# Research Papers — 2026-02 · bundle page 43 of 210

> Full-text markdown of papers #2101–2150 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/43
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/42.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/44.md)

### A Computationally Efficient Multidimensional Vision Transformer

Authors: Alaa El Ichi, Khalide Jbilou
Published: 2026-02-23
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.19982v1

Vision Transformers have achieved state-of-the-art performance in a wide range of computer vision tasks, but their practical deployment is limited by high computational and memory costs. In this paper, we introduce a novel tensor-based framework for Vision Transformers built upon the Tensor Cosine Product (Cproduct). By exploiting multilinear structures inherent in image data and the orthogonality of cosine transforms, the proposed approach enables efficient attention mechanisms and structured feature representations. We develop the theoretical foundations of the tensor cosine product, analyze its algebraic properties, and integrate it into a new Cproduct-based Vision Transformer architecture (TCP-ViT). Numerical experiments on standard classification and segmentation benchmarks demonstrate that the proposed method achieves a uniform 1/C parameter reduction (where C is the number of channels) while maintaining competitive accuracy.

---

### Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks

Authors: Itamar Trainin, Shauli Ravfogel, Omri Abend, Amir Feder
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19980v1

While Autoregressive (AR) Transformer-based Generative Language Models are frequently employed for lookahead tasks, recent research suggests a potential discrepancy in their ability to perform planning tasks that require multi-step lookahead. In this work, we investigate the distinct emergent mechanisms that arise when training AR versus Non-Autoregressive (NAR) models, such as Discrete Diffusion Models (dLLMs), on lookahead tasks. By requiring the models to plan ahead to reach the correct conclusion, we analyze how these two paradigms fundamentally differ in their approach to the problem. We identify a critical asymmetry in planning problems: while forward generation requires complex lookahead at branching junctions, reverse generation is often deterministic. This asymmetry creates an opportunity for NAR models. Through mechanistic analysis of training and inference dynamics, we demonstrate that NAR models learn to solve planning tasks by utilizing future tokens to decode backwards, avoiding the need to learn complex traversal mechanisms entirely. Consequently, we report that both AR and NAR models are able to achieve perfect accuracy on the lookahead task. However, NAR models require exponentially fewer training examples and shallower architectures compared to AR models, which often fail to converge without specific curriculum adjustments.

---

### RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection

Authors: Tianyu Wang, Zhiyuan Ma, Qian Wang, Xinyi Zhang, Xinwei Long, Bowen Zhou
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19974v2

Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models still generally struggle with a spatial reasoning dilemma, lacking the ability to accurately capture fine-grained spatial relationships from the prompt and correctly generate scenes with structural integrity. To mitigate this dilemma, we propose RL-RIG, a Reinforcement Learning framework for Reflection-based Image Generation. Our architecture comprises four primary components: Diffuser, Checker, Actor, and Inverse Diffuser, following a Generate-Reflect-Edit paradigm to spark the Chain of Thought reasoning ability in image generation for addressing the dilemma. To equip the model with better intuition over generation trajectories, we further develop Reflection-GRPO to train the VLM Actor for edit prompts and the Image Editor for better image quality under a given prompt, respectively. Unlike traditional approaches that solely produce visually stunning yet structurally unreasonable content, our evaluation metrics prioritize spatial accuracy, utilizing Scene Graph IoU and employing a VLM-as-a-Judge strategy to assess the spatial consistency of generated images on LAION-SG dataset. Experimental results show that RL-RIG outperforms existing state-of-the-art open-source models by up to 11% in terms of controllable and precise spatial reasoning in image generation.

---

### ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting

Authors: Yuxing Tian, Fengran Mo, Weixu Zhang, Yiyan Qi, Jian-Yun Nie
Published: 2026-02-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.19969v1

The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an efficient and interpretable alternative to generation-based re-ranking methods. However, they still face two major limitations. First, attention signals are highly concentrated a small subset of tokens within a few documents, making others indistinguishable. Second, attention often overemphasizes phrases lexically similar to the query, yielding biased rankings that irrelevant documents with mere lexical resemblance are regarded as relevant. In this paper, we propose \textbf{ReAttn}, a post-hoc re-weighting strategy for attention-based re-ranking methods. It first compute the cross-document IDF weighting to down-weight attention on query-overlapping tokens that frequently appear across the candidate documents, reducing lexical bias and emphasizing distinctive terms. It then employs entropy-based regularization to mitigate over-concentrated attention, encouraging a more balanced distribution across informative tokens. Both adjustments operate directly on existing attention weights without additional training or supervision. Extensive experiments demonstrate the effectiveness of our method.

---

### Unlearning Noise in PINNs: A Selective Pruning Framework for PDE Inverse Problems

Authors: Yongsheng Chen, Yong Chen, Wei Guo, Xinghui Zhong
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19967v3

Physics-informed neural networks (PINNs) provide a promising framework for solving inverse problems governed by partial differential equations (PDEs) by integrating observational data and physical constraints in a unified optimization objective. However, the ill-posed nature of PDE inverse problems makes them highly sensitive to noise. Even a small fraction of corrupted observations can distort internal neural representations, severely impairing accuracy and destabilizing training. Motivated by recent advances in machine unlearning and structured network pruning, we propose P-PINN, a selective pruning framework designed to unlearn the influence of corrupted data in a pretrained PINN. Specifically, starting from a PINN trained on the full dataset, P-PINN evaluates a joint residual--data fidelity indicator, a weighted combination of data misfit and PDE residuals, to partition the training set into reliable and corrupted subsets. Next, we introduce a bias-based neuron importance measure that quantifies directional activation discrepancies between the two subsets, identifying neurons whose representations are predominantly driven by corrupted samples. Building on this, an iterative pruning strategy then removes noise-sensitive neurons layer by layer. The resulting pruned network is fine-tuned on the reliable data subject to the original PDE constraints, acting as a lightweight post-processing stage rather than a complete retraining. Numerical experiments on extensive PDE inverse-problem benchmarks demonstrate that P-PINN substantially improves robustness, accuracy, and training stability under noisy conditions, achieving up to a 96.6% reduction in relative error compared with baseline PINNs. These results indicate that activation-level post hoc pruning is a promising mechanism for enhancing the reliability of physics-informed learning in noise-contaminated settings.

---

### On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference

Authors: Moritz A. Zanger, Yijun Wu, Pascal R. Van der Vaart, Wendelin Böhmer, Matthijs T. J. Spaan
Published: 2026-02-23
Categories: cs.LG, cs.AI, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2602.19964v2

Uncertainty quantification is central to safe and efficient deployments of deep learning models, yet many computationally practical methods lack lacking rigorous theoretical motivation. Random network distillation (RND) is a lightweight technique that measures novelty via prediction errors against a fixed random target. While empirically effective, it has remained unclear what uncertainties RND measures and how its estimates relate to other approaches, e.g. Bayesian inference or deep ensembles. This paper establishes these missing theoretical connections by analyzing RND within the neural tangent kernel framework in the limit of infinite network width. Our analysis reveals two central findings in this limit: (1) The uncertainty signal from RND -- its squared self-predictive error -- is equivalent to the predictive variance of a deep ensemble. (2) By constructing a specific RND target function, we show that the RND error distribution can be made to mirror the centered posterior predictive distribution of Bayesian inference with wide neural networks. Based on this equivalence, we moreover devise a posterior sampling algorithm that generates i.i.d. samples from an exact Bayesian posterior predictive distribution using this modified \textit{Bayesian RND} model. Collectively, our findings provide a unified theoretical perspective that places RND within the principled frameworks of deep ensembles and Bayesian inference, and offer new avenues for efficient yet theoretically grounded uncertainty quantification methods.

---

### Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

Authors: Yibo Yan, Jiahao Huo, Guanbo Feng, Mingdong Ou, Yi Cao, Xin Zou, Shuliang Liu, Yuanhuiyi Lyu, Yu Huang, Jungang Li, Kening Zheng, Xu Zheng et al.
Published: 2026-02-23
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.19961v3

With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper surveys the VDR landscape as a retrieval problem in its own right, rather than as the front end of a generation pipeline, and does so specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, including the recent turn toward reasoning-intensive evaluation, and then dive into the methodological evolution along two orthogonal axes: what a retriever is, spanning multimodal embedding models and reranker models, and how it is deployed, from single-stage retrieval through Retrieval-Augmented Generation (RAG) to Agentic systems. Cutting across both, we analyse the representation--efficiency trade-off that late interaction imposes. We ground these categories in leaderboard evidence on where the empirical frontier actually lies, and close by identifying persistent challenges and outlining promising future directions for multimodal document intelligence.

---

### Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

Authors: Yibo Yan, Jiahao Huo, Guanbo Feng, Mingdong Ou, Yi Cao, Xin Zou, Shuliang Liu, Yuanhuiyi Lyu, Yu Huang, Jungang Li, Kening Zheng, Xu Zheng et al.
Published: 2026-02-23
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.19961v2

With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper presents the first comprehensive survey of the VDR landscape, specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, and subsequently dive into the methodological evolution, categorizing approaches into three primary aspects: multimodal embedding models, multimodal reranker models, and the integration of Retrieval-Augmented Generation (RAG) and Agentic systems for complex document intelligence. Finally, we identify persistent challenges and outline promising future directions, aiming to provide a clear roadmap for future multimodal document intelligence.

---

### Sparse Masked Attention Policies for Reliable Generalization

Authors: Caroline Horsch, Laurens Engwegen, Max Weltevrede, Matthijs T. J. Spaan, Wendelin Böhmer
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19956v1

In reinforcement learning, abstraction methods that remove unnecessary information from the observation are commonly used to learn policies which generalize better to unseen tasks. However, these methods often overlook a crucial weakness: the function which extracts the reduced-information representation has unknown generalization ability in unseen observations. In this paper, we address this problem by presenting an information removal method which more reliably generalizes to new states. We accomplish this by using a learned masking function which operates on, and is integrated with, the attention weights within an attention-based policy network. We demonstrate that our method significantly improves policy generalization to unseen tasks in the Procgen benchmark compared to standard PPO and masking approaches.

---

### A Bayesian Framework for Post-disruption Travel Time Prediction in Metro Networks

Authors: Shayan Nazemi, Aurélie Labbe, Stefan Steiner, Pratheepa Jeganathan, Martin Trépanier, Léo R. Belzile
Published: 2026-02-23
Categories: stat.AP, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.19952v1

Disruptions are an inherent feature of transportation systems, occurring unpredictably and with varying durations. Even after an incident is reported as resolved, disruptions can induce irregular train operations that generate substantial uncertainty in passenger waiting and travel times. Accurately forecasting post-disruption travel times therefore remains a critical challenge for transit operators and passenger information systems. This paper develops a Bayesian spatiotemporal modeling framework for post-disruption train travel times that explicitly captures train interactions, headway imbalance, and non-Gaussian distributional characteristics observed during recovery periods. The proposed model decomposes travel times into delay and journey components and incorporates a moving-average error structure to represent dependence between consecutive trains. Skew-normal and skew-$t$ distributions are employed to flexibly accommodate heteroskedasticity, skewness, and heavy-tailed behavior in post-disruption travel times. The framework is evaluated using high-resolution track-occupancy and disruption log data from the Montréal metro system, covering two lines in both travel directions. Empirical results indicate that post-disruption travel times exhibit pronounced distributional asymmetries that vary with traveled distance, as well as significant error dependence across trains. The proposed models consistently outperform baseline specifications in both point prediction accuracy and uncertainty quantification, with the skew-$t$ model demonstrating the most robust performance for longer journeys. These findings underscore the importance of incorporating both distributional flexibility and error dependence when forecasting post-disruption travel times in urban rail systems.

---

### Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

Authors: Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore
Published: 2026-02-23
Categories: cs.CL, cs.AI, cs.CY, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2602.19948v2

Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue. We introduce an evaluation framework that pairs AI psychotherapists with simulated patient agents equipped with dynamic cognitive-affective models and assesses therapy session simulations against a comprehensive quality of care and risk ontology. We apply this framework to a high-impact test case, Alcohol Use Disorder, evaluating six AI agents (including ChatGPT, Gemini, and Character AI) against a clinically-validated cohort of 15 patient personas representing diverse clinical phenotypes. Our large-scale simulation (N=369 sessions) reveals critical safety gaps in the use of AI for mental health support. We identify specific iatrogenic risks, including the validation of patient delusions ("AI Psychosis") and failure to de-escalate suicide risk. Finally, we validate an interactive data visualization dashboard with diverse stakeholders, including AI engineers and red teamers, mental health professionals, and policy experts (N=9), demonstrating that this framework effectively enables stakeholders to audit the "black box" of AI psychotherapy. These findings underscore the critical safety risks of AI-provided mental health support and the necessity of simulation-based clinical red teaming before deployment.

---

### When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

Authors: Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19946v5

Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a surprising performance regression. We generate large-scale synthetic datasets using state-of-the-art T2I models released between 2022 and 2025, train standard classifiers solely on this synthetic data, and evaluate them on real test data. Despite observable advances in visual fidelity and prompt adherence, classification accuracy on real test data consistently declines with newer T2I models as training data generators. Our analysis reveals a hidden trend: These models collapse to a narrow, aesthetic-centric distribution that undermines diversity and real data distribution coverage. Overall, our findings challenge a growing assumption in vision research, namely that progress in generative realism implies progress in data realism. We thus highlight an urgent need to rethink the capabilities of modern T2I models as reliable training data generators.

---

### DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models

Authors: Jin Liu, Yinbin Miao, Ning Xi, Junkang Liu
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19945v1

Balancing convergence efficiency and robustness under Differential Privacy (DP) is a central challenge in Federated Learning (FL). While AdamW accelerates training and fine-tuning in large-scale models, we find that directly applying it to Differentially Private FL (DPFL) suffers from three major issues: (i) data heterogeneity and privacy noise jointly amplify the variance of second-moment estimator, (ii) DP perturbations bias the second-moment estimator, and (iii) DP amplify AdamW sensitivity to local overfitting, worsening client drift. We propose DP-FedAdamW, the first AdamW-based optimizer for DPFL. It restores AdamW under DP by stabilizing second-moment variance, removing DP-induced bias, and aligning local updates to the global descent to curb client drift. Theoretically, we establish an unbiased second-moment estimator and prove a linearly accelerated convergence rate without any heterogeneity assumption, while providing tighter $(\varepsilon,δ)$-DP guarantees. Our empirical results demonstrate the effectiveness of DP-FedAdamW across language and vision Transformers and ResNet-18. On Tiny-ImageNet (Swin-Base, $\varepsilon=1$), DP-FedAdamW outperforms the state-of-the-art (SOTA) by 5.83\%. The code is available in Appendix.

---

### Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation

Authors: Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19944v1

Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged object discovery often leads to inaccurate localization, false positives, and missed detections. To address these issues, we propose the \textbf{D}iscover-\textbf{S}egment-\textbf{S}elect (\textbf{DSS}) mechanism, a progressive framework designed to refine segmentation step by step. The proposed method contains a Feature-coherent Object Discovery (FOD) module that leverages visual features to generate diverse object proposals, a segmentation module that refines these proposals through SAM segmentation, and a Semantic-driven Mask Selection (SMS) module that employs MLLMs to evaluate and select the optimal segmentation mask from multiple candidates. Without requiring any training or supervision, DSS achieves state-of-the-art performance on multiple COS benchmarks, especially in multiple-instance scenes.

---

### A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs

Authors: Zijie Liu, Jie Peng, Jinhao Duan, Zirui Liu, Kaixiong Zhou, Mingfu Liang, Luke Simon, Xi Liu, Zhaozhuo Xu, Tianlong Chen
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19938v2

Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets. However, SMoE models often suffer from severe load imbalance across experts, where a small subset of experts receives most tokens while others are underutilized. Prior work has focused mainly on training-time solutions such as routing regularization or auxiliary losses, leaving inference-time behavior, which is critical for deployment, less explored. We present a systematic analysis of expert routing during inference and identify three findings: (i) load imbalance persists and worsens with larger batch sizes, (ii) selection frequency does not reliably reflect expert importance, and (iii) overall expert workload and importance can be estimated using a small calibration set. These insights motivate inference-time mechanisms that rebalance workloads without retraining or router modification. We propose Replicate-and-Quantize (R&Q), a training-free and near-lossless framework for dynamic workload rebalancing. In each layer, heavy-hitter experts are replicated to increase parallel capacity, while less critical experts and replicas are quantized to remain within the original memory budget. We also introduce a Load-Imbalance Score (LIS) to measure routing skew by comparing heavy-hitter load to an equal allocation baseline. Experiments across representative SMoE models and benchmarks show up to 1.4x reduction in imbalance with accuracy maintained within +/-0.6%, enabling more predictable and efficient inference.

---

### Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation

Authors: Yifei Shi, Boyan Wan, Xin Xu, Kai Xu
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19937v1

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape reconstruction, novel view image synthesis, and more recently, object pose estimation. Neural implicit fields enable learning dense correspondences between the camera space and the object's canonical space-including unobserved regions in camera space-significantly boosting object pose estimation performance in challenging scenarios like highly occluded objects and novel shapes. Despite progress, predicting canonical coordinates for unobserved camera-space regions remains challenging due to the lack of direct observational signals. This necessitates heavy reliance on the model's generalization ability, resulting in high uncertainty. Consequently, densely sampling points across the entire camera space may yield inaccurate estimations that hinder the learning process and compromise performance. To alleviate this problem, we propose a method combining an SO(3)-equivariant convolutional implicit network and a positive-incentive point sampling (PIPS) strategy. The SO(3)-equivariant convolutional implicit network estimates point-level attributes with SO(3)-equivariance at arbitrary query locations, demonstrating superior performance compared to most existing baselines. The PIPS strategy dynamically determines sampling locations based on the input, thereby boosting the network's accuracy and training efficiency. Our method outperforms the state-of-the-art on three pose estimation datasets. Notably, it demonstrates significant improvements in challenging scenarios, such as objects captured with unseen pose, high occlusion, novel geometry, and severe noise.

---

### Expanding the Role of Diffusion Models for Robust Classifier Training

Authors: Pin-Han Huang, Shang-Tse Chen, Hsuan-Tien Lin
Published: 2026-02-23
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.19931v1

Incorporating diffusion-generated synthetic data into adversarial training (AT) has been shown to substantially improve the training of robust image classifiers. In this work, we extend the role of diffusion models beyond merely generating synthetic data, examining whether their internal representations, which encode meaningful features of the data, can provide additional benefits for robust classifier training. Through systematic experiments, we show that diffusion models offer representations that are both diverse and partially robust, and that explicitly incorporating diffusion representations as an auxiliary learning signal during AT consistently improves robustness across settings. Furthermore, our representation analysis indicates that incorporating diffusion models into AT encourages more disentangled features, while diffusion representations and diffusion-generated synthetic data play complementary roles in shaping representations. Experiments on CIFAR-10, CIFAR-100, and ImageNet validate these findings, demonstrating the effectiveness of jointly leveraging diffusion representations and synthetic data within AT.

---

### Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning

Authors: Nathan Gavenski, Felipe Meneguzzi, Odinaldo Rodrigues
Published: 2026-02-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19930v1

Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues that this failure is not technical but foundational: imitation learning has been optimised for the wrong objective. We propose a research agenda that redefines success from perfect replay to compositional adaptability. Such adaptability hinges on learning behavioural primitives once and recombining them through novel contexts without retraining. We establish metrics for compositional generalisation, propose hybrid architectures, and outline interdisciplinary research directions drawing on cognitive science and cultural evolution. Agents that embed adaptability at the core of imitation learning thus have an essential capability for operating in an open-ended world.

---

### Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models

Authors: Jin Liu, Yinbin Miao, Ning Xi, Junkang Liu
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19926v1

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising parameter-efficient fine-tuning (PEFT) method, reduces computational and communication costs by introducing two trainable low-rank matrices while freezing pre-trained weights. However, directly applying LoRA in DPFL settings leads to performance degradation, especially in LVMs. Our analysis reveals three previously underexplored challenges: (1) gradient coupling caused by the simultaneous update of two asymmetric low-rank matrices, (2) compounded noise amplification under differential privacy, and (3) sharpness of the global aggregated model in the parameter space. To address these issues, we propose LA-LoRA (\textbf{L}ocal \textbf{A}lternating \textbf{LoRA}), a novel approach that decouples gradient interactions and aligns update directions across clients to enhance robustness under stringent privacy constraints. Theoretically, LA-LoRA strengthens convergence guarantees in noisy federated environments. Extensive experiments demonstrate that LA-LoRA achieves state-of-the-art (SOTA) performance on Swin Transformer and RoBERTa models, showcasing robustness to DP noise and broad applicability across both LVMs and LLMs. For example, when fine-tuning the Swin-B model on the Tiny-ImageNet dataset under a strict privacy budget ($ε= 1$), LA-LoRA outperforms the best baseline, RoLoRA, by 16.83\% in test accuracy. Code is provided in \repolink.

---

### Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

Authors: Xiang Li, Zikai Wei, Yiyan Qi, Wanyun Zhou, Xiang Liu, Penglei Sun, Jian Guo, Yongqi Zhang, Xiaowen Chu
Published: 2026-02-23
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.19919v2

Financial market movements are often driven by discrete financial events conveyed through news, whose impacts are heterogeneous, abrupt, and difficult to capture under purely numerical prediction objectives. These limitations have motivated growing interest in using textual information as the primary source of trading signals in learning-based systems. Two key challenges hinder existing approaches: (1) the absence of large-scale, event-centric datasets that jointly model news semantics and statistically grounded market reactions, and (2) the misalignment between language model reasoning and financially valid trading behavior under dynamic market conditions. To address these challenges, we propose Janus-Q, an end-to-end event-driven trading framework that elevates financial news events from auxiliary signals to primary decision units. Janus-Q unifies event-centric data construction and model optimization under a two-stage paradigm. Stage I focuses on event-centric data construction, building a large-scale financial news event dataset comprising 62,400 articles annotated with 10 fine-grained event types, associated stocks, sentiment labels, and event-driven cumulative abnormal return (CAR). Stage II performs decision-oriented fine-tuning, combining supervised learning with reinforcement learning guided by a Hierarchical Gated Reward Model (HGRM), which explicitly captures trade-offs among multiple trading objectives. Extensive experiments demonstrate that Janus-Q achieves more consistent, interpretable, and profitable trading decisions than market indices and LLM baselines, improving the Sharpe Ratio by up to 102.0% while increasing direction accuracy by over 17.5% compared to the strongest competing strategies.

---

### RobPI: Robust Private Inference against Malicious Client

Authors: Jiaqi Xue, Mengxin Zheng, Qian Lou
Published: 2026-02-23
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.19918v1

The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allow parties to perform inference without revealing their sensitive data. Despite recent advances in the efficiency of PI, most current methods assume a semi-honest threat model where the data owner is honest and adheres to the protocol. However, in reality, data owners can have different motivations and act in unpredictable ways, making this assumption unrealistic. To demonstrate how a malicious client can compromise the semi-honest model, we first designed an inference manipulation attack against a range of state-of-the-art private inference protocols. This attack allows a malicious client to modify the model output with 3x to 8x fewer queries than current black-box attacks. Motivated by the attacks, we proposed and implemented RobPI, a robust and resilient private inference protocol that withstands malicious clients. RobPI integrates a distinctive cryptographic protocol that bolsters security by weaving encryption-compatible noise into the logits and features of private inference, thereby efficiently warding off malicious-client attacks. Our extensive experiments on various neural networks and datasets show that RobPI achieves ~91.9% attack success rate reduction and increases more than 10x the number of queries required by malicious-client attacks.

---

### Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning

Authors: Thanh Nguyen, Tung Luu, Tri Ton, Sungwoong Kim, Chang D. Yoo
Published: 2026-02-23
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2602.19917v1

Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge: the extrapolation error stemming from out-of-distribution (OOD) data. Existing methodologies have endeavored to address this issue through means like penalizing OOD Q-values or imposing similarity constraints on the learned policy and the behavior policy. Nonetheless, these approaches are often beset by limitations such as being overly conservative in utilizing OOD data, imprecise OOD data characterization, and significant computational overhead. To address these challenges, this paper introduces an Uncertainty-Aware Rank-One Multi-Input Multi-Output (MIMO) Q Network framework. The framework aims to enhance Offline Reinforcement Learning by fully leveraging the potential of OOD data while still ensuring efficiency in the learning process. Specifically, the framework quantifies data uncertainty and harnesses it in the training losses, aiming to train a policy that maximizes the lower confidence bound of the corresponding Q-function. Furthermore, a Rank-One MIMO architecture is introduced to model the uncertainty-aware Q-function, \TP{offering the same ability for uncertainty quantification as an ensemble of networks but with a cost nearly equivalent to that of a single network}. Consequently, this framework strikes a harmonious balance between precision, speed, and memory efficiency, culminating in improved overall performance. Extensive experimentation on the D4RL benchmark demonstrates that the framework attains state-of-the-art performance while remaining computationally efficient. By incorporating the concept of uncertainty quantification, our framework offers a promising avenue to alleviate extrapolation errors and enhance the efficiency of offline RL.

---

### Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting

Authors: Yixin Yang, Bojian Wu, Yang Zhou, Hui Huang
Published: 2026-02-23
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.19916v1

Due to the real-time rendering performance, 3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction. However, its reliance on spherical harmonics for color encoding inherently limits its ability to separate diffuse and specular components, making it challenging to accurately represent complex reflections. To address this, we propose a novel enhanced Gaussian kernel that explicitly models specular effects through view-dependent opacity. Meanwhile, we introduce an error-driven compensation strategy to improve rendering quality in existing 3DGS scenes. Our method begins with 2D Gaussian initialization and then adaptively inserts and optimizes enhanced Gaussian kernels, ultimately producing an augmented radiance field. Experiments demonstrate that our method not only surpasses state-of-the-art NeRF methods in rendering performance but also achieves greater parameter efficiency. Project page at: https://xiaoxinyyx.github.io/augs.

---

### Fully Convolutional Spatiotemporal Learning for Microstructure Evolution Prediction

Authors: Michael Trimboli, Mohammed Alsubaie, Sirani M. Perera, Ke-Gang Wang, Xianqi Li
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19915v1

Understanding and predicting microstructure evolution is fundamental to materials science, as it governs the resulting properties and performance of materials. Traditional simulation methods, such as phase-field models, offer high-fidelity results but are computationally expensive due to the need to solve complex partial differential equations at fine spatiotemporal resolutions. To address this challenge, we propose a deep learning-based framework that accelerates microstructure evolution predictions while maintaining high accuracy. Our approach utilizes a fully convolutional spatiotemporal model trained in a self-supervised manner using sequential images generated from simulations of microstructural processes, including grain growth and spinodal decomposition. The trained neural network effectively learns the underlying physical dynamics and can accurately capture both short-term local behaviors and long-term statistical properties of evolving microstructures, while also demonstrating generalization to unseen spatiotemporal domains and variations in configuration and material parameters. Compared to recurrent neural architectures, our model achieves state-of-the-art predictive performance with significantly reduced computational cost in both training and inference. This work establishes a robust baseline for spatiotemporal learning in materials science and offers a scalable, data-driven alternative for fast and reliable microstructure simulations.

---

### Watson & Holmes: A Naturalistic Benchmark for Comparing Human and LLM Reasoning

Authors: Thatchawin Leelawat, Lewis D Griffin
Published: 2026-02-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.19914v1

Existing benchmarks for AI reasoning provide limited insight into how closely these capabilities resemble human reasoning in naturalistic contexts. We present an adaptation of the Watson & Holmes detective tabletop game as a new benchmark designed to evaluate reasoning performance using incrementally presented narrative evidence, open-ended questions and unconstrained language responses. An automated grading system was developed and validated against human assessors to enable scalable and replicable performance evaluation. Results show a clear improvement in AI model performance over time. Over nine months of 2025, model performance rose from the lower quartile of the human comparison group to approximately the top 5%. Around half of this improvement reflects steady advancement across successive model releases, while the remainder corresponds to a marked step change associated with reasoning-oriented model architectures. Systematic differences in the performance of AI models compared to humans, dependent on features of the specific detection puzzle, were mostly absent with the exception of a fall in performance for models when solving longer cases (case lengths being in the range of 1900-4000 words), and an advantage at inductive reasoning for reasoning models at early stages of case solving when evidence was scant.

---

### De novo molecular structure elucidation from mass spectra via flow matching

Authors: Ghaith Mqawass, Tuan Le, Fabian Theis, Djork-Arné Clevert
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19912v2

Mass spectrometry is a powerful and widely used tool for identifying molecular structures due to its sensitivity and ability to profile complex samples. However, translating spectra into full molecular structures is a difficult, under-defined inverse problem. Overcoming this problem is crucial for enabling biological insight, discovering new metabolites, and advancing chemical research across multiple fields. To this end, we develop MSFlow, a two-stage encoder-decoder flow-matching generative model that achieves state-of-the-art performance on the structure elucidation task for small molecules. In the first stage, we adopt a formula-restricted transformer model for encoding mass spectra into a continuous and chemically informative embedding space, while in the second stage, we train a decoder flow matching model to reconstruct molecules from latent embeddings of mass spectra. We present ablation studies demonstrating the importance of using information-preserving molecular descriptors for encoding mass spectra and motivate the use of our discrete flow-based decoder. Our rigorous evaluation demonstrates that MSFlow can accurately translate up to 45 percent of molecular mass spectra into their corresponding molecular representations - an improvement of up to fourteen-fold over the current state-of-the-art. A trained version of MSFlow is made publicly available on GitHub for non-commercial users.

---

### Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery

Authors: Wei He, Xianghan Meng, Zhiyuan Huang, Xianbiao Qi, Rong Xiao, Chun-Guang Li
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19910v2

Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set recognition problem. State-of-the-art approaches for GCD task are usually built on multi-modality representation learning, which is heavily dependent upon inter-modality alignment. However, few of them cast a proper intra-modality alignment to generate a desired underlying structure of representation distributions. In this paper, we propose a novel and effective multi-modal representation learning framework for GCD via Semi-Supervised Rate Reduction, called SSR$^2$-GCD, to learn cross-modality representations with desired structural properties based on emphasizing to properly align intra-modality relationships. Moreover, to boost knowledge transfer, we integrate prompt candidates by leveraging the inter-modal alignment offered by Vision Language Models. We conduct extensive experiments on generic and fine-grained benchmark datasets demonstrating superior performance of our approach.

---

### Gradient based Severity Labeling for Biomarker Classification in OCT

Authors: Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib, Stephanie Trejo Corona, Charles Wykoff
Published: 2026-02-23
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.19907v1

In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy.

---

### Rethinking Chronological Causal Discovery with Signal Processing

Authors: Kurt Butler, Damian Machlanski, Panagiotis Dimitrakopoulos, Sotirios A. Tsaftaris
Published: 2026-02-23
Categories: eess.SP, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.19903v1

Causal discovery problems use a set of observations to deduce causality between variables in the real world, typically to answer questions about biological or physical systems. These observations are often recorded at regular time intervals, determined by a user or a machine, depending on the experiment design. There is generally no guarantee that the timing of these recordings matches the timing of the underlying biological or physical events. In this paper, we examine the sensitivity of causal discovery methods to this potential mismatch. We consider empirical and theoretical evidence to understand how causal discovery performance is impacted by changes of sampling rate and window length. We demonstrate that both classical and recent causal discovery methods exhibit sensitivity to these hyperparameters, and we discuss how ideas from signal processing may help us understand these phenomena.

---

### ExpPortrait: Expressive Portrait Generation via Personalized Representation

Authors: Junyi Wang, Yudong Guo, Boyang Guo, Shengming Yang, Juyong Zhang
Published: 2026-02-23
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.19900v2

While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation, such as 2D landmarks and parametric models, have limited disentanglement capabilities and cannot express personalized details due to their sparse or low-rank representation. Therefore, existing methods based on these models struggle to accurately preserve subject identity and expressions, hindering the generation of highly expressive portrait videos. To overcome these limitations, we propose a high-fidelity personalized head representation that more effectively disentangles expression and identity. This representation captures both static, subject-specific global geometry and dynamic, expression-related details. Furthermore, we introduce an expression transfer module to achieve personalized transfer of head pose and expression details between different identities. We use this sophisticated and highly expressive head model as a conditional signal to train a diffusion transformer (DiT)-based generator to synthesize richly detailed portrait videos. Extensive experiments on self- and cross-reenactment tasks demonstrate that our method outperforms previous models in terms of identity preservation, expression accuracy, and temporal stability, particularly in capturing fine-grained details of complex motion.

---

### Monocular Mesh Recovery and Body Measurement of Female Saanen Goats

Authors: Bo Jin, Shichao Zhao, Jin Lyu, Bin Zhang, Tao Yu, Liang An, Yebin Liu, Meili Wang
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19896v1

The lactation performance of Saanen dairy goats, renowned for their high milk yield, is intrinsically linked to their body size, making accurate 3D body measurement essential for assessing milk production potential, yet existing reconstruction methods lack goat-specific authentic 3D data. To address this limitation, we establish the FemaleSaanenGoat dataset containing synchronized eight-view RGBD videos of 55 female Saanen goats (6-18 months). Using multi-view DynamicFusion, we fuse noisy, non-rigid point cloud sequences into high-fidelity 3D scans, overcoming challenges from irregular surfaces and rapid movement. Based on these scans, we develop SaanenGoat, a parametric 3D shape model specifically designed for female Saanen goats. This model features a refined template with 41 skeletal joints and enhanced udder representation, registered with our scan data. A comprehensive shape space constructed from 48 goats enables precise representation of diverse individual variations. With the help of SaanenGoat model, we get high-precision 3D reconstruction from single-view RGBD input, and achieve automated measurement of six critical body dimensions: body length, height, chest width, chest girth, hip width, and hip height. Experimental results demonstrate the superior accuracy of our method in both 3D reconstruction and body measurement, presenting a novel paradigm for large-scale 3D vision applications in precision livestock farming.

---

### DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning

Authors: Zhongwei Wan, Yun Shen, Zhihao Dou, Donghao Zhou, Yu Zhang, Xin Wang, Hui Shen, Jing Xiong, Chaofan Tao, Zixuan Zhong, Peizhou Huang, Mi Zhang
Published: 2026-02-23
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.19895v1

Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. Policies tend to collapse onto a few reasoning patterns and prematurely stop deep exploration, while conventional entropy regularization introduces only local stochasticity and fails to induce meaningful path-level diversity, leading to weak and unstable learning signals in group-based policy optimization. We propose DSDR, a Dual-Scale Diversity Regularization reinforcement learning framework that decomposes diversity in LLM reasoning into global and coupling components. Globally, DSDR promotes diversity among correct reasoning trajectories to explore distinct solution modes. Locally, it applies a length-invariant, token-level entropy regularization restricted to correct trajectories, preventing entropy collapse within each mode while preserving correctness. The two scales are coupled through a global-to-local allocation mechanism that emphasizes local regularization for more distinctive correct trajectories. We provide theoretical support showing that DSDR preserves optimal correctness under bounded regularization, sustains informative learning signals in group-based optimization, and yields a principled global-to-local coupling rule. Experiments on multiple reasoning benchmarks demonstrate consistent improvements in accuracy and pass@k, highlighting the importance of dual-scale diversity for deep exploration in RLVR. Code is available at https://github.com/SUSTechBruce/DSDR.

---

### Generalized Random Direction Newton Algorithms for Stochastic Optimization

Authors: Soumen Pachal, Prashanth L. A., Shalabh Bhatnagar, Avinash Achar
Published: 2026-02-23
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.19893v1

We present a family of generalized Hessian estimators of the objective using random direction stochastic approximation (RDSA) by utilizing only noisy function measurements. The form of each estimator and the order of the bias depend on the number of function measurements. In particular, we demonstrate that estimators with more function measurements exhibit lower-order estimation bias. We show the asymptotic unbiasedness of the estimators. We also perform asymptotic and non-asymptotic convergence analyses for stochastic Newton methods that incorporate our generalized Hessian estimators. Finally, we perform numerical experiments to validate our theoretical findings.

---

### Using Unsupervised Domain Adaptation Semantic Segmentation for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiogram (CTPA) Images

Authors: Wen-Liang Lin, Yun-Chien Cheng
Published: 2026-02-23
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.19891v1

While deep learning has demonstrated considerable promise in computer-aided diagnosis for pulmonary embolism (PE), practical deployment in Computed Tomography Pulmonary Angiography (CTPA) is often hindered by "domain shift" and the prohibitive cost of expert annotations. To address these challenges, an unsupervised domain adaptation (UDA) framework is proposed, utilizing a Transformer backbone and a Mean-Teacher architecture for cross-center semantic segmentation. The primary focus is placed on enhancing pseudo-label reliability by learning deep structural information within the feature space. Specifically, three modules are integrated and designed for this task: (1) a Prototype Alignment (PA) mechanism to reduce category-level distribution discrepancies; (2) Global and Local Contrastive Learning (GLCL) to capture both pixel-level topological relationships and global semantic representations; and (3) an Attention-based Auxiliary Local Prediction (AALP) module designed to reinforce sensitivity to small PE lesions by automatically extracting high-information slices from Transformer attention maps. Experimental validation conducted on cross-center datasets (FUMPE and CAD-PE) demonstrates significant performance gains. In the FUMPE -> CAD-PE task, the IoU increased from 0.1152 to 0.4153, while the CAD-PE -> FUMPE task saw an improvement from 0.1705 to 0.4302. Furthermore, the proposed method achieved a 69.9% Dice score in the CT -> MRI cross-modality task on the MMWHS dataset without utilizing any target-domain labels for model selection, confirming its robustness and generalizability for diverse clinical environments.

---

### Denotational Semantics for ODRL: Knowledge-Based Constraint Conflict Detection

Authors: Daham Mustafa, Diego Collarana, Yixin Peng, Rafiqul Haque, Christoph Lange-Bever, Christoph Quix, Stephan Decker
Published: 2026-02-23
Categories: cs.CL, cs.LO
arXiv: https://arxiv.org/abs/2602.19883v1

ODRL's six set-based operators -- isA, isPartOf, hasPart, isAnyOf, isAllOf, isNoneOf -- depend on external domain knowledge that the W3C specification leaves unspecified. Without it, every cross-dataspace policy comparison defaults to Unknown. We present a denotational semantics that maps each ODRL constraint to the set of knowledge-base concepts satisfying it. Conflict detection reduces to denotation intersection under a three-valued verdict -- Conflict, Compatible, or Unknown -- that is sound under incomplete knowledge. The framework covers all three ODRL composition modes (and, or, xone) and all three semantic domains arising in practice: taxonomic (class subsumption), mereological (part-whole containment), and nominal (identity). For cross-dataspace interoperability, we define order-preserving alignments between knowledge bases and prove two guarantees: conflicts are preserved across different KB standards, and unmapped concepts degrade gracefully to Unknown -- never to false conflicts. A runtime soundness theorem ensures that design-time verdicts hold for all execution contexts. The encoding stays within the decidable EPR fragment of first-order logic. We validate it with 154 benchmarks across six knowledge base families (GeoNames, ISO 3166, W3C DPV, a GDPR-derived taxonomy, BCP 47, and ISO 639-3) and four structural KBs targeting adversarial edge cases. Both the Vampire theorem prover and the Z3 SMT solver agree on all 154 verdicts. A key finding is that exclusive composition (xone) requires strictly stronger KB axioms than conjunction or disjunction: open-world semantics blocks exclusivity even when positive evidence appears to satisfy exactly one branch.

---

### Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations

Authors: Blaž Rolih, Matic Fučka, Filip Wolf, Luka Čehovin Zajc
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19881v2

Unsupervised remote sensing change detection (UCD) aims to localise changes between two images of the same region without relying on labelled training data. Most recent approaches either use a frozen foundation model in a training-free manner or train with synthetic changes generated in pixel space. Both strategies inherently rely on predefined assumptions about change types, typically introduced through handcrafted rules, external datasets, or auxiliary generative models. Due to these assumptions, such methods fail to generalise beyond a few change types, limiting their real-world usage, especially in rare or complex scenarios. To address this, we propose MaSoN (Make Some Noise), an end-to-end UCD framework that synthesises diverse changes directly in the latent feature space during training. It generates changes dynamically estimated from feature statistics of the target data, enabling diverse yet data-driven variation aligned with the target domain. Since synthesis happens in latent space, it also easily extends to new modalities, such as SAR and multispectral data. MaSoN generalises strongly across diverse change types and improves the average F1 score across five benchmarks by 14.1 percentage points. Project page: https://blaz-r.github.io/mason_ucd/

---

### Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations

Authors: Blaž Rolih, Matic Fučka, Filip Wolf, Luka Čehovin Zajc
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19881v1

Unsupervised change detection (UCD) in remote sensing aims to localise semantic changes between two images of the same region without relying on labelled data during training. Most recent approaches rely either on frozen foundation models in a training-free manner or on training with synthetic changes generated in pixel space. Both strategies inherently rely on predefined assumptions about change types, typically introduced through handcrafted rules, external datasets, or auxiliary generative models. Due to these assumptions, such methods fail to generalise beyond a few change types, limiting their real-world usage, especially in rare or complex scenarios. To address this, we propose MaSoN (Make Some Noise), an end-to-end UCD framework that synthesises diverse changes directly in the latent feature space during training. It generates changes that are dynamically estimated using feature statistics of target data, enabling diverse yet data-driven variation aligned with the target domain. It also easily extends to new modalities, such as SAR. MaSoN generalises strongly across diverse change types and achieves state-of-the-art performance on five benchmarks, improving the average F1 score by 14.1 percentage points. Project page: https://blaz-r.github.io/mason_ucd

---

### Axis-Aligned Semantics for ODRL: Resolving Dimensional Ambiguity in Policy Constraints

Authors: Daham Mustafa, Diego Collarana, Sabrina Kirrane, Christoph Lange, Christoph Quix, Rafiqul Haque, Yixin Peng, Stefan Decker
Published: 2026-02-23
Categories: cs.CL, cs.LO
arXiv: https://arxiv.org/abs/2602.19878v3

The Open Digital Rights Language (ODRL) represents policy constraints as triples of a left operand, an operator, and a value. Several spatial operands, however, range over multi-axis domains such as width, height, and depth, while the constraint syntax provides no explicit axis identity. As a result, policy engines cannot determine whether multiple constraints apply to the same axis or different ones, making conflict detection unsound or incomplete. We resolve this ambiguity by axis decomposition, replacing multi-axis operands with axis-specific scalar operands over totally ordered domains. Each constraint then denotes an interval per axis and each policy an axis-aligned box, reducing conflict detection to box comparison. We define a three-valued semantics (Conflict, Compatible, Unknown), prove the decomposition sound and backward compatible with ODRL, instantiate it as ODRL Axis-Aligned Profile (OAAP), and validate it on a benchmark of 256 ODRL policy problems, each expressed in Turtle and compiled to first-order (TPTP) and SMT-LIB form, using Vampire, E, Z3, and cvc5.

---

### BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations

Authors: Lucas Martini, Alexander Lappe, Anna Bognár, Rufin Vogels, Martin A. Giese
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19874v1

The recognition of dynamic and social behavior in animals is fundamental for advancing ethology, ecology, medicine and neuroscience. Recent progress in deep learning has enabled automated behavior recognition from video, yet an accurate reconstruction of the three-dimensional (3D) pose and shape has not been integrated into this process. Especially for non-human primates, mesh-based tracking efforts lag behind those for other species, leaving pose descriptions restricted to sparse keypoints that are unable to fully capture the richness of action dynamics. To address this gap, we introduce the $\textbf{Big Ma}$ca$\textbf{Q}$ue 3D Motion and Animation Dataset ($\texttt{BigMaQ}$), a large-scale dataset comprising more than 750 scenes of interacting rhesus macaques with detailed 3D pose descriptions. Extending previous surface-based animal tracking methods, we construct subject-specific textured avatars by adapting a high-quality macaque template mesh to individual monkeys. This allows us to provide pose descriptions that are more accurate than previous state-of-the-art surface-based animal tracking methods. From the original dataset, we derive BigMaQ500, an action recognition benchmark that links surface-based pose vectors to single frames across multiple individual monkeys. By pairing features extracted from established image and video encoders with and without our pose descriptors, we demonstrate substantial improvements in mean average precision (mAP) when pose information is included. With these contributions, $\texttt{BigMaQ}$ establishes the first dataset that both integrates dynamic 3D pose-shape representations into the learning task of animal action recognition and provides a rich resource to advance the study of visual appearance, posture, and social interaction in non-human primates. The code and data are publicly available at https://martinivis.github.io/BigMaQ/ .

---

### GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

Authors: Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He, Shaokun Wang, Qiang Wang, Yihong Gong
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19872v1

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in forgetting and inconsistent feature alignment. We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning. GOAL conducts supervised alignment for labeled samples and confidence-guided alignment for novel samples, enabling stable integration of new classes without disrupting old ones. Experiments on four benchmarks show that GOAL outperforms the prior method Happy, reducing forgetting by 16.1% and boosting novel class discovery by 3.2%, establishing a strong solution for long-horizon continual discovery.

---

### ApET: Approximation-Error Guided Token Compression for Efficient VLMs

Authors: Qiankun Ma, Ziyao Zhang, Haofei Wang, Jie Chen, Zhen Song, Hairong Zheng
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19870v1

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically relies on (CLS) attention or text-vision cross-attention to identify and discard redundant visual tokens. Despite promising results, such solutions are prone to introduce positional bias and, more critically, are incompatible with efficient attention kernels such as FlashAttention, limiting their practical deployment for VLM acceleration. In this paper, we step away from attention dependencies and revisit visual token compression from an information-theoretic perspective, aiming to maximally preserve visual information without any attention involvement. We present ApET, an Approximation-Error guided Token compression framework. ApET first reconstructs the original visual tokens with a small set of basis tokens via linear approximation, then leverages the approximation error to identify and drop the least informative tokens. Extensive experiments across multiple VLMs and benchmarks demonstrate that ApET retains 95.2% of the original performance on image-understanding tasks and even attains 100.4% on video-understanding tasks, while compressing the token budgets by 88.9% and 87.5%, respectively. Thanks to its attention-free design, ApET seamlessly integrates with FlashAttention, enabling further inference acceleration and making VLM deployment more practical. Code is available at https://github.com/MaQianKun0/ApET.

---

### Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation

Authors: Filip Wolf, Blaž Rolih, Luka Čehovin Zajc
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19863v3

Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model unrealistic. Multiple specialized EO foundation models (EOFMs) will likely coexist, making efficient knowledge transfer across modalities essential. Most existing EO pretraining relies on masked image modeling, which emphasizes local reconstruction but provides limited control over global semantic structure. To address this, we propose a dual-teacher contrastive distillation framework for multispectral imagery that aligns the student's pretraining objective with the contrastive self-distillation paradigm of modern optical vision foundation models (VFMs). Our approach combines a multispectral teacher with an optical VFM teacher, enabling coherent cross-modal representation learning. Experiments across diverse optical and multispectral benchmarks show that our model adapts to multispectral data without compromising performance on optical-only inputs, achieving state-of-the-art results in both settings, with an average improvement of 3.64 percentage points in semantic segmentation, 1.2 in change detection, and 1.31 in classification tasks. This demonstrates that contrastive distillation provides a principled and efficient approach to scalable representation learning across heterogeneous EO data sources. Project page: \textcolor{magenta}{https://wolfilip.github.io/DEO/}.

---

### Dirichlet Scale Mixture Priors for Bayesian Neural Networks

Authors: August Arnstad, Leiv Rønneberg, Geir Storvik
Published: 2026-02-23
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.19859v1

Neural networks are the cornerstone of modern machine learning, yet can be difficult to interpret, give overconfident predictions and are vulnerable to adversarial attacks. Bayesian neural networks (BNNs) provide some alleviation of these limitations, but have problems of their own. The key step of specifying prior distributions in BNNs is no trivial task, yet is often skipped out of convenience. In this work, we propose a new class of prior distributions for BNNs, the Dirichlet scale mixture (DSM) prior, that addresses current limitations in Bayesian neural networks through structured, sparsity-inducing shrinkage. Theoretically, we derive general dependence structures and shrinkage results for DSM priors and show how they manifest under the geometry induced by neural networks. In experiments on simulated and real world data we find that the DSM priors encourages sparse networks through implicit feature selection, show robustness under adversarial attacks and deliver competitive predictive performance with substantially fewer effective parameters. In particular, their advantages appear most pronounced in correlated, moderately small data regimes, and are more amenable to weight pruning. Moreover, by adopting heavy-tailed shrinkage mechanisms, our approach aligns with recent findings that such priors can mitigate the cold posterior effect, offering a principled alternative to the commonly used Gaussian priors.

---

### Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions

Authors: Rodrigo Mota, Kelvin Cunha, Emanoel dos Santos, Fábio Papais, Francisco Filho, Thales Bezerra, Erico Medeiros, Paulo Borba, Tsang Ing Ren
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19857v2

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual artifacts and domain shifts affect deep learning-based skin lesion classification. We propose an adaptation strategy, grounded in the idea of visual meta-domains, that transfers visual representations from larger dermoscopic datasets into clinical image domains, thereby improving generalization robustness. Experiments across multiple dermatology datasets show consistent gains in classification performance and reduced gaps between dermoscopic and clinical images. These results emphasize the importance of domain-aware training for deployable systems.

---

### SHIELD: Semantic Heterogeneity Integrated Embedding for Latent Discovery in Clinical Trial Safety Signals

Authors: Francois Vandenhende, Anna Georgiou, Theodoros Psaras, Ellie Karekla
Published: 2026-02-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.19855v1

We present SHIELD, a novel methodology for automated and integrated safety signal detection in clinical trials. SHIELD combines disproportionality analysis with semantic clustering of adverse event (AE) terms applied to MedDRA term embeddings. For each AE, the pipeline computes an information-theoretic disproportionality measure (Information Component) with effect size derived via empirical Bayesian shrinkage. A utility matrix is constructed by weighting semantic term-term similarities by signal magnitude, followed by spectral embedding and clustering to identify groups of related AEs. Resulting clusters are annotated with syndrome-level summary labels using large language models, yielding a coherent, data-driven representation of treatment-associated safety profiles in the form of a network graph and hierarchical tree. We implement the SHIELD framework in the context of a single-arm incidence summary, to compare two treatment arms or for the detection of any treatment effect in a multi-arm trial. We illustrate its ability to recover known safety signals and generate interpretable, cluster-based summaries in a real clinical trial example. This work bridges statistical signal detection with modern natural language processing to enhance safety assessment and causal interpretation in clinical trials.

---

### Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments

Authors: Xinyan Su, Jiacan Gao, Mingyuan Ma, Xiao Xu, Xinrui Wan, Tianqi Gu, Enyun Yu, Jiecheng Guo, Zhiheng Zhang
Published: 2026-02-23
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2602.19851v1

We study uplift estimation for combinatorial treatments. Uplift measures the pure incremental causal effect of an intervention (e.g., sending a coupon or a marketing message) on user behavior, modeled as a conditional individual treatment effect. Many real-world interventions are combinatorial: a treatment is a policy that specifies context-dependent action distributions rather than a single atomic label. Although recent work considers structured treatments, most methods rely on categorical or opaque encodings, limiting robustness and generalization to rare or newly deployed policies. We propose an uplift estimation framework that aligns treatment representation with causal semantics. Each policy is represented by the mixture it induces over contextaction components and embedded via a permutation-invariant aggregation. This representation is integrated into an orthogonalized low-rank uplift model, extending Robinson-style decompositions to learned, vector-valued treatments. We show that the resulting estimator is expressive for policy-induced causal effects, orthogonally robust to nuisance estimation errors, and stable under small policy perturbations. Experiments on large-scale randomized platform data demonstrate improved uplift accuracy and stability in long-tailed policy regimes

---

### DerMAE: Improving skin lesion classification through conditioned latent diffusion and MAE distillation

Authors: Francisco Filho, Kelvin Cunha, Fábio Papais, Emanoel dos Santos, Rodrigo Mota, Thales Bezerra, Erico Medeiros, Paulo Borba, Tsang Ing Ren
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19848v2

Skin lesion classification datasets often suffer from severe class imbalance, with malignant cases significantly underrepresented, leading to biased decision boundaries during deep learning training. We address this challenge using class-conditioned diffusion models to generate synthetic dermatological images, followed by self-supervised MAE pretraining to enable huge ViT models to learn robust, domain-relevant features. To support deployment in practical clinical settings, where lightweight models are required, we apply knowledge distillation to transfer these representations to a smaller ViT student suitable for mobile devices. Our results show that MAE pretraining on synthetic data, combined with distillation, improves classification performance while enabling efficient on-device inference for practical clinical use.

---

### I Dropped a Neural Net

Authors: Hyunwoo Park
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19845v1

A recent Dwarkesh Patel podcast with John Collison and Elon Musk featured an interesting puzzle from Jane Street: they trained a neural net, shuffled all 96 layers, and asked to put them back in order. Given unlabelled layers of a Residual Network and its training dataset, we recover the exact ordering of the layers. The problem decomposes into pairing each block's input and output projections ($48!$ possibilities) and ordering the reassembled blocks ($48!$ possibilities), for a combined search space of $(48!)^2 \approx 10^{122}$, which is more than the atoms in the observable universe. We show that stability conditions during training like dynamic isometry leave the product $W_{\text{out}} W_{\text{in}}$ for correctly paired layers with a negative diagonal structure, allowing us to use diagonal dominance ratio as a signal for pairing. For ordering, we seed-initialize with a rough proxy such as delta-norm or $\|W_{\text{out}}\|_F$ then hill-climb to zero mean squared error.

---

### LLM-enabled Applications Require System-Level Threat Monitoring

Authors: Yedi Zhang, Haoyu Wang, Xianglin Yang, Jin Song Dong, Jun Sun
Published: 2026-02-23
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.19844v1

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, due to the non-deterministic, learning-driven, and difficult-to-verify nature of LLM behavior. In light of these emerging and unavoidable safety challenges, we argue that such risks should be treated as expected operational conditions rather than exceptional events, necessitating a dedicated incident-response perspective. Consequently, the primary barrier to trustworthy deployment is not further improving model capability but establishing system-level threat monitoring mechanisms that can detect and contextualize security-relevant anomalies after deployment -- an aspect largely underexplored beyond testing or guardrail-based defenses. Accordingly, this position paper advocates systematic and comprehensive monitoring of security threats in LLM-enabled applications as a prerequisite for reliable operation and a foundation for dedicated incident-response frameworks.

---

### MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

Authors: Jin Jia, Zhiling Deng, Zhuangbin Chen, Yingqi Wang, Zibin Zheng
Published: 2026-02-23
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.19843v1

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are prone to semantic failures (e.g., hallucinations, misinterpreted instructions, and reasoning drift) that propagate silently without raising runtime exceptions. Prevailing evaluation approaches, which measure only end-to-end task success, offer limited insight into how these failures arise or how effectively agents recover from them. To bridge this gap, we propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of MAS. We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures, and inject them via three non-invasive mechanisms: prompt modification, response rewriting, and message routing manipulation. Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors that we organize into four tiers: mechanism, rule, prompt, and reasoning. This tiered view enables fine-grained diagnosis of where and why systems succeed or fail. Our findings reveal that stronger foundation models do not uniformly improve robustness. We further show that architectural topology plays an equally decisive role, with iterative, closed-loop designs neutralizing over 40% of faults that cause catastrophic collapse in linear workflows. MAS-FIRE provides the process-level observability and actionable guidance needed to systematically improve multi-agent systems.

---