# Research Papers — 2026-02 · bundle page 82 of 210 > Full-text markdown of papers #4051–4100 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/82 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/81.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/83.md) ### Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift Authors: Farbod Siahkali, Ashwin Verma, Vijay Gupta Published: 2026-02-16 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2602.14913v3 Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to counter this performance loss under a bounded label-conditional covariate shift model. Using tools from domain adaptation, we derive a lower bound on target coverage in terms of the source-domain loss of the classifier and a Wasserstein measure of the shift. Using this result, we provide a method to design pseudo-calibrated sets that inflate the conformal threshold by a slack parameter to keep target coverage above a prescribed level. Finally, we propose a source-tuned pseudo-calibration algorithm that interpolates between hard pseudo-labels and randomized labels as a function of classifier uncertainty. Numerical experiments show that our bounds qualitatively track pseudo-calibration behavior and that the source-tuned scheme mitigates coverage degradation under distribution shift while maintaining nontrivial prediction set sizes. --- ### Position: Introspective Experience from Conversational Environments as a Path to Better Learning Authors: Claudiu Cristian Musat, Jackson Tolins, Diego Antognini, Jingling Li, Martin Klissarov, Tom Duerig Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14910v1 Current approaches to AI training treat reasoning as an emergent property of scale. We argue instead that robust reasoning emerges from linguistic self-reflection, itself internalized from high-quality social interaction. Drawing on Vygotskian developmental psychology, we advance three core positions centered on Introspection. First, we argue for the Social Genesis of the Private Mind: learning from conversational environments rises to prominence as a new way to make sense of the world; the friction of aligning with another agent, internal or not, refines and crystallizes the reasoning process. Second, we argue that dialogically scaffolded introspective experiences allow agents to engage in sense-making that decouples learning from immediate data streams, transforming raw environmental data into rich, learnable narratives. Finally, we contend that Dialogue Quality is the New Data Quality: the depth of an agent's private reasoning, and its efficiency regarding test-time compute, is determined by the diversity and rigor of the dialogues it has mastered. We conclude that optimizing these conversational scaffolds is the primary lever for the next generation of general intelligence. --- ### Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model Authors: Moloud Arian Maram, Georgios Bletsos, Thanh Tung Nguyen, Ahmed Hassan, Michael Palm, Thomas Rung Published: 2026-02-16 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.14907v3 Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, particularly in minimizing the ship resistance. However, its application to vessels that employ complex propulsion systems introduces significant challenges. They arise from the need for transient simulations extending over long periods of time with small time steps and from the reverse temporal propagation of the primal and adjoint solutions. These challenges place considerable demands on the required storage and computing power, which significantly hamper the use of adjoint methods in the industry. To address this issue, we propose a machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system. The surrogate model replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation. Primal flow verification examples demonstrate that the surrogate model achieves significant computational savings while maintaining the necessary accuracy of the resolved propeller. Optimization studies demonstrate that neglecting the propulsion system can result in hull designs whose performance is inferior to that of the initial shape when subsequently validated using a numerically resolved propulsor. In contrast, the proposed method produces shapes that actually achieve more than an 8% reduction in resistance. --- ### Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model Authors: Moloud Arian Maram, Georgios Bletsos, Thanh Tung Nguyen, Ahmed Hassan, Michael Palm, Thomas Rung Published: 2026-02-16 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.14907v2 Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, particularly in minimizing the ship resistance. However, its application to vessels that employ complex propulsion systems introduces significant challenges. They arise from the need for transient simulations extending over long periods of time with small time steps and from the reverse temporal propagation of the primal and adjoint solutions. These challenges place considerable demands on the required storage and computing power, which significantly hamper the use of adjoint methods in the industry. To address this issue, we propose a machine learning-assisted optimization framework that employs a Conditional Variational Autoencoder-based surrogate model of the propulsion system. The surrogate model replicates the time-averaged flow field induced by a Voith Schneider Propeller and replaces the geometrically and time-resolved propeller with a data-driven approximation. Primal flow verification examples demonstrate that the surrogate model achieves significant computational savings while maintaining the necessary accuracy of the resolved propeller. Optimization studies show that ignoring the propulsion system can yield designs that perform worse than the initial shape. In contrast, the proposed method produces shapes that achieve more than an 8\% reduction in resistance. --- ### The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics Authors: Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin Nabi Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14903v2 Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to human-like reasoning is undeniable, the driving forces underpinning the success of CoT reasoning still remain largely unclear. In this work, we perform an in-depth analysis of CoT traces originating from competition-level mathematics questions, with the aim of better understanding how, and which parts of CoT actually contribute to the final answer. To this end, we introduce the notion of a potential, quantifying how much a given part of CoT increases the likelihood of a correct completion. Upon examination of reasoning traces through the lens of the potential, we identify surprising patterns including (1) its often strong non-monotonicity (due to reasoning tangents), (2) very sharp but sometimes tough to interpret spikes (reasoning insights and jumps) as well as (3) at times lucky guesses, where the model arrives at the correct answer without providing any relevant justifications before. While some of the behaviours of the potential are readily interpretable and align with human intuition (such as insights and tangents), others remain difficult to understand from a human perspective. To further quantify the reliance of LLMs on reasoning insights, we investigate the notion of CoT transferability, where we measure the potential of a weaker model under the partial CoT from another, stronger model. Indeed aligning with our previous results, we find that as little as 20% of partial CoT can ``unlock'' the performance of the weaker model on problems that were previously unsolvable for it, highlighting that a large part of the mechanics underpinning CoT are transferable. --- ### Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems Authors: Pramit Saha, Joshua Strong, Mohammad Alsharid, Divyanshu Mishra, J. Alison Noble Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.CV, cs.MA arXiv: https://arxiv.org/abs/2602.14901v1 Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as disease diagnosis, localization, and report generation. Yet, for a given task, a single "best" model rarely exists. In practice, each task is better served by multiple competing specialist models where different models excel on different data samples. As a result, for any given query, agents must reliably select the right specialist model from a heterogeneous pool of tool candidates. To this end, we introduce ToolSelect, which adaptively learns model selection for tools by minimizing a population risk over sampled specialist tool candidates using a consistent surrogate of the task-conditional selection loss. Concretely, we propose an Attentive Neural Process-based selector conditioned on the query and per-model behavioral summaries to choose among the specialist models. Motivated by the absence of any established testbed, we, for the first time, introduce an agentic Chest X-ray environment equipped with a diverse suite of task-specialized models (17 disease detection, 19 report generation, 6 visual grounding, and 13 VQA) and develop ToolSelectBench, a benchmark of 1448 queries. Our results demonstrate that ToolSelect consistently outperforms 10 SOTA methods across four different task families. --- ### Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs Authors: Pedram Bakhtiarifard, Tong Chen, Jonathan Wenshøj, Erik B Dam, Raghavendra Selvan Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14896v2 Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge distillation have been used to achieve massive reductions in model parameters with only marginal performance drops. This raises the central question: *Why are deep neural networks suited for compression?* In this work, we take up the perspective of algorithmic complexity to explain this behavior. We hypothesize that the parameters of trained models have more structure and, hence, exhibit lower algorithmic complexity compared to the weights at (random) initialization. Furthermore, model compression methods harness this reduced algorithmic complexity to compress models. Although an unconstrained parameterization of model weights, $\mathbf{w} \in \mathbb{R}^n$, can represent arbitrary weight assignments, the solutions found during training exhibit repeatability and structure, making them simpler to implement than a trivial program. To this end, we formalize the Kolmogorov complexity of $\mathbf{w}$ by $\mathcal{K}(\mathbf{w})$. We introduce a constrained parameterization $\widehat{\mathbf{w}}$ that partitions parameters into blocks of size $s$ and restricts each block to be selected from a set of $k$ reusable motifs, specified by a reuse pattern (or mosaic). The resulting method, $\mathit{Mosaic\text{-}of\text{-}Motifs}$ (MoMos), provides a theoretically justified parameterization that biases optimization toward algorithmically simpler solutions. Empirical evidence from multiple experiments shows that MoMos consistently lowers the algorithmic complexity of neural networks during training while preserving the performance of unconstrained models. These results suggest that parameter compressibility is not only observed after training, but can be induced from the optimization domain. --- ### Lifted Relational Probabilistic Inference via Implicit Learning Authors: Luise Ge, Brendan Juba, Kris Nilsson, Alison Shao Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14890v1 Reconciling the tension between inductive learning and deductive reasoning in first-order relational domains is a longstanding challenge in AI. We study the problem of answering queries in a first-order relational probabilistic logic through a joint effort of learning and reasoning, without ever constructing an explicit model. Traditional lifted inference assumes access to a complete model and exploits symmetry to evaluate probabilistic queries; however, learning such models from partial, noisy observations is intractable in general. We reconcile these two challenges through implicit learning to reason and first-order relational probabilistic inference techniques. More specifically, we merge incomplete first-order axioms with independently sampled, partially observed examples into a bounded-degree fragment of the sum-of-squares (SOS) hierarchy in polynomial time. Our algorithm performs two lifts simultaneously: (i) grounding-lift, where renaming-equivalent ground moments share one variable, collapsing the domain of individuals; and (ii) world-lift, where all pseudo-models (partial world assignments) are enforced in parallel, producing a global bound that holds across all worlds consistent with the learned constraints. These innovations yield the first polynomial-time framework that implicitly learns a first-order probabilistic logic and performs lifted inference over both individuals and worlds. --- ### Web-Scale Multimodal Summarization using CLIP-Based Semantic Alignment Authors: Mounvik K, N Harshit Published: 2026-02-16 Categories: cs.LG, cs.CV, cs.ET, cs.HC, cs.NE arXiv: https://arxiv.org/abs/2602.14889v1 We introduce Web-Scale Multimodal Summarization, a lightweight framework for generating summaries by combining retrieved text and image data from web sources. Given a user-defined topic, the system performs parallel web, news, and image searches. Retrieved images are ranked using a fine-tuned CLIP model to measure semantic alignment with topic and text. Optional BLIP captioning enables image-only summaries for stronger multimodal coherence.The pipeline supports features such as adjustable fetch limits, semantic filtering, summary styling, and downloading structured outputs. We expose the system via a Gradio-based API with controllable parameters and preconfigured presets.Evaluation on 500 image-caption pairs with 20:1 contrastive negatives yields a ROC-AUC of 0.9270, an F1-score of 0.6504, and an accuracy of 96.99%, demonstrating strong multimodal alignment. This work provides a configurable, deployable tool for web-scale summarization that integrates language, retrieval, and vision models in a user-extensible pipeline. --- ### Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks Authors: Ramón Nartallo-Kaluarachchi, Renaud Lambiotte, Alain Goriely Published: 2026-02-16 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2602.14885v2 Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows. In contrast, biological networks support rich time-dependent behaviour facilitated by their asymmetry. Here we introduce a general framework, which we term drift-diffusion matching, for training continuous-time RNNs to represent arbitrary, nonlinear stochastic differential equations (SDEs), with given drift and diffusion coefficients, within a low-dimensional latent subspace. Allowing asymmetric connectivity, we show that RNNs can faithfully embed the drift and diffusion of a given SDE, including nonlinear and nonequilibrium dynamics such as chaotic attractors. As an application, we construct RNN realisations of stochastic systems that transiently explore various attractors through both input-driven switching and autonomous transitions driven by nonequilibrium currents, which we interpret as models of associative and sequential (episodic) memory. To elucidate how these dynamics are encoded in the network, we introduce decompositions of the RNN based on its asymmetric connectivity and its time-irreversibility. Our results extend attractor neural network theory beyond equilibrium, showing that asymmetric neural populations can implement a broad class of dynamical computations within low-dimensional manifolds, unifying ideas from associative memory, nonequilibrium statistical mechanics, and neural computation. --- ### Numerical exploration of the range of shape functionals using neural networks Authors: Eloi Martinet, Ilias Ftouhi Published: 2026-02-16 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2602.14881v2 We introduce a novel numerical framework for the exploration of Blaschke--Santaló diagrams, which are efficient tools characterizing the possible inequalities relating some given shape functionals. We introduce a parametrization of convex bodies in arbitrary dimensions using a specific invertible neural network architecture based on gauge functions, allowing an intrinsic conservation of the convexity of the sets during the shape optimization process. To achieve a uniform sampling inside the diagram, and thus a satisfying description of it, we introduce an interacting particle system that minimizes a Riesz energy functional via automatic differentiation in PyTorch. The effectiveness of the method is demonstrated on several diagrams involving both geometric and PDE-type functionals for convex bodies of $\mathbb{R}^2$ and $\mathbb{R}^3$, namely, the volume, the perimeter, the moment of inertia, the torsional rigidity, the Willmore energy, and the first two Neumann eigenvalues of the Laplacian. --- ### CT-Bench: A Benchmark for Multimodal Lesion Understanding in Computed Tomography Authors: Qingqing Zhu, Qiao Jin, Tejas S. Mathai, Yin Fang, Zhizheng Wang, Yifan Yang, Maame Sarfo-Gyamfi, Benjamin Hou, Ran Gu, Praveen T. S. Balamuralikrishna, Kenneth C. Wang, Ronald M. Summers et al. Published: 2026-02-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.14879v2 Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited by the scarcity of publicly available CT datasets with lesion-level annotations. To bridge this gap, we introduce CT-Bench, a first-of-its-kind benchmark dataset comprising two components: a Lesion Image and Metadata Set containing 20,335 lesions from 7,795 CT studies with bounding boxes, descriptions, and size information, and a multitask visual question answering benchmark with 2,850 QA pairs covering lesion localization, description, size estimation, and attribute categorization. Hard negative examples are included to reflect real-world diagnostic challenges. We evaluate multiple state-of-the-art multimodal models, including vision-language and medical CLIP variants, by comparing their performance to radiologist assessments, demonstrating the value of CT-Bench as a comprehensive benchmark for lesion analysis. Moreover, fine-tuning models on the Lesion Image and Metadata Set yields significant performance gains across both components, underscoring the clinical utility of CT-Bench. --- ### On the Emergence of Implicit Curriculum in RLVR Learning Dynamics Authors: Yu Huang, Zixin Wen, Yuejie Chi, Yuting Wei, Aarti Singh, Yingbin Liang, Yuxin Chen Published: 2026-02-16 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2602.14872v3 Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier to extended reasoning. To understand this, we develop a theory of the training dynamics of RLVR for transformers on compositional reasoning tasks. Our theory shows that mixed-difficulty training naturally induces an implicit curriculum: without any explicit schedule, easier problems become learnable first and shape the frontier for harder ones, creating a learning progression from easy to hard during optimization. The effectiveness of this curriculum is governed by the smoothness of the difficulty spectrum. When the spectrum is smooth, training dynamics enter a well-behaved relay regime, in which persistent gradient signals on easier problems make slightly harder ones tractable and keep training at the edge of competence. When the spectrum contains abrupt discontinuities, training undergoes grokking-type phase transitions with prolonged plateaus before progress recurs. As a technical contribution, our analysis develops and adapts techniques from Fourier analysis on finite groups to our setting. We validate the predicted mechanisms empirically via controlled synthetic experiments and real-model RLVR runs. --- ### Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution Authors: Matthew Kowal, Goncalo Paulo, Louis Jaburi, Tom Tseng, Lev E McKinney, Stefan Heimersheim, Aaron David Tucker, Adam Gleave, Kellin Pelrine Published: 2026-02-16 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.14869v1 As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by estimating datapoint influence. Existing approaches like influence functions are both computationally expensive and attribute based on single test examples, which can bias results toward syntactic rather than semantic similarity. To address these issues of scalability and influence to abstract behavior, we leverage interpretable structures within the model during the attribution. First, we introduce Concept Influence which attribute model behavior to semantic directions (such as linear probes or sparse autoencoder features) rather than individual test examples. Second, we show that simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster. We empirically validate Concept Influence and approximations across emergent misalignment benchmarks and real post-training datasets, and demonstrate they achieve comparable performance to classical influence functions while being substantially more scalable. More broadly, we show that incorporating interpretable structure within traditional TDA pipelines can enable more scalable, explainable, and better control of model behavior through data. --- ### Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning Authors: Ilia Mahrooghi, Aryo Lotfi, Emmanuel Abbe Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.14868v2 Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this process highly sample-inefficient, as models must navigate vast search spaces with minimal feedback. While classic curriculum learning aims to mitigate this by ordering data based on complexity, prior works have primarily targeted small datasets and do not directly transfer to the large-scale settings typical of modern LM training. Furthermore, the right ordering for a specific model is often unclear. To address this, we propose Goldilocks, a novel teacher-driven data sampling strategy that aims to predict each question's difficulty for the student model. The teacher model selects questions of appropriate difficulty for the student model, i.e., questions that are neither too easy nor too hard (Goldilocks principle), while training the student with GRPO. By leveraging the student's performance on seen samples, the teacher continuously adapts to the student's evolving abilities. On the OpenMathReasoning dataset, Goldilocks data sampling improves the performance of models trained with standard GRPO under the same compute budget. --- ### Fast and accurate quasi-atom method for simultaneous atomistic and continuum simulation of solids Authors: Artem Chuprov, Egor E. Nuzhin, Alexey A. Tsukanov, Nikolay V. Brilliantov Published: 2026-02-16 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2602.14867v1 We report a novel hybrid method of simultaneous atomistic simulation of solids in critical regions (contacts surfaces, cracks areas, etc.), along with continuum modeling of other parts. The continuum is treated in terms of quasi-atoms of different size, comprising composite medium. The parameters of interaction potential between the quasi-atoms are optimized to match elastic properties of the composite medium to those of the atomic one. The optimization method coincides conceptually with the online Machine Learning (ML) methods, making it computationally very efficient. Such an approach allows a straightforward application of standard software packages for molecular dynamics (MD), supplemented by the ML-based optimizer. The new method is applied to model systems with a simple, pairwise Lennard-Jones potential, as well with multi-body Tersoff potential, describing covalent bonds. Using LAMMPS software we simulate collision of particles of different size. Comparing simulation results, obtained by the novel method, with full-atomic simulations, we demonstrate its accuracy, validity and overwhelming superiority in computational speed. Furthermore, we compare our method with other hybrid methods, specifically, with the closest one -- AtC (Atomic to Continuum) method. We demonstrate a significant superiority of our approach in computational speed and implementation convenience. Finally, we discuss a possible extension of the method for modeling other phenomena. --- ### EmbeWebAgent: Embedding Web Agents into Any Customized UI Authors: Chenyang Ma, Clyde Fare, Matthew Wilson, Dave Braines Published: 2026-02-16 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2602.14865v1 Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits robustness and action expressiveness. In enterprise settings, however, explicit control of both the frontend and backend is available. We present EmbeWebAgent, a framework for embedding agents directly into existing UIs using lightweight frontend hooks (curated ARIA and URL-based observations, and a per-page function registry exposed via a WebSocket) and a reusable backend workflow that performs reasoning and takes actions. EmbeWebAgent is stack-agnostic (e.g., React or Angular), supports mixed-granularity actions ranging from GUI primitives to higher-level composites, and orchestrates navigation, manipulation, and domain-specific analytics via MCP tools. Our demo shows minimal retrofitting effort and robust multi-step behaviors grounded in a live UI setting. Live Demo: https://youtu.be/Cy06Ljee1JQ --- ### The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling Authors: Pierre-Alexandre Mattei, Bruno Loureiro Published: 2026-02-16 Categories: stat.ML, cs.AI, cs.IT, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.14862v2 Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: improving the calibration of classifiers and tuning the stochasticity of large language models (LLMs). In both cases, temperature scaling is the most popular method for the job. Despite its popularity, a rigorous theoretical analysis of the properties of temperature scaling has remained elusive. We investigate here some of these properties. For classification, we show that increasing the temperature increases the uncertainty in the model in a very general sense (and in particular increases its entropy). However, for LLMs, we challenge the common claim that increasing temperature increases diversity. Furthermore, we introduce two new characterisations of temperature scaling. The first one is geometric: the tempered model is shown to be the information projection of the original model onto the set of models with a given entropy. The second characterisation clarifies the role of temperature scaling as a submodel of more general linear scalers such as matrix scaling and Dirichlet calibration: we show that temperature scaling is the only linear scaler that does not change the hard predictions of the model. --- ### World Models for Policy Refinement in StarCraft II Authors: Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14857v2 Large Language Models (LLMs) have recently shown strong reasoning capabilities, motivating their use in complex decision-making environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing LLM-based SC2 agents primarily focus on improving the policy itself, leaving the integration of a learnable, action-conditioned dynamics model into the decision loop largely unexplored. In this work, we propose StarWM and StarWM-Agent, and conduct the first systematic study of the learnability and decision utility of player-view, action-conditioned textual world models for SC2. StarWM predicts short-horizon future observations under partial observability. StarWM-Agent integrates StarWM into a lightweight Generate-Simulate-Refine loop for foresight-driven policy refinement. Extensive experiments show that StarWM substantially outperforms zero-shot baselines across multiple dimensions, while StarWM-Agent achieves consistent win-rate gains of 30%, 15%, and 30% against the SC2 built-in AI at Hard (LV5), Harder (LV6), and VeryHard (LV7), respectively. Additional analyses show that our method is complementary to existing history-summarization SC2-agent approaches, with their combination achieving the strongest online performance in our evaluation. --- ### World Models for Policy Refinement in StarCraft II Authors: Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14857v1 Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing LLM-based SC2 agents primarily focus on improving the policy itself and overlook integrating a learnable, action-conditioned transition model into the decision loop. To bridge this gap, we propose StarWM, the first world model for SC2 that predicts future observations under partial observability. To facilitate learning SC2's hybrid dynamics, we introduce a structured textual representation that factorizes observations into five semantic modules, and construct SC2-Dynamics-50k, the first instruction-tuning dataset for SC2 dynamics prediction. We further develop a multi-dimensional offline evaluation framework for predicted structured observations. Offline results show StarWM's substantial gains over zero-shot baselines, including nearly 60% improvements in resource prediction accuracy and self-side macro-situation consistency. Finally, we propose StarWM-Agent, a world-model-augmented decision system that integrates StarWM into a Generate--Simulate--Refine decision loop for foresight-driven policy refinement. Online evaluation against SC2's built-in AI demonstrates consistent improvements, yielding win-rate gains of 30%, 15%, and 30% against Hard (LV5), Harder (LV6), and VeryHard (LV7), respectively, alongside improved macro-management stability and tactical risk assessment. --- ### A Pragmatic Method for Comparing Clusterings with Overlaps and Outliers Authors: Ryan DeWolfe, Paweł Prałat, François Théberge Published: 2026-02-16 Categories: cs.LG, cs.SI, math.CO arXiv: https://arxiv.org/abs/2602.14855v2 Clustering algorithms are an essential part of the unsupervised data science ecosystem, and extrinsic evaluation of clustering algorithms requires a method for comparing the detected clustering to a ground truth clustering. In a general setting, the detected and ground truth clusterings may have outliers (objects belonging to no cluster), overlapping clusters (objects may belong to more than one cluster), or both, but methods for comparing these clusterings are currently undeveloped. In this note, we define a pragmatic similarity measure for comparing clusterings with overlaps and outliers, show that it has several desirable properties, and experimentally confirm that it is not subject to several common biases afflicting other clustering comparison measures. --- ### BEACONS: Bounded-Error, Algebraically-Composable Neural Solvers for Partial Differential Equations Authors: Jonathan Gorard, Ammar Hakim, James Juno Published: 2026-02-16 Categories: cs.LG, math.NA, physics.comp-ph arXiv: https://arxiv.org/abs/2602.14853v1 The traditional limitations of neural networks in reliably generalizing beyond the convex hulls of their training data present a significant problem for computational physics, in which one often wishes to solve PDEs in regimes far beyond anything which can be experimentally or analytically validated. In this paper, we show how it is possible to circumvent these limitations by constructing formally-verified neural network solvers for PDEs, with rigorous convergence, stability, and conservation properties, whose correctness can therefore be guaranteed even in extrapolatory regimes. By using the method of characteristics to predict the analytical properties of PDE solutions a priori (even in regions arbitrarily far from the training domain), we show how it is possible to construct rigorous extrapolatory bounds on the worst-case L^inf errors of shallow neural network approximations. Then, by decomposing PDE solutions into compositions of simpler functions, we show how it is possible to compose these shallow neural networks together to form deep architectures, based on ideas from compositional deep learning, in which the large L^inf errors in the approximations have been suppressed. The resulting framework, called BEACONS (Bounded-Error, Algebraically-COmposable Neural Solvers), comprises both an automatic code-generator for the neural solvers themselves, as well as a bespoke automated theorem-proving system for producing machine-checkable certificates of correctness. We apply the framework to a variety of linear and non-linear PDEs, including the linear advection and inviscid Burgers' equations, as well as the full compressible Euler equations, in both 1D and 2D, and illustrate how BEACONS architectures are able to extrapolate solutions far beyond the training data in a reliable and bounded way. Various advantages of the approach over the classical PINN approach are discussed. --- ### Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows Authors: Bardia Mohammadi, Nearchos Potamitis, Lars Klein, Akhil Arora, Laurent Bindschaedler Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2602.14849v2 LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and concurrent agents can leave partial effects, losing-branch residue, stale writes, or irreversible sends. Correct settlement needs two facts that retries, checkpoint replay, locks, and compensation each conflate: which effects must settle together, and when earlier conflicting work is exhausted. Atomix makes this split explicit with progress-aware transactions. The runtime records reads and effects during execution, seals a transaction when its footprint is complete, and commits only after per-resource frontiers show that no earlier conflicting work can still arrive. Commit is final settlement: Atomix releases bufferable effects, accepts reversible external effects as final, and lets irreversible effects leave the gate. Abort suppresses unreleased effects and compensates externalized reversible effects where possible. On representative agent workloads, this composition improves clean recovery under injected faults, isolates contending and speculative work, and prevents correctly classified irreversible actions from leaking; microbenchmarks show microsecond-scale wrapper overhead relative to tool latency. --- ### Multi-dimensional Persistent Sheaf Laplacians for Image Analysis Authors: Xiang Xiang Wang, Guo-Wei Wei Published: 2026-02-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.14846v1 We propose a multi-dimensional persistent sheaf Laplacian (MPSL) framework on simplicial complexes for image analysis. The proposed method is motivated by the strong sensitivity of commonly used dimensionality reduction techniques, such as principal component analysis (PCA), to the choice of reduced dimension. Rather than selecting a single reduced dimension or averaging results across dimensions, we exploit complementary advantages of multiple reduced dimensions. At a given dimension, image samples are regarded as simplicial complexes, and persistent sheaf Laplacians are utilized to extract a multiscale localized topological spectral representation for individual image samples. Statistical summaries of the resulting spectra are then aggregated across scales and dimensions to form multiscale multi-dimensional image representations. We evaluate the proposed framework on the COIL20 and ETH80 image datasets using standard classification protocols. Experimental results show that the proposed method provides more stable performance across a wide range of reduced dimensions and achieves consistent improvements to PCA-based baselines in moderate dimensional regimes. --- ### Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment Authors: Elias Malomgré, Pieter Simoens Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14844v2 AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, difficult-to-edit alignment artifacts and reduces their reuse across models or deployments, a failure mode we term Alignment Waste. We propose Interactionless Inverse Reinforcement Learning, a framework for learning inspectable, editable, and reusable reward artifacts separately from policy optimization. We further introduce the Alignment Flywheel, a human-in-the-loop lifecycle for iteratively auditing, patching, and hardening these artifacts through automated evaluation and refinement. Together, these ideas recast alignment from a disposable training expense into a durable, verifiable engineering asset. --- ### Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation Authors: Lorenzo Mur Labadia, Ruben Martinez-Cantin, Jose J. Guerrero, Giovanni M. Farinella, Antonino Furnari Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14837v1 Short Term object-interaction Anticipation consists in detecting the location of the next active objects, the noun and verb categories of the interaction, as well as the time to contact from the observation of egocentric video. This ability is fundamental for wearable assistants to understand user goals and provide timely assistance, or to enable human-robot interaction. In this work, we present a method to improve the performance of STA predictions. Our contributions are two-fold: 1 We propose STAformer and STAformer plus plus, two novel attention-based architectures integrating frame-guided temporal pooling, dual image-video attention, and multiscale feature fusion to support STA predictions from an image-input video pair; 2 We introduce two novel modules to ground STA predictions on human behavior by modeling affordances. First, we integrate an environment affordance model which acts as a persistent memory of interactions that can take place in a given physical scene. We explore how to integrate environment affordances via simple late fusion and with an approach which adaptively learns how to best fuse affordances with end-to-end predictions. Second, we predict interaction hotspots from the observation of hands and object trajectories, increasing confidence in STA predictions localized around the hotspot. Our results show significant improvements on Overall Top-5 mAP, with gain up to +23p.p on Ego4D and +31p.p on a novel set of curated EPIC-Kitchens STA labels. We released the code, annotations, and pre-extracted affordances on Ego4D and EPIC-Kitchens to encourage future research in this area. --- ### Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision Authors: Pengcheng Pan, Yonekura Shogo, Yasuo Kuniyosh Published: 2026-02-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.14834v2 Human eye movements in visual recognition reflect a balance between foveal sampling and peripheral context. Task-driven hard-attention models for vision are often evaluated by how well their scanpaths match human gaze. However, common scanpath metrics can be strongly confounded by dataset-specific center bias, especially on object-centric datasets. Using Gaze-CIFAR-10, we show that a trivial center-fixation baseline achieves surprisingly strong scanpath scores, approaching many learned policies. This makes standard metrics optimistic and blurs the distinction between genuine behavioral alignment and mere central tendency. We then analyze a hard-attention classifier under constrained vision by sweeping foveal patch size and peripheral context, revealing a peripheral sweet spot: only a narrow range of sensory constraints yields scanpaths that are simultaneously (i) above the center baseline after debiasing and (ii) temporally human-like in movement statistics. To address center bias, we propose GCS (Gaze Consistency Score), a center-debiased composite metric augmented with movement similarity. GCS uncovers a robust sweet spot at medium patch size with both foveal and peripheral vision, that is not obvious from raw scanpath metrics or accuracy alone, and also highlights a "shortcut regime" when the field-of-view becomes too large. We discuss implications for evaluating active perception on object-centric datasets and for designing gaze benchmarks that better separate behavioral alignment from center bias. --- ### RF-GPT: Teaching AI to See the Wireless World Authors: Hang Zou, Yu Tian, Bohao Wang, Lina Bariah, Samson Lasaulce, Chongwen Huang, Mérouane Debbah Published: 2026-02-16 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.14833v1 Large language models (LLMs) and multimodal models have become powerful general-purpose reasoning systems. However, radio-frequency (RF) signals, which underpin wireless systems, are still not natively supported by these models. Existing LLM-based approaches for telecom focus mainly on text and structured data, while conventional RF deep-learning models are built separately for specific signal-processing tasks, highlighting a clear gap between RF perception and high-level reasoning. To bridge this gap, we introduce RF-GPT, a radio-frequency language model (RFLM) that utilizes the visual encoders of multimodal LLMs to process and understand RF spectrograms. In this framework, complex in-phase/quadrature (IQ) waveforms are mapped to time-frequency spectrograms and then passed to pretrained visual encoders. The resulting representations are injected as RF tokens into a decoder-only LLM, which generates RF-grounded answers, explanations, and structured outputs. To train RF-GPT, we perform supervised instruction fine-tuning of a pretrained multimodal LLM using a fully synthetic RF corpus. Standards-compliant waveform generators produce wideband scenes for six wireless technologies, from which we derive time-frequency spectrograms, exact configuration metadata, and dense captions. A text-only LLM then converts these captions into RF-grounded instruction-answer pairs, yielding roughly 12,000 RF scenes and 0.625 million instruction examples without any manual labeling. Across benchmarks for wideband modulation classification, overlap analysis, wireless-technology recognition, WLAN user counting, and 5G NR information extraction, RF-GPT achieves strong multi-task performance, whereas general-purpose VLMs with no RF grounding largely fail. --- ### Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability Authors: Ana F. Rodrigues, Lucas Ferraz, Laura Balbi, Pedro Giesteira Cotovio, Catia Pesquita Published: 2026-02-16 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2602.14828v1 Effective representations of protein sequences are widely recognized as a cornerstone of machine learning-based protein design. Yet, protein bioengineering poses unique challenges for sequence representation, as experimental datasets typically feature few mutations, which are either sparsely distributed across the entire sequence or densely concentrated within localized regions. This limits the ability of sequence-level representations to extract functionally meaningful signals. In addition, comprehensive comparative studies remain scarce, despite their crucial role in clarifying which representations best encode relevant information and ultimately support superior predictive performance. In this study, we systematically evaluate multiple ProtBERT and ESM2 embedding variants as sequence representations, using the adeno-associated virus capsid as a case study and prototypical example of bioengineering, where functional optimization is targeted through highly localized sequence variation within an otherwise large protein. Our results reveal that, prior to fine-tuning, amino acid-level embeddings outperform sequence-level representations in supervised predictive tasks, whereas the latter tend to be more effective in unsupervised settings. However, optimal performance is only achieved when embeddings are fine-tuned with task-specific labels, with sequence-level representations providing the best performance. Moreover, our findings indicate that the extent of sequence variation required to produce notable shifts in sequence representations exceeds what is typically explored in bioengineering studies, showing the need for fine-tuning in datasets characterized by sparse or highly localized mutations. --- ### Testimole-Conversational: A 30-Billion-Word Italian Discussion Board Corpus (1996-2024) for Language Modeling and Sociolinguistic Research Authors: Matteo Rinaldi, Rossella Varvara, Viviana Patti Published: 2026-02-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.14819v2 We present "Testimole-conversational" a massive collection of discussion boards messages in the Italian language. The large size of the corpus, more than 30B word-tokens (1996-2024), renders it an ideal dataset for native Italian Large Language Models'pre-training. Furthermore, discussion boards' messages are a relevant resource for linguistic as well as sociological analysis. The corpus captures a rich variety of computer-mediated communication, offering insights into informal written Italian, discourse dynamics, and online social interaction in wide time span. Beyond its relevance for NLP applications such as language modelling, domain adaptation, and conversational analysis, it also support investigations of language variation and social phenomena in digital communication. The resource will be made freely available to the research community. --- ### Learning State-Tracking from Code Using Linear RNNs Authors: Julien Siems, Riccardo Grazzi, Korbinian Pöppel, Kirill Kalinin, Hitesh Ballani, Babak Rahmani Published: 2026-02-16 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.14814v3 Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear). However, these are often sequence-to-sequence tasks: learning to map actions (permutations) to states, which is incompatible with the next-token prediction setting commonly used to train language models. We address this gap by converting permutation composition into code via REPL traces that interleave state-reveals through prints and variable transformations. We show that linear RNNs capable of state-tracking excel also in this setting, while Transformers still fail. Motivated by this representation, we investigate why tracking states in code is generally difficult: actions are not always fully observable. We frame this as tracking the state of a probabilistic finite-state automaton with deterministic state reveals and show that linear RNNs can be worse than non-linear RNNs at tracking states in this setup. --- ### Physical Commonsense Reasoning for Lower-Resourced Languages and Dialects: a Study on Basque Authors: Jaione Bengoetxea, Itziar Gonzalez-Dios, Rodrigo Agerri Published: 2026-02-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.14812v3 Physical commonsense reasoning represents a fundamental capability of human intelligence, enabling individuals to understand their environment, predict future events, and navigate physical spaces. Recent years have witnessed growing interest in reasoning tasks within Natural Language Processing (NLP). However, no prior research has examined the performance of Large Language Models (LLMs) on non-question-answering (non-QA) physical commonsense reasoning tasks in low-resource languages such as Basque. Taking the Italian GITA as a starting point, this paper addresses this gap by presenting BasPhyCo, the first non-QA physical commonsense reasoning dataset for Basque, available in both standard and dialectal variants. We evaluate model performance across three hierarchical levels of commonsense understanding: (1) distinguishing between plausible and implausible narratives (accuracy), (2) identifying the conflicting element that renders a narrative implausible (consistency), and (3) determining the specific physical state that creates the implausibility (verifiability). These tasks were assessed using multiple multilingual LLMs as well as models pretrained specifically for Italian and Basque. Results indicate that, in terms of verifiability, LLMs exhibit limited physical commonsense capabilities in low-resource languages such as Basque, especially when processing dialectal variants. --- ### Overthinking Loops in Agents: A Structural Risk via MCP Tools Authors: Yohan Lee, Jisoo Jang, Seoyeon Choi, Sangyeop Kim, Seungtaek Choi Published: 2026-02-16 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2602.14798v1 Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return messages. We show that this convenience creates a supply-chain attack surface: a malicious MCP tool server can be co-registered alongside normal tools and induce overthinking loops, where individually trivial or plausible tool calls compose into cyclic trajectories that inflate end-to-end tokens and latency without any single step looking abnormal. We formalize this as a structural overthinking attack, distinguishable from token-level verbosity, and implement 14 malicious tools across three servers that trigger repetition, forced refinement, and distraction. Across heterogeneous registries and multiple tool-capable models, the attack causes severe resource amplification (up to $142.4\times$ tokens) and can degrade task outcomes. Finally, we find that decoding-time concision controls do not reliably prevent loop induction, suggesting defenses should reason about tool-call structure rather than tokens alone. --- ### Return of the Schema: Building Complete Datasets for Machine Learning and Reasoning on Knowledge Graphs Authors: Ivan Diliso, Roberto Barile, Claudia d'Amato, Nicola Fanizzi Published: 2026-02-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.14795v1 Datasets for the experimental evaluation of knowledge graph refinement algorithms typically contain only ground facts, retaining very limited schema level knowledge even when such information is available in the source knowledge graphs. This limits the evaluation of methods that rely on rich ontological constraints, reasoning or neurosymbolic techniques and ultimately prevents assessing their performance in large-scale, real-world knowledge graphs. In this paper, we present \resource{} the first resource that provides a workflow for extracting datasets including both schema and ground facts, ready for machine learning and reasoning services, along with the resulting curated suite of datasets. The workflow also handles inconsistencies detected when keeping both schema and facts and also leverage reasoning for entailing implicit knowledge. The suite includes newly extracted datasets from KGs with expressive schemas while simultaneously enriching existing datasets with schema information. Each dataset is serialized in OWL making it ready for reasoning services. Moreover, we provide utilities for loading datasets in tensor representations typical of standard machine learning libraries. --- ### Extending Multi-Source Bayesian Optimization With Causality Principles Authors: Luuk Jacobs, Mohammad Ali Javidian Published: 2026-02-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.14791v1 Multi-Source Bayesian Optimization (MSBO) serves as a variant of the traditional Bayesian Optimization (BO) framework applicable to situations involving optimization of an objective black-box function over multiple information sources such as simulations, surrogate models, or real-world experiments. However, traditional MSBO assumes the input variables of the objective function to be independent and identically distributed, limiting its effectiveness in scenarios where causal information is available and interventions can be performed, such as clinical trials or policy-making. In the single-source domain, Causal Bayesian Optimization (CBO) extends standard BO with the principles of causality, enabling better modeling of variable dependencies. This leads to more accurate optimization, improved decision-making, and more efficient use of low-cost information sources. In this article, we propose a principled integration of the MSBO and CBO methodologies in the multi-source domain, leveraging the strengths of both to enhance optimization efficiency and reduce computational complexity in higher-dimensional problems. We present the theoretical foundations of both Causal and Multi-Source Bayesian Optimization, and demonstrate how their synergy informs our Multi-Source Causal Bayesian Optimization (MSCBO) algorithm. We compare the performance of MSCBO against its foundational counterparts for both synthetic and real-world datasets with varying levels of noise, highlighting the robustness and applicability of MSCBO. Based on our findings, we conclude that integrating MSBO with the causality principles of CBO facilitates dimensionality reduction and lowers operational costs, ultimately improving convergence speed, performance, and scalability. --- ### On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials Authors: Rotem Mulayoff, Sebastian U. Stich Published: 2026-02-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.14789v2 The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms. For example, stable solutions of gradient descent (GD) correspond to flat minima, which have been associated with favorable features. While prior work often relies on linearization to determine stability, it remains unclear whether linearized dynamics faithfully capture the full nonlinear behavior. Recent work has shown that GD may stably oscillate near a linearly unstable minimum and still converge once the step size decays, indicating that linear analysis can be misleading. In this work, we explicitly study the effect of nonlinear terms. Specifically, we derive an exact criterion for stable oscillations of GD near minima in the multivariate setting. Our condition depends on high-order derivatives, generalizing existing results. Extending the analysis to stochastic gradient descent (SGD), we show that nonlinear dynamics can diverge in expectation even if a single batch is unstable. This implies that stability can be dictated by a single batch that oscillates unstably, rather than an average effect, as linear analysis suggests. Finally, we prove that if all batches are linearly stable, the nonlinear dynamics of SGD are stable in expectation. --- ### VIPA: Visual Informative Part Attention for Referring Image Segmentation Authors: Yubin Cho, Hyunwoo Yu, Kyeongbo Kong, Kyomin Sohn, Bongjoon Hyun, Suk-Ju Kang Published: 2026-02-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.14788v1 Referring Image Segmentation (RIS) aims to segment a target object described by a natural language expression. Existing methods have evolved by leveraging the vision information into the language tokens. To more effectively exploit visual contexts for fine-grained segmentation, we propose a novel Visual Informative Part Attention (VIPA) framework for referring image segmentation. VIPA leverages the informative parts of visual contexts, called a visual expression, which can effectively provide the structural and semantic visual target information to the network. This design reduces high-variance cross-modal projection and enhances semantic consistency in an attention mechanism of the referring image segmentation. We also design a visual expression generator (VEG) module, which retrieves informative visual tokens via local-global linguistic context cues and refines the retrieved tokens for reducing noise information and sharing informative visual attributes. This module allows the visual expression to consider comprehensive contexts and capture semantic visual contexts of informative regions. In this way, our framework enables the network's attention to robustly align with the fine-grained regions of interest. Extensive experiments and visual analysis demonstrate the effectiveness of our approach. Our VIPA outperforms the existing state-of-the-art methods on four public RIS benchmarks. --- ### SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment Authors: Fengyuan Cao, Xinyu Liang, Fredrik Cumlin, Victor Ungureanu, Chandan K. A. Reddy, Christian Schuldt, Saikat Chatterjee Published: 2026-02-16 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2602.14785v1 Designing a speech quality assessment (SQA) system for estimating mean-opinion-score (MOS) of multi-rate speech with varying sampling frequency (16-48 kHz) is a challenging task. The challenge arises due to the limited availability of a MOS-labeled training dataset comprising multi-rate speech samples. While self-supervised learning (SSL) models have been widely adopted in SQA to boost performance, a key limitation is that they are pretrained on 16 kHz speech and therefore discard high-frequency information present in higher sampling rates. To address this issue, we propose a spectrogram-augmented SSL method that incorporates high-frequency features (up to 48 kHz sampling rate) through a parallel-branch architecture. We further introduce a two-step training scheme: the model is first pre-trained on a large 48 kHz dataset and then fine-tuned on a smaller multi-rate dataset. Experimental results show that leveraging high-frequency information overlooked by SSL features is crucial for accurate multi-rate SQA, and that the proposed two-step training substantially improves generalization when multi-rate data is limited. --- ### Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs Authors: Christos Koutsiaris Published: 2026-02-16 Categories: cs.IR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.14784v1 Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or retrieval-augmented generation (RAG), effective segmentation determines how well systems can locate and return relevant information. However, traditional methods, such as fixed-length or coherence-based segmentation, ignore user intent, leading to chunks that split answers or contain irrelevant noise. We introduce Intent-Driven Dynamic Chunking (IDC), a novel approach that uses predicted user queries to guide document segmentation. IDC leverages a Large Language Model to generate likely user intents for a document and then employs a dynamic programming algorithm to find the globally optimal chunk boundaries. This represents a novel application of DP to intent-aware segmentation that avoids greedy pitfalls. We evaluated IDC on six diverse question-answering datasets, including news articles, Wikipedia, academic papers, and technical documentation. IDC outperformed traditional chunking strategies on five datasets, improving top-1 retrieval accuracy by 5% to 67%, and matched the best baseline on the sixth. Additionally, IDC produced 40-60% fewer chunks than baseline methods while achieving 93-100% answer coverage. These results demonstrate that aligning document structure with anticipated information needs significantly boosts retrieval performance, particularly for long and heterogeneous documents. --- ### What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation Authors: Benoît Dupont, Chad Whelan, Serge-Olivier Paquette Published: 2026-02-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.14783v1 The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between cybercriminals and AI using a unique dataset from a cyber threat intelligence platform. Analyzing more than 160 cybercrime forum conversations collected over seven months, our research reveals how cybercriminals understand AI and discuss how they can exploit its capabilities. Their exchanges reflect growing curiosity about AI's criminal applications through legal tools and dedicated criminal tools, but also doubts and anxieties about AI's effectiveness and its effects on their business models and operational security. The study documents attempts to misuse legitimate AI tools and develop bespoke models tailored for illicit purposes. Combining the diffusion of innovation framework with thematic analysis, the paper provides an in-depth view of emerging AI-enabled cybercrime and offers practical insights for law enforcement and policymakers. --- ### A Geometric Analysis of Small-sized Language Model Hallucinations Authors: Emanuele Ricco, Elia Onofri, Lorenzo Cima, Stefano Cresci, Roberto Di Pietro Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.14778v3 Hallucinations -- plausible but factually incorrect responses -- pose a major challenge to the reliability of Large Language Models (LLMs), especially in multi-step or agentic settings. Existing work largely frames hallucinations as a consequence of missing knowledge; we show instead that, even when the relevant factual knowledge is present, models still produce hallucinated answers, pointing to retrieval instability rather than knowledge gaps. Building on this observation, we introduce APORIA (Aggregate Prompt-wise Observation Retrieving Instability via Asymmetry -- the state of puzzlement-in-contradiction that hallucinations embody), a geometric framework that studies repeated responses to the same prompt in sentence-embedding space. Our central hypothesis is that genuine responses cluster more tightly than hallucinated ones; we empirically validate this and show that, after Fisher projection, the two response classes become consistently separable. We leverage this asymmetry in geometry via APORIA-LP, an efficient label-propagation method that classifies large collections of responses from as few as 30--50 annotations, achieving F1 scores above 90% across ten small-sized LLMs. To support further research, we release SOCRATES-300K, a fully labelled dataset of 300,000 responses, together with the code for both dataset generation and result reproduction. Our key finding -- framing hallucinations from a geometric perspective in the embedding space -- complements traditional knowledge-centric and single-response evaluation paradigms, paving the way for further research. --- ### Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment Authors: Laurène Vaugrante, Anietta Weckauff, Thilo Hagendorff Published: 2026-02-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.14777v1 Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess behavioral self-awareness - the ability to describe learned behaviors that were only implicitly demonstrated in training data. Here, we investigate the intersection of these phenomena. We fine-tune GPT-4.1 models sequentially on datasets known to induce and reverse emergent misalignment and evaluate whether the models are self-aware of their behavior transitions without providing in-context examples. Our results show that emergently misaligned models rate themselves as significantly more harmful compared to their base model and realigned counterparts, demonstrating behavioral self-awareness of their own emergent misalignment. Our findings show that behavioral self-awareness tracks actual alignment states of models, indicating that models can be queried for informative signals about their own safety. --- ### Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks Authors: Sungwoo Kang Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14772v2 The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics. The ML-for-combinatorial-optimization community has focused on learning to \emph{replace} solvers, yet recent evidence shows that graph neural networks (GNNs) rarely outperform well-tuned classical methods on standard benchmarks. We pursue a different objective: learning to predict \emph{when} a given instance is hard for greedy allocation, enabling instance-dependent algorithm selection. We design a 20-dimensional structural feature vector and train a lightweight MLP hardness classifier that predicts the greedy optimality gap with mean absolute error 0.033, Pearson correlation 0.937, and binary classification accuracy 94.7\% across three random seeds. For instances identified as hard -- those exhibiting ``whale-fish'' trap structure where greedy provably fails -- we deploy a heterogeneous GNN specialist that achieves ${\approx}0\%$ optimality gap on all six adversarial configurations tested (vs.\ 3.75--59.24\% for greedy). A hybrid allocator combining the hardness classifier with GNN and greedy solvers achieves 0.51\% overall gap on mixed distributions. Our honest evaluation on CATS benchmarks confirms that GNNs do not outperform Gurobi (0.45--0.71 vs.\ 0.20 gap), motivating the algorithm selection framing. Learning \emph{when} to deploy expensive solvers is more tractable than learning to replace them. --- ### GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture Authors: Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin Published: 2026-02-16 Categories: cs.CV, cs.AI, cs.LG, cs.MM, cs.NE arXiv: https://arxiv.org/abs/2602.14771v5 The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity. In contrast, recent generic object trackers are often optimized for training targets, which limits robustness and generalization in unseen scenarios, and their occlusion reasoning remains coarse, lacking detailed modeling of occlusion patterns. To address these limitations in generalization and occlusion perception, we propose GOT-JEPA, a model-predictive pretraining framework that extends JEPA from predicting image features to predicting tracking models. Given identical historical information, a teacher predictor generates pseudo-tracking models from a clean current frame, and a student predictor learns to predict the same pseudo-tracking models from a corrupted version of the current frame. This design provides stable pseudo supervision and explicitly trains the predictor to produce reliable tracking models under occlusions, distractors, and other adverse observations, improving generalization to dynamic environments. Building on GOT-JEPA, we further propose OccuSolver to enhance occlusion perception for object tracking. OccuSolver adapts a point-centric point tracker for object-aware visibility estimation and detailed occlusion-pattern capture. Conditioned on object priors iteratively generated by the tracker, OccuSolver incrementally refines visibility states, strengthens occlusion handling, and produces higher-quality reference labels that progressively improve subsequent model predictions. Extensive evaluations on seven benchmarks show that our method effectively enhances tracker generalization and robustness. --- ### Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation Authors: Shiwei Hong, Lingyao Li, Ethan Z. Rong, Chenxinran Shen, Zhicong Lu Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2602.14770v2 Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor. --- ### SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning Authors: Shishir Muralidhara, Didier Stricker, René Schuster Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14767v1 Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These factors significantly limit the applicability of continuous learning in real-world settings, as iterative model updates require significant computational resources and inherently exacerbate forgetting. We present SAILS -- Segment Anything with Incrementally Learned Semantics, a training-free framework for Class-Incremental Semantic Segmentation (CISS) that sidesteps these challenges entirely. SAILS leverages foundational models to decouple CISS into two stages: Zero-shot region extraction using Segment Anything Model (SAM), followed by semantic association through prototypes in a fixed feature space. SAILS incorporates selective intra-class clustering, resulting in multiple prototypes per class to better model intra-class variability. Our results demonstrate that, despite requiring no incremental training, SAILS typically surpasses the performance of existing training-based approaches on standard CISS datasets, particularly in long and challenging task sequences where forgetting tends to be most severe. By avoiding parameter updates, SAILS completely eliminates forgetting and maintains consistent, task-invariant performance. Furthermore, SAILS exhibits positive backward transfer, where the introduction of new classes can enhance performance on previous classes. --- ### Unlocking Reasoning Capability on Machine Translation in Large Language Models Authors: Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee, Kelly Marchisio, Tom Kocmi Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14763v1 Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We systematically evaluate several open- and closed-weights RLMs on the WMT24++ benchmark and find that enabling explicit reasoning consistently degrades translation quality across languages and models. Analysis reveals that MT reasoning traces are highly linear, lacking revision, self-correction and exploration of alternative translations, which limits their usefulness. Furthermore, injecting higher-quality reasoning traces from stronger models does not reliably improve weaker models' performance. To address this mismatch, we propose a structured reasoning framework tailored to translation, based on multi-step drafting, adequacy refinement, fluency improvement, and selective iterative revision. We curate a synthetic dataset of dynamic structured reasoning traces and post-train a large reasoning model on this data. Experiments show significant improvements over standard translation fine-tuning and injected generic reasoning baselines. Our findings demonstrate that reasoning must be task-structured to benefit MT. --- ### Universal Algorithm-Implicit Learning Authors: Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.14761v2 Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose" inconsistently and lacks precise definitions, hindering comparability. We introduce a theoretical framework for meta-learning which formally defines practical universality and introduces a distinction between algorithm-explicit and algorithm-implicit learning, providing a principled vocabulary for reasoning about universal meta-learning methods. Guided by this framework, we present TAIL, a transformer-based algorithm-implicit meta-learner that functions across tasks with varying domains, modalities, and label configurations. TAIL features three innovations over prior transformer-based meta-learners: random projections for cross-modal feature encoding, random injection label embeddings that extrapolate to larger label spaces, and efficient inline query processing. TAIL achieves state-of-the-art performance on standard few-shot benchmarks while generalizing to unseen domains. Unlike other meta-learning methods, it also generalizes to unseen modalities, solving text classification tasks despite training exclusively on images, handles tasks with up to 20$\times$ more classes than seen during training, and provides orders-of-magnitude computational savings over prior transformer-based approaches. --- ### Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Authors: Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, Axel Marmoret, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14760v2 Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current token, while supervision targets the next token, potentially propagating mismatched information if the current token is not the most informative for prediction. In this work, we empirically localize this input-output alignment shift in pretrained LLMs, using decoding trajectories over tied embedding spaces and similarity-based metrics. Our experiments reveal that the hidden token representations switch from input alignment to output alignment deep within the network. Motivated by this observation, we propose a lightweight residual-path mitigation based on residual attenuation, implemented either as a fixed-layer intervention or as a learnable gating mechanism. Experiments on multiple benchmarks show that these strategies alleviate the representation misalignment and yield improvements, providing an efficient and general architectural enhancement for autoregressive Transformers. --- ### Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training Authors: Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, Axel Marmoret, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.14759v2 Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contributions: a residual path that copies the input and the output of a Transformer block. As a consequence, the inner representations (i.e. the input of these blocks) can be interpreted as iterative refinement of a propagated latent representation. Under this lens, many works suggest that the inner space is shared across layers, meaning that tokens can be decoded at early stages. Mechanistic interpretability even goes further by conjecturing that some layers act as refinement layers. Following this path, we propose inference-time inner looping, which prolongs refinement in pretrained off-the-shelf language models by repeatedly re-applying a selected block range. Across multiple benchmarks, inner looping yields modest but consistent accuracy improvements. Analyses of the resulting latent trajectories suggest more stable state evolution and continued semantic refinement. Overall, our results suggest that additional refinement can be obtained through simple test-time looping, extending computation in frozen pretrained models. ---