Papers

Pneumonia is difficult to diagnose in older long-term care residents; multimorbidity and atypical presentations obscure signs, motivating operationally efficient objective testing. We analyzed multi-channel digital stethoscope recordings from 185 Japanese residents (73 pneumonia, 112 symptomatic without), using radiologist-confirmed chest X-rays and clinician diagnoses as supervisory signals that train convolutional neural networks, multimodal fusion, and channel-based variants with time-domain Grad-CAM interpretability. Models were evaluated with repeated patient-level cross-validation showing models with X-ray supervision outperformed clinician supervision (F1 0.729, accuracy 0.783 vs. F1 0.637, accuracy 0.711). Additionally, a three-channel selection protocol maintained performance (F1 0.736; accuracy 0.803), with two mid-thoracic sites ranking highest and Grad-CAM attention overlapping adventitious sounds. These findings indicate automated multi-channel lung-sound analysis can aid long-term care pneumonia diagnosis, with X-ray supervision being more reliable than clinical, and fewer channels preserving performance while lowering acquisition times.

This paper studies multivariate conformal prediction (CP), a distribution-free uncertainty quantification framework with finite-sample coverage guarantees. The efficiency of multivariate prediction sets hinges critically on the residual geometry encoded by the nonconformity score, while existing minimum-volume methods rely on quantile thresholds that ignore tail residual severity and implicitly bind geometry learning to coverage level. We propose a tail-aware geometry learning framework for conformal ellipsoids that decouples tail sensitivity in geometry learning from the final coverage guarantee. Using a two-split design, we learn the metric matrix via volume minimization under a CVaR constraint on an estimation split, then apply standard conformal calibration on a held-out calibration split. The resulting problem is convex and admits a bounded-reweighting interpretation that prioritizes high-residual samples. Moreover, we theoretically characterize the trade-off between ellipsoidal volume and tail severity. Experimental results demonstrate the effectiveness of the proposed method.

Diffusion language models generate text through iterative denoising, exposing intermediate trajectories before final answers are produced. We identify a recurring reasoning failure, stable-but-wrong lock-in, where an answer stabilizes early around an incorrect value while substantial denoising remains. Surface-level decoding signals such as confidence, entropy, margin, and answer stability are insufficient to reliably distinguish correct from erroneous lock-in. We formulate selective reasoning repair as a lightweight test-time planning problem and propose LOCKR, a hidden-state trajectory-guided planner that decides when to allocate additional computation, expands a structured set of targeted repair branches, and selects the most promising continuation using trajectory-aware verification. Across two diffusion language models and three mathematical reasoning benchmarks, hidden-state trajectories consistently outperform surface signals and single hidden snapshots for both wrong-lock-in detection and repair selection. On natural evaluation distributions, LOCKR yields absolute accuracy gains of 2.21–5.37 percentage points across all five evaluated settings, with repair rates ranging from 22% to 41%. These results establish hidden diffusion trajectories as actionable signals for selective test-time reasoning repair.

Aerial radiation surveys achieve higher sensitivity when the radiation detector is held close to the ground. Detector sensitivity falls off roughly with the inverse square of the distance to the source, so a detector flown high is slower to reach a given minimum detectable activity. Flying the vehicle low puts the propellers near the ground, where downwash can disturb the surveyed area and resuspend contaminated particulates. Tether suspension decouples the detector from the vehicle altitude, but leaves the payload unactuated and only indirectly controllable. We therefore present a vision-based control approach for an aerial sensing payload suspended on a tether beneath a heavy-lift drone. Because a survey plan is decided as radiation detections arrive, we design a pilot aid for commanding the survey trajectory manually with a handheld transmitter. The controller regulates the payload, rather than the vehicle, onto that trajectory. The system uses onboard sensors with a downward-facing camera fixed to the drone body tracking a ring marker on the payload. A four-state Kalman filter estimates the tether swing angles and rates from payload bearing measurements, and a linear quadratic regulator with integral action takes the payload position as the regulated output. In outdoor flight tests under wind, the payload-aware controller reduced payload tracking error during transit by 20% when compared against a vehicle-referenced baseline, with the cost of higher peak error on arrival at a waypoint.

Embodied navigation requires spatial representations that generalize across unseen environments, yet collecting large amounts of annotated data from real 3D environments is difficult. We propose NaviScale for semantic-map-based object navigation (ObjectNav), whose predictor can be trained on pairs of partial and complete semantic maps without reconstructing a complete 3D environment for every training sample. The framework generates large-scale semantic map training data by composing floorplans of real homes with room-level semantic and obstacle maps extracted from MP3D and HM3DSem. NaviScale increases data diversity in two ways: inter-room scaling increases floorplan-level structural diversity, while intra-room scaling fills each fixed floorplan with different combinations of room maps matched by room category. Visibility through Ray Casting (VisRC) converts the composed maps into partial observations that account for field of view, sensing range, and occlusion. The resulting dataset contains 192,000 semantic maps generated from 24,000 floorplans associated with 12,794 properties. With 300k training iterations and the training and inference settings described in this paper, the system reaches 64.3% SR and 34.8% SPL on HM3D, together with 43.1% SR and 16.8% SPL on MP3D, without changing the prediction architecture. Additional experiments evaluate the quality of the composed maps, the effects of semantic-segmentation errors, and deployment on a physical robot.

We address adaptive computation in 3D medical image segmentation: instead of designing another backbone, we ask how much spectral mixing each network stage needs and let optimization answer. We derive FHEAT, a two-parameter operator family, from the discrete cosine transform (DCT) solution of a fractional heat equation. A fractional order alpha and a diffusion strength D govern the operator, and at D=0 it is exactly the identity. Reparametrized by the semigroup time tau = D*alpha, same-resolution instances compose exactly, so any distribution of diffusion across same-resolution stages amounts to a single Sobolev-type regularizer of learned strength. This identity limit lets the optimizer of each layer, not the designer, decide whether global mixing is needed and how sharp it should be. We instantiate FHEAT in a lightweight U-shaped architecture (Light-UNETR) paired with a Kolmogorov-Arnold mixer (KAN3D) with adaptive rational activations, yielding FHEAT-Seg. At 5% to 20% label rates on three public benchmarks, training produces gradient-driven spectral sparsification: seven of the eight stage-level operators drive D to zero, and the survivor saturates at the sharpest low-pass (alpha ~ 0.9) in the decoder layer feeding the semi-supervised attention map. The retired layers become exact identity shortcuts at inference, cutting FLOPs from 4.29G to 0.90G (a 79% drop) at 0.975M parameters. Under a standard semi-supervised protocol, FHEAT-Seg reaches Dice scores of 90.47% (left atrium), 78.79% (Pancreas-CT), and 81.90% (BraTS 2019), ahead of five semi-supervised methods and the Light-UNETR baseline. The large variant also surpasses Light-UNETR-L under full supervision (Dice 93.09%, 85.11%, and 87.19%) with 2.851M parameters and 55.75G FLOPs. These results suggest that the allocation of spectral computation is a learnable property of optimization dynamics, not a manual design commitment.

Topology optimization (TO) remains computationally intensive due to repeated finite element analysis (FEA) evaluations required at each iteration. While neural network-based surrogates offer potential acceleration, existing approaches often suffer from gradient inconsistency between predicted objectives and sensitivities, leading to optimization instability. This work presents KATOsuper, an objective-agnostic framework that couples neural-reparameterized topology optimization with a Sensitivity-Consistent Fourier Neural Operator (SC-FNO). The framework employs the forward_split architecture, which derives deployed sensitivities via automatic differentiation through the predicted objective field and thereby preserves consistency between the predicted objective and the gradient used for optimization. The case studies include three 2D benchmark problems and three 3D structures considering compliance or stress minimization. A physics-informed multi-channel input encoding with Fourier position embedding enables resolution-invariant learning, supporting zero-shot extrapolation beyond the training resolution, with useful performance at moderate scaling factors and topology-preserving exploration at up to 64x without retraining. The framework extends to 3D through KATO3D, featuring novel KANConv3D blocks with learnable B-spline activations. KATOsuper demonstrates 15–110x deployment-time speedup over MATLAB baselines while maintaining competitive optimality, with the clearest gains observed in complex 3D and stress-optimization cases. The insight that sensitivity direction matters more than magnitude enables robust optimization even with approximate physics evaluation, extensible to other differentiable physics-driven design objectives.

Compiler optimizations traditionally rely on handcrafted heuristics that often fail to generalize across programs and architectures. We investigate whether large language models can participate in compiler optimization through a verification-centered systems architecture that couples generative rewriting with formal equivalence checking. Using lazification in LLVM IR as a case study, we fine-tune a code-centric LLM on transformations produced by Wyvern and embed Alive2 into a feedback loop that enforces semantic preservation for every generated rewrite. Correctness is enforced externally as a runtime control layer rather than learned implicitly. During inference, candidate transformations are symbolically validated and regenerated when necessary, ensuring accepted rewrites satisfy formal constraints. On the LLVM test suite, the fine-tuned model reproduces core optimization behaviors while applying fewer transformations overall. Although Wyvern remains faster on most benchmarks, 9.8% achieve comparable or improved runtime under the learned system, with no semantic violations observed. Verification overhead remains bounded and convergence stable. These results demonstrate that generative AI components can be safely integrated into compiler pipelines through deterministic validation and structured feedback, offering a scalable architectural pattern for trustworthy AI-driven software infrastructure.

Open-ended queries in modern Retrieval-Augmented Generation (RAG) are increasingly "diffuse," requiring a large set of documents to be assembled into a finite LLM context window. To ensure retrieval quality, systems use fast dual-encoders and more expensive cross-encoders (CEs) to score candidates. However, the CE budget $B$ is strictly bounded by latency and is often smaller than the context window capacity $k$. This mismatch makes standard reranking structurally flawed: it wastes compute verifying obvious top candidates while ignoring relevant documents further down the initial ranking. To address this, we introduce BoundaryMORPH, a novel algorithm that allocates CE budget specifically for the LLM's context capacity $k$. Using a Gaussian Process, BoundaryMORPH treats the initial dual-encoder ranking as a structural prior and intelligently spends CE calls on resolving top-$k$ set membership at the boundary, rather than seeking a single most-relevant document. Information from each CE call propagates to unscored documents, maximizing the utility of the budget. We demonstrate that BoundaryMORPH achieves state-of-the-art set retrieval quality across multiple models and datasets with open-ended queries ($+5.4$ nCG@100 over the strongest baseline).

Subgraph sampling reduces the training cost of large-scale graph neural networks, but sampling criteria may overlook the geometric roles of edges. We propose a resistance-curvature-guided sampling framework built on ERC-LG, a curvature approximation method for large-scale graphs. ERC-LG combines Johnson-Lindenstrauss projections with regularized multi-GPU batched conjugate gradient solvers, avoiding explicit Laplacian pseudoinverse computation and full embedding storage. The resulting curvature informs node- and edge-sampling probabilities for constructing GNN training subgraphs. Experiments show numerical agreement with pseudoinverse-based curvature and reduced runtime compared with CG-only computation. ERC-LG-based sampling variants achieve the highest mean accuracy on six of seven real-world datasets in downstream node classification.

Spatial transcriptomics (ST) measures gene expression in tissue context, but dense capture grids can be costly and may repeatedly sample morphologically similar regions. Most active learning strategies were developed for categorical labels and independent samples. We conduct a retrospective pool-based benchmark of active learning versus uniform Random sampling for ST, where expression vectors are high-dimensional and continuous and candidates are spatially correlated. Using two fully profiled public ST cohorts, we mask candidate expression vectors and simulate multi-round selection with uncertainty-based Monte Carlo dropout (MC-dropout) and temporal output discrepancy (TOD), and diversity-based CoreSet and TypiClust-inspired selection. We compare 160 completed configurations at 5%, 10%, 30%, and 50% of the fold-wide training spot pool under patient-level cross-validation, with a separate full-label reference. Within each budget, strategies share the selection schedule, morphology-to-expression predictor, and optimization protocol. We assess mean per-gene within-slide Pearson correlation coefficient (PCC), expression-cluster agreement, and Moran's I fidelity. On HER2-positive breast cancer, pooled mean PCC differences from Random across the four active strategies were -0.0176, -0.0117, +0.0056, and +0.0057 at 5%, 10%, 30%, and 50%, respectively. On cutaneous squamous cell carcinoma (cSCC), three strategies were below Random at 5%, and all four were below Random at 10%. On HER2-positive breast cancer, CoreSet and MC-dropout had lower PCC but higher expression-cluster agreement than Random at the two smallest budgets; this pattern did not reproduce on cSCC. Under the reported fixed training horizons, the evaluated active strategies do not consistently improve on Random at small budgets, and rankings depend on the evaluation measure.

Prediction with expert advice is a fundamental problem in online learning. When the time horizon $T$ is known in advance, the minimax cumulative regret over $n$ experts is asymptotically $\sqrt{\frac{T \ln n}{2}}$. This is achieved by the Multiplicative Weights Update algorithm with a learning rate tuned to $T$, and is known to be tight. If instead the regret bound is required to hold simultaneously at every time $t$, the best known guarantee has been $\sqrt{t \ln n}$—a factor of $\sqrt{2}$ worse—and it has remained unknown whether this factor of $\sqrt{2}$ is necessary. We show that it is not. We give an algorithm, requiring no knowledge of the horizon, whose cumulative regret satisfies $R_t \le \bigl(1 + O(\sqrt{\ln \ln n / \ln n})\bigr)\sqrt{t \ln n / 2}$ simultaneously for every $t \ge 1$.

Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the first grapheme-to-phoneme (G2P) benchmark for UGT in English, Vietnamese, and Korean, together with an inference-grounded taxonomy for fine-grained diagnosis. Existing G2P models and frontier LLMs exhibit a systematic canonical-to-non-canonical performance gap, reaching up to 66.8 PER points. As a benchmark baseline, we propose a simple compositional G2P approach that incorporates canonical-form evidence through exact-match lookup and staged decoding. Across matched ByT5 and Qwen2.5-0.5B backbones, explicit canonical-form modeling consistently reduces non-canonical G2P errors. The 0.5B variant also performs competitively with much larger few-shot frontier LLMs, highlighting the benefit of explicitly modeling canonical-form inference for UGT phonemization.

xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world views through a typed frontend and provider-owned CUDA runtime. Its reasoning modes share device data planes, but their execution boundaries differ: ordinary Datalog and exact inference are host-orchestrated, while certified resident recursive and Monte Carlo sampled cores record zero tracked host-device transfers before a bounded terminal receipt. The probabilistic path supports end-to-end gradients through GPU knowledge compilation from provenance to CNF to Decision-DNNF, exact weighted model counting, and backward gradients. A final smoothed circuit is certified against its source formula before caching or evaluation. Circuit caching yields a 2.74x MNIST-addition training speedup; a worst-case-optimal join subsystem yields a 27.96x geometric-mean gain over xlog's binary-join baseline. MNIST-addition accuracy matches Scallop's (0.9561 versus 0.9468), but no per-epoch speed claim is made because baseline epoch time varies with CPU quota. In five hub-skewed triangle-counting cases, the Souffle-to-fused-xlog execution-time ratio rises from 0.88x at 150k edges, where Souffle is faster, to 5.54x at 1.2M; fused peak device allocations are 85-1,033 MB versus 3,287-44,979 MB for the materializing arm. Exact inference is correctness-equivalent to but slower than ProbLog2. On a public video benchmark, a proximity predicate trained only through symbolic credit replaces hand-set geometry at unchanged held-out accuracy; within Event-Calculus rule search it fails ten-fold cross-validation and does not transfer on a leak-free split. On a maritime corpus, weighted clauses beat crisp selection by 0.065 F1, with the result reproduced by one chronological training pass.

The growing deployment of Internet of Things (IoT) devices has increased the need for privacy-preserving intrusion detection systems that operate directly on resource-constrained hardware. Federated Learning enables collaborative model training without sharing raw data, but conventional federated models are often too large and unstable for deployment on microcontroller-class devices. TinyML techniques enable compact neural networks but are typically designed for inference-only workloads. This work investigates combining Federated Learning with TinyML-based model compression for intrusion detection in IoT environments. We evaluate compression strategies including knowledge distillation, structured pruning, and quantization within a federated training pipeline. Preliminary results show that training stability plays a critical role in federated TinyML systems. In particular, server-coordinated cosine learning-rate scheduling improves Attack Recall from 46.7% to 93.85% while enabling substantial model compression and efficient edge deployment. These findings provide insights for designing lightweight and privacy preserving intrusion detection systems for IoT devices.

Sequential RecSys are central to modern personalization, exploiting user's historical interaction sequences to drive next-step decisions. Deep learning models, particularly CNN and Transformer-based architectures, have proven highly effective at capturing temporal dependencies in these histories. For transparency and trust, understanding which past interactions drive a given recommendation is increasingly important — both for developers auditing model behavior and for users seeking a rationale. However, the non-linearities that give these models their predictive power also render them black boxes, making it difficult to attribute decisions to specific interactions. While gradient-based, perturbation-based, and attention-based explainability methods exist, a systematic benchmark of their faithfulness for sequential recommendation is missing. We address this gap by introducing a dual-model masking metric in which one model supplies per-timestep attribution scores and a separately trained, masking-robust probe measures the resulting change in predicted probability. Using this metric, we benchmark ten XAI methods across CNN, Transformer, SASRec, and BERT4Rec backbones on KuaiRand and MovieLens, complemented by analyses of temporal attribution patterns, item popularity confounding, and robustness to input corruption. Our key findings are: (1) gradient-based methods, particularly GradientSHAP and Integrated Gradients, yield the most faithful and robust attributions; (2) raw attention weights are unreliable, but gradient-weighted attention restores faithfulness on shorter sequences, with degradation on longer horizons as softmax attention probabilities converge toward uniform importance scores, diminishing the method's ability to identify informative interactions; and (3) temporal attribution patterns in faithful methods reflect genuine task structure rather than recency or popularity bias.

Sparse communication in decentralized zeroth-order learning requires compatible peer-state coordinates. We characterize this one-hop condition and develop ZO-COSMO, coupling two-query estimation with average-preserving masked consensus using $q$ values per active link. Global supports serve all-neighbor mixing; matching updates require agreement only within each pair. We derive a sharp contraction-per-scalar bound within the matching class and convergence guarantees for the core and sparse-momentum updates. At fixed matching, exact moment identities characterize how shared directions preserve gradient-heterogeneity cancellation and redistribute estimation error and disagreement. Mechanism experiments cover unequal curvatures, noise, and sparse momentum. Further tests span $64$ synthetic agents and eight logical Qwen LoRA workers. At matched payload budgets, Qwen2-7B QNLI gains $3.65$ accuracy points over explicit-index Rand-$k$; edge-local updates gain $3.42$ and $2.53$ points over all-neighbor mixing on eight-worker complete and ring graphs. A matched-first-step ablation gives a $3.92$-point momentum benefit. Seed-aware and same-matching controls distinguish encoding, scheduling, and query correlation.

Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum-likelihood objectives Shen et al. [2016]. Although introduced a decade ago, recent work shows renewed potential for risk-based optimization in modern language models Yang et al. [2024], Jinnai et al. [2025]. We apply MRT to power outage report generation for the Outage Data Initiative Nationwide (ODIN), transforming heterogeneous reports into standardized XML compliant with CIM IEC 61968-3. Our MRT approach improves Qwen2.5-7B-Instruct overall accuracy from 16.20% to 68.95%, demonstrating the effectiveness of sequence- level optimization for domain-specific structured generation

Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean Spearman correlations of 0.81-0.88. Moving the same sound between speech and pauses changes this pattern. At quiet to moderate levels, pause interference produces larger drift, while speech interference usually causes greater loss on intent recognition, speaker verification and speech recognition. Emotion recognition shows a weaker placement effect. Pause interference also changes speech-frame representations beyond the injected region. Even below the estimated recording background, interference can change embeddings as much as repeated speech takes do. Drift helps rank the effects of different sounds, but larger drift does not consistently indicate greater task loss.

Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes converge to redundant features, fail to capture diverse semantic parts, and lack quantitative interpretability assessment. We propose Diversity-Aware Prototype Learning (DAPL), which enforces prototype diversity through architectural constraints rather than explicit regularization. Our approach leverages multi-head self-attention with strict one-to-one attention-to-prototype mapping, ensuring each prototype specializes in distinct visual features. We further introduce foreground-aware training to focus prototypes on semantically meaningful regions and develop comprehensive evaluation metrics (Coverage and Diversity) for quantitative interpretability assessment. Experiments on CUB-200-2011 demonstrate substantial improvements: DAPL with foreground-aware training achieves 81.69% accuracy with 0.596 Coverage and 0.427 Diversity, providing the best overall balance across all evaluated prototype-based methods. Code is available at https://github.com/xinmiaolin/DAPL.

With the rising computational and monetary costs of training large language models (LLMs), checkpointing—periodically storing model states for recovery—becomes essential for fault tolerance. Conventional checkpointing entails a severe trade-off between checkpoint frequency (I/O overhead) and computational recovery (recovery time). State-of-the-art approaches mitigate this cost through pipelining checkpoint I/Os, differential checkpointing, or in-memory persistence, yet none leverage the distinct characteristics of LLM training dynamics, where model weight updates are non-uniformly distributed across transformer layers. This observation implies that saving all weights each time might not be efficient. Inspired by this observation, we present LayerCheck, a layer-wise adaptive checkpointing framework that selectively persists layers whose updates exceed a threshold. This design avoids periodic I/O bursts by distributing layer-wise checkpoint writes over time, resulting in smoother and more balanced I/O profiles. Upon recovery, LayerCheck reconstructs a mixed-timestamp composite model state by aggregating the most recently persisted versions of each layer together with their matching optimizer states. Under a bounded per-layer staleness guard, this introduces a controlled perturbation: under standard Adam assumptions it adds a bounded staleness term, and empirically the post-restart loss deviates from the failure-free trajectory by at most 0.54%. Empirical results on multiple open-source LLMs with different datasets further demonstrate that recovered models preserve the original convergence behavior and accuracy while substantially reducing checkpoint overheads. Specifically, LayerCheck achieves up to 22.6x reduction in total checkpoint size and 1.31x reduction in end-to-end training time compared to state-of-the-art systems, significantly lowering the cost of checkpointing.

Zeroth-order (ZO) optimization is an attractive option for memory-efficient LLM fine-tuning, but its fault tolerance remains underexplored. Unlike first-order training, ZO progress can be represented by lightweight seed-and-scalar step logs, yet naive log-only recovery still incurs replay cost that grows with training progress, and shortcut replay does not preserve the executed floating-point trajectory. We present ZOCheck, a fault-tolerant ZO training system that exploits this replayable structure through a CPU shadow process that continuously replays logged updates, materializes consistent recovery images off the GPU critical path, and persists them asynchronously. ZOCheck therefore combines non-blocking checkpointing during training with fast recovery from a near-current state. We also develop a cost model for choosing the snapshot policy under realistic failure rates. Experiments show that ZOCheck reduces checkpoint overhead by up to 219.7x and recovery latency by 1.55x on average compared with asynchronous full-state checkpointing, translating into up to 21.3x lower end-to-end wasted time across the evaluated failure rates, while preserving exact recovery behavior.

Dissipativity is a fundamental system-theoretic property closely related to stability, passivity, and input–output stability, and is particularly important in robotics, where learned dynamics models are often embedded within feedback control loops. However, most existing approaches for learning dissipative dynamics are based on continuous-time formulations, which require ODE solvers during training or inference and can therefore be computationally expensive. Moreover, because practical implementations are inherently discrete-time, direct discretization of a continuous-time passive system does not necessarily preserve passivity, motivating the need for explicit discrete-time guarantees. This study proposes a method for learning incrementally dissipative dynamics from input–output time-series data using a deep multilayer perceptron formulated directly in discrete time. Through a constrained parameterization and a dedicated training procedure, the proposed model guarantees incremental dissipativity by construction rather than through regularization. Lyapunov-based analysis establishes the corresponding dissipativity and stability guarantees, while simulations on robotic dynamical systems demonstrate competitive prediction accuracy, computational efficiency, and consistent preservation of incremental dissipativity compared with baseline methods.

Compositionality, the ability to represent complex acoustic scenes as combinations of simpler sound sources, is central to auditory perception and classical additive signal models. Still, it remains unclear whether modern pre-trained audio representations internalize additive structure without compositional supervision. Existing evaluation frameworks of audio compositional reasoning largely focus on cross-modal audio-text alignment, leaving open whether audio representations themselves exhibit additive compositional structure independent of text grounding, analogous to vector arithmetic in word representations. To investigate this, we adopt a two-step diagnostic for frozen audio representations. First, we quantify linear alignment between representations and sound source labels using canonical correlation analysis. Second, we test additive compositional generalization via leave-one-combination-out reconstruction, grouping clips by exact source-label set, averaging their representations, and predicting held-out means from per-source contributions fitted only on training combinations. With larger combination holdouts, CLAP outperforms the permuted and label-overlap baselines on FSD50K, while the speech models do not outperform the label-overlap baseline. We examine representations generated by Wav2Vec2, HuBERT, and CLAP on FSD50K and CHiME-Home datasets. All three models show consistently higher linear correlation and more accurate leave-one-combination-out reconstructions than the permuted baselines. However, only CLAP shows large cosine similarity gains, which could be associated with its training on many kinds of audio and text. Finally, we note that all three models exhibit reconstruction residuals, revealing limits of additive compositionality such as nonlinear or non-compositional audio structure.

Physical AI has gained increasing attention for its role in developing AI systems that better understand, predict, and control real-world dynamics. Achieving this requires AI models that not only achieve high prediction accuracy but also preserve fundamental physical properties of dynamical systems. In this paper, we propose a deep discrete-time dissipative recurrent neural network (DissipNet) that explicitly enforces dissipativity, a key property related to stability and energy dissipation, through structural weight constraints and a dedicated training algorithm. By construction, the proposed network is capable of learning dissipative dynamics while preserving their inherent stability, which is formally analyzed using Lyapunov theory. In contrast to Physics-Informed Neural Networks (PINNs), which incorporate governing equations into the training loss but do not guarantee preservation of internal analytical properties such as dissipativity or passivity, our approach provides explicit guarantees on stability at the model level. We demonstrate the effectiveness of the proposed method through several modeling applications, and compare its performance with a naive recurrent neural network (RNN) and a PINN-based model.

Generative artificial intelligence (GenAI) is increasingly described in higher education as a tool, collaborator, evaluator, proxy, and infrastructure. These labels are not neutral: they shape who is seen as acting, knowing, and, crucially, being answerable when someone uses AI. This study examines how scholars distribute such responsibility across 366 English-language titles and abstracts published between November 2022 and 14 August 2026. A corpus-assisted discourse analysis combined frequency counts, five-word collocations, actor-predicate associations, obligation-clause coding, and heuristic analysis of passives, nominalisations, and reporting metonymies. The final corpus contained 91,405 tokens, drawn from 8,734 unique records screened after deduplication. AI was the most frequently named actor, appearing 2,050 times and entering 447 predicate associations, most involving action. Students, by contrast, were more often associated with knowing, judging, and verifying, yet no sentence ever made AI explicitly responsible. Responsibility fell largely on educators, institutions, and policy, or disappeared through passive and nominalised constructions. Even frequent phrases such as "responsible AI" and "responsible use" rarely identify who is accountable for what. The findings reveal a persistent gap between giving AI functional agency and assigning normative accountability.

Personalized recommendation depends critically on how user representations are constructed from historical behavior. Two paradigms have emerged for constructing semantic user profiles in content-based recommendation. First, aggregate methods derive user representations as numerical aggregates of semantic item embeddings. Second, LLM-based methods generate natural-language summaries of user preferences and encode them through a text encoder. Each paradigm can be combined with temporal disentanglement of recent versus historical behavior. LLM-based profile generation is significantly more expensive than aggregate approaches, raising the question of when this additional cost is justified. We present a systematic comparison of four semantic user-profiling strategies, factorially crossed across representation type and temporal handling, evaluated on a real-world production dataset. The comparison reveals how these strategies differ across user behavior types, across both accuracy and beyond-accuracy dimensions of recommendation quality, and across the temporal-window setting that governs the disentanglement.

Estimating the causal effects of medical treatments is difficult when clinically important outcomes are costly to measure or require long follow-up. Short-term or inexpensive surrogate outcomes offer a potential alternative, but surrogate biomarkers may be unavailable or difficult to identify. Advances in artificial intelligence (AI) have enabled increasingly accurate prediction of clinical outcomes from inexpensive, high-dimensional measurements, which creates an opportunity to use AI predictions themselves as surrogates. To this end, we develop a framework for estimating treatment effects from paired measurements obtained before and after treatment for each treated individual. A pretrained AI model is applied to the before and after measurements, and our estimator compares the resulting outcome predictions. We characterize the technical assumptions under which this within-person contrast identifies the average treatment effect on the treated, even when clinical outcomes are never observed for treated individuals. When these assumptions cannot be justified, we use prediction-powered inference to correct bias using a small number of observed clinical outcomes and obtain valid inference. Synthetic and real-world cardio-oncology experiments demonstrate the validity and accuracy of the approach.

Benchmark contamination is usually treated as a provenance question: did evaluation material appear in training? Provenance cannot supply the quantity needed to interpret a benchmark score: how much exposure changed it. We introduce LeakScale, a causal measurement framework that makes benchmark-specific exposure manipulable and measures its effect. LeakScale constructs fresh executable tasks whose correct behavior depends on private, non-derivable information, counterfactually certifies every candidate answer, and trains complementary adapters so that every family is exposed in exactly one adapter and unexposed in the other. Across 2,048 families, two model families, two executable domains, three task formulations, and 589,824 generations, exposure increases exact-task accuracy in every model-by-domain cell. Primary effects range from +3.22 to +10.66 percentage points; every family-clustered 95% interval excludes zero, and all four primary tests survive Holm correction. The effect also remains positive in all eight surface-paraphrase and isomorphic-transfer measurements. These results show that benchmark exposure can causally and reproducibly alter reported performance, including after the evaluation surface changes. LeakScale shifts contamination analysis from detecting contact to measuring how strongly a score depends on it.

Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.