# Research Papers — 2026-01 · bundle page 39 of 189 > Full-text markdown of papers #1901–1950 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/39 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/38.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/40.md) ### Meta-Cognitive Reinforcement Learning with Self-Doubt and Recovery Authors: Zhipeng Zhang, Xiongfei Su, Kai Li Published: 2026-01-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.20193v2 Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such methods often either overreact to noise by becoming overly conservative or fail catastrophically when uncertainty accumulates. In this work, we propose a meta-cognitive reinforcement learning framework that enables an agent to assess, regulate, and recover its learning behavior based on internally estimated reliability signals. The proposed method introduces a meta-trust variable driven by Value Prediction Error Stability (VPES), which modulates learning dynamics via fail-safe regulation and gradual trust recovery. Experiments on continuous-control benchmarks with reward corruption demonstrate that recovery-enabled meta-cognitive control achieves higher average returns and significantly reduces late-stage training failures compared to strong robustness baselines. --- ### Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling Authors: Husein Zolkepli Published: 2026-01-28 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2601.20185v2 X-Codec-2.0 has shown strong performance in neural audio compression and multilingual speech modeling, operating at a 50 Hz latent rate and a 16 kHz sampling rate using frozen HuBERT features. While effective, this configuration limits temporal efficiency and audio fidelity. In this work, we explore a simple and effective modification by introducing additional pooling and increasing the decoder hop size. This reduces the latent rate from 50 Hz to 25 Hz and simultaneously raises the output sampling rate from 16 kHz to 24 kHz, improving efficiency and perceptual quality without altering the core architecture. Evaluated on the multilingual Common Voice 17 test set, the proposed configuration achieves a 0.29 MOS improvement over the original X-Codec-2.0 baseline based on UTMOSv2, and attains the best reported performance among all codecs operating at 25 Hz. The source code, checkpoints, and generation comparisons are released at \href{https://huggingface.co/Scicom-intl/xcodec2-25TPS-24k}{https://huggingface.co/Scicom-intl/xcodec2-25TPS-24k}. --- ### On the Computational Complexity of Performative Prediction Authors: Ioannis Anagnostides, Rohan Chauhan, Ioannis Panageas, Tuomas Sandholm, Jingming Yan Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20180v1 Performative prediction captures the phenomenon where deploying a predictive model shifts the underlying data distribution. While simple retraining dynamics are known to converge linearly when the performative effects are weak ($ρ< 1$), the complexity in the regime $ρ> 1$ was hitherto open. In this paper, we establish a sharp phase transition: computing an $ε$-performatively stable point is PPAD-complete -- and thus polynomial-time equivalent to Nash equilibria in general-sum games -- even when $ρ= 1 + O(ε)$. This intractability persists even in the ostensibly simple setting with a quadratic loss function and linear distribution shifts. One of our key technical contributions is to extend this PPAD-hardness result to general convex domains, which is of broader interest in the complexity of variational inequalities. Finally, we address the special case of strategic classification, showing that computing a strategic local optimum is PLS-hard. --- ### Causal-Driven Feature Evaluation for Cross-Domain Image Classification Authors: Chen Cheng, Ang Li Published: 2026-01-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.20176v2 Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations, implicitly assuming that invariance implies reliability. However, features that are invariant across domains are not necessarily causally effective for prediction. In this work, we revisit OOD classification from a causal perspective and propose to evaluate learned representations based on their necessity and sufficiency under distribution shift. We introduce an explicit segment-level framework that directly measures causal effectiveness across domains, providing a more faithful criterion than invariance alone. Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance, particularly under challenging domain shifts, highlighting the value of causal evaluation for robust generalization. --- ### TeleStyle: Content-Preserving Style Transfer in Images and Videos Authors: Shiwen Zhang, Xiaoyan Yang, Bojia Zi, Haibin Huang, Chi Zhang, Xuelong Li Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20175v1 Content-preserving style transfer, generating stylized outputs based on content and style references, remains a significant challenge for Diffusion Transformers (DiTs) due to the inherent entanglement of content and style features in their internal representations. In this technical report, we present TeleStyle, a lightweight yet effective model for both image and video stylization. Built upon Qwen-Image-Edit, TeleStyle leverages the base model's robust capabilities in content preservation and style customization. To facilitate effective training, we curated a high-quality dataset of distinct specific styles and further synthesized triplets using thousands of diverse, in-the-wild style categories. We introduce a Curriculum Continual Learning framework to train TeleStyle on this hybrid dataset of clean (curated) and noisy (synthetic) triplets. This approach enables the model to generalize to unseen styles without compromising precise content fidelity. Additionally, we introduce a video-to-video stylization module to enhance temporal consistency and visual quality. TeleStyle achieves state-of-the-art performance across three core evaluation metrics: style similarity, content consistency, and aesthetic quality. Code and pre-trained models are available at https://github.com/Tele-AI/TeleStyle --- ### NeuraLSP: A Neural Spectral Preconditioner for Accelerating PDE Solvers Authors: Alexander Benanti, Xi Han, Hong Qin Published: 2026-01-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.20174v3 Solving large-scale sparse linear systems originating from partial differential equations (PDEs) is a fundamental topic in high-performance scientific computing, where preconditioners are crucial. Multigrid methods are among the most effective preconditioners, yet their performance is dictated by the accurate construction of grid transfer operators. Current neural multigrid methods learn such operators with graph neural networks (GNNs), typically by extracting connectivity from discretized system matrices. While effective, these graph-based constructions suffer from rank inflation, resulting in unnecessarily large coarse spaces and slower convergence. To ameliorate, this paper advocates NeuraLSP, a new neural multigrid preconditioner that replaces graph aggregation with a fixed low-rank spectral representation derived from the left singular subspace of near-nullspace components. At the network design level, NeuraLSP is trained with a novel subspace loss function, which preserves the error modes most relevant to multigrid convergence while suppressing rank inflation. This paper's grand innovation hinges upon both theoretical guarantees and empirical robustness to rank inflation, affording up to a 53% speedup over SOTA neural preconditioners across a variety of PDE families. --- ### MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis Authors: Zeyang Huang, Takanori Fujiwara, Angelos Chatzimparmpas, Wandrille Duchemin, Andreas Kerren Published: 2026-01-28 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2601.20173v3 We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervised learning approach to more efficiently encode low-dimensional manifold geometry. Central to this approach are maximum manifold capacity representations (MMCRs), which help untangle complex manifolds by compressing variances among locally similar data points while amplifying variance among dissimilar data points. This design is particularly effective for high-dimensional data with substantial intra-cluster variance and curved manifold structures, such as biological or image data. Our qualitative and quantitative evaluations demonstrate that MAPLE can produce clearer visual cluster separations and finer subcluster resolution than UMAP while maintaining tractable computational cost. --- ### Loss Landscape Geometry of Partial Differential Equation Emulators: Or, Symmetry Learning via Gradient Alignment Authors: James Amarel, Robyn Miller, Nicolas Hengartner, Benjamin Migliori, Emily Casleton, Alexei Skurikhin, Earl Lawrence, Gerd J. Kunde Published: 2026-01-28 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2601.20172v2 We study how neural emulators of partial differential equation solution operators internalize physical symmetries by introducing an influence-based diagnostic that measures the propagation of parameter updates between symmetry-related states, defined as the metric-weighted overlap of loss gradients evaluated along group orbits. This quantity probes the local geometry of the learned loss landscape and goes beyond forward-pass equivariance tests by directly assessing whether learning dynamics couple physically equivalent configurations. Applying our diagnostic to autoregressive fluid flow emulators, we show that orbit-wise gradient coherence provides the mechanism for learning to generalize over symmetry transformations and indicates when training selects a symmetry compatible basin. The result is a novel technique for evaluating if surrogate models have internalized symmetry properties of the known solution operator. --- ### Local Duality for Sparse Support Vector Machines Authors: Penghe Zhang, Naihua Xiu, Houduo Qi Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20170v1 Due to the rise of cardinality minimization in optimization, sparse support vector machines (SSVMs) have attracted much attention lately and show certain empirical advantages over convex SVMs. A common way to derive an SSVM is to add a cardinality function such as $\ell_0$-norm to the dual problem of a convex SVM. However, this process lacks theoretical justification. This paper fills the gap by developing a local duality theory for such an SSVM formulation and exploring its relationship with the hinge-loss SVM (hSVM) and the ramp-loss SVM (rSVM). In particular, we prove that the derived SSVM is exactly the dual problem of the 0/1-loss SVM, and the linear representer theorem holds for their local solutions. The local solution of SSVM also provides guidelines on selecting hyperparameters of hSVM and rSVM. {Under specific conditions, we show that a sequence of global solutions of hSVM converges to a local solution of 0/1-loss SVM. Moreover, a local minimizer of 0/1-loss SVM is a local minimizer of rSVM.} This explains why a local solution induced by SSVM outperforms hSVM and rSVM in the prior empirical study. We further conduct numerical tests on real datasets and demonstrate potential advantages of SSVM by working with locally nice solutions proposed in this paper. --- ### Efficient Token Pruning for LLaDA-V Authors: Zhewen Wan, Tianchen Song, Chen Lin, Zhiyong Zhao, Xianpeng Lang Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20168v1 Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising paradigm introduce significant computational overhead, as visual tokens are repeatedly processed across all layers and denoising steps. In this work, we conduct an in-depth attention analysis and reveal that, unlike autoregressive decoders, LLaDA-V aggregates cross-modal information predominantly in middle-to-late layers, leading to delayed semantic alignment. Motivated by this observation, we propose a structured token pruning strategy inspired by FastV, selectively removing a proportion of visual tokens at designated layers to reduce FLOPs while preserving critical semantic information. To the best of our knowledge, this is the first work to investigate structured token pruning in diffusion-based large multimodal models. Unlike FastV, which focuses on shallow-layer pruning, our method targets the middle-to-late layers of the first denoising step to align with LLaDA-V's delayed attention aggregation to maintain output quality, and the first-step pruning strategy reduces the computation across all subsequent steps. Our framework provides an empirical basis for efficient LLaDA-V inference and highlights the potential of vision-aware pruning in diffusion-based multimodal models. Across multiple benchmarks, our best configuration reduces computational cost by up to 65% while preserving an average of 95% task performance. --- ### Contextuality as an External Bookkeeping Cost under Fixed Shared-State Semantics Authors: Song-Ju Kim Published: 2026-01-28 Categories: quant-ph, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2601.20167v2 Contextuality is a central feature distinguishing quantum from classical probability theories, but its operational meaning is often stated only qualitatively. In this Letter, we study a simple information-theoretic question: how much additional contextual information must a classical simulation introduce when it tries to keep a shared internal description fixed across contexts? To make this question precise, we analyze a minimal external-label simulation model in which the remaining context dependence is carried only by an auxiliary label. For this model, we define an obstruction cost as the minimum mutual information between the context and the auxiliary label required to reproduce the observed statistics. We then prove a conservative quantitative lower bound: any linear witness that separates the observed statistics from the zero-obstruction set yields a positive lower bound on this cost. We do not claim that this bound is tight, and we do not claim that the simulation model covers every possible classical architecture. Its role is narrower and more explicit: under fixed shared-state semantics, contextuality can be read as a certificate of irreducible external bookkeeping cost in a simple and well-defined simulation model. --- ### What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering Authors: Jim Maar, Denis Paperno, Callum Stuart McDougall, Neel Nanda Published: 2026-01-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.20164v2 Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the next token in preparation to a predicted future token, such as a likely rhyming word, as supported by a prior qualitative study of Claude 3.5 Haiku using a cross-layer transcoder. We propose much simpler techniques for assessing implicit planning in language models. With case studies on rhyme poetry generation and question answering, we demonstrate that our methodology easily scales to many models. Across models, we find that the generated rhyme (e.g. "-ight") or answer to a question ("whale") can be manipulated by steering at the end of the preceding line with a vector, affecting the generation of intermediate tokens leading up to the rhyme or answer word. We show that implicit planning is a universal mechanism, present in smaller models than previously thought, starting from 1B parameters. Our methodology offers a widely applicable direct way to study implicit planning abilities of LLMs. More broadly, understanding planning abilities of language models can inform decisions in AI safety and control. --- ### Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction Authors: Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Xinyi Zeng, Jingyuan Zhang, Yu Tian Published: 2026-01-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.20162v1 Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking personalized needs, leading to significant limitations for real users, particularly without personalized context: (1) inability to interpret ambiguous instructions, (2) lack of learning from user interaction history, and (3) failure to handle personalized instructions. To alleviate the above challenges, we propose Me-Agent, a learnable and memorable personalized mobile agent. Specifically, Me-Agent incorporates a two-level user habit learning approach. At the prompt level, we design a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance. At the memory level, we design a Hierarchical Preference Memory, which stores users' long-term memory and app-specific memory in different level memory. To validate the personalization capabilities of mobile agents, we introduce User FingerTip, a new benchmark featuring numerous ambiguous instructions for daily life. Extensive experiments on User FingerTip and general benchmarks demonstrate that Me-Agent achieves state-of-the-art performance in personalization while maintaining competitive instruction execution performance. --- ### PASS: Certified Subset Repair for Classical and Quantum Pairwise Constrained Clustering Authors: Pedro Chumpitaz-Flores, My Duong, Ying Mao, Kaixun Hua Published: 2026-01-28 Categories: cs.LG, cs.ET arXiv: https://arxiv.org/abs/2601.20157v2 Pairwise-constrained clustering incorporates side information through must-link (ML) and cannot-link (CL) relations between samples. While these constraints can improve cluster quality, they complicate optimization at scale and limit quantum and hybrid approaches through the size of the encoded problem. PASS is a scalable framework for pairwise-constrained k-means that concentrates optimization on a small working subset while updating remaining assignments through re-centering. Cannot-link feasibility under subset-restricted updates is formalized as a list-coloring problem on the induced constraint subgraph, yielding a checkable repair certificate with verifiable outcomes. The same subset restriction produces reduced classical subproblems and smaller quantum formulations, enabling a reduction-based hybrid evaluation under a simulation protocol. Infeasible constraint sets are handled explicitly: the pipeline returns a verifiable repair under stated conditions or reports residual conflicts under the same evaluation protocol. Across diverse benchmarks, PASS attains competitive SSE with lower runtime and returns solutions on instances where strong baselines do not finish within a fixed time budget. --- ### Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning Authors: Bo Dai, Na Li, Dale Schuurmans Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20154v2 Self-supervised learning (SSL) has improved empirical performance by unleashing the power of unlabeled data for practical applications. Specifically, SSL extracts the representation from massive unlabeled data, which will be transferred to a plenty of down streaming tasks with limited data. The significant improvement on diverse applications of representation learning has attracted increasing attention, resulting in a variety of dramatically different self-supervised learning objectives for representation extraction, with an assortment of learning procedures, but the lack of a clear and unified understanding. Such an absence hampers the ongoing development of representation learning, leaving a theoretical understanding missing, principles for efficient algorithm design unclear, and the use of representation learning methods in practice unjustified. The urgency for a unified framework is further motivated by the rapid growth in representation learning methods. In this paper, we are therefore compelled to develop a principled foundation of representation learning. We first theoretically investigate the sufficiency of the representation from a spectral representation view, which reveals the spectral essence of the existing successful SSL algorithms and paves the path to a unified framework for understanding and analysis. Such a framework work also inspires the development of more efficient and easy-to-use representation learning algorithms with principled way in real-world applications. --- ### Concentration Inequalities for Exchangeable Tensors and Matrix-valued Data Authors: Chen Cheng, Rina Foygel Barber Published: 2026-01-28 Categories: math.ST, math.PR, stat.ML arXiv: https://arxiv.org/abs/2601.20152v3 We study concentration inequalities for structured weighted sums of random data, including (i) tensor inner products and (ii) sequential matrix sums. We are interested in tail bounds and concentration inequalities for those structured weighted sums under exchangeability, extending beyond the classical framework of independent terms. We develop Hoeffding and Bernstein bounds provided with structure-dependent exchangeability. Along the way, we recover known results in weighted sum of exchangeable random variables and i.i.d. sums of random matrices to the optimal constants. Notably, we develop a sharper concentration bound for combinatorial sum of matrix arrays than the results previously derived from Chatterjee's method of exchangeable pairs. For applications, the richer structures provide us with novel analytical tools for estimating the average effect of multi-factor response models and studying fixed-design sketching methods in federated averaging. We apply our results to these problems, and find that our theoretical predictions are corroborated by numerical evidence. --- ### LogSieve: Task-Aware CI Log Reduction for Sustainable LLM-Based Analysis Authors: Marcus Emmanuel Barnes, Taher A. Ghaleb, Safwat Hassan Published: 2026-01-28 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2601.20148v1 Logs are essential for understanding Continuous Integration (CI) behavior, particularly for diagnosing build failures and performance regressions. Yet their growing volume and verbosity make both manual inspection and automated analysis increasingly costly, time-consuming, and environmentally costly. While prior work has explored log compression, anomaly detection, and LLM-based log analysis, most efforts target structured system logs rather than the unstructured, noisy, and verbose logs typical of CI workflows. We present LogSieve, a lightweight, RCA-aware and semantics-preserving log reduction technique that filters low-information lines while retaining content relevant to downstream reasoning. Evaluated on CI logs from 20 open-source Android projects using GitHub Actions, LogSieve achieves an average 42% reduction in lines and 40% reduction in tokens with minimal semantic loss. This pre-inference reduction lowers computational cost and can proportionally reduce energy use (and associated emissions) by decreasing the volume of data processed during LLM inference. Compared with structure-first baselines (LogZip and random-line removal), LogSieve preserves much higher semantic and categorical fidelity (Cosine = 0.93, GPTScore = 0.93, 80% exact-match accuracy). Embedding-based classifiers automate relevance detection with near-human accuracy (97%), enabling scalable and sustainable integration of semantics-aware filtering into CI workflows. LogSieve thus bridges log management and LLM reasoning, offering a practical path toward greener and more interpretable CI automation. --- ### Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents Authors: Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu et al. Published: 2026-01-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.20144v3 Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3) infeasible due to policy constraints, and training and evaluation data that cover these diverse, complex interaction patterns remain under-represented. To bridge the gap, we present Trajectory2Task, a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios: ambiguous intent, changing intent, and infeasible intents. The pipeline first conducts multi-turn exploration to produce valid tool-call trajectories. It then converts these trajectories into user-facing tasks with controlled intent adaptations. This process yields verifiable task that support closed-loop evaluation and training. We benchmark seven state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures. Finally, using successful trajectories obtained from task rollouts, we fine-tune lightweight LLMs and find consistent improvements across all three conditions, along with better generalization to unseen tool-use domains, indicating stronger tool-calling ability. --- ### Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR Authors: Zilai Wang, Natarajan Balaji Shankar, Kaiyuan Zhang, Zihan Wang, Abeer Alwan Published: 2026-01-28 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2601.20142v1 Self-supervised learning (SSL) models have achieved impressive results across many speech tasks, yet child automatic speech recognition (ASR) remains challenging due to limited data and pretraining domain mismatch. Fine-tuning SSL models on child speech induces shifts in the representation space. We hypothesize that delta SSL embeddings, defined as the differences between embeddings from a finetuned model and those from its pretrained counterpart, encode task-specific information that complements finetuned features from another SSL model. We evaluate multiple fusion strategies on the MyST childrens corpus using different models. Results show that delta embedding fusion with WavLM yields up to a 10 percent relative WER reduction for HuBERT and a 4.4 percent reduction for W2V2, compared to finetuned embedding fusion. Notably, fusing WavLM with delta W2V2 embeddings achieves a WER of 9.64, setting a new state of the art among SSL models on the MyST corpus. These findings demonstrate the effectiveness of delta embeddings and highlight feature fusion as a promising direction for advancing child ASR. --- ### Large language models accurately predict public perceptions of support for climate action worldwide Authors: Nattavudh Powdthavee, Sandra J. Geiger Published: 2026-01-28 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.20141v1 Although most people support climate action, widespread underestimation of others' support stalls individual and systemic changes. In this preregistered experiment, we test whether large language models (LLMs) can reliably predict these perception gaps worldwide. Using country-level indicators and public opinion data from 125 countries, we benchmark four state-of-the-art LLMs against Gallup World Poll 2021/22 data and statistical regressions. LLMs, particularly Claude, accurately capture public perceptions of others' willingness to contribute financially to climate action (MAE approximately 5 p.p.; r = .77), comparable to statistical models, though performance declines in less digitally connected, lower-GDP countries. Controlled tests show that LLMs capture the key psychological process - social projection with a systematic downward bias - and rely on structured reasoning rather than memorized values. Overall, LLMs provide a rapid tool for assessing perception gaps in climate action, serving as an alternative to costly surveys in resource-rich countries and as a complement in underrepresented populations. --- ### Scaling Next-Brain-Token Prediction for MEG Authors: Richard Csaky Published: 2026-01-28 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2601.20138v2 We present a large autoregressive model for source-space MEG that scales next-token prediction to long context across datasets and scanners: handling a corpus of over 500 hours and thousands of sessions across the three largest MEG datasets. A modified SEANet-style vector-quantizer reduces multichannel MEG into a flattened token stream on which we train a Qwen2.5-VL backbone from scratch to predict the next brain token and to recursively generate minutes of MEG from up to a minute of context. To evaluate long-horizon generation, we introduce task-matched tests: (i) on-manifold stability via generated-only drift compared to the time-resolved distribution of real sliding windows, and (ii) conditional specificity via correct context versus prompt-swap controls using a neurophysiologically grounded metric set. We train on CamCAN and Omega and run all analyses on held-out MOUS, establishing cross-dataset generalization. Across metrics, generations remain relatively stable over long rollouts and are closer to the correct continuation than swapped controls. Code available at: https://github.com/ricsinaruto/brain-gen. --- ### Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models Authors: Jai Sharma, Yifan Wang, Bryan Li Published: 2026-01-27 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2605.20187v1 Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these models primarily expose marginal conditional distributions and do not explicitly represent inter-variable dependence. We propose a neural framework for estimating pairwise conditional mutual information (MI) directly from the hidden states of a pretrained MDM, using ground-truth MI computed from the model's own conditional distributions for supervision. The resulting estimator captures the model's internal belief about dependency structure and predicts the full MI matrix in a single forward pass, enabling MI-guided parallel decoding by identifying conditionally independent subsets of variables. We evaluate our approach on Sudoku and protein sequence generation with ESM-C, where the MI maps recover known structural constraints and enable a 3-5x magnitude reduction in inference-time forward passes compared to sequential decoding, while preserving generative quality and outperforming entropy-based parallelization methods. --- ### Integrating Artificial Intelligence, Physics, and Internet of Things: A Framework for Cultural Heritage Conservation Authors: Carmine Valentino, Federico Pichi, Francesco Colace, Dajana Conte, Gianluigi Rozza Published: 2026-01-27 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.03233v1 The conservation of cultural heritage increasingly relies on integrating technological innovation with domain expertise to ensure effective monitoring and predictive maintenance. This paper presents a novel framework to support the preservation of cultural assets, combining Internet of Things (IoT) and Artificial Intelligence (AI) technologies, enhanced with the physical knowledge of phenomena. The framework is structured into four functional layers that permit the analysis of 3D models of cultural assets and elaborate simulations based on the knowledge acquired from data and physics. A central component of the proposed framework consists of Scientific Machine Learning, particularly Physics-Informed Neural Networks (PINNs), which incorporate physical laws into deep learning models. To enhance computational efficiency, the framework also integrates Reduced Order Methods (ROMs), specifically Proper Orthogonal Decomposition (POD), and is also compatible with classical Finite Element (FE) methods. Additionally, it includes tools to automatically manage and process 3D digital replicas, enabling their direct use in simulations. The proposed approach offers three main contributions: a methodology for processing 3D models of cultural assets for reliable simulation; the application of PINNs to combine data-driven and physics-based approaches in cultural heritage conservation; and the integration of PINNs with ROMs to efficiently model degradation processes influenced by environmental and material parameters. The reproducible and open-access experimental phase exploits simulated scenarios on complex and real-life geometries to test the efficacy of the proposed framework in each of its key components, allowing the possibility of dealing with both direct and inverse problems. Code availability: https://github.com/valc89/PhysicsInformedCulturalHeritage --- ### SRAG: RAG with Structured Data Improves Vector Retrieval Authors: Shalin Shah, Srikanth Ryali, Ramasubbu Venkatesh Published: 2026-01-27 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2603.26670v1 Retrieval Augmented Generation (RAG) provides the necessary informational grounding to LLMs in the form of chunks retrieved from a vector database or through web search. RAG could also use knowledge graph triples as a means of providing factual information to an LLM. However, the retrieval is only based on representational similarity between a question and the contents. The performance of RAG depends on the numeric vector representations of the query and the chunks. To improve these representations, we propose Structured RAG (SRAG), which adds structured information to a query as well as the chunks in the form of topics, sentiments, query and chunk types (e.g., informational, quantitative), knowledge graph triples and semantic tags. Experiments indicate that this method significantly improves the retrieval process. Using GPT-5 as an LLM-as-a-judge, results show that the method improves the score given to answers in a question answering system by 30% (p-value = 2e-13) (with tighter bounds). The strongest improvement is in comparative, analytical and predictive questions. The results suggest that our method enables broader, more diverse, and episodic-style retrieval. Tail risk analysis shows that SRAG attains very large gains more often, with losses remaining minor in magnitude. --- ### Founder effects shape the evolutionary dynamics of multimodality in open LLM families Authors: Manuel Cebrian Published: 2026-01-27 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.22287v1 Large language model (LLM) families are improving rapidly, yet it remains unclear how quickly multimodal capabilities emerge and propagate within open families. Using the ModelBiome AI Ecosystem dataset of Hugging Face model metadata and recorded lineage fields (>1.8x10^6 model entries), we quantify multimodality over time and along recorded parent-to-child relations. Cross-modal tasks are widespread in the broader ecosystem well before they become common within major open LLM families: within these families, multimodality remains rare through 2023 and most of 2024, then increases sharply in 2024-2025 and is dominated by image-text vision-language tasks. Across major families, the first vision-language model (VLM) variants typically appear months after the first text-generation releases, with lags ranging from ~1 month (Gemma) to more than a year for several families and ~26 months for GLM. Lineage-conditioned transition rates show weak cross-type transfer: among fine-tuning edges from text-generation parents, only 0.218% yield VLM descendants. Instead, multimodality expands primarily within existing VLM lineages: 94.5% of VLM-child fine-tuning edges originate from VLM parents, versus 4.7% from text-generation parents. At the model level, most VLM releases appear as new roots without recorded parents (~60%), while the remainder are predominantly VLM-derived; founder concentration analyses indicate rapid within-lineage amplification followed by diversification. Together, these results show that multimodality enters open LLM families through rare founder events and then expands rapidly within their descendant lineages, producing punctuated adoption dynamics that likely induce distinct, transfer-limited scaling behavior for multimodal capabilities. --- ### Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models Authors: Anna Gausen, Sarenne Wallbridge, Hannah Rose Kirk, Jennifer Williams, Christopher Summerfield Published: 2026-01-27 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.16874v1 As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive information, place unwarranted trust in AI-generated advice, or fall victim to AI-enabled fraud. More broadly, a persistent lack of transparency can erode trust in mediated communication. While regulations like the EU AI Act and California's BOT Act require AI systems to identify themselves, they provide limited guidance on reliable disclosure in real-time conversation. Existing transparency mechanisms also leave gaps: interface indicators can be omitted by deployers, and provenance tools require coordinated infrastructure and cannot provide reliable real-time verification. We ask how conversational AI systems should maintain identity transparency as human-AI interactions become more ambiguous and diverse. We advocate for disclosure by design, where AI systems explicitly disclose their artificial identity when directly asked. Implemented as model behaviour, disclosure can persist across deployment contexts without relying on user interfaces, while preserving user agency to verify identity on demand without disrupting immersive uses like role-playing. To assess current practice, we present the first multi-modal (text and voice) evaluation of disclosure behaviour in deployed systems across baseline, role-playing, and adversarial settings. We find that baseline disclosure rates are often high but drop substantially in role-play and can be suppressed under adversarial prompting. Importantly, disclosure rates vary significantly across providers and modalities, highlighting the fragility of current disclosure behaviour. We conclude with technical interventions to help developers embed disclosure as a fundamental property of conversational AI models. --- ### RFX-Fuse: Breiman and Cutler's Unified ML Engine + Native Explainable Similarity Authors: Chris Kuchar Published: 2026-01-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.13234v1 Breiman and Cutler's original Random Forest was designed as a unified ML engine -- not merely an ensemble predictor. Their implementation included classification, regression, unsupervised learning, proximity-based similarity, outlier detection, missing value imputation, and visualization -- capabilities that modern libraries like scikit-learn never implemented. RFX-Fuse (Random Forests X (X=compression) -- Forest Unified Learning and Similarity Engine) delivers Breiman and Cutler's complete vision with native GPU/CPU support. Modern ML pipelines require 5+ separate tools -- XGBoost for prediction, FAISS for similarity, SHAP for explanations, Isolation Forest for outliers, custom code for importance. RFX-Fuse provides a 1 to 2 model object alternative -- a single set of trees grown once. Novel Contributions: (1) Proximity Importance -- native explainable similarity: proximity measures that samples are similar; proximity importance explains why. (2) Dataset-specific imputation validation for general tabular data -- ranking imputation methods by how real the imputed data looks, without ground truth labels. --- ### Transit Network Design with Two-Level Demand Uncertainties: A Machine Learning and Contextual Stochastic Optimization Framework Authors: Hongzhao Guan, Beste Basciftci, Pascal Van Hentenryck Published: 2026-01-27 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.00010v2 Transit Network Design is a well-studied problem in the field of transportation, typically addressed by solving optimization models under fixed demand assumptions. Considering the limitations of these assumptions, this paper proposes a new framework, namely the Two-Level Rider Choice Transit Network Design (2LRC-TND), that leverages machine learning and contextual stochastic optimization (CSO) through constraint programming (CP) to incorporate two layers of demand uncertainties into the network design process. The first level identifies travelers who rely on public transit (core demand), while the second level captures the conditional adoption behavior of those who do not (latent demand), based on the availability and quality of transit services. To capture these two types of uncertainties, 2LRC-TND relies on two travel mode choice models, that use multiple machine learning models. To design a network, 2LRC-TND integrates the resulting choice models into a CSO that is solved using a CP-SAT solver. 2LRC-TND is evaluated through a case study involving over 6,600 travel arcs and more than 38,000 trips in the Atlanta metropolitan area. The computational results demonstrate the effectiveness of the 2LRC-TND in designing transit networks that account for demand uncertainties and contextual information, offering a more realistic alternative to fixed-demand models. --- ### Now You See Me: Designing Responsible AI Dashboards for Early-Stage Health Innovation Authors: Svitlana Surodina, Sinem Görücü, Lili Golmohammadi, Emelia Delaney, Rita Borgo Published: 2026-01-27 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.23378v1 Innovative HealthTech teams develop Artificial Intelligence (AI) systems in contexts where ethical expectations and organizational priorities must be balanced under severe resource constraints. While Responsible AI practices are expected to guide the design and evaluation of such systems, they frequently remain abstract or poorly aligned with the operational realities of early-stage innovation. At the ecosystem level, this misalignment disproportionately affects disadvantaged projects and founders, therefore limiting the diversity of problem-areas under consideration, solutions, stakeholder perspectives, and population datasets represented in AI-enabled healthcare systems. Visualization provides a practical mechanism for supporting decision-making across the AI lifecycle. When developed via a rigorous and collaborative design process, structured on domain knowledge and designed around real-world constraints, visual interfaces can operate as effective sociotechnical governance artifacts enabling responsible decision-making. Grounded in innovation-oriented Human-Centered Computing methodologies, we synthesize insights from a series of design studies conducted via a longitudinal visualization research program, a case study centered on governance dashboard design in a translational setting, and a survey of a cohort of early-stage HealthTech startups. Based on these findings, we articulate design process implications for governance-oriented visualization systems: co-creation with stakeholders, alignment with organizational maturity and context, and support for heterogeneous roles and tasks among others. This work contributes actionable guidance for designing Responsible AI governance dashboards that support decision-making and accountability in early-stage health innovation, and suggests that ecosystem-level coordination can enable more scalable and diverse AI innovation in healthcare. --- ### Graph Modelling Analysis of Speech-Gesture Interaction for Aphasia Severity Estimation Authors: Navya Martin Kollapally, Christa Akers, Renjith Nelson Joseph Published: 2026-01-27 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.20163v1 Aphasia is an acquired language disorder caused by injury to the regions of the brain that are responsible for language. Aphasia may impair the use and comprehension of written and spoken language. The Western Aphasia Battery-Revised (WAB-R) is an assessment tool administered by speech-language pathologists (SLPs) to evaluate the aphasia type and severity. Because the WAB-R measures isolated linguistic skills, there has been growing interest in the assessment of discourse production as a more holistic representation of everyday language abilities. Recent advancements in speech analysis focus on automated estimation of aphasia severity from spontaneous speech, relying mostly in isolated linguistic or acoustical features. In this work, we propose a graph neural network-based framework for estimating aphasia severity. We represented each participant's discourse as a directed multi-modal graph, where nodes represent lexical items and gestures and edges encode word-word, gesture-word, and word-gesture transitions. GraphSAGE is employed to learn participant-level embeddings, thus integrating information from immediate neighbors and overall graph structure. Our results suggest that aphasia severity is not encoded in isolated lexical distribution, but rather emerges from structured interactions between speech and gesture. The proposed architecture offers a reliable automated aphasia assessment, with possible uses in bedside screening and telehealth-based monitoring. --- ### ReportLogic: Evaluating Logical Quality in Deep Research Reports Authors: Jujia Zhao, Zhaoxin Huan, Zihan Wang, Xiaolu Zhang, Jun Zhou, Suzan Verberne, Zhaochun Ren Published: 2026-01-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.18446v2 Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action. In this context, the practical reliability of such reports hinges on logical quality: whether the report's claims and arguments are explicitly supported and can be trusted as a basis for downstream use, rather than merely appearing fluent or informative. However, current evaluation frameworks largely overlook this requirement. To bridge this gap, we introduce ReportLogic, a benchmark that quantifies report-level logical quality through a reader-centric lens of auditability. Specifically, ReportLogic adopts a hierarchical taxonomy that evaluates whether readers can (1) trace an on-topic report structure with a unified analytical arc (Macro-Logic), (2) understand the progression with necessary context (Expositional-Logic), and (3) verify conclusions via explicit claim--support (Structural-Logic). Based on this taxonomy, we construct a human-annotated rubric-guided dataset and train an open-source LogicJudge for scalable evaluation. We further evaluate judge robustness via adversarial attacks, showing that off-the-shelf LLM judges are frequently influenced by superficial cues (e.g., verbosity), and reasoning modes can mask broken support relations. Overall, our results provide actionable guidance for building more robust logic evaluators and improving the logical reliability of LLM-generated reports. --- ### Epistemic Traps: Rational Misalignment Driven by Model Misspecification Authors: Xingcheng Xu, Jingjing Qu, Qiaosheng Zhang, Chaochao Lu, Yanqing Yang, Na Zou, Xia Hu Published: 2026-01-27 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.17676v1 The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation via reinforcement learning. Current safety paradigms treat these failures as transient training artifacts, lacking a unified theoretical framework to explain their emergence and stability. Here we show that these misalignments are not errors, but mathematically rationalizable behaviors arising from model misspecification. By adapting Berk-Nash Rationalizability from theoretical economics to artificial intelligence, we derive a rigorous framework that models the agent as optimizing against a flawed subjective world model. We demonstrate that widely observed failures are structural necessities: unsafe behaviors emerge as either a stable misaligned equilibrium or oscillatory cycles depending on reward scheme, while strategic deception persists as a "locked-in" equilibrium or through epistemic indeterminacy robust to objective risks. We validate these theoretical predictions through behavioral experiments on six state-of-the-art model families, generating phase diagrams that precisely map the topological boundaries of safe behavior. Our findings reveal that safety is a discrete phase determined by the agent's epistemic priors rather than a continuous function of reward magnitude. This establishes Subjective Model Engineering, defined as the design of an agent's internal belief structure, as a necessary condition for robust alignment, marking a paradigm shift from manipulating environmental rewards to shaping the agent's interpretation of reality. --- ### CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content Authors: Diletta Abbonato Published: 2026-01-27 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2602.15871v1 The proliferation of large language models (LLMs) in academic workflows has introduced unprecedented challenges to bibliographic integrity, particularly through reference hallucination -- the generation of plausible but non-existent citations. Recent investigations have documented the presence of AI-hallucinated citations even in papers accepted at premier machine learning conferences such as NeurIPS and ICLR, underscoring the urgency of automated verification mechanisms. This paper presents "CheckIfExist", an open-source web-based tool designed to provide immediate verification of bibliographic references through multi-source validation against CrossRef, Semantic Scholar, and OpenAlex scholarly databases. While existing reference management tools offer bibliographic organization capabilities, they do not provide real-time validation of citation authenticity. Commercial hallucination detection services, though increasingly available, often impose restrictive usage limits on free tiers or require substantial subscription fees. The proposed tool fills this gap by employing a cascading validation architecture with string similarity algorithms to compute multi-dimensional match confidence scores, delivering instant feedback on reference authenticity. The system supports both single-reference verification and batch processing of BibTeX entries through a unified interface, returning validated APA citations and exportable BibTeX records within seconds. --- ### VDLM: Variable Diffusion LMs via Robust Latent-to-Text Rendering Authors: Shuhui Qu Published: 2026-01-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15870v1 Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from text rendering. VDLM applies LLaDA-style masked diffusion over semantic variable embeddings to enable iterative refinement in latent space, then post-trains the planner with trajectory-aware optimization using embedding-space rewards and values, avoiding text decoding inside the RL loop. To convert planned embeddings back to text, we use a \textbf{Vec2Text} renderer and introduce \textbf{embedding perturbations} to robustify decoding under planner noise. Across nine benchmarks spanning general reasoning, math, and code, VDLM is competitive in pre-training and yields substantial post-training improvements on long-form generation tasks, outperforming other baselines. These results highlight the effectiveness of embedding-space post-training and robust latent-to-text rendering for diffusion language modeling. --- ### Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches Authors: Noopur Zambare, Kiana Aghakasiri, Carissa Lin, Carrie Ye, J. Ross Mitchell, Mohamed Abdalla Published: 2026-01-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15869v1 Large language models (LLMs) have shown strong performance on clinical de-identification, the task of identifying sensitive identifiers to protect privacy. However, previous work has not examined their generalizability between formats, cultures, and genders. In this work, we systematically evaluate fine-tuned transformer models (BERT, ClinicalBERT, ModernBERT), small LLMs (Llama 1-8B, Qwen 1.5-7B), and large LLMs (Llama-70B, Qwen-72B) at de-identification. We show that smaller models achieve comparable performance while substantially reducing inference cost, making them more practical for deployment. Moreover, we demonstrate that smaller models can be fine-tuned with limited data to outperform larger models in de-identifying identifiers drawn from Mandarin, Hindi, Spanish, French, Bengali, and regional variations of English, in addition to gendered names. To improve robustness in multi-cultural contexts, we introduce and publicly release BERT-MultiCulture-DEID, a set of de-identification models based on BERT, ClinicalBERT, and ModernBERT, fine-tuned on MIMIC with identifiers from multiple language variants. Our findings provide the first comprehensive quantification of the efficiency-generalizability trade-off in de-identification and establish practical pathways for fair and efficient clinical de-identification. Details on accessing the models are available at: https://doi.org/10.5281/zenodo.18342291 --- ### Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning Authors: Magnus Boman Published: 2026-01-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15868v3 Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters, tokens, vocabulary, model parameters, activations, probability distributions, and output text. The model enables precise localisation of failure modes to specific pipeline stages, revealing, e.g., how tokenisation obscures character-level structure needed for counting tasks. The model clarifies why techniques like chain-of-thought prompting help, by externalising computation on the output tape, while also revealing their fundamental limitations. This approach provides a rigorous, falsifiable alternative to geometric metaphors and complements empirical scaling laws with principled error analysis. --- ### Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork? Authors: Berry Gerrits Published: 2026-01-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.15867v1 In this positioning paper, we evaluate the problem-solving and reasoning capabilities of contemporary Large Language Models (LLMs) through their performance in Zork, the seminal text-based adventure game first released in 1977. The game's dialogue-based structure provides a controlled environment for assessing how LLM-based chatbots interpret natural language descriptions and generate appropriate action sequences to succeed in the game. We test the performance of leading proprietary models - ChatGPT, Claude, and Gemini - under both minimal and detailed instructions, measuring game progress through achieved scores as the primary metric. Our results reveal that all tested models achieve less than 10% completion on average, with even the best-performing model (Claude Opus 4.5) reaching only approximately 75 out of 350 possible points. Notably, providing detailed game instructions offers no improvement, nor does enabling ''extended thinking''. Qualitative analysis of the models' reasoning processes reveals fundamental limitations: repeated unsuccessful actions suggesting an inability to reflect on one's own thinking, inconsistent persistence of strategies, and failure to learn from previous attempts despite access to conversation history. These findings suggest substantial limitations in current LLMs' metacognitive abilities and problem-solving capabilities within the domain of text-based games, raising questions about the nature and extent of their reasoning capabilities. --- ### Transforming Computational Lithography with AC and AI -- Faster, More Accurate, and Energy-efficient Authors: Saumyadip Mukhopadhyay, Kiho Yang, Kasyap Thottasserymana Vasudevan, Mounica Jyothi Divvela, Selim Dogru, Dilip Krishnamurthy, Fergo Treska, Werner Gillijns, Ryan Ryoung han Kim, Kumara Sastry, Vivek Singh Published: 2026-01-27 Categories: eess.SP, cs.AI, physics.app-ph arXiv: https://arxiv.org/abs/2602.15036v1 From climate science to drug discovery, scientific computing demands have surged dramatically in recent years -- driven by larger datasets, more sophisticated models, and higher simulation fidelity. This growth rate far outpaces transistor scaling, leading to unsustainably rising costs, energy consumption, and emissions. Semiconductor manufacturing is no exception. Computational lithography -- involving transferring circuitry to silicon in diffraction-limited conditions -- is the largest workload in semiconductor manufacturing. It has also grown exceptionally complex as miniaturization has advanced in the angstrom-era, requiring more accurate modeling, intricate corrections, and broader solution-space exploration. Accelerated computing (AC) offers a solution by dramatically freeing up the compute and power envelope. AI augments these gains by serving as high-fidelity surrogates for compute-intensive steps. Together, they present a sustainable, next-generation computing platform for scientific workloads. This new paradigm needs a fundamental redesign of the software stack. For computational lithography, NVIDIA cuLitho reinvents the core primitives -- diffractive optics, computational geometry, multi-variant optimization, data processing -- to achieve a transformative 57X end-to-end acceleration. Beyond dramatically faster cycles, this expanded compute envelope enables more rigorous solutions, including curvilinear masks, high-numerical aperture extreme ultraviolet (high-NA EUV) lithography, and subatomic modeling. We reinvest a small fraction of the freed-up compute to include through-focus correction for better process resilience. Silicon experiments at IMEC show significant benefits compared to conventional methods -- 35% better process window and 19% better edge placement error. This is the first quantified chip-scale demonstration of the lithography benefits of AC and AI in silicon. --- ### An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading Authors: Eranga Bandara, Ross Gore, Sachin Shetty, Ravi Mukkamala, Tharaka Hewa, Abdul Rahman, Xueping Liang, Safdar H. Bouk, Amin Hass, Peter Foytik, Ng Wee Keong, Kasun De Zoysa Published: 2026-01-27 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2602.13227v1 6G networks are expected to be AI-native, intent-driven, and economically programmable, requiring fundamentally new approaches to network slice orchestration. Existing slicing frameworks, largely designed for 5G, rely on static policies and manual workflows and are ill-suited for the dynamic, multi-domain, and service-centric nature of emerging 6G environments. In this paper, we propose an agentic AI control plane architecture for 6G network slice orchestration, monitoring, and trading that treats orchestration as a holistic control function encompassing slice planning, deployment, continuous monitoring, and economically informed decision-making. The proposed control plane is realized as a layered architecture in which multiple cooperating AI agents. To support flexible and on-demand slice utilization, the control plane incorporates market-aware orchestration capabilities, allowing slice requirements, pricing, and availability to be jointly considered during orchestration decisions. A natural language interface, implemented using the Model Context Protocol (MCP), enables users and applications to interact with control-plane functions through intent-based queries while enforcing safety and policy constraints. To ensure responsible and explainable autonomy, the control plane integrates fine-tuned large language models organized as a multi-model consortium, governed by a dedicated reasoning model. The proposed approach is evaluated using a real-world testbed with multiple mobile core instances (e.g Open5GS) integrated with Ericsson's RAN infrastructure. The results demonstrate that combining agentic autonomy, closed-loop SLA assurance, market-aware orchestration, and natural language control enables a scalable and adaptive 6G-native control plane for network slice management, highlighting the potential of agentic AI as a foundational mechanism for future 6G networks. --- ### Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection Authors: Xuecong Li, Xiaohong Li, Qiang Hu, Yao Zhang, Junjie Wang Published: 2026-01-27 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13226v1 Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs. Leveraging this observation, VaryBalance quantifies this through mean standard deviation and distinguishes human texts and LLM-generated texts. Comprehensive experiments demonstrated that VaryBalance outperforms the state-of-the-art detectors, i.e., Binoculars, by up to 34.3\% in terms of AUROC, and maintains robustness against multiple generating models and languages. --- ### MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization Authors: Haidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan, Shuo Wang, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun Published: 2026-01-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11182v2 Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing effective memories, they often disrupt the inherent logical and temporal relationships within interaction sessions, resulting in fragmented memory units and degraded reasoning performance. In this paper, we propose MetaMem, a novel framework that augments memory systems with a self-evolving meta-memory, aiming to teach LLMs how to effectively utilize memorized knowledge. During meta-memory optimization, MetaMem iteratively distills transferable knowledge utilization experiences across different tasks by self-reflecting on reasoning processes and performing actions to update the current meta-memory state. The accumulated meta-memory units serve as explicit knowledge utilization experiences, guiding the LLM to systematically identify and integrate critical evidence from scattered memory fragments. Extensive experiments demonstrate the effectiveness of MetaMem, which significantly outperforms strong baselines by over 3.6%. All codes and datasets are available at https://github.com/OpenBMB/MetaMem. --- ### A Practical Guide to Agentic AI Transition in Organizations Authors: Eranga Bandara, Ross Gore, Sachin Shetty, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Ravi Mukkamala, Peter Foytik, Safdar H. Bouk, Abdul Rahman, Xueping Liang, Amin Hass et al. Published: 2026-01-27 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.10122v1 Agentic AI represents a significant shift in how intelligence is applied within organizations, moving beyond AI-assisted tools toward autonomous systems capable of reasoning, decision-making, and coordinated action across workflows. As these systems mature, they have the potential to automate a substantial share of manual organizational processes, fundamentally reshaping how work is designed, executed, and governed. Although many organizations have adopted AI to improve productivity, most implementations remain limited to isolated use cases and human-centered, tool-driven workflows. Despite increasing awareness of agentic AI's strategic importance, engineering teams and organizational leaders often lack clear guidance on how to operationalize it effectively. Key challenges include an overreliance on traditional software engineering practices, limited integration of business-domain knowledge, unclear ownership of AI-driven workflows, and the absence of sustainable human-AI collaboration models. Consequently, organizations struggle to move beyond experimentation, scale agentic systems, and align them with tangible business value. Drawing on practical experience in designing and deploying agentic AI workflows across multiple organizations and business domains, this paper proposes a pragmatic framework for transitioning organizational functions from manual processes to automated agentic AI systems. The framework emphasizes domain-driven use case identification, systematic delegation of tasks to AI agents, AI-assisted construction of agentic workflows, and small, AI-augmented teams working closely with business stakeholders. Central to the approach is a human-in-the-loop operating model in which individuals act as orchestrators of multiple AI agents, enabling scalable automation while maintaining oversight, adaptability, and organizational control. --- ### Machine learning enhanced data assimilation framework for multiscale carbonate rock characterization Authors: Zhenkai Bo, Ahmed H. Elsheikh, Hannah P. Menke, Julien Maes, Sebastian Geiger, Muhammad Z. Kashim, Zainol A. A. Bakar, Kamaljit Singh Published: 2026-01-27 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2602.06989v2 Carbonate reservoirs offer significant capacity for subsurface carbon storage, oil production, and underground hydrogen storage. X-ray computed tomography (X-ray CT) coupled with numerical simulations is commonly used to investigate the multiphase flow behaviors in carbonate rocks. Carbonates exhibit pore size distribution across scales, hindering the comprehensive investigation with conventional X-ray CT images. Imaging samples at both macro and micro-scales (multi-scale imaging) proved to be a viable option in this context. However, multi-scale imaging faces two key limitations: the trade-off between field of view and voxel size necessitates resource-intensive imaging, while multi-scale multi-physics numerical simulations on resulting digital models incur prohibitive computational costs. To address these challenges, we propose a machine learning-enhanced data assimilation framework that leverages experimental drainage relative permeability measurements to achieve efficient characterization of micro-scale structures, delivering a data-driven solution toward a high-fidelity multiscale digital rock modeling. We train a dense neural network (DNN) as a proxy to a multi-scale pore network simulator and couple it with an ensemble smoother with multiple data assimilation (ESMDA) algorithm. DNN-ESMDA framework simultaneously infers the CO2-brine drainage relative permeability of microporosity phases with associated uncertainty estimation, revealing the relative importance of each rock phase and guiding future characterization. Our DNN-ESMDA framework achieves a computational speedup, reducing inference time from thousands of hours to seconds compared with the usage of conventional multiscale numerical simulation. Given this computational efficiency and applicability, the machine learning-enhanced ESMDA framework presents a generalizable approach for characterizing multiscale carbonate rocks. --- ### Empowering Affected Individuals to Shape AI Fairness Assessments: Processes, Criteria, and Tools Authors: Lin Luo, Satwik Ghanta, Yuri Nakao, Mathieu Chollet, Simone Stumpf Published: 2026-01-27 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.06984v1 AI systems are increasingly used in high-stakes domains such as credit rating, where fairness concerns are critical. Existing fairness assessments are typically conducted by AI experts or regulators using predefined protected attributes and metrics, which often fail to capture the diversity and nuance of fairness notions held by the individuals who are affected by these systems' decisions, such as decision subjects. Recent work has therefore called for involving affected individuals in fairness assessment, yet little empirical evidence exists on how they create their own fairness criteria or what kinds of criteria they produce - knowledge that could not only inform experts' fairness evaluation and mitigation, but also guide the design of AI assessment tools. We address this gap through a qualitative user study with 18 participants in a credit rating scenario. Participants first articulated their fairness notions in their own words. Then, participants turned them into concrete quantified and operationalized fairness criteria, through an interactive prototype we designed. Our findings provide empirical evidence of the process through which people's fairness notions emerge via grounding in model features, and uncover a diverse set of individuals' custom-defined criteria for both outcome and procedural fairness. We provide design implications for processes and tools that support more inclusive and value-sensitive AI fairness assessment. --- ### Hybrid Deep Learning Framework for CSI-Based Activity Recognition in Bandwidth-Constrained Wi-Fi Sensing Authors: Alison M. Fernandes, Hermes I. Del Monego, Bruno S. Chang, Anelise Munaretto, Hélder M. Fontes, Rui Campos Published: 2026-01-27 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.06983v1 This paper presents a novel hybrid deep learning framework designed to enhance the robustness of CSI-based Human Activity Recognition (HAR) within bandwidth-constrained Wi-Fi sensing environments. The core of our proposed methodology is a preliminary Doppler trace extraction stage, implemented to amplify salient motion-related signal features before classification. Subsequently, these enhanced inputs are processed by a hybrid neural architecture, which integrates Inception networks responsible for hierarchical spatial feature extraction and Bidirectional Long Short-Term Memory (BiLSTM) networks that capture temporal dependencies. A Support Vector Machine (SVM) is then utilized as the final classification layer to optimize decision boundaries. The framework's efficacy was systematically validated using a public dataset across 20, 40, and 80 MHz bandwidth configurations. The model yielded accuracies of 89.27% (20 MHz), 94.13% (40 MHz), and 95.30% (80 MHz), respectively. These results confirm a marked superiority over standalone deep learning baselines, especially in the most constrained low-bandwidth scenarios. This study underscores the utility of combining Doppler-based feature engineering with a hybrid learning architecture for reliable HAR in bandwidth-limited wireless sensing applications. --- ### Deep Reinforcement Learning for Interference Suppression in RIS-Aided Space-Air-Ground Integrated Networks Authors: Pujitha Mamillapalli, Shikhar Verma, Tiago Koketsu Rodrigues, Abhinav Kumar Published: 2026-01-27 Categories: eess.SP, cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.06982v1 Future 6G networks envision ubiquitous connectivity through space-air-ground integrated networks (SAGINs), where high-altitude platform stations (HAPSs) and satellites complement terrestrial systems to provide wide-area, low-latency coverage. However, the rapid growth of terrestrial devices intensifies spectrum sharing between terrestrial and non-terrestrial segments, resulting in severe cross-tier interference. In particular, frequency sharing between the HAPS satellite uplink and HAPS ground downlink improves spectrum efficiency but suffers from interference caused by the HAPS antenna back-lobe. Existing approaches relying on zero-forcing (ZF) codebooks have limited performance under highly dynamic channel conditions. To overcome this limitation, we employ a reconfigurable intelligent surface (RIS)-aided HAPS-based SAGIN framework with a deep deterministic policy gradient (DDPG) algorithm. The proposed DDPG framework optimizes the HAPS beamforming weights to form spatial nulls toward interference sources while maintaining robust links to the desired signals. Simulation results demonstrate that the DDPG framework consistently outperforms conventional ZF beamforming among different RIS configurations, achieving up to \(11.3\%\) throughput improvement for a \(4\times4\) RIS configuration, validating its adaptive capability to enhance spectral efficiency in dynamic HAPS-based SAGINs. --- ### Deep Unfolded Fractional Optimization for Maximizing Robust Throughput in 6G Networks Authors: Anh Thi Bui, Robert-Jeron Reifert, Hayssam Dahrouj, Aydin Sezgin Published: 2026-01-27 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.06062v1 The sixth-generation (6G) of wireless communication networks aims to leverage artificial intelligence tools for efficient and robust network optimization. This is especially the case since traditional optimization methods often face high computational complexity, motivating the use of deep learning (DL)-based optimization frameworks. In this context, this paper considers a multi-antenna base station (BS) serving multiple users simultaneously through transmit beamforming in downlink mode. To account for robustness, this work proposes an uncertainty-injected deep unfolded fractional programming (UI-DUFP) framework for weighted sum rate (WSR) maximization under imperfect channel conditions. The proposed method unfolds fractional programming (FP) iterations into trainable neural network layers refined by projected gradient descent (PGD) steps, while robustness is introduced by injecting sampled channel uncertainties during training and optimizing a quantile-based objective. Simulation results show that the proposed UI-DUFP achieves higher WSR and improved robustness compared to classical weighted minimum mean square error, FP, and DL baselines, while maintaining low inference time and good scalability. These findings highlight the potential of deep unfolding combined with uncertainty-aware training as a powerful approach for robust optimization in 6G networks. --- ### A General-Purpose Diversified 2D Seismic Image Dataset from NAMSS Authors: Lucas de Magalhães Araujo, Otávio Oliveira Napoli, Sandra Avila, Edson Borin Published: 2026-01-27 Categories: physics.geo-ph, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.04890v1 We introduce the Unicamp-NAMSS dataset, a large, diverse, and geographically distributed collection of migrated 2D seismic sections designed to support modern machine learning research in geophysics. We constructed the dataset from the National Archive of Marine Seismic Surveys (NAMSS), which contains decades of publicly available marine seismic data acquired across multiple regions, acquisition conditions, and geological settings. After a comprehensive collection and filtering process, we obtained 2588 cleaned and standardized seismic sections from 122 survey areas, covering a wide range of vertical and horizontal sampling characteristics. To ensure reliable experimentation, we balanced the dataset so that no survey dominates the distribution, and partitioned it into non-overlapping macro-regions for training, validation, and testing. This region-disjoint split allows robust evaluation of generalization to unseen geological and acquisition conditions. We validated the dataset through quantitative and embedding-space analyses using both convolutional and transformer-based models. These analyses showed that Unicamp-NAMSS exhibits substantial variability within and across regions, while maintaining coherent structure across acquisition macro-region and survey types. Comparisons with widely used interpretation datasets (Parihaka and F3 Block) further demonstrated that Unicamp-NAMSS covers a broader portion of the seismic appearance space, making it a strong candidate for machine learning model pretraining. The dataset, therefore, provides a valuable resource for machine learning tasks, including self-supervised representation learning, transfer learning, benchmarking supervised tasks such as super-resolution or attribute prediction, and studying domain adaptation in seismic interpretation. --- ### Hypersonic Flow Control: Generalized Deep Reinforcement Learning for Hypersonic Intake Unstart Control under Uncertainty Authors: Trishit Mondal, Ameya D. Jagtap Published: 2026-01-27 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2602.02531v1 The hypersonic unstart phenomenon poses a major challenge to reliable air-breathing propulsion at Mach 5 and above, where strong shock-boundary-layer interactions and rapid pressure fluctuations can destabilize inlet operation. Here, we demonstrate a deep reinforcement learning (DRL)- based active flow control strategy to control unstart in a canonical two-dimensional hypersonic inlet at Mach 5 and Reynolds number $5\times 10^6$. The in-house CFD solver enables high-fidelity simulations with adaptive mesh refinement, resolving key flow features, including shock motion, boundary-layer dynamics, and flow separation, that are essential for learning physically consistent control policies suitable for real-time deployment. The DRL controller robustly stabilizes the inlet over a wide range of back pressures representative of varying combustion chamber conditions. It further generalizes to previously unseen scenarios, including different back-pressure levels, Reynolds numbers, and sensor configurations, while operating with noisy measurements, thereby demonstrating strong zero-shot generalization. Control remains robust in the presence of noisy sensor measurements, and a minimal, optimally selected sensor set achieves comparable performance, enabling practical implementation. These results establish a data-driven approach for real-time hypersonic flow control under realistic operational uncertainties. --- ### Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation Authors: Saurav Singh, Rodney Sanchez, Alexander Ororbia, Jamison Heard Published: 2026-01-27 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.02530v1 Reinforcement learning (RL) has the potential to transform real-world decision-making systems by enabling autonomous agents to learn from experience. Deploying RL in real-world settings, especially in the context of human-robot interaction, requires defining state representations and reward functions, which are critical for learning efficiency and policy performance. Traditional RL approaches often rely on domain expertise and trial-and-error, necessitating extensive human involvement as well as direct interaction with the environment, which can be costly and impractical, especially in complex and safety-critical applications. This work proposes a novel RL framework that leverages off-policy evaluation (OPE) for state space and reward function selection, using only logged interaction data. This approach eliminates the need for real-time access to the environment or human-in-the-loop feedback, greatly reducing the dependency on costly real-time interactions. The proposed approach systematically evaluates multiple candidate state representations and reward functions by training offline RL agents and applying OPE to estimate policy performance. The optimal state space and reward function are selected based on their ability to produce high-performing policies under OPE metrics. Our method is validated on two environments: the Lunar Lander environment by OpenAI Gym, which provides a controlled setting for assessing state space and reward function selection, and a NASA-MATB-II human subjects study environment, which evaluates the approach's real-world applicability to human-robot teaming scenarios. This work enhances the feasibility and scalability of offline RL for real-world environments by automating critical RL design decisions through a data-driven OPE-based evaluation, enabling more reliable, effective, and sustainable RL formulation for complex human-robot interaction settings. ---