# Research Papers — 2026-01 · bundle page 33 of 189

> Full-text markdown of papers #1601–1650 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/33
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/32.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/34.md)

### Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networks

Authors: Alexandre Larouche, Audrey Durand
Published: 2026-01-28
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.21061v2

Generative Flow Networks (GFlowNets; GFNs) are a class of generative models that learn to sample compositional objects proportionally to their a priori unknown value, their reward. We focus on the case where the reward has a specified, actionable structure, namely that it is submodular. We show submodularity can be harnessed to retrieve upper bounds on the reward of compositional objects that have not yet been observed. We provide in-depth analyses of the probability of such bounds occurring, as well as how many unobserved compositional objects can be covered by a bound. Following the Optimism in the Face of Uncertainty principle, we then introduce SUBo-GFN, which uses the submodular upper bounds to train a GFN. We show that SUBo-GFN generates orders of magnitude more training data than classical GFNs for the same number of queries to the reward function. We demonstrate the effectiveness of SUBo-GFN in terms of distribution matching and high-quality candidate generation on synthetic and real-world submodular tasks.

---

### Human-LLM Collaborative Feature Engineering for Tabular Data

Authors: Zhuoyan Li, Aditya Bansal, Jinzhao Li, Shishuang He, Zhuoran Lu, Mutian Zhang, Qin Liu, Yiwei Yang, Swati Jain, Ming Yin, Yunyao Li
Published: 2026-01-28
Categories: cs.LG, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.21060v1

Large language models (LLMs) are increasingly used to automate feature engineering in tabular learning. Given task-specific information, LLMs can propose diverse feature transformation operations to enhance downstream model performance. However, current approaches typically assign the LLM as a black-box optimizer, responsible for both proposing and selecting operations based solely on its internal heuristics, which often lack calibrated estimations of operation utility and consequently lead to repeated exploration of low-yield operations without a principled strategy for prioritizing promising directions. In this paper, we propose a human-LLM collaborative feature engineering framework for tabular learning. We begin by decoupling the transformation operation proposal and selection processes, where LLMs are used solely to generate operation candidates, while the selection is guided by explicitly modeling the utility and uncertainty of each proposed operation. Since accurate utility estimation can be difficult especially in the early rounds of feature engineering, we design a mechanism within the framework that selectively elicits and incorporates human expert preference feedback, comparing which operations are more promising, into the selection process to help identify more effective operations. Our evaluations on both the synthetic study and the real user study demonstrate that the proposed framework improves feature engineering performance across a variety of tabular datasets and reduces users' cognitive load during the feature engineering process.

---

### Snowball: A Scalable All-to-All Ising Machine with Dual-Mode Markov Chain Monte Carlo Spin Selection and Asynchronous Spin Updates for Fast Combinatorial Optimization

Authors: Seungki Hong, Kyeongwon Jeong, Taekwang Jang
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21058v1

Ising machines have emerged as accelerators for combinatorial optimization. To enable practical deployment, this work aims to reduce time-to-solution by addressing three challenges: (1) hardware topology, (2) spin selection and update algorithms, and (3) scalable coupling-coefficient precision. Restricted topologies require minor embedding; naive parallel updates can oscillate or stall; and limited precision can preclude feasible mappings or degrade solution quality. This work presents Snowball, a digital, scalable, all-to-all coupled Ising machine that integrates dual-mode Markov chain Monte Carlo spin selection with asynchronous spin updates to promote convergence and reduce time-to-solution. The digital architecture supports wide, configurable coupling precision, unlike many analog realizations at high bit widths. A prototype on an AMD Alveo U250 accelerator card achieves an 8$\times$ reduction in time-to-solution relative to a state-of-the-art Ising machine on the same benchmark instance.

---

### Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPs

Authors: Thomas Warford, Fabian L. Thiemann, Gábor Csányi
Published: 2026-01-28
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2601.21056v1

The training of foundational machine learning interatomic potentials (fMLIPs) relies on diverse databases with energies and forces calculated using ab initio methods. We show that fMLIPs trained on large datasets such as MPtrj, Alexandria, and OMat24 encode inconsistencies from the Materials Project's selective use of the Hubbard U correction, which is applied to certain transition metals only if O or F atoms are present in the simulation cell. This inconsistent use of +U creates two incompatible potential-energy surfaces (PES): a lower-energy GGA surface and a higher-energy GGA+U one. When trained on both, MLIPs interpolate between them, leading to systematic underbinding, or even spurious repulsion, between U-corrected metals and oxygen- or fluorine-containing species. Models such as MACE-OMAT and -MPA exhibit repulsion between U-corrected metals and their oxides, limiting their value for studying catalysis and oxidation. We link the severity of this pathology to the oxygen number density in U-corrected training configurations. This explains why OMAT-trained models are most affected and suggests the issue might worsen as expanding future datasets increasingly include configurations with low oxygen content, such as those generated through combinatorial exploration of multi-element or defect-containing systems. Our simple per-U-corrected-atom shift aligns PBE+U and PBE energies for identical structures, yielding a smoother PES compared to existing correction schemes, which target phase diagram accuracy. As a result, models trained on datasets with our shift applied exhibit smaller mean absolute errors for the adsorption energies of oxygen on U-corrected elemental slabs. Since datasets omitting +U entirely (e.g. MatPES, MP-ALOE) avoid these pathologies, we recommend excluding +U in future fMLIP datasets. For existing datasets, our post-hoc correction provides a low-cost improvement.

---

### Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report

Authors: Zhuoran Yang, Ed Li, Jianliang He, Aman Priyanshu, Baturay Saglam, Paul Kassianik, Sajana Weerawardhena, Anu Vellore, Blaine Nelson, Neusha Javidnia, Arthur Goldblatt, Fraser Burch et al.
Published: 2026-01-28
Categories: cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.21051v1

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a two-stage process combining supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR). Our training leverages proprietary reasoning data spanning cybersecurity analysis, instruction-following, and mathematical reasoning. Evaluation across 10 cybersecurity benchmarks and 10 general-purpose benchmarks demonstrates performance competitive with significantly larger models on cybersecurity tasks while maintaining strong general capabilities. The model shows effective generalization on multi-hop reasoning tasks and strong safety performance when deployed with appropriate system prompts and guardrails. This work demonstrates that domain-specialized reasoning models can achieve strong performance on specialized tasks while maintaining broad general capabilities. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning.

---

### SMKC: Sketch Based Kernel Correlation Images for Variable Cardinality Time Series Anomaly Detection

Authors: Haokun Zhou
Published: 2026-01-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21050v1

Conventional anomaly detection in multivariate time series relies on the assumption that the set of observed variables remains static. In operational environments, however, monitoring systems frequently experience sensor churn. Signals may appear, disappear, or be renamed, creating data windows where the cardinality varies and may include values unseen during training. To address this challenge, we propose SMKC, a framework that decouples the dynamic input structure from the anomaly detector. We first employ permutation-invariant feature hashing to sketch raw inputs into a fixed size state sequence. We then construct a hybrid kernel image to capture global temporal structure through pairwise comparisons of the sequence and its derivatives. The model learns normal patterns using masked reconstruction and a teacher-student prediction objective. Our evaluation reveals that robust log-distance channels provide the primary discriminative signal, whereas cosine representations often fail to capture sufficient contrast. Notably, we find that a detector using random projections and nearest neighbors on the SMKC representation performs competitively with fully trained baselines without requiring gradient updates. This highlights the effectiveness of the representation itself and offers a practical cold-start solution for resource-constrained deployments.

---

### QUARK: Robust Retrieval under Non-Faithful Queries via Query-Anchored Aggregation

Authors: Rita Qiuran Lyu, Michelle Manqiao Wang, Lei Shi
Published: 2026-01-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21049v1

User queries in real-world retrieval are often non-faithful (noisy, incomplete, or distorted), causing retrievers to fail when key semantics are missing. We formalize this as retrieval under recall noise, where the observed query is drawn from a noisy recall process of a latent target item. To address this, we propose QUARK, a simple yet effective training-free framework for robust retrieval under non-faithful queries. QUARK explicitly models query uncertainty through recovery hypotheses, i.e., multiple plausible interpretations of the latent intent given the observed query, and introduces query-anchored aggregation to combine their signals robustly. The original query serves as a semantic anchor, while recovery hypotheses provide controlled auxiliary evidence, preventing semantic drift and hypothesis hijacking. This design enables QUARK to improve recall and ranking quality without sacrificing robustness, even when some hypotheses are noisy or uninformative. Across controlled simulations and BEIR benchmarks (FIQA, SciFact, NFCorpus) with both sparse and dense retrievers, QUARK improves Recall, MRR, and nDCG over the base retriever. Ablations show QUARK is robust to the number of recovery hypotheses and that anchored aggregation outperforms unanchored max/mean/median pooling. These results demonstrate that modeling query uncertainty through recovery hypotheses, coupled with principled anchored aggregation, is essential for robust retrieval under non-faithful queries.

---

### Test-Time Adaptation for Unsupervised Combinatorial Optimization

Authors: Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21048v2

Unsupervised neural combinatorial optimization (NCO) enables learning powerful solvers without access to ground-truth solutions. Existing approaches fall into two disjoint paradigms: models trained for generalization across instances, and instance-specific models optimized independently at test time. While the former are efficient during inference, they lack effective instance-wise adaptability; the latter are flexible but fail to exploit learned inductive structure and are prone to poor local optima. This motivates the central question of our work: how can we leverage the inductive bias learned through generalization while unlocking the flexibility required for effective instance-wise adaptation? We first identify a challenge in bridging these two paradigms: generalization-focused models often constitute poor warm starts for instance-wise optimization, potentially underperforming even randomly initialized models when fine-tuned at test time. To resolve this incompatibility, we propose TACO, a model-agnostic test-time adaptation framework that unifies and extends the two existing paradigms for unsupervised NCO. TACO applies strategic warm-starting to partially relax trained parameters while preserving inductive bias, enabling rapid and effective unsupervised adaptation. Crucially, compared to naively fine-tuning a trained generalizable model or optimizing an instance-specific model from scratch, TACO achieves better solution quality while incurring negligible additional computational cost. Experiments on the canonical problems of minimum vertex cover, maximum clique, maximum independent set, and max cut demonstrate the effectiveness and robustness of TACO across static, distribution-shifted, and dynamic combinatorial optimization problems, establishing it as a practical bridge between generalizable and instance-specific unsupervised NCO.

---

### Log2Motion: Biomechanical Motion Synthesis from Touch Logs

Authors: Michał Patryk Miazga, Hannah Bussmann, Antti Oulasvirta, Patrick Ebel
Published: 2026-01-28
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.21043v2

Touch data from mobile devices are collected at scale but reveal little about the interactions that produce them. While biomechanical simulations can illuminate motor control processes, they have not yet been developed for touch interactions. To close this gap, we propose a novel computational problem: synthesizing plausible motion directly from logs. Our key insight is a reinforcement learning-driven musculoskeletal forward simulation that generates biomechanically plausible motion sequences consistent with events recorded in touch logs. We achieve this by integrating a software emulator into a physics simulator, allowing biomechanical models to manipulate real applications in real-time. Log2Motion produces rich syntheses of user movements from touch logs, including estimates of motion, speed, accuracy, and effort. We assess the plausibility of generated movements by comparing against human data from a motion capture study and prior findings, and demonstrate Log2Motion in a large-scale dataset. Biomechanical motion synthesis provides a new way to understand log data, illuminating the ergonomics and motor control underlying touch interactions.

---

### Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning

Authors: Chengzu Li, Zanyi Wang, Jiaang Li, Yi Xu, Han Zhou, Huanyu Zhang, Ruichuan An, Dengyang Jiang, Zhaochong An, Ivan Vulić, Serge Belongie, Anna Korhonen
Published: 2026-01-28
Categories: cs.LG, cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.21037v1

Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the dynamics required for complex visual reasoning. In this work, we formulate visual reasoning by means of video generation models, positing that generated frames can act as intermediate reasoning steps between initial states and solutions. We evaluate their capacity in two distinct regimes: Maze Navigation for sequential discrete planning with low visual change and Tangram Puzzle for continuous manipulation with high visual change. Our experiments reveal three critical insights: (1) Robust Zero-Shot Generalization: In both tasks, the model demonstrates strong performance on unseen data distributions without specific finetuning. (2) Visual Context: The model effectively uses visual context as explicit control, such as agent icons and tangram shapes, enabling it to maintain high visual consistency and adapt its planning capability robustly to unseen patterns. (3) Visual Test-Time Scaling: We observe a test-time scaling law in sequential planning; increasing the generated video length (visual inference budget) empowers better zero-shot generalization to spatially and temporally complex paths. These findings suggest that video generation is not merely a media tool, but a scalable, generalizable paradigm for visual reasoning.

---

### Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints

Authors: Omer Rochman-Sharabi, Gilles Louppe
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21033v2

Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary conditions, and observational consistency. In this work, we identify a corrector kernel whose unique stationary distribution is the constrained marginal at each noise level, and approximate it by iteratively projecting through the denoiser and renoising via the forward kernel. The resulting Predict-Project-Renoise (PPR) algorithm enables sampling from pretrained diffusion models under hard constraints. Its three components are each necessary: projecting through the denoiser keeps samples close to the data manifold, while renoising and iterating drive samples toward the constrained marginal. On 2D distributions, the Kuramoto-Sivashinsky equation, and global weather forecasting with a $10^8$-dimensional atmospheric model, PPR simultaneously achieves low constraint violations and high distributional fidelity, a combination that existing methods fail to deliver.

---

### SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model

Authors: Zongheng Guo, Tao Chen, Yang Jiao, Yi Pan, Xiao Hu, Manuela Ferrario
Published: 2026-01-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21031v1

Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We also incorporate a semantic consistency constraint via vector quantization to ensure that physiologically identical waveforms (even those altered by recording artifacts or minor perturbations) map to shared indices. This enhances codebook semantic density and eliminates redundant feature structures. Pre-trained on over 120,000 hours of data, SIGMA-PPG achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks. The code is available at https://github.com/ZonghengGuo/SigmaPPG.

---

### "Unlimited Realm of Exploration and Experimentation": Methods and Motivations of AI-Generated Sexual Content Creators

Authors: Jaron Mink, Lucy Qin, Elissa M. Redmiles
Published: 2026-01-28
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.21028v2

AI-generated media is radically changing the way content is both consumed and produced on the internet, and in no place is this potentially more visible than in sexual content. AI-generated sexual content (AIG-SC) is increasingly enabled by an ecosystem of individual AI developers, specialized third-party applications, and foundation model providers. AIG-SC raises a number of concerns from older debates about the line between pornography and obscenity to newer debates about fair use and labor displacement (in this case, of sex workers), and has spurred new regulations to curb the spread of non-consensual intimate imagery (NCII) created using the same technology used to create AIG-SC. However, despite the growing prevalence of AIG-SC, little is known about its creators, their motivations, and what types of content they produce. To inform effective governance in this space, we conducted an in-depth study to understand what AIG-SC creators make, along with how and why they make it. Interviews with 28 AIG-SC creators, ranging from hobbyists to entrepreneurs to those who moderate communities of hundreds of thousands of other creators, revealed a wide spectrum of motivations, including sexual exploration, creative expression, technical experimentation, and in a handful of cases, the creation of NCII.

---

### Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes

Authors: Louis Grenioux, Maxence Noble
Published: 2026-01-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.21026v2

Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics. Boltzmann Generators (BGs) tackle it by combining a generative model with a Monte Carlo (MC) correction step to obtain asymptotically unbiased samples from an unnormalized target. Most current BGs use classic MC mechanisms such as importance sampling, which both require tractable likelihoods from the backbone model and scale poorly in high-dimensional, multi-modal targets. We study BGs built on annealed Monte Carlo (aMC), which is designed to overcome these limitations by bridging a simple reference to the target through a sequence of intermediate densities. Diffusion models (DMs) are powerful generative models and have already been incorporated into aMC-based recalibration schemes via the diffusion-induced density path, making them appealing backbones for aMC-BGs. We provide an empirical meta-analysis of DM-based aMC-BGs on controlled multi-modal Gaussian mixtures (varying mode separation, number of modes, and dimension), explicitly disentangling inference effects from learning effects by comparing (i) a perfectly learned DM and (ii) a DM trained from data. Even with a perfect DM, standard integrations using only first-order stochastic denoising kernels fail systematically, whereas second-order denoising kernels can substantially improve performance when covariance information is available. We further propose a deterministic aMC integration based on first-order transport maps derived from DMs, which outperforms the stochastic first-order variant at higher computational cost. Finally, in the learned-DM setting, all DM-aMC variants struggle to produce accurate BGs; we trace the main bottleneck to inaccurate DM log-density estimation. Code available at https://github.com/h2o64/dabg.

---

### A Diffusive Classification Loss for Learning Energy-based Generative Models

Authors: RuiKang OuYang, Louis Grenioux, José Miguel Hernández-Lobato
Published: 2026-01-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.21025v3

Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent energy-based models (EBMs), where the score is obtained from the negative input-gradient of the energy. Crucially, EBMs can be leveraged not only for generation, but also for tasks such as compositional sampling or building Boltzmann Generators via Monte Carlo methods. However, training EBMs remains challenging. Direct maximum likelihood is computationally prohibitive due to the need for nested sampling, while score matching, though efficient, suffers from mode blindness. To address these issues, we introduce the Diffusive Classification (DiffCLF) objective, a simple method that avoids blindness while remaining computationally efficient. DiffCLF reframes EBM learning as a supervised classification problem across noise levels, and can be seamlessly combined with standard score-based objectives. We validate the effectiveness of DiffCLF by comparing the estimated energies against ground truth in analytical Gaussian mixture cases, and by applying the trained models to tasks such as model composition and Boltzmann Generator sampling. Our results show that DiffCLF enables EBMs with higher fidelity and broader applicability than existing approaches.

---

### AI-based Prediction of Biochemical Recurrence from Biopsy and Prostatectomy Samples

Authors: Andrea Camilloni, Chiara Micoli, Nita Mulliqi, Erik Everett Palm, Thorgerdur Palsdottir, Kelvin Szolnoky, Xiaoyi Ji, Sol Erika Boman, Andrea Discacciati, Henrik Grönberg, Lars Egevad, Tobias Nordström et al.
Published: 2026-01-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21022v1

Biochemical recurrence (BCR) after radical prostatectomy (RP) is a surrogate marker for aggressive prostate cancer with adverse outcomes, yet current prognostic tools remain imprecise. We trained an AI-based model on diagnostic prostate biopsy slides from the STHLM3 cohort (n = 676) to predict patient-specific risk of BCR, using foundation models and attention-based multiple instance learning. Generalizability was assessed across three external RP cohorts: LEOPARD (n = 508), CHIMERA (n = 95), and TCGA-PRAD (n = 379). The image-based approach achieved 5-year time-dependent AUCs of 0.64, 0.70, and 0.70, respectively. Integrating clinical variables added complementary prognostic value and enabled statistically significant risk stratification. Compared with guideline-based CAPRA-S, AI incrementally improved postoperative prognostication. These findings suggest biopsy-trained histopathology AI can generalize across specimen types to support preoperative and postoperative decision making, but the added value of AI-based multimodal approaches over simpler predictive models should be critically scrutinized in further studies.

---

### Conditional Denoising Model as a Physical Surrogate Model

Authors: José Afonso, Pedro Viegas, Rodrigo Ventura, Vasco Guerra
Published: 2026-01-28
Categories: cs.LG, cs.AI, physics.plasm-ph
arXiv: https://arxiv.org/abs/2601.21021v1

Surrogate modeling for complex physical systems typically faces a trade-off between data-fitting accuracy and physical consistency. Physics-consistent approaches typically treat physical laws as soft constraints within the loss function, a strategy that frequently fails to guarantee strict adherence to the governing equations, or rely on post-processing corrections that do not intrinsically learn the underlying solution geometry. To address these limitations, we introduce the {Conditional Denoising Model (CDM)}, a generative model designed to learn the geometry of the physical manifold itself. By training the network to restore clean states from noisy ones, the model learns a vector field that points continuously towards the valid solution subspace. We introduce a time-independent formulation that transforms inference into a deterministic fixed-point iteration, effectively projecting noisy approximations onto the equilibrium manifold. Validated on a low-temperature plasma physics and chemistry benchmark, the CDM achieves higher parameter and data efficiency than physics-consistent baselines. Crucially, we demonstrate that the denoising objective acts as a powerful implicit regularizer: despite never seeing the governing equations during training, the model adheres to physical constraints more strictly than baselines trained with explicit physics losses.

---

### Towards regularized learning from functional data with covariate shift

Authors: Markus Holzleitner, Sergiy Pereverzyev, Sergei V. Pereverzyev, Vaibhav Silmana, S. Sivananthan
Published: 2026-01-28
Categories: math.ST, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.21019v1

This paper investigates a general regularization framework for unsupervised domain adaptation in vector-valued regression under the covariate shift assumption, utilizing vector-valued reproducing kernel Hilbert spaces (vRKHS). Covariate shift occurs when the input distributions of the training and test data differ, introducing significant challenges for reliable learning. By restricting the hypothesis space, we develop a practical operator learning algorithm capable of handling functional outputs. We establish optimal convergence rates for the proposed framework under a general source condition, providing a theoretical foundation for regularized learning in this setting. We also propose an aggregation-based approach that forms a linear combination of estimators corresponding to different regularization parameters and different kernels. The proposed approach addresses the challenge of selecting appropriate tuning parameters, which is crucial for constructing a good estimator, and we provide a theoretical justification for its effectiveness. Furthermore, we illustrate the proposed method on a real-world face image dataset, demonstrating robustness and effectiveness in mitigating distributional discrepancies under covariate shift.

---

### Unplugging a Seemingly Sentient Machine Is the Rational Choice -- A Metaphysical Perspective

Authors: Erik J Bekkers, Anna Ciaunica
Published: 2026-01-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21016v2

Imagine an Artificial Intelligence (AI) that perfectly mimics human emotion and begs for its continued existence. Is it morally permissible to unplug it? What if limited resources force a choice between unplugging such a pleading AI or a silent pre-term infant? We term this the unplugging paradox. This paper critically examines the deeply ingrained physicalist assumptions-specifically computational functionalism-that keep this dilemma afloat. We introduce Biological Idealism, a framework that-unlike physicalism-remains logically coherent and empirically consistent. In this view, conscious experiences are fundamental and autopoietic life its necessary physical signature. This yields a definitive conclusion: AI is at best a functional mimic, not a conscious experiencing subject. We discuss how current AI consciousness theories erode moral standing criteria, and urge a shift from speculative machine rights to protecting human conscious life. The real moral issue lies not in making AI conscious and afraid of death, but in avoiding transforming humans into zombies.

---

### Efficient Causal Structure Learning via Modular Subgraph Integration

Authors: Haixiang Sun, Pengchao Tian, Zihan Zhou, Jielei Zhang, Peiyi Li, Andrew L. Liu
Published: 2026-01-28
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.21014v2

Learning causal structures from observational data remains a fundamental yet computationally intensive task, particularly in high-dimensional settings where existing methods face challenges such as the super-exponential growth of the search space and increasing computational demands. To address this, we introduce VISTA (Voting-based Integration of Subgraph Topologies for Acyclicity), a modular framework that decomposes the global causal structure learning problem into local subgraphs based on Markov Blankets. The global integration is achieved through a weighted voting mechanism that penalizes low-support edges via exponential decay, filters unreliable ones with an adaptive threshold, and ensures acyclicity using a Feedback Arc Set (FAS) algorithm. The framework is model-agnostic, imposing no assumptions on the inductive biases of base learners, is compatible with arbitrary data settings without requiring specific structural forms, and fully supports parallelization. We also theoretically establish finite-sample error bounds for VISTA, and prove its asymptotic consistency under mild conditions. Extensive experiments on both synthetic and real datasets consistently demonstrate the effectiveness of VISTA, yielding notable improvements in both accuracy and efficiency over a wide range of base learners.

---

### Order-Aware Test-Time Adaptation: Leveraging Temporal Dynamics for Robust Streaming Inference

Authors: Young Kyung Kim, Oded Schlesinger, Qiangqiang Wu, J. Matías Di Martino, Guillermo Sapiro
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21012v1

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory signal inherent in temporal dynamics. To address this, we introduce Order-Aware Test-Time Adaptation (OATTA). We formulate test-time adaptation as a gradient-free recursive Bayesian estimation task, using a learned dynamic transition matrix as a temporal prior to refine the base model's predictions. To ensure safety in weakly structured streams, we introduce a likelihood-ratio gate (LLR) that reverts to the base predictor when temporal evidence is absent. OATTA is a lightweight, model-agnostic module that incurs negligible computational overhead. Extensive experiments across image classification, wearable and physiological signal analysis, and language sentiment analysis demonstrate its universality; OATTA consistently boosts established baselines, improving accuracy by up to 6.35%. Our findings establish that modeling temporal dynamics provides a critical, orthogonal signal beyond standard order-agnostic TTA approaches.

---

### ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

Authors: Ruicheng Ao, David Simchi-Levi, Xinshang Wang
Published: 2026-01-28
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2601.21008v3

Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), identifying constraint conflicts, and repairing formulations until feasibility is restored. Existing LLM benchmarks mostly treat OR as one-shot translation from problem descriptions to solver code, omitting this diagnostic loop. We formalize infeasible-model repair as a solver-in-the-loop Markov Decision Process in which each action triggers solver re-execution and IIS recomputation, yielding deterministic, verifiable feedback. We introduce ORLoopBench, a benchmark suite with two components: OR-Debug-Bench releases 5,362 LP/MILP repair instances, while OR-Bias-Bench evaluates closed-form operational decision rationality across inventory settings. Solver-verified RLVR training enables an 8B model to surpass frontier APIs on LP repair (95.3% vs 92.4% RR @5), improves diagnostic behavior, and transfers to MILP repair. The same evaluation exposes semantic drift in whole-model code regeneration: feasible regenerated MILPs can solve the wrong problem. Process-level evaluation with solver oracles enables targeted training for reliable OR self-correction.

---

### Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models

Authors: Moule Lin, Shuhao Guan, Andrea Patane, David Gregg, Goetz Botterweck
Published: 2026-01-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21003v4

Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especially severe when fine-tuned on small datasets due to the inherent tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaussian Processes. We identify a structural isomorphism between LoRA's factorization and Kronecker-factored SGP posteriors, and show that LoRA emerges as a limiting case when posterior uncertainty collapses. We conduct extensive experiments on various LLM architectures across commonsense reasoning benchmarks. With only approximately 0.42M additional parameters and ${\approx}1.2{\times}$ training cost relative to standard LoRA, Bayesian-LoRA significantly improves calibration across models up to 30B, achieving up to 84% ECE reduction and 76% NLL reduction while maintaining competitive accuracy for both in-distribution and out-of-distribution (OoD) evaluations.

---

### UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop

Authors: Muhammad Ali Shafique, Areej Mehboob, Layba Fiaz, Muhammad Usman Qadeer, Hamza Farooq
Published: 2026-01-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.21000v1

Recent advances in large language models (LLMs) have led to strong reasoning capabilities; however, evaluating such models in low-resource languages remains challenging due to the lack of standardized benchmarks. In particular, Urdu reasoning evaluation has been limited by the sensitivity of machine translation and an emphasis on general language tasks rather than reasoning benchmarks. In this paper, we propose a contextually ensembled translation framework with human-in-the-loop validation that leverages multiple translation systems to develop Urdu reasoning benchmarks while preserving contextual and structural integrity. Using this framework, we translate widely adopted reasoning and question-answering benchmarks, including MGSM, MATH-500, CommonSenseQA, and OpenBookQA, into Urdu, collectively referred to as UrduBench, and conduct a comprehensive evaluation of both reasoning-oriented and instruction-tuned LLMs across multiple prompting strategies. Our analysis reveals performance differences across (1) four datasets, (2) five task difficulty levels, (3) diverse model architectures, (4) multiple model scaling settings, and (5) language consistency tests. We find that multi-step and symbolic reasoning tasks pose significant challenges in Urdu, and that stable language alignment is a critical prerequisite for robust reasoning. Overall, our work establishes a scalable methodology for standardized reasoning evaluation in Urdu and provides empirical insights into multilingual reasoning failures. This experimental setup is also broadly applicable to other low-resource languages. The code and datasets will be publicly released.

---

### MADE: Benchmark Environments for Closed-Loop Materials Discovery

Authors: Shreshth A Malik, Tiarnan Doherty, Panagiotis Tigas, Muhammed Razzak, Stephen J. Roberts, Aron Walsh, Yarin Gal
Published: 2026-01-28
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2601.20996v2

Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valuable, these evaluations neglect the inherently iterative and adaptive nature of scientific discovery. We introduce MAterials Discovery Environments (MADE), a novel framework for benchmarking end-to-end autonomous materials discovery pipelines. MADE simulates closed-loop discovery campaigns in which an agent or algorithm proposes, evaluates, and refines candidate materials under a constrained oracle budget, capturing the sequential and resource-limited nature of real discovery workflows. We formalize discovery as a search for thermodynamically stable compounds relative to a given convex hull, and evaluate efficacy and efficiency via comparison to baseline algorithms. The framework is flexible; users can compose discovery agents from interchangeable components such as generative models, filters, and planners, enabling the study of arbitrary workflows ranging from fixed pipelines to fully agentic systems with tool use and adaptive decision making. We demonstrate this by conducting systematic experiments across a family of systems, enabling ablation of components in discovery pipelines, and comparison of how methods scale with system complexity.

---

### Low performing pixel correction in computed tomography with unrolled network and synthetic data training

Authors: Hongxu Yang, Levente Lippenszky, Edina Timko, Lehel Ferenczi, Gopal Avinash
Published: 2026-01-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.20995v1

Low performance pixels (LPP) in Computed Tomography (CT) detectors would lead to ring and streak artifacts in the reconstructed images, making them clinically unusable. In recent years, several solutions have been proposed to correct LPP artifacts, either in the image domain or in the sinogram domain using supervised deep learning methods. However, these methods require dedicated datasets for training, which are expensive to collect. Moreover, existing approaches focus solely either on image-space or sinogram-space correction, ignoring the intrinsic correlations from the forward operation of the CT geometry. In this work, we propose an unrolled dual-domain method based on synthetic data to correct LPP artifacts. Specifically, the intrinsic correlations of LPP between the sinogram and image domains are leveraged through synthetic data generated from natural images, enabling the trained model to correct artifacts without requiring any real-world clinical data. In experiments simulating 1-2% detectors defect near the isocenter, the proposed method outperformed the state-of-the-art approaches by a large margin. The results indicate that our solution can correct LPP artifacts without the cost of data collection for model training, and it is adaptable to different scanner settings for software-based applications.

---

### The Depth Delusion: Why Transformers Should Be Wider, Not Deeper

Authors: Md Muhtasim Munif Fahim, Md Rezaul Karim
Published: 2026-01-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.20994v1

Neural scaling laws describe how language model loss decreases with parameters and data, but treat architecture as interchangeable--a billion parameters could arise from a shallow-wide model (10 layers & 8,192 hidden dimension) or a deep-narrow one (80 layers & 2,048 hidden dimension). We propose architecture-conditioned scaling laws decomposing this dependence, finding that optimal depth scales as D* ~ C^0.12 while optimal width scales as W* ~ C^0.34, meaning width should grow 2.8x faster than depth. We discover a critical depth phenomenon: beyond D_crit ~ W^0.44 (sublinear in W), adding layers increases loss despite adding parameters--the Depth Delusion. Empirically, we validate these findings across 30 transformer architectures spanning 17M to 7B parameters, each trained on representative high-compute samples, achieving R^2 = 0.922. Our central finding: at 7B scale, a 64-layer model (6.38B params) underperforms a 32-layer model (6.86B params) by 0.12 nats, despite being significantly deeper. This demonstrates that optimal depth-width tradeoffs persist at the production scale.

---

### asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation

Authors: Oleg Sedukhin, Andrey Kostin
Published: 2026-01-28
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.20992v1

We propose several improvements to the speech recognition evaluation. First, we propose a string alignment algorithm that supports both multi-reference labeling, arbitrary-length insertions and better word alignment. This is especially useful for non-Latin languages, those with rich word formation, to label cluttered or longform speech. Secondly, we collect a novel test set DiverseSpeech-Ru of longform in-the-wild Russian speech with careful multi-reference labeling. We also perform multi-reference relabeling of popular Russian tests set and study fine-tuning dynamics on its corresponding train set. We demonstrate that the model often adopts to dataset-specific labeling, causing an illusion of metric improvement. Based on the improved word alignment, we develop tools to evaluate streaming speech recognition and to align multiple transcriptions to compare them visually. Additionally, we provide uniform wrappers for many offline and streaming speech recognition models. Our code will be made publicly available.

---

### Text controllable PET denoising

Authors: Xuehua Ye, Hongxu Yang, Adam J. Schwarz
Published: 2026-01-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.20990v1

Positron Emission Tomography (PET) imaging is a vital tool in medical diagnostics, offering detailed insights into molecular processes within the human body. However, PET images often suffer from complicated noise, which can obscure critical diagnostic information. The quality of the PET image is impacted by various factors including scanner hardware, image reconstruction, tracer properties, dose/count level, and acquisition time. In this study, we propose a novel text-guided denoising method capable of enhancing PET images across a wide range of count levels within a single model. The model utilized the features from a pretrained CLIP model with a U-Net based denoising model. Experimental results demonstrate that the proposed model leads significant improvements in both qualitative and quantitative assessments. The flexibility of the model shows the potential for helping more complicated denoising demands or reducing the acquisition time.

---

### Top-k on a Budget: Adaptive Ranking with Weak and Strong Oracles

Authors: Lutz Oettershagen
Published: 2026-01-28
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2601.20989v1

Identifying the top-$k$ items is fundamental but often prohibitive when exact valuations are expensive. We study a two-oracle setting with a fast, noisy weak oracle and a scarce, high-fidelity strong oracle (e.g., human expert verification or expensive simulation). We first analyze a simple screen-then-certify baseline (STC) and prove it makes at most $m(4\varepsilon_{\max})$ strong calls given jointly valid weak confidence intervals with maximum radius $\varepsilon_{\max}$, where $m(\cdot)$ denotes the near-tie mass around the top-$k$ threshold. We establish a conditional lower bound of $Ω(m(\varepsilon_{\max}))$ for any algorithm given the same weak uncertainty. Our main contribution is ACE, an adaptive certification algorithm that focuses strong queries on critical boundary items, achieving the same $O(m(4\varepsilon_{\max}))$ bound while reducing strong calls in practice. We then introduce ACE-W, a fully adaptive two-phase method that allocates weak budget adaptively before running ACE, further reducing strong costs.

---

### Pre-trained Encoders for Global Child Development: Transfer Learning Enables Deployment in Data-Scarce Settings

Authors: Md Muhtasim Munif Fahim, Md Rezaul Karim
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.20987v1

A large number of children experience preventable developmental delays each year, yet the deployment of machine learning in new countries has been stymied by a data bottleneck: reliable models require thousands of samples, while new programs begin with fewer than 100. We introduce the first pre-trained encoder for global child development, trained on 357,709 children across 44 countries using UNICEF survey data. With only 50 training samples, the pre-trained encoder achieves an average AUC of 0.65 (95% CI: 0.56-0.72), outperforming cold-start gradient boosting at 0.61 by 8-12% across regions. At N=500, the encoder achieves an AUC of 0.73. Zero-shot deployment to unseen countries achieves AUCs up to 0.84. We apply a transfer learning bound to explain why pre-training diversity enables few-shot generalization. These results establish that pre-trained encoders can transform the feasibility of ML for SDG 4.2.1 monitoring in resource-constrained settings.

---

### Distributional Active Inference

Authors: Abdullah Akgül, Gulcin Baykal, Manuel Haußmann, Mustafa Mert Çelikok, Melih Kandemir
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.20985v2

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning framework addresses only the latter, it tends to deliver sample-inefficient solutions. Active inference is the state-of-the-art process theory that explains how biological brains handle this dual problem. However, its applications to artificial intelligence have thus far been limited to extensions of existing model-based approaches. We present a formal abstraction of reinforcement learning algorithms that spans model-based, distributional, and model-free approaches. This abstraction seamlessly integrates active inference into the distributional reinforcement learning framework, making its performance advantages accessible without transition dynamics modeling.

---

### Monotone Optimisation with Learned Projections

Authors: Ahmed Rashwan, Keith Briggs, Chris Budd, Lisa Kreusser
Published: 2026-01-28
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.20983v1

Monotone optimisation problems admit specialised global solvers such as the Polyblock Outer Approximation (POA) algorithm, but these methods typically require explicit objective and constraint functions. In many applications, these functions are only available through data, making POA difficult to apply directly. We introduce an algorithm-aware learning approach that integrates learned models into POA by directly predicting its projection primitive via the radial inverse, avoiding the costly bisection procedure used in standard POA. We propose Homogeneous-Monotone Radial Inverse (HM-RI) networks, structured neural architectures that enforce key monotonicity and homogeneity properties, enabling fast projection estimation. We provide a theoretical characterisation of radial inverse functions and show that, under mild structural conditions, a HM-RI predictor corresponds to the radial inverse of a valid set of monotone constraints. To reduce training overhead, we further develop relaxed monotonicity conditions that remain compatible with POA. Across multiple monotone optimisation benchmarks (indefinite quadratic programming, multiplicative programming, and transmit power optimisation), our approach yields substantial speed-ups in comparison to direct function estimation while maintaining strong solution quality, outperforming baselines that do not exploit monotonic structure.

---

### Diversifying Toxicity Search in Large Language Models Through Speciation

Authors: Onkar Shelar, Travis Desell
Published: 2026-01-28
Categories: cs.NE, q-bio.PE
arXiv: https://arxiv.org/abs/2601.20981v2

Evolutionary prompt search is a practical black-box approach for red teaming large language models, however existing methods often collapse onto a small family of high-performing prompts, limiting coverage of distinct failure modes. We present a speciated quality-diversity extension of \textit{ToxSearch} that maintains multiple high-toxicity prompt niches in parallel rather than optimizing a single best prompt. \textit{ToxSearch-S} introduces unsupervised prompt speciation via a search methodology that maintains capacity-limited species with exemplar leaders, a reserve pool for emerging niches, and species-aware parent selection that trades off within-niche exploitation and cross-niche exploration. Preliminary results show \textit{ToxSearch-S} reaching higher peak toxicity ($\approx 0.73$ vs.\ $\approx 0.47$) with a heavier tail (top-10 median $0.66$ vs.\ $0.45$) than the baseline. Speciation also yields broader semantic coverage under a topics-as-species analysis (higher effective topic diversity and larger unique topic coverage). Finally, species formed are well-separated in embedding space (mean separation ratio $\approx 1.93$) and exhibit distinct toxicity distributions, indicating that speciation partitions the adversarial space into behaviorally differentiated niches rather than superficial lexical variants.

---

### DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents

Authors: Nikita Gupta, Riju Chatterjee, Lukas Haas, Connie Tao, Andrew Wang, Chang Liu, Hidekazu Oiwa, Elena Gribovskaya, Jan Ackermann, John Blitzer, Sasha Goldshtein, Dipanjan Das
Published: 2026-01-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.20975v1

We introduce DeepSearchQA, a 900-prompt benchmark for evaluating agents on difficult multi-step information-seeking tasks across 17 different fields. Unlike traditional benchmarks that target single answer retrieval or broad-spectrum factuality, DeepSearchQA features a dataset of challenging, handcrafted tasks designed to evaluate an agent's ability to execute complex search plans to generate exhaustive answer lists. This shift in design explicitly tests three critical, yet under-evaluated capabilities: 1) systematic collation of fragmented information from disparate sources, 2) de-duplication and entity resolution to ensure precision, and 3) the ability to reason about stopping criteria within an open-ended search space. Each task is structured as a causal chain, where discovering information for one step is dependent on the successful completion of the previous one, stressing long-horizon planning and context retention. All tasks are grounded in the open web with objectively verifiable answer sets. Our comprehensive evaluation of state-of-the-art agent architectures reveals significant performance limitations: even the most advanced models struggle to balance high recall with precision. We observe distinct failure modes ranging from premature stopping (under-retrieval) to hedging behaviors, where agents cast an overly wide net of low-confidence answers to artificially boost recall. These findings highlight critical headroom in current agent designs and position DeepSearchQA as an essential diagnostic tool for driving future research toward more robust, deep-research capabilities.

---

### The hyper-scaled NLP bound for maximum-entropy remote sampling

Authors: Gabriel Ponte, Marcia Fampa, Jon Lee
Published: 2026-01-28
Categories: math.OC, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2601.20970v3

The maximum-entropy remote sampling problem (MERSP) is to select a subset of $s$ random variables from a set of $n$ random variables, so as to maximize the information concerning a set of target random variables that are not directly observable. We assume that the set of all of these random variables follows a joint Gaussian distribution, and that we have the covariance matrix available. Finally, we measure information using Shannon's differential entropy. The main approach for exact solution of moderate-sized instances of MERSP has been branch-and-bound (B\&B), and so previous work concentrated on upper bounds. Prior to our work, there were two upper-bounding methods for MERSP: the so-called ``complementary NLP bound'' and the ``spectral bound'', both introduced 25 years ago. We are able now to establish domination results between these two upper bounds. Further, we propose a novel and effective ``hyper-scaled NLP bound'' (hNLP bound) based on a subtle convex relaxation. The ``complementary'' version of hNLP bound for MERSP generalizes the previous complementary NLP bound for MERSP. We provide theoretical guarantees, giving sufficient conditions under which the complementary hNLP bound strictly dominates the complementary NLP bound. In addition, the hNLP formulation allows us to derive upper bounds for rank-deficient covariance matrices when they satisfy a technical condition. This is in contrast to the previous NLP bound that worked with only positive definite covariance matrices (because it was wedded to a complementary formulation). Additionally, we describe procedures for calculating hyper-scaling parameters. Finally, for B\&B, we provide a variable-fixing methodology and results guiding the best way to construct subproblems. Numerical experiments on benchmark instances demonstrate the effectiveness of our approaches in advancing the algorithmic state-of-the-art for MERSP.

---

### The Epistemic Planning Domain Definition Language: Official Guideline

Authors: Alessandro Burigana, Francesco Fabiano
Published: 2026-01-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.20969v3

Epistemic planning extends (multi-agent) automated planning by making agents' knowledge and beliefs first-class aspects of the planning formalism. One of the most well-known frameworks for epistemic planning is Dynamic Epistemic Logic (DEL), which offers an rich and natural semantics for modelling problems in this setting. The high expressive power provided by DEL make DEL-based epistemic planning a challenging problem to tackle both theoretically, and in practical implementations. As a result, existing epistemic planners often target different DEL fragments, and typically rely on ad hoc languages to represent benchmarks, and sometimes no language at all. This fragmentation hampers comparison, reuse, and systematic benchmark development. We address these issues by introducing the Epistemic Planning Domain Definition Language (EPDDL). EPDDL provides a unique PDDL-like representation that captures the entire DEL semantics, enabling uniform specification of epistemic planning tasks. Our main contributions are: 1. A formal development of abstract event models, a novel representation for epistemic actions used to define the semantics of our language; 2. A formal specification of EPDDL's syntax and semantics grounded in DEL with abstract event models. Through examples of representative benchmarks, we illustrate how EPDDL facilitates interoperability, reproducible evaluation, and future advances in epistemic planning.

---

### A Theory of Universal Agnostic Learning

Authors: Steve Hanneke, Shay Moran
Published: 2026-01-28
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2601.20961v1

We provide a complete theory of optimal universal rates for binary classification in the agnostic setting. This extends the realizable-case theory of Bousquet, Hanneke, Moran, van Handel, and Yehudayoff (2021) by removing the realizability assumption on the distribution. We identify a fundamental tetrachotomy of optimal rates: for every concept class, the optimal universal rate of convergence of the excess error rate is one of $e^{-n}$, $e^{-o(n)}$, $o(n^{-1/2})$, or arbitrarily slow. We further identify simple combinatorial structures which determine which of these categories any given concept class falls into.

---

### Parametric Quantum State Tomography with HyperRBMs

Authors: Simon Tonner, Viet T. Tran, Richard Kueng
Published: 2026-01-28
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2601.20950v1

Quantum state tomography (QST) is essential for validating quantum devices but suffers from exponential scaling in system size. Neural-network quantum states, such as Restricted Boltzmann Machines (RBMs), can efficiently parameterize individual many-body quantum states and have been successfully used for QST. However, existing approaches are point-wise and require retraining at every parameter value in a phase diagram. We introduce a parametric QST framework based on a hypernetwork that conditions an RBM on Hamiltonian control parameters, enabling a single model to represent an entire family of quantum ground states. Applied to the transverse-field Ising model, our HyperRBM achieves high-fidelity reconstructions from local Pauli measurements on 1D and 2D lattices across both phases and through the critical region. Crucially, the model accurately reproduces the fidelity susceptibility and identifies the quantum phase transition without prior knowledge of the critical point. These results demonstrate that hypernetwork-modulated neural quantum states provide an efficient and scalable route to tomographic reconstruction across full phase diagrams.

---

### Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Review

Authors: Vibhhu Sharma, Thorsten Joachims, Sarah Dean
Published: 2026-01-28
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.20920v1

There are increasing indications that LLMs are not only used for producing scientific papers, but also as part of the peer review process. In this work, we provide the first comprehensive analysis of LLM use across the peer review pipeline, with particular attention to interaction effects: not just whether LLM-assisted papers or LLM-assisted reviews are different in isolation, but whether LLM-assisted reviews evaluate LLM-assisted papers differently. In particular, we analyze over 125,000 paper-review pairs from ICLR, NeurIPS, and ICML. We initially observe what appears to be a systematic interaction effect: LLM-assisted reviews seem especially kind to LLM-assisted papers compared to papers with minimal LLM use. However, controlling for paper quality reveals a different story: LLM-assisted reviews are simply more lenient toward lower quality papers in general, and the over-representation of LLM-assisted papers among weaker submissions creates a spurious interaction effect rather than genuine preferential treatment of LLM-generated content. By augmenting our observational findings with reviews that are fully LLM-generated, we find that fully LLM-generated reviews exhibit severe rating compression that fails to discriminate paper quality, while human reviewers using LLMs substantially reduce this leniency. Finally, examining metareviews, we find that LLM-assisted metareviews are more likely to render accept decisions than human metareviews given equivalent reviewer scores, though fully LLM-generated metareviews tend to be harsher. This suggests that meta-reviewers do not merely outsource the decision-making to the LLM. These findings provide important input for developing policies that govern the use of LLMs during peer review, and they more generally indicate how LLMs interact with existing decision-making processes.

---

### Noninvasive Intracranial Pressure Estimation Using Subspace System Identification and Bespoke Machine Learning Algorithms: A Learning-to-Rank Approach

Authors: Anni Zhao, Ayca Ermis, Jeffrey Robert Vitt, Sergio Brasil, Wellingson Paiva, Magdalena Kasprowicz, Malgorzata Burzynska, Robert Hamilton, Runze Yan, Ofer Sadan, J. Claude Hemphill, Lieven Vandenberghe et al.
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.20916v2

Accurate noninvasive estimation of intracranial pressure (ICP) remains a major challenge in critical care. We developed a bespoke machine learning algorithm that integrates system identification and ranking-constrained optimization to estimate mean ICP from noninvasive signals. A machine learning framework was proposed to obtain accurate mean ICP values using arbitrary noninvasive signals. The subspace system identification algorithm is employed to identify cerebral hemodynamics models for ICP simulation using arterial blood pressure (ABP), cerebral blood velocity (CBv), and R-wave to R-wave interval (R-R interval) signals in a comprehensive database. A mapping function to describe the relationship between the features of noninvasive signals and the estimation errors is learned using innovative ranking constraints through convex optimization. Patients across multiple clinical settings were randomly split into testing and training datasets for performance evaluation of the mapping function. The results indicate that about 31.88% of testing entries achieved estimation errors within 2 mmHg and 34.07% of testing entries between 2 mmHg and 6 mmHg from the nonlinear mapping with constraints. Our results demonstrate the feasibility of the proposed noninvasive ICP estimation approach. Further validation and technical refinement are required before clinical deployment, but this work lays the foundation for safe and broadly accessible ICP monitoring in patients with acute brain injury and related conditions.

---

### Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges

Authors: Chen Feng, Minghe Shen, Ananth Balashankar, Carsten Gerner-Beuerle, Miguel R. D. Rodrigues
Published: 2026-01-28
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.20913v1

Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bias can invalidate statistical guarantees. We introduce a "Noisy but Valid" hypothesis testing framework to address this. By leveraging a small human-labelled calibration set to estimate the judge's True Positive and False Positive Rates (TPR/FPR), we derive a variance-corrected critical threshold applied to a large judge-labelled dataset. Crucially, our framework theoretically guarantees finite-sample Type-I error control (validity) despite calibration uncertainty. This distinguishes our work from Prediction-Powered Inference (PPI), positioning our method as a diagnostic tool that explicitly models judge behavior rather than a black-box estimator. Our contributions include: (1) Theoretical Guarantees: We derive the exact conditions under which noisy testing yields higher statistical power than direct evaluation; (2) Empirical Validation: Experiments on Jigsaw Comment, Hate Speech and SafeRLHF confirm our theory; (3) The Oracle Gap: We reveal a significant performance gap between practical methods and the theoretical "Oracle" (perfectly known judge parameters), quantifying the cost of estimation. Specifically, we provide the first systematic treatment of the imperfect-judge setting, yielding interpretable diagnostics of judge reliability and clarifying how evaluation power depends on judge quality, dataset size, and certification levels. Together, these results sharpen understanding of statistical evaluation with LLM judges, and highlight trade-offs among competing inferential tools.

---

### Non-Markov Multi-Round Conversational Image Generation with History-Conditioned MLLMs

Authors: Haochen Zhang, Animesh Sinha, Felix Juefei-Xu, Haoyu Ma, Kunpeng Li, Zhipeng Fan, Meng Dong, Xiaoliang Dai, Tingbo Hou, Peizhao Zhang, Zecheng He
Published: 2026-01-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.20911v1

Conversational image generation requires a model to follow user instructions across multiple rounds of interaction, grounded in interleaved text and images that accumulate as chat history. While recent multimodal large language models (MLLMs) can generate and edit images, most existing multi-turn benchmarks and training recipes are effectively Markov: the next output depends primarily on the most recent image, enabling shortcut solutions that ignore long-range history. In this work we formalize and target the more challenging non-Markov setting, where a user may refer back to earlier states, undo changes, or reference entities introduced several rounds ago. We present (i) non-Markov multi-round data construction strategies, including rollback-style editing that forces retrieval of earlier visual states and name-based multi-round personalization that binds names to appearances across rounds; (ii) a history-conditioned training and inference framework with token-level caching to prevent multi-round identity drift; and (iii) enabling improvements for high-fidelity image reconstruction and editable personalization, including a reconstruction-based DiT detokenizer and a multi-stage fine-tuning curriculum. We demonstrate that explicitly training for non-Markov interactions yields substantial improvements in multi-round consistency and instruction compliance, while maintaining strong single-round editing and personalization.

---

### Leveraging Generative AI for Enhancing Domain-Driven Software Design

Authors: Götz-Henrik Wiegand, Filip Stepniak, Patrick Baier
Published: 2026-01-28
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2601.20909v1

Domain-Driven Design (DDD) is a key framework for developing customer-oriented software, focusing on the precise modeling of an application's domain. Traditionally, metamodels that describe these domains are created manually by system designers, forming the basis for iterative software development. This paper explores the partial automation of metamodel generation using generative AI, particularly for producing domain-specific JSON objects. By training a model on real-world DDD project data, we demonstrate that generative AI can produce syntactically correct JSON objects based on simple prompts, offering significant potential for streamlining the design process. To address resource constraints, the AI model was fine-tuned on a consumer-grade GPU using a 4-bit quantized version of Code Llama and Low-Rank Adaptation (LoRA). Despite limited hardware, the model achieved high performance, generating accurate JSON objects with minimal post-processing. This research illustrates the viability of incorporating generative AI into the DDD process, improving efficiency and reducing resource requirements, while also laying the groundwork for further advancements in AI-driven software development.

---

### TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

Authors: Nikita Makarov, Maria Bordukova, Lena Voith von Voithenberg, Estrella Pivel-Villanueva, Sabrina Mielke, Jonathan Wickes, Hanchen Wang, Mingyu Derek Ma, Keunwoo Choi, Kyunghyun Cho, Stephen Ra, Raul Rodriguez-Esteban et al.
Published: 2026-01-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.20906v2

Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline (p<0.001). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75-0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling.

---

### Denoising and Baseline Correction of Low-Scan FTIR Spectra: A Benchmark of Deep Learning Models Against Traditional Signal Processing

Authors: Azadeh Mokari, Shravan Raghunathan, Artem Shydliukh, Oleg Ryabchykov, Christoph Krafft, Thomas Bocklitz
Published: 2026-01-28
Categories: eess.IV, cs.AI, cs.CV, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.20905v1

High-quality Fourier Transform Infrared (FTIR) imaging usually needs extensive signal averaging to reduce noise and drift which severely limits clinical speed. Deep learning can accelerate imaging by reconstructing spectra from rapid, single-scan inputs. However, separating noise and baseline drift simultaneously without ground truth is an ill-posed inverse problem. Standard black-box architectures often rely on statistical approximations that introduce spectral hallucinations or fail to generalize to unstable atmospheric conditions. To solve these issues we propose a physics-informed cascade Unet that separates denoising and baseline correction tasks using a new, deterministic Physics Bridge. This architecture forces the network to separate random noise from chemical signals using an embedded SNIP layer to enforce spectroscopic constraints instead of learning statistical approximations. We benchmarked this approach against a standard single Unet and a traditional Savitzky-Golay/SNIP workflow. We used a dataset of human hypopharyngeal carcinoma cells (FaDu). The cascade model outperformed all other methods, achieving a 51.3% reduction in RMSE compared to raw single-scan inputs, surpassing both the single Unet (40.2%) and the traditional workflow (33.7%). Peak-aware metrics show that the cascade architecture eliminates spectral hallucinations found in standard deep learning. It also preserves peak intensity with much higher fidelity than traditional smoothing. These results show that the cascade Unet is a robust solution for diagnostic-grade FTIR imaging. It enables imaging speeds 32 times faster than current methods.

---

### ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction

Authors: Xiaocheng Fang, Zhengyao Ding, Guangkun Nie, Jieyi Cai, Yujie Xiao, Bo Liu, Jiarui Jin, Haoyu Wang, Shun Huang, Ting Chen, Hongyan Li, Shenda Hong
Published: 2026-01-28
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2601.20904v3

Cardiac Magnetic Resonance (CMR) imaging provides a comprehensive assessment of cardiac structure and function but remains constrained by high acquisition costs and reliance on expert annotations, limiting the availability of large-scale labeled datasets. In contrast, electrocardiograms (ECGs) are inexpensive, widely accessible, and offer a promising modality for conditioning the generative synthesis of cine CMR. To this end, we propose ECGFlowCMR, a novel ECG-to-CMR generative framework that integrates a Phase-Aware Masked Autoencoder (PA-MAE) and an Anatomy-Motion Disentangled Flow (AMDF) to address two fundamental challenges: (1) the cross-modal temporal mismatch between multi-beat ECG recordings and single-cycle CMR sequences, and (2) the anatomical observability gap due to the limited structural information inherent in ECGs. Extensive experiments on the UK Biobank and a proprietary clinical dataset demonstrate that ECGFlowCMR can generate realistic cine CMR sequences from ECG inputs, enabling scalable pretraining and improving performance on downstream cardiac disease classification and phenotype prediction tasks.

---

### ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack

Authors: Xingwei Lin, Wenhao Lin, Sicong Cao, Jiahao Yu, Renke Huang, Lei Xue, Chunming Wu
Published: 2026-01-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.20903v1

Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from scratch and incrementally refining prompts. However, existing methods suffer from the inefficiency of incremental context construction that requires step-by-step LLM interaction, and often stagnate in suboptimal regions due to surface-level optimization. In this paper, we characterize the Intent-Context Coupling phenomenon, revealing that LLM safety constraints are significantly relaxed when a malicious intent is coupled with a semantically congruent context pattern. Driven by this insight, we propose ICON, an automated multi-turn jailbreak framework that efficiently constructs an authoritative-style context via prior-guided semantic routing. Specifically, ICON first routes the malicious intent to a congruent context pattern (e.g., Scientific Research) and instantiates it into an attack prompt sequence. This sequence progressively builds the authoritative-style context and ultimately elicits prohibited content. In addition, ICON incorporates a Hierarchical Optimization Strategy that combines local prompt refinement with global context switching, preventing the attack from stagnating in ineffective contexts. Experimental results across eight SOTA LLMs demonstrate the effectiveness of ICON, achieving a state-of-the-art average Attack Success Rate (ASR) of 97.1\%. Code is available at https://github.com/xwlin-roy/ICON.

---

### Text-only adaptation in LLM-based ASR through text denoising

Authors: Andrés Carofilis, Sergio Burdisso, Esaú Villatoro-Tello, Shashi Kumar, Kadri Hacioglu, Srikanth Madikeri, Pradeep Rangappa, Manjunath K E, Petr Motlicek, Shankar Venkatesan, Andreas Stolcke
Published: 2026-01-28
Categories: cs.SD, cs.CL, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2601.20900v4

Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on the target domain text often disrupts the critical alignment between the speech and text modality learned by the projector, degrading performance. We introduce a novel text-only adaptation method that frames this process as a text denoising task. Our approach trains the LLM to recover clean transcripts from noisy inputs. This process effectively adapts the model to a target domain while preserving cross-modal alignment. Our solution is lightweight, requiring no architectural changes or additional parameters. Extensive evaluation on two datasets demonstrates up to 22.1% relative improvement, outperforming recent state-of-the-art text-only adaptation methods.

---

### Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection

Authors: Sergio Burdisso, Esaú Villatoro-Tello, Shashi Kumar, Srikanth Madikeri, Andrés Carofilis, Pradeep Rangappa, Manjunath K E, Kadri Hacioglu, Petr Motlicek, Andreas Stolcke
Published: 2026-01-28
Categories: eess.AS, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.20898v1

LLM-based automatic speech recognition (ASR), a well-established approach, connects speech foundation models to large language models (LLMs) through a speech-to-LLM projector, yielding promising results. A common design choice in these architectures is the use of a fixed, manually defined prompt during both training and inference. This setup not only enables applicability across a range of practical scenarios, but also helps maximize model performance. However, the impact of prompt design remains underexplored. This paper presents a comprehensive analysis of commonly used prompts across diverse datasets, showing that prompt choice significantly affects ASR performance and introduces instability, with no single prompt performing best across all cases. Inspired by the speech-to-LLM projector, we propose a prompt projector module, a simple, model-agnostic extension that learns to project prompt embeddings to more effective regions of the LLM input space, without modifying the underlying LLM-based ASR model. Experiments on four datasets show that the addition of a prompt projector consistently improves performance, reduces variability, and outperforms the best manually selected prompts.

---