Machine Learning · Cross-listed from cs.CV
RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings
Wei Zhang and Ming Tang
Foundation models provide powerful representations for
brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms. Clinical assessment of
brain MRI is commonly organized around anatomically defined structures and regional abnormalities, whereas conventional explanation methods typically produce voxel- or patch-level importance maps that do not explicitly quantify the contributions of individual
brain regions. To address this mismatch, we propose RegionFM, an interpretable framework that integrates anatomical
segmentation with
brain MRI foundation-model
embeddings. RegionFM first divides each MRI scan into anatomical regions and constructs a separate MRI volume for each region. A frozen foundation model then encodes each region into an
embedding, and a region-additive logistic model combines these
embeddings such that every anatomical region contributes an explicit scalar term to the final prediction. This formulation supports both subject-level and cohort-level analyses of regional contributions. We evaluate RegionFM on cognitive-impairment classification using
embeddings from multiple pretrained
brain MRI foundation models. The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations. Randomized
embedding ablations yield near-chance performance, indicating that the predictions rely on meaningful structure captured by the foundation-model
embeddings rather than simple feature statistics. Overall, RegionFM better aligns model explanations with anatomy-based clinical
reasoning while maintaining competitive predictive performance.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears
Ahmed Tahiru Issah, Charles B. Delahunt and Carine Mukamakuza
Malaria diagnosis in endemic regions depends on species-level identification of Plasmodium parasites in thick blood smears, but deep learning detectors classify detections without providing morphological evidence for their predictions, limiting the ability of microscopists to audit those predictions at the case level. We present SGMCE (Segment-Grounded Morphological Concept Explanation), a post-hoc explanation framework that requires no additional training, no morphological annotations, and no labelled explanation data, yet produces per-detection natural-
language explanations anchored in thick-smear morphology. For each detection, SGMCE extracts mask-guided crop thumbnails, computes fourteen handcrafted computer-
vision morphological features (shape, colour, chromatin, haemozoin pigment) using adaptive within-mask thresholds, and queries GPT-4o with both visual evidence and computed measurements, conditioned on a thick-smear-specific knowledge base compiled from the World Health Organization bench aids. The primary output is a structured explanation identifying which morphological features support the detected species and why the competing species are excluded. Explanations are validated by four automatic metrics: Knowledge-Base Consistency (KBC), CV-Claim Faithfulness (CCF), Discriminativeness Score (DS), and LLM-as-Judge (LLMj). A sentence-level semantic scoring rule with species-aware negation filtering resolves the vocabulary mismatch between clinical prose and knowledge-base terms. Across 737 detections from 139 thick-smear images spanning four Plasmodium species and white blood
cells, parasite-class mean KBC is 0.91, mean DS is 0.99, and mean CCF is 0.97, while a per-rule CCF breakdown confirms that the CV-grounded claims made by the
vision-
language model are consistent with the measurements they cite.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
Alexander Selivanov, Friederike Jungmann, Jan Kehrer et al. (+3 more)
Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac
magnetic resonance (CMR). Furthermore, most existing ECGAI systems are limited to fixed diagnostic labels or automated reports, constraining their use for patient-specific clinical
reasoning. To address this gap, we introduce ECG-LLM, an ECG-conditioned large
language model trained across four cohorts comprising 679,112 ECG studies from 186,409 patients. Using a novel
multimodal-to-
language supervision strategy, ECG-LLM is trained on clinically structured question-answer pairs derived from ECG signals, clinical context, CMR, and ECHO. This unified approach enables the model to answer diverse cardiovascular questions from a 12-lead ECG alone, spanning both conventional interpretation and phenotypes not directly visible on standard ECGs. ECG-LLM successfully recovers conventional ECG measurements, such as heart rate, and strongly predicts complex CMR-derived phenotypes, including ventricular and atrial volumes and ventricular function. Crucially, it detects vital echocardiographic phenotypes, including increased LV wall thickness, aortic stenosis, and right-ventricular systolic dysfunction. On standard ECG understanding tasks, ECG-LLM matches or exceeds existing baselines for diagnostic report generation and the ECG-QA
benchmark. By moving beyond fixed-label prediction, this
multimodal framework provides clinically valuable, question-driven cardiovascular
reasoning to support general practitioner and front-line triage decisions when specialist review is delayed.
Read the full abstract ▾
All authors Alexander Selivanov, Friederike Jungmann, Jan Kehrer, Karl-Ludwig Laugwitz, Eimo Martens, Daniel Rueckert
Machine Learning · Cross-listed from cs.CV
Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architecture-Agnostic Brain Tumor MRI Triage
Medhansh Sharma
Deep networks now subtype
brain tumors on MRI about as well as specialist readers, yet accuracy is not what keeps them out of the clinic. What matters at the point of care is whether a model's confidence can be trusted to flag the cases it is likely to misclassify and defer them to a human. Deterministic estimates cannot: an auxiliary confidence head trained alongside the classifier collapses to a near-constant output that says nothing about correctness. This study proposes an uncertainty-first pipeline for four-class
brain tumor MRI (glioma, meningioma, pituitary, no tumor) that reads predictive uncertainty from Monte Carlo (MC) Dropout over T = 20 passes and turns the resulting
entropy into an explicit rule for deferring uncertain cases to a radiologist. We partitioned 7,200 images by perceptual-hash cluster, closing the near-duplicate leakage that inflates accuracy under naive splitting, and evaluated the pipeline on ViT-B/16 and ResNet-50 across five seeds along three axes: discrimination, calibration, and selective prediction. Both discriminate strongly (macro-AUC 0.994; accuracy 0.962 and 0.964), and no seed separates them (0 of 5 significant, p < 0.05), so the result is driven by the uncertainty pipeline, not the network. A single temperature scalar pulls the deterministic softmax into tight calibration (expected calibration error 0.016-0.020), and deferring the most uncertain 5% of cases lifts accuracy on the rest to about 0.98 on both (area under the risk-coverage curve 0.010-0.011). MC-Dropout uncertainty here is thus calibrated, non-collapsing, and directly actionable through a concrete deferral rule, providing an architecture-agnostic basis for calibrated, defer-to-human
brain tumor MRI triage under internal validation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data
Usman M. Khan
World models, especially based on JEPA architectures, have been shown to learn robust dynamics of various environments. However, learning from visually complex real-world data remains a challenge, especially in unpredictable outdoor environments. We introduce depth as a
geometric prior during training in learning more robust latent dynamics directly from
robot video data and handling visual complexity. This combines depth supervision with an isotropy-inducing latent regularizer (SIGReg), maximizing task-agnostic latent diversity while constraining how that diversity is organized, with the combined objective targeting the highest-
entropy representation consistent with scene geometry. To satisfy this greater complexity without increasing inference time, we also add training-only overparameterization. Training an 18M-parameter model on
video from a real agricultural
robot, we evaluate with frozen-representation visual odometry probes, predictor-based surprise detection, and multi-step latent rollout fidelity. Compared to the baseline LeWM, our method lowers visual odometry probe error by 33%, substantially increases surprise-score separation both in-domain and on the out-of-domain TartanGround
benchmark, and improves multi-step rollout fidelity under domain shift, with gains that grow with rollout horizon. Notably, we also see improvements in surprise-score separation on physics understanding that is not directly tied to 3D geometry, such as lighting and shadows. These results show that a lightweight training-time
geometric prior makes a compact JEPA world model more useful and more transferable on real outdoor data with strong underlying representations, without adding inference overhead. Our work suggests that depth as a physically grounded prior can enhance world model generalization on a variety of tasks.
Read the full abstract ▾
Machine Learning
Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling
Junhao Song, Yu Zhou, William Knottenbelt et al. (+1 more)
The scaling hypothesis assumes that increasing model parameters yields emergent
reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic
quantum circuit synthesis is a directional error. Unlike natural
languages,
quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified
quantum programs means that models learn syntax but fail to capture the physical semantics of the
Hilbert space. Since the valid subset of
circuit designs decays exponentially with the number of
qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric
agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular
quantum program generation. These considerations point toward generation methods that encode task-specific rules of
quantum information, rather than relying on imitation alone.
Read the full abstract ▾
All authors Junhao Song, Yu Zhou, William Knottenbelt, Yudong Cao
Machine Learning · Cross-listed from q-bio.QM
DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales
Kaihui Cheng, Zhiqiang Cai, Peng Tu et al. (+6 more)
Proteins function through coordinated motion across multiple spatial and temporal scales, underpinning processes such as ligand binding, allostery, and catalysis. However, accessing long-timescale conformational change through molecular dynamics (MD) simulations remains prohibitively expensive for systematic exploration across diverse systems. Here, we present DyneTrion, a generative
protein dynamics emulator that jointly enforces
geometric symmetry, structural consistency and temporal coherence within a single framework. DyneTrion uses a tri-
attention architecture that integrates invariant point
attention (IPA) for SE(3)-robust
geometric updates, spatial
attention anchored to a reference conformation to preserve structural integrity, and temporal
attention to model correlated
evolution across time frames. Across 100-ns MD trajectory simulation
benchmarks, DyneTrion reproduces MD-derived flexibility, ensemble distributions and interaction observables while maintaining stereochemical validity during extrapolation. To evaluate long time-scale generalization, we introduce dynamicPDB, a
dataset of over 10,000
proteins with up to 1-$\mu$s all-atom trajectories at 10-ps resolution and accompanying physical annotations. On microsecond trajectories, DyneTrion preserves free-energy landscapes and metastable-state populations, and it supports large conformational propagation in apo-to-holo transitions and fast folders. Together, DyneTrion provides a scalable path from static structure prediction toward time-resolved, ensemble-faithful
protein modeling. The code is publicly available at https://github.com/fudan-generative-
vision/DyneTrion
Read the full abstract ▾
All authors Kaihui Cheng, Zhiqiang Cai, Peng Tu, Yisong Yao, Limei Han, Libo Wu, Siyu Zhu, Tzuhsiung Yang, Yuan Qi
Machine Learning · Cross-listed from cs.CL
Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel
Sietse Schelpe
We report a way to make a frozen small
language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context. The restore is bit-exact: under a pinned deterministic configuration, the grafted logits are byte-for-byte identical to a fresh computation (SHA-256 equality), with zero KL divergence and 100% argmax agreement over fifty samples. We show that own-position graft is the unique numerically exact operating point on a model with floating-point rotary encoding, and we verify byte-exactness on two model scales (12B, 31B) and two GPU targets, one through a pre-registered replay. On AIME 2025, a frozen Gemma-4-12B moves from 80.0% to 93.3% once a verified solution library is grafted, above its own 77.5% and its 31B sibling's 89.2% published anchors. On the recurring case, eight problems the base model never solves within a 401,026-
token budget are answered from cached verified solutions in 61 total decode
tokens, a factor of 6,574 fewer
tokens and about 8,700x less energy; the capability claim proper rests on held-out transfer (7 of 7 at 31B). The same byte-exact store widens usable context from 32,768 to 2,854,766
tokens at zero extra accelerator
memory, and moves byte-identical between machines of the same architecture. We describe the system at the behavior level; the engine is proprietary, and every reported number is backed by committed input and output hashes so the scoring can be re-checked without it.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generation
Nutan Chen, Jianxiang Feng, Marvin Alles et al. (+1 more)
In recent years Flow Matching has become a prominent method for generative modeling
robot motion generation. In its generic form Flow Matching is an ODE-based neural sampler that is trained by regressing empirical flow fields associated with motion samples as data. However, in
robot motion generation we often have additional constraints that might not be present in the collected data. The majority of current approaches train the flow on the available data and use inference-time guidance to enforce task-specific constraints. To address this mismatch, we propose ConFlow, a constraint-guided flow matching framework that incorporates constraint information directly into the training objective via differentiable barrier or cost functions. To address design specifications such as smoothness and boundary conditions, we propose replacing the standard Gaussian source distribution used in flow matching training with a conditional Gaussian Process. Our approach also uses infeasible demonstrations as negative supervision, improving constraint satisfaction without requiring additional expert data. Experiments on a two-
robot navigation task demonstrate that ConFlow achieves lower collision rates and higher trajectory quality than standard flow matching baselines, with or without inference-time guidance. These results validate training-time constraint integration as an effective approach to closing the training–inference gap in generative motion models.
Read the full abstract ▾
All authors Nutan Chen, Jianxiang Feng, Marvin Alles, Botond Cseke
Machine Learning
HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects
Akshay Sasi
Machine-learning
datasets labelled "4D" universally denote three spatial dimensions plus time. We introduce HyperShadow, the first public
benchmark in which the fourth, fifth, and sixth dimensions are spatial: the task is to decide whether a 3D point cloud is a native three-dimensional shape or the projection, the "shadow", of a rigid object living in R^N (N = 4-6). We show this task is fundamentally distinct from intrinsic-dimension estimation: a shadow is still at-most-3-dimensional data, and standard
estimators (TwoNN, Levina-Bickel MLE) reach only 71-73% accuracy. Detection instead requires projection signatures, density folds, filled volumes with characteristic radial profiles, and
topology changes, which a 190k-parameter point network recovers at 96.6% accuracy across four corruption tiers, generalizing at 79-91% to object families never seen in training. On a temporal track of rigidly rotating objects we introduce a zero-parameter
rigidity witness: the residual of the optimal rigid 3D
alignment (Kabsch) between consecutive frames, which must vanish for any rigid 3D motion but cannot vanish for the shadow of a rigid rotation in R^N. This single interpretable statistic separates the classes at AUROC 0.982. All data are generated reproducibly from seeds; the
dataset, models, and code are released publicly. HyperShadow makes no claim about physical reality; it is a controlled instrument for studying which observable statistics can certify incompatibility with a purely three-dimensional explanation.
Read the full abstract ▾
Machine Learning
Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment
Mohammad Rashid and Hema Yoganarasimhan
Ad-load design is a central supply-side decision in sponsored search: more sponsored slots can raise revenue, but may crowd out organic results and degrade user outcomes. We study this trade-off using a large-scale randomized field experiment on an Android app store, where over five million users are exposed to one through six sponsored slots. Increasing ad load raises revenue by up to 43%, but reduces total search conversions by up to 5% and daily engagement by up to 2.2%. These average effects mask substantial heterogeneity: additional slots generate large revenue gains for high-ad-conversion queries, but little or negative marginal revenue for low-conversion queries. The trade-off also shifts within query as advertiser composition changes, such as brand-advertiser presence. Motivated by these findings, we design and deploy a novel adaptive
algorithm – exploration-augmented Locally Adaptive Ad Load (e-LAAL). e-LAAL combines LAAL, a model-free query-level decision rule that updates ad-load recommendations using recent outcomes, with static exploration arms that maintain support and provide fixed-policy counterfactual
benchmarks. We provide a finite-time dynamic-regret guarantee for the e-LAAL architecture. In a platform-level production deployment serving 22.3 million users and 77.6 million searches, e-LAAL improves the empirical revenue–conversion trade-off relative to deployed static
benchmarks and outperforms uniform and historical query-dependent static
benchmarks.
Read the full abstract ▾
Machine Learning
LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration
Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati et al. (+3 more)
Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present
LATTICE (Latent
Alignment of Tissue-level and Transcriptomic Information for Cross-modal
Embedding), a graph-based self-supervised framework that learns spot-level representations from harmonized
multimodal features.
LATTICE integrates five aligned modality blocks per Visium spot: Visium RNA, scMultiome RNA, scMultiome ATAC, spatial ATAC, and spatial CUT&Tag. These modalities capture spatial transcriptomic measurements, single-
cell inferred regulatory activity, and in situ chromatin and histone states within a unified
lattice representation.
LATTICE constructs a spatial neighborhood graph and trains a TransformerConv encoder using masked reconstruction, cross-modal
alignment, and spatial smoothness objectives. On a private 11-sample melanoma cohort from an anonymized clinical collaborator comprising 54{,}912 total spots,
LATTICE demonstrated stable optimization behavior, reproducible
embeddings across analysis seeds, and complete
multimodal integration across all samples. Adding scMultiome RNA to Visium RNA alone substantially improved concordance with Space Ranger clusters across 11 runs (adjusted Rand index [ARI] +0.157, normalized mutual information [NMI] +0.143, and spatial contiguity +0.174). Additional modalities further improved spatial contiguity and
multimodal utility score (MUS), although they sometimes reduced agreement with RNA-derived reference labels, likely because the learned
embeddings captured chromatin and regulatory structure beyond transcriptomic similarity alone. These results position
LATTICE as a practical and empirically grounded framework for
multimodal spatial omics integration, while also highlighting the need for stronger supervision and broader external benchmarking.
Read the full abstract ▾
All authors Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Hien Van Nguyen, Kunal Rai, Tania Banerjee
Machine Learning · Cross-listed from cs.IT
Decision Making Needs Uncertainty Quantification [Lecture Notes]
Osvaldo Simeone
Many signal processing systems ultimately exist to act. Whenever the state variable that determines the action to be taken by a decision maker, or
agent, is uncertain, the way that uncertainty is represented decides how well the
agent performs and how much its performance can be trusted. This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the {objective} and the knowledge of an
agent and the form of uncertainty representation that is sufficient to act optimally. To start, assuming a known environment distribution, we show that a risk-neutral
agent needs the posterior distribution over the state, whereas a risk-averse
agent can rely without loss of optimality on a {prediction set} and a worst-case decision rule. We then turn to the case in which the environment is unknown, and identify three complementary approaches to address the resulting epistemic uncertainty: calibration of a fixed predictor, credal (ambiguity) sets with distributionally robust optimization, and
Bayesian inference over model parameters. The common thread is that reliable decisions require an uncertainty representation matched to the decision objective and to the knowledge profile of the
agent, together with a guarantee that certifies the utility the
agent will actually obtain.
Read the full abstract ▾
Machine Learning
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg et al. (+1 more)
Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns
diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.
Read the full abstract ▾
All authors Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood
Machine Learning · Cross-listed from cs.AI
CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models
Zhu Cheng, Zhenming Wang, Yu Tang et al. (+13 more)
Product catalogs are the backbone of e-commerce sites, yet a large number of structured attributes (SAs) – such as material, color, and shape – often have missing values. Typically, SA values are extracted from product information, including titles and descriptions. While LLM-based generator-evaluator frameworks have demonstrated effectiveness for SA prediction – where an LLM generates SA values and another evaluates them – they face challenges when the Generator and Evaluator produce conflicting outputs, as either component can make mistakes. We introduce CatalogAgent, a novel agentic system that continuously improves Generator and Evaluator models for e-commerce catalog enrichment. When disagreements arise from (1) internal conflicts between the LLM-based Generator and Evaluator, or (2) external feedback from sellers on LLM outputs, a Supervisor
Agent intervenes to mediate these conflicts and make final decisions. The system also incorporates a
Memory Base and a
Memory Summarizer that stores Supervisor
Agent activities from individual cases and aggregates patterns into learnings. These learnings are fed back to the worker Generator and Evaluator LLMs, enabling self-improvement without human intervention. Through context engineering – injecting learnings and insights into worker LLMs' contexts – the system successfully transfers the Supervisor's capabilities to the Generator and Evaluator, improving their performance by 15.24% and 13.98%, respectively. Our experiments demonstrate a new paradigm of Supervisor
Agent-mediated self-learning systems for improving generative AI model accuracy.
Read the full abstract ▾
All authors Zhu Cheng, Zhenming Wang, Yu Tang, Dan Liu, Bryan Zhang, Athanasios N. Nikolakopoulos, Pranav Souri Itabada, Jing Zhang, Chih-Chi Chou, Peng Gao, Fatemeh Mansoori, Bharat Bojja, Sarath Chander, Sameer Thombare, Umit Batur, Tarik Arici
Machine Learning · Cross-listed from cs.CL
MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation
Thanni Adewuyi, Anuoluwa Sotome, Samuel Okoko et al. (+6 more)
Large
language models achieve strong scores on medical
benchmarks, yet these
benchmarks evaluate each question in isolation, providing no measure of whether a system can distinguish clinically similar presentations requiring different interventions. We introduce MamaBench, the first counterfactual
benchmark for maternal and paediatric AI: 434 expert-authored clinical narratives in 217 pairs across 371 pathologies, evaluated via the Bias Trap Rate (BTR), the conditional probability that a model fails the counterfactual given success on the base case. We propose Evidence-Anchored RAG (EA-RAG), a three-stage
retrieval method that replaces aggregate similarity with an evidence coverage objective through clinical parameter extraction, coverage
auditing, and contrastive sub-queries. Across eight configurations of four frontier LLMs, base accuracy overstates robust accuracy by 16-28 percentage points in every model. EA-RAG achieves 20.3% BTR and 65.0% robust accuracy on Claude Sonnet 4.6, a 5.5 percentage point BTR reduction without degrading base accuracy. The residual 20% BTR confirms that counterfactual robustness in clinical AI remains an open challenge. Keywords: counterfactual evaluation, clinical AI, maternal healthcare,
retrieval-augmented generation, diagnostic robustness
Read the full abstract ▾
All authors Thanni Adewuyi, Anuoluwa Sotome, Samuel Okoko, Angel Ezendu, Oluwafunke Akinbuwa, Oluwaseun Odunsi, Oluwasegun Oguntuase, Ifeoma Nwabueze, Abiodun Adereni
Machine Learning · Cross-listed from cs.CC
Random Parameter Noise Does Not Make Exact ReLU Verification Easy
Mojtaba Soltanalian
We study exact verification of ReLU networks in an
adversarial smoothed model. Every network weight and bias is independently perturbed by Gaussian noise, clipped to $[-2,2]$, and rounded to the exact dyadic grid determined by the input bit complexity. We show that, under the standard assumption $\mathrm{NP}\not\subseteq\mathrm{BPP}$, there is no sound and complete verifier whose expected running time is
polynomial in network size, bit complexity, and inverse noise level for every base instance. The conclusion already holds at the fixed noise level $\sigma_\star=2^{-11}$ for one-hidden-layer networks over a unit box, with hidden fan-in at most three and base coefficients in $[-1,1]$. The proof combines an exact gap
embedding with a quantitative robustness argument. For every E3SAT formula $\Phi$ with $m$ clauses, a four-ReLU-per-clause construction satisfies $\max_{x\in[0,1]^n} g_\Phi(x)=(m-\operatorname{unsat}(\Phi))/3$, and coordinatewise threshold rounding never decreases the objective. A weighted parameter-sensitivity inequality and Gaussian concentration then show that a verification gap linear in $m$ survives the aggregate perturbation of all coefficients with probability at least $1-e^{-m/8}$. The proof includes clipping, exact dyadic rounding, output-layer perturbations,
polynomial-bit sampling of the rounded Gaussian law, and the conversion from expected smoothed running time to a BPP
algorithm. Computational checks test the exact identity and illustrate the different scaling of extensive and constant gaps; they are diagnostics rather than evidence for the complexity
theorem. The result concerns worst-case base networks in the stated absolute-noise model, but it shows that parameter nondegeneracy alone does not yield a universal smoothed-
polynomial guarantee for exact verification.
Read the full abstract ▾
Machine Learning
A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning
Yang Liu, Yuhao Liu and Yunran Wei
We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting
agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive
Bayesian IRL method that infers
agents' latent risk objectives from their noisy observed decisions, explicitly allowing
agents to take
stochastic and suboptimal actions. We establish the existence of a finite set of distinguishing questions that identifies the preferred distortion riskmetric within the candidate class and prove that the convergence rate of the
algorithm is of order $O(\exp(-cm+O(\sqrt{m\log m})))$ under general settings, where $c>0$ is a constant and $m$ denotes the number of
algorithm iterations. On the optimization side, we develop a model-free RL
algorithm for optimizing policies under conditional distortion riskmetrics. By representing the objective as an integral of the conditional cost
quantile function with respect to the distortion function, the method unifies distortion-riskmetric objectives. We optimize diverse risk objectives by extending the Proximal Policy Optimization (PPO)
algorithm with policy, value, and
quantile neural networks, where the
quantile network estimates the full conditional cost
quantile function and enables numerical evaluation of general risk objectives. A comprehensive empirical study demonstrates the framework's elicitation accuracy and effectiveness in complex financial environments.
Read the full abstract ▾
Machine Learning
Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion
Fengzhuo Zhang, Zhuoran Yang and Dirk Bergemann
Large
Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive Supervised Fine-Tuning (SFT) versus lightweight In-Context Learning (ICL)? How does congestion from other users' personalization choices reshape these incentives? And what strategies should platforms adopt when offering multiple personalization
algorithms? We develop a tractable framework for LLM serving that captures the statistical-economic trade-offs users face. Our analysis yields several surprising insights. First, we show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios, but congestion can flip these rankings. Second,
equilibrium resource consumption exhibits pronounced non-monotonicity: improving pretraining precision reduces the congestion, while broader pretraining coverage and harder tasks sometimes increase it. Third, we prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load. Experiments with GPT-2 on linear regression tasks validate our theoretical predictions about
algorithm performance. Complementing these results, our review of documentation from 21 major AI platforms shows that the share offering both SFT and ICL increased from 9.5% in 2021 to 71.4% in 2025, consistent with our platform-design implications.
Read the full abstract ▾
Machine Learning
Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning
Haobo Zhang, Jiankun Wang, Suraj Rajendran et al. (+5 more)
Federated fine-tuning of large pre-trained models increasingly relies on Low-Rank Adaptation (LoRA) to reduce communication and computation, but heterogeneous clients can make adapter aggregation unstable. We identify the data-parameter interference as a
geometric source of this instability. This interference is controlled by the
alignment between LoRA update subspaces and client activations, suggesting that
federated LoRA aggregation should be viewed not only as parameter averaging but also as subspace allocation. We propose Dynamic Subspace Boosting (Dysco), a plug-in method that allocates client-specific LoRA subspaces in a
federated and dynamic manner. In each round, clients compute activation-insensitive subspaces from local representations and transmit only the resulting bases; the server then constructs client-specific merged subspaces through a closed-form solution that maximizes compatibility with other clients' insensitive directions. To handle representation drift, Dysco performs multi-round subspace boosting to preserve past update directions while adapting to future representations. We provide a convergence analysis that embeds the data-parameter interference as an aggregation-error term in a standard
federated optimization bound, and prove that Dysco's server-fixed merged subspaces yield a tighter upper bound on this error. Experiments on controlled synthetic
federated tasks and on MIMIC-IV clinical-note classification with Llama-3.2-1B show that Dysco substantially reduces interference, reduces the final-round synthetic training loss by up to 9 times relative to baselines under the orthogonal-subspace partition the theory identifies, improves all five tested FL
algorithms by up to 4.3% on MIMIC, outperforms recent
federated LoRA methods, and adds only 0.9% wall-clock overhead. Our code is available at https://github.com/illidanlab/Dysco.
Read the full abstract ▾
All authors Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou
Machine Learning · Cross-listed from math.PR
NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes
Anastasis Kratsios, Giulia Livieri and Philipp Schmocker
We address fundamental challenges in representing and computing $\mathbb{R}^{d}$-valued predictable square-integrable processes over $[0,T]$, collected in the space $\mathcal{H}^2_T(\mathbb{R}^{d})$. These processes are central to continuous-time
stochastic control, reinforcement learning, and mathematical finance. Although Wiener-chaos expansions offer strong theoretical tools, traditional computational methods are hindered by the need for large chaos dictionaries and high-order iterated integrals. To overcome these obstacles, we introduce NeuralChaos – a neural operator architecture that produces elements of $\mathcal{H}^2_T(\mathbb{R}^{d})$ using only finitely many evaluations of the driving Brownian motion, while preserving predictability and square-integrability. We prove that NeuralChaos is dense in $\mathcal{H}^2_T(\mathbb{R}^{d})$ and achieves the best $N$-term chaoslet approximation rates for compressible and Malliavin–Sobolev regular processes. Moreover, compressibility is shown to be typical for processes from $\mathcal{H}^2_T(\mathbb{R}^{d})$ under non-degenerate sub-Gaussian sampling. In contrast, we show that finite-dimensional Markovian neural SDE models constitute a meagre and Gaussian-null subset in $\mathcal{H}^2_T(\mathbb{R}^{d})$, regardless of discretization, whereas compressible processes are generic. Numerical experiments on a
stochastic optimal control problem and dynamic hedging highlight the practical effectiveness of our approach. Our results enable more efficient and expressive modelling in
stochastic analysis and mathematical finance.
Read the full abstract ▾
Machine Learning
Learning Who to Treat When Treatment is Missing
Johnna Sundberg, Rayid Ghani, Eli Ben-Michael et al. (+1 more)
Policy learning methods are increasingly used to inform treatment allocation under budget constraints. Most proposed methods assume complete treatment data, yet applications frequently suffer from missingness that can bias estimates and lead to suboptimal policies. We address this gap by extending efficient
estimators for average treatment effect (ATE) estimation to policy value and conditional average treatment effect (CATE) estimation under missing at random (MAR) and missing completely conditionally at random (MCCAR) treatment data. Through asymptotic efficiency analysis, we prove that the MAR
estimator, which leverages partially-observed units, is both valid and more efficient than the MCCAR
estimator when MCCAR assumptions hold. This result provides formal justification for preferring MAR-based estimation in policy learning under both missing data settings. Our comprehensive experiments using synthetic and semi-synthetic
datasets confirm that correctly specifying the missingness mechanism is crucial: misspecified
estimators remain biased regardless of sample size, while our
estimators achieve near-oracle performance when assumptions are satisfied. Our work provides practitioners with theoretically grounded, empirically validated tools for robust policy learning in the presence of missing treatment data.
Read the full abstract ▾
All authors Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy
Machine Learning
Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
Jan Betley, Johannes Treutlein, Jan Dubiński et al. (+5 more)
People use
language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a
Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current
alignment training and evaluations do not adequately address it.
Read the full abstract ▾
All authors Jan Betley, Johannes Treutlein, Jan Dubiński, Harry Mayne, Karol Gałązka, Niels Warncke, Anna Sztyber-Betley, Owain Evans
Machine Learning · Cross-listed from cs.CV
Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
Laurin Lux, Alexander H. Berger, Moritz Knolle et al. (+2 more)
Region-based loss functions, such as the Dice loss, have established themselves as the de facto standard for highly class- and region-imbalanced
segmentation tasks. However, models trained using region-based loss functions are notoriously miscalibrated and typically yield over-confident predictions. In medical imaging applications, such as defining tumor resection margins, this miscalibration is hindering clinical adoption. In this work, we outline a novel gradient perspective on this overconfidence and show how it affects region-based loss functions. We propose a "surgery" on the gradient vector field as a simple, yet effective intervention to mitigate calibration issues. This surgery adds a factor to the loss's partial derivative, scaling the gradient's magnitude linearly with the prediction error. In empirical evaluations across 2D and 3D medical
segmentation tasks, we demonstrate the effectiveness of this intervention while maintaining high prediction accuracy when used in conjunction with any region-based loss function.
Read the full abstract ▾
All authors Laurin Lux, Alexander H. Berger, Moritz Knolle, Daniel Rückert, Johannes C. Paetzold
Machine Learning
Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data
Youssef Drissi, Markus Ettl, Shivaram Subramanian et al. (+2 more)
We introduce COAT (Counterfactual Optimal Action Tree), a framework for learning interpretable prescriptive policies from observational data. COAT combines counterfactual outcome estimation with large-scale mixed-integer optimization, using column generation to translate causal predictions into feasible, transparent decisions under business and regulatory constraints. We apply COAT to airline ancillary pricing, a setting characterized by complex business rules and limited experimental flexibility. In a 17-week field pilot with a major global airline, COAT increased upsell revenue per booking by 6.9%, with the airline projecting \$50-\$150 million in incremental annual premium seat revenue across eligible domestic
markets. The success of the pilot led to scaled adoption and informed broader AI-driven decision initiatives within the organization.
Read the full abstract ▾
All authors Youssef Drissi, Markus Ettl, Shivaram Subramanian, Wei Sun, Zack Xue
Machine Learning
Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models
Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis et al. (+4 more)
In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple
datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models,
datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen
datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the
dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source
datasets, discussing the implications of the obtained results in relation to the characteristics of the
datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems.
Read the full abstract ▾
All authors Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis, Dimitrios Kotios, Vasileios Koukos, Dimosthenis Kyriazis, Jonh Soldatos
Machine Learning
NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis
Lincan Li, Zheng Chen and Yushun Dong
Seizure diagnosis from
EEG signals is a critical yet persistently challenging task, due to the complicated neural dynamics and the spurious connections in inter-channel modeling. While spatial-temporal graph neural networks (STGNNs) have advanced
EEG brain network representation learning, the resulting graph structures suffer from low clinical plausibility and limited interpretability due to their purely data-driven nature. To this end, we introduce NeuroGRIP, a
retrieval-augmented graph refinement framework that incorporates external medical knowledge to calibrate noisy
EEG graphs. We first construct a large-scale, domain-specific knowledge base derived from authoritative clinical guidelines. Leveraging large
language models, we extract structured biomedical entities and relations to form a textual knowledge graph (KG), which serves as external knowledge source of clinical priors. Our framework performs
alignment-aware query construction by projecting STGNN-generated
EEG node
embeddings into the semantic space of KG. Semantic queries are then executed via FAISS-based similarity search over knowledge triplets to retrieve relation evidence. Each predicted edge is assigned a confidence score based on retrieved similarity, relation type, and source reliability, enabling us to prune medically implausible edges from the originally predicted graph. Extensive experiments on TUSZ and CHB-MIT demonstrate that NeuroGRIP not only improves seizure detection accuracy but also enhances interpretability by grounding each prediction in clinically validated knowledge. This work provides the first unified framework that tightly couples
brain dynamics with external medical expertise via
retrieval-augmented
reasoning, paving the way for knowledge-enhanced, explainable clinical diagnosis. The code is available at: https://github.com/LincanLi-X/NeuroGRIP.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs
Manuel Fernandez V and Yizhe Zhu
We study sparse threshold random
geometric graphs generated by high-dimensional spherical or Gaussian latent vectors. Although each edge has marginal probability $p$, shared latent variables make the adjacency entries dependent. At the connectivity scale $np=\Omega(\log n)$, the spherical adjacency
matrix satisfies, with high probability,$\|A-\mathbb E A\|_{\mathrm{op}}=O\left(\sqrt{np\log n}+np\tau\right)$, where $\tau$ is the cap threshold; an analogous estimate holds for Gaussian vectors after controlling radial fluctuations. This sharpens the spectral bound in Liu, Mohanty, Schramm, and Yang (2023) under weaker assumptions and strengthens the global-synchronization guarantee of Abdalla, Bandeira, and Invernizzi (2024) for the homogeneous Kuramoto model. The leading eigenspace also estimates the latent geometry. When $np\gg\log n$, vector and relative Gram-
matrix errors vanish for$\log(1/p)\ll d\ll np\log(1/p)/\log n$ in the spherical model and $\log^2(1/p)\log n\ll d\ll np\log(1/p)/\log n$ in the Gaussian model, improving the recovery conditions of Li and Schramm (2023). For the Gaussian mixture block model introduced there, a
polynomial-time semidefinite program gives, to our knowledge, the first exact-recovery guarantee at the connectivity scale in a moderate-separation regime. At much larger separation, fixed edge density creates isolated vertices and makes exact recovery impossible. Our reusable decoupling and
matrix concentration framework avoids trace-moment methods and applies broadly to random graph models with latent vectors.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network
Daniel Gaytan-Villarreal, Peter Meiring, Daniel Baxter et al. (+6 more)
Ionizing radiation from
cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting
qubits (charge jumps), causing correlated errors that challenge fault-tolerant
quantum computing while simultaneously providing a detection signature for
quantum sensing applications. Current detection methods operate offline, introducing latency incompatible with in-the-loop
qubit control. In this paper, an online detector of charge jumps for superconducting
qubits, based on a dilated causal convolutional neural network (DCCNN) designed for in-the-loop deployment on the
Quantum Instrumentation Control Kit (QICK) platform, is presented. The network is trained on synthetic Ramsey
tomography scans generated from
qubit templates measured at the Northwestern Experimental Underground Site (NEXUS) at Fermilab, and translated to FPGA firmware via hls4ml with ap_fixed$\langle 16,6 \rangle$ quantization, reaching a per-inference latency of $ 32.0 \mu$s on the Zynq UltraScale+ RFSoC ZCU216. At this operating point the DCCNN matches the detection efficiency of the established offline $\chi^2$
algorithm ($0.843 \pm 0.022$ vs. $0.868 \pm 0.007$ on $|\Delta q| \in [0.1, 0.5] e$ at matched false-positive rate), while requiring no per-
qubit hyperparameter tuning. This shifts charge-jump detection from a post-hoc diagnostic to a control-loop primitive, enabling adaptive protocols that respond to radiation-induced events in situ, with applications to
quantum-computing error mitigation and to the use of superconducting
qubits as particle detectors.
Read the full abstract ▾
All authors Daniel Gaytan-Villarreal, Peter Meiring, Daniel Baxter, Daniel Bowring, Grace Bratrud, Matteo Cremonesi, Giuseppe Di Guglielmo, Grace Wagner, Bowen Xiao
Machine Learning · Cross-listed from cs.CV
XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation
Md Mahedi Hasan, Md Mushfiqur Rahaman, Alan Pachkovskiy et al. (+3 more)
Defect
segmentation in additive manufacturing (AM) X-ray computed
tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions. Although recent foundation models such as the Segment Anything Model (SAM) provide strong general-purpose
segmentation priors, their natural-image pre-training transfers poorly to the AM XCT domain, where defects appear as subtle non-semantic microstructural anomalies. Moreover, adapting SAM to the AM domain is further limited by the large domain gap and scarcity of labeled real XCT data. We present XCT-SAM, a sequential parameter-efficient adaptation framework for AM XCT defect
segmentation. Instead of adapting SAM directly from natural images to XCT data, we first fine-tune Conv-LoRA adapters on an
alloy-microstructure
dataset and subsequently transfer the adapted model to XCT images, progressively bridging the domain gap. Using Conv-LoRA adapters with rank r=2, the framework injects convolutional spatial inductive bias into SAM's backbone while training approximately 4.15M parameters and keeping over 99% of the model frozen. We evaluate XCT-SAM on out-of-distribution CycleGAN-XCT
benchmarks and real-world NIST XCT scans. Across both settings, XCT-SAM consistently outperforms zero-shot SAM and other domain-adapted SAM baselines, achieving the best overall IoU and Dice scores. These results demonstrate the effectiveness of intermediate domain adaptation with parameter-efficient adapters for industrial XCT defect
segmentation. The source code is publicly available at https://github.com/Mahedi-61/XCT-SAM.git
Read the full abstract ▾
All authors Md Mahedi Hasan, Md Mushfiqur Rahaman, Alan Pachkovskiy, Imtiaz Ahmed, Jeremy Dawson, Srinjoy Das