# Research Papers — 2026-02 · bundle page 81 of 210

> Full-text markdown of papers #4001–4050 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/81
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/80.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/82.md)

### StrokeNeXt: A Siamese-encoder Approach for Brain Stroke Classification in Computed Tomography Imagery

Authors: Leo Thomas Ramos, Angel D. Sappa
Published: 2026-02-16
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.15087v1

We present StrokeNeXt, a model for stroke classification in 2D Computed Tomography (CT) images. StrokeNeXt employs a dual-branch design with two ConvNeXt encoders, whose features are fused through a lightweight convolutional decoder based on stacked 1D operations, including a bottleneck projection and transformation layers, and a compact classification head. The model is evaluated on a curated dataset of 6,774 CT images, addressing both stroke detection and subtype classification between ischemic and hemorrhage cases. StrokeNeXt consistently outperforms convolutional and Transformer-based baselines, reaching accuracies and F1-scores of up to 0.988. Paired statistical tests confirm that the performance gains are statistically significant, while class-wise sensitivity and specificity demonstrate robust behavior across diagnostic categories. Calibration analysis shows reduced prediction error compared to competing methods, and confusion matrix results indicate low misclassification rates. In addition, the model exhibits low inference time and fast convergence.

---

### TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics

Authors: Tobia Boschi, Andrea Loreti, Nicola C. Amorisco, Rodrigo H. Ordonez-Hurtado, Cécile Rousseau, George K. Holt, Eszter Székely, Alexander Whittle, Samuel Jackson, Adriano Agnello, Stanislas Pamela, Alessandra Pascale et al.
Published: 2026-02-16
Categories: physics.plasm-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.15084v2

We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model components. To represent multi-modal signals, we use a lightweight fixed-basis Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, which comprises 14 tasks with heterogeneous reconstruction and forecasting objectives. Our results show that fine-tuned TokaMind outperforms the strongest benchmark baseline on all but one task. Compared with training the same architecture from scratch under a matched epoch budget, warm-start adaptation is most beneficial on demanding downstream settings, including long-horizon forecasting and high-dimensional equilibrium objectives. These findings highlight the value of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights are publicly available at github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamind and huggingface.co/UKAEA-IBM-STFC, respectively.

---

### S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization

Authors: Zineb Lahrichi, Gaëtan Hadjeres, Gaël Richard, Geoffroy Peeters
Published: 2026-02-16
Categories: cs.SD, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2602.15082v2

Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods remain constrained to low-resolution audio and degrade substantially at very low bitrates, where audible artifacts are prominent. In this paper, we present S-PRESSO, a 48kHz sound effect compression model that produces both continuous and discrete embeddings at ultra-low bitrates, down to 0.096 kbps, via offline quantization. Our model relies on a pretrained latent diffusion model to decode compressed audio embeddings learned by a latent encoder. Leveraging the generative priors of the diffusion decoder, we achieve extremely low frame rates, down to 1Hz (750x compression rate), producing convincing and realistic reconstructions at the cost of exact fidelity. Despite operating at high compression rates, we demonstrate that S-PRESSO outperforms both continuous and discrete baselines in audio quality, acoustic similarity and reconstruction metrics.

---

### Near-Optimal Sample Complexity for Online Constrained MDPs

Authors: Chang Liu, Yunfan Li, Lin F. Yang
Published: 2026-02-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.15076v1

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used to enforce safety constraints while optimizing performance. However, existing methods often suffer from significant safety violations or require a high sample complexity to generate near-optimal policies. We address two settings: relaxed feasibility, where small violations are allowed, and strict feasibility, where no violation is allowed. We propose a model-based primal-dual algorithm that balances regret and bounded constraint violations, drawing on techniques from online RL and constrained optimization. For relaxed feasibility, we prove that our algorithm returns an $\varepsilon$-optimal policy with $\varepsilon$-bounded violation with arbitrarily high probability, requiring $\tilde{O}\left(\frac{SAH^3}{\varepsilon^2}\right)$ learning episodes, matching the lower bound for unconstrained MDPs. For strict feasibility, we prove that our algorithm returns an $\varepsilon$-optimal policy with zero violation with arbitrarily high probability, requiring $\tilde{O}\left(\frac{SAH^5}{\varepsilon^2ζ^2}\right)$ learning episodes, where $ζ$ is the problem-dependent Slater constant characterizing the size of the feasible region. This result matches the lower bound for learning CMDPs with access to a generative model. Our results demonstrate that learning CMDPs in an online setting is as easy as learning with a generative model and is no more challenging than learning unconstrained MDPs when small violations are allowed.

---

### Structure-Aware Piano Accompaniment via Style Planning and Dataset-Aligned Pattern Retrieval

Authors: Wanyu Zang, Yang Yu, Meng Yu
Published: 2026-02-16
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2602.15074v1

We introduce a structure-aware approach for symbolic piano accompaniment that decouples high-level planning from note-level realization. A lightweight transformer predicts an interpretable, per-measure style plan conditioned on section/phrase structure and functional harmony, and a retriever then selects and reharmonizes human-performed piano patterns from a corpus. We formulate retrieval as pattern matching under an explicit energy with terms for harmonic feasibility, structural-role compatibility, voice-leading continuity, style preferences, and repetition control. Given a structured lead sheet and optional keyword prompts, the system generates piano-accompaniment MIDI. In our experiments, transformer style-planner-guided retrieval produces diverse long-form accompaniments with strong style realization. We further analyze planner ablations and quantify inter-style isolation. Experimental results demonstrate the effectiveness of our inference-time approach for piano accompaniment generation.

---

### EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing

Authors: Yehonathan Litman, Shikun Liu, Dario Seyb, Nicholas Milef, Yang Zhou, Carl Marshall, Shubham Tulsiani, Caleb Leak
Published: 2026-02-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.15031v2

High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bottleneck, as they are often designed to inefficiently process the full video context regardless of the inpainting mask's size, even for sparse, localized edits. In this paper, we introduce EditCtrl, an efficient video inpainting control framework that focuses computation only where it is needed. Our approach features a novel local video context module that operates solely on masked tokens, yielding a computational cost proportional to the edit size. This local-first generation is then guided by a lightweight temporal global context embedder that ensures video-wide context consistency with minimal overhead. Not only is EditCtrl 10 times more compute efficient than state-of-the-art generative editing methods, it even improves editing quality compared to methods designed with full-attention. Finally, we showcase how EditCtrl unlocks new capabilities, including multi-region editing with text prompts and autoregressive content propagation.

---

### Image Generation with a Sphere Encoder

Authors: Kaiyu Yue, Menglin Jia, Ji Hou, Tom Goldstein
Published: 2026-02-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.15030v1

We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer than five steps. Our approach works by learning an encoder that maps natural images uniformly onto a spherical latent space, and a decoder that maps random latent vectors back to the image space. Trained solely through image reconstruction losses, the model generates an image by simply decoding a random point on the sphere. Our architecture naturally supports conditional generation, and looping the encoder/decoder a few times can further enhance image quality. Across several datasets, the sphere encoder approach yields performance competitive with state of the art diffusions, but with a small fraction of the inference cost. Project page is available at https://sphere-encoder.github.io .

---

### Symmetry in language statistics shapes the geometry of model representations

Authors: Dhruva Karkada, Daniel J. Korchinski, Andres Nava, Matthieu Wyart, Yasaman Bahri
Published: 2026-02-16
Categories: cs.LG, cond-mat.dis-nn, cs.CL
arXiv: https://arxiv.org/abs/2602.15029v3

The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe. To explain this neural code, we first show that language statistics exhibit translation symmetry (for example, the frequency with which any two months co-occur in text depends only on the time interval between them). We prove that this symmetry governs these geometric structures in high-dimensional word embedding models, and we analytically derive the manifold geometry of word representations. These predictions empirically match large text embedding models and large language models. Moreover, the representational geometry persists at moderate embedding dimension even when the relevant statistics are perturbed (e.g., by removing all sentences in which two months co-occur). We prove that this robustness emerges naturally when the co-occurrence statistics are controlled by an underlying latent variable. Our results indicate that these representational manifolds originate in the statistical symmetries of natural language.

---

### Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization

Authors: Shangding Gu
Published: 2026-02-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.15028v1

Large language models (LLMs) are increasingly deployed in privacy-critical and personalization-oriented scenarios, yet the role of context length in shaping privacy leakage and personalization effectiveness remains largely unexplored. We introduce a large-scale benchmark, PAPerBench, to systematically study how increasing context length influences both personalization quality and privacy protection in LLMs. The benchmark comprises approximately 29,000 instances with context lengths ranging from 1K to 256K tokens, yielding a total of 377K evaluation questions. It jointly evaluates personalization performance and privacy risks across diverse scenarios, enabling controlled analysis of long-context model behavior. Extensive evaluations across state-of-the-art LLMs reveal consistent performance degradation in both personalization and privacy as context length increases. We further provide a theoretical analysis of attention dilution under context scaling, explaining this behavior as an inherent limitation of soft attention in fixed-capacity Transformers. The empirical and theoretical findings together suggest a general scaling gap in current models -- long context, less focus. We release the benchmark to support reproducible evaluation and future research on scalable privacy and personalization. Code and data are available at https://github.com/SafeRL-Lab/PAPerBench

---

### Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation

Authors: Cai Zhou, Zijie Chen, Zian Li, Jike Wang, Kaiyi Jiang, Pan Li, Rose Yu, Muhan Zhang, Stephen Bates, Tommi Jaakkola
Published: 2026-02-16
Categories: cs.LG, cs.AI, math.GR, q-bio.BM
arXiv: https://arxiv.org/abs/2602.15022v1

Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equivariance through architectural constraints such as equivariant denoisers and invariant priors. In this paper, we challenge this tradition through the alternative canonicalization perspective: first map each sample to an orbit representative with a canonical pose or order, train an unconstrained (non-equivariant) diffusion or flow model on the canonical slice, and finally recover the invariant distribution by sampling a random symmetry transform at generation time. Building on a formal quotient-space perspective, our work provides a comprehensive theory of canonical diffusion by proving: (i) the correctness, universality and superior expressivity of canonical generative models over invariant targets; (ii) canonicalization accelerates training by removing diffusion score complexity induced by group mixtures and reducing conditional variance in flow matching. We then show that aligned priors and optimal transport act complementarily with canonicalization and further improves training efficiency. We instantiate the framework for molecular graph generation under $S_n \times SE(3)$ symmetries. By leveraging geometric spectra-based canonicalization and mild positional encodings, canonical diffusion significantly outperforms equivariant baselines in 3D molecule generation tasks, with similar or even less computation. Moreover, with a novel architecture Canon, CanonFlow achieves state-of-the-art performance on the challenging GEOM-DRUG dataset, and the advantage remains large in few-step generation.

---

### Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI

Authors: Xiaosheng Zhao, Yuan-Sen Ting, Rosemary F. G. Wyse, Alexander S. Szalay, Yang Huang, László Dobos, Tamás Budavári, Viska Wei
Published: 2026-02-16
Categories: astro-ph.SR, astro-ph.GA, cs.LG
arXiv: https://arxiv.org/abs/2602.15021v2

Cross-survey generalization is a critical challenge in stellar spectral analysis, particularly in cases such as transferring from low- to moderate-resolution surveys. We investigate this problem using pre-trained models, focusing on simple neural networks such as multilayer perceptrons (MLPs), with a case study transferring from LAMOST low-resolution spectra (LRS) to DESI medium-resolution spectra (MRS). Specifically, we pre-train MLPs on either LRS or their embeddings and fine-tune them for application to DESI stellar spectra. We compare MLPs trained directly on spectra with those trained on embeddings derived from transformer-based models (self-supervised foundation models pre-trained for multiple downstream tasks). We also evaluate different fine-tuning strategies, including residual-head fine-tuning, LoRA, and full fine-tuning. We find that MLPs pre-trained on LAMOST LRS achieve strong performance, even without fine-tuning, and that modest fine-tuning with DESI spectra further improves the results. For iron abundance, embeddings from a transformer-based model yield advantages in the metal-rich ((Fe/H) > -1.0) regime, but underperform in the metal-poor regime compared to MLPs trained directly on LRS. We also show that the optimal fine-tuning strategy depends on the specific stellar parameter under consideration. These results highlight that simple pre-trained MLPs can provide competitive cross-survey generalization, while the role of spectral foundation models for cross-survey stellar parameter estimation requires further exploration.

---

### Hunt Globally: Wide Search AI Agents for Drug Asset Scouting in Investing, Business Development, and Competitive Intelligence

Authors: Vlad Vinogradov, Alisa Vinogradova, Luba Greenwood, Ilya Yasny, Dmitry Kobyzev, Shoman Kasbekar, Kong Nguyen, Dmitrii Radkevich, Roman Doronin, Andrey Doronichev
Published: 2026-02-16
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.15019v5

Bio-pharmaceutical innovation has shifted: many new drug assets now originate outside the United States and are disclosed primarily via regional, non-English channels. Recent data suggests over 85% of patent filings originate outside the U.S., with China accounting for nearly half of the global total; a growing share of scholarly output is also non-U.S. Industry estimates put China at 30% of global drug development, spanning 1,200+ novel candidates. In this high-stakes environment, failing to surface "under-the-radar" assets creates multi-billion-dollar risk for investors and business development teams, making asset scouting a coverage-critical competition where speed and completeness drive value. Yet today's Deep Research AI agents still lag human experts in achieving high-recall discovery across heterogeneous, multilingual sources without hallucinations. We propose a benchmarking methodology for drug asset scouting and a tuned, tree-based self-learning Bioptic Agent aimed at complete, non-hallucinated scouting. We construct a challenging completeness benchmark using a multilingual multi-agent pipeline: complex user queries paired with ground-truth assets that are largely outside U.S.-centric radar. To reflect real deal complexity, we collected screening queries from expert investors, BD, and VC professionals, and used them as priors to conditionally generate benchmark queries. For grading, we use LLM-as-judge evaluation calibrated to expert opinions. On this benchmark, our Bioptic Agent achieves 79.7% F1 score, outperforming Gemini 3.1 Deep Think (59.2%), Gemini 3.1 Pro Deep Research (58.6%), Claude Opus 4.6 (56.2%), OpenAI GPT-5.2 Pro (46.6%), Perplexity Deep Research (44.2%), and Exa Websets (26.9%). Performance improves steeply with additional compute, supporting the view that more compute yields better results.

---

### Neurosim: A Fast Simulator for Neuromorphic Robot Perception

Authors: Richeek Das, Pratik Chaudhari
Published: 2026-02-16
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.15018v2

Neurosim is a fast, real-time, high-performance library for simulating sensors such as dynamic vision sensors, RGB cameras, depth sensors, and inertial sensors. It can also simulate agile dynamics of multi-rotor vehicles in complex and dynamic environments. Neurosim can achieve frame rates as high as ~2700 FPS on a desktop GPU. Neurosim integrates with a ZeroMQ-based communication library called Cortex to facilitate seamless integration with machine learning and robotics workflows. Cortex provides a high-throughput, low-latency message-passing system for Python and C++ applications, with native support for NumPy arrays and PyTorch tensors. This paper discusses the design philosophy behind Neurosim and Cortex. It demonstrates how they can be used to (i) train neuromorphic perception and control algorithms, e.g., using self-supervised learning on time-synchronized multi-modal data, and (ii) test real-time implementations of these algorithms in closed-loop. Neurosim and Cortex are available at https://github.com/grasp-lyrl/neurosim .

---

### Scaling Beyond Masked Diffusion Language Models

Authors: Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux, Jingyu Liu, John Thickstun, Ante Jukic
Published: 2026-02-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.15014v1

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on language modeling benchmarks. In this work, we present the first scaling law study of uniform-state and interpolating discrete diffusion methods. We also show that Masked diffusion models can be made approximately 12% more FLOPs-efficient when trained with a simple cross-entropy objective. We find that perplexity is informative within a diffusion family but can be misleading across families, where models with worse likelihood scaling may be preferable due to faster and more practical sampling, as reflected by the speed-quality Pareto frontier. These results challenge the view that Masked diffusion is categorically the future of diffusion language modeling and that perplexity alone suffices for cross-algorithm comparison. Scaling all methods to 1.7B parameters, we show that uniform-state diffusion remains competitive on likelihood-based benchmarks and outperforms autoregressive and Masked diffusion models on GSM8K, despite worse validation perplexity. We provide the code, model checkpoints, and video tutorials on the project page: http://s-sahoo.github.io/scaling-dllms

---

### Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation

Authors: Ruoxi Liu, Philipp Koehn
Published: 2026-02-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.15013v1

This paper proposes a novel method for Text Style Transfer (TST) based on parameter-efficient fine-tuning of Large Language Models (LLMs). Addressing the scarcity of parallel corpora that map between styles, the study employs roundtrip translation to synthesize such parallel datasets from monolingual corpora. This approach creates 'neutralized' text devoid of stylistic attributes, essentially creating a shared input style at training-time and inference-time. Experimental results demonstrate consistent superiority of this method over zero-shot prompting and fewshot ICL techniques measured by BLEU scores and style accuracy scores across four investigated domains. Furthermore, the integration of retrieval-augmented generation (RAG) for terminology and name knowledge enhances robustness and stylistic consistency.

---

### Cold-Start Personalization via Training-Free Priors from Structured World Models

Authors: Avinandan Bose, Shuyue Stella Li, Faeze Brahman, Pang Wei Koh, Simon Shaolei Du, Yulia Tsvetkov, Maryam Fazel, Lin Xiao, Asli Celikyilmaz
Published: 2026-02-16
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.15012v1

Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available. The core challenge is a routing problem: each task admits dozens of preference dimensions, yet individual users care about only a few, and which ones matter depends on who is asking. With a limited question budget, asking without structure will miss the dimensions that matter. Reinforcement learning is the natural formulation, but in multi-turn settings its terminal reward fails to exploit the factored, per-criterion structure of preference data, and in practice learned policies collapse to static question sequences that ignore user responses. We propose decomposing cold-start elicitation into offline structure learning and online Bayesian inference. Pep (Preference Elicitation with Priors) learns a structured world model of preference correlations offline from complete profiles, then performs training-free Bayesian inference online to select informative questions and predict complete preference profiles, including dimensions never asked about. The framework is modular across downstream solvers and requires only simple belief models. Across medical, mathematical, social, and commonsense reasoning, Pep achieves 80.8% alignment between generated responses and users' stated preferences versus 68.5% for RL, with 3-5x fewer interactions. When two users give different answers to the same question, Pep changes its follow-up 39-62% of the time versus 0-28% for RL. It does so with ~10K parameters versus 8B for RL, showing that the bottleneck in cold-start elicitation is the capability to exploit the factored structure of preference data.

---

### BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames

Authors: Max Sobol Mark, Jacky Liang, Maria Attarian, Chuyuan Fu, Debidatta Dwibedi, Dhruv Shah, Aviral Kumar
Published: 2026-02-16
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.15010v2

Many robot tasks require attending to the history of past observations. For example, finding an item in a room requires remembering which places have already been searched. However, the best-performing robot policies typically condition only on the current observation, limiting their applicability to such tasks. Naively conditioning on past observations often fails due to spurious correlations: policies latch onto incidental features of training histories that do not generalize to out-of-distribution trajectories upon deployment. We analyze why policies latch onto these spurious correlations and find that this problem stems from limited coverage over the space of possible histories during training, which grows exponentially with horizon. Existing regularization techniques provide inconsistent benefits across tasks, as they do not fundamentally address this coverage problem. Motivated by these findings, we propose Big Picture Policies (BPP), an approach that conditions on a minimal set of meaningful keyframes detected by a vision-language model. By projecting diverse rollouts onto a compact set of task-relevant events, BPP substantially reduces distribution shift between training and deployment, without sacrificing expressivity. We evaluate BPP on four challenging real-world manipulation tasks and three simulation tasks, all requiring history conditioning. BPP achieves 70% higher success rates than the best comparison on real-world evaluations. Videos are available at https://bigpicturepolicies.github.io/

---

### Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees

Authors: Daniil Dmitriev, Zhihan Huang, Yuting Wei
Published: 2026-02-16
Categories: cs.LG, cs.IT, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.15008v2

Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling efficiency of score-based discrete diffusion models under a continuous-time Markov chain (CTMC) formulation, with a focus on $τ$-leaping-based samplers. We establish sharp convergence guarantees for attaining $\varepsilon$ accuracy in Kullback-Leibler (KL) divergence for both uniform and masking noising processes. For uniform discrete diffusion, we show that the $τ$-leaping algorithm achieves an iteration complexity of order $\tilde O(d/\varepsilon)$, with $d$ the ambient dimension of the target distribution, eliminating linear dependence on the vocabulary size $S$ and improving existing bounds by a factor of $d$; moreover, we establish a matching algorithmic lower bound showing that linear dependence on the ambient dimension is unavoidable in general. For masking discrete diffusion, we introduce a modified $τ$-leaping sampler whose convergence rate is governed by an intrinsic information-theoretic quantity, termed the effective total correlation, which is bounded by $d \log S$ but can be sublinear or even constant for structured data. As a consequence, the sampler provably adapts to low-dimensional structure without prior knowledge or algorithmic modification, yielding sublinear convergence rates for various practical examples (such as hidden Markov models, image data, and random graphs). Our analysis requires no boundedness or smoothness assumptions on the score estimator beyond control of the score entropy loss.

---

### Distributed Quantum Gaussian Processes for Multi-Agent Systems

Authors: Meet Gandhi, George P. Kontoudis
Published: 2026-02-16
Categories: cs.MA, cs.LG, math.DG
arXiv: https://arxiv.org/abs/2602.15006v2

Gaussian Processes (GPs) are a powerful tool for probabilistic modeling, but their performance is often constrained in complex, large-scale real-world domains due to the limited expressivity of classical kernels. Quantum computing offers the potential to overcome this limitation by embedding data into exponentially large Hilbert spaces, capturing complex correlations that remain inaccessible to classical computing approaches. In this paper, we propose a Distributed Quantum Gaussian Process (DQGP) method in a multi-agent setting to enhance modeling capabilities and scalability. To address the challenging non-Euclidean optimization problem, we develop a Distributed consensus Riemannian Alternating Direction Method of Multipliers (DR-ADMM) algorithm that aggregates local agent models into a global model. We evaluate the efficacy of our method through numerical experiments conducted on a quantum simulator in classical hardware. We use real-world, non-stationary elevation datasets of NASA's Shuttle Radar Topography Mission and synthetic datasets generated by Quantum Gaussian Processes. Beyond modeling advantages, our framework highlights potential computational speedups that quantum hardware may provide, particularly in Gaussian processes and distributed optimization.

---

### Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation

Authors: Mengdan Zhu, Yufan Zhao, Tao Di, Yulan Yan, Liang Zhao
Published: 2026-02-16
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.15005v1

News recommendation plays a critical role in online news platforms by helping users discover relevant content. Cross-domain news recommendation further requires inferring user's underlying information needs from heterogeneous signals that often extend beyond direct news consumption. A key challenge lies in moving beyond surface-level behaviors to capture deeper, reusable user interests while maintaining scalability in large-scale production systems. In this paper, we present a reinforcement learning framework that trains large language models to generate high-quality lists of interest-driven news search queries from cross-domain user signals. We formulate query-list generation as a policy optimization problem and employ GRPO with multiple reward signals. We systematically study two compute dimensions: inference-time sampling and model capacity, and empirically observe consistent improvements with increased compute that exhibit scaling-like behavior. Finally, we perform on-policy distillation to transfer the learned policy from a large, compute-intensive teacher to a compact student model suitable for scalable deployment. Extensive offline experiments, ablation studies and large-scale online A/B tests in a production news recommendation system demonstrate consistent gains in both interest modeling quality and downstream recommendation performance.

---

### PDE foundation models are skillful AI weather emulators for the Martian atmosphere

Authors: Johannes Schmude, Sujit Roy, Liping Wang, Theodore van Kessel, Levente Klein, Marcus Freitag, Eloisa Bentivegna, Robert Manson-Sawko, Bjorn Lutjens, Manil Maskey, Campbell Watson, Rahul Ramachandran et al.
Published: 2026-02-16
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2602.15004v1

We show that AI foundation models that are pretrained on numerical solutions to a diverse corpus of partial differential equations can be adapted and fine-tuned to obtain skillful predictive weather emulators for the Martian atmosphere. We base our work on the Poseidon PDE foundation model for two-dimensional systems. We develop a method to extend Poseidon from two to three dimensions while keeping the pretraining information. Moreover, we investigate the performance of the model in the presence of sparse initial conditions. Our results make use of four Martian years (approx.~34 GB) of training data and a median compute budget of 13 GPU hours. We find that the combination of pretraining and model extension yields a performance increase of 34.4\% on a held-out year. This shows that PDEs-FMs can not only approximate solutions to (other) PDEs but also anchor models for real-world problems with complex interactions that lack a sufficient amount of training data or a suitable compute budget.

---

### Boundary Point Jailbreaking of Black-Box LLMs

Authors: Xander Davies, Giorgi Giglemiani, Edmund Lau, Eric Winsor, Geoffrey Irving, Yarin Gal
Published: 2026-02-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.15001v2

Frontier LLMs are safeguarded against attempts to extract harmful information via adversarial prompts known as "jailbreaks". Recently, defenders have developed classifier-based systems that have survived thousands of hours of human red teaming. We introduce Boundary Point Jailbreaking (BPJ), a new class of automated jailbreak attacks that evade the strongest industry-deployed safeguards. Unlike previous attacks that rely on white/grey-box assumptions (such as classifier scores or gradients) or libraries of existing jailbreaks, BPJ is fully black-box and uses only a single bit of information per query: whether or not the classifier flags the interaction. To achieve this, BPJ addresses the core difficulty in optimising attacks against robust real-world defences: evaluating whether a proposed modification to an attack is an improvement. Instead of directly trying to learn an attack for a target harmful string, BPJ converts the string into a curriculum of intermediate attack targets and then actively selects evaluation points that best detect small changes in attack strength ("boundary points"). We believe BPJ is the first fully automated attack algorithm that succeeds in developing universal jailbreaks against Constitutional Classifiers, as well as the first automated attack algorithm that succeeds against GPT-5's input classifier without relying on human attack seeds. BPJ is difficult to defend against in individual interactions but incurs many flags during optimisation, suggesting that effective defence requires supplementing single-interaction methods with batch-level monitoring.

---

### Spectral Convolution on Orbifolds for Geometric Deep Learning

Authors: Tim Mangliers, Bernhard Mössner, Benjamin Himpel
Published: 2026-02-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.14997v2

Geometric deep learning (GDL) deals with supervised learning on data domains that go beyond Euclidean structure, such as data with graph or manifold structure. Due to the demand that arises from application-related data, there is a need to identify further topological and geometric structures with which these use cases can be made accessible to machine learning. There are various techniques, such as spectral convolution, that form the basic building blocks for some convolutional neural network-like architectures on non-Euclidean data. In this paper, the concept of spectral convolution on orbifolds is introduced. This provides a building block for making learning on orbifold structured data accessible using GDL. The theory discussed is illustrated using an example from music theory.

---

### On the Semantics of Primary Cause in Hybrid Dynamic Domains

Authors: Shakil M. Khan, Asim Mehmood, Sandra Zilles
Published: 2026-02-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.14994v1

Reasoning about actual causes of observed effects is fundamental to the study of rationality. This important problem has been studied since the time of Aristotle, with formal mathematical accounts emerging recently. We live in a world where change due to actions can be both discrete and continuous, that is, hybrid. Yet, despite extensive research on actual causation, only few recent studies looked into causation with continuous change. Building on recent progress, in this paper we propose two definitions of primary cause in a hybrid action-theoretic framework, namely the hybrid temporal situation calculus. One of these is foundational in nature while the other formalizes causation through contributions, which can then be verified from a counterfactual perspective using a modified ``but-for'' test. We prove that these two definitions are indeed equivalent. We then show that our definitions of causation have some intuitively justifiable properties.

---

### ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery

Authors: Ayush Shrivastava, Kirtan Gangani, Laksh Jain, Mayank Goel, Nipun Batra
Published: 2026-02-16
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.14989v1

Vision language models (VLMs) achieve strong performance on RGB imagery, but they do not generalize to thermal images. Thermal sensing plays a critical role in settings where visible light fails, including nighttime surveillance, search and rescue, autonomous driving, and medical screening. Unlike RGB imagery, thermal images encode physical temperature rather than color or texture, requiring perceptual and reasoning capabilities that existing RGB-centric benchmarks do not evaluate. We introduce ThermEval-B, a structured benchmark of approximately 55,000 thermal visual question answering pairs designed to assess the foundational primitives required for thermal vision language understanding. ThermEval-B integrates public datasets with our newly collected ThermEval-D, the first dataset to provide dense per-pixel temperature maps with semantic body-part annotations across diverse indoor and outdoor environments. Evaluating 25 open-source and closed-source VLMs, we find that models consistently fail at temperature-grounded reasoning, degrade under colormap transformations, and default to language priors or fixed responses, with only marginal gains from prompting or supervised fine-tuning. These results demonstrate that thermal understanding requires dedicated evaluation beyond RGB-centric assumptions, positioning ThermEval as a benchmark to drive progress in thermal vision language modeling.

---

### Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations

Authors: Carolin Cissee, Raneen Younis, Zahra Ahmadi
Published: 2026-02-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.14983v1

Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal contrastive learning has achieved remarkable progress, most existing methods predominantly capture redundant cross-modal signals, often neglecting modality-specific (unique) and interaction-driven (synergistic) information. Recent extensions broaden this perspective, yet they either fail to explicitly model synergistic interactions or learn different information components in an entangled manner, leading to incomplete representations and potential information leakage. We introduce \textbf{COrAL}, a principled framework that explicitly and simultaneously preserves redundant, unique, and synergistic information within multimodal representations. COrAL employs a dual-path architecture with orthogonality constraints to disentangle shared and modality-specific features, ensuring a clean separation of information components. To promote synergy modeling, we introduce asymmetric masking with complementary view-specific patterns, compelling the model to infer cross-modal dependencies rather than rely solely on redundant cues. Extensive experiments on synthetic benchmarks and diverse MultiBench datasets demonstrate that COrAL consistently matches or outperforms state-of-the-art methods while exhibiting low performance variance across runs. These results indicate that explicitly modeling the full spectrum of multimodal information yields more stable, reliable, and comprehensive embeddings.

---

### Block Empirical Likelihood Inference for Longitudinal Generalized Partially Linear Single-Index Models

Authors: Tianni Zhang, Yuyao Wang, Yu Lu, Mengfei Ran
Published: 2026-02-16
Categories: stat.ME, math.ST, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2602.14981v2

Generalized partially linear single-index models (GPLSIMs) provide a flexible and interpretable semiparametric framework for longitudinal outcomes by combining a low-dimensional parametric component with a nonparametric index component. For repeated measurements, valid inference is challenging because within-subject correlation induces nuisance parameters and variance estimation can be unstable in semiparametric settings. We propose a profile estimating-equation approach based on spline approximation of the unknown link function and construct a subject-level block empirical likelihood (BEL) for joint inference on the parametric coefficients and the single-index direction. The resulting BEL ratio statistic enjoys a Wilks-type chi-square limit, yielding likelihood-free confidence regions without explicit sandwich variance estimation. We also discuss practical implementation, including constrained optimization for the index parameter, working-correlation choices, and bootstrap-based confidence bands for the nonparametric component. Simulation studies and an application to the epilepsy longitudinal study illustrate the finite-sample performance.

---

### MacroGuide: Topological Guidance for Macrocycle Generation

Authors: Alicja Maksymiuk, Alexandre Duplessis, Michael Bronstein, Alexander Tong, Fernanda Duarte, İsmail İlkan Ceylan
Published: 2026-02-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.14977v1

Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public datasets and the challenges of enforcing topological constraints in standard deep generative models. We introduce MacroGuide: Topological Guidance for Macrocycle Generation, a diffusion guidance mechanism that uses Persistent Homology to steer the sampling of pretrained molecular generative models toward the generation of macrocycles, in both unconditional and conditional (protein pocket) settings. At each denoising step, MacroGuide constructs a Vietoris-Rips complex from atomic positions and promotes ring formation by optimizing persistent homology features. Empirically, applying MacroGuide to pretrained diffusion models increases macrocycle generation rates from 1% to 99%, while matching or exceeding state-of-the-art performance on key quality metrics such as chemical validity, diversity, and PoseBusters checks.

---

### Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces

Authors: Nicolaï Gouraud, Côme Cattin, Thomas Plé, Olivier Adjoua, Louis Lagardère, Jean-Philip Piquemal
Published: 2026-02-16
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.14975v3

Following our previous work (J. Phys. Chem. Lett., 2026, 17, 5, 1288-1295), we propose the DMTS-NC approach, a distilled multi-time-step (DMTS) strategy using non-conservative (NC) forces to further accelerate atomistic molecular dynamics simulations using foundation neural network models such as FeNNix-Bio1. There, a dual-level reversible reference system propagator algorithm (RESPA) formalism couples a target accurate conservative potential to a simplified distilled representation optimized for the production of non-conservative forces. Despite being non-conservative, the distilled architecture is designed to enforce key physical priors, such as equivariance under rotation and cancellation of atomic force components. These choices facilitate the distillation process and therefore improve drastically the robustness of simulation, significantly limiting abnormal discrepancies between the two models, thus achieving excellent agreement with the forces data. Overall, the DMTS-NC scheme is found to be more stable and efficient than its conservative counterpart with additional speedups reaching 15-30% over DMTS. Requiring no fine-tuning steps, it is easier to implement and can be pushed to the limit of the systems physical resonances to maintain accuracy while providing maximum efficiency. We obtain additional speedup by combining hydrogen mass repartitioning (HMR), High Hydrogen Friction (HHF) to further extended the largest timestep up to 10fs of our schemes while conserving stability and accuracy. As for DMTS, DMTS-NC is applicable to any neural network potential and can be applied to approaches that are computationally heavier than FeNNix-Bio1. We show a proof of principle applying the approach to the distillation of MACE-OFF23 with consequent speedups ranging from 3.66 to 5.64 compared to single timestep.

---

### Use What You Know: Causal Foundation Models with Partial Graphs

Authors: Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Schölkopf
Published: 2026-02-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.14972v3

Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions. Recently proposed Causal Foundation Models (CFMs) promise a more unified approach by amortising causal discovery and inference in a single step. However, in their current state, they do not allow for the incorporation of any domain knowledge, which can lead to suboptimal predictions. We bridge this gap by introducing methods to condition CFMs on causal information, such as the causal graph or more readily available ancestral information. When access to complete causal graph information is too strict a requirement, our approach also effectively leverages partial causal information. We systematically evaluate conditioning strategies and find that injecting learnable biases into the attention mechanism, together with a graph-convolutional encoder, is a highly effective method to utilise full and partial causal information. Our experiments show that this conditioning allows a general-purpose CFM to match the performance of specialised models trained on specific causal structures. Overall, our approach addresses a central hurdle on the path towards all-in-one causal foundation models: the capability to answer causal queries in a data-driven manner while effectively leveraging any amount of domain expertise.

---

### Use What You Know: Causal Foundation Models with Partial Graphs

Authors: Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Schölkopf
Published: 2026-02-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.14972v2

Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions. Recently proposed Causal Foundation Models (CFMs) promise a more unified approach by amortising causal discovery and inference in a single step. However, in their current state, they do not allow for the incorporation of any domain knowledge, which can lead to suboptimal predictions. We bridge this gap by introducing methods to condition CFMs on causal information, such as the causal graph or more readily available ancestral information. When access to complete causal graph information is too strict a requirement, our approach also effectively leverages partial causal information. We systematically evaluate conditioning strategies and find that injecting learnable biases into the attention mechanism, together with a graph-convolutional encoder, is a highly effective method to utilise full and partial causal information. Our experiments show that this conditioning allows a general-purpose CFM to match the performance of specialised models trained on specific causal structures. Overall, our approach addresses a central hurdle on the path towards all-in-one causal foundation models: the capability to answer causal queries in a data-driven manner while effectively leveraging any amount of domain expertise.

---

### Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance System

Authors: Kawin Mayilvaghanan, Siddhant Gupta, Ayush Kumar
Published: 2026-02-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.14970v1

Large Language Models (LLMs) are increasingly deployed in contact-center Quality Assurance (QA) to automate agent performance evaluation and coaching feedback. While LLMs offer unprecedented scalability and speed, their reliance on web-scale training data raises concerns regarding demographic and behavioral biases that may distort workforce assessment. We present a counterfactual fairness evaluation of LLM-based QA systems across 13 dimensions spanning three categories: Identity, Context, and Behavioral Style. Fairness is quantified using the Counterfactual Flip Rate (CFR), the frequency of binary judgment reversals, and the Mean Absolute Score Difference (MASD), the average shift in coaching or confidence scores across counterfactual pairs. Evaluating 18 LLMs on 3,000 real-world contact center transcripts, we find systematic disparities, with CFR ranging from 5.4% to 13.0% and consistent MASD shifts across confidence, positive, and improvement scores. Larger, more strongly aligned models show lower unfairness, though fairness does not track accuracy. Contextual priming of historical performance induces the most severe degradations (CFR up to 16.4%), while implicit linguistic identity cues remain a persistent bias source. Finally, we analyze the efficacy of fairness-aware prompting, finding that explicit instructions yield only modest improvements in evaluative consistency. Our findings underscore the need for standardized fairness auditing pipelines prior to deploying LLMs in high-stakes workforce evaluation.

---

### PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement

Authors: Yian Wang, Han Yang, Minghao Guo, Xiaowen Qiu, Tsun-Hsuan Wang, Wojciech Matusik, Joshua B. Tenenbaum, Chuang Gan
Published: 2026-02-16
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.14968v1

Automatically generating interactive 3D environments is crucial for scaling up robotic data collection in simulation. While prior work has primarily focused on 3D asset placement, it often overlooks the physical relationships between objects (e.g., contact, support, balance, and containment), which are essential for creating complex and realistic manipulation scenarios such as tabletop arrangements, shelf organization, or box packing. Compared to classical 3D layout generation, producing complex physical scenes introduces additional challenges: (a) higher object density and complexity (e.g., a small shelf may hold dozens of books), (b) richer supporting relationships and compact spatial layouts, and (c) the need to accurately model both spatial placement and physical properties. To address these challenges, we propose PhyScensis, an LLM agent-based framework powered by a physics engine, to produce physically plausible scene configurations with high complexity. Specifically, our framework consists of three main components: an LLM agent iteratively proposes assets with spatial and physical predicates; a solver, equipped with a physics engine, realizes these predicates into a 3D scene; and feedback from the solver informs the agent to refine and enrich the configuration. Moreover, our framework preserves strong controllability over fine-grained textual descriptions and numerical parameters (e.g., relative positions, scene stability), enabled through probabilistic programming for stability and a complementary heuristic that jointly regulates stability and spatial relations. Experimental results show that our method outperforms prior approaches in scene complexity, visual quality, and physical accuracy, offering a unified pipeline for generating complex physical scene layouts for robotic manipulation.

---

### PAct: Part-Decomposed Single-View Articulated Object Generation

Authors: Qingming Liu, Xinyue Yao, Shuyuan Zhang, Yueci Deng, Guiliang Liu, Zhen Liu, Kui Jia
Published: 2026-02-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.14965v1

Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential. Yet producing high-fidelity articulated assets remains difficult to scale because it requires reliable part decomposition and kinematic rigging. Existing approaches largely fall into two paradigms: optimization-based reconstruction or distillation, which can be accurate but often takes tens of minutes to hours per instance, and inference-time methods that rely on template or part retrieval, producing plausible results that may not match the specific structure and appearance in the input observation. We introduce a part-centric generative framework for articulated object creation that synthesizes part geometry, composition, and articulation under explicit part-aware conditioning. Our representation models an object as a set of movable parts, each encoded by latent tokens augmented with part identity and articulation cues. Conditioned on a single image, the model generates articulated 3D assets that preserve instance-level correspondence while maintaining valid part structure and motion. The resulting approach avoids per-instance optimization, enables fast feed-forward inference, and supports controllable assembly and articulation, which are important for embodied interaction. Experiments on common articulated categories (e.g., drawers and doors) show improved input consistency, part accuracy, and articulation plausibility over optimization-based and retrieval-driven baselines, while substantially reducing inference time.

---

### Tool-Aware Planning in Contact Center AI: Evaluating LLMs through Lineage-Guided Query Decomposition

Authors: Varun Nathan, Shreyas Guha, Ayush Kumar
Published: 2026-02-16
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2602.14955v1

We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools (Text2SQL (T2S)/Snowflake) and unstructured tools (RAG/transcripts) with explicit depends_on for parallelism. Our contributions are threefold: (i) a reference-based plan evaluation framework operating in two modes - a metric-wise evaluator spanning seven dimensions (e.g., tool-prompt alignment, query adherence) and a one-shot evaluator; (ii) a data curation methodology that iteratively refines plans via an evaluator->optimizer loop to produce high-quality plan lineages (ordered plan revisions) while reducing manual effort; and (iii) a large-scale study of 14 LLMs across sizes and families for their ability to decompose queries into step-by-step, executable, and tool-assigned plans, evaluated under prompts with and without lineage. Empirically, LLMs struggle on compound queries and on plans exceeding 4 steps (typically 5-15); the best total metric score reaches 84.8% (Claude-3-7-Sonnet), while the strongest one-shot match rate at the "A+" tier (Extremely Good, Very Good) is only 49.75% (o3-mini). Plan lineage yields mixed gains overall but benefits several top models and improves step executability for many. Our results highlight persistent gaps in tool-understanding, especially in tool-prompt alignment and tool-usage completeness, and show that shorter, simpler plans are markedly easier. The framework and findings provide a reproducible path for assessing and improving agentic planning with tools for answering data-analysis queries in contact-center settings.

---

### Locally Adaptive Multi-Objective Learning

Authors: Jivat Neet Kaur, Isaac Gibbs, Michael I. Jordan
Published: 2026-02-16
Categories: cs.LG, math.OC, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.14952v1

We consider the general problem of learning a predictor that satisfies multiple objectives of interest simultaneously, a broad framework that captures a range of specific learning goals including calibration, regret, and multiaccuracy. We work in an online setting where the data distribution can change arbitrarily over time. Existing approaches to this problem aim to minimize the set of objectives over the entire time horizon in a worst-case sense, and in practice they do not necessarily adapt to distribution shifts. Earlier work has aimed to alleviate this problem by incorporating additional objectives that target local guarantees over contiguous subintervals. Empirical evaluation of these proposals is, however, scarce. In this article, we consider an alternative procedure that achieves local adaptivity by replacing one part of the multi-objective learning method with an adaptive online algorithm. Empirical evaluations on datasets from energy forecasting and algorithmic fairness show that our proposed method improves upon existing approaches and achieves unbiased predictions over subgroups, while remaining robust under distribution shift.

---

### Gradient Networks for Universal Magnetic Modeling of Synchronous Machines

Authors: Junyi Li, Tim Foissner, Floran Martin, Antti Piippo, Marko Hinkkanen
Published: 2026-02-16
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2602.14947v4

This paper presents a physics-constrained neural network framework for magnetic modeling of saturable synchronous machines, including spatial harmonics. By embedding gradient networks into the machine equations to model conservative electromagnetic behavior, the framework satisfies reciprocity and energy conservation by construction, while universally approximating any physically feasible magnetic characteristic. Unlike lookup tables and black-box neural networks, it guarantees monotonicity, invertibility, and smooth outputs, and remains highly data efficient. The method is validated using measured and finite-element method (FEM) data from a 5.6-kW permanent-magnet (PM) synchronous reluctance machine, and is demonstrated in real-time closed-loop control on an embedded platform. The results confirm accurate, physically consistent, and computationally efficient performance.

---

### Gradient Networks for Universal Magnetic Modeling of Synchronous Machines

Authors: Junyi Li, Tim Foissner, Floran Martin, Antti Piippo, Marko Hinkkanen
Published: 2026-02-16
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2602.14947v3

This paper presents a physics-constrained neural network framework for dynamic modeling of saturable synchronous machines, including spatial harmonics. The proposed architecture embeds gradient networks directly into the fundamental machine equations to model nonlinear, coupled electromagnetic behavior. By learning the gradient of magnetic field energy, the model satisfies reciprocity and energy-balance constraints by construction. The approach can universally approximate any physically feasible magnetic characteristics while offering key advantages over lookup tables and conventional black-box networks: monotonicity, smooth outputs, and improved generalization from limited data. These properties also support robust model inversion and trajectory optimization for control. The method is validated using measured and finite-element-method (FEM) data from a 5.6-kW permanent-magnet (PM) synchronous reluctance machine and is further demonstrated experimentally in real-time closed-loop operation on an embedded control platform. The results show accurate and physically consistent modeling performance, even with limited training data.

---

### AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories

Authors: Zun Wang, Han Lin, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal
Published: 2026-02-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.14941v2

Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering anchor videos from the reconstructed geometry in the history. However, reconstructing a global 3D scene from multiple views inevitably introduces cross-view misalignment, as pose and depth estimation errors cause the same surfaces to be reconstructed at slightly different 3D locations across views. When fused, these inconsistencies accumulate into noisy geometry that contaminates the conditioning signals and degrades generation quality. We introduce AnchorWeave, a memory-augmented video generation framework that replaces a single misaligned global memory with multiple clean local geometric memories and learns to reconcile their cross-view inconsistencies. To this end, AnchorWeave performs coverage-driven local memory retrieval aligned with the target trajectory and integrates the selected local memories through a multi-anchor weaving controller during generation. Extensive experiments demonstrate that AnchorWeave significantly improves long-term scene consistency while maintaining strong visual quality, with ablation and analysis studies further validating the effectiveness of local geometric conditioning, multi-anchor control, and coverage-driven retrieval.

---

### AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories

Authors: Zun Wang, Han Lin, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal
Published: 2026-02-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.14941v1

Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering anchor videos from the reconstructed geometry in the history. However, reconstructing a global 3D scene from multiple views inevitably introduces cross-view misalignment, as pose and depth estimation errors cause the same surfaces to be reconstructed at slightly different 3D locations across views. When fused, these inconsistencies accumulate into noisy geometry that contaminates the conditioning signals and degrades generation quality. We introduce AnchorWeave, a memory-augmented video generation framework that replaces a single misaligned global memory with multiple clean local geometric memories and learns to reconcile their cross-view inconsistencies. To this end, AnchorWeave performs coverage-driven local memory retrieval aligned with the target trajectory and integrates the selected local memories through a multi-anchor weaving controller during generation. Extensive experiments demonstrate that AnchorWeave significantly improves long-term scene consistency while maintaining strong visual quality, with ablation and analysis studies further validating the effectiveness of local geometric conditioning, multi-anchor control, and coverage-driven retrieval.

---

### Fault Detection in Electrical Distribution System using Autoencoders

Authors: Sidharthenee Nayak, Victor Sam Moses Babu, Chandrashekhar Narayan Bhende, Pratyush Chakraborty, Mayukha Pal
Published: 2026-02-16
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2602.14939v1

In recent times, there has been considerable interest in fault detection within electrical power systems, garnering attention from both academic researchers and industry professionals. Despite the development of numerous fault detection methods and their adaptations over the past decade, their practical application remains highly challenging. Given the probabilistic nature of fault occurrences and parameters, certain decision-making tasks could be approached from a probabilistic standpoint. Protective systems are tasked with the detection, classification, and localization of faulty voltage and current line magnitudes, culminating in the activation of circuit breakers to isolate the faulty line. An essential aspect of designing effective fault detection systems lies in obtaining reliable data for training and testing, which is often scarce. Leveraging deep learning techniques, particularly the powerful capabilities of pattern classifiers in learning, generalizing, and parallel processing, offers promising avenues for intelligent fault detection. To address this, our paper proposes an anomaly-based approach for fault detection in electrical power systems, employing deep autoencoders. Additionally, we utilize Convolutional Autoencoders (CAE) for dimensionality reduction, which, due to its fewer parameters, requires less training time compared to conventional autoencoders. The proposed method demonstrates superior performance and accuracy compared to alternative detection approaches by achieving an accuracy of 97.62% and 99.92% on simulated and publicly available datasets.

---

### Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients

Authors: Martin Van Waerebeke, Marco Lorenzi, Kevin Scaman, El Mahdi El Mhamdi, Giovanni Neglia
Published: 2026-02-16
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.14938v1

In machine unlearning, $(\varepsilon,δ)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex objectives, existing first-order methods achieve $(\varepsilon,δ)-$unlearning, but they only use the forget set to calibrate injected noise, never as a direct optimization signal. In contrast, efficient empirical heuristics often exploit the forget samples (e.g., via gradient ascent) but come with no formal unlearning guarantees. We bridge this gap by presenting the Variance-Reduced Unlearning (VRU) algorithm. To the best of our knowledge, VRU is the first first-order algorithm that directly includes forget set gradients in its update rule, while provably satisfying ($(\varepsilon,δ)-$unlearning. We establish the convergence of VRU and show that incorporating the forget set yields strictly improved rates, i.e. a better dependence on the achieved error compared to existing first-order $(\varepsilon,δ)-$unlearning methods. Moreover, we prove that, in a low-error regime, VRU asymptotically outperforms any first-order method that ignores the forget set.Experiments corroborate our theory, showing consistent gains over both state-of-the-art certified unlearning methods and over empirical baselines that explicitly leverage the forget set.

---

### Activation-Space Uncertainty Quantification for Pretrained Networks

Authors: Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez, Jonathan Plenk, Alvaro Cartea, Jose Miguel Hernández-Lobato
Published: 2026-02-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.14934v2

Reliable uncertainty estimates are crucial for deploying pretrained models; yet, many strong methods for quantifying uncertainty require retraining, Monte Carlo sampling, or expensive second-order computations and may alter a frozen backbone's predictions. To address this, we introduce Gaussian Process Activations (GAPA), a post-hoc method that shifts Bayesian modeling from weights to activations. GAPA replaces standard nonlinearities with Gaussian-process activations whose posterior mean exactly matches the original activation, preserving the backbone's point predictions by construction while providing closed-form epistemic variances in activation space. To scale to modern architectures, we use a sparse variational inducing-point approximation over cached training activations, combined with local k-nearest-neighbor subset conditioning, enabling deterministic single-pass uncertainty propagation without sampling, backpropagation, or second-order information. Across regression, classification, image segmentation, and language modeling, GAPA matches or outperforms strong post-hoc baselines in calibration and out-of-distribution detection while remaining efficient at test time.

---

### Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery

Authors: Chandrakanth Gudavalli, Tajuddin Manhar Mohammed, Abhay Yadav, Ananth Vishnu Bhaskar, Hardik Prajapati, Cheng Peng, Rama Chellappa, Shivkumar Chandrasekaran, B. S. Manjunath
Published: 2026-02-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.14929v1

Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challenging under large viewpoint gaps or when GPS is unreliable. We introduce Wrivinder, a zero-shot, geometry-driven framework that aggregates multiple ground photographs to reconstruct a consistent 3D scene and align it with overhead satellite imagery. Wrivinder combines SfM reconstruction, 3D Gaussian Splatting, semantic grounding, and monocular depth--based metric cues to produce a stable zenith-view rendering that can be directly matched to satellite context for metrically accurate camera geo-localization. To support systematic evaluation of this task, which lacks suitable benchmarks, we also release MC-Sat, a curated dataset linking multi-view ground imagery with geo-registered satellite tiles across diverse outdoor environments. Together, Wrivinder and MC-Sat provide a first comprehensive baseline and testbed for studying geometry-centered cross-view alignment without paired supervision. In zero-shot experiments, Wrivinder achieves sub-30\,m geolocation accuracy across both dense and large-area scenes, highlighting the promise of geometry-based aggregation for robust ground-to-satellite localization.

---

### From Classical to Quantum: Extending Prometheus for Unsupervised Discovery of Phase Transitions in Three Dimensions and Quantum Systems

Authors: Brandon Yee, Wilson Collins, Pairie Koh, Maximilian Rutkowski
Published: 2026-02-16
Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2602.14928v4

We extend the Prometheus framework for unsupervised phase transition discovery from two-dimensional classical systems to three-dimensional classical systems and quantum many-body systems. Building upon preliminary observations from a 2D Ising model student abstract (Yee et al., 2026), we address two fundamental questions: (1) Does the framework scale to higher dimensions where exact solutions are unavailable? (2) Can it generalize to quantum phase transitions driven by quantum fluctuations rather than thermal fluctuations? For the 3D Ising model on lattices up to $L{=}32$, we achieve critical temperature detection within 0.01\% of literature values ($\Tc/J = 4.511 \pm 0.005$) and extract critical exponents with ${\geq}70\%$ accuracy, with statistical analysis correctly identifying the 3D Ising universality class ($p = 0.72$). For quantum systems, we develop quantum-aware VAE (Q-VAE) architectures operating on complex-valued wavefunctions with fidelity-based loss functions, achieving 2\% accuracy in quantum critical point detection for the transverse field Ising model. For the disordered TFIM, we perform a consistency check of activated dynamical scaling $\ln ξ\sim |h - \hc|^{-ψ}$, extracting tunneling exponent $ψ= 0.48 \pm 0.08$ consistent with theoretical predictions ($ψ= 0.5$, $Δχ^2 = 12.3$, $p < 0.001$). This demonstrates that unsupervised learning can identify qualitatively different \emph{types} of critical behavior, serving as a consistency check on known IRFP physics.

---

### MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design

Authors: Gen Zhou, Sugitha Janarthanan, Lianghong Chen, Pingzhao Hu
Published: 2026-02-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.14926v1

To address the global health threat of antimicrobial resistance, antimicrobial peptides (AMP) are being explored for their potent and promising ability to fight resistant pathogens. While artificial intelligence (AI) is being employed to advance AMP discovery and design, most AMP design models struggle to balance key goals like activity, toxicity, and novelty, using rigid or unclear scoring methods that make results hard to interpret and optimize. As the capabilities of Large Language Models (LLM) advance and evolve swiftly, we turn to AI multi-agent collaboration based on such models (multi-agent LLMs), which show rapidly rising potential in complex scientific design scenarios. Based on this, we introduce MAC-AMP, a closed-loop multi-agent collaboration (MAC) system for multi-objective AMP design. The system implements a fully autonomous simulated peer review-adaptive reinforcement learning framework that requires only a task description and example dataset to design novel AMPs. The novelty of our work lies in introducing a closed-loop multi-agent system for AMP design, with cross-domain transferability, that supports multi-objective optimization while remaining explainable rather than a 'black box'. Experiments show that MAC-AMP outperforms other AMP generative models by effectively optimizing AMP generation for multiple key molecular properties, demonstrating exceptional results in antibacterial activity, AMP likeliness, toxicity compliance, and structural reliability.

---

### ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI

Authors: Gaoyang Zhang, Shanghong Zou, Yafang Wang, He Zhang, Ruohua Xu, Feng Zhao
Published: 2026-02-16
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.14922v1

To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs heterogeneous, platform-specific Domain Specific Languages (DSLs) into standardized, modular workflow segments. It employs a dual knowledge architecture-integrating graph and vector databases-to facilitate synergistic retrieval of both topological structures and functional semantics. Finally, workflows are intelligently assembled using a retrieval-augmented generation (RAG) strategy. Tested on 200 real-world n8n workflows, the system achieves over 90% accuracy in both extraction and construction. This framework provides a standardized solution for the automated reorganization and efficient reuse of enterprise digital assets.

---

### BHyGNN+: Unsupervised Representation Learning for Heterophilic Hypergraphs

Authors: Tianyi Ma, Yiyue Qian, Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye
Published: 2026-02-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.14919v1

Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterophilic hypergraphs, where nodes connected by the same hyperedge tend to have dissimilar semantic representations or belong to different classes. While several HyGNNs, including our prior work BHyGNN, have been proposed to address heterophily, their reliance on labeled data significantly limits their applicability in real-world scenarios where annotations are scarce or costly. To overcome this limitation, we introduce BHyGNN+, a self-supervised learning framework that extends BHyGNN for representation learning on heterophilic hypergraphs without requiring ground-truth labels. The core idea of BHyGNN+ is hypergraph duality, a structural transformation where the roles of nodes and hyperedges are interchanged. By contrasting augmented views of a hypergraph against its dual using cosine similarity, our framework captures essential structural patterns in a fully unsupervised manner. Notably, this duality-based formulation eliminates the need for negative samples, a common requirement in existing hypergraph contrastive learning methods that is often difficult to satisfy in practice. Extensive experiments on eleven benchmark datasets demonstrate that BHyGNN+ consistently outperforms state-of-the-art supervised and self-supervised baselines on both heterophilic and homophilic hypergraphs. Our results validate the effectiveness of leveraging hypergraph duality for self-supervised learning and establish a new paradigm for representation learning on challenging, unlabeled hypergraphs.

---

### BFS-PO: Best-First Search for Large Reasoning Models

Authors: Fiorenzo Parascandolo, Wenhui Tan, Enver Sangineto, Ruihua Song, Rita Cucchiara
Published: 2026-02-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.14917v1

Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown excellent performance in reasoning tasks using long reasoning chains. However, this has also led to a significant increase of computational costs and the generation of verbose output, a phenomenon known as overthinking. The tendency to overthinking is often exacerbated by Reinforcement Learning (RL) algorithms such as GRPO/DAPO. In this paper, we propose BFS-PO, an RL algorithm which alleviates this problem using a Best-First Search exploration strategy. Specifically, BFS-PO looks for the shortest correct answer using a backtracking mechanism based on maximum entropy nodes. By generating progressively shorter responses during training, BFS-PO learns to produce concise reasoning chains. Using different benchmarks and base LRMs, we show that BFS-PO can simultaneously increase the LRM accuracy and shorten its answers.

---

### Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation

Authors: Olivier Jeunen, Shashank Gupta
Published: 2026-02-16
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2602.14914v3

Off-policy evaluation (OPE) is essential for assessing ranking and recommendation systems without costly online interventions. Self-Normalised Inverse Propensity Scoring (SNIPS) is a standard tool for variance reduction in OPE, leveraging a multiplicative control variate. Recent advances in off-policy learning suggest that additive control variates (baseline corrections) may offer superior performance, yet theoretical guarantees for evaluation are lacking. This paper provides a definitive answer: we prove that $β^\star$-IPS, an estimator with an optimal additive baseline, asymptotically dominates SNIPS in Mean Squared Error. By analytically decomposing the variance gap, we show that SNIPS is asymptotically equivalent to using a specific -- but generally sub-optimal -- additive baseline. Our results theoretically justify shifting from self-normalisation to optimal baseline corrections for both ranking and recommendation.

---