Search research

While interpretable prototype networks offer compelling case-based reasoning for clinical diagnostics, their raw continuous outputs lack the semantic structure required for medical documentation. Bridging this gap via standard Retrieval-Augmented Generation (RAG) routinely triggers ``retrieval sycophancy,'' where Large Language Models (LLMs) hallucinate post-hoc rationalizations to align with visual predictions. We introduce ProtoMedAgent, a framework that formalizes multimodal clinical reporting as an iterative, zero-gradient test-time optimization problem over a strict neuro-symbolic bottleneck. Operating on a frozen prototype backbone, we distill latent visual and tabular features into a discrete semantic memory. Online generation is strictly constrained by exact set-theoretic differentials and a reflective Scribe-Critic loop, mathematically precluding unsupported narrative claims. To safely bound data disclosure, we introduce a semantic privacy gate governed by $k$-anonymity and $\ell$-diversity. Evaluated on a 4,160-patient clinical cohort, ProtoMedAgent achieves 91.2% Comparison Set Faithfulness where it fundamentally outperforms standard RAG (46.2%). ProtoMedAgent additionally leverages a binding $\ell$-diversity phase transition to systematically reduce artifact-level membership inference risks by an absolute 9.8%.

EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to clinical trust. We apply TopK Sparse Autoencoders (SAEs) across three architecturally distinct EEG transformers: SleepFM, REVE, and LaBraM to extract sparse feature dictionaries from their embeddings. By grounding these features in a clinical taxonomy (abnormality, age, sex, and medication), we benchmark monosemanticity and entanglement across architectures. A single hyperparameter procedure, driven by an intrinsic dictionary health audit, transfers robustly across all three architectures. Via concept steering, we introduce a "target vs. off-target" probe area metric to quantify steering selectivity and reveal three operational regimes: selectively steerable, encoded but entangled, and non-encoded. This framework exposes critical representational failures: "wrecking-ball" interventions that collapse global model performance, and clinical entanglements, such as age-pathology confounding, where it is impossible to suppress one concept without corrupting the other. Finally, a spectral decoder maps these interventions back to the amplitude spectrum, translating latent manipulations into physiologically interpretable frequency signatures, such as pathological slow-wave suppression and $α$-band restoration.

Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While these models have advanced rapidly, their internal mechanisms remain largely a mystery. Techniques such as Sparse Autoencoders (SAE) have emerged to understand these mechanisms by projecting dense representations into a sparse vector. While existing research has demonstrated the viability of the SAE in interpreting text-based Large Language Models (LLMs), there are no equivalent studies that demonstrate the application of a SAE to audio processing models like Automatic Speech Recognizers (ASRs). In this work, a SAE is applied to Whisper, a Transformer-based ASR, training a high-dimensional sparse latent space on frame-level embeddings extracted from the Whisper encoder. Our work uncovers diverse monosemantic features across linguistic and non-linguistic boundaries, and demonstrates cross-lingual feature steering. This work establishes the viability of a SAE model and demonstrates that Whisper encodes a rich amount of linguistic information.

TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a trained neural network and human-understandable, high-level concepts. Though effective, TCAV suffers from significant computational overhead, inter-layer disagreement of TCAV scores, and statistical instability. This work takes a step toward addressing these challenges by introducing E-TCAV, a framework for efficient approximation of TCAV scores, which is based on extensive investigation into three key aspects of the TCAV methodology: 1) the effect of latent classifiers on the stability of TCAV scores, 2) the inter-layer agreement of TCAV scores, and 3) the use of the penultimate layer as a fast proxy for earlier layers for TCAV computation. To ensure a solid foundation for E-TCAV, we conduct extensive evaluations across four different architectures and five datasets, encompassing problems from both computer vision and natural language domains. Our results show that the layers in the final block of the neural network strongly agree with the penultimate layer in terms of the TCAV scores, and the commonly observed variance of the TCAV scores can be attributed to the choice of the latent classifier. Leveraging this inter-layer agreement and the degeneracy of directional sensitivities at the penultimate layer, E-TCAV guarantees linearly scaling speed-ups with respect to the network's size and the number of evaluation samples, marking a step towards efficient model debugging and real-time concept-guided training.

Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used to visualize model decisions in the form of saliency maps; however, these explanations do not influence how models learn during training, allowing non-causal or confounding features to persist. This motivates the incorporation of explanation supervision directly into the training objective to guide model attention toward clinically meaningful regions and promote clinically grounded decision-making. This paper presents a systematic approach to integrate explanation loss into model training and analyzes how different explanation loss designs and supervision strengths influence both predictive performance and spatial faithfulness of explanations. To quantitatively assess interpretability, two complementary explanation performance metrics-annotation coverage and saliency precision-are introduced, enabling rigorous evaluation beyond qualitative visualization. Our experimental results reveal a clear trade-off between explanation quality and explanation loss coefficients. Furthermore, quantitative statistical analysis yields consistently improved explanation alignment while maintaining comparable accuracy. Experiments were conducted on annotated chest X-ray datasets; however, the proposed framework is applicable to a broad range of annotated biomedical imaging modalities. Overall, these findings demonstrate that explanation supervision is not a monolithic design choice and provide practical guidance for incorporating explanation loss into training objectives under noisy clinical annotations.

Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are hypothesis-driven; they first informally define a task with a dataset, and then apply a circuit discovery algorithm over that dataset to obtain a single circuit. This imposes two strong assumptions: that the LM implements the task with a single circuit, and that the dataset adequately represents the task as humans understand it. We systematically test these assumptions across four previously studied tasks and find that even minor dataset variations that preserve task semantics can produce circuits with low edge overlap and cross-dataset faithfulness. More strikingly, when applied to a mixed dataset with two distinct tasks whose separately discovered circuits have near-zero cross-faithfulness, existing methods still return a single circuit with high faithfulness across both tasks. This indicates that current methods discover dataset-specific circuits, rather than general task circuits. We propose Data-driven Circuit Discovery (DCD), a new discovery framework that drops both assumptions: instead of returning a single circuit for a dataset, DCD first clusters examples in the dataset by how similarly the model processes them and discovers a separate circuit for each group. This allows distinct mechanisms to appear separately rather than merged into a single circuit; each circuit explains its group, not the full task. Experiments show that DCD discovers multiple circuits per dataset, each more faithful to its group than a single circuit discovered by existing methods. Broadly, DCD lets the data reveal mechanistic structure within LMs, rather than relying on human-defined task boundaries that may not align with how models organize their computation.

Mechanistic interpretability papers increasingly use causal vocabulary: circuits, mediators, causal abstraction, monosemanticity. Such claims require explicit identification assumptions. A purposive audit of 10 papers across four methodological strands finds no dedicated identification-assumptions section and a recurring pattern: validation metrics such as faithfulness, completeness, monosemanticity, alignment, or ablation effects are reported as causal support without stating the assumptions that make them identifying. A two-human-coder audit on $n=30$ reproduces the direction of the main finding: dedicated identification sections are absent, and validation-metric substitution is common, though exact Dim B/D counts are coding-rule sensitive. The paper proposes a disclosure norm: state whether the claim is causal, name the identification strategy, enumerate assumptions, stress at least one, and explain how conclusions shift if assumptions fail. Validation is not identification.

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces high-dimensional, unstructured datasets that are difficult to compare systematically. We propose a framework that reframes mechanistic analysis as a graph machine-learning problem by representing activation-patching profiles as patch-effect graphs over model components. We introduce three graph-construction methods: direct-influence via causal mediation, partial-correlation, and co-influence and apply graph kernels to analyze the resulting structures. Evaluating this approach on GPT-2 Small using Indirect Object Identification (IOI) and related tasks, we find that patch-effect graphs preserve discriminative structural signals. Specifically, localized edge-slot features provide higher classification accuracy than global graph-shape descriptors. A screened paired-patching validation suggests that CI and PC selected candidate edges correspond to stronger activation-influence effects than random or low-rank candidates. Crucially, by evaluating these representations against rigorous prompt-only and raw patch-effect controls, we make the evidential scope of the benchmark explicit: graph features compress structured patching signal, while raw tensors and surface cues define strong baselines that any circuit-level claim should address. Ultimately, our framework provides a compression and evaluation pipeline for comparing patching-derived structures under controlled baselines, separating robust slice-discriminative evidence from stronger task-general causal-circuit claims.

Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time series data remains unexplored. The persistent competitiveness of simple linear models such as DLinear has fueled ongoing debate, but no mechanistic explanation for this phenomenon has been offered. We address this gap by applying sparse autoencoders (SAEs), a tool from mechanistic interpretability, to probe the internal representations of PatchTST. We first establish that a single-layer, narrow-dimensional transformer matches the forecasting performance of deeper configurations across commonly used benchmarks. We then train SAEs on the post-GELU intermediate FFN activations with dictionary sizes ranging from 0.5x to 4.0x the native dimensionality. Expanding the dictionary yields negligible downstream performance change (average 0.214%), with large portions of overcomplete dictionaries remaining inactive. Targeted causal interventions on dominant latent features produce minimal forecast perturbation. Across all evaluated settings, we observe no empirical evidence that the analyzed FFN representations rely on strong superposition. Instead, the representations remain sparse, stable under aggressive dictionary expansion, and largely insensitive to latent interventions. These results demonstrate that superposition is not necessary for competitive performance on standard forecasting benchmarks, suggesting they may not demand the rich compositional representations that drive transformer success in language modeling, and helping explain the persistent competitiveness of simple linear models

Vision-Language-Action (VLA) policies often fail under distribution shift, suggesting that decisions may depend on spurious visual correlations rather than task-relevant causes. We formulate visual-action attribution as an interventional estimation problem. Accordingly, we introduce the Interventional Significance Score (ISS), an interventional masking procedure for estimating the causal influence of visual regions on action predictions, and the Nuisance Mass Ratio (NMR), a scalar measure of attribution to task-irrelevant features. We analyze the statistical properties of ISS and show that it admits unbiased estimation, and we characterize conditions under which action prediction error provides a valid proxy for causal influence. Experiments across diverse manipulation tasks indicate that NMR predicts generalization behavior and that ISS yields more faithful explanations than existing interpretability methods. These results suggest that interventional attribution provides a simple diagnostic approach for identifying causal misalignment in embodied policies.

Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners. While recent tools provide insights into model internals or generation outcomes, they often lack decoding-time signals, fine-grained uncertainty measures, and interactive mechanisms for exploring alternative generation paths. We present TokenScope, an interactive interpretability and analysis tool for decoder-based LLMs that exposes token-level metrics, attention patterns, and structural information during generation. TokenScope supports interactive token replacement, counterfactual branching, and code-aware aggregation via abstract syntax trees. By unifying decoding-time signals with structural program analysis, TokenScope enables systematic investigation of LLM behaviour during code generation.

Mechanistic interpretability research on emotion in large language models -- linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steering vector extraction -- depends on stimuli that contain the words for the emotions they test. When a probe fires on "I am furious", it is unclear whether the model has detected anger or detected the word "furious". The two readings have very different consequences for every downstream claim about emotion circuits, features, and interventions. We release AIPsy-Affect, a 480-item clinical stimulus battery that removes the confound at the stimulus level: 192 keyword-free vignettes evoking each of Plutchik's eight primary emotions through narrative situation alone, 192 matched neutral controls that share characters, setting, length, and surface structure with the affect surgically removed, plus moderate-intensity and discriminant-validity splits. The matched-pair structure supports linear probing, activation patching, SAE feature analysis, causal ablation, and steering vector extraction under a strong methodological guarantee: any internal representation that distinguishes a clinical item from its matched neutral cannot be doing so on the basis of emotion-keyword presence. A three-method NLP defense battery -- bag-of-words sentiment, an emotion-category lexicon, and a contextual transformer classifier -- confirms the property: bag-of-words methods see only situational vocabulary, and a contextual classifier detects affect (p < 10^-15) but cannot identify the category (5.2% top-1 vs. 82.5% on a keyword-rich control). AIPsy-Affect extends our earlier 96-item battery (arXiv:2603.22295) by a factor of four and is released openly under MIT license.

While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous systems, as stakeholders cannot certify their validity. Recent work demonstrates this concretely: two papers found conflicting conclusions for the same behavior, and a third study revealed that both were partially correct but incomparable due to methodological inconsistencies. Without standardized auditing, such ambiguities hinder adoption in high-stakes contexts requiring strong correctness guarantees. We call for the MI community to work towards developing a novel reviewing system that complements peer review via: (1) Continuous reviewing supported by a \emph{Collaborative Reviewing Platform} where meta-science results and discussions (such as critiques, negative results, post-hoc extensions, reproductions, replications, and partial results) that fit outside of papers are organized and discussed, allowing for comments and revisions to be made at any time (2) Generalizing good practices found on this platform into expert-verified guidelines and protocols to improve auditing efficiency, and (3) Source-based auditing systems that track arguments which claims depend on. This position paper encourages constructive debate over the necessity, design and implementation of such a framework, providing early concrete examples to help catalyze these dialogues. Overall, we propose that auditing MI itself is essential for its application in AI safety, industry, and governance.

Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their behavior on commonly used benchmarks underexplored. To address this gap, we study contrastive, LRP-based attribution as a practical tool for analyzing LLM failures in realistic settings. We formulate failure analysis as \textit{contrastive attribution}, attributing the logit difference between an incorrect output token and a correct alternative to input tokens and internal model states, and introduce an efficient extension that enables construction of cross-layer attribution graphs for long-context inputs. Using this framework, we conduct a systematic empirical study across benchmarks, comparing attribution patterns across datasets, model sizes, and training checkpoints. Our results show that this token-level contrastive attribution can yield informative signals in some failure cases, but is not universally applicable, highlighting both its utility and its limitations for realistic LLM failure analysis. Our code is available at: https://aka.ms/Debug-XAI.

Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XAI). In this paper, we present a method to enhance the interpretability of ML models by using a Knowledge Graph (KG). We store domain-specific data along with ML results and their corresponding explanations, establishing a structured connection between domain knowledge and ML insights. To make these insights accessible to users, we designed a selective retrieval method in which relevant triplets are extracted from the KG and processed by a Large Language Model (LLM) to generate user-friendly explanations of ML results. We evaluated our method in a manufacturing environment using the XAI Question Bank. Beyond standard questions, we introduce more complex, tailored questions that highlight the strengths of our approach. We evaluated 33 questions, analyzing responses using quantitative metrics such as accuracy and consistency, as well as qualitative ones such as clarity and usefulness. Our contribution is both theoretical and practical: from a theoretical perspective, we present a novel approach for effectively enabling LLMs to dynamically access a KG in order to improve the explainability of ML results. From a practical perspective, we provide empirical evidence showing that such explanations can be successfully applied in real-world manufacturing environments, supporting better decision-making in manufacturing processes.

We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal polynomial kernels. Since the associated reproducing kernel Hilbert space is finite-dimensional and admits an explicit tensor-product orthonormal basis, the fitted decision function can be expanded exactly in intrinsic RKHS coordinates. This leads to Orthogonal Representation Contribution Analysis (ORCA), a diagnostic framework based on normalized Orthogonal Kernel Contribution (OKC) indices. These indices quantify how the squared RKHS norm of the classifier is distributed across interaction orders, total polynomial degrees, marginal coordinate effects, and pairwise contributions. The methodology is fully post-training and requires neither surrogate models nor retraining. We illustrate its diagnostic value on a synthetic double-spiral problem and on a real five-dimensional echocardiogram dataset. The results show that the proposed indices reveal structural aspects of model complexity that are not captured by predictive accuracy alone.

While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. Using numerical analysis techniques, we rigorously quantify the accuracy, convergence rates, and generalization bounds of certain ML models applied to linear differential equations for parameter discovery or solution finding. Beyond the quantity and discretization of data, we identify that the function space of the data is critical to the generalization of the model. A similar lack of generalization is empirically demonstrated for commonly used models, including physics-specific techniques. Counterintuitively, we find that different classes of models can exhibit opposing generalization behaviors. Based on our theoretical analysis, we also introduce a new mechanistic interpretability lens on scientific models whereby Green's function representations can be extracted from the weights of black-box models. Our results inform a new cross-validation technique for measuring generalization in physical systems, which can serve as a benchmark.

Image denoising remains a fundamental problem in image restoration, with applications in photography, biomedical, and scientific imaging. Modern deep neural networks achieve strong performance by learning powerful image priors, but often rely on large black-box models with limited interpretability. In contrast, DCT-based sliding-window and collaborative filtering methods such as BM3D offer clear algorithmic structure, but depend on handcrafted and non-differentiable operations. This work studies how far such structured collaborative filtering principles can be pushed when reformulated as trainable models. We introduce DeepBM3D, a compact fully differentiable architecture that combines non-local patch grouping, DCT-domain filtering, and multi-stage refinement within a BM3D-inspired pipeline. Lightweight convolutional feature extractors guide patch grouping, while filtering is performed through learned Wiener weights in the DCT domain. Experiments show that DeepBM3D improves over classical and hybrid baselines, remains competitive with FFDNet at low and moderate noise levels, and performs particularly well on repetitive textures.

Distinguishing GPT-assisted from independently authored student writing has become a critical challenge in academia. This paper evaluates the discriminative capability of interpretable stylometric features extracted solely from submitted text. Using data from 90 participants who wrote both independently and with ChatGPT assistance, we evaluate eight machine learning classifiers while keeping data from the same participant together during validation. On the held-out test set, Random Forest achieved an ROC-AUC of 0.87 and an F1-score of 0.84, with False Positive and False Negative rates of 22.2% and 11.1%, respectively. SHAP analysis shows that lexical and grammatical characteristics drive the resulting predictions. The findings suggest that transparent, text-intrinsic features provide measurable signal for detecting GPT-assisted writing.

Despite the success of neural models in natural language processing, their black-box nature limits interpretability and conceals the linguistic phenomena underlying their predictions. We present SLITE, an explainable hybrid model for Recognizing Textual Entailment that integrates two complementary layers of semantic analysis: a structural-relational layer, based on semantic compatibility and incompatibility between compositional entities, and a distributional-informational layer, based on structured patterns of information change between embedding-based representations of the premise and the hypothesis. We propose 17 features that combine entity-level semantic relations, polarity-sensitive lexical matching, and alignment measures over semantic sub-representations of the similarity matrix, including measures based on entropy and transfer entropy. A logistic regression trained on these features achieves an accuracy of 83% on three-class SICK and 96% on SICK-CE, outperforming IsoLex by 4 percentage points and falling within 2 percentage points of RoBERTa with a fraction of its computational complexity. Ablation studies and SHAP analysis confirm that structural-relational features are the primary drivers of classification, while distributional-informational features provide essential complementary contributions, particularly for detecting neutrality and contradiction. Our results demonstrate that further exploration of hybrid approaches is a viable and scientifically productive alternative to massive neural architectures, and we hope they will strengthen the dialogue between linguistic theory and computational modeling of inference

Feature importance is central to interpretable machine learning, but the term "importance" encompasses several fundamentally different notions of relevance. We develop a unified perspective based on null importance: a population-level characterization of when a feature is irrelevant under a specified notion of relevance. We consider standard notions of null importance arising from marginal and conditional statistical relevance, predictive risk, functional invariance, and causal effects, and show how these notions answer different scientific questions. We illustrate the framework in two applications in which the distinction is particularly consequential: algorithmic fairness, where common fairness criteria correspond to different notions of null importance, and genomic perturbation modeling, where different notions of relevance lead to different conclusions about what a prediction model has learned. The framework connects three aspects of feature analysis: the scientific question defining relevance, the data and model assumptions that shape how different null notions relate, and the methods used to assess importance. We establish sufficient conditions under which null notions coincide and give counterexamples showing how they diverge when those conditions fail. We then characterize which nulls different method families target and when their zero-importance statistics identify those targets. Finally, simulations spanning feature dependence, redundancy, nonlinearity, hidden features and other standard phenomena, along with case studies on image and multiomics data, provide empirical evidence for these theoretical distinctions and their practical consequences. Taken together, these results provide a common statistical language for relating scientific questions, data-generating assumptions, and algorithms, and clarify the conclusions that feature-importance analyses can support.

Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble member. We ask how well deep learning surrogates can reproduce these simulations at a fraction of this cost, training them on 10,584 fire spread simulations at 2m resolution for the Rectoret region in Catalonia, Spain. Four architectures are compared: a patch-based U-Net, a transfer-learned ResNet-50, a physics-informed network constrained by the wind-driven advection equation and a Swin-Unet transformer. Among the terrain and vegetation variables, only surface fuel load predicts burn probability with any strength (r = 0.27) and including it lowers prediction error by 21%. The remaining variables correlate weakly and are highly duplicative. Next, an experiment with saliency, occlusion and rotation demonstrates the models' learning. Convolutional models rely primarily on distance from the current fire front, while Swin-Unet assigns more weight to fuel and terrain, a finding also noted in an unrelated wildfire dataset. When applied without retraining to the second region, Pedriza, all three convolutional models still predict fire spread, losing accuracy by a small but systematic margin.

Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthermore, most classification-oriented explainability tools are ill-suited to detection tasks involving imagery of social organisms or those with colonial life histories, as they ignore multiple detections within a scene and produce single-instance outputs that blur evidence across individuals. These methods also generate low-resolution, often biologically irrelevant visuals, limiting their utility for debugging, targeted data augmentation, and refined data collection. We proposed Det-LIME, a detector-aware, multi-instance adaptation of Local Interpretable Model-Agnostic Explanations (LIME) that produced instance-specific, box-aligned explanations by combining per-detection weighting, a proximity kernel that emphasizes regions near each box, and Intersection-over-Union-based matching to track the same instance across perturbations. We evaluated Det-LIME on aerial drone imagery for harbor seal detection, with an additional seabird case study to assess generality, and compared it with vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient-based attribution methods. Using the Attribution Ratio and Max Saliency Hit Rate metrics, we showed that Det-LIME consistently improved multi-instance attribution. In practice, these higher-resolution, instance-aware explanations provide insight into model outputs and support post-processing, debugging, and actionable improvements in modeling and data collection or augmentation.

Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven workflow aligned with standardized criteria. While multimodal large language models (MLLMs) show promise for automated medical report generation, most existing systems rely on end-to-end multimodal fusion without modeling clinically defined intermediate attributes, leading to limited grounding and interpretability. To address this issue, we propose CORAL (COncept-grounded ReAsoning with Localization), a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process. CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module. The resulting textual concept tokens are combined with mask-modulated visual features within an MLLM to enable structured report generation and diagnostic prediction. Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.

Hyperspectral images (HSIs) are often degraded by mixed noise, including band-dependent Gaussian perturbations and structured artifacts such as stripes, dead-lines, and impulse noise. Most deep denoisers regress the clean image directly, entangling signal and structured noise. We instead model HSI denoising as $\Y=\A\X+\Snoise+\Nnoise$, where $\A\X$ is a low-rank spectral-subspace (unmixing) reconstruction, $\Snoise$ is structured sparse noise and $\Nnoise$ is residual Gaussian noise. The resulting regularized optimization problem is unrolled into AXS-Net, a $K$-stage alternating proximal-point framework. Each stage combines an analytic spectral-basis gradient step, an SSX-Block proximal operator for abundance coefficients, and an SBlock proximal operator for the structured residual with column-consistent and sparse priors. This optimization correspondence exposes interpretable endmembers, abundance maps, and structured-noise estimates. Across ICVL, CAVE, and Harvard datasets and five noise configurations, the proposed AXS-Net achieves strong in-domain accuracy and competitive zero-shot transfer, with consistent gains across all five noise regimes on ICVL and Harvard. The recovered structured-noise closely follows the synthetic reference, and the recovered spectral basis is smooth and band-ordered rather than an arbitrary set of latent channels.

Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.

Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges made it anomalous. We propose DIFFINT, an autoencoder whose latent bottleneck is structured as a set of soft, axis-aligned interval memberships learned end-to-end directly from raw numerical data, without any discretization or binarization. Each latent unit corresponds to a human-readable hyper-rectangle in feature space; an instance is encoded by how strongly it falls inside each interval relative to the other units, and its reconstruction error is the anomaly score. This keeps the power of differentiable representation learning while exposing an inspectable internal structure. We make the inductive bias precise: a certified reconstruction-error lower bound for points that fall outside every active coordinate of the learned support (with a Lipschitz-enforced decoder), and a graded, empirically verified suppression mechanism for the usual case in which only a few features are abnormal; and we provide a closed-form, label-free importance that ranks each (unit, feature) pair from quantities the model already maintains, turning trained intervals into auditable candidate constraints without ever seeing an anomaly label. On 48 ADBench benchmarks against 22 baselines under a common [-1, 1]-normalized protocol, DIFFINT attains the best mean rank overall on both metrics (4.10 on ROC-AUC, 4.16 on AUPR); among inlier-only detectors it leads its regime clearly, and it is competitive with the strongest contaminated-data detectors (see the stratified and complete-case analyses). It is the only interpretable detector in the statistically-tied leading cluster of seven methods.

Magnetic core loss originates in the hysteresis loop: the energy dissipated per excitation cycle equals the loop area, and frequency, temperature, and waveform shape set the loss by reshaping the loop geometry. Most existing models let these conditions act only on a terminal scalar - empirical equations fold them into fitted exponents, and data-driven predictors append them to encoded features - so no intermediate hysteresis representation remains for the conditions to reshape. This paper proposes CAHR-Net, a condition-adaptive hysteresis reconstruction network that injects the operating conditions where they physically act. It preserves the interpretable chain from flux density waveform to magnetic field reconstruction, loop-area integration, and power loss estimation, and uses feature-wise linear modulation to inject frequency, temperature, and waveform statistics into the intermediate reconstruction representation. A matched large-batch training protocol based on AdamW, cosine scheduling, and a staged reconstruction-to-power-loss objective is also reported, because the modulation pathway takes effect only within it. On the MagNet final A-E material protocol, CAHR-Net attains an average p95 relative error of 6.89% with only 1874 parameters, the lowest among all compared methods, together with a lower worst-material p95 than the strongest black-box solution at about 48x fewer parameters; it reduces the average p95 of the physical reconstruction backbone from 7.47% to 6.89% and the p95 of material D, the most difficult material, from 16.40% to 14.87%. Ablation and condition-slice analyses attribute the improvement to the coupling of physical loop reconstruction, structured condition modulation, and the matched optimization trajectory.

Compact snapshot hyperspectral cameras provide rich instantaneous spectral measurements for ground-level machine vision, but at lower spatial resolution than standard RGB cameras. RGB-guided hyperspectral super-resolution (HSR) addresses this limitation by transferring spatial detail from a high-resolution RGB guide to a low-resolution hyperspectral image (HSI). These dual-camera systems are typically in a horizontal rig geometry, requiring cross-camera image alignment due to different fields of view. However, residual misregistration can inject spurious high-frequency details. Existing learned unaligned-fusion methods are usually trained for a fixed spectral support and spatial scale factors and can be computationally demanding, limiting their flexibility across sensors. We propose a lightweight and interpretable RGB-guided HSR framework combining cross-modal flow alignment with model-based Gram-Schmidt orthogonalization fusion. The method first warps the RGB guide onto the HSI grid, then estimates an energy-based confidence weight map by measuring local alignment reliability. This map is then used both in a weighted least-squares spectral regression and in a gated fusion between the super-resolved estimate and an HSI-preserving estimate. Unlike existing learned methods, the proposed framework has a low computational footprint and supports VIS-NIR spectral supports and scale factors without retraining. Experiments on the Real benchmark show that the proposed method improves reconstruction accuracy over learned fusion baselines while remaining substantially faster. On a 34-frame sequence acquired with our real RGB-HSI dual-camera setup, a reduced-resolution quantitative evaluation validates the method under genuine cross-sensor radiometric, noise, and geometric differences, while native-resolution qualitative results demonstrate deployment on the full 51-band VIS-NIR acquisition.

Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution images. Existing remedies fall into two families: (1) Training-free methods based on attention or confidence scores are accurate but slow, since they require multiple MLLM queries per example. (2) Reinforcement Learning (RL) trained tool-use models are faster at inference but opaque, since their tool calls remain uncontrollable and hard to interpret. To overcome this, we propose \emph{VisLens} (Visual Focus via Logit Lens), a Visual Search method built on the logit lens, which decodes the semantics held in a hidden state by projecting it through the LLM head. VisLens further uses a lightweight tuned-lens that maps early hidden states into the final hidden state space, so visual tokens can be read out from early layers. These tokens are matched to target words in the query to generate a crop of the relevant region, which is fed back in alongside the original image to produce the final answer. The whole process, from decoding to the final answer, completes in a single forward pass without repeated queries. VisLens matches or exceeds prior baselines while delivering a substantial latency advantage, running $8.5$--$9.9\times$ faster than Thyme and up to $22.2\times$ faster than training-free multi-pass search methods.