriented paradigm that preserves the target while reducing its perceptual separability from the synthesized surroundings, rather than maintaining its visual prominence, without parameter updates. We instantiate this paradigm with FreeCam based on a frozen inpainting diffusion framework to preserve the foreground. Within this framework, a Contextual Reasoning Module exploits frozen multimodal priors to infer an environment favorable to concealment, thereby promoting semantic compatibility, while an Intrinsic Appearance Module extracts low-level color and texture cues from the foreground to guide background synthesis toward appearance assimilation. Extensive experiments demonstrate that FreeCam achieves state-of-the-art generation quality and camouflage effectiveness without task-specific training, while its generated images provide synthetic supervision for camouflaged object detection and reduce target detectability under general object detectors.

Soft robots are commonly sought for safety-critical interactions in delicate environments, where accurate position and orientation control is imperative. Model predictive control (MPC) offers a solution, but it requires a model of the robot's infinite-dimensional nonlinear dynamics that is at once accurate and computationally cheap. Recent theory on adiabatic spectral submanifolds (aSSMs) and their applications to soft robots provide data-driven model-reduction methods to construct such models. Here, we extend these methods to identify aSSMs from enlarged observable datasets and upgrade the currently available aSSM-MPC schemes. Evaluated on a high-fidelity finite-element simulation of a pressure-actuated soft arm, our controller reduces position and orientation tracking error by more than 60% compared to existing data-driven baselines.

Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remain system-specific and require substantial retraining when network configurations, generation mixes, or state-variable sets change. Uni-TSA introduced a general-purpose TSA framework that combines channel-independent modeling with a pretrained large language model (LLM) predictor. Nevertheless, its application to heterogeneous systems is limited by ambiguity in short observations, a mismatch between numerical trajectories and LLM embeddings, neglected coupling among state variables, and the high inference cost of dense backbones. This paper proposes LLaTSA, an LLM-aligned framework for general-purpose trajectory-based TSA. LLaTSA first incorporates operating conditions, disturbance attributes, and state-variable identity through a structured textual prefix. It then aligns normalized temporal patches with a TSA-related vocabulary before processing them with a pretrained sparse decoder-only mixture-of-experts (MoE) backbone. A state-variable coupling module captures coordinated post-fault evolution, while teacher forcing and rollout-based training support iterative long-horizon prediction. Case studies on multiple test systems demonstrate accurate trajectory prediction, reliable stability discrimination, and effective adaptation across unseen scenarios.

Log-Structured Merge-tree (LSM) aims to achieve high write throughput, but is known to experience the write stall problems when subjected to sustained write pressure. We quantify the occurrence probability and average duration of write stalls in LSM using a queuing model in the write–flush–compaction pipeline, moving beyond existing empirical analysis. The proposed model demonstrates that a monolithic LSM with a single pipeline cannot eliminate write stalls, revealing that internal sharding within the LSM offers an opportunity for fundamental write stall mitigation. To break this structural bottleneck, we propose DiaLSM, an internally shard-based LSM architecture. Instead of forcing all writes through one pipeline, DiaLSM splits the write–flush–compaction path into multiple independent shards and employs dynamic fallback redirection, allowing writes to proceed even when some shards stall. Implemented on RocksDB, DiaLSM achieves up to 2.4x higher throughput, 94% lower stalls, and significantly lower latency than state-of-the-art methods ADOC and Sub-Compaction, as demonstrated by db_bench, YCSB, and Sysbench OLTP evaluations.

Transmission grids are increasingly stressed by the fluctuating nature of renewable energy sources and by increasing electricity demand. Such grids were mainly built for a different generation fleet and load conditions. Grid topology optimization offers the possibility to redistribute power flows by modifying the busbar topology of substations in the grid. However, the combinatorial explosion of feasible busbar configurations makes topology optimization impractical for system operators. This paper proposes a methodology to identify a small subset of high-value busbar topologies to capture the economic benefit of topology optimization across a range of renewable-demand patterns. The optimization model is based on a LPAC approximation of the optimal power flow formulation, and AC-feasibility checks of the optimal topology applied to the IEEE 118-bus test case. In the test case, we select two distinct pairs of substations (46-49 and 24-69) and we optimize their topology separately over 365 clustered timesteps with different wind and load conditions. For each pair, we identify the four most recurrent optimal topologies and evaluate their performance under standard, and congested conditions, with and without a discrete load growth. Results show that selecting from this reduced set of topologies reduces total generation costs by up to 0.147% compared to a plain AC-OPF. In addition, we show the influence of topology optimization on the hosting capacity of selected busbars under discrete load growth. Our findings provide a practical methodology for system operators to select a subset of optimal busbar topologies to be used in their grid for different wind-load conditions, resulting in decreasing generation costs without the computational and operational risks of real-time switching decisions.

Reliable small-molecule identification often requires complementary evidence from multiple spectroscopic measurements. In practice, however, spectra may be unavailable, degraded by measurement-related variations, or even incorrectly associated with a sample, thereby hindering accurate molecular identification. Herein, we propose a multimodal mixed-condition training strategy that accommodates missing, degraded, and mismatched measurements for small-molecule structure identification. The strategy incorporates chemical and spectroscopic knowledge through predefined missing-input configurations, modality-specific spectral perturbations, and chemically informed spectrum replacements. Models were trained on 635,441 samples comprising mass spectrometry (MS), infrared (IR), and nuclear magnetic resonance (NMR) simulated spectra from the Multimodal Spectroscopic Dataset (MSSD). They were then systematically evaluated on 79,462 held-out samples across 30 views designed to represent variations in spectra. A controlled comparison of complete-input and mixed-condition training under concatenation and mixture-of-experts (MoE) fusion showed that the training strategy was the principal source of improvement. For MoE, mixed-condition training increased the mean reciprocal rank (MRR) by 6.08% (from 0.9203 to 0.9763) and the top-1 molecular identification rate by 7.67% (from 89.50% to 96.36%). Notably, under single-modality inputs, IR MRR increased 2.15-fold (from 0.4337 to 0.9307), while MS MRR increased 2.31-fold (from 0.3711 to 0.8575). With the proposed strategy, complete-input performance remained high, while sample-level mismatch detection also improved. Together, these results highlight the potential of multimodal mixed-condition training for practical molecular identification by explicitly addressing incomplete, degraded, and mismatched measurements encountered in real-world analysis.

We study exploration of anonymous, port-free graphs by a single agent with no internal memory. To compensate for the lack of memory, the agent uses writable vertex colors as external memory. From every starting vertex, the agent must visit all vertices, return to its start, and terminate there. Throughout, recoloring is unrestricted, and the color count includes the common initial color. However, to our knowledge, no nontrivial color lower bound was known for unrestricted recoloring. We determine the optimal number of colors on two classes defined by block structure and prove the first nontrivial color lower bounds for unrestricted recoloring. First, a single three-color algorithm explores every tree and every simple cycle in $O(n)$ moves, and no algorithm with at most two colors explores $P_3$, the path on three vertices. Second, we give a four-color algorithm that explores every graph whose blocks are cycles or complete bipartite graphs in $O(n)$ moves, and we prove that no algorithm with at most three colors explores all subcubic pseudotrees. Hence four colors are optimal for every class between subcubic pseudotrees and this block-defined class. On cacti, this improves the previous five-color upper bound to a tight four. The lower bound reduces the possible initial actions by hand and rules out the remaining cases by a machine-checked SAT certificate on nine graphs with at most five vertices. Finally, we extend the known five-color algorithm for triangle-free graphs to graphs whose blocks are cliques or triangle-free, using $O(n\Delta)$ moves, where $\Delta$ is the maximum degree.

A chart may be declarative; authoring it is not. Visualization grammars often describe charts as finished specifications, whereas people construct them through a sequence of authoring actions. This mismatch can make visualization code difficult for humans to interpret and for machines to generate from human intent. ggaction addresses this gap by modeling the chart authoring process itself. In ggaction, individual authoring actions are abstracted as functions, and the authoring process is expressed as a chain of these functions. This representation more closely aligns chart designers' authoring intent with code specifications, making the code easily understandable to both humans and machines, including language models. Through a series of evaluations, we show that ggaction is sufficiently expressive to capture common chart authoring intents and outperforms widely used visualization grammars, including Vega-Lite and ggplot2, in both human and machine interpretability. ggaction is available at github.com/ggaction/ggaction.

AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document images largely underexplored. This omission is concerning because documents often appear in sensitive real-world scenarios, such as invoices, expense reports, certificates, and medical records. In this paper, we first construct a controlled diagnostic benchmark, AIGDoc-Pilot, and reveal that existing detectors suffer substantial performance degradation on AI-generated document images, with the mean AUC dropping by more than 7%. Based on this, we further reveal two document-specific properties behind this gap: generation artifacts exhibit strong spatial inconsistency across local regions, and text density significantly affects real-synthetic separability, where text-dense regions offer stronger discriminative evidence. Motivated by these findings, we construct AIGDoc, a larger document-centric dataset containing diverse real-world documents and AI-generated counterparts produced by multiple advanced generation and editing models. Extensive experiments on AIGDoc demonstrate that existing detectors still struggle to reliably identify AI-generated documents, while document-based training partially narrows the gap. Together, these results offer valuable insights for developing dependable and generalizable detectors in document-centric scenarios. The code and datasets will be made publicly available upon acceptance of the paper.

Medical vision-language models (VLMs) allow a single model to perform clinical image analysis tasks ranging from diagnosis classification to report generation. However, joint adaptation is challenged by heterogeneous output formats, conflicting task gradients, and imbalanced training data. Hence, we present Two-Stage Mixture-of-LoRA, a framework built on MedGemma-1.5-4B. The framework uses a shared-specific Mixture-of-LoRA architecture comprising one shared LoRA and six task-specific expert LoRAs, together with a two-stage training procedure. In Stage 1, we jointly train the shared LoRA and all task-specific expert LoRAs on all tasks. In Stage 2, we first freeze the backbone, the shared LoRA, and all non-target experts, and refine one task expert at a time. Classification and regression then receive an additional modality-balanced continuation, in which smaller modality groups are repeated to match the largest group. In the FLARE 2026 Task 3 test sets, the proposed method achieves 0.85 balanced accuracy for classification, 0.48 micro-F1 for multi-label classification, 0.79 detection F1, and 17.39 regression MAE. Code is available at https://github.com/YuanYL03/MICCAI-FLARE-2026-Challenge-Task3-2D.

Mapping crystalline phases at heterogeneous interfaces is essential for understanding material performance and degradation. However, structural heterogeneity, phase overlap, and local disorder complicate diffraction interpretation, while growing data volumes make manual analysis increasingly impractical. We introduce 4DMulti, a physics-guided learning framework for automated multicomponent identification from large-scale four-dimensional scanning transmission electron microscopy (4D-STEM) data. The supporting diffraction data resource comprises over 6 million high-quality experimental patterns and labeled patterns generated by Sim2real. A retrieval-conditioned latent diffusion transformer (Sim2real) translates simulated patterns into experimental-style examples under constraints designed to preserve Bragg geometry, while a rotation-invariant coordinate convolutional network identifies phases across in-plane rotations. 4DMulti achieves 98.82% classification accuracy on a five-phase experimental nanoparticle benchmark, with ablation studies supporting the complementary benefits of domain adaptation and rotation-invariant classification. We define diffraction-inferred structural complexity (DISC), a normalized predictive entropy score that quantifies phase-assignment ambiguity within a specified candidate phase library. We apply 4DMulti to generate structural maps of superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. 4DMulti connects simulation-derived crystallographic knowledge to automated experimental interpretation, establishing a foundation for scalable analysis of complex interfaces and data-driven discovery of interfacial design principles.

Computed tomography (CT) plays an essential role in clinical workflow to improve patient outcomes. However, access to CT imaging and specialist interpretation remains limited, particularly in rural, regional, remote (RRR), and other resource-limited settings. Recent advances in mobile CT, telehealth, and artificial intelligence (AI) provide opportunities to extend advanced imaging services to populations in RRR settings. This review examines: 1) mobile CT systems deployed in trucks, trailers, ambulances, and other mobile platforms; 2) telehealth technologies supporting CT-based healthcare; and 3) AI for CT that has received regulatory authorisation or is currently deployed in clinical practice. Applications are evaluated across four clinical functions: screening and diagnosis, patient monitoring, risk prediction, and intervention or therapeutic decision support. The review covers neurological, thoracic, cardiovascular, abdominal, oncological, musculoskeletal, and interventional imaging, with particular attention to stroke, cancer, and other image-guided treatment. Other factors such as regulatory status, deployment status, and estimated technology readiness (TRL) level are compared. Current evidence indicates that mobile CT, telehealth, and AI for conventional CT are individually relatively mature, but fully integration of these technologies remains less widely deployed and validated in the clinical settings. Key barriers include regulatory variation, domain shift, connectivity requirements, cost, workflow integration, cybersecurity, and limited evidence of patient-level benefit. Future research should prioritise prospective, multicentre evaluation of integrated CT systems in real-world and underserved clinical settings.

Instruction-guided music editors typically process each request independently, limiting their ability to support workflows in which users progressively refine a track. We introduce AURA, a unified multimodal framework for conversational music editing. AURA uses a multimodal large language model to interpret the complete dialogue history, an optional image, and reference audio, distilling the editing intent into compact concept tokens. A concept-to-audio module injects these tokens and frame-aligned reference features into a frozen MusicGen backbone, enabling precise edits while preserving unaffected content. AURA optimizes only 91M parameters while retaining 1.9B frozen backbone parameters. Experiments on Slakh2100 and MoisesDB demonstrate substantial improvements in edit correctness and content preservation over existing instruction-guided methods, including a 4-5 times reduction in FAD for out-of-domain addition and removal.

Control barrier functions (CBFs) provide a mathematically grounded framework for enforcing local collision-avoidance constraints in autonomous mobile robots, commonly through optimization-based safety filters. However, a minimum-intervention CBF filter lacks task-level maneuver awareness and may fail to select a productive avoidance direction when multiple distinct maneuvers are locally viable, leading to safe but stalled behavior in geometrically ambiguous environments. This paper presents BIG-CBF, Behavior-Imagination-Guided Control Barrier Function with shared uncertainty, a two-rate navigation architecture that separates low-rate maneuver selection from high-rate safety filtering. Over a short horizon, six closed-loop feedback behaviors are imagined and evaluated using analytic CBF compatibility together with a lightweight objective accounting for task progress, freezing, smoothness, and switching. To reduce planning-execution mismatch, the imagination and execution layers share consistent uncertainty sources for relative-motion delay, obstacle prediction, zero-order-hold motion, and command-execution residuals, while a hard CBF remains the final safety authority. In a 3,600-episode comparative benchmark across nine scenarios, BIG-CBF achieves the highest overall task success rate of 99.78% while substantially reducing downstream CBF intervention. On a physical omnidirectional robot with onboard Jetson Orin Nano computation, BIG-CBF completes all 15 evaluation runs without a recorded contact event. Matched hardware comparisons against the non-shared variant further show lower CBF intervention energy and activation frequency, supporting improved consistency between maneuver selection and safety-critical execution.

Decentralized training enables large-model training over low-end GPUs and internet-grade connections, but communication along both data-parallel and pipeline-parallel axes becomes the primary bottleneck. We study post-pretraining adaptation in this setting. We propose an asynchronous two-circuit system: a fast compressed training circuit drives throughput using activation masking for pipeline-parallel (PP) transfer and compressed data-parallel (DP) synchronization, while a slow anchor circuit runs occasional unmasked forward–backward passes off the critical path. Then, we introduce a spectral correction optimizer that uses these delayed anchor priors to denoise masked gradients without blocking the fast stream. Although prior work has found aggressive activation compression unreliable, we show that masking supports post-pretraining adaptation at high compression rates when anchored this way. Pipeline-parallel compression alone yields up to a $9\times$ throughput gain, and combining it with data-parallel compression increases beyond $40\times$ over internet-grade $\sim 200$Mbps connections, while matching dense uncompressed performance across domain adaptation and continual pretraining.