Papers

To enable flexible and rapid aerodynamic performance evaluation in turbomachinery design, this paper proposes a panoramic performance prediction framework. Unlike most previous prediction models that directly predict the objective functions of interest, our approach first predicts the basic parameters of the Navier-Stokes equations, such as temperature, pressure, and density. Utilizing these basic physical quantities, it subsequently predicts key performance parameters of the turbine stage meridian plane. By adopting this methodology, our proposed panoramic performance prediction framework functions similarly to a CFD simulator, capable of predicting various objective of interest to the designers. To enhance prediction accuracy, a transformer-enhanced neural operator (TNO) is introduced within this framework. Using the Rotor 37 blades as a reference, the proposed TNO is trained to predict the performance of a transonic compressor blade in the meridian plane. The TNO can accurately predict total quantities such as isentropic efficiency, mass flow, and distributions of total pressure ratio. Remarkably, the prediction error of TNO is observed to be smaller than that of state-of-the-art deep learning operators such as the FNO and DeepONet. Furthermore, the TNO is applied to downstream tasks, including sensitivity analysis and optimization of various objective functions. The results confirm that the TNO can operate almost like a CFD simulator, while reducing the computational cost of downstream tasks by four orders of magnitude. The effectiveness and reliability of the proposed TNO for solving different kinds of downstream tasks have been well demonstrated.

Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a complementary view inspired by human cognitive learning: people learn activities by remembering examples, forming rules, and repairing mistakes, not by backpropagating. This proposed tool implements AHL for HAR: a learning-time agent reasons over sensor protocols, proposes executable heuristic policies, records repair traces, and exports an LLM-free policy for edge deployment. We focus on the HAR benchmark family and provide an end-to-end workflow from dataset observation to edge-oriented export. On eleven HAR datasets evaluated so far, AHL policies reach strong executable-policy performance while remaining inspectable, editable, and replayable \footnote{https://github.com/zhaxidele/ahl-ts-studio}.

We study signed, weighted affine $p$-adic residual objectives as native encodings of finite-domain constraints. For primes that separate the finite alphabet, sufficiently weighted positive unary rows pin each coefficient to its allowed set, while negative rows reward unequal endpoints or clause satisfaction. A coordinatewise domination theorem places every global minimiser in the finite domain; there the loss is, up to an additive constant, the all-different conflict count or the negative number of satisfied CNF clauses. Standard Sudoku provides an $81$-coefficient case study without a one-hot lift. A client-side implementation exposes the generated dataframes, arithmetic, diagnostics, and searches.

The studying of opinion dynamics and its propagation within social networks is crucial for addressing a wide range of challenges, including political polarization, public health, and marketing strategies. In this work, we study the problem of opinion dynamics by proposing a framework based on Friedkin-Johnsen (FJ) to identifies influential users and study their impact on dynamics opinions of community. The FJ model assume each individual have two opinions: initial and expressed. Through a series of initial opinion manipulation experiments, the proposed framework assesses the impact of influential versus random users on the overall community opinion. The proposed framework is validated using a tweet dataset representing the U.S. presidential election. The results shows that influencers with highest influencing score, significantly shift the overall community opinion. Moreover, the results shows that the impact of influencers not limited to direct neighbors , but beyond it, to their neighbors of neighbors . This study demonstrates how digital influencers on social media can shape public opinion regarding a subject or cause.

Span-level masked language modeling (MLM) has shown to be advantageous to pre-trained language models over the original single-token MLM, as entities/phrases and their dependencies are critical to language understanding. Previous works only consider span length with some discrete distributions, while the dependencies among spans are ignored, i.e., assuming that the positions of masked spans are uniformly distributed. In this paper, we present POSPAN, a general framework to allow diverse position-constrained span masking strategies via the combination of span length distribution and position constraint distribution, which unifies all existing span-level masking methods. To verify the effectiveness of POSPAN in pre-training, we evaluate it on the datasets from several NLU benchmarks. Experimental results indicate that the position constraint is capable of enhancing span-level masking broadly, and our best POSPAN setting consistently outperforms its span-length-only counterparts and vanilla MLM. We also conduct theoretical analysis for the position constraint in masked language models to shed light on the reason why POSPAN works well, demonstrating the rationality and necessity of POSPAN.

Users often need ask questions and seek answers online. The Question - Answering (QA) forums such as Stack Overflow cannot always respond to the questions timely and properly. In this paper, we propose HintMiner, a novel automatic question hints mining tool for users to help them find answers. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users' questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. Using the huge amount of online Q&A posts, we design a self-supervised objective to train the MiningNet that is a neural encoder-decoder model based on the transformer and copying mechanisms. We have evaluated HintMiner on 60,000 Stack Overflow questions. The experiment results show that the proposed approach is effective. For example, HintMiner achieves an average BLEU score of 36.17% and an average ROUGE-2 score of 36.29%. Our tool and experimental data are publicly available.

Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fine-Tuning (SFT), which often leads to surface-level pattern matching and degrades general capabilities. While Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising alternative, its scalability in MMIF is severely bottlenecked by the scarcity of high-quality, RL-ready multimodal data. To bridge this gap, we present MIFS (Multimodal Instruction Following Synthesis), a systematic pipeline designed to generate RL-ready multimodal data. Specifically, MIFS introduces a generative constraint protocol to synthesize diverse raw samples, followed by a learnability-aware distillation mechanism that filters data based on RL training dynamics to ensure stable policy optimization. Furthermore, a code-based verifier provides high-precision reward signals for policy learning. The resulting dataset comprises 90k samples across 8 constraint categories and 14 task domains. Empirical evaluations demonstrate that MIFS-trained MLLMs achieve an average improvement of 8.13% on four MMIF benchmarks and a 3$\times$ faster training convergence compared to using raw data. Crucially, our approach mitigates the generalization trade-offs typical of SFT, preserving core visual capabilities while significantly boosting instruction-following precision.

Red-light violations and harsh braking at signalized intersections are major contributors to traffic accidents. This paper analyzes and predicts human driver decision-making and longitudinal trajectory behavior during traffic light signal transitions. We collected a diverse real-world dataset comprising 449 approach runs under varying speed and distance conditions. Vehicle motion was recorded using RTK-corrected GNSS with centimeter-level accuracy, and driver heart rate and multi-level comfort ratings were monitored. Spatial and temporal calibration ensured precise alignment between vehicle state and signal timing. Statistical analysis identifies required deceleration as the dominant single predictor of the stop-go decision, and heteroscedastic Gaussian modeling of peak deceleration reveals five empirical comfort ranges derived from human stopping behavior. Based on this insight, we propose a two-stage modeling framework. Stage 1 predicts the binary maneuver decision, and Stage 2 generates the longitudinal acceleration trajectory using a decision-conditioned autoregressive Transformer with physics constraints, including target-state conditioning and jerk limits. The proposed architecture outperforms baseline methods and achieves 0.49m/s^2 acceleration MAE and 0.62m distance MAE. It also estimates the future stopping-comfort level of the human driver from a single yellow-onset snapshot. Qualitative results demonstrate realistic human-like braking behavior. The dataset and source code are publicly available.

Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability. (2) Reflection is often deferred until task completion. (3) Knowledge is often acquired only in response to downstream task demands. To address these limitations, we introduce OmniHarness, a framework for generalizable visual generation via symbolic policy learning. OmniHarness abstracts verified executions into symbolic policies for visual generation task families, capturing shared procedures and applicability conditions while removing instance-specific inputs. The harness instantiates, adapts, and composes these policies for new tasks. Intermediate verification guides refinement and failure recovery during execution. Through self-directed inquiry, OmniHarness autonomously generates and executes practice tasks near its capability limits before downstream objectives are specified. Execution feedback continually refines the policies while model parameters remain fixed. Experiments across six benchmarks, three MLLM backbones, and three visual agent frameworks demonstrate strong performance and continual capability expansion. On ComfyBench's Creative tasks, OmniHarness achieves a 95.0% resolve rate, exceeding the strongest baseline by 27.5 percentage points. Frozen policy snapshots improve existing visual agent systems through plug-and-play reuse.

Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason a Reinforcement Learning (RL) agent shouldn't do the same: known behaviour patterns need not be learned, only applied. Neuro-symbolic RL bridges prior knowledge and RL by injecting symbolic knowledge alongside a learned policy. The point at which this knowledge is integrated is critical: a poor choice can produce, for instance, hallucinated preconditions, which surface as safety and reliability problems in agents acting in changing environments. We formalise this behavioural knowledge as a precondition Bayesian network (BN) over the agent's structural actions - the actions whose legality depends on preconditions, such as picking up a key, grasping a block, toggling a door, or dropping an object. The BN restricts when these actions may fire, and we inject it into the RL loop at three placements: (1) a symbolic verifier, consulted only at inference, that fires a structural action once its preconditions hold; (2) a symbolic enforcer, active during both training and inference, that governs structural-action use throughout learning; and (3) a symbolic learner, which folds the knowledge into the network and learns the restriction and use of structural actions itself. To test the three variants we run experiments on two benchmarks with opposite regimes: one built on long, ordered planning chains, the other on continuous manipulation. We compare against strong baselines on solution quality, sample efficiency, and traceability. The payoff is substantial. On MiniGrid, all three placements improve the solution quality over the PPO+RND baseline, the symbolic enforcer leading at $98.2\%$ against the baseline's $88.8\%$. On Fetch, $\dots$

Transformer-based multi-target tracking (MTT) jointly learns data association and state estimation, but MT3/Track-MT3-style trackers repeatedly re-encode measurement windows, incurring redundant computation. We propose Causal Neural Set Filtering (CNSF)\footnote{\href{https://github.com/daihuangyu/CNSF}{Code: https://github.com/daihuangyu/CNSF}}, a neural set filter that encodes only current measurements while carrying past evidence in a structured recursive track state. CNSF combines exclusive Sinkhorn association, association-conditioned Kalman-shaped updates with moment matching, and recurrent Bernoulli lifecycle modeling with measurement-driven birth. These mechanisms impose soft one-to-one constraints, propagate association-induced state uncertainty, and support existence estimation under missed detections and birth–death transitions. On a held-out three-regime simulated test set, CNSF reduces mean GOSPA and T-GOSPA relative to Track-MT3 by 19.3% and 30.4%, with 55.9% fewer parameters and a $3.76\times$ speedup in single-thread CPU inference.

High-throughput calculations using density-functional theory (DFT) are commonly used to explore point defects for applications in power electronics and quantum technologies. There is currently a major shift away from these traditional simulation techniques towards machine learning (ML) methods. We explore a class of physics-guided ML models for predicting defect formation energies and zero-phonon lines (ZPL) to identify point defects for quantum applications. The models are specifically targeted for use in a prescreening step for accelerated high-throughput workflows, and are therefore designed to avoid the costly relaxation step typically present with ML interatomic potentials (MLIPs). We compare performance for single and double point defect systems in 4H-SiC with ridge, kernel ridge, and multilayer perceptron (MLP) models using three different descriptors representing the defect systems. For vacancies and substitutions, the optimized models give mean absolute errors (MAEs) of 0.437 eV for the formation energy and 0.202 eV for ZPLs, which is just above the level at which such predictions can be useful even beyond the targeted prescreening, i.e., in some applications they may completely replace the need for costly DFT calculations. For interstitials the MAEs are larger, 1.101 eV for the formation energy and 0.230 eV for the ZPL, which, while still useful for prescreening, will not generally be useful for more detailed characterization. Hence, while the results may be further improved by model design and optimization, the models presented in this work are already useful for prescreening in high-throughput characterization of point defects.

Scientific machine learning methods such as physics-informed neural networks (PINNs) increasingly rely on domain decomposition for better scalability while solving partial differential equations (PDEs) over complex geometries, yet the resulting composite loss comprising residual, boundary, and interface terms is highly susceptible to conflicting gradients that degrade training. This work bridges domain decomposition with projection-based gradient surgery to systematically mitigate such conflicts in 2D and 3D settings. We evaluate two existing projection-based algorithms, PCGrad and ConFIG, and identify their performance degradation in specific scenarios such as 3D domains with multiple overlapping interfaces. To address this limitation, we propose Norm-PCGrad, a normalized variant that achieves state-of-the-art accuracy across a range of 2D and 3D domain decomposition problems. Across the benchmarks considered, Norm-PCGrad consistently achieves the lowest relative $L_2$ error compared to training without gradient surgery as well as to existing algorithms such as PCGrad and ConFIG, while incurring negligible additional computational overhead. To improve computational efficiency of domain decomposition frameworks such as Extended PINN (XPINN), we propose replacing vanilla PINNs in selected subdomains with separable architectures such as Separable PINN (SPINN), reducing the computational cost from quadratic (or cubic) to linear. We additionally demonstrate that gradient surgery extends to physics-informed Kolmogorov-Arnold Networks (PIKANs), yielding substantial accuracy improvements for 3D domain decomposition and confirming the generality of the proposed approach across network architectures.

Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation, fine-tuning, and external verifiers require new infrastructure that clinical governance must approve and may add latency or extra model calls. Inference-time correction uses the model's internal logit signals, but a fixed transformation need not suit every question. A corrector that improves accuracy by about ten percentage points on a truthfulness stress test yields negligible gains on clinical multiple-choice benchmarks, where instruction tuning concentrates output probability on one answer and leaves low terminal entropy. We introduce ALTAS, which reads terminal entropy and late-layer linearity ($R^2$) from one forward pass to choose per question between greedy decoding and late-layer trajectory correction. No classifier, probe, or head is trained; the router operates on candidate-answer logits and adds 6.5% latency overhead. Applied to every question, the correction improves TruthfulQA over greedy at 3B and 8B by 11.4 and 10.0 percentage points, respectively ($p<10^{-10}$). Gated per question, ALTAS retains gains of 8.3 to 9.5 percentage points while keeping MedQA, PubMedQA, and MedHallu within a one-percentage-point do-no-harm band, with no statistically significant differences from greedy. The method passes verification sweeps over frozen thresholds, the scoring rule, and the domain label.

Earth system modeling is shifting from task-specific predictors toward foundation models with general spatiotemporal representation capabilities. Although these models can jointly encode dynamic Earth fields, external forcings, and static geographic context for multistep forecasting, accurate point predictions or statistically calibrated intervals alone are insufficient for high-impact applications such as extremeweather warning, flood control, renewable-energy dispatch, and emergency resource allocation. What matters in practice is whether predictive uncertainty can be translated into reliable decision risk under specific actions, loss functions, and risk preferences. We propose a decision-oriented uncertainty quantification framework for Earth system spatiotemporal foundation models. The framework produces predictive distributions of future states and uses a decision risk adapter to map forecast samples, decision context, and utility functions into action-conditional risks. A utility-aware calibration module further enforces reliability at the downstream decision-loss level rather than only at the forecast-value level. Calibrated risks are then used to select warning, dispatch, inspection, or resource-allocation actions. Compared with the strongest baseline, the proposed method reduces decision regret by 18.7%, lowers the missed-event rate from 14.2% to 9.1%, and improves expected utility by 11.6%, while maintaining 90.4% predictive coverage and reducing decision calibration error from 0.083 to 0.047. These results suggest that decision-oriented uncertainty quantification can improve the robustness and operational value of Earth system foundation models in risk-sensitive applications.

This paper introduces a novel framework for Regularized Multivariate Functional Principal Component Analysis (ReMFPCA) via Functional Singular Value Decomposition (SVD). The proposed method extends existing MFPCA approaches by incorporating a generalized functional SVD within a Hilbert space framework, enabling simultaneous regularization of both functional principal components (PCs) and their associated PC scores. A key innovation of this framework is the inclusion of a sparsity penalty on the PC scores, which enhances interpretability by filtering out irrelevant subject-specific variations. This dual-penalization strategy represents a significant advancement beyond existing covariance-based eigen decomposition methods, which penalize only the functional PCs. Two power algorithm implementations, sequential and joint, are proposed, together with a cross-validation approach based on iterative regression for optimal smoothing parameter selection. Comprehensive simulation studies and real data applications demonstrate that the proposed framework substantially improves the extraction of informative and interpretable components, offering methodological and practical benefits for analyzing multivariate functional data across diverse domains.

Importance weights are essential in domain adaptation under label shift, yet their utility is often undermined by the finite sample uncertainty associated with their estimation. Existing methods typically analyze this uncertainty through Gaussian elimination on interval-valued linear systems, which leads to overly conservative confidence regions and inefficient downstream applications. We propose a paradigm shift from inversion-based inference to a direct matrix constraint framework. We use this framework to define a joint confidence region and extract marginal intervals via linear programming, deriving provably tighter bounds for importance weights while maintaining exact finite-sample validity. Furthermore, we analyze the confidence region's geometry and provide the theoretical results for its diameter bounds. Evaluated across text, image, multimodal benchmarks, including AGNews, MNIST, CIFAR-10, N24News, and a real-world autonomous driving dataset, nuImages, our approach consistently yields shorter confidence intervals and smaller prediction sets than inversion-based methods.

There is a tradeoff in machine translation meta-evaluation between prioritizing alignment with adequacy versus fluency. The balance depends on the combination of translation systems in the meta-evaluation dataset. This system set is a small, filtered sample whose characteristics change heavily across years and language pairs; it does not represent the true system distribution. Consequently, the adequacy-fluency balance is often unrepresentative and subject to change. For sensitive domains, controlling this balance is critical. We expose this balance as a tunable choice. To achieve a target balance, we reweight existing systems while minimizing distortion from uniform weighting, ensuring the evaluated systems remain real and representative. We provide an exact optimization algorithm with theoretical guarantees and pruning mechanisms to compute these weights. To validate meta-evaluation internal consistency, we design a scorer-augmentation framework that establishes a known relative identity for the scorers. Results demonstrate that our reweighting method effectively controls the adequacy-fluency balance and preserves the internal consistency, outperforming prior approaches. Finally, we analyze the performance of popular scorers across a sweep of this parameter.

We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each update must preserve the endpoint mappings at previously learned samples while protecting private data. This gives each agent three roles: (i) a learner that updates the model parameters, (ii) a teacher whose sample is learned at the current iteration, and (iii) a protected agent whose sample has already been learned. We build on Tuning without Forgetting (TwF) method to preserve previously learned mappings and show that TwF provides an indistinguishability guarantee for the learner whenever the set of protected agents contains another sample with the same label. For the teacher, we formulate a minimax optimal control problem that models the differential privacy noise as a worst-case disturbance to prevent performance loss while maintaining the same level of privacy for the gradient. For the protected agents, we compute the projections locally and aggregate them using a private push-sum gossip protocol. We prove geometric convergence of the decentralized gossip algorithm and of the distributed projection for TwF.

Hip exoskeletons may improve recovery from unexpected gait perturbations, yet personalizing assistance remains difficult because balance is multidimensional and human-in-the-loop experiments are small-sample and noisy. We present a participant-specific composite balance cost that integrates seven biomechanical sub-metrics spanning margin of stability, center-of-mass dynamics, and whole-body angular momentum. The sub-metrics are converted to direction-aligned, dimensionless cost features, and nonnegative fusion weights are learned on the simplex. Coupled with an empirical-Bayes hierarchical model, the learned-composite selector estimates each tested condition's posterior probability of being best, P(best), and a high-probability candidate set with size $K_{0.8}$. The framework was evaluated with three participants walking at 1.1 m/s during unilateral belt-slip perturbations across 46 hip-assistance conditions. In the full-budget analysis (B = 4 repeats per condition), the selector concentrated 80% of the posterior probability within 1 to 5 of 46 conditions, compared with 2 to 12 for equal-weight fusion and 4 to 37 for principal component analysis fusion. This smaller candidate set could shorten personalization experiments and limit participants' exposure to repeated perturbations in future studies. Selected-condition trials showed lower observed composite costs than no-torque trials, with nominal p < 0.05 for P2 and P3. Leave-one-repeat-out refits yielded positive mean held-out rank correlations for all participants and moderate stability of the learned weights and candidate sets. These proof-of-concept results support participant-specific composite balance evaluation for candidate selection in perturbation-based human-in-the-loop experiments.

Early detection of cognitive decline from speech offers a scalable and non-invasive alternative to conventional clinical assessment. Verbal fluency tasks are particularly informative, but most automated approaches aggregate features across an entire recording, overlooking temporal speech dynamics. We propose the Cognitive Instability-Aware Cross-Modal Attention Network (CCMAN), a transfer learning framework that learns task-agnostic cognitive speech representations from multiple memory-probing tasks before fine-tuning on a minute-long semantic and phonemic verbal fluency task. CCMAN integrates semantic, acoustic, and linguistic information through bidirectional cross-attention, gated multimodal fusion, and transformer-based temporal modelling to derive interpretable biomarkers of cognitive decline. Experiments were conducted on 165.44 hours of speech from 843 participants (498 healthy controls, 245 with mild cognitive impairment, and 100 with dementia). CCMAN achieved Macro-F1 scores of 0.81 and 0.59 for binary and multiclass semantic fluency classification, and 0.77 and 0.53 for phonemic fluency, consistently outperforming strong static and temporal baselines. Statistical analyses showed that semantic drift variance and pause variance, but not mean semantic drift, were significantly elevated in both MCI and dementia relative to healthy controls, while pause duration increased progressively over the task with the steepest slope in dementia, supporting global and progressive temporal speech instability as interpretable biomarkers. Evaluation on the independent PROCESS-2 benchmark further demonstrated the generalisability of the proposed framework, improving the baseline Macro-F1 by up to 9%. These findings support temporal speech instability as a dynamic speech biomarker for robust, interpretable, and generalisable early detection of cognitive decline.

Operational logs create a need for private, resource-efficient incident analysis, but aggregate detection scores can conceal severe prediction bias. We present TriCalRAG, a reproducible benchmark for log-anomaly detection with generated root-cause and remediation outputs across BGL, HDFS, Thunderbird, and OpenStack. The primary evaluation compares Qwen2.5-14B and Mistral-Small-22B, served through vLLM on one NVIDIA RTX PRO 6000 GPU (96 GB), under zero-shot, few-shot, and retrieval-augmented generation (RAG) prompting across three data-sampling seeds. We report F1, bootstrap confidence intervals, predicted-positive rates, throughput, and memory use, with DeepLog as a held-out classical baseline. Mistral-Small attains a higher macro-averaged F1 than Qwen2.5-14B (0.644 versus 0.560), whereas Qwen provides approximately twice the throughput. A separate log-probability evaluation compares raw decisions with Contextual Calibration (CC) and Batch Calibration (BC): neither correction consistently improves prediction-balance diagnostics across prompting strategies. Supplementary single-run comparisons extend evaluation to 4-bit Llama-3.1-70B via local Ollama and Claude Haiku 4.5 via Anthropic's cloud API; RAG improves F1 on all four datasets for both models. Claude's reported aggregate F1 increases from 0.566 to 0.695, while the estimated API cost rises from \$0.94 to \$2.15 per 1,000 incidents. Local deployment ablations show approximately 41-fold throughput scaling with batching and 20% lower latency with 4-bit quantization on the tested workload. These findings support retrieval as useful context for anomaly decisions, while the supplementary protocols, unvalidated explanation quality, and prediction-balance diagnostics limit broader claims about RCA accuracy and probabilistic calibration.

Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model stops refusing harmful requests. That fact says how easily refusal can be removed, not what the refusal decision was reading in the first place. We ask what it reads, and we separate that from what the model comprehends. Across four open-weight models spanning three families, moral comprehension is native to pretraining: a low-rank moral subspace crystallizes during pretraining, and alignment rotates it once without rebuilding it. The refusal gate, in contrast, is a fresh post-training construction with only a weak pretraining precursor, written into a narrow control-token channel where the refusal decision is orthogonal to the moral-judgment decision. The central result is causal and comes from one model, OLMo-3. A nested interchange rank sweep patches successively larger slices of the moral subspace between matched requests and reads how much of refusal's response transfers: as the basis widens, moral judgment keeps reading more of it, while refusal levels off at the level of a single harm direction, and about three-quarters of refusal's causal input lies outside the moral subspace altogether. Refusal reads the harm percept, not the moral content that judgment reads on the same patches. The picture is not uniform across families. Llama reads broad moral content; Qwen reads beyond the single harm cue but is unresolved at our sample size; GPT-OSS reads harm, and its refusals can be argued in either direction by its own reasoning trace. Where refusal reads only a low-rank slice and routes around the bulk of what the model knows, a rank-one edit removes it. Whether widening what refusal reads would also deepen the behavior is the open question this raises.

Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an interchange patch among others. These measurements fail in specific, diagnosable ways that return a plausible number instead of an error, so a broken instrument can easily read as a finding. A covariance-matched null can saturate until every direction looks typical, a per-head attribution can overshoot the true residual write threefold on reordered-normalization architectures, an interchange patch can go sign-chaotic because its outcome is pinned at a ceiling, or a read-from verdict can be an artifact of measuring past the layer where the model already decided. This note documents six such failures from a causal interpretability program on refusal and moral representation, spanning several papers and a four-model open-weight panel; each mode is established on one or two of the four. For each we give the tell that catches it and a protocol keyed to a detectable trigger (reordered normalization, massive activations, a low-dimensional decision channel), so we and readers can check whether a given setup is exposed. The discipline reduces to four moves: calibrate against a positive-control ladder, certify with an orthogonal cell, compute power before spending compute, and state every read-from verdict at a depth referenced to the model's commitment. The evidence is four architectures across three families within a single program; external replication across programs is future work.

Deep Learning (DL)-based channel estimation has shown high accuracy and low latency in terrestrial 5G NR, but Low Earth Orbit (LEO) Non-Terrestrial Networks (NTNs) introduce Doppler and synchronization impairments that may require NTN-specific architectures. We test whether High-Efficiency Learning-based channel Estimation using dual Neural Attention (HELENA), originally designed for terrestrial channels, remains effective after NTN retraining and suitable across high-performance and power-constrained inference platforms. Its unchanged architecture is trained on paired receiver-compensated (NTN-1) and residual-impaired (NTN-2) datasets and compared with eight terrestrial-origin models trained on the same NTN data and the NTN-specific MDELAN-SISO. HELENA achieves the lowest observed SNR-averaged NMSE among the DL estimators in both conditions, including 55.8-62.7% lower linear-scale NMSE than MDELAN-SISO. All DL models degrade in NTN-2, demonstrating the challenge posed by residual Doppler and its associated impairments. On an RTX PRO 4500, HELENA achieves 0.0595 ms 99th-percentile (P99) inference latency, 88.1% below the 0.5 ms budget, with lower energy than its closest attention-based competitors. On a 10 W Jetson Orin NX, it retains a favorable accuracy-energy trade-off, but no model meets the P99 budget. Thus, HELENA needs no NTN-specific redesign for the evaluated task, while embedded tail latency remains an open challenge.

Federated learning enables collaborative model development without centralizing patient data, but annotation reliability at participating institutions cannot always be assumed. In ophthalmic imaging, differences in disease prevalence and class composition can resemble changes caused by corrupted supervision. We introduce OCT-FedSIR, a reliability-aware spectral framework for federated OCT classification under client-dependent annotation noise and heterogeneous data distributions. OCT-FedSIR combines class-balanced spectral estimation, Stage-I logit adjustment, complementary spectral descriptors, selective spectral relabeling, and noise-aware federated optimization. We evaluated the framework on the Kermany, University of Illinois Chicago, and Wake Forest datasets under symmetric and structured asymmetric noise and three levels of non-IID heterogeneity. Across 117 experimental conditions, OCT-FedSIR achieved a mean accuracy of 86.73%, compared with 79.94% for RoFL and 78.75% for FedCorr. It correctly separated clients with original and corrupted annotations across all evaluated conditions, while the original FedSIR identification procedure was less robust, particularly under asymmetric noise. Spectral relabeling recovered 77.2% of corrupted annotations with 91.3% correction precision and a 3.5% false-correction rate. Retaining corrected clients outperformed spectral pruning by 9.30 percentage points on average. These findings show that annotation noise can often be identified and corrected without discarding informative client data.

Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts. WaVeFuse addresses these limitations through a unified dual-branch architecture. Symlet-4 wavelet denoising (level 2, MAD soft threshold) suppresses microstructure noise in OHLCV. Seven low-lag TIs computed from denoised prices are encoded by a causal channel-wise continuous wavelet transform (Morlet, 32 scales) into a per-timestep scale-space matrix. A CNN-BiLSTM branch captures temporal dynamics, while a dual-layer Transformer (heads=4, dk in {16, 32}) models inter-scale spectral dependencies, and their representations are integrated by a 2-token softmax gate Vertical Attention Fusion (VAF) that dynamically reweights branches as market regimes shift. Evaluated under walk-forward validation (WFV) on KOSPI, DAX, NYSE Composite, and Russell 2000 (2010-2023), WaVeFuse achieves R2 = 0.81-0.96 and directional accuracy 70.5-78.3%. It outperforms seven state-of-the-art models by 8.9-20.2% MAE across twelve dataset-period configurations. Diebold-Mariano statistics (4.62-10.38, p<0.001) confirm superiority over a well-tuned XGBoost benchmark across four indices. Ablation verifies component-wise contributions. Under realistic backtesting with 10 basis point transaction costs, WaVeFuse's directional strategy achieves a mean Sharpe ratio of 3.69 across four markets and limits maximum drawdown to 7.5% during the COVID-19 crash. With 152k parameters (0.68MB) and sub-1.3ms GPU inference, WaVeFuse delivers a computationally efficient, regime-robust framework suitable for research and decision-support deployment.

To successfully deploy a model in time-varying environments such as streaming data prediction and sensing control, domain-incremental learning (DIL) has attracted attention since it aims to adapt a previously trained model to newly arriving domains, while reserving knowledge from earlier domains without accessing their data. Incremental learning across domains can be regarded as a recurrent update, in which the current model is obtained by updating the model carried over from previous domains. Conventional DIL approaches that rely on domain-invariant feature learning and weight regularization gradually overwrite or constrain parameters learned in previous domains, leading to catastrophic forgetting. Instead, this paper proposes a new domain-specific parameter-isolation architecture that retains all past domains. The proposed architecture mitigates catastrophic forgetting through a full-order recurrent update, constructing a new expert using domain-specific data conditioned on all previously frozen models. To achieve this, we incorporate data-free generative replay to reconstruct previous-domain data and cross-domain feature generation to recover later expert features missing from earlier domain samples. Finally, we apply the proposed model architecture to domain-agnostic incremental learning for audio classification, as defined in the DCASE 2026 Challenge Task 7. Consequently, we achieve micro and macro accuracies of 78.4% and 78.9%, respectively, representing increases of 33 and 25 percentage points over the Challenge baseline. Ablation studies are conducted to examine the effectiveness of each processing component in terms of classification accuracy.

Demand forecasting is critical in modern industry, offering opportunities to reduce costs and gain competitive advantage through improved inventory management. However, forecasting becomes particularly challenging for products with intermittent demand, where demand occurs infrequently and time series contain many zero observations. Such dynamics are common across diverse sectors, such as industrial organizations, consumer goods, aviation, automotive, and electronics. Motivated by these challenges, this paper explores the potential of gradient boosting models to improve forecasting performance. We evaluate statistical, specialized, machine learning, and ensemble approaches across multiple datasets. The results show that specialized methods achieve the strongest performance among individual models, while gradient boosting on its own tends to underperform. However, combining a machine learning model with a specialized approach improves forecasting accuracy by up to 10%, demonstrating that even simple ensembles can outperform single models. Overall, the findings highlight the value of combining machine learning with domain-specific forecasting techniques for intermittent demand.

Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, verification computes representations for both accepted and rejected tokens. Yet, conventional drafters retain only the representations of accepted tokens, leaving the substantial verifier computation spent on rejected tokens effectively wasted. We find that these discarded hidden states generated during target forward retain useful information about future tokens that can improve subsequent drafts. However, realizing this opportunity poses two distinct challenges. At inference, recycling overhead can increase drafting latency, diminishing the speedup gained from increased acceptance length. During training, standard parallel drafter training does not produce inference-aligned rejected states, while obtaining them through sequential rollouts would sacrifice parallelism across training positions. We introduce Carryover Drafting, which addresses both challenges. Carryover recycles rejected target hidden states as temporary KV context, allowing the drafter to selectively attend to them. It reuses the drafter's existing interface and adds only a single learned embedding to distinguish rejected states from committed context. The additional KV context is replaced each drafting round, keeping its length bounded by one proposal block. We introduce parallel draft–verify–draft training that exposes the drafter to inference-aligned rejected states while preserving parallelism across training positions. Experiments with DFlash and a DSpark-derived semi-autoregressive drafter across two target models show that this simple Carryover mechanism improves average acceptance length by 6.5–14.7% and end-to-end vLLM speedup by 7.9–14.4% over the corresponding baselines, with speedup gains reaching 28.8% on translation.