Machine Learning · Cross-listed from cs.CL
LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
William Lugoloobi, Thomas Foster, William Bankes et al. (+1 more)
Running LLMs with extended
reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We investigate whether their own likelihood of success is recoverable from their internal representations before generation, and if this signal can guide more efficient inference. We train linear probes on pre-generation activations to predict policy-specific success on math and coding tasks, substantially outperforming surface features such as question length and TF-IDF. Using E2H-AMC, which provides both human and model performance on identical problems, we show that models encode a model-specific notion of difficulty that is distinct from human difficulty, and that this distinction increases with extended
reasoning. Leveraging these probes, we demonstrate that routing queries across a pool of models can exceed the best-performing model whilst reducing inference cost by up to 70% on MATH, showing that internal representations enable practical efficiency gains even when they diverge from human intuitions about difficulty. Our code is available at: https://github.com/KabakaWilliam/llms_know_difficulty
Read the full abstract ▾
All authors William Lugoloobi, Thomas Foster, William Bankes, Chris Russell
Machine Learning
Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education
Anna Bodonhelyi, Mengdi Wang, Efe Bozkir et al. (+2 more)
Since the COVID-19 pandemic, online courses have expanded access to education, yet the absence of direct instructor support challenges learners' ability to self-regulate
attention and engagement. Mind wandering and disengagement can be detrimental to learning outcomes, making their automated detection via
video-based indicators a promising approach for real-time learner support. However, machine learning-based approaches often require sharing sensitive data, raising
privacy concerns.
Federated learning offers a
privacy-preserving alternative by enabling decentralized model training while also distributing computational load. We propose a framework exploiting cross-device
federated learning to address different manifestations of behavioral and cognitive disengagement during remote learning, specifically behavioral disengagement, mind wandering, and boredom. We fit
video-based cognitive disengagement detection models using facial expressions and gaze features. By adopting
federated learning, we safeguard users' data
privacy through
privacy-by-design and introduce a novel solution with the potential for real-time learner support. We further address challenges posed by eyeglasses by incorporating related features, enhancing overall model performance. To validate the performance of our approach, we conduct extensive experiments on five
datasets and
benchmark multiple
federated learning
algorithms. Our results show great promise for
privacy-preserving educational technologies promoting learner engagement.
Read the full abstract ▾
All authors Anna Bodonhelyi, Mengdi Wang, Efe Bozkir, Babette Bühler, Enkelejda Kasneci
Machine Learning · Cross-listed from cs.GT
Routing, Cascades, and User Choice for LLMs
Rafid Mahmood
To mitigate the trade-offs between performance and costs, LLM providers route user tasks to different models based on task difficulty and latency. We study the effect of LLM routing with respect to user behavior. We propose a game between an LLM provider with two models (standard and
reasoning) and a user who can re-
prompt or abandon tasks if the routed model cannot solve them. The user's goal is to maximize their utility minus the delay from using the model, while the provider minimizes the cost of servicing the user. We solve this Stackelberg game by fully characterizing the user best response and simplifying the provider problem. We observe that in nearly all cases, the optimal routing policy involves a static policy with no cascading that depends on the expected utility of the models to the user. Furthermore, we reveal a misalignment gap between the provider-optimal and user-preferred routes when the user's and provider's rankings of the models with respect to utility and cost differ. Finally, we demonstrate conditions for extreme misalignment where providers are incentivized to throttle the latency of the models to minimize their costs, consequently depressing user utility. The results yield simple threshold rules for single-provider, single-user interactions and clarify when routing, cascading, and throttling help or harm.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Stemphonic: All-at-once Flexible Multi-stem Music Generation
Shih-Lun Wu, Ge Zhu, Juan-Pablo Caceres et al. (+2 more)
Music stem generation, the task of producing musically-synchronized and isolated instrument audio clips, offers the potential of greater user control and better
alignment with musician workflows compared to conventional text-to-music models. Existing stem generation approaches, however, either rely on fixed architectures that output a predefined set of stems in parallel, or generate only one stem at a time, resulting in slow inference despite flexibility in stem combination. We propose Stemphonic, a
diffusion-/flow-based framework that overcomes this trade-off and generates a variable set of synchronized stems in one inference pass. During training, we treat each stem as a batch element, group synchronized stems in a batch, and apply a shared noise latent to each group. At inference-time, we use a shared initial noise latent and stem-specific text inputs to generate synchronized multi-stem outputs in one pass. We further expand our approach to enable one-pass conditional multi-stem generation and stem-wise activity controls to empower users to iteratively generate and orchestrate the temporal layering of a mix. We
benchmark our results on multiple open-source stem evaluation sets and show that Stemphonic produces higher-quality outputs while accelerating the full mix generation process by 25 to 50%. Demos at: https://stemphonic-demo.vercel.app.
Read the full abstract ▾
All authors Shih-Lun Wu, Ge Zhu, Juan-Pablo Caceres, Cheng-Zhi Anna Huang, Nicholas J. Bryan
Machine Learning
Statistical benchmarking of transformer models in low signal-to-noise time-series forecasting
Cyril Garcia and Guillaume Remy
We study the performance of
transformer architectures for multivariate time-series
forecasting in low-data regimes consisting of only a few years of daily observations. Using synthetically generated processes with known temporal and cross-sectional dependency structures and varying signal-to-noise ratios, we conduct bootstrapped experiments that enable direct evaluation via out-of-sample correlations with the optimal ground-truth predictor. We show that two-way
attention transformers, which alternate between temporal and cross-sectional self-
attention, can outperform standard baselines-Lasso, boosting methods, and fully connected multilayer perceptrons-across a wide range of settings, including low signal-to-noise regimes. We further introduce a dynamic sparsification procedure for
attention matrices applied during training, and demonstrate that it becomes significantly effective in noisy environments, where the correlation between the target variable and the optimal predictor is on the order of a few percent. Analysis of the learned
attention patterns reveals interpretable structure and suggests connections to sparsity-inducing regularization in classical regression, providing insight into why these models generalize effectively under noise.
Read the full abstract ▾
Machine Learning
Differentiable Tripartite Modularity for Clustering Heterogeneous Graphs
Benoît Hurpeau
Clustering heterogeneous relational data remains a central challenge in graph learning, particularly when interactions involve more than two types of entities. While differentiable modularity objectives such as DMoN have enabled end-to-end community detection on homogeneous and bipartite graphs, extending these approaches to higher-order relational structures remains non-trivial. In this work, we introduce a differentiable formulation of tripartite modularity for graphs composed of three node types connected through mediated interactions. Community structure is defined in terms of weighted co-paths across the tripartite graph, together with an exact factorized computation that avoids the explicit construction of dense third-order tensors. A structural normalization at pivot nodes is introduced to control extreme degree heterogeneity and ensure stable optimization. The resulting objective can be optimized jointly with a graph neural network in an end-to-end manner, while retaining linear complexity in the number of edges. We validate the proposed framework on large-scale urban cadastral data, where it exhibits robust convergence behavior and produces spatially coherent partitions. These results highlight differentiable tripartite modularity as a generic methodological building block for unsupervised clustering of heterogeneous graphs.
Read the full abstract ▾
Machine Learning
CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization
Beicheng Xu, Keyao Ding, Wei Liu et al. (+2 more)
Feature Engineering (FE) is pivotal in automated machine learning (AutoML) but remains a bottleneck for traditional methods, which operate within rigid search spaces and lack domain awareness. While Large
Language Models (LLMs) offer a promising alternative to generate unbounded operators with semantic
reasoning, existing methods focus on isolated subtasks such as feature generation, falling short of free-form FE pipelines. Moreover, they are rarely coupled with hyperparameter optimization (HPO) of the downstream ML model, leading to greedy "FE-then-HPO" workflows that cannot capture strong FE-HPO interactions. In this paper, we present CoFEH, a collaborative framework that interleaves LLM-based FE and
Bayesian HPO for robust end-to-end AutoML. CoFEH uses an LLM-driven FE optimizer powered by Tree of Thought (TOT) to explore flexible FE pipelines, a
Bayesian optimization (BO) module to solve HPO, and a dynamic optimizer selector that adaptively interleaves FE and HPO steps. Crucially, we introduce a mutual conditioning mechanism that shares context between LLM and BO, enabling mutually informed decisions. Experiments show that CoFEH outperforms both traditional and LLM-based baselines in both standalone FE and joint FE+HPO settings.
Read the full abstract ▾
All authors Beicheng Xu, Keyao Ding, Wei Liu, Yupeng Lu, Bin Cui
Machine Learning · Cross-listed from eess.SP
Robust Processing and Learning: Principles, Methods, and Wireless Applications
Shixiong Wang, Wei Dai, Li-Chun Wang et al. (+1 more)
This tutorial-style overview article examines the fundamental principles and methods of robustness, using wireless sensing and communication (WSC) as the narrative and exemplifying framework. First, we formalize the conceptual and mathematical foundations of robustness, highlighting the interpretations and relations across robust statistics, optimization, and machine learning. Key techniques, such as robust estimation and testing, distributionally robust optimization, and regularized and adversary training, are investigated. Together, the costs of robustness in system design, for example, the compromised nominal performances and the extra computational burdens, are discussed. Second, we review recent robust signal processing solutions for WSC that address model mismatch, data scarcity,
adversarial perturbation, and distributional shift. Specific applications include robust ranging-based localization, modality sensing, channel estimation, receive combining, waveform design, and
federated learning. Through this effort, we aim to introduce the classical developments and recent advances in robustness theory to the general signal processing community, exemplifying how robust statistical, optimization, and machine learning approaches can address the uncertainties inherent in WSC systems.
Read the full abstract ▾
All authors Shixiong Wang, Wei Dai, Li-Chun Wang, Geoffrey Ye Li
Machine Learning · Cross-listed from stat.ML
Stabilized Maximum-Likelihood Iterative Quantum Amplitude Estimation for Structural CVaR under Correlated Random Fields
Alireza Tabarraei
Conditional Value-at-Risk (CVaR) is a central tail-risk measure in
stochastic structural mechanics, yet its accurate evaluation under high-dimensional, spatially correlated material uncertainty remains computationally prohibitive for classical Monte Carlo methods. Leveraging bounded-expectation reformulations of CVaR compatible with
quantum amplitude estimation, we develop a
quantum-enhanced inference framework that casts CVaR evaluation as a statistically consistent, confidence-constrained maximum-likelihood amplitude estimation problem. The proposed method extends iterative
quantum amplitude estimation (IQAE) by
embedding explicit maximum-likelihood inference within a rigorously controlled interval-tracking architecture. To ensure global correctness under finite-shot noise and the non-injective oscillatory response induced by Grover amplification, we introduce a stabilized inference scheme incorporating multi-hypothesis feasibility tracking, periodic low-depth disambiguation, and a bounded restart mechanism governed by an explicit failure-probability budget. This formulation preserves the quadratic oracle-complexity advantage of amplitude estimation while providing finite-sample confidence guarantees and reduced
estimator variance. The framework is demonstrated on
benchmark problems with spatially correlated lognormal Young's modulus fields generated using a Nystrom low-rank Gaussian kernel model. Numerical results show that the proposed
estimator achieves substantially lower oracle complexity than classical Monte Carlo CVaR estimation at comparable confidence levels, while maintaining rigorous statistical reliability. This work establishes a practically robust and theoretically grounded
quantum-enhanced methodology for tail-risk quantification in
stochastic continuum mechanics.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
Fabian Schaipp, Robert M. Gower and Adrien Taylor
We present a theoretical analysis of
stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify a key quantity that, for each method, describes how the performance degrades as the step size becomes too large. For convex problems, we show that this quantity directly impacts the suboptimality bound of the method. Most importantly, our analysis provides direct theoretical evidence that adaptive step-size methods, such as SPS or NGN, are more robust than SGD. This allows us to quantify the advantage of these adaptive methods beyond empirical evaluation. Finally, we show through experiments that our theoretical bound qualitatively mirrors the actual performance as a function of the step size, even for non-convex problems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NI
Hybrid Responsible AI-Stochastic Approach for SLA Compliance in Multivendor 6G Networks
Emanuel Figetakis and Ahmed Refaey Hussein
The convergence of AI and 6G network automation introduces new challenges in maintaining transparency,
fairness, and accountability across multivendor management systems. Although closed-loop AI orchestration improves adaptability and self-optimization, it also creates a responsibility gap, where violations of SLAs cannot be causally attributed to specific
agents or vendors. This paper presents a hybrid responsible AI-
stochastic learning framework that embeds
fairness, robustness, and auditability directly into the network control loop. The framework integrates RAI games with
stochastic optimization, enabling dynamic
adversarial reweighting and probabilistic exploration across heterogeneous vendor domains. An RAAP continuously records AI-driven decision trajectories and produces dual accountability reports: user-level SLA summaries and operator-level responsibility analytics. Experimental evaluations on synthetic two-class multigroup
datasets demonstrate that the proposed hybrid model improves the accuracy of the worst group by up to 10.5%. Specifically, hybrid RAI achieved a WGAcc of 60.5% and an AvgAcc of 72.7%, outperforming traditional RAI-GA (50.0%) and ERM (21.5%). The audit mechanism successfully traced 99% simulated SLA violations to the AI entities responsible, producing both vendor and
agent-level accountability indices. These results confirm that the proposed hybrid approach enhances
fairness and robustness as well as establishes a concrete accountability framework for autonomous SLA assurance in multivendor 6G networks.
Read the full abstract ▾
Machine Learning
PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation
Xuhang Wu, Zhuoxuan Liang, Wei Li et al. (+2 more)
With the rapid advancement of IoT and edge computing, sensor networks have become indispensable, driving the need for large-scale sensor deployment. However, the high deployment cost hinders their scalability. To tackle the issues, Spatial Interpolation (SI) introduces virtual sensors to infer readings from observed sensors, leveraging graph structure. However, current graph-based SI methods rely on pre-trained models, lack adaptation to larger and unseen graphs at test-time, and overlook test data utilization. To address these issues, we propose PlugSI, a plug-and-play framework that refines test-time graph through two key innovations. First, we design an Unknown
Topology Adapter (UTA) that adapts to the new graph structure of each small-batch at test-time, enhancing the generalization of SI pre-trained models. Second, we introduce a Temporal Balance Adapter (TBA) that maintains a stable historical consensus to guide UTA adaptation and prevent drifting caused by noise in the current batch. Empirically, extensive experiments demonstrate PlugSI can be seamlessly integrated into existing graph-based SI methods and provide significant improvement (e.g., a 10.81% reduction in MAE).
Read the full abstract ▾
All authors Xuhang Wu, Zhuoxuan Liang, Wei Li, Xiaohua Jia, Sumi Helal
Machine Learning
A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer
Azkaa Nasir, Fatima Dossa, Muhammad Ahmed Atif et al. (+1 more)
Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also fail under substantial domain shift. This paper presents a controlled empirical study examining how architectural differences between Double Deep Q-Networks (DDQN) and Dueling DQN influence transfer behavior across environments. Using CartPole as a source task and LunarLander as a structurally distinct target task, we evaluate a fixed layer-wise representation transfer protocol under identical hyperparameters and training conditions, with baseline
agents trained from scratch used to contextualize transfer effects. Empirical results show that DDQN consistently avoids negative transfer under the examined setup and maintains learning dynamics comparable to baseline performance in the target environment. In contrast, Dueling DQN consistently exhibits negative transfer under identical conditions, characterized by degraded rewards and unstable optimization behavior. Statistical analysis across multiple random seeds confirms a significant performance gap under transfer. These findings suggest that architectural inductive bias is strongly associated with robustness to cross-environment transfer in value-based deep reinforcement learning under the examined transfer protocol.
Read the full abstract ▾
All authors Azkaa Nasir, Fatima Dossa, Muhammad Ahmed Atif, Mohammad Shahid Shaikh
Machine Learning · Cross-listed from cs.CL
Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs
Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya et al. (+1 more)
As
reasoning LLMs increasingly trade
tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those
tokens buy useful
reasoning, recovery from hard instances, or unnecessary verbosity. We introduce a trace-optional evaluation protocol that exactly decomposes
token efficiency using three observables available even for closed models: completion rate, conditional correctness given completion, and generated length. When instance-level workload metadata is available, we further normalize generated length by declared task-implied work and separate mean verbalization overhead from workload-dependent scaling. When such metadata is absent, we define an auditable solver-derived workload scale and evaluate its stability under leave-self-out, leave-top-k, and held-out-reference-pool perturbations. We evaluate 14 shared open-weight models on CogniLoad, GSM8K, ProofWriter, and ZebraLogic. We further evaluate 11 additional models on CogniLoad, enabling a fine-grained analysis of
reasoning-task difficulty factors: task length, intrinsic difficulty, and distractor density. Efficiency and overhead rankings remain stable across all
benchmark pairs, more robustly than accuracy rankings, while the decomposition separates logic-limited, context-limited (truncation-driven), and verbosity-limited failure modes that look identical under accuracy-per-
token. We release an evaluation artifact and reporting template, which elaborates on why an LLM is inefficient at
reasoning.
Read the full abstract ▾
All authors Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya, Benjamin Ricaud
Machine Learning
Fully-automated sleep staging: multicenter validation of a generalizable deep neural network for Parkinson's disease and isolated REM sleep behavior disorder
Jesper Strøm, Casper Skjærbæk, Natasha Becker Bertelsen et al. (+11 more)
Isolated REM sleep behavior disorder (iRBD) is a key prodromal marker of Parkinson's disease (PD), and
video-polysomnography (vPSG) remains the diagnostic gold standard. However, manual sleep staging is particularly challenging in neurodegenerative diseases due to
EEG abnormalities and fragmented sleep, making PSG assessments a bottleneck for deploying new RBD screening technologies at scale. We adapted U-Sleep, a deep neural network, for generalizable sleep staging in PD and iRBD. A pretrained U-Sleep model, based on a large, multisite non-neurodegenerative
dataset (PUB; 19,236 PSGs across 12 sites), was fine-tuned on research
datasets from two centers (Lundbeck Foundation Parkinson's Disease Research Center (PACE) and the Cologne-Bonn Cohort (CBC); 112 PD, 138 iRBD, 89 age-matched controls. The resulting model was evaluated on an independent
dataset from the Danish Center for Sleep Medicine (DCSM; 81 PD, 36 iRBD, 87 sleep-clinic controls). A subset of PSGs with low agreement between the human rater and the model (Cohen's $\kappa$ < 0.6) was re-scored by a second blinded human rater to identify sources of disagreement. Finally, we applied confidence-based thresholds to optimize REM sleep staging. The pretrained model achieved mean $\kappa$ = 0.81 in PUB, but $\kappa$ = 0.66 when applied directly to PACE/CBC. By fine-tuning the model, we developed a generalized model with $\kappa$ = 0.74 on PACE/CBC (p < 0.001 vs. the pretrained model). In DCSM, mean and median $\kappa$ increased from 0.60 to 0.64 (p < 0.001) and 0.64 to 0.69 (p < 0.001), respectively. In the interrater study, PSGs with low agreement between the model and the initial scorer showed similarly low agreement between human scorers. Applying a confidence threshold increased the proportion of correctly identified REM sleep epochs from 85% to 95.5%, while preserving sufficient (> 5 min) REM sleep for 95% of subjects.
Read the full abstract ▾
All authors Jesper Strøm, Casper Skjærbæk, Natasha Becker Bertelsen, Steffen Torpe Simonsen, Niels Okkels, David Bertram, Sinah Röttgen, Konstantin Kufer, Kaare B. Mikkelsen, Marit Otto, Poul Jørgen Jennum, Per Borghammer, Michael Sommerauer, Preben Kidmose
Machine Learning · Cross-listed from math.DS
Toeplitz Based Spectral Methods for Data-driven Dynamical Systems
Vladimir R. Kostic, Karim Lounici and Massimiliano Pontil
We introduce a Toeplitz-based framework for data-driven spectral estimation of linear
evolution operators in dynamical systems. Focusing on transfer and Koopman operators from
equilibrium trajectories without access to the underlying equations of motion, our method applies Toeplitz filters to the infinitesimal generator to extract
eigenvalues, eigenfunctions, and spectral measures. Structural prior knowledge, such as self-adjointness or skew-
symmetry, can be incorporated by design. The approach is statistically consistent and computationally efficient, leveraging both primal and dual
algorithms commonly used in statistical learning. Numerical experiments on deterministic and chaotic systems demonstrate that the framework can recover spectral properties beyond the reach of standard data-driven methods.
Read the full abstract ▾
Machine Learning
When Less is More: The LLM Scaling Paradox in Context Compression
Ruishan Guo, Yibing Liu, Guoxin Ma et al. (+6 more)
Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabilities. However, under lossy context compression in a compressor–decoder setup, we find a \textbf{Size-Fidelity Paradox}: increasing compressor size can lessen the faithfulness of reconstructed contexts though reconstruction error decreases. Across 27 compressor setups spanning model families, scales, and compression rates, we coin this paradox arising from two dominant factors: 1) knowledge overwriting: larger models increasingly replace source facts with their own prior beliefs, e.g., “the white strawberry“ $\to$ “the red strawberry“; and 2) semantic drift: larger models tend to paraphrase or restructure content instead of reproducing it verbatim, e.g., “Alice hit Bob“ $\to$ “Bob hit Alice“. Interestingly, this paradox persists across varied settings, with mid-sized compressors often outperforming larger ones in faithful recovery. By analyzing the compressed
memory via
embedding geometry and reconstruction determinacy, we further reveal that compressors tend to organize
memory across broader semantic subspaces, yielding more ambiguous representations prone to overwriting, drift, and weakened recovery. These findings complement existing evaluations of context compression and expose a breakdown of scaling laws when the objective shifts from plausible generation to faithful preservation.
Read the full abstract ▾
All authors Ruishan Guo, Yibing Liu, Guoxin Ma, Yan Wang, Yueyang Zhang, Long Xia, Kecheng Chen, Zhiyuan Sun, Daiting Shi
Machine Learning
Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path
Andres Saurez, Neha Sengar and Dongsoo Har
Circuit discovery and activation steering in
transformers have developed as separate research threads, yet both operate on the same representational space. Are they two views of the same underlying structure? We show they follow a single
geometric principle: answer
tokens, processed in isolation, encode the directions that would produce them. This
Circuit Fingerprint hypothesis enables
circuit discovery without gradients or causal intervention – recovering comparable structure to gradient-based methods through
geometric alignment alone. We validate this on standard
benchmarks (IOI, SVA, MCQA) across four model families, achieving
circuit discovery performance comparable to gradient-based methods. The same directions that identify
circuit components also enable controlled steering – achieving 69.8%
emotion classification accuracy versus 53.1% for instruction prompting while preserving factual accuracy. Beyond method development, this read-write duality reveals that
transformer circuits are fundamentally
geometric structures: interpretability and controllability are two facets of the same object.
Read the full abstract ▾
Machine Learning
Why Linear Interpretability Works: Invariant Subspaces as a Result of Architectural Constraints
Andres Saurez, Yousung Lee and Dongsoo Har
Linear probes and sparse autoencoders consistently recover meaningful structure from
transformer representations – yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity but a consequence of architectural necessity:
transformers communicate information through linear interfaces (
attention OV
circuits, unembedding
matrices), and any semantic feature decoded through such an interface must occupy a context-invariant linear subspace. We formalize this as the Invariant Subspace Necessity
theorem and derive the Self-Reference Property:
tokens directly provide the
geometric direction for their associated features, enabling zero-shot identification of semantic structure without labeled data or learned probes. Empirical validation in eight classification tasks and four model families confirms the
alignment between class
tokens and semantically related instances. Our framework provides a principled architectural explanation for why linear interpretability methods work, unifying linear probes and sparse autoencoders.
Read the full abstract ▾
Machine Learning
Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective
Kun Chen, Peng Shi, Fanfan Liu et al. (+4 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the
reasoning capabilities of Large
Language Models (LLMs). However, continuous training often leads to policy
entropy collapse, characterized by a rapid decay in
entropy that results in premature overconfidence, reduced output diversity, and vanishing gradient norms that inhibit learning. Gradient-Preserving Clipping is a primary factor influencing these dynamics, but existing mitigation strategies are largely static and lack a framework connecting clipping mechanisms to precise
entropy control. This paper proposes reshaping
entropy control in RL from the perspective of Gradient-Preserving Clipping. We first theoretically and empirically verify the contributions of specific importance sampling ratio regions to
entropy growth and reduction. Leveraging these findings, we introduce a novel regulation mechanism using dynamic clipping thresholds to precisely manage
entropy. Furthermore, we design and evaluate dynamic
entropy control strategies, including increase-then-decrease, decrease-increase-decrease, and oscillatory decay. Experimental results demonstrate that these strategies effectively mitigate
entropy collapse and achieve superior performance across multiple
benchmarks.
Read the full abstract ▾
All authors Kun Chen, Peng Shi, Fanfan Liu, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao
Machine Learning
Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis
Surjo Dey and Pallabi Saikia
This study investigates the explainability of generative
diffusion models in the context of medical imaging, focusing on
Magnetic resonance imaging (MRI) synthesis. Although
diffusion models have shown strong performance in generating realistic medical images, their internal decision making process remains largely opaque. We present a faithfulness-based explainability framework that analyzes how prototype-based explainability methods like ProtoPNet (PPNet), Enhanced ProtoPNet (EPPNet), and ProtoPool can link the relationship between generated and training features. Our study focuses on understanding the
reasoning behind image formation through denoising trajectory of
diffusion model and subsequently prototype explainability with faithfulness analysis. Experimental analysis shows that EPPNet achieves the highest faithfulness (with score 0.1534), offering more reliable insights, and explainability into the generative process. The results highlight that
diffusion models can be made more transparent and trustworthy through faithfulness-based explanations, contributing to safer and more interpretable applications of generative AI in healthcare.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Self-Supervised Learning as Discrete Communication
Kawtar Zaher, Ilyass Moummad, Olivier Buisson et al. (+1 more)
Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work, we frame visual self-supervised learning as a discrete communication process between a teacher and a student network, where semantic information is transmitted through a fixed-capacity binary channel. Rather than aligning continuous features, the student predicts multi-label binary messages produced by the teacher. Discrete agreement is enforced through an element-wise binary cross-
entropy objective, while a coding-rate regularization term encourages effective utilization of the constrained channel, promoting structured representations. We further show that periodically reinitializing the projection head strengthens this effect by encouraging
embeddings that remain predictive across multiple discrete encodings. Extensive experiments demonstrate consistent improvements over continuous agreement baselines on image classification,
retrieval, and dense visual prediction tasks, as well as under domain shift through self-supervised adaptation. Beyond backbone representations, we analyze the learned binary codes and show that they form a compact and informative discrete
language, capturing semantic factors reusable across classes.
Read the full abstract ▾
All authors Kawtar Zaher, Ilyass Moummad, Olivier Buisson, Alexis Joly
Machine Learning
Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
Matteo Pannacci, Andrea Fanti, Elena Umili et al. (+1 more)
In this work we address the problem of training a Reinforcement Learning
agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on
vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms the only other previous method for multi-task learning that does not assume knowledge of the true symbol grounding.
Read the full abstract ▾
All authors Matteo Pannacci, Andrea Fanti, Elena Umili, Roberto Capobianco
Machine Learning
Towards Poisoning Robustness Certification for Natural Language Generation
Mihnea Ghitu and Matthew Wicker
Understanding the reliability of natural
language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide provable robustness bounds for classification tasks, they are fundamentally ill-equipped for autoregressive generation: they cannot handle sequential predictions or the exponentially large output space of
language models. To establish a framework for certified natural
language generation, we formalize two security properties: stability (robustness to any change in generation) and validity (robustness to targeted, harmful changes in generation). We introduce Targeted Partition Aggregation (TPA), the first
algorithm to certify validity/targeted attacks by computing the minimum poisoning budget needed to induce a specific harmful class,
token, or phrase. Further, we extend TPA to provide tighter guarantees for multi-turn generations using mixed integer linear programming (MILP). Empirically, we demonstrate TPA's effectiveness across diverse settings including: certifying validity of
agent tool-calling when adversaries modify up to 0.5% of the
dataset and certifying 8-
token stability horizons in preference-based
alignment. Though inference-time latency remains an open challenge, our contributions enable certified deployment of
language models in security-critical applications.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Linear Model Extraction via Factual and Counterfactual Queries
Daan Otto, Jannis Kurtz, Dick den Hertog et al. (+1 more)
In model extraction attacks, the goal is to reveal the parameters of a black-box machine learning model by querying the model for a selected set of data points. Due to an increasing demand for explanations, this may involve counterfactual queries besides the typically considered factual queries. In this work, we consider linear models and three types of queries: factual, counterfactual, and robust counterfactual. First, for an arbitrary set of queries, we derive novel mathematical formulations for the classification regions for which the decision of the unknown model is known, without recovering any of the model parameters. Second, we derive bounds on the number of queries needed to extract the model's parameters for (robust) counterfactual queries under arbitrary norm-based distances. We show that the full model can be recovered using just a single counterfactual query when differentiable distance measures are employed. In contrast, when using polyhedral distances for instance, the number of required queries grows linearly with the dimension of the data space. For robust counterfactuals, the latter number of queries doubles. Consequently, the applied distance function and robustness of counterfactuals have a significant impact on the model's security.
Read the full abstract ▾
All authors Daan Otto, Jannis Kurtz, Dick den Hertog, Ilker Birbil
Machine Learning · Cross-listed from cs.CV
Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings
Laura Paul, Holger Rauhut, Martin Burger et al. (+2 more)
Recent advances in imaging technologies, deep learning and numerical performance have enabled non-invasive detailed analysis of artworks, supporting their documentation and conservation. In particular, automated detection of craquelure in digitized paintings is crucial for assessing degradation and guiding restoration, yet remains challenging due to the possibly complex scenery and the visual similarity between cracks and crack-like artistic features such as brush strokes or hair. We propose a hybrid approach that models crack detection as an inverse problem, decomposing an observed image into a crack-free painting and a crack component. A deep generative model is employed as powerful prior for the underlying artwork, while crack structures are captured using a Mumford–Shah-type variational functional together with a crack prior. Joint optimization yields a pixel-level map of crack localizations in the painting.
Read the full abstract ▾
All authors Laura Paul, Holger Rauhut, Martin Burger, Samira Kabri, Tim Roith
Machine Learning
ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm
Hanyong Wang and Menglong Yang
Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most successful deep reinforcement-learning
algorithm, the Proximal Policy Optimization
algorithm (PPO) clips the policy gradient within a conservative on-policy updates, which ensures reliable and stable policy improvement. However, this training pattern may sacrifice sample efficiency. On the other hand, off-policy methods make more adequate use of data through sample reuse, though at the cost of increased the estimation variance and bias. To leverage the advantages of both, in this paper, we propose a new PPO variant based on the stability guarantee from conservative on-policy iteration with a more efficient off-policy data utilization. Specifically, we first derive an extended off-policy improvement from an expectation form of generalized policy improvement lower bound. Then, we extend the clipping mechanism with segmented exponential functions for a suitable surrogate objective function. Third, the trajectories generated by the past $M$ policies are organized in the replay buffer for off-policy training. We refer to this method as Extended Off-policy Proximal Policy Optimization (ExO-PPO). Compared with PPO and some other state-of-the-art variants, we demonstrate an improved performance of ExO-PPO with balanced sample efficiency and stability on varied tasks in the empirical experiments.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Efficient Remote KV Cache Reuse with GPU-native Video Codec
Liang Mi, Weijun Wang, Jinghan Chen et al. (+3 more)
Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While it excels in high-speed networks, its performance degrades significantly in bandwidth-limited scenarios. Recent studies address this by transmitting KV caches in compressed form, but the associated heavyweight decompression counteracts the KV reuse benefits. In this paper, we propose an efficient and widely deployable remote KV cache reuse solution that leverages GPU-native
video codecs. Our system, KVCodec, enables effective KV cache coding with two techniques. The codec-friendly tensor layout compresses the KV cache in a highly compact
video format, enabling fast transmission. The efficient KV fetcher orchestrates the transmission, decoding, and restoration of compressed KV caches in an efficient pipelined manner, eliminating resource contention, masking network fluctuations, and achieving minimum time-to-first-
token (TTFT). We prototype KVCodec on diverse GPUs from high- to low-end. Experiments reveal that it reduces TTFT by up to 3.51 times while maintaining lossless accuracy, compared to SOTA methods.
Read the full abstract ▾
All authors Liang Mi, Weijun Wang, Jinghan Chen, Ting Cao, Haipeng Dai, Yunxin Liu
Machine Learning · Cross-listed from stat.ML
Continual Learning for non-stationary regression via Memory-Efficient Replay
Pablo García-Santaclara, Bruno Fernández-Castro, RebecaP.Díaz-Redondo et al. (+1 more)
Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by continual learning (CL), which allows systems to gradually acquire knowledge without incurring the prohibitive costs of retraining them from scratch. Most research on continual learning focuses on classification problems, while very few studies address regression tasks. We propose the first prototype-based generative replay framework designed for online task-free continual regression. Our approach defines an adaptive output-space discretization model, enabling prototype-based generative replay for continual regression without storing raw data. Evidence obtained from several
benchmark datasets shows that our framework reduces forgetting and provides more stable performance than other state-of-the-art solutions.
Read the full abstract ▾
All authors Pablo García-Santaclara, Bruno Fernández-Castro, RebecaP.Díaz-Redondo, Martín Alonso-Gamarra
Machine Learning · Cross-listed from quant-ph
SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator
Jialiang Tang, Jialin Zhang and Xiaoming Sun
Quantum machine learning (QML), as an interdisciplinary field bridging
quantum computing and machine learning, has garnered significant
attention in recent years. Currently, the field as a whole faces challenges due to incomplete theoretical foundations for the expressivity of
quantum neural networks (QNNs). In this paper we propose a constructive QNN model and demonstrate that it possesses the universal approximation property (UAP), which means it can approximate any square-integrable function up to arbitrary accuracy. Furthermore, it supports switching function bases, thus adaptable to various scenarios in numerical approximation and machine learning. Our model has asymptotic advantages over the best classical feed-forward neural networks in terms of
circuit size and achieves optimal parameter complexity when approximating Sobolev functions under $L_2$ norm.
Read the full abstract ▾