# Research Papers — 2026-02 · bundle page 48 of 210

> Full-text markdown of papers #2351–2400 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/48
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/47.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/49.md)

### Regularity of Second-Order Elliptic PDEs in Spectral Barron Spaces

Authors: Ziang Chen, Liqiang Huang, Mengxuan Yang, Shengxuan Zhou
Published: 2026-02-22
Categories: math.AP, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.19381v2

We establish a regularity theorem for second-order elliptic PDEs on $\mathbb{R}^{d}$ in spectral Barron spaces. Under mild ellipticity and smallness assumptions, the solution gains two additional orders of Barron regularity. As a corollary, we identify a class of PDEs whose solutions can be approximated by two-layer neural networks with cosine activation functions, where the width of the neural network is independent of the spatial dimension.

---

### Regularity of Second-Order Elliptic PDEs in Spectral Barron Spaces

Authors: Ziang Chen, Liqiang Huang, Mengxuan Yang, Shengxuan Zhou
Published: 2026-02-22
Categories: math.AP, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.19381v1

We establish a regularity theorem for second-order elliptic PDEs on $\mathbb{R}^{d}$ in spectral Barron spaces. Under mild ellipticity and smallness assumptions, the solution gains two additional orders of Barron regularity. As a corollary, we identify a class of PDEs whose solutions can be approximated by two-layer neural networks with cosine activation functions, where the width of the neural network is independent of the spatial dimension.

---

### Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization

Authors: Huayu Wang, Bahaa Alattar, Cheng-Yen Yang, Hsiang-Wei Huang, Jung Heon Kim, Linda Shapiro, Nathan White, Jenq-Neng Hwang
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19380v1

Temporal stability in glottic opening localization remains challenging due to the complementary weaknesses of single-frame detectors and foundation-model trackers: the former lacks temporal context, while the latter suffers from memory drift. Specifically, in video laryngoscopy, rapid tissue deformation, occlusions, and visual ambiguities in emergency settings require a robust, temporally aware solution that can prevent progressive tracking errors. We propose Closed-Loop Memory Correction (CL-MC), a detector-in-the-loop framework that supervises Segment Anything Model 2(SAM2) through confidence-aligned state decisions and active memory rectification. High-confidence detections trigger semantic resets that overwrite corrupted tracker memory, effectively mitigating drift accumulation with a training-free foundation tracker in complex endoscopic scenes. On emergency intubation videos, CL-MC achieves state-of-the-art performance, significantly reducing drift and missing rate compared with the SAM2 variants and open loop based methods. Our results establish memory correction as a crucial component for reliable clinical video tracking. Our code will be available in https://github.com/huayuww/CL-MR.

---

### Stable Deep Reinforcement Learning via Isotropic Gaussian Representations

Authors: Ali Saheb Pasand, Johan Obando-Ceron, Aaron Courville, Pouya Bashivan, Pablo Samuel Castro
Published: 2026-02-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19373v3

Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian embeddings are provably advantageous. In particular, they induce stable tracking of time-varying targets for linear readouts, achieve maximal entropy under a fixed variance budget, and encourage a balanced use of all representational dimensions--all of which enable agents to be more adaptive and stable. Building on this insight, we propose the use of Sketched Isotropic Gaussian Regularization for shaping representations toward an isotropic Gaussian distribution during training. We demonstrate empirically, over a variety of domains, that this simple and computationally inexpensive method improves performance under non-stationarity while reducing representation collapse, neuron dormancy, and training instability.

---

### Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization

Authors: Yanting Yang, Shenyuan Gao, Qingwen Bu, Li Chen, Dimitris N. Metaxas
Published: 2026-02-22
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.19372v1

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general perceive-reason-act framework for this goal. However, previous approaches using reflective planning to guide VLMs in correcting actions encounter significant limitations. These methods rely on inefficient and often inaccurate implicit learning of state-values from noisy foresight predictions, evaluate only a single greedy future, and suffer from substantial inference latency. To address these limitations, we propose a novel test-time computation framework that decouples state evaluation from action generation. This provides a more direct and fine-grained supervisory signal for robust decision-making. Our method explicitly models the advantage of an action plan, quantified by its reduction in distance to the goal, and uses a scalable critic to estimate. To address the stochastic nature of single-trajectory evaluation, we employ beam search to explore multiple future paths and aggregate them during decoding to model their expected long-term returns, leading to more robust action generation. Additionally, we introduce a lightweight, confidence-based trigger that allows for early exit when direct predictions are reliable, invoking reflection only when necessary. Extensive experiments on diverse, unseen multi-stage robotic manipulation tasks demonstrate a 24.6% improvement in success rate over state-of-the-art baselines, while significantly reducing inference time by 56.5%.

---

### Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces

Authors: Pratham Yashwante, Rose Yu
Published: 2026-02-22
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.19367v1

The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and language, and it remains unclear whether time series participate in such convergence. We first examine this in a trimodal setting and find that independently pretrained time series, vision, and language encoders exhibit near-orthogonal geometry in the absence of explicit coupling. We then apply post-hoc alignment by training projection heads over frozen encoders using contrastive learning, and analyze the resulting representations with respect to geometry, scaling behavior, and dependence on information density and input modality characteristics. Our investigation reveals that overall alignment in contrastive representation spaces improves with model size, but this alignment is asymmetric: time series align more strongly with visual representations than with text, and images can act as effective intermediaries between time series and language. We further see that richer textual descriptions improve alignment only up to a threshold; training on denser captions does not lead to further improvement. Analogous effects are observed for visual representations. Our findings shed light on considerations for building multimodal systems involving non-conventional data modalities beyond vision and language.

---

### LLMs Can Learn to Reason Via Off-Policy RL

Authors: Daniel Ritter, Owen Oertell, Bradley Guo, Jonathan Chang, Kianté Brantley, Wen Sun
Published: 2026-02-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19362v2

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference policies break this assumption, making the data off-policy by design. To rectify this, prior work has focused on making this off-policy data appear more on-policy, either via importance sampling (IS), or by more closely aligning the training and inference policies by explicitly modifying the inference engine. In this work, we embrace off-policyness and propose a novel off-policy RL algorithm that does not require these modifications: Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL). We show that OAPL outperforms GRPO with importance sampling on competition math benchmarks, and can match the performance of a publicly available coding model, DeepCoder, on LiveCodeBench, while using 3x fewer generations during training. We further empirically demonstrate that models trained via OAPL have improved test time scaling under the Pass@k metric. OAPL allows for efficient, effective post-training even with lags of more than 400 gradient steps between the training and inference policies, 100x more off-policy than prior approaches.

---

### Vid2Sid: Videos Can Help Close the Sim2Real Gap

Authors: Kevin Qiu, Yu Zhang, Marek Cygan, Josie Hughes
Published: 2026-02-22
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.19359v1

Calibrating a robot simulator's physics parameters (friction, damping, material stiffness) to match real hardware is often done by hand or with black-box optimizers that reduce error but cannot explain which physical discrepancies drive the error. When sensing is limited to external cameras, the problem is further compounded by perception noise and the absence of direct force or state measurements. We present Vid2Sid, a video-driven system identification pipeline that couples foundation-model perception with a VLM-in-the-loop optimizer that analyzes paired sim-real videos, diagnoses concrete mismatches, and proposes physics parameter updates with natural language rationales. We evaluate our approach on a tendon-actuated finger (rigid-body dynamics in MuJoCo) and a deformable continuum tentacle (soft-body dynamics in PyElastica). On sim2real holdout controls unseen during training, Vid2Sid achieves the best average rank across all settings, matching or exceeding black-box optimizers while uniquely providing interpretable reasoning at each iteration. Sim2sim validation confirms that Vid2Sid recovers ground-truth parameters most accurately (mean relative error under 13\% vs. 28--98\%), and ablation analysis reveals three calibration regimes. VLM-guided optimization excels when perception is clean and the simulator is expressive, while model-class limitations bound performance in more challenging settings.

---

### Referring Layer Decomposition

Authors: Fangyi Chen, Yaojie Shen, Lu Xu, Ye Yuan, Shu Zhang, Yulei Niu, Longyin Wen
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19358v1

Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate individual scene elements. In contrast, layered representations, where scenes are explicitly separated into objects, environmental context, and visual effects, provide a more intuitive and structured framework for interpreting and editing visual content. To bridge this gap and enable both compositional understanding and controllable editing, we introduce the Referring Layer Decomposition (RLD) task, which predicts complete RGBA layers from a single RGB image, conditioned on flexible user prompts, such as spatial inputs (e.g., points, boxes, masks), natural language descriptions, or combinations thereof. At the core is the RefLade, a large-scale dataset comprising 1.11M image-layer-prompt triplets produced by our scalable data engine, along with 100K manually curated, high-fidelity layers. Coupled with a perceptually grounded, human-preference-aligned automatic evaluation protocol, RefLade establishes RLD as a well-defined and benchmarkable research task. Building on this foundation, we present RefLayer, a simple baseline designed for prompt-conditioned layer decomposition, achieving high visual fidelity and semantic alignment. Extensive experiments show our approach enables effective training, reliable evaluation, and high-quality image decomposition, while exhibiting strong zero-shot generalization capabilities.

---

### MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations

Authors: Nilay Yilmaz, Maitreya Patel, Naga Sai Abhiram Kusumba, Yixuan He, Yezhou Yang
Published: 2026-02-22
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.19357v1

Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition where actions and perception are connected on a mental level. To explore whether state-of-the-art Vision-Language Models (VLMs) exhibit this ability, we develop MentalBlackboard, an open-ended spatial visualization benchmark for Paper Folding and Hole Punching tests within two core tasks: prediction and planning. Our prediction experiments reveal that models struggle with applying symmetrical transformations, even when they predict the sequence of unfolding steps correctly. Also, rotations introduce a significant challenge to the physical situational awareness for models. The planning task reveals limitations of models in analyzing symmetrical relationships and in implementing the multi-stage symmetry process, with Claude Opus 4.1 achieving the highest planning score at an accuracy of 10\%. The top-performing model, o3, attains a peak performance of 71.6\% on the generalization task, which does not require spatial visualization but transfers spatial data; however, it achieves only 25\% accuracy on text-based prediction tasks.

---

### Active perception and disentangled representations allow continual, episodic zero and few-shot learning

Authors: David Rawlinson, Gideon Kowadlo
Published: 2026-02-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19355v1

Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled representations at the boundaries of entities or classes, which can lead to destructive interference when rapid, high-magnitude updates are required for continual or few-shot learning. Techniques for fast learning with non-interfering representations exist, but they generally fail to generalize. Here, we describe a Complementary Learning System (CLS) in which the fast learner entirely foregoes generalization in exchange for continual zero-shot and few-shot learning. Unlike most CLS approaches, which use episodic memory primarily for replay and consolidation, our fast, disentangled learner operates as a parallel reasoning system. The fast learner can overcome observation variability and uncertainty by leveraging a conventional slow, statistical learner within an active perception system: A contextual bias provided by the fast learner induces the slow learner to encode novel stimuli in familiar, generalized terms, enabling zero-shot and few-shot learning. This architecture demonstrates that fast, context-driven reasoning can coexist with slow, structured generalization, providing a pathway for robust continual learning.

---

### PoseCraft: Tokenized 3D Body Landmark and Camera Conditioning for Photorealistic Human Image Synthesis

Authors: Zhilin Guo, Jing Yang, Kyle Fogarty, Jingyi Wan, Boqiao Zhang, Tianhao Wu, Weihao Xia, Chenliang Zhou, Sakar Khattar, Fangcheng Zhong, Cristina Nader Vasconcelos, Cengiz Oztireli
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19350v1

Digitizing humans and synthesizing photorealistic avatars with explicit 3D pose and camera controls are central to VR, telepresence, and entertainment. Existing skinning-based workflows require laborious manual rigging or template-based fittings, while neural volumetric methods rely on canonical templates and re-optimization for each unseen pose. We present PoseCraft, a diffusion framework built around tokenized 3D interface: instead of relying only on rasterized geometry as 2D control images, we encode sparse 3D landmarks and camera extrinsics as discrete conditioning tokens and inject them into diffusion via cross-attention. Our approach preserves 3D semantics by avoiding 2D re-projection ambiguity under large pose and viewpoint changes, and produces photorealistic imagery that faithfully captures identity and appearance. To train and evaluate at scale, we also implement GenHumanRF, a data generation workflow that renders diverse supervision from volumetric reconstructions. Our experiments show that PoseCraft achieves significant perceptual quality improvement over diffusion-centric methods, and attains better or comparable metrics to latest volumetric rendering SOTA while better preserving fabric and hair details.

---

### UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation

Authors: Rohit Mohan, Florian Drews, Yakov Miron, Daniele Cattaneo, Abhinav Valada
Published: 2026-02-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19349v2

LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode. Under adverse conditions, degradation or failure of the camera sensor can significantly compromise the reliability of the perception system. To address this problem, we introduce UP-Fuse, a novel uncertainty-aware fusion framework in the 2D range-view that remains robust under camera sensor degradation, calibration drift, and sensor failure. Raw LiDAR data is first projected into the range-view and encoded by a LiDAR encoder, while camera features are simultaneously extracted and projected into the same shared space. At its core, UP-Fuse employs an uncertainty-guided fusion module that dynamically modulates cross-modal interaction using predicted uncertainty maps. These maps are learned by quantifying representational divergence under diverse visual degradations, ensuring that only reliable visual cues influence the fused representation. The fused range-view features are decoded by a novel hybrid 2D-3D transformer that mitigates spatial ambiguities inherent to the 2D projection and directly predicts 3D panoptic segmentation masks. Extensive experiments on Panoptic nuScenes, SemanticKITTI, and our introduced Panoptic Waymo benchmark demonstrate the efficacy and robustness of UP-Fuse, which maintains strong performance even under severe visual corruption or misalignment, making it well suited for robotic perception in safety-critical settings.

---

### MultiDiffSense: Diffusion-Based Multi-Modal Visuo-Tactile Image Generation Conditioned on Object Shape and Contact Pose

Authors: Sirine Bhouri, Lan Wei, Jian-Qing Zheng, Dandan Zhang
Published: 2026-02-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19348v1

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning. We present MultiDiffSense, a unified diffusion model that synthesises images for multiple vision-based tactile sensors (ViTac, TacTip, ViTacTip) within a single architecture. Our approach uses dual conditioning on CAD-derived, pose-aligned depth maps and structured prompts that encode sensor type and 4-DoF contact pose, enabling controllable, physically consistent multi-modal synthesis. Evaluating on 8 objects (5 seen, 3 novel) and unseen poses, MultiDiffSense outperforms a Pix2Pix cGAN baseline in SSIM by +36.3% (ViTac), +134.6% (ViTacTip), and +64.7% (TacTip). For downstream 3-DoF pose estimation, mixing 50% synthetic with 50% real halves the required real data while maintaining competitive performance. MultiDiffSense alleviates the data-collection bottleneck in tactile sensing and enables scalable, controllable multi-modal dataset generation for robotic applications.

---

### Smooth Gate Functions for Soft Advantage Policy Optimization

Authors: Egor Denisov, Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko
Published: 2026-02-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19345v2

Group Relative Policy Optimization (GRPO) has significantly advanced the training of large language models and enhanced their reasoning capabilities, while it remains susceptible to instability due to the use of hard clipping. Soft Adaptive Policy Optimization (SAPO) addresses this limitation by replacing clipping with a smooth sigmoid-based gate function, which leads to more stable updates. We have decided to push this theory further and investigate the impact of different gate functions on both training stability and final model performance. We formalize the key properties that admissible gates should satisfy and identify several families of such functions for empirical evaluation. This paper presents an analysis of our findings based on experiments conducted with the Qwen2.5-7B-Instruct model on mathematical reasoning tasks. These results provide practical guidance for designing smoother and more robust policy optimization objectives for large language model training.

---

### SplitLight: An Exploratory Toolkit for Recommender Systems Datasets and Splits

Authors: Anna Volodkevich, Dmitry Anikin, Danil Gusak, Anton Klenitskiy, Evgeny Frolov, Alexey Vasilev
Published: 2026-02-22
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.19339v1

Offline evaluation of recommender systems is often affected by hidden, under-documented choices in data preparation. Seemingly minor decisions in filtering, handling repeats, cold-start treatment, and splitting strategy design can substantially reorder model rankings and undermine reproducibility and cross-paper comparability. In this paper, we introduce SplitLight, an open-source exploratory toolkit that enables researchers and practitioners designing preprocessing and splitting pipelines or reviewing external artifacts to make these decisions measurable, comparable, and reportable. Given an interaction log and derived split subsets, SplitLight analyzes core and temporal dataset statistics, characterizes repeat consumption patterns and timestamp anomalies, and diagnoses split validity, including temporal leakage, cold-user/item exposure, and distribution shifts. SplitLight further allows side-by-side comparison of alternative splitting strategies through comprehensive aggregated summaries and interactive visualizations. Delivered as both a Python toolkit and an interactive no-code interface, SplitLight produces audit summaries that justify evaluation protocols and support transparent, reliable, and comparable experimentation in recommender systems research and industry.

---

### PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification

Authors: Isun Chehreh, Ebrahim Ansari
Published: 2026-02-22
Categories: cs.CL, cs.IR, cs.SI
arXiv: https://arxiv.org/abs/2602.19333v2

This research introduces the first large-scale, well-balanced Persian social media text classification dataset, specifically designed to address the lack of comprehensive resources in this domain. The dataset comprises 36,000 posts across nine categories (Economic, Artistic, Sports, Political, Social, Health, Psychological, Historical, and Science & Technology), each containing 4,000 samples to ensure balanced class distribution. Data collection involved 60,000 raw posts from various Persian social media platforms, followed by rigorous preprocessing and hybrid annotation combining ChatGPT-based few-shot prompting with human verification. To mitigate class imbalance, we employed undersampling with semantic redundancy removal and advanced data augmentation strategies integrating lexical replacement and generative prompting. We benchmarked several models, including BiLSTM, XLM-RoBERTa (with LoRA and AdaLoRA adaptations), FaBERT, SBERT-based architectures, and the Persian-specific TookaBERT (Base and Large). Experimental results show that transformer-based models consistently outperform traditional neural networks, with TookaBERT-Large achieving the best performance (Precision: 0.9622, Recall: 0.9621, F1- score: 0.9621). Class-wise evaluation further confirms robust performance across all categories, though social and political texts exhibited slightly lower scores due to inherent ambiguity. This research presents a new high-quality dataset and provides comprehensive evaluations of cutting-edge models, establishing a solid foundation for further developments in Persian NLP, including trend analysis, social behavior modeling, and user classification. The dataset is publicly available to support future research endeavors.

---

### Training-Free Cross-Architecture Merging for Graph Neural Networks

Authors: Rishabh Bhattacharya, Vikaskumar Kalsariya, Naresh Manwani
Published: 2026-02-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19332v1

Model merging has emerged as a powerful paradigm for combining the capabilities of distinct expert models without the high computational cost of retraining, yet current methods are fundamentally constrained to homogeneous architectures. For GNNs, however, message passing is topology-dependent and sensitive to misalignment, making direct parameter-space merging unreliable. To bridge this gap, we introduce H-GRAMA (Heterogeneous Graph Routing and Message Alignment), a training-free framework that lifts merging from parameter space to operator space. We formalize Universal Message Passing Mixture (UMPM), a shared operator family that expresses heterogeneous GNN layers in a common functional language. H-GRAMA enables cross-architecture GNN merging (e.g., GCN to GAT) without retraining, retaining high specialist accuracy in most cases in compatible depth settings and achieving inference speedups of 1.2x to 1.9x over ensembles.

---

### Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence

Authors: Chaitanya Kapoor, Alex H. Williams, Meenakshi Khosla
Published: 2026-02-22
Categories: cs.LG, cs.NE, stat.ML
arXiv: https://arxiv.org/abs/2602.19331v1

Representational similarity metrics typically force all units to be matched, making them susceptible to noise and outliers common in neural representations. We extend the soft-matching distance to a partial optimal transport setting that allows some neurons to remain unmatched, yielding rotation-sensitive but robust correspondences. This partial soft-matching distance provides theoretical advantages -- relaxing strict mass conservation while maintaining interpretable transport costs -- and practical benefits through efficient neuron ranking in terms of cross-network alignment without costly iterative recomputation. In simulations, it preserves correct matches under outliers and reliably selects the correct model in noise-corrupted identification tasks. On fMRI data, it automatically excludes low-reliability voxels and produces voxel rankings by alignment quality that closely match computationally expensive brute-force approaches. It achieves higher alignment precision across homologous brain areas than standard soft-matching, which is forced to match all units regardless of quality. In deep networks, highly matched units exhibit similar maximally exciting images, while unmatched units show divergent patterns. This ability to partition by match quality enables focused analyses, e.g., testing whether networks have privileged axes even within their most aligned subpopulations. Overall, partial soft-matching provides a principled and practical method for representational comparison under partial correspondence.

---

### CTS-Bench: Benchmarking Graph Coarsening Trade-offs for GNNs in Clock Tree Synthesis

Authors: Barsat Khadka, Kawsher Roxy, Md Rubel Ahmed
Published: 2026-02-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19330v2

Graph Neural Networks (GNNs) are increasingly explored for physical design analysis in Electronic Design Automation, particularly for modeling Clock Tree Synthesis behavior such as clock skew and buffering complexity. However, practical deployment remains limited due to the prohibitive memory and runtime cost of operating on raw gate-level netlists. Graph coarsening is commonly used to improve scalability, yet its impact on CTS-critical learning objectives is not well characterized. This paper introduces CTS-Bench, a benchmark suite for systematically evaluating the trade-offs between graph coarsening, prediction accuracy, and computational efficiency in GNN-based CTS analysis. CTS-Bench consists of 4,860 converged physical design solutions spanning five architectures and provides paired raw gate-level and clustered graph representations derived from post-placement designs. Using clock skew prediction as a representative CTS task, we demonstrate a clear accuracy-efficiency trade-off. While graph coarsening reduces GPU memory usage by up to 17.2x and accelerates training by up to 3x, it also removes structural information essential for modeling clock distribution, frequently resulting in negative $R^2$ scores under zero-shot evaluation. Our findings indicate that generic graph clustering techniques can fundamentally compromise CTS learning objectives, even when global physical metrics remain unchanged. CTS-Bench enables principled evaluation of CTS-aware graph coarsening strategies, supports benchmarking of GNN architectures and accelerators under realistic physical design constraints, and provides a foundation for developing learning-assisted CTS analysis and optimization techniques.

---

### Dynamic Elasticity Between Forest Loss and Carbon Emissions: A Subnational Panel Analysis of the United States

Authors: Keonvin Park
Published: 2026-02-22
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2602.19329v1

Accurate quantification of the relationship between forest loss and associated carbon emissions is critical for both environmental monitoring and policy evaluation. Although many studies have documented spatial patterns of forest degradation, there is limited understanding of the dynamic elasticity linking tree cover loss to carbon emissions at subnational scales. In this paper, we construct a comprehensive panel dataset of annual forest loss and carbon emission estimates for U.S. subnational administrative units from 2001 to 2023, based on the Hansen Global Forest Change dataset. We apply fixed effects and dynamic panel regression techniques to isolate within-region variation and account for temporal persistence in emissions. Our results show that forest loss has a significant positive short-run elasticity with carbon emissions, and that emissions exhibit strong persistence over time. Importantly, the estimated long-run elasticity, accounting for autoregressive dynamics, is substantially larger than the short-run effect, indicating cumulative impacts of repeated forest loss events. These findings highlight the importance of modeling temporal dynamics when assessing environmental responses to land cover change. The dynamic elasticity framework proposed here offers a robust and interpretable tool for analyzing environmental change processes, and can inform both regional monitoring systems and carbon accounting frameworks.

---

### Soft Sequence Policy Optimization

Authors: Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko
Published: 2026-02-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19327v3

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift toward sequence-level importance sampling weights that better align with the sequence-level rewards used in many tasks, and (ii) alternatives to the PPO-style clipping that aim to avoid the associated loss of training signal and entropy collapse. We introduce Soft Sequence Policy Optimization, an off-policy reinforcement learning objective that incorporates soft gating functions over token-level probability ratios within sequence-level importance weights. We provide theoretical motivation for SSPO and investigate practical modifications to improve optimization behavior. Empirically, we demonstrate that SSPO improves training stability and performance both in mathematical reasoning and coding tasks.

---

### City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

Authors: Rui Liu, Steven Jige Quan, Zhong-Ren Peng, Zijun Yao, Han Wang, Pengyang Wang, Kunpeng Liu, Yanjie Fu, Dongjie Wang
Published: 2026-02-22
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.19326v3

Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints is labor-intensive and error-prone. To tackle this, we propose CEAE, a hierarchical agentic framework that formulates urban renewal as machine-executable GeoJSON editing from natural-language instructions. CEAE decomposes instructions into hierarchical geometric intents, executing edits from coarse to fine while preserving spatial consistency through a self-reflective execution-validation loop. Experimental results show that CEAE outperforms baselines in execution validity, robustness, and geometric accuracy.

---

### City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

Authors: Rui Liu, Steven Jige Quan, Zhong-Ren Peng, Zijun Yao, Han Wang, Zhengzhang Chen, Kunpeng Liu, Yanjie Fu, Dongjie Wang
Published: 2026-02-22
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.19326v2

As cities evolve over time, challenges such as traffic congestion and functional imbalance increasingly necessitate urban renewal through efficient modification of existing plans, rather than complete re-planning. In practice, even minor urban changes require substantial manual effort to redraw geospatial layouts, slowing the iterative planning and decision-making procedure. Motivated by recent advances in agentic systems and multimodal reasoning, we formulate urban renewal as a machine-executable task that iteratively modifies existing urban plans represented in structured geospatial formats. More specifically, we represent urban layouts using GeoJSON and decompose natural-language editing instructions into hierarchical geometric intents spanning polygon-, line-, and point-level operations. To coordinate interdependent edits across spatial elements and abstraction levels, we propose a hierarchical agentic framework that jointly performs multi-level planning and execution with explicit propagation of intermediate spatial constraints. We further introduce an iterative execution-validation mechanism that mitigates error accumulation and enforces global spatial consistency during multi-step editing. Extensive experiments across diverse urban editing scenarios demonstrate significant improvements in efficiency, robustness, correctness, and spatial validity over existing baselines.

---

### RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework

Authors: Mohammad Tahmid Noor, Shayan Abrar, Jannatul Adan Mahi, Md Parvez Mia, Asaduzzaman Hridoy, Samanta Ghosh
Published: 2026-02-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19324v1

Early and accurate classification of retinal diseases is critical to counter vision loss and for guiding clinical management of retinal diseases. In this study, we proposed a deep learning method for retinal disease classification utilizing optical coherence tomography (OCT) images from the Retinal OCT Image Classification - C8 dataset (comprising 24,000 labeled images spanning eight conditions). Images were resized to 224x224 px and tested on convolutional neural network (CNN) architectures: Xception and InceptionV3. Data augmentation techniques (CutMix, MixUp) were employed to enhance model generalization. Additionally, we applied GradCAM and LIME for interpretability evaluation. We implemented this in a real-world scenario via our web application named RetinaVision. This study found that Xception was the most accurate network (95.25%), followed closely by InceptionV3 (94.82%). These results suggest that deep learning methods allow effective OCT retinal disease classification and highlight the importance of implementing accuracy and interpretability for clinical applications.

---

### DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering

Authors: Yiran Qiao, Yiren Lu, Yunlai Zhou, Rui Yang, Linlin Hou, Yu Yin, Jing Ma
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19323v2

3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, where imperceptible yet consistent perturbations can drastically degrade rendering quality, increase training and rendering time, and inflate memory usage, even leading to server denial-of-service. In our work, to mitigate this issue, we begin by analyzing the distinct behaviors of adversarial perturbations in the low- and high-frequency components of input images using wavelet transforms. Based on this observation, we design a simple yet effective frequency-aware defense strategy that reconstructs training views by filtering high-frequency noise while preserving low-frequency content. This approach effectively suppresses adversarial artifacts while maintaining the authenticity of the original scene. Notably, it does not significantly impair training on clean data, achieving a desirable trade-off between robustness and performance on clean inputs. Through extensive experiments under a wide range of attack intensities on multiple benchmarks, we demonstrate that our method substantially enhances the robustness of 3DGS without access to clean ground-truth supervision. By highlighting and addressing the overlooked vulnerabilities of 3D Gaussian Splatting, our work paves the way for more robust and secure 3D reconstructions.

---

### US-JEPA: A Joint Embedding Predictive Architecture for Ultrasound

Authors: Ashwath Radhachandran, Vedrana Ivezić, Shreeram Athreya, Corey W. Arnold, William Speier
Published: 2026-02-22
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19322v2

Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods relying on a pixel-level reconstruction objective. Joint-Embedding Predictive Architectures (JEPAs) address this drawback by predicting masked latent representations rather than raw pixels. However, standard approaches depend on hyperparameter-brittle and computationally expensive online teachers updated via exponential moving average. We propose US-JEPA, a self-supervised framework that adopts the Static-teacher Asymmetric Latent Training (SALT) objective. By using a frozen, domain-specific teacher to provide stable latent targets, US-JEPA decouples student-teacher optimization and pushes the student to expand upon the semantic priors of the teacher. In addition, we provide the first rigorous comparison of all publicly available state-of-the-art ultrasound foundation models on UltraBench, a public dataset benchmark spanning multiple organs and pathological conditions. Under linear probing for diverse classification tasks, US-JEPA achieves performance competitive with or superior to domain-specific and universal vision foundation model baselines. Our results demonstrate that masked latent prediction provides a stable and efficient path toward robust ultrasound representations.

---

### US-JEPA: A Joint Embedding Predictive Architecture for Medical Ultrasound

Authors: Ashwath Radhachandran, Vedrana Ivezić, Shreeram Athreya, Ronit Anilkumar, Corey W. Arnold, William Speier
Published: 2026-02-22
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19322v1

Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods relying on a pixel-level reconstruction objective. Joint-Embedding Predictive Architectures (JEPAs) address this drawback by predicting masked latent representations rather than raw pixels. However, standard approaches depend on hyperparameter-brittle and computationally expensive online teachers updated via exponential moving average. We propose US-JEPA, a self-supervised framework that adopts the Static-teacher Asymmetric Latent Training (SALT) objective. By using a frozen, domain-specific teacher to provide stable latent targets, US-JEPA decouples student-teacher optimization and pushes the student to expand upon the semantic priors of the teacher. In addition, we provide the first rigorous comparison of all publicly available state-of-the-art ultrasound foundation models on UltraBench, a public dataset benchmark spanning multiple organs and pathological conditions. Under linear probing for diverse classification tasks, US-JEPA achieves performance competitive with or superior to domain-specific and universal vision foundation model baselines. Our results demonstrate that masked latent prediction provides a stable and efficient path toward robust ultrasound representations.

---

### Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

Authors: Dongming Jiang, Yi Li, Songtao Wei, Jinxin Yang, Ayushi Kishore, Alysa Zhao, Dingyi Kang, Xu Hu, Feng Chen, Qiannan Li, Bingzhe Li
Published: 2026-02-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.19320v2

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system perspectives. We first introduce a concise taxonomy of MAG systems based on four memory structures. Then, we analyze key pain points limiting current systems, including benchmark saturation effects, metric validity and judge sensitivity, backbone-dependent accuracy, and the latency and throughput overhead introduced by memory maintenance. By connecting the memory structure to empirical limitations, this survey clarifies why current agentic memory systems often underperform their theoretical promise and outlines directions for more reliable evaluation and scalable system design.

---

### Health+: Empowering Individuals via Unifying Health Data

Authors: Sujaya Maiyya, Shantanu Sharma, Avinash Kumar
Published: 2026-02-22
Categories: cs.MM, cs.AI, cs.CR, cs.DB, cs.DC
arXiv: https://arxiv.org/abs/2602.19319v1

Managing personal health data is a challenge in today's fragmented and institution-centric healthcare ecosystem. Individuals often lack meaningful control over their medical records, which are scattered across incompatible systems and formats. This vision paper presents Health+, a user-centric, multimodal health data management system that empowers individuals (including those with limited technical expertise) to upload, query, and share their data across modalities (e.g., text, images, reports). Rather than aiming for institutional overhaul, Health+ emphasizes individual agency by providing intuitive interfaces and intelligent recommendations for data access and sharing. At the system level, it tackles the complexity of storing, integrating, and securing heterogeneous health records, ensuring both efficiency and privacy. By unifying multimodal data and prioritizing patients, Health+ lays the foundation for a more connected, interpretable, and user-controlled health information ecosystem.

---

### Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering

Authors: Maryam Amirizaniani, Alireza Salemi, Hamed Zamani
Published: 2026-02-22
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.19317v1

Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-augmented generation (RAG) solutions that construct personal context by retrieving relevant items from the user's profile. Existing methods use the user's query directly to retrieve personal documents, and such strategies often lead to surface-level personalization. We propose PR2 (Personalized Retrieval-Augmented Reasoning), a reinforcement learning framework that integrates reasoning and retrieval from personal context for personalization. PR2 learns adaptive retrieval-reasoning policies, determining when to retrieve, what evidence to retrieve from user profiles, and how to incorporate it into intermediate reasoning steps. By optimizing multi-turn reasoning trajectories under a personalized reward function, the framework reinforces reasoning paths that better align with user-specific preferences and contextual signals reflected by the reward model. Extensive experiments on the LaMP-QA benchmark using three LLMs show that PR2 consistently outperforms strong baselines, achieving an average relative improvement of 8.8%-12% in personalized QA.

---

### Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition

Authors: Alexandros Haliassos, Rodrigo Mira, Stavros Petridis
Published: 2026-02-22
Categories: cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2602.19316v1

Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its reliance on autoregressive pseudo-labelling makes training expensive, while its decoupled supervision of CTC and attention branches increases susceptibility to self-reinforcing errors, particularly under distribution shifts involving longer sequences, noise, or unseen domains. We propose CTC-driven teacher forcing, where greedily decoded CTC pseudo-labels are fed into the decoder to generate attention targets in a single forward pass. Although these can be globally incoherent, in the pseudo-labelling setting they enable efficient and effective knowledge transfer. Because CTC and CTC-driven attention pseudo-labels have the same length, the decoder can predict both simultaneously, benefiting from the robustness of CTC and the expressiveness of attention without costly beam search. We further propose mixed sampling to mitigate the exposure bias of the decoder relying solely on CTC inputs. The resulting method, USR 2.0, halves training time, improves robustness to out-of-distribution inputs, and achieves state-of-the-art results on LRS3, LRS2, and WildVSR, surpassing USR and modality-specific self-supervised baselines.

---

### Online Navigation Planning for Long-term Autonomous Operation of Underwater Gliders

Authors: Victor-Alexandru Darvariu, Charlotte Z. Reed, Jan Stratmann, Bruno Lacerda, Benjamin Allsup, Stephen Woodward, Elizabeth Siddle, Trishna Saeharaseelan, Owain Jones, Dan Jones, Tobias Ferreira, Chloe Baker et al.
Published: 2026-02-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.19315v2

Underwater glider robots have become indispensable for ocean sampling, yet fully autonomous long-term operation remains rare in practice. Although stakeholders are calling for tools to manage increasingly large fleets of gliders, existing methods have seen limited adoption due to their inability to account for environmental uncertainty and operational constraints. In this work, we demonstrate that uncertainty-aware online navigation planning can be deployed in real-world glider missions at scale. We formulate the problem as a stochastic shortest-path Markov Decision Process and propose a sample-based online planner based on Monte Carlo Tree Search. Samples are generated by a physics-informed simulator calibrated on real-world glider data that captures uncertain execution of controls and ocean current forecasts while remaining computationally tractable. Our methodology is integrated into an autonomous system for Slocum gliders that performs closed-loop replanning at each surfacing. The system was validated in two North Sea deployments totalling approximately 3 months and 1000 km, representing the longest fully autonomous glider campaigns in the literature to date. Results demonstrate improvements of up to 9.88% in dive duration and 16.51% in path length compared to standard straight-to-goal navigation, including a statistically significant path length reduction of 9.55% in a field deployment.

---

### IPv2: An Improved Image Purification Strategy for Real-World Ultra-Low-Dose Lung CT Denoising

Authors: Guoliang Gong, Man Yu
Published: 2026-02-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19314v1

The image purification strategy constructs an intermediate distribution with aligned anatomical structures, which effectively corrects the spatial misalignment between real-world ultra-low-dose CT and normal-dose CT images and significantly enhances the structural preservation ability of denoising models. However, this strategy exhibits two inherent limitations. First, it suppresses noise only in the chest wall and bone regions while leaving the image background untreated. Second, it lacks a dedicated mechanism for denoising the lung parenchyma. To address these issues, we systematically redesign the original image purification strategy and propose an improved version termed IPv2. The proposed strategy introduces three core modules, namely Remove Background, Add noise, and Remove noise. These modules endow the model with denoising capability in both background and lung tissue regions during training data construction and provide a more reasonable evaluation protocol through refined label construction at the testing stage. Extensive experiments on our previously established real-world patient lung CT dataset acquired at 2% radiation dose demonstrate that IPv2 consistently improves background suppression and lung parenchyma restoration across multiple mainstream denoising models. The code is publicly available at https://github.com/MonkeyDadLufy/Image-Purification-Strategy-v2.

---

### TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

Authors: Shirui Chen, Cole Harrison, Ying-Chun Lee, Angela Jin Yang, Zhongzheng Ren, Lillian J. Ratliff, Jiafei Duan, Dieter Fox, Ranjay Krishna
Published: 2026-02-22
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19313v2

General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior. Yet obtaining such feedback at scale remains difficult, since existing approaches often rely on manual progress annotations, task-specific demonstrations, or reward models trained on curated robot datasets. We introduce TOPReward, a training-free progress reward method that probes pretrained Video-Language Models (VLMs) through their internal token probabilities rather than asking them to generate numerical progress values. Given a video prefix and a language instruction, TOPReward measures the model's likelihood that the instructed task has been completed, converting latent video-language understanding into a dense reward signal without task-specific reward-model training or manually annotated progress labels. We evaluate TOPReward on ManiRewardBench, our real-world manipulation benchmark spanning 130 unique tasks and four robot platforms, as well as on Open X-Embodiment datasets. Across these settings, TOPReward substantially outperforms prior training-free VLM reward methods on open-source models and is competitive with a trained reward-model baseline on progress-estimation metrics, while requiring no reward-model training. Additional analyses show that the reward is sensitive to the specified instruction and is not explained by time index alone. Finally, TOPReward supports downstream applications including success detection and offline reward-weighted behavior cloning.

---

### Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference

Authors: Kyriakos Stylianopoulos, Mario Edoardo Pandolfo, Paolo Di Lorenzo, George C. Alexandropoulos
Published: 2026-02-22
Categories: cs.ET, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.19312v1

The upcoming sixth Generation (6G) of wireless networks envisions ultra-low latency and energy efficient Edge Inference (EI) for diverse Internet of Things (IoT) applications. However, traditional digital hardware for machine learning is power intensive, motivating the need for alternative computation paradigms. Over-The-Air (OTA) computation is regarded as an emerging transformative approach assigning the wireless channel to actively perform computational tasks. This article introduces the concept of Metasurfaces-Integrated Neural Networks (MINNs), a physical-layer-enabled deep learning framework that leverages programmable multi-layer metasurface structures and Multiple-Input Multiple-Output (MIMO) channels to realize computational layers in the wave propagation domain. The MINN system is conceptualized as three modules: Encoder, Channel (uncontrollable propagation features and metasurfaces), and Decoder. The first and last modules, realized respectively at the multi-antenna transmitter and receiver, consist of conventional digital or purposely designed analog Deep Neural Network (DNN) layers, and the metasurfaces responses of the Channel module are optimized alongside all modules as trainable weights. This architecture enables computation offloading into the end-to-end physical layer, flexibly among its constituent modules, achieving performance comparable to fully digital DNNs while significantly reducing power consumption. The training of the MINN framework, two representative variations, and performance results for indicative applications are presented, highlighting the potential of MINNs as a lightweight and sustainable solution for future EI-enabled wireless systems. The article is concluded with a list of open challenges and promising research directions.

---

### WildOS: Open-Vocabulary Object Search in the Wild

Authors: Hardik Shah, Erica Tevere, Deegan Atha, Marcel Kaufmann, Shehryar Khattak, Manthan Patel, Marco Hutter, Jonas Frey, Patrick Spieler
Published: 2026-02-22
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.19308v1

Autonomous navigation in complex, unstructured outdoor environments requires robots to operate over long ranges without prior maps and limited depth sensing. In such settings, relying solely on geometric frontiers for exploration is often insufficient. In such settings, the ability to reason semantically about where to go and what is safe to traverse is crucial for robust, efficient exploration. This work presents WildOS, a unified system for long-range, open-vocabulary object search that combines safe geometric exploration with semantic visual reasoning. WildOS builds a sparse navigation graph to maintain spatial memory, while utilizing a foundation-model-based vision module, ExploRFM, to score frontier nodes of the graph. ExploRFM simultaneously predicts traversability, visual frontiers, and object similarity in image space, enabling real-time, onboard semantic navigation tasks. The resulting vision-scored graph enables the robot to explore semantically meaningful directions while ensuring geometric safety. Furthermore, we introduce a particle-filter-based method for coarse localization of the open-vocabulary target query, that estimates candidate goal positions beyond the robot's immediate depth horizon, enabling effective planning toward distant goals. Extensive closed-loop field experiments across diverse off-road and urban terrains demonstrate that WildOS enables robust navigation, significantly outperforming purely geometric and purely vision-based baselines in both efficiency and autonomy. Our results highlight the potential of vision foundation models to drive open-world robotic behaviors that are both semantically informed and geometrically grounded. Project Page: https://leggedrobotics.github.io/wildos/

---

### Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation

Authors: Haojun Shi, Suyu Ye, Katherine M. Guerrerio, Jianzhi Shen, Yifan Yin, Daniel Khashabi, Chien-Ming Huang, Tianmin Shu
Published: 2026-02-22
Categories: cs.RO, cs.AI, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2602.19304v1

Successful cooperation among decentralized agents requires each agent to quickly adapt its plan to the behavior of other agents. In scenarios where agents cannot confidently predict one another's intentions and plans, language communication can be crucial for ensuring safety. In this work, we focus on path-level cooperation in which agents must adapt their paths to one another in order to avoid collisions or perform physical collaboration such as joint carrying. In particular, we propose a safe and interpretable multimodal path planning method, CaPE (Code as Path Editor), which generates and updates path plans for an agent based on the environment and language communication from other agents. CaPE leverages a vision-language model (VLM) to synthesize a path editing program verified by a model-based planner, grounding communication to path plan updates in a safe and interpretable way. We evaluate our approach in diverse simulated and real-world scenarios, including multi-robot and human-robot cooperation in autonomous driving, household, and joint carrying tasks. Experimental results demonstrate that CaPE can be integrated into different robotic systems as a plug-and-play module, greatly enhancing a robot's ability to align its plan to language communication from other robots or humans. We also show that the combination of the VLM-based path editing program synthesis and model-based planning safety enables robots to achieve open-ended cooperation while maintaining safety and interpretability.

---

### ALPACA: A Reinforcement Learning Environment for Medication Repurposing and Treatment Optimization in Alzheimer's Disease

Authors: Nolan Brady, Tom Yeh
Published: 2026-02-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.19298v1

Evaluating personalized, sequential treatment strategies for Alzheimer's disease (AD) using clinical trials is often impractical due to long disease horizons and substantial inter-patient heterogeneity. To address these constraints, we present the Alzheimer's Learning Platform for Adaptive Care Agents (ALPACA), an open-source, Gym-compatible reinforcement learning (RL) environment for systematically exploring personalized treatment strategies using existing therapies. ALPACA is powered by the Continuous Action-conditioned State Transitions (CAST) model trained on longitudinal trajectories from the Alzheimer's Disease Neuroimaging Initiative (ADNI), enabling medication-conditioned simulation of disease progression under alternative treatment decisions. We show that CAST autoregressively generates realistic medication-conditioned trajectories and that RL policies trained in ALPACA outperform no-treatment and behavior-cloned clinician baselines on memory-related outcomes. Interpretability analyses further indicated that the learned policies relied on clinically meaningful patient features when selecting actions. Overall, ALPACA provides a reusable in silico testbed for studying individualized sequential treatment decision-making for AD.

---

### Automated Generation of Microfluidic Netlists using Large Language Models

Authors: Jasper Davidson, Skylar Stockham, Allen Boston, Ashton Snelgrove, Valerio Tenace, Pierre-Emmanuel Gaillardon
Published: 2026-02-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.19297v2

Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for many practitioners. While progress has been made in microfluidic design automation (MFDA), a practical and intuitive solution is still needed to connect microfluidic practitioners with MFDA techniques. This work introduces the first practical application of large language models (LLMs) in this context, providing a preliminary demonstration. Building on prior research in hardware description language (HDL) code generation with LLMs, we propose an initial methodology to convert natural language microfluidic device specifications into system-level structural Verilog netlists. We demonstrate the feasibility of our approach by generating structural netlists for practical benchmarks representative of typical microfluidic designs with correct functional flow and an average syntactical accuracy of 88%.

---

### AdsorbFlow: energy-conditioned flow matching enables fast and realistic adsorbate placement

Authors: Jiangjie Qiu, Wentao Li, Honghao Chen, Leyi Zhao, Xiaonan Wang
Published: 2026-02-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19289v1

Identifying low-energy adsorption geometries on catalytic surfaces is a practical bottleneck for computational heterogeneous catalysis: the difficulty lies not only in the cost of density functional theory (DFT) but in proposing initial placements that relax into the correct energy basins. Conditional denoising diffusion has improved success rates, yet requires $\sim$100 iterative steps per sample. Here we introduce AdsorbFlow, a deterministic generative model that learns an energy-conditioned vector field on the rigid-body configuration space of adsorbate translation and rotation via conditional flow matching. Energy information enters through classifier-free guidance conditioning -- not energy-gradient guidance -- and sampling reduces to integrating an ODE in as few as 5 steps. On OC20-Dense with full DFT single-point verification, AdsorbFlow with an EquiformerV2 backbone achieves 61.4% SR@10 and 34.1% SR@1 -- surpassing AdsorbDiff (31.8% SR@1, 41.0% SR@10) at every evaluation level and AdsorbML (47.7% SR@10) -- while using 20 times fewer generative steps and achieving the lowest anomaly rate among generative methods (6.8%). On 50 out-of-distribution systems, AdsorbFlow retains 58.0% SR@10 with a MLFF-to-DFT gap of only 4~percentage points. These results establish that deterministic transport is both faster and more accurate than stochastic denoising for adsorbate placement.

---

### MRI Contrast Enhancement Kinetics World Model

Authors: Jindi Kong, Yuting He, Cong Xia, Rongjun Ge, Shuo Li
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19285v1

Clinical MRI contrast acquisition suffers from inefficient information yield, which presents as a mismatch between the risky and costly acquisition protocol and the fixed and sparse acquisition sequence. Applying world models to simulate the contrast enhancement kinetics in the human body enables continuous contrast-free dynamics. However, the low temporal resolution in MRI acquisition restricts the training of world models, leading to a sparsely sampled dataset. Directly training a generative model to capture the kinetics leads to two limitations: (a) Due to the absence of data on missing time, the model tends to overfit to irrelevant features, leading to content distortion. (b) Due to the lack of continuous temporal supervision, the model fails to learn the continuous kinetics law over time, causing temporal discontinuities. For the first time, we propose MRI Contrast Enhancement Kinetics World model (MRI CEKWorld) with SpatioTemporal Consistency Learning (STCL). For (a), guided by the spatial law that patient-level structures remain consistent during enhancement, we propose Latent Alignment Learning (LAL) that constructs a patient-specific template to constrain contents to align with this template. For (b), guided by the temporal law that the kinetics follow a consistent smooth trend, we propose Latent Difference Learning (LDL) which extends the unobserved intervals by interpolation and constrains smooth variations in the latent space among interpolated sequences. Extensive experiments on two datasets show our MRI CEKWorld achieves better realistic contents and kinetics. Codes will be available at https://github.com/DD0922/MRI-Contrast-Enhancement-Kinetics-World-Model.

---

### Limited Reasoning Space: The cage of long-horizon reasoning in LLMs

Authors: Zhenyu Li, Guanlin Wu, Cheems Wang, Yongqiang Zhao
Published: 2026-02-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.19281v2

The test-time compute strategy, such as Chain-of-Thought (CoT), has significantly enhanced the ability of large language models to solve complex tasks like logical reasoning. However, empirical studies indicate that simply increasing the compute budget can sometimes lead to a collapse in test-time performance when employing typical task decomposition strategies such as CoT. This work hypothesizes that reasoning failures with larger compute budgets stem from static planning methods, which hardly perceive the intrinsic boundaries of LLM reasoning. We term it as the Limited Reasoning Space hypothesis and perform theoretical analysis through the lens of a non-autonomous stochastic dynamical system. This insight suggests that there is an optimal range for compute budgets; over-planning can lead to redundant feedback and may even impair reasoning capabilities. To exploit the compute-scaling benefits and suppress over-planning, this work proposes Halo, a model predictive control framework for LLM planning. Halo is designed for long-horizon tasks with reason-based planning and crafts an entropy-driven dual controller, which adopts a Measure-then-Plan strategy to achieve controllable reasoning. Experimental results demonstrate that Halo outperforms static baselines on complex long-horizon tasks by dynamically regulating planning at the reasoning boundary.

---

### A Two-Stage Detection-Tracking Framework for Stable Apple Quality Inspection in Dense Conveyor-Belt Environments

Authors: Keonvin Park, Aditya Pal, Jin Hong Mok
Published: 2026-02-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19278v1

Industrial fruit inspection systems must operate reliably under dense multi-object interactions and continuous motion, yet most existing works evaluate detection or classification at the image level without ensuring temporal stability in video streams. We present a two-stage detection-tracking framework for stable multi-apple quality inspection in conveyor-belt environments. An orchard-trained YOLOv8 model performs apple localization, followed by ByteTrack multi-object tracking to maintain persistent identities. A ResNet18 defect classifier, fine-tuned on a healthy-defective fruit dataset, is applied to cropped apple regions. Track-level aggregation is introduced to enforce temporal consistency and reduce prediction oscillation across frames. We define video-level industrial metrics such as track-level defect ratio and temporal consistency to evaluate system robustness under realistic processing conditions. Results demonstrate improved stability compared to frame-wise inference, suggesting that integrating tracking is essential for practical automated fruit grading systems.

---

### DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

Authors: Krishna Khadka, Yu Lei, Raghu N. Kacker, D. Richard Kuhn
Published: 2026-02-22
Categories: cs.CV, cs.SE
arXiv: https://arxiv.org/abs/2602.19274v1

We introduce a gradient-free framework for identifying minimal, sufficient, and decision-preserving explanations in vision models by isolating the smallest subset of representational units whose joint activation preserves predictions. Unlike existing approaches that aggregate all units, often leading to cluttered saliency maps, our approach, DD-CAM, identifies a 1-minimal subset whose joint activation suffices to preserve the prediction (i.e., removing any unit from the subset alters the prediction). To efficiently isolate minimal sufficient subsets, we adapt delta debugging, a systematic reduction strategy from software debugging, and configure its search strategy based on unit interactions in the classifier head: testing individual units for models with non-interacting units and testing unit combinations for models in which unit interactions exist. We then generate minimal, prediction-preserving saliency maps that highlight only the most essential features. Our experimental evaluation demonstrates that our approach can produce more faithful explanations and achieve higher localization accuracy than the state-of-the-art CAM-based approaches.

---

### Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data

Authors: Junkang Liu, Fanhua Shang, Hongying Liu, Jin Liu, Weixin An, Yuanyuan Liu
Published: 2026-02-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19271v1

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key culprit is \emph{preconditioner drift}: client-side second-order training induces heterogeneous \emph{curvature-defined geometries} (i.e., preconditioner coordinate systems), and server-side model averaging updates computed under incompatible metrics, corrupting the global descent direction. To address this geometric mismatch, we propose \texttt{FedPAC}, a \emph{preconditioner alignment and correction} framework for reliable federated second-order optimization. \texttt{FedPAC} explicitly decouples parameter aggregation from geometry synchronization by: (i) \textbf{Alignment} (i.e.,aggregating local preconditioners into a global reference and warm-starting clients via global preconditioner); and (ii) \textbf{Correction} (i.e., steering local preconditioned updates using a global preconditioned direction to suppress long-term drift). We provide drift-coupled non-convex convergence guarantees with linear speedup under partial participation. Empirically, \texttt{FedPAC} consistently improves stability and accuracy across vision and language tasks, achieving up to $5.8\%$ absolute accuracy gain on CIFAR-100 with ViTs. Code is available at https://anonymous.4open.science/r/FedPAC-8B24.

---

### CORVET: A CORDIC-Powered, Resource-Frugal Mixed-Precision Vector Processing Engine for High-Throughput AIoT applications

Authors: Sonu Kumar, Mohd Faisal Khan, Mukul Lokhande, Santosh Kumar Vishvakarma
Published: 2026-02-22
Categories: cs.AR, cs.AI, cs.CV, cs.NE, eess.IV
arXiv: https://arxiv.org/abs/2602.19268v1

This brief presents a runtime-adaptive, performance-enhanced vector engine featuring a low-resource, iterative CORDIC-based MAC unit for edge AI acceleration. The proposed design enables dynamic reconfiguration between approximate and accurate modes, exploiting the latency-accuracy trade-off for a wide range of workloads. Its resource-efficient approach further enables up to 4x throughput improvement within the same hardware resources by leveraging vectorised, time-multiplexed execution and flexible precision scaling. With a time-multiplexed multi-AF block and a lightweight pooling and normalisation unit, the proposed vector engine supports flexible precision (4/8/16-bit) and high MAC density. The ASIC implementation results show that each MAC stage can save up to 33% of time and 21% of power, with a 256-PE configuration that achieves higher compute density (4.83 TOPS/mm2 ) and energy efficiency (11.67 TOPS/W) than previous state-of-the-art work. A detailed hardware-software co-design methodology for object detection and classification tasks on Pynq-Z2 is discussed to assess the proposed architecture, demonstrating a scalable, energy-efficient solution for edge AI applications.

---

### Spectral bias in physics-informed and operator learning: Analysis and mitigation guidelines

Authors: Siavash Khodakarami, Vivek Oommen, Nazanin Ahmadi Daryakenari, Maxim Beekenkamp, George Em Karniadakis
Published: 2026-02-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19265v1

Solving partial differential equations (PDEs) by neural networks as well as Kolmogorov-Arnold Networks (KANs), including physics-informed neural networks (PINNs), physics-informed KANs (PIKANs), and neural operators, are known to exhibit spectral bias, whereby low-frequency components of the solution are learned significantly faster than high-frequency modes. While spectral bias is often treated as an intrinsic representational limitation of neural architectures, its interaction with optimization dynamics and physics-based loss formulations remains poorly understood. In this work, we provide a systematic investigation of spectral bias in physics-informed and operator learning frameworks, with emphasis on the coupled roles of network architecture, activation functions, loss design, and optimization strategy. We quantify spectral bias through frequency-resolved error metrics, Barron-norm diagnostics, and higher-order statistical moments, enabling a unified analysis across elliptic, hyperbolic, and dispersive PDEs. Through diverse benchmark problems, including the Korteweg-de Vries, wave and steady-state diffusion-reaction equations, turbulent flow reconstruction, and earthquake dynamics, we demonstrate that spectral bias is not simply representational but fundamentally dynamical. In particular, second-order optimization methods substantially alter the spectral learning order, enabling earlier and more accurate recovery of high-frequency modes for all PDE types. For neural operators, we further show that spectral bias is dependent on the neural operator architecture and can also be effectively mitigated through spectral-aware loss formulations without increasing the inference cost.

---

### Prognostics of Multisensor Systems with Unknown and Unlabeled Failure Modes via Bayesian Nonparametric Process Mixtures

Authors: Kani Fu, Sanduni S Disanayaka Mudiyanselage, Chunli Dai, Minhee Kim
Published: 2026-02-22
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2602.19263v1

Modern manufacturing systems often experience multiple and unpredictable failure behaviors, yet most existing prognostic models assume a fixed, known set of failure modes with labeled historical data. This assumption limits the use of digital twins for predictive maintenance, especially in high-mix or adaptive production environments, where new failure modes may emerge, and the failure mode labels may be unavailable. To address these challenges, we propose a novel Bayesian nonparametric framework that unifies a Dirichlet process mixture module for unsupervised failure mode discovery with a neural network-based prognostic module. The key innovation lies in an iterative feedback mechanism to jointly learn two modules. These modules iteratively update one another to dynamically infer, expand, or merge failure modes as new data arrive while providing high prognostic accuracy. Experiments on both simulation and aircraft engine datasets show that the proposed approach performs competitively with or significantly better than existing approaches. It also exhibits robust online adaptation capabilities, making it well-suited for digital-twin-based system health management in complex manufacturing environments.

---

### DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

Authors: Aleksei Liuliakov, Luca Hermes, Barbara Hammer
Published: 2026-02-22
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2602.19261v2

Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models have similarly been applied to combinatorial structure generation, including neural architecture search (NAS). However, neural architectures are directed acyclic graphs (DAGs) where edge direction encodes functional semantics such as data flow-information that existing graph diffusion methods, designed for undirected structures, discard. We propose Directed Graph Policy Optimization (DGPO), which extends reinforcement learning fine-tuning of discrete graph diffusion models to DAGs via topological node ordering and positional encoding. Validated on NAS-Bench-101 and NAS-Bench-201, DGPO matches the benchmark optimum on all three NAS-Bench-201 tasks (91.61%, 73.49%, 46.77%). The central finding is that the model learns transferable structural priors: pretrained on only 7% of the search space, it generates near-oracle architectures after fine-tuning, within 0.32 percentage points of the full-data model and extrapolating 7.3 percentage points beyond its training ceiling. Bidirectional control experiments confirm genuine reward-driven steering, with inverse optimization reaching near random-chance accuracy (9.5%). These results demonstrate that reinforcement learning-steered discrete diffusion, once extended to handle directionality, provides a controllable generative framework for directed combinatorial structures.

---