# Research Papers — 2026-02 · bundle page 78 of 210 > Full-text markdown of papers #3851–3900 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/78 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/77.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/79.md) ### SecCodeBench-V2 Technical Report Authors: Longfei Chen, Ji Zhao, Lanxiao Cui, Tong Su, Xingbo Pan, Ziyang Li, Yongxing Wu, Qijiang Cao, Qiyao Cai, Jing Zhang, Yuandong Ni, Junyao He et al. Published: 2026-02-17 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2602.15485v2 We introduce SecCodeBench-V2, a publicly released benchmark for evaluating Large Language Model (LLM) copilots' capabilities of generating secure code. SecCodeBench-V2 comprises 98 generation and fix scenarios derived from Alibaba Group's industrial productions, where the underlying security issues span 22 common CWE (Common Weakness Enumeration) categories across five programming languages: Java, C, Python, Go, and JavaScript. SecCodeBench-V2 adopts a function-level task formulation: each scenario provides a complete project scaffold and requires the model to implement or patch a designated target function under fixed interfaces and dependencies. For each scenario, SecCodeBench-V2 provides executable proof-of-concept (PoC) test cases for both functional validation and security verification. All test cases are authored and double-reviewed by security experts, ensuring high fidelity, broad coverage, and reliable ground truth. Beyond the benchmark itself, we build a unified evaluation pipeline that assesses models primarily via dynamic execution. For most scenarios, we compile and run model-generated artifacts in isolated environments and execute PoC test cases to validate both functional correctness and security properties. For scenarios where security issues cannot be adjudicated with deterministic test cases, we additionally employ an LLM-as-a-judge oracle. To summarize performance across heterogeneous scenarios and difficulty levels, we design a Pass@K-based scoring protocol with principled aggregation over scenarios and severity, enabling holistic and comparable evaluation across models. Overall, SecCodeBench-V2 provides a rigorous and reproducible foundation for assessing the security posture of AI coding assistants, with results and artifacts released at https://alibaba.github.io/sec-code-bench. The benchmark is publicly available at https://github.com/alibaba/sec-code-bench. --- ### Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction Authors: Amartyaveer, Murali Kadambi, Chandra Mohan Sharma, Anupam Mondal, Prasanta Kumar Ghosh Published: 2026-02-17 Categories: eess.AS, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.15484v2 In this study, we have presented a novel approach to predict the Short-Time Objective Intelligibility (STOI) metric using a bottleneck transformer architecture. Traditional methods for calculating STOI typically requires clean reference speech, which limits their applicability in the real world. To address this, numerous deep learning-based nonintrusive speech assessment models have garnered significant interest. Many studies have achieved commendable performance, but there is room for further improvement. We propose the use of bottleneck transformer, incorporating convolution blocks for learning frame-level features and a multi-head self-attention (MHSA) layer to aggregate the information. These components enable the transformer to focus on the key aspects of the input data. Our model has shown higher correlation and lower mean squared error for both seen and unseen scenarios compared to the state-of-the-art model using self-supervised learning (SSL) and spectral features as inputs. --- ### LLM-as-Judge on a Budget Authors: Aadirupa Saha, Aniket Wagde, Branislav Kveton Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15481v2 LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean scores accurately. This raises a critical challenge: given a fixed computational budget $B$, how to optimally allocate queries across $K$ prompt-response pairs to minimize estimation error? We present a principled variance-adaptive approach leveraging multi-armed bandit theory and concentration inequalities. Our method dynamically allocates queries based on estimated score variances, concentrating resources where uncertainty is highest. Further, our algorithm is shown to achieve a worst-case score-estimation error of $\tilde{O}\left(\sqrt{\frac{\sum_{i=1}^K σ_i^2}{B}}\right)$, $σ_i^2$ being the unknown score variance for pair $i \in (K)$ with near-optimal budget allocation. Experiments on \emph{Summarize-From-Feedback} and \emph{HelpSteer2} demonstrate that our method significantly outperforms uniform allocation, reducing worst-case estimation error while maintaining identical budgets. Our work establishes a theoretical foundation for efficient LLM evaluation with practical implications for AI safety, model alignment, and automated assessment at scale. --- ### Evaluating Federated Learning for Cross-Country Mood Inference from Smartphone Sensing Data Authors: Sharmad Kalpande, Saurabh Shirke, Haroon R. Lone Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15478v1 Mood instability is a key behavioral indicator of mental health, yet traditional assessments rely on infrequent and retrospective reports that fail to capture its continuous nature. Smartphone-based mobile sensing enables passive, in-the-wild mood inference from everyday behaviors; however, deploying such systems at scale remains challenging due to privacy constraints, uneven sensing availability, and substantial variability in behavioral patterns. In this work, we study mood inference using smartphone sensing data in a cross-country federated learning setting, where each country participates as an independent client while retaining local data. We introduce FedFAP, a feature-aware personalized federated framework designed to accommodate heterogeneous sensing modalities across regions. Evaluations across geographically and culturally diverse populations show that FedFAP achieves an AUROC of 0.744, outperforming both centralized approaches and existing personalized federated baselines. Beyond inference, our results offer design insights for mood-aware systems, demonstrating how population-aware personalization and privacy-preserving learning can enable scalable and mood-aware mobile sensing technologies. --- ### POP: Prior-Fitted First-Order Optimization Policies Authors: Jan Kobiolka, Christian Frey, Gresa Shala, Arlind Kadra, Erind Bedalli, Josif Grabocka Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15473v2 Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcement Learning (RL) policy that predicts adaptive learning rates for gradient descent, conditioned on the contextual information provided in the optimization trajectory. Our method introduces a novel RL reward formulation, a new function-scaling strategy for in-distribution generalization, and a novel prior that is used to sample millions of synthetic optimization problems. We evaluate POP on an established benchmark including 43 optimization functions of various complexity, where it significantly outperforms gradient-based methods. Our evaluation demonstrates strong generalization capabilities without task-specific tuning. --- ### Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows Authors: Ramansh Sharma, Matthew Lowery, Houman Owhadi, Varun Shankar Published: 2026-02-17 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.15472v4 We present a novel property-preserving kernel-based operator learning method for incompressible flows governed by the incompressible Navier--Stokes equations. Traditional numerical solvers incur significant computational costs to respect incompressibility. Operator learning offers efficient surrogate models, but current neural operators fail to exactly enforce physical properties such as incompressibility, periodicity, and turbulence. Our kernel method maps input functions to expansion coefficients of output functions in a property-preserving kernel basis, ensuring that predicted velocity fields $\textit{analytically}$ and $\textit{simultaneously}$ preserve the aforementioned physical properties. Our method leverages efficient numerical linear algebra, simple rootfinding, and streaming to allow for training at-scale on desktop GPUs. We also present universal approximation results and both pessimistic and more realistic $\textit{a priori}$ convergence rates for our framework. We evaluate the method on challenging 2D and 3D, laminar and turbulent, incompressible flow problems. Our method achieves up to six orders of magnitude lower relative $\ell_2$ errors upon generalization and trains up to five orders of magnitude faster compared to neural operators, despite our method being trained on desktop GPUs and neural operators being trained on cutting-edge GPU servers. Moreover, while our method enforces incompressibility analytically, neural operators exhibit very large deviations. Our results show that our method provides an accurate and efficient surrogate for incompressible flows. --- ### The Skeletal Trap: Mapping Spatial Inequality and Ghost Stops in Ankara's Transit Network Authors: Elifnaz Kancan Published: 2026-02-17 Categories: physics.soc-ph, cs.LG arXiv: https://arxiv.org/abs/2602.15470v1 Ankara's public transport crisis is commonly framed as a shortage of buses or operational inefficiency. This study argues that the problem is fundamentally morphological and structural. The city's leapfrog urban expansion has produced fragmented peripheral clusters disconnected from a rigid, center-oriented bus network. As a result, demand remains intensely concentrated along the Kizilay-Ulus axis and western corridors, while peripheral districts experience either chronic under-service or enforced transfer dependency. The deficiency is therefore not merely quantitative but rooted in the misalignment between urban macroform and network architecture. The empirical analysis draws on a 173-day operational dataset derived from route-level passenger and trip reports published by EGO under the former "Transparent Ankara" initiative. To overcome the absence of stop-level geospatial data, a Connectivity-Based Weighted Distribution Model reallocates passenger volumes to 1 km x 1 km grid cells using network centrality. The findings reveal persistent center-periphery asymmetries, structural bottlenecks, and spatially embedded accessibility inequalities. --- ### Emergent Morphing Attack Detection in Open Multi-modal Large Language Models Authors: Marija Ivanovska, Vitomir Štruc Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15461v1 Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models (MLLMs) have demonstrated strong visual-linguistic reasoning, but their potential in biometric forensics remains underexplored. In this paper, we present the first systematic zero-shot evaluation of open-source MLLMs for single-image MAD, using publicly available weights and a standardized, reproducible protocol. Across diverse morphing techniques, many MLLMs show non-trivial discriminative ability without any fine-tuning or domain adaptation, and LLaVA1.6-Mistral-7B achieves state-of-the-art performance, surpassing highly competitive task-specific MAD baselines by at least 23% in terms of equal error rate (EER). The results indicate that multimodal pretraining can implicitly encode fine-grained facial inconsistencies indicative of morphing artifacts, enabling zero-shot forensic sensitivity. Our findings position open-source MLLMs as reproducible, interpretable, and competitive foundations for biometric security and forensic image analysis. This emergent capability also highlights new opportunities to develop state-of-the-art MAD systems through targeted fine-tuning or lightweight adaptation, further improving accuracy and efficiency while preserving interpretability. To support future research, all code and evaluation protocols will be released upon publication. --- ### On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks Authors: Yannic Neuhaus, Nicolas Flammarion, Matthias Hein, Francesco Croce Published: 2026-02-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.15460v1 Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of reasoning models is still vaguely defined and poorly understood. In this work, we present an evaluation framework to rigorously examine how well chain-of-thought (CoT) approaches generalize on a simple planning task. Specifically, we consider a grid-based navigation task in which a model is provided with a map and must output a sequence of moves that guides a player from a start position to a goal while avoiding obstacles. The versatility of the task and its data allows us to fine-tune model variants using different input representations (visual and textual) and CoT reasoning strategies, and systematically evaluate them under both in-distribution (ID) and out-of-distribution (OOD) test conditions. Our experiments show that, while CoT reasoning improves in-distribution generalization across all representations, out-of-distribution generalization (e.g., to larger maps) remains very limited in most cases when controlling for trivial matches with the ID data. Surprisingly, we find that reasoning traces which combine multiple text formats yield the best (and non-trivial) OOD generalization. Finally, purely text-based models consistently outperform those utilizing image-based inputs, including a recently proposed approach relying on latent space reasoning. --- ### Benchmarking IoT Time-Series AD with Event-Level Augmentations Authors: Dmitry Zhevnenko, Ilya Makarov, Aleksandr Kovalenko, Fedor Meshchaninov, Anton Kozhukhov, Vladislav Travnikov, Makar Ippolitov, Kirill Yashunin, Iurii Katser Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15457v2 Anomaly detection (AD) for safety-critical IoT time series should be judged at the event level: reliability and earliness under realistic perturbations. Yet many studies still emphasize point-level results on curated base datasets, limiting value for model selection in practice. We introduce an evaluation protocol with unified event-level augmentations that simulate real-world issues: calibrated sensor dropout, linear and log drift, additive noise, and window shifts. We also perform sensor-level probing via mask-as-missing zeroing with per-channel influence estimation to support root-cause analysis. We evaluate 14 representative models on five public anomaly datasets (SWaT, WADI, SMD, SKAB, TEP) and two industrial datasets (steam turbine, nuclear turbogenerator) using unified splits and event aggregation. There is no universal winner: graph-structured models transfer best under dropout and long events (e.g., on SWaT under additive noise F1 drops 0.804->0.677 for a graph autoencoder, 0.759->0.680 for a graph-attention variant, and 0.762->0.756 for a hybrid graph attention model); density/flow models work well on clean stationary plants but can be fragile to monotone drift; spectral CNNs lead when periodicity is strong; reconstruction autoencoders become competitive after basic sensor vetting; predictive/hybrid dynamics help when faults break temporal dependencies but remain window-sensitive. The protocol also informs design choices: on SWaT under log drift, replacing normalizing flows with Gaussian density reduces high-stress F1 from ~0.75 to ~0.57, and fixing a learned DAG gives a small clean-set gain (~0.5-1.0 points) but increases drift sensitivity by ~8x. --- ### In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations Authors: Mohammad Aflah Khan, Mahsa Amani, Soumi Das, Bishwamittra Ghosh, Qinyuan Wu, Krishna P. Gummadi, Manish Gupta, Abhilasha Ravichander Published: 2026-02-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15456v1 Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize information retrieved from the platforms' back-end databases or via web search. In these scenarios, LLM agents govern the information users receive, by drawing users' attention to particular instances of retrieved information at the expense of others. While much prior work has focused on biases in the information LLMs themselves generate, less attention has been paid to the factors that influence what information LLMs select and present to users. We hypothesize that when information is attributed to specific sources (e.g., particular publishers, journals, or platforms), current LLMs exhibit systematic latent source preferences- that is, they prioritize information from some sources over others. Through controlled experiments on twelve LLMs from six model providers, spanning both synthetic and real-world tasks, we find that several models consistently exhibit strong and predictable source preferences. These preferences are sensitive to contextual framing, can outweigh the influence of content itself, and persist despite explicit prompting to avoid them. They also help explain phenomena such as the observed left-leaning skew in news recommendations in prior work. Our findings advocate for deeper investigation into the origins of these preferences, as well as for mechanisms that provide users with transparency and control over the biases guiding LLM-powered agents. --- ### Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer Authors: Hayato Kunugi, Mohsen Rahmani, Yosuke Iyama, Yutaro Hirono, Akira Suma, Matthew Woolway, Vladimir Vargas-Calderón, William Kim, Kevin Chern, Mohammad Amin, Masaru Tateno Published: 2026-02-17 Categories: q-bio.QM, cs.AI, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2602.15451v3 Deep generative modeling to stochastically design small molecules is an emerging technology for accelerating drug discovery and development. However, one major issue in molecular generative models is their lower frequency of drug-like compounds. To resolve this problem, we developed a novel framework for optimization of deep generative models integrated with a D-Wave quantum annealing computer, where our Neural Hash Function (NHF) presented herein is used both as the regularization and binarization schemes simultaneously, of which the latter is for transformation between continuous and discrete signals of the classical and quantum neural networks, respectively, in the error evaluation (i.e., objective) function. The compounds generated via the quantum-annealing generative models exhibited higher quality in both validity and drug-likeness than those generated via the fully-classical models, and was further indicated to exceed even the training data in terms of drug-likeness features, without any restraints and conditions to deliberately induce such an optimization. These results indicated an advantage of quantum annealing to aim at a stochastic generator integrated with our novel neural network architectures, for the extended performance of feature space sampling and extraction of characteristic features in drug design. --- ### TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models Authors: Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jiasi Shen, Jing Tang, Jianguo Li Published: 2026-02-17 Categories: cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2602.15449v1 Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is essential to overcoming this hurdle. Reinforcement Fine-Tuning (RFT) has emerged as a promising strategy to address this need. However, most existing approaches overlook the heterogeneous difficulty and granularity inherent in test cases, leading to an imbalanced distribution of reward signals and consequently biased gradient updates during training. To address this, we propose Test-driven and cApability-adaptive cuRriculum reinfOrcement fine-Tuning (TAROT). TAROT systematically constructs, for each problem, a four-tier test suite (basic, intermediate, complex, edge), providing a controlled difficulty landscape for curriculum design and evaluation. Crucially, TAROT decouples curriculum progression from raw reward scores, enabling capability-conditioned evaluation and principled selection from a portfolio of curriculum policies rather than incidental test-case difficulty composition. This design fosters stable optimization and more efficient competency acquisition. Extensive experimental results reveal that the optimal curriculum for RFT in code generation is closely tied to a model's inherent capability, with less capable models achieving greater gains with an easy-to-hard progression, whereas more competent models excel under a hard-first curriculum. TAROT provides a reproducible method that adaptively tailors curriculum design to a model's capability, thereby consistently improving the functional correctness and robustness of the generated code. All code and data are released to foster reproducibility and advance community research at https://github.com/deep-diver/TAROT. --- ### Algorithmic Approaches to Opinion Selection for Online Deliberation: A Comparative Study Authors: Salim Hafid, Manon Berriche, Jean-Philippe Cointet Published: 2026-02-17 Categories: cs.CY, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2602.15439v1 During deliberation processes, mediators and facilitators typically need to select a small and representative set of opinions later used to produce digestible reports for stakeholders. In online deliberation platforms, algorithmic selection is increasingly used to automate this process. However, such automation is not without consequences. For instance, enforcing consensus-seeking algorithmic strategies can imply ignoring or flattening conflicting preferences, which may lead to erasing minority voices and reducing content diversity. More generally, across the variety of existing selection strategies (e.g., consensus, diversity), it remains unclear how each approach influences desired democratic criteria such as proportional representation. To address this gap, we benchmark several algorithmic approaches in this context. We also build on social choice theory to propose a novel algorithm that incorporates both diversity and a balanced notion of representation in the selection strategy. We find empirically that while no single strategy dominates across all democratic desiderata, our social-choice-inspired selection rule achieves the strongest trade-off between proportional representation and diversity. --- ### Logit Distance Bounds Representational Similarity Authors: Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele, Andrea Dittadi, Simon Buchholz Published: 2026-02-17 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.15438v3 For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations are equal up to an invertible linear transformation. We ask whether an analogous conclusion holds approximately when the distributions are close instead of equal. Building on the observation of Nielsen et al. (2025) that closeness in KL divergence need not imply high linear representational similarity, we study a distributional distance based on logit differences and show that closeness in this distance does yield linear similarity guarantees. Specifically, we define a representational dissimilarity measure based on the models' identifiability class and prove that it is bounded by the logit distance. We further show that, when model probabilities are bounded away from zero, KL divergence upper-bounds logit distance; yet the resulting bound fails to provide nontrivial control in practice. As a consequence, KL-based distillation can match a teacher's predictions while failing to preserve linear representational properties, such as linear-probe recoverability of human-interpretable concepts. In distillation experiments on synthetic and image datasets, logit-distance distillation yields students with higher linear representational similarity and better preservation of the teacher's linearly recoverable concepts. --- ### Measuring Social Integration Through Participation: Categorizing Organizations and Leisure Activities in the Displaced Karelians Interview Archive using LLMs Authors: Joonatan Laato, Veera Schroderus, Jenna Kanerva, Jenni Kauppi, Virpi Lummaa, Filip Ginter Published: 2026-02-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15436v1 Digitized historical archives make it possible to study everyday social life on a large scale, but the information extracted directly from text often does not directly allow one to answer the research questions posed by historians or sociologists in a quantitative manner. We address this problem in a large collection of Finnish World War II Karelian evacuee family interviews. Prior work extracted more than 350K mentions of leisure time activities and organizational memberships from these interviews, yielding 71K unique activity and organization names -- far too many to analyze directly. We develop a categorization framework that captures key aspects of participation (the kind of activity/organization, how social it typically is, how regularly it happens, and how physically demanding it is). We annotate a gold-standard set to allow for a reliable evaluation, and then test whether large language models can apply the same schema at scale. Using a simple voting approach across multiple model runs, we find that an open-weight LLM can closely match expert judgments. Finally, we apply the method to label the 350K entities, producing a structured resource for downstream studies of social integration and related outcomes. --- ### GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search Authors: Rong Fu, Jia Yee Tan, Chunlei Meng, Shuo Yin, Xiaowen Ma, Wangyu Wu, Simon Fong Published: 2026-02-17 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.15423v5 As the burgeoning power requirements of sophisticated neural architectures escalate, the information retrieval community has recognized ecological sustainability as a pivotal priority that necessitates a fundamental paradigm shift in model design. While contemporary neural rankers have attained unprecedented accuracy, the substantial environmental externalities associated with their computational intensity often remain overlooked in large-scale deployments. We present GaiaFlow, an innovative framework engineered to facilitate carbon-frugal search by operationalizing semantic-guided diffusion tuning. Our methodology orchestrates the convergence of retrieval-guided Langevin dynamics and a hardware-independent performance modeling strategy to optimize the trade-off between search precision and environmental preservation. By incorporating adaptive early exit protocols and precision-aware quantized inference, the proposed architecture significantly mitigates operational carbon footprints while maintaining robust retrieval quality across heterogeneous computing infrastructures. Extensive experimental evaluations demonstrate that GaiaFlow achieves a superior equilibrium between effectiveness and energy efficiency, offering a scalable and sustainable pathway for next-generation neural search systems. --- ### Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas Authors: Alper Demir, Hüseyin Aydın, Kale-ab Abebe Tessera, David Abel, Stefano V. Albrecht Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15407v1 Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by incorporating intrinsic drives that encourage prosocial or fair behavior. However, most existing methods assume that agents face identical incentives in the dilemma and require continuous access to global information about other agents to assess fairness. In this work, we introduce asymmetric variants of well-known SSD environments and examine how natural differences between agents influence cooperation dynamics. Our findings reveal that existing fairness-based methods struggle to adapt under asymmetric conditions by enforcing raw equality that wrongfully incentivize defection. To address this, we propose three modifications: (i) redefining fairness by accounting for agents' reward ranges, (ii) introducing an agent-based weighting mechanism to better handle inherent asymmetries, and (iii) localizing social feedback to make the methods effective under partial observability without requiring global information sharing. Experimental results show that in asymmetric scenarios, our method fosters faster emergence of cooperative policies compared to existing approaches, without sacrificing scalability or practicality. --- ### Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits Authors: Gilad Nurko, Roi Benita, Yehoshua Dissen, Tomohiro Nakatani, Marc Delcroix, Shoko Araki, Joseph Keshet Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15405v2 Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancement and classification as separate, sequential stages: first enhancing the signal and then applying a classifier. This approach fails to leverage the semantic information in the classifier's output during denoising. In this work, we propose a general, domain-agnostic framework that integrates two interacting diffusion models: one operating on the input signal and the other on the classifier's output logits, without requiring any retraining or fine-tuning of the classifier. This coupled formulation enables mutual guidance, where the enhancing signal refines the class estimation and, conversely, the evolving class logits guide the signal reconstruction towards discriminative regions of the manifold. We introduce three strategies to effectively model the joint distribution of the input and the logit. We evaluated our joint enhancement method for image classification and automatic speech recognition. The proposed framework surpasses traditional sequential enhancement baselines, delivering robust and flexible improvements in classification accuracy under diverse noise conditions. --- ### Common Belief Revisited Authors: Thomas Ågotnes Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15403v1 Contrary to common belief, common belief is not KD4. If individual belief is KD45, common belief does indeed lose the 5 property and keep the D and 4 properties -- and it has none of the other commonly considered properties of knowledge and belief. But it has another property: $C(Cφ\rightarrow φ)$ -- corresponding to so-called shift-reflexivity (reflexivity one step ahead). This observation begs the question: is KD4 extended with this axiom a complete characterisation of common belief in the KD45 case? If not, what \emph{is} the logic of common belief? In this paper we show that the answer to the first question is ``no'': there is one additional axiom, and, furthermore, it relies on the number of agents. We show that the result is a complete characterisation of common belief, settling the open problem. --- ### ActionCodec: What Makes for Good Action Tokenizers Authors: Zibin Dong, Yicheng Liu, Shiduo Zhang, Baijun Ye, Yifu Yuan, Fei Ni, Jingjing Gong, Xipeng Qiu, Hang Zhao, Yinchuan Li, Jianye Hao Published: 2026-02-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.15397v1 Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-following and training efficiency. Central to this paradigm is action tokenization, yet its design has primarily focused on reconstruction fidelity, failing to address its direct impact on VLA optimization. Consequently, the fundamental question of \textit{what makes for good action tokenizers} remains unanswered. In this paper, we bridge this gap by establishing design principles specifically from the perspective of VLA optimization. We identify a set of best practices based on information-theoretic insights, including maximized temporal token overlap, minimized vocabulary redundancy, enhanced multimodal mutual information, and token independence. Guided by these principles, we introduce \textbf{ActionCodec}, a high-performance action tokenizer that significantly enhances both training efficiency and VLA performance across diverse simulation and real-world benchmarks. Notably, on LIBERO, a SmolVLM2-2.2B fine-tuned with ActionCodec achieves a 95.5\% success rate without any robotics pre-training. With advanced architectural enhancements, this reaches 97.4\%, representing a new SOTA for VLA models without robotics pre-training. We believe our established design principles, alongside the released model, will provide a clear roadmap for the community to develop more effective action tokenizers. --- ### Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching Authors: Jeongwoo Shin, Jinhwan Sul, Joonseok Lee, Jaewong Choi, Jaemoo Choi Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15396v1 Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces independent data-noise coupling. We propose Adjoint Schrödinger Bridge Matching (ASBM), a generative modeling framework that recovers optimal trajectories in high dimensions via two stages. First, we view the Schrödinger Bridge (SB) forward dynamic as a coupling construction problem and learn it through a data-to-energy sampling perspective that transports data to an energy-defined prior. Then, we learn the backward generative dynamic with a simple matching loss supervised by the induced optimal coupling. By operating in a non-memoryless regime, ASBM produces significantly straighter and more efficient sampling paths. Compared to prior works, ASBM scales to high-dimensional data with notably improved stability and efficiency. Extensive experiments on image generation show that ASBM improves fidelity with fewer sampling steps. We further showcase the effectiveness of our optimal trajectory via distillation to a one-step generator. --- ### Doubly Stochastic Mean-Shift Clustering Authors: Tom Trigano, Yann Sepulcre, Itshak Lapidot Published: 2026-02-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.15393v1 Standard Mean-Shift algorithms are notoriously sensitive to the bandwidth hyperparameter, particularly in data-scarce regimes where fixed-scale density estimation leads to fragmentation and spurious modes. In this paper, we propose Doubly Stochastic Mean-Shift (DSMS), a novel extension that introduces randomness not only in the trajectory updates but also in the kernel bandwidth itself. By drawing both the data samples and the radius from a continuous uniform distribution at each iteration, DSMS effectively performs a better exploration of the density landscape. We show that this randomized bandwidth policy acts as an implicit regularization mechanism, and provide convergence theoretical results. Comparative experiments on synthetic Gaussian mixtures reveal that DSMS significantly outperforms standard and stochastic Mean-Shift baselines, exhibiting remarkable stability and preventing over-segmentation in sparse clustering scenarios without other performance degradation. --- ### Improving LLM Reliability through Hybrid Abstention and Adaptive Detection Authors: Ankit Sharma, Nachiket Tapas, Jyotiprakash Patra Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15391v1 Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe content generation. Conventional guardrails based on static rules or fixed confidence thresholds are typically context-insensitive and computationally expensive, resulting in high latency and degraded user experience. To address these limitations, we introduce an adaptive abstention system that dynamically adjusts safety thresholds based on real-time contextual signals such as domain and user history. The proposed framework integrates a multi-dimensional detection architecture composed of five parallel detectors, combined through a hierarchical cascade mechanism to optimize both speed and precision. The cascade design reduces unnecessary computation by progressively filtering queries, achieving substantial latency improvements compared to non-cascaded models and external guardrail systems. Extensive evaluation on mixed and domain-specific workloads demonstrates significant reductions in false positives, particularly in sensitive domains such as medical advice and creative writing. The system maintains high safety precision and near-perfect recall under strict operating modes. Overall, our context-aware abstention framework effectively balances safety and utility while preserving performance, offering a scalable solution for reliable LLM deployment. --- ### From Chain-Ladder to Individual Claims Reserving Authors: Ronald Richman, Mario V. Wüthrich Published: 2026-02-17 Categories: stat.AP, q-fin.RM, stat.ML arXiv: https://arxiv.org/abs/2602.15385v2 The chain-ladder (CL) method is the most widely used claims reserving technique in non-life insurance. This manuscript introduces a novel approach to computing the CL reserves based on a fundamental restructuring of the data utilization for the CL prediction procedure. Instead of rolling forward the cumulative claims with estimated CL factors, we estimate multi-period factors that project the latest observations directly to the ultimate claims. This alternative perspective on CL reserving creates a natural pathway for the application of machine learning techniques to individual claims reserving. As a proof of concept, we present a small-scale real data application employing neural networks for individual claims reserving. --- ### World-Model-Augmented Web Agents with Action Correction Authors: Zhouzhou Shen, Xueyu Hu, Xiyun Li, Tianqing Fang, Juncheng Li, Shengyu Zhang Published: 2026-02-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.15384v1 Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and might not possess comprehensive awareness of execution risks, prematurely performing risky actions that cause losses and lead to task failure. To address these challenges, we propose WAC, a web agent that integrates model collaboration, consequence simulation, and feedback-driven action refinement. To overcome the cognitive isolation of individual models, we introduce a multi-agent collaboration process that enables an action model to consult a world model as a web-environment expert for strategic guidance; the action model then grounds these suggestions into executable actions, leveraging prior knowledge of environmental state transition dynamics to enhance candidate action proposal. To achieve risk-aware resilient task execution, we introduce a two-stage deduction chain. A world model, specialized in environmental state transitions, simulates action outcomes, which a judge model then scrutinizes to trigger action corrective feedback when necessary. Experiments show that WAC achieves absolute gains of 1.8% on VisualWebArena and 1.3% on Online-Mind2Web. --- ### Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation Authors: Shuwei Li, Lei Tan, Robby T. Tan Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15383v1 Day-to-night unpaired image translation is important to downstream tasks but remains challenging due to large appearance shifts and the lack of direct pixel-level supervision. Existing methods often introduce semantic hallucinations, where objects from target classes such as traffic signs and vehicles, as well as man-made light effects, are incorrectly synthesized. These hallucinations significantly degrade downstream performance. We propose a novel framework that detects and suppresses hallucinations of target-class features during unpaired translation. To detect hallucination, we design a dual-head discriminator that additionally performs semantic segmentation to identify hallucinated content in background regions. To suppress these hallucinations, we introduce class-specific prototypes, constructed by aggregating features of annotated target-domain objects, which act as semantic anchors for each class. Built upon a Schrodinger Bridge-based translation model, our framework performs iterative refinement, where detected hallucination features are explicitly pushed away from class prototypes in feature space, thus preserving object semantics across the translation trajectory.Experiments show that our method outperforms existing approaches both qualitatively and quantitatively. On the BDD100K dataset, it improves mAP by 15.5% for day-to-night domain adaptation, with a notable 31.7% gain for classes such as traffic lights that are prone to hallucinations. --- ### Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems Authors: Xiaoze Liu, Ruowang Zhang, Weichen Yu, Siheng Xiong, Liu He, Feijie Wu, Hoin Jung, Matt Fredrikson, Xiaoqian Wang, Jing Gao Published: 2026-02-17 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15382v3 Heterogeneous multi-agent systems combine models with different capabilities through a common communication interface. Exchanging internal states directly requires translating between model-specific representations and controlling intermediate computation. We introduce the Vision Wormhole, which repurposes the visual input interface of Vision-Language Models (VLMs) for continuous communication between frozen heterogeneous agents. A Universal Visual Codec encodes each sender's latent rollout into a fixed-size message, maps it through a shared reference space, and decodes received messages into the receiver's image-token span. Per-model codecs and affine reference maps form a hub-and-spoke architecture with $O(N)$ components for $N$ models. Each model learns its codec independently through self-distillation on anchor texts, and shared-anchor alignment enables reuse across communication partners. Across four VLM families, six team configurations, and nine reasoning benchmarks, Vision Wormhole improves accuracy by 6.0 percentage points on average over text-mediated MAS and achieves a 1.69$\times$ geometric-mean speedup in batch-normalized end-to-end runtime. --- ### The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems Authors: Xiaoze Liu, Ruowang Zhang, Weichen Yu, Siheng Xiong, Liu He, Feijie Wu, Hoin Jung, Matt Fredrikson, Xiaoqian Wang, Jing Gao Published: 2026-02-17 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.15382v2 Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete text communication, which imposes runtime overhead and information quantization loss. While latent state transfer offers an alternative, existing approaches either assume homogeneous sender--receiver architectures or rely on pair-specific learned translators, limiting scalability across diverse model families with disjoint manifolds. We reconceptualize the visual interface of Vision-Language Models (VLMs), trained for natural images, as a continuous communication channel between heterogeneous agents, and instantiate this idea as the \textbf{Vision Wormhole}: a Universal Visual Codec maps reasoning traces into a shared continuous reference space and injects them into the receiver's visual pathway, yielding cross-architecture latent state transfer without per-pair translators. The framework adopts a hub-and-spoke topology that reduces alignment complexity from $O(N^2)$ to $O(N)$, and is trained by label-free teacher--student distillation against the text channel, requiring no parallel hidden-state supervision. Extensive experiments across heterogeneous VLM families (Qwen-VL, Gemma, SmolVLM2, LFM2.5-VL) and nine reasoning benchmarks show that the Vision Wormhole reduces end-to-end wall-clock time across most evaluated settings and yields positive macro-average $Δ$-accuracy. --- ### Automatic Funny Scene Extraction from Long-form Cinematic Videos Authors: Sibendu Paul, Haotian Jiang, Caren Chen Published: 2026-02-17 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2602.15381v1 Automatically extracting engaging and high-quality humorous scenes from cinematic titles is pivotal for creating captivating video previews and snackable content, boosting user engagement on streaming platforms. Long-form cinematic titles, with their extended duration and complex narratives, challenge scene localization, while humor's reliance on diverse modalities and its nuanced style add further complexity. This paper introduces an end-to-end system for automatically identifying and ranking humorous scenes from long-form cinematic titles, featuring shot detection, multimodal scene localization, and humor tagging optimized for cinematic content. Key innovations include a novel scene segmentation approach combining visual and textual cues, improved shot representations via guided triplet mining, and a multimodal humor tagging framework leveraging both audio and text. Our system achieves an 18.3% AP improvement over state-of-the-art scene detection on the OVSD dataset and an F1 score of 0.834 for detecting humor in long text. Extensive evaluations across five cinematic titles demonstrate 87% of clips extracted by our pipeline are intended to be funny, while 98% of scenes are accurately localized. With successful generalization to trailers, these results showcase the pipeline's potential to enhance content creation workflows, improve user engagement, and streamline snackable content generation for diverse cinematic media formats. --- ### Fractional-Order Federated Learning Authors: Mohammad Partohaghighi, Roummel Marcia, YangQuan Chen Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15380v1 Federated learning (FL) allows remote clients to train a global model collaboratively while protecting client privacy. Despite its privacy-preserving benefits, FL has significant drawbacks, including slow convergence, high communication cost, and non-independent-and-identically-distributed (non-IID) data. In this work, we present a novel FedAvg variation called Fractional-Order Federated Averaging (FOFedAvg), which incorporates Fractional-Order Stochastic Gradient Descent (FOSGD) to capture long-range relationships and deeper historical information. By introducing memory-aware fractional-order updates, FOFedAvg improves communication efficiency and accelerates convergence while mitigating instability caused by heterogeneous, non-IID client data. We compare FOFedAvg against a broad set of established federated optimization algorithms on benchmark datasets including MNIST, FEMNIST, CIFAR-10, CIFAR-100, EMNIST, the Cleveland heart disease dataset, Sent140, PneumoniaMNIST, and Edge-IIoTset. Across a range of non-IID partitioning schemes, FOFedAvg is competitive with, and often outperforms, these baselines in terms of test performance and convergence speed. On the theoretical side, we prove that FOFedAvg converges to a stationary point under standard smoothness and bounded-variance assumptions for fractional order $0<α\le 1$. Together, these results show that fractional-order, memory-aware updates can substantially improve the robustness and effectiveness of federated learning, offering a practical path toward distributed training on heterogeneous data. --- ### FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations Authors: Zhihao Shu, Md Musfiqur Rahman Sanim, Hangyu Zheng, Kunxiong Zhu, Miao Yin, Gagan Agrawal, Wei Niu Published: 2026-02-17 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2602.15379v1 The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational resources. Existing DNN acceleration frameworks primarily deploy a weight preloading strategy, where all model parameters are loaded into memory before execution on mobile GPUs. We posit that this approach is not adequate for modern DNN workloads that comprise very large model(s) and possibly execution of several distinct models in succession. In this work, we introduce FlashMem, a memory streaming framework designed to efficiently execute large-scale modern DNNs and multi-DNN workloads while minimizing memory consumption and reducing inference latency. Instead of fully preloading weights, FlashMem statically determines model loading schedules and dynamically streams them on demand, leveraging 2.5D texture memory to minimize data transformations and improve execution efficiency. Experimental results on 11 models demonstrate that FlashMem achieves 2.0x to 8.4x memory reduction and 1.7x to 75.0x speedup compared to existing frameworks, enabling efficient execution of large-scale models and multi-DNN support on resource-constrained mobile GPUs. --- ### Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language Authors: Prathamesh Devadiga, Paras Chopra Published: 2026-02-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15378v1 Can large language models converse in languages virtually absent from their training data? We investigate this question through a case study on Tulu, a Dravidian language with over 2 million speakers but minimal digital presence. Rather than fine-tuning an LLM, we examine whether structured prompts alone can elicit basic conversational ability under controlled prompting. We systematically tackle various challenges posed by absence of training data for Tulu by combining explicit grammar documentation, negative constraints to suppress high-probability tokens from related languages, romanization standardization, and quality-controlled synthetic data generation via self-play. Evaluated on a manually curated held-out set across three LLMs (Gemini 2.0 Flash, GPT-4o, Llama 3.1 70B) and validated by native speakers, our approach reduces vocabulary contamination from 80% to 5% while achieving 85% grammatical accuracy. Cross-model analysis reveals that negative constraints provide consistent improvements (12--18 percentage points), while grammar documentation effects vary by model architecture (8--22 points). --- ### Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework Authors: Mengze Hong, Chen Jason Zhang, Zichang Guo, Hanlin Gu, Di Jiang, Li Qing Published: 2026-02-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.15377v1 Customer service automation has seen growing demand within digital transformation. Existing approaches either rely on modular system designs with extensive agent orchestration or employ over-simplified instruction schemas, providing limited guidance and poor generalizability. This paper introduces an orchestration-free framework using Task-Oriented Flowcharts (TOFs) to enable end-to-end automation without manual intervention. We first define the components and evaluation metrics for TOFs, then formalize a cost-efficient flowchart construction algorithm to abstract procedural knowledge from service dialogues. We emphasize local deployment of small language models and propose decentralized distillation with flowcharts to mitigate data scarcity and privacy issues in model training. Extensive experiments validate the effectiveness in various service tasks, with superior quantitative and application performance compared to strong baselines and market products. By releasing a web-based system demonstration with case studies, we aim to promote streamlined creation of future service automation. --- ### A Unified Evaluation of Learning-Based Similarity Techniques for Malware Detection Authors: Udbhav Prasad, Aniesh Chawla Published: 2026-02-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.15376v1 Cryptographic digests (e.g., MD5, SHA-256) are designed to provide exact identity. Any single-bit change in the input produces a completely different hash, which is ideal for integrity verification but limits their usefulness in many real-world tasks like threat hunting, malware analysis and digital forensics, where adversaries routinely introduce minor transformations. Similarity-based techniques address this limitation by enabling approximate matching, allowing related byte sequences to produce measurably similar fingerprints. Modern enterprises manage tens of thousands of endpoints with billions of files, making the effectiveness and scalability of the proposed techniques more important than ever in security applications. Security researchers have proposed a range of approaches, including similarity digests and locality-sensitive hashes (e.g., ssdeep, sdhash, TLSH), as well as more recent machine-learning-based methods that generate embeddings from file features. However, these techniques have largely been evaluated in isolation, using disparate datasets and evaluation criteria. This paper presents a systematic comparison of learning-based classification and similarity methods using large, publicly available datasets. We evaluate each method under a unified experimental framework with industry-accepted metrics. To our knowledge, this is the first reproducible study to benchmark these diverse learning-based similarity techniques side by side for real-world security workloads. Our results show that no single approach performs well across all dimensions; instead, each exhibits distinct trade-offs, indicating that effective malware analysis and threat-hunting platforms must combine complementary classification and similarity techniques rather than rely on a single method. --- ### Far Out: Evaluating Language Models on Slang in Australian and Indian English Authors: Deniz Kaya Dilsiz, Dipankar Srirag, Aditya Joshi Published: 2026-02-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.15373v2 Language models exhibit systematic performance gaps when processing text in non-standard language varieties, yet their ability to comprehend variety-specific slang remains underexplored for several languages. We present a comprehensive evaluation of slang awareness in Indian English (en-IN) and Australian English (en-AU) across seven state-of-the-art language models. We construct two complementary datasets: WEB, containing 377 web-sourced usage examples from Urban Dictionary, and GEN, featuring 1,492 synthetically generated usages of these slang terms, across diverse scenarios. We assess language models on three tasks: target word prediction (TWP), guided target word prediction (TWP$^*$) and target word selection (TWS). Our results reveal four key findings: (1) Higher average model performance TWS versus TWP and TWP$^*$, with average accuracy score increasing from 0.03 to 0.49 respectively (2) Stronger average model performance on WEB versus GEN datasets, with average similarity score increasing by 0.03 and 0.05 across TWP and TWP$^*$ tasks respectively (3) en-IN tasks outperform en-AU when averaged across all models and datasets, with TWS demonstrating the largest disparity, increasing average accuracy from 0.44 to 0.54. These findings underscore fundamental asymmetries between generative and discriminative competencies for variety-specific language, particularly in the context of slang expressions despite being in a technologically rich language such as English. --- ### GMAIL: Generative Modality Alignment for generated Image Learning Authors: Shentong Mo, Sukmin Yun Published: 2026-02-17 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2602.15368v1 Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the indiscriminate use of generated images as real images for training can even cause mode collapse due to modality discrepancies between real and synthetic domains. In this paper, we propose a novel framework for discriminative use of generated images, coined GMAIL, that explicitly treats generated images as a separate modality from real images. Instead of indiscriminately replacing real images with generated ones in the pixel space, our approach bridges the two distinct modalities in the same latent space through a multi-modal learning approach. To be specific, we first fine-tune a model exclusively on generated images using a cross-modality alignment loss and then employ this aligned model to further train various vision-language models with generated images. By aligning the two modalities, our approach effectively leverages the benefits of recent advances in generative models, thereby boosting the effectiveness of generated image learning across a range of vision-language tasks. Our framework can be easily incorporated with various vision-language models, and we demonstrate its efficacy throughout extensive experiments. For example, our framework significantly improves performance on image captioning, zero-shot image retrieval, zero-shot image classification, and long caption retrieval tasks. It also shows positive generated data scaling trends and notable enhancements in the captioning performance of the large multimodal model, LLaVA. --- ### CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies Authors: Sibo Zhang, Rui Jing, Liangfu Lv, Jian Zhang, Yunliang Zang Published: 2026-02-17 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2602.15367v1 Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most existing approaches address these issues primarily through optimization strategies, while the role of architectural priors in shaping representation learning and decision dynamics is less explored. Inspired by structural principles of the cerebellum, we propose a biologically grounded RL architecture that incorporate large expansion, sparse connectivity, sparse activation, and dendritic-level modulation. Experiments on noisy, high-dimensional RL benchmarks show that both the cerebellar architecture and dendritic modulation consistently improve sample efficiency, robustness, and generalization compared to conventional designs. Sensitivity analysis of architectural parameters suggests that cerebellum-inspired structures can offer optimized performance for RL with constrained model parameters. Overall, our work underscores the value of cerebellar structural priors as effective inductive biases for RL. --- ### Automated Multi-Source Debugging and Natural Language Error Explanation for Dashboard Applications Authors: Devendra Tata, Mona Rajhans Published: 2026-02-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.15362v1 Modern web dashboards and enterprise applications increasingly rely on complex, distributed microservices architectures. While these architectures offer scalability, they introduce significant challenges in debugging and observability. When failures occur, they often manifest as opaque error messages to the end-user such as Something went wrong. This masks the underlying root cause which may reside in browser side exceptions, API contract violations, or server side logic failures. Existing monitoring tools capture these events in isolation but fail to correlate them effectively or provide intelligible explanations to non technical users. This paper proposes a novel system for Automated Multi Source Debugging and Natural Language Error Explanation. The proposed framework automatically collects and correlates error data from disparate sources such as browser, API, server logs and validates API contracts in real time, and utilizes Large Language Models to generate natural language explanations. This approach significantly reduces Mean Time to Resolution for support engineers and improves the user experience by transforming cryptic error codes into actionable insights. --- ### DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles Authors: Rong Fu, Jiekai Wu, Yang Li, Xiaowen Ma, Wangyu Wu, Simon Fong Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15355v6 The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments. --- ### DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles Authors: Rong Fu, Jiekai Wu, Yee Tan Jia, Yang Li, Xiaowen Ma, Wangyu Wu, Simon Fong Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15355v5 The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments. --- ### NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering Authors: Rong Fu, Yang Li, Zeyu Zhang, Jiekai Wu, Yaohua Liu, Shuaishuai Cao, Yangchen Zeng, Yuhang Zhang, Xiaojing Du, Simon Fong Published: 2026-02-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.15353v4 Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs provide a compact symbolic substrate for factual grounding, but integrating graph structure with neural models is nontrivial: naively embedding graph facts into prompts leads to inefficiency and fragility, while purely symbolic or search-heavy approaches can be costly in retrievals and lack gradient-based refinement. We introduce NeuroSymActive, a modular framework that combines a differentiable neural-symbolic reasoning layer with an active, value-guided exploration controller for Knowledge Graph Question Answering. The method couples soft-unification style symbolic modules with a neural path evaluator and a Monte-Carlo style exploration policy that prioritizes high-value path expansions. Empirical results on standard KGQA benchmarks show that NeuroSymActive attains strong answer accuracy while reducing the number of expensive graph lookups and model calls compared to common retrieval-augmented baselines. --- ### Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid Authors: Mohamad Chehade, Hao Zhu Published: 2026-02-17 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2602.15350v1 Public Safety Power Shutoffs (PSPS) force rapid topology changes that can render standard operating points infeasible, requiring operators to quickly identify corrective transmission switching actions that reduce load shedding while maintaining acceptable voltage behavior. We present a verifiable, multi-stage adaptation pipeline that fine-tunes an instruction-tuned large language model (LLM) to generate \emph{open-only} corrective switching plans from compact PSPS scenario summaries under an explicit switching budget. First, supervised fine-tuning distills a DC-OPF MILP oracle into a constrained action grammar that enables reliable parsing and feasibility checks. Second, direct preference optimization refines the policy using AC-evaluated preference pairs ranked by a voltage-penalty metric, injecting voltage-awareness beyond DC imitation. Finally, best-of-$N$ selection provides an inference-time addition by choosing the best feasible candidate under the target metric. On IEEE 118-bus PSPS scenarios, fine-tuning substantially improves DC objective values versus zero-shot generation, reduces AC power-flow failure from 50\% to single digits, and improves voltage-penalty outcomes on the common-success set. Code and data-generation scripts are released to support reproducibility. --- ### CREMD: Crowd-Sourced Emotional Multimodal Dogs Dataset Authors: Jinho Baek, Houwei Cao, Kate Blackwell Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15349v1 Dog emotion recognition plays a crucial role in enhancing human-animal interactions, veterinary care, and the development of automated systems for monitoring canine well-being. However, accurately interpreting dog emotions is challenging due to the subjective nature of emotional assessments and the absence of standardized ground truth methods. We present the CREMD (Crowd-sourced Emotional Multimodal Dogs Dataset), a comprehensive dataset exploring how different presentation modes (e.g., context, audio, video) and annotator characteristics (e.g., dog ownership, gender, professional experience) influence the perception and labeling of dog emotions. The dataset consists of 923 video clips presented in three distinct modes: without context or audio, with context but no audio, and with both context and audio. We analyze annotations from diverse participants, including dog owners, professionals, and individuals with varying demographic backgrounds and experience levels, to identify factors that influence reliable dog emotion recognition. Our findings reveal several key insights: (1) while adding visual context significantly improved annotation agreement, our findings regarding audio cues are inconclusive due to design limitations (specifically, the absence of a no-context-with-audio condition and limited clean audio availability); (2) contrary to expectations, non-owners and male annotators showed higher agreement levels than dog owners and female annotators, respectively, while professionals showed higher agreement levels, aligned with our initial hypothesis; and (3) the presence of audio substantially increased annotators' confidence in identifying specific emotions, particularly anger and fear. --- ### Effective and Robust Multimodal Medical Image Analysis Authors: Joy Dhar, Nayyar Zaidi, Maryam Haghighat Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15346v1 Multimodal Fusion Learning (MFL), leveraging disparate data from various imaging modalities (e.g., MRI, CT, SPECT), has shown great potential for addressing medical problems such as skin cancer and brain tumor prediction. However, existing MFL methods face three key limitations: a) they often specialize in specific modalities, and overlook effective shared complementary information across diverse modalities, hence limiting their generalizability for multi-disease analysis; b) they rely on computationally expensive models, restricting their applicability in resource-limited settings; and c) they lack robustness against adversarial attacks, compromising reliability in medical AI applications. To address these limitations, we propose a novel Multi-Attention Integration Learning (MAIL) network, incorporating two key components: a) an efficient residual learning attention block for capturing refined modality-specific multi-scale patterns and b) an efficient multimodal cross-attention module for learning enriched complementary shared representations across diverse modalities. Furthermore, to ensure adversarial robustness, we extend MAIL network to design Robust-MAIL by incorporating random projection filters and modulated attention noise. Extensive evaluations on 20 public datasets show that both MAIL and Robust-MAIL outperform existing methods, achieving performance gains of up to 9.34% while reducing computational costs by up to 78.3%. These results highlight the superiority of our approaches, ensuring more reliable predictions than top competitors. Code: https://github.com/misti1203/MAIL-Robust-MAIL. --- ### ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models Authors: Mitchell Piehl, Zhaohan Xi, Zuobin Xiong, Pan He, Muchao Ye Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15344v1 Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable because memory provides extra attack surfaces. In this paper, we present the first systematic study of black-box adversarial memory injection attacks that target the similarity-based retrieval mechanism in long-term memory-augmented LLMs. We introduce ER-MIA, a unified framework that exposes this vulnerability and formalizes two realistic attack settings: content-based attacks and question-targeted attacks. In these settings, ER-MIA includes an arsenal of composable attack primitives and ensemble attacks that achieve high success rates under minimal attacker assumptions. Extensive experiments across multiple LLMs and long-term memory systems demonstrate that similarity-based retrieval constitutes a fundamental and system-level vulnerability, revealing security risks that persist across memory designs and application scenarios. --- ### Benchmarking Self-Supervised Models for Cardiac Ultrasound View Classification Authors: Youssef Megahed, Salma I. Megahed, Robin Ducharme, Inok Lee, Adrian D. C. Chan, Mark C. Walker, Steven Hawken Published: 2026-02-17 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.15339v1 Reliable interpretation of cardiac ultrasound images is essential for accurate clinical diagnosis and assessment. Self-supervised learning has shown promise in medical imaging by leveraging large unlabelled datasets to learn meaningful representations. In this study, we evaluate and compare two self-supervised learning frameworks, USF-MAE, developed by our team, and MoCo v3, on the recently introduced CACTUS dataset (37,736 images) for automated simulated cardiac view (A4C, PL, PSAV, PSMV, Random, and SC) classification. Both models used 5-fold cross-validation, enabling robust assessment of generalization performance across multiple random splits. The CACTUS dataset provides expert-annotated cardiac ultrasound images with diverse views. We adopt an identical training protocol for both models to ensure a fair comparison. Both models are configured with a learning rate of 0.0001 and a weight decay of 0.01. For each fold, we record performance metrics including ROC-AUC, accuracy, F1-score, and recall. Our results indicate that USF-MAE consistently outperforms MoCo v3 across metrics. The average testing AUC for USF-MAE is 99.99% (+/-0.01% 95% CI), compared to 99.97% (+/-0.01%) for MoCo v3. USF-MAE achieves a mean testing accuracy of 99.33% (+/-0.18%), higher than the 98.99% (+/-0.28%) reported for MoCo v3. Similar trends are observed for the F1-score and recall, with improvements statistically significant across folds (paired t-test, p=0.0048 < 0.01). This proof-of-concept analysis suggests that USF-MAE learns more discriminative features for cardiac view classification than MoCo v3 when applied to this dataset. The enhanced performance across multiple metrics highlights the potential of USF-MAE for improving automated cardiac ultrasound classification. --- ### Discovering Implicit Large Language Model Alignment Objectives Authors: Edward Chen, Sanmi Koyejo, Carlos Guestrin Published: 2026-02-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.15338v2 Large language model (LLM) alignment relies on complex reward signals that often obscure the specific behaviors being incentivized, creating critical risks of misalignment and reward hacking. Existing interpretation methods typically rely on pre-defined rubrics, risking the omission of "unknown unknowns", or fail to identify objectives that comprehensively cover and are causal to the model behavior. To address these limitations, we introduce Obj-Disco, a framework that automatically decomposes an alignment reward signal into a sparse, weighted combination of human-interpretable natural language objectives. Our approach utilizes an iterative greedy algorithm to analyze behavioral changes across training checkpoints, identifying and validating candidate objectives that best explain the residual reward signal. Extensive evaluations across diverse tasks, model sizes, and alignment algorithms demonstrate the framework's robustness. Experiments with popular open-source reward models show that the framework consistently captures > 90% of reward behavior, a finding further corroborated by human evaluation. Additionally, a case study on alignment with an open-source reward model reveals that Obj-Disco can successfully identify latent misaligned incentives that emerge alongside intended behaviors. Our work provides a crucial tool for uncovering the implicit objectives in LLM alignment, paving the way for more transparent and safer AI development. --- ### FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning Authors: Chaoyi Lu, Yiding Sun, Zhichuan Yang, Jinqian Chen, Dongfu Yin, Jihua Zhu Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15337v2 Asynchronous Federated Learning (AFL) has emerged as a significant research area in recent years. By not waiting for slower clients and executing the training process concurrently, it achieves faster training speed compared to traditional federated learning. However, due to the staleness introduced by the asynchronous process, its performance may degrade in some scenarios. Existing methods often use the round difference between the current model and the global model as the sole measure of staleness, which is coarse-grained and lacks observation of the model itself, thereby limiting the performance ceiling of asynchronous methods. In this paper, we propose FedPSA (Parameter Sensitivity-based Asynchronous Federated Learning), a more fine-grained AFL framework that leverages parameter sensitivity to measure model obsolescence and establishes a dynamic momentum queue to assess the current training phase in real time, thereby adjusting the tolerance for outdated information dynamically. Extensive experiments on multiple datasets and comparisons with various methods demonstrate the superior performance of FedPSA, achieving up to 6.37\% improvement over baseline methods and 1.93\% over the current state-of-the-art method. --- ### Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models Authors: Waldemar Chang Published: 2026-02-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.15332v2 Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens correlated with an answer, but rarely reveal where consequential reasoning turns occur, which earlier context triggers them under causal intervention, or whether highlighted text actually steers the rollout. We introduce Directional Reasoning Trajectory Change (DRTC), a process-causal method that (i) detects pivot decision points via uncertainty and distribution-shift signals and (ii) applies receiver-side interventions that preserve the realized continuation without resampling while blocking information flow from selected earlier chunks only at a pivot. DRTC measures how each intervention redirects the log-probability trajectory relative to the realized rollout direction, yielding signed per-chunk attributions; we also compute logit-space curvature changes and curvature signatures as a complementary geometric diagnostic. Across four reasoning models, influence is sharply concentrated (Gini approximately 0.50-0.58, top-5% mass approximately 0.23-0.28), and learned pivots induce stronger effects than matched random spans. In a 500-problem MATH scaling study with R1-Distill-Qwen-1.5B, learned spans continue to outperform matched random spans (median Delta=0.409, 355/500 positive; p=2.3e-21), and curvature-impact co-localizes with DRTC within traces as a diagnostic. We benchmark against gradient- and perturbation-based chunk attributions and show graded outcome linkage: under embedding-interpolation edits, top-ranked DRTC chunks reduce teacher-forced gold-answer log-probability more than strict position-matched random chunks on a stability-filtered subset. Overall, DRTC provides a causally grounded view of how specific context elements steer on-policy reasoning trajectories. ---