Machine Learning · Cross-listed from cs.AI
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
Kyungmin Park and Taesup Kim
Safety-aligned Large
Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent work attributes this to shallow safety, where
alignment concentrates in the first few output
tokens. We show that shallow safety is a special case of a broader inference-time vulnerability, in which short
token injections at any generation step can substantially alter subsequent safety behavior. We also find that a model's
alignment with refusal directions in its hidden states does not predict its robustness to such injection, revealing that internal state alone does not determine generation behavior under perturbation. To address this, we align models directly on generation trajectories constructed by simulating mid-sequence perturbation, and show that this improves robustness to mid-sequence injection and generalizes to attacks that exploit early-
token generation. Our work argues that robust safety
alignment requires training on the generation process itself, not only its outputs.
Read the full abstract ▾
Machine Learning
UniFair: A unified fair clustering approach based on separation and compactness
Antonia Karra, Vasiliki Papanikou, Georgios Vardakas et al. (+2 more)
Clustering is increasingly used to support high-impact decisions, yet standard objectives such as k-means can produce clusterings that treat demographic groups unequally. Existing fair clustering methods typically optimize a single notion of
fairness and often overlook how clustering costs interact with the geometry of the induced decision boundaries. We propose UniFair, a unified framework that jointly optimizes separation
fairness and social
fairness. Separation
fairness encourages protected groups to lie farther from the induced decision boundaries, while social
fairness reduces disparities in within-cluster distortion by penalizing group-wise clustering costs. We develop gradient-based optimization procedures for separation-fair and unified k-means objectives, and extend them to deep clustering by enforcing the same criteria in the latent space of an autoencoder. Experiments on tabular and image
datasets show that UniFair reduces both boundary-related and cost-based group disparities with only a modest increase in clustering loss.
Read the full abstract ▾
All authors Antonia Karra, Vasiliki Papanikou, Georgios Vardakas, Evaggelia Pitoura, Aristidis Likas
Machine Learning
Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control
Jihoon Hong, Alice Chan, Qiyue Dai et al. (+2 more)
Text-to-
video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs without sacrificing visual quality. Activation steering offers an attractive mechanistic alternative to finetuning and
prompt filtering, but existing T2V steering methods remain limited, typically applying coarse, non-anticipative interventions that can lead to oversteering and content degradation. To close this gap, we propose Latent Activation Linear-Quadratic Regulator (LA-LQR), a reduced-order optimal control framework for minimally invasive T2V steering. LA-LQR formulates T2V inference as a dynamical system and computes closed-loop feedback interventions that steer activations toward desired feature setpoints while penalizing unnecessary perturbations. To make optimal control feasible for high-dimensional
video activations, we project activations onto a low-dimensional, task-relevant subspace derived from contrastive
prompt pairs, estimate local linear dynamics in this latent space, and solve a latent LQR problem to obtain timestep- and layer-specific steering signals. We provide theoretical bounds relating latent setpoint tracking to raw activation-space feature control, and empirically validate the fidelity of the reduced latent dynamics. On concept steering and
video safety
benchmarks, LA-LQR reduces unsafe generations relative to baselines, while preserving
prompt fidelity and visual quality.
Read the full abstract ▾
All authors Jihoon Hong, Alice Chan, Qiyue Dai, Julian Skifstad, Glen Chou
Machine Learning
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
Chong Zhang, Xiang Li, Jia Wang et al. (+3 more)
The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability. We propose a principled, attack-agnostic robustness metric based on the spectral norm of the Fisher Information
Matrix (FIM), which quantifies the worst-case sensitivity of the model's output distribution to input perturbations. Theoretically, we establish that the FIM equals the variance of the input Jacobian and derive closed-form spectral bounds for common architectures, including VGG, ResNet, DenseNet, and
Transformer, providing the first theoretical robustness ranking. To enable scalable evaluation, we develop efficient
algorithms, including power iteration and Hutchinson-based estimation, that support both white-box and black-box settings. Extensive experiments across multiple
datasets, including CIFAR, ImageNet, and medical images, and across multiple architectures show a strong correlation between our metric and
adversarial vulnerability. Our framework serves as an interpretable diagnostic tool that complements attack-based evaluations, offering insights into architectural sensitivity and guiding the design of more robust models. Code is available at: https://github.com/franz-chang/SRP/.
Read the full abstract ▾
All authors Chong Zhang, Xiang Li, Jia Wang, Qiufeng Wang, Eng Gee Lim, Xiaobo Jin
Machine Learning · Cross-listed from math.OC
Near-Optimal Decentralized Stochastic Convex Optimization over Networks
Nitai Kluger, Amit Attia and Tomer Koren
We study decentralized
stochastic smooth convex optimization, where $M$ workers minimize an average objective using local
stochastic gradients and neighbor-only communication over a fixed gossip network. A central question in this setting is to determine the largest number of workers that can be used under a total budget of $N$ gradient samples while still preserving the centralized $O(1/\sqrt N)$ statistical rate. We introduce an accelerated decentralized method that preserves this rate for up to $\smash{M\lesssim \sqrt{\rho}\,N^{3/4}}$ workers, where $\rho$ is the spectral gap of the gossip network, improving the best prior maximal scaling of $\smash{M\lesssim \rho\sqrt N}$. The method is based on a one-step-delayed
stochastic acceleration scheme that enables workers to interleave minibatching with accelerated gossip while controlling residual disagreement, and its guarantee depends only logarithmically on the optimum-local heterogeneity. We also establish a matching lower bound for linear-span decentralized first-order methods, showing that the method is optimal up to logarithmic factors.
Read the full abstract ▾
Machine Learning
Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
Vincent Bürgin, Daniel Herbst, Ya-Wei Eileen Lin et al. (+1 more)
Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter
symmetries: transformations that leave the realized function unchanged. Despite growing
attention to parameter
symmetries, the exact interplay between parameters, data, and representations remains underexplored. To investigate this, we develop a theoretical framework of effective function classes, i.e., the set of functions a
neuron can realize on its input support, and the norm cost of realizing them. We then formalize effective
symmetry breaking via
neuron identifiability across independent training runs. Our analysis shows that neural networks can admit large families of approximately equivalent solutions even in structurally asymmetric models. We further show that
neuron identifiability enables representation merging without prior
alignment, and characterize when such merging admits a linear low-loss path. These findings highlight the role of effective function classes in affecting the loss landscape.
Read the full abstract ▾
All authors Vincent Bürgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka
Machine Learning
An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
Ossi Lehtinen
Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_{\text{model}}$-dimensional vector per time step. We audit eight input encoders – a shared-scalar baseline, per-channel linear projections, an orthogonality regulariser, a nonlinear MLP, block-partitioned concatenation, channel-independent and channel-as-
token architectures, and a projected positional encoding – on a synthetic
benchmark where channel identity is informative and on ETTh1, scored by next-step negative log-likelihood. The headline is practical near-equivalence within a wide "top tier": the standard per-channel linear projection matches every alternative up to small, statistically real but practically modest differences. A direct
geometric probe attributes this to a spontaneous orthogonalisation of the per-channel projections: with no explicit regulariser they tighten well beyond the near-orthogonality of random initialisation, letting the standard linear recover channel identity from the summed
embedding. Two encoders lose decisively: the shared-scalar baseline collapses for information-theoretic reasons we make explicit, and the channel-independent PatchTST-spirit baseline overfits universally on the synthetic
benchmark and underperforms on both. Paired tests resolve two small gaps: projecting the sinusoidal positional encoding through a learned linear layer edges the rest at small $C$ by extending this orthogonality to the positional subspace; a nonlinear MLP stem edges them at the largest $C$, with the gap shrinking under more training data. The practical recommendation: use the standard per-channel linear projection by default; reach for something more elaborate only when the task calls for it.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment
Ajay Vishwanath and Christian Omlin
Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being fully dependent on the reward function design. Thus far, this technique has been demonstrated to be effective in grid worlds and toy-problem environments with minimal state and action spaces. To expand this research to more sophisticated environments, we introduce a two-player multi-
agent environment based on the role-playing board game known as Fog of Love. In this environment, two
agents compete to fulfill their individual virtues, while also cooperating to satisfy their relationship. Given the multi-
agent nature, this is a complex problem where multi-
agent deep deterministic policy gradient
agents neither compete nor cooperate successfully. We present evidence that localized affinities enhance
agent performance in achieving both competitive and cooperative objectives, resulting from superior overall scores in both domains. This not only results in virtuous choices but also clarifies an
agent's teleology and makes its behavior human-level interpretable.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection
Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan et al. (+1 more)
Safe
robot control requires maximizing return while satisfying safety constraints. In off-policy safe reinforcement learning, reward and safety Q-values are commonly learned by separate critic ensembles, with uncertainty handled independently for each objective. This objective-wise treatment neglects inter-objective correlation and can lead to overly conservative value estimates, thereby reducing sample efficiency. To address this issue, we propose Cholesky-Ordered Projection Q-learning (COP-Q), a safety-first method that incorporates inter-objective covariance into vector-valued Q-value estimation. COP-Q constructs a generalized confidence bound in the joint Q-value space and uses Cholesky factorization to encode objective priority in a sequential form. This preserves conservatism on safety while adaptively reducing excessive conservatism on the reward objective. The resulting estimate is used in both temporal-difference target computation and actor optimization. COP-Q incurs minimal computational overhead and is readily compatible with most existing deep Q-learning frameworks. Experiments on
robot locomotion in Brax and safe
navigation in Safety-Gymnasium, covering both hard- and soft-safety settings, demonstrate that COP-Q achieves strong safety performance together with competitive or improved sample efficiency relative to representative baselines.
Read the full abstract ▾
All authors Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan, Julian F. P. Kooij
Machine Learning · Cross-listed from cs.CL
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
Soyeong Jeong, Jinheon Baek, Minki Kang et al. (+1 more)
Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-
agent baselines on task coverage, identification, and resolution.
Read the full abstract ▾
All authors Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang
Machine Learning
Curvature-aware dynamic precision approach for physics-informed neural networks
Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn et al. (+1 more)
Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by
embedding physical laws directly into neural network training. However, recent studies show that PINN optimisation is sensitive to numerical precision. Existing implementations commonly use either single precision (FP32), which is computationally efficient but prone to failure modes, or double precision (FP64), which is robust but substantially expensive. This creates a trade-off between computational efficiency and numerical accuracy. To reduce the computational cost of double-precision training while retaining prediction accuracy, we propose a
curvature-aware precision controller that adapts numerical precision during training rather than treating it as a fixed implementation choice. The proposed method reuses
curvature information derived from the limited-
memory BFGS (L-BFGS) optimiser to construct a precision controller, retaining FP32 when lower precision is sufficient and promoting computation to FP64 when the training dynamics indicate numerical sensitivity or precision-limited stagnation. We evaluate the proposed approach on four canonical PINN failure-mode
benchmarks and an irradiance-driven ordinary differential equation example. We further test the proposed approach across different neural network architectures. The method consistently matches or even slightly exceeds full FP64 solution accuracy while reducing training time relative to full double-precision training on all
benchmark equations. The obtained results indicate that precision sensitivity in PINN optimisation is phase-dependent, and that selectively applying higher precision only during numerically critical stages can lower computational cost without sacrificing predictive accuracy.
Read the full abstract ▾
All authors Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn, Taniya Kapoor
Machine Learning
Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning
Viktor Veselý, Aleksandar Todorov, Erwan Escudie et al. (+1 more)
Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood. We identify a systematic failure mode in deep reinforcement learning (RL) termed Trace-Mediated Peak Bias (TMPB). At intermediate eligibility trace depths,
agents irrationally prefer trajectories with high-magnitude reward “peaks” over alternatives with higher cumulative returns. This provides a mechanistic account of the Peak-End Rule: a human
memory bias where experiences are judged by their most intense moments rather than integrated utility. We show that TMPB emerges because traces amplify distal Temporal Difference errors into “gradient shocks” that fixed-step-size
Stochastic Gradient Descent cannot normalize, leading to global overestimation. Conversely, adaptive optimizers mitigate this pathology via second-moment normalization. Our results suggest that human-like saliency distortions may emerge naturally from the mathematical constraints of credit assignment in distributed systems, and that adaptive optimization is a theoretical necessity for rational value estimation.
Read the full abstract ▾
All authors Viktor Veselý, Aleksandar Todorov, Erwan Escudie, Matthia Sabatelli
Machine Learning
Contrastive Learning and Correlation Clustering for Sequences of Network Telescope Data
Jannik Presberger, Alexander Männel, Maynard Koch et al. (+3 more)
Understanding activities of Internet scanners is challenging; it often requires identifying relationships between sources, a task for which semantic annotations are scarce. This work investigates whether semantically meaningful pairwise relationships between sequences of network flow records can be estimated by contrastive learning, without pretraining and without annotations. To this end, we propose a
transformer model that embeds minimally preprocessed sequences of network flow records and train it using contrastive learning. With the similarities obtained from this model, we state a correlation clustering problem and solve it locally. Experimentally, we show: Learned similarities are higher on average for sequences originating from the same source than for sequences originating from different sources, and this property generalizes to unseen sequences of unseen sources. Moreover, correlation clustering yields clusters consistent with scanner labels. The complete source code of the
algorithms and for reproducing the experiments is publicly available.
Read the full abstract ▾
All authors Jannik Presberger, Alexander Männel, Maynard Koch, Thomas C. Schmidt, Matthias Wählisch, Bjoern Andres
Machine Learning · Cross-listed from cs.CL
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Jingwen Chen, Wenkai Yang, Shengda Fan et al. (+7 more)
Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large
language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement. We systematically examine this failure through three vital dimensions of experience internalization: (1) Experience Granularity: We find that principle-level experience is more durable than instance-level experience, as it effectively abstracts transferable strategies away from trajectory-specific details. (2) Experience Injection Pattern: Our analysis reveals that step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states, a property that is critical for long-horizon tool use. (3) Internalization Regime: We demonstrate that off-policy context-
distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-
distillation, which is inherently limited by local corrections on student-induced flawed states. Together, these insights yield a simple yet robust recipe for stable and sustainable experience internalization, providing concrete guidance for engineering self-evolving and continually learning LLMs.
Read the full abstract ▾
All authors Jingwen Chen, Wenkai Yang, Shengda Fan, Wenbo Nie, Chenxing Sun, Shaodong Zheng, Yangen Hu, Lu Pan, Ke Zeng, Yankai Lin
Machine Learning
Graph-Guided Universum Learning in Generalized Eigenvalue Proximal SVMs for Alzheimer's Disease Classification
Yogesh Kumar, Vrushank Ahire and Mudasir Ganaie
Early and accurate detection of Alzheimer's disease (AD) is important for timely intervention and disease management. Generalized
Eigenvalue Proximal Support Vector Machine (GEPSVM) and its Universum-based variants have shown promising results for AD classification. However, existing methods treat Universum samples as independent points and do not consider the
geometric relationships among them. This paper proposes two graph-guided Universum learning models, namely UG-GEPSVM and IUG-GEPSVM, for AD versus cognitively normal (CN) classification using structural MRI data. In the proposed framework, mild cognitive impairment (MCI) subjects are used as Universum data to provide intermediate information between AD and CN classes. A graph is constructed over the Universum samples using Gaussian similarity, Minimum Spanning Tree connectivity, and multi-hop propagation. From this graph, a
Laplacian matrix is derived that captures the
geometric structure of the MCI samples. This
Laplacian-based regularization is incorporated into the learning process in place of the conventional independent Universum penalty term. UG-GEPSVM integrates this regularization into the generalized
eigenvalue formulation, while IUG-GEPSVM extends the numerically stable improved GEPSVM framework using a standard
eigenvalue formulation. Experiments on ADNI MRI
dataset variants using ICA- and PCA-based features at five different noise levels show that both proposed models consistently outperform existing GEPSVM and Universum-based methods. UG-GEPSVM achieves the highest average AUC of 88.07% and maintains stable performance under increasing noise levels. Statistical tests further confirm the significance of the observed improvements.
Read the full abstract ▾
Machine Learning
From Cone Geometry to Monge Structure: Local Defects and Global Regret in High-Dimensional Optimal Transport
Lei Luo and Jian Yang
Exact optimal transport in high dimensions becomes tractable only when additional structure selects the optimal coupling. Classical Monge transportation solves the discrete problem once a cost array is known to be Monge, but it does not explain when geometry in the original feature space creates that structure. We characterize this regime for cone-induced orders and squared Mahalanobis costs: Macuteness of the cone is equivalent to the Monge property of every cross-cost
matrix generated by two cone chains, after which classical northwest-corner optimality gives exact transport. When the inequalities fail, we derive an exact variational representation of northwestcorner regret over a marginal-dependent cumulative-deficit polytope. Its Fréchet box relaxation yields a projection-free, marginal-weighted localdefect bound; we characterize when the relaxation is exact and prove that it is worst-case sharp when only local defect budgets are known. We further show that the worst-case defect patterns can be realized by genuine squared-Euclidean cross-costs. Finally, Mahalanobis distances of observed increments to the cone control the local defects, while a strict
geometric margin gives an explicit radius of exact stability. The resulting theory links high-dimensional ground-space geometry to exact Monge transport and quantifies the global loss induced by local departures from ordered structure.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation
Prerana Ramkumar, Nouhaila Innan and Muhammad Shafique
Scene Graph Generation (SGG) requires relational
reasoning over objects and their interactions, but performance is constrained by long-tail predicate imbalance. Classical SGG models rely on
dataset statistics, leading to biased predictions toward frequent relations rather than fine-grained semantic predicates. Although debiasing improves mean recall, predicate classification in existing frameworks still relies on high-dimensional classical decision modules with high parameter overhead. This work introduces a resource-efficient hybrid
quantum predicate classifier for SGG by replacing the classical predicate head in the CFEN with a QP-Head trained using class-balanced WCE. To the best of our knowledge, this work is among the first evaluations of a hybrid
quantum architecture for scene graph predicate classification on Visual Genome 150. We evaluate the impact of
qubit count, encoding strategy, entangling
topology, and
circuit depth. Under a 4-
qubit configuration using Amplitude
Embedding and Strongly Entangling Layers, the QP-Head projects 4096-dimensional pair features into a 16-dimensional
quantum input while using 96 trainable
quantum parameters. Operating within this compressed representation space under WCE training, it achieves strong long-tail recognition, reaching a peak mR@100 of 57.25% compared to the 41.1% mR@100 reported in the CFEN baseline under standard training. Protocol-matched ablations indicate that the primary advantage of the
quantum head lies in extreme representational compactness rather than an accuracy gain over full-dimensional weighted classical heads: it achieves global recall within 0.19pp of the 2048-dimensional WCE classical baseline while operating from a 128x smaller head feature space. Scaling to 8
qubits maintains robust long-tail performance (55.38% mR@100 with 384
quantum parameters), while depth analysis highlights expressibility-latency trade-offs.
Read the full abstract ▾
Machine Learning
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh et al. (+3 more)
End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model. A natural approach is to reuse a shared
Transformer block recurrently, but we find that naive looping does not fully exploit additional recurrent compute. We introduce LARM, a depth-conditioned looped
Transformer that turns recurrent encoder depth into a controllable test-time compute axis. LARM combines sparse CTC checkpoints, supervision-clock
embeddings, FiLM depth conditioning, and delayed soft-posterior feedback. These components structure the loop into recognition checkpoints separated by latent refinement phases and allow shared weights to specialize across recurrent steps. On LibriSpeech, LARM improves WER as the number of inference loops increases and achieves performance competitive with deeper unshared-parameter baselines. Our results show that test-time compute scaling can extend beyond autoregressive
language-model
reasoning to continuous non-autoregressive
speech recognition.
Read the full abstract ▾
All authors Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh, Driss Khalil, Petr Motlicek, Ina Kodrasi
Machine Learning
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
Ayushman Raghuvanshi, Thummaluru Siddartha Reddy, Sundeep Prabhakar Chepuri et al. (+1 more)
Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural patterns. To mitigate this, we derive a parameter-efficient state-space modeling framework for continuous-time dynamic graphs (CTDG-SSM) from first principles. We first introduce continuous-time
Topology-Aware higher order
polynomial projection operator (CTT-HiPPO), a novel
memory-based reformulation of HiPPO to jointly encode temporal dynamics and graph structure. The solution from CTT-HiPPO is obtained by projecting the classical HiPPO solution through a
polynomial of the
Laplacian matrix, yielding
topology-aware
memory updates that admit an equivalent state-space formulation for CTDGs (CTDG-SSM). Then a computationally efficient discrete formulation is obtained using the zero-order hold approach for model implementation. Across
benchmarks on dynamic link prediction, dynamic node classification, and sequence classification, CTDG-SSM achieves state-of-the-art performance. Notably, it achieves large performance gains on
datasets that require long range temporal (LRT) and spatial
reasoning.
Read the full abstract ▾
All authors Ayushman Raghuvanshi, Thummaluru Siddartha Reddy, Sundeep Prabhakar Chepuri, Mahesh Chandran
Machine Learning · Cross-listed from math.NA
Fitting scattered data with optional monotonicity constraints on GPU: LipFit package
Gleb Beliakov
This paper presents a method of multivariate scattered data interpolation and approximation that produces optimal Lipschitz-continuous approximation, subject to the desired monotonicity constraints. This method relies on tight upper and lower approximations to the data, and is similar in its spirit to the nearest-neighbour approximation but does not suffer from discontinuities. Local Lipschitz interpolation and Lipschitz smoothing are also presented. This approach falls under the umbrella of instance-based approximation with no training phase, and it is suitable for GPU-based parallelisation. A Python GPU-friendly package LipFit which implements the methods discussed is discussed.
Read the full abstract ▾
Machine Learning
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Kaichao You, Ximei Wang, Mingsheng Long et al. (+1 more)
Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target domain. However,
algorithm comparison is cumbersome in Deep UDA due to the absence of accurate and standardized model selection method, posing an obstacle to further advances in the field. Existing model selection methods for Deep UDA are either highly biased, restricted, unstable, or even controversial (requiring labeled target data). To this end, we propose Deep Embedded Validation (DEV), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance. The variance is further reduced by the technique of control variate. The efficacy of the method has been justified both theoretically and empirically.
Read the full abstract ▾
All authors Kaichao You, Ximei Wang, Mingsheng Long, Michael I. Jordan
Machine Learning
Why Muon Outperforms Adam: A Curvature Perspective
Shuche Wang, Fengzhuo Zhang, Jiaxiang Li et al. (+2 more)
Muon improves training efficiency over Adam in large
language-model training by about two times, but the local
geometric source of this advantage remains unclear. Our work takes a first step toward demystifying
Muon's superiority over Adam from a
curvature perspective. First, we apply a second-order Taylor approximation to the training landscape and show that
Muon achieves a larger one-step loss decrease than Adam at matched validation loss. The two optimizers have comparable first-order gains, but
Muon consistently incurs a smaller second-order
curvature penalty. Second, we decompose this
curvature penalty into the squared update norm and Normalized Directional Sharpness (NDS). We find that
Muon and Adam have comparable update norms, so
Muon's smaller
curvature penalty is driven by lower NDS, not update scale. Third, we study how training data and model structure shape
Muon's NDS advantage. Using Zipf-Probabilistic Context-Free Grammar (PCFG) data with controlled imbalance, we show that data imbalance amplifies
Muon's NDS advantage over Adam. A within-/cross-layer decomposition further shows that, in the middle and late stages of training,
Muon's lower NDS is mainly sustained by smaller within-layer
curvature. Beyond empirical evidence, we analyze stylized quadratic problems with heterogeneous
curvature and gradient
alignment toward high-
curvature modes. We prove that
Muon attains a smaller average NDS than GD by balancing update energy across
curvature groups; when
curvature heterogeneity is sufficiently strong, this also yields lower local quadratic loss after the same number of steps.
Read the full abstract ▾
All authors Shuche Wang, Fengzhuo Zhang, Jiaxiang Li, Dirk Bergemann, Zhuoran Yang
Machine Learning · Cross-listed from cs.CL
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata et al. (+3 more)
Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the budget, so
prompt optimization is a search over the Pareto front of accuracy and
prompt-
token cost rather than for one
prompt. The usual shortcut, collapsing the objectives into a weighted sum, fixes the trade-off weight before search and often recovers only a narrow region of the front, a failure we call scalarization collapse. We present CRAFT (Cost-aware Refinement And Front-aware Tuning), a Pareto-front
prompt optimizer that treats target-LLM validation calls as the scarce resource and allocates them to candidates near the optimistic candidate front. Each round, complementary accuracy-oriented and cost-oriented generators propose edits, Pareto-gap acquisition spends the per-round validation budget, and NSGA-II retention keeps a spread-out population. Across six classification and
reasoning benchmarks, CRAFT's retained fronts reach both high-accuracy and low-cost regions, while accuracy-only, cost-only, and weighted-sum baselines each concentrate in narrower regions. The accuracy-cost trade-off becomes a post-search choice, not a pre-search weight.
Read the full abstract ▾
All authors Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata, Parag Agrawal, Yova Kementchedjhieva, Manish Gupta
Machine Learning · Cross-listed from cs.NE
U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts
Alexander Hagg, Tania Guerrero and Dirk Reith
Optimizing urban layouts for
climate adaptation requires balancing building density with cold-air ventilation. Because physics-based
climate simulations are computationally expensive, planners typically evaluate fewer than ten manual designs. \gls{qd}
algorithms offer a way to systematically illuminate the design space, but they require surrogate models to be practical. In this paper, we replace a slow, regulatory physics simulator with a spatial deep-learning surrogate (U-Net) inside an offline MAP-Elites loop. We systematically compare this spatial approach with a traditional \gls{gp} surrogate across different training-data strategies (quasi-random Sobol sampling vs.\ active \gls{qd} bootstrapping). Our results reveal that scalar \gls{gp} surrogates fail catastrophically when trained on random samples, requiring expensive, actively generated \gls{qd} archives to generalize. In contrast, the spatial inductive bias of the U-Net allows it to learn the underlying physics mapping robustly ($R^2 = 0.996$), completely independent of the training data source. This allows offline \gls{qd} optimization to achieve highly accurate fitness rankings ($\rho = 0.994$) using only a one-time batch of random training samples. The resulting pipeline, deployed in the open-source OpenSKIZZE tool, generates thousands of diverse,
climate-evaluated building layouts in under ten minutes.
Read the full abstract ▾
Machine Learning
ALINC: Active Learning for Inductive Node Classification via Graph Sampling
Pascal Plettenberg, Denis Huseljic, André Alcalde et al. (+2 more)
Active learning (AL) for node classification typically focuses on selecting the most informative nodes for annotation within one or a few large graphs (e.g., in social network analysis). However, in other domains, such as molecular chemistry or electronic design automation,
datasets consist of thousands of independent graphs. In many of these inductive settings, annotating an individual node requires a full-graph analysis, which effectively yields the remaining node labels on-the-fly. Therefore, these scenarios require AL strategies that select entire graphs instead of single nodes, a problem which has not been tackled in the literature so far. Thus, we introduce ALINC, an AL framework for inductive node classification via graph sampling. It bridges the existing methodological gap by elevating node-level utility measures to graph-level selection criteria through various aggregation mechanisms. In an extensive
benchmark including ten strategies, three aggregation methods, and four
datasets, we identify CoreSet, TypiClust, and BADGE as the top-performing graph sampling strategies. Our detailed analysis further reveals that the choice of the aggregation method is pivotal, as it substantially affects model performance and annotation costs. Finally, we demonstrate the effectiveness of ALINC in two use case studies: site-of-metabolism prediction in molecules and design automation of printed
circuit board schematics.
Read the full abstract ▾
All authors Pascal Plettenberg, Denis Huseljic, André Alcalde, Bernhard Sick, Josephine M. Thomas
Machine Learning
Explainably Safe Reinforcement Learning
Sabine Rieder, Stefan Pranger, Debraj Chakraborty et al. (+2 more)
Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly important for learned systems, whose decision-making processes are often highly opaque. Shielding is a prominent model-based technique for enforcing safety in reinforcement learning. However, because shields are automatically synthesized using rigorous formal methods, their decisions are often similarly difficult for humans to interpret. Recently, decision trees became customary to represent controllers and policies. However, since shields are inherently non-deterministic, their decision tree representations become too large to be explainable in practice. To address this challenge, we propose a novel approach for explainable safe RL that enhances trust by providing human-interpretable explanations of the shield's decisions. Our method represents the shielding policy as a hierarchy of decision trees, offering top-down, case-based explanations. At design time, we use a world model to analyze the safety risks of executing actions in given states. Based on this analysis, we construct both the shield and a high-level decision tree that classifies states into risk categories (safe, critical, dangerous, unsafe), explaining why a situation may be safety-critical. At runtime, we generate localized decision trees that explain which actions are allowed and why others are deemed unsafe. Our method facilitates explainability of the safety aspect in safe-by-shielding reinforcement learning, requires no additional information beyond what is already used for shielding, incurs minimal overhead, and integrates readily into existing shielded RL pipelines. In our experiments, we compute explanations using decision trees that are several orders of magnitude smaller than the original shield.
Read the full abstract ▾
All authors Sabine Rieder, Stefan Pranger, Debraj Chakraborty, Jan Křetínský, Bettina Könighofer
Machine Learning
VentAgent: When LLMs Learn to Breathe – Multi-Objective Arbitration for ARDS Ventilation
Teqi Hao, Yuxuan Fu, Xiaoyu Tan et al. (+4 more)
Mechanical ventilation for Acute Respiratory Distress Syndrome (ARDS) requires balancing competing physiological goals, including oxygenation, lung protection, and acid-base homeostasis. However, current data-driven methods, especially those imitating retrospective Electronic Health Records (EHR), often suffer from imitation bias. They may capture superficial correlations from inconsistent clinical demonstrations, such as associating passive ventilator settings with survival because such settings are common in stable patients, and thus fail to generalize to volatile or out-of-distribution phenotypes. Standard Reinforcement Learning (RL) methods also struggle with the
adversarial trade-offs of critical care and often produce opaque policies with limited clinical interpretability. To address these limitations, we introduce VentAgent, a hierarchical framework in which Large
Language Models (LLMs) act as transparent arbitrators for mechanical ventilation. We reformulate ventilation control as a dynamic Multi-Objective Arbitration process rather than single-objective optimization. VentAgent decomposes decision-making into three interpretable stages: Perception, Planning, and Orchestration. By leveraging the semantic
reasoning capabilities of LLMs, it synthesizes strategies from heterogeneous experts and resolves conflicting clinical priorities through an explicit coordination mechanism. Evaluations on a high-fidelity physiological simulator show that VentAgent outperforms state-of-the-art RL and classical control baselines. Moreover, it converts control decisions into human-readable
reasoning chains, offering a safer, more interpretable, and adaptable paradigm for critical care automation.
Read the full abstract ▾
All authors Teqi Hao, Yuxuan Fu, Xiaoyu Tan, Shaojie Shi, Bohao Lv, Yinghui Xu, Xihe Qiu
Machine Learning
Liyi Feng, Yifa Tang, Yulin Xie et al. (+2 more)
High-dimensional
Hamiltonian systems play a central role in many scientific and engineering disciplines, with dynamics that evolve on
symplectic manifolds. Although deep learning provides powerful tools for constructing its low-dimensional surrogates from data, the intrinsic
symplectic structure is easily destroyed during model reduction. As a result, a standard autoencoder may produce latent coordinates that do not support a
Hamiltonian flow, leading to unstable long-time prediction. In this paper, we first establish a universal approximation
theorem for
symplectic embeddings. And based on the theory, we propose symplecticity-preserving autoencoders (SpAE), in which the decoder is parameterized as a
symplectic embedding and the encoder is constructed as the corresponding
symplectic projection. This architecture is expressive enough to approximate nonlinear
symplectic embeddings and the corresponding
symplectic projection, preserves the
symplectic structure exactly by construction, and can be trained by standard unconstrained optimization, thereby improving both reconstruction and prediction accuracy. Extensive experiments on high-dimensional
lattice and particle systems demonstrate the effectiveness of the proposed method.
Read the full abstract ▾
All authors Liyi Feng, Yifa Tang, Yulin Xie, Ruili Zhang, Aiqing Zhu
Machine Learning
QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy
Pasindu Wickramasinghe, Achyuta Muthuvelan, Rachmad Vidya Wicaksana Putra et al. (+2 more)
LLMs have become the state-of-the-art
algorithms for solving NLP tasks. However, they typically come at huge computational and
memory costs, thus making them difficult to deploy on embedded systems. Toward this, state-of-the-art methods typically employ uniform post-training quantization (PTQ) across
attention blocks of the network, hence overlooking the potential of applying different quantization levels in the same network. They also employ complex operations to mitigate the negative impact of activation outliers, hence incurring high computational overheads. Moreover, they have not considered evaluation using emerging LLMs with non-conventional
attention architectures (e.g., state-space models), which pose different challenges in applying quantization. To address these limitations, we propose QuBLAST, a novel PTQ methodology that employs block-level compression approach with activation scaling strategy for LLMs. Block-level compression approach enables mixed-precision quantization across blocks of the network, while activation scaling strategy efficiently mitigates the negative impact of activation outliers. Specifically, QuBLAST first analyzes the sensitivity of different
attention blocks in the pre-trained model through the cross-
entropy loss analysis. QuBLAST leverages this sensitivity analysis to determine the weight quantization level for each
attention block in the model. Furthermore, QuBLAST employs the activation scaling map for each block to control the range of activation values and mitigate the negative impact of activation outliers, thereby enabling better quantization results. Experimental results show that, QuBLAST reduces model sizes by 40%-45.2% across different model architectures (i.e., Qwen3-8B, Llama3-8B, Mistral v0.1-8B, and Falcon H1R-7B), while maintaining the performance within 5% perplexity increase for the WikiText-2 and WikiText-103
datasets.
Read the full abstract ▾
All authors Pasindu Wickramasinghe, Achyuta Muthuvelan, Rachmad Vidya Wicaksana Putra, Minghao Shao, Muhammad Shafique
Machine Learning · Cross-listed from cs.CV
Beyond Symmetric Alignment: Spectral Diagnostics of Modality Imbalance in Vision-Language Models in the Medical Domain
Alessandro Gambetti, Qiwei Han, Cláudia Soares et al. (+1 more)
Vision-
Language Models (VLMs) struggle when applied to medical image-text data, yet the tools available to diagnose this failure remain limited. Existing representation
alignment metrics are symmetric, collapsing both modalities into a single score and hiding which modality drives cross-modal degradation. We introduce the Spectral
Alignment Score (SAS), an asymmetric metric that projects both modalities onto the principal eigenbasis of an anchor modality and computes
eigenvalue-weighted per-eigenmode correlations, resulting in directional scores whose difference quantifies modality information imbalance. We embed SAS within a benchmarking framework evaluating 15 VLMs across natural and medical image-text
datasets alongside 6
alignment metrics and bidirectional
retrieval. Our experiments show that medical images retain richer structural information than their paired clinical reports, a directional asymmetry invisible to all competing metrics, and that SAS achieves the strongest zero-label correlation with
retrieval performance in the medical domain, positioning it as a practical diagnostic tool for clinical deployment. Code is available at this URL: https://github.com/iamalegambetti/medical-vlms-assessment.
Read the full abstract ▾
All authors Alessandro Gambetti, Qiwei Han, Cláudia Soares, Hong Shen