# Research Papers — 2026-03 · bundle page 108 of 243 > Full-text markdown of papers #5351–5400 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/108 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/107.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/109.md) ### GazeOnce360: Fisheye-Based 360° Multi-Person Gaze Estimation with Global-Local Feature Fusion Authors: Zhuojiang Cai, Zhenghui Sun, Feng Lu Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17161v1 We present GazeOnce360, a novel end-to-end model for multi-person gaze estimation from a single tabletop-mounted upward-facing fisheye camera. Unlike conventional approaches that rely on forward-facing cameras in constrained viewpoints, we address the underexplored setting of estimating the 3D gaze direction of multiple people distributed across a 360° scene from an upward fisheye perspective. To support research in this setting, we introduce MPSGaze360, a large-scale synthetic dataset rendered using Unreal Engine, featuring diverse multi-person configurations with accurate 3D gaze and eye landmark annotations. Our model tackles the severe distortion and perspective variation inherent in fisheye imagery by incorporating rotational convolutions and eye landmark supervision. To better capture fine-grained eye features crucial for gaze estimation, we propose a dual-resolution architecture that fuses global low-resolution context with high-resolution local eye regions. Experimental results demonstrate the effectiveness of each component in our model. This work highlights the feasibility and potential of fisheye-based 360° gaze estimation in practical multi-person scenarios. Project page: https://caizhuojiang.github.io/GazeOnce360/. --- ### Self-Regularized Learning Methods Authors: Max Schölpple, Liu Fanghui, Ingo Steinwart Published: 2026-03-17 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2603.17160v1 We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations that many algorithms, such as gradient-descent based learning, exhibit implicit regularization. In a nutshell, for a self-regularized algorithm the complexity of the predictor is inherently controlled by that of the simplest comparator achieving the same empirical risk. This framework is sufficiently rich to cover both classical regularized empirical risk minimization and gradient descent. Building on self-regularization, we provide a thorough statistical analysis of such algorithms including minmax-optimal rates, where it suffices to show that the algorithm is self-regularized -- all further requirements stem from the learning problem itself. Finally, we discuss the problem of data-dependent hyperparameter selection, providing a general result which yields minmax-optimal rates up to a double logarithmic factor and covers data-driven early stopping for RKHS-based gradient descent. --- ### BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images Authors: David Skuddis, Vincent Ress, Wei Zhang, Vincent Ofosu Nyako, Norbert Haala Published: 2026-03-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.17159v1 We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific patterns at a prescribed spatial density and treat them as landmarks. A consistency loss aligns learnable global landmark coordinates with per-frame heatmaps, yielding consistent landmark detections across the scene. Across campus, industrial, and forest environments, BEV-SLD delivers robust localization and achieves strong performance compared to state-of-the-art methods. --- ### A Lensless Polarization Camera Authors: Noa Kraicer, Shay Elmalem, Erez Yosef, Hani Barhum, Raja Giryes Published: 2026-03-17 Categories: eess.IV, cs.CV, physics.optics arXiv: https://arxiv.org/abs/2603.17156v1 Polarization imaging is a technique that creates a pixel map of the polarization state in a scene. Although invisible to the human eye, polarization can assist various sensing and computer vision tasks. Existing polarization cameras use spatial or temporal multiplexing, which increases the camera volume, weight, cost, or all of the above. Recent lensless imaging approaches, such as DiffuserCam, have demonstrated that compact imaging systems can be realized by replacing the lens with a coding element and performing computational reconstruction. In this work, we propose a compact lensless polarization camera composed of a diffuser and a simple striped polarization mask. By combining this optical design with a reconstruction algorithm that explicitly models the polarization-encoded lensless measurements, four linear polarization images are recovered from a single snapshot. Our results demonstrate the potential of lensless approaches for polarization imaging and reveal the physical factors that govern reconstruction quality, guiding the development of high-quality practical systems. --- ### Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints Authors: Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray Published: 2026-03-17 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.17152v1 Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations. --- ### Shallow Representation of Option Implied Information Authors: Jimin Lin Published: 2026-03-17 Categories: q-fin.CP, stat.ML arXiv: https://arxiv.org/abs/2603.17151v1 Option prices encode the market's collective outlook through implied density and implied volatility. An explicit link between implied density and implied volatility translates the risk-neutrality of the former into conditions on the latter to rule out static arbitrage. Despite earlier recognition of their parity, the two had been studied in isolation for decades until the recent demand in implied volatility modeling rejuvenated such parity. This paper provides a systematic approach to build neural representations of option implied information. As a preliminary, we first revisit the explicit link between implied density and implied volatility through an alternative and minimalist lens, where implied volatility is viewed not as volatility but as a pointwise corrector mapping the Black-Scholes quasi-density into the implied risk-neutral density. Building on this perspective, we propose the neural representation that incorporates arbitrage constraints through the differentiable corrector. With an additive logistic model as the synthetic benchmark, extensive experiments reveal that deeper or wider network structures do not necessarily improve the model performance due to the nonlinearity of both arbitrage constraints and neural derivatives. By contrast, a shallow feedforward network with a single hidden layer and a specific activation effectively approximates implied density and implied volatility. --- ### Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents Authors: Shuvendu K. Lahiri Published: 2026-03-17 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2603.17150v1 Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise program behavior -- the \emph{intent gap} -- has always plagued software engineering, but AI-generated code amplifies it to an unprecedented scale. This article argues that \textbf{intent formalization} -- the translation of informal user intent into a set of checkable formal specifications -- is the key challenge that will determine whether AI makes software more reliable or merely more abundant. Intent formalization offers a tradeoff spectrum suitable to the reliability needs of different contexts: from lightweight tests that disambiguate likely misinterpretations, through full functional specifications for formal verification, to domain-specific languages from which correct code is synthesized automatically. The central bottleneck is \emph{validating specifications}: since there is no oracle for specification correctness other than the user, we need semi-automated metrics that can assess specification quality with or without code, through lightweight user interaction and proxy artifacts such as tests. We survey early research that demonstrates the \emph{potential} of this approach: interactive test-driven formalization that improves program correctness, AI-generated postconditions that catch real-world bugs missed by prior methods, and end-to-end verified pipelines that produce provably correct code from informal specifications. We outline the open research challenges -- scaling beyond benchmarks, achieving compositionality over changes, metrics for validating specifications, handling rich logics, designing human-AI specification interactions -- that define a research agenda spanning AI, programming languages, formal methods, and human-computer interaction. --- ### Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning Authors: Awatif Yasmin, Tarek Mahmud, Sana Alamgeer, Anne H. H. Ngu Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17148v1 Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback samples. This imbalance biases the model toward routine activities and weakens its sensitivity to true fall events. To address this challenge, we propose a personalization framework that combines semi-supervised clustering with contrastive learning to identify and balance the most informative user feedback samples. The framework is evaluated under three retraining strategies, including Training from Scratch (TFS), Transfer Learning (TL), and Few-Shot Learning (FSL), to assess adaptability across learning paradigms. Real-time experiments with ten participants show that the TFS approach achieves the highest performance, with up to a 25% improvement over the baseline, while FSL achieves the second-highest performance with a 7% improvement, demonstrating the effectiveness of selective personalization for real-world deployment. --- ### Multilingual Reference Need Assessment System for Wikipedia Authors: Aitolkyn Baigutanova, Francisco Navas, Pablo Aragon, Mykola Trokhymovych, Muniza Aslam, Ai-Jou Chou, Miriam Redi, Diego Saez-Trumper Published: 2026-03-17 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2603.17146v1 Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content needs to be verifiable, meaning that readers can check that claims are backed by references to reliable sources. This depends on manual verification by editors, an effective but labor-intensive process, especially given the high volume of daily edits. To address this challenge, we introduce a multilingual machine learning system to assist editors in identifying claims requiring citations. Our approach is tested in 10 language editions of Wikipedia, outperforming existing benchmarks for reference need assessment. We not only consider machine learning evaluation metrics but also system requirements, allowing us to explore the trade-offs between model accuracy and computational efficiency under real-world infrastructure constraints. We deploy our system in production and release data and code to support further research. --- ### REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge Authors: Yasi Zhang, Tianyu Chen, Mingyuan Zhou, Oscar Leong, Ying Nian Wu, Michal Lukasik Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17145v2 Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the ground truth is 5. Conversely, existing regression-aware approaches are often confined to Supervised Fine-Tuning (SFT), limiting their ability to explore optimal reasoning paths. To bridge this gap, we propose \textbf{REAL} (\underline{RE}gression-\underline{A}ware Reinforcement \underline{L}earning), a principled RL framework designed to optimize regression rewards, and also proven to be optimal for correlation metrics. A key technical challenge is that the regression objective is explicitly policy-dependent, thus invalidating standard policy gradient methods. To address this, we employ the generalized policy gradient estimator, which naturally decomposes optimization into two complementary components: (1) exploration over Chain-of-Thought (CoT) trajectory, and (2) regression-aware prediction refinement of the final score. Extensive experiments across model scales (8B to 32B) demonstrate that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods, exhibiting significantly better generalization on out-of-domain benchmarks. On Qwen3-32B specifically, we achieve gains of +8.40 Pearson and +7.20 Spearman correlation over the SFT baseline, and +18.30/+11.20 over the base model. These findings highlight the critical value of integrating regression objectives into RL exploration for accurate LLM evaluation. --- ### Contextual Preference Distribution Learning Authors: Benjamin Hudson, Laurent Charlin, Emma Frejinger Published: 2026-03-17 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.17139v1 Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and leverage them to solve downstream problems, for example risk-averse formulations. We focus on human choice settings that can be formulated as (integer) linear programs. In such settings, existing inverse optimization and choice modelling methods infer preferences from observed choices but typically produce point estimates or fail to capture contextual shifts, making them unsuitable for risk-averse decision-making. Using a bounded-variance score function gradient estimator, we train a predictive model mapping contextual features to a rich class of parameterizable distributions. This approach yields a maximum likelihood estimate. The model generates scenarios for unseen contexts in the subsequent optimization phase. In a synthetic ridesharing environment, our approach reduces average post-decision surprise by up to 114$\times$ compared to a risk-neutral approach with perfect predictions and up to 25$\times$ compared to leading risk-averse baselines. --- ### SMAL-pets: SMAL Based Avatars of Pets from Single Image Authors: Piotr Borycki, Joanna Waczyńska, Yizhe Zhu, Yongqiang Gao, Przemysław Spurek Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17131v1 Creating high-fidelity, animatable 3D dog avatars remains a formidable challenge in computer vision. Unlike human digital doubles, animal reconstruction faces a critical shortage of large-scale, annotated datasets for specialized applications. Furthermore, the immense morphological diversity across species, breeds, and crosses, which varies significantly in size, proportions, and features, complicates the generalization of existing models. Current reconstruction methods often struggle to capture realistic fur textures. Additionally, ensuring these avatars are fully editable and capable of performing complex, naturalistic movements typically necessitates labor-intensive manual mesh manipulation and expert rigging. This paper introduces SMAL-pets, a comprehensive framework that generates high-quality, editable animal avatars from a single input image. Our approach bridges the gap between reconstruction and generative modeling by leveraging a hybrid architecture. Our method integrates 3D Gaussian Splatting with the SMAL parametric model to provide a representation that is both visually high-fidelity and anatomically grounded. We introduce a multimodal editing suite that enables users to refine the avatar's appearance and execute complex animations through direct textual prompts. By allowing users to control both the aesthetic and behavioral aspects of the model via natural language, SMAL-pets provides a flexible, robust tool for animation and virtual reality. --- ### Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication Authors: Omar Erak, Omar Alhussein, Fang Fang, Sami Muhaidat Published: 2026-03-17 Categories: cs.LG, cs.IT, eess.IV arXiv: https://arxiv.org/abs/2603.17126v1 Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end training. Specifically, we enforce topological consistency by penalizing Wasserstein distances between cubical persistence diagrams of original and reconstructed images, and between Vietoris--Rips persistence of latent features before and after the channel to promote a robust latent manifold. TopoJSCC is based on end-to-end learning and requires no side information. Experiments show improved topology preservation and peak signal-to-noise ratio (PSNR) in low signal-to-noise ratio (SNR) and bandwidth-ratio regimes. --- ### Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework Authors: Taiwo Onitiju, Iman Vakilinia Published: 2026-03-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.17123v1 Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive comparative security assessment exists across major LLM architectures, leaving organizations unable to quantify risk or select appropriately secure LLMs for sensitive applications. This research addresses this gap by establishing a standardized vulnerability assessment framework and developing a multi-layered defensive system to protect against identified threats. We systematically evaluate five widely-deployed LLM families GPT-4, GPT-3.5 Turbo, Claude-3 Haiku, LLaMA-2-70B, and Gemini-2.5-pro against 10,000 adversarial prompts spanning six attack categories. Our assessment reveals critical security disparities, with vulnerability rates ranging from 11.9\% to 29.8\%, demonstrating that LLM capability does not correlate with security robustness. To mitigate these risks, we develop a production-ready defensive framework achieving 83\% average detection accuracy with only 5\% false positives. These results demonstrate that systematic security assessment combined with external defensive measures provides a viable path toward safer LLM deployment in production environments. --- ### MosaicMem: Hybrid Spatial Memory for Controllable Video World Models Authors: Wei Yu, Runjia Qian, Yumeng Li, Liquan Wang, Songheng Yin, Sri Siddarth Chakaravarthy P, Dennis Anthony, Yang Ye, Yidi Li, Weiwei Wan, Animesh Garg Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17117v1 Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses. We propose Mosaic Memory (MosaicMem), a hybrid spatial memory that lifts patches into 3D for reliable localization and targeted retrieval, while exploiting the model's native conditioning to preserve prompt-following generation. MosaicMem composes spatially aligned patches in the queried view via a patch-and-compose interface, preserving what should persist while allowing the model to inpaint what should evolve. With PRoPE camera conditioning and two new memory alignment methods, experiments show improved pose adherence compared to implicit memory and stronger dynamic modeling than explicit baselines. MosaicMem further enables minute-level navigation, memory-based scene editing, and autoregressive rollout. --- ### Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching Authors: Davide Di Gioia Published: 2026-03-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17112v2 Advanced AI reasoning systems route tasks through dynamic execution graphs of specialized agents. We identify a structural blind spot in this architecture: schedulers optimize load and fitness but lack a model of how failure propagates differently in tree-like versus cyclic graphs. In tree-like regimes, a single failure cascades exponentially; in dense cyclic regimes, it self-limits. A geometry-blind scheduler cannot distinguish these cases. We formalize this observability gap as an online geometry-control problem. We prove a cascade-sensitivity condition: failure spread is supercritical when per-edge propagation probability exceeds the inverse of the graph's branching factor (p > e^{-γ}, where γis the BFS shell-growth exponent). We close this gap with a spatio-temporal sidecar that predicts which routing geometry fits the current topology. The sidecar comprises (i) a Euclidean propagation scorer for dense, cyclic subgraphs, (ii) a hyperbolic scorer capturing exponential risk in tree-like subgraphs, and (iii) a compact learned gate (133 parameters) that blends the two scores using topology and geometry-aware features. On 250 benchmark scenarios spanning five topology regimes, the sidecar lifts the native scheduler's win rate from 50.4% to 87.2% (+36.8 pp). In tree-like regimes, gains reach +48 to +68 pp. The learned gate achieves held-out AUC = 0.9247, confirming geometry preference is recoverable from live signals. Cross-architecture validation on Barabasi-Albert, Watts-Strogatz, and Erdos-Renyi graphs confirms propagation modeling generalizes across graph families. --- ### Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles Authors: Zacharie Bugaud Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17111v1 Ensembling Vision-Language Models (VLMs) from different providers maximizes benchmark accuracy, yet models from the same architectural family share correlated errors that standard voting ignores. We study this structure across 17 VLMs from 8 families on VQAv2, TextVQA, and GQA. Family-correlated errors reduce effective ensemble dimensionality to 2.5-3.6 independent voters and create a Misleading tier (1.5-6.5% of questions) where correlated majority errors destroy accuracy to 0% despite the best model being correct. We propose three family-aware methods. Hierarchical Family Voting (HFV) aggregates within families before voting across them, recovering +18-26 pp on the Misleading tier. QualRCCV, a training-free method weighting models by calibration, family quality, and inverse family size, is the first to beat calibrated voting on all three benchmarks (p<0.05). Learned Candidate Scoring (LCS) trains a cross-validated classifier to re-rank candidate answers using support breadth, family diversity, and model quality, achieving the largest gains: +0.68% VQAv2, +0.61% TextVQA, +2.45% GQA -- all significant -- and is the only learned method that never degrades any benchmark. On VQAv2 test-standard (EvalAI), LCS reaches 87.83% with 12 models, confirming generalization. --- ### Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation Authors: Marceau Lafargue-Hauret, Raghav Mehta, Fabio De Sousa Ribeiro, Mélanie Roschewitz, Ben Glocker Published: 2026-03-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.17110v1 Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducing bias. Self-supervised learning, needing only images, has become key for pre-training. Recent work combining contrastive learning with counterfactual generation improves representation learning for classification but does not readily extend to pixel-level tasks. We propose a pipeline combining counterfactual generation with dense contrastive learning via Dual-View (DVD-CL) and Multi-View (MVD-CL) methods, along with supervised variants that utilize available silver-standard annotations. A new visualisation algorithm, the Color-coded High Resolution Overlay map (CHRO-map) is also introduced. Experiments show annotation-free DVD-CL outperforms other dense contrastive learning methods, while supervised variants using silver-standard labels outperform training on the silver-standard labeled data directly, achieving $\sim$94% DSC on challenging data. These results highlight that pixel-level contrastive learning, enhanced by counterfactuals and silver-standard annotations, improves robustness to acquisition and pathological variations. --- ### SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval Authors: Akshaj Murhekar, Christina Liu, Abhijit Mishra, Shounak Roychowdhury, Jacek Gwizdka Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17109v2 Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. Most existing Brain-Computer Interface (BCI) approaches rely on memory-intensive fine-tuning of Large Language Models (LLMs) or encoder-decoder models on raw EEG signals, resulting in expensive training pipelines, limited accessibility, and potential exposure of sensitive neural data. We introduce SENSE (SEmantic Neural Sparse Extraction), a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning. SENSE decouples decoding into two stages: on-device semantic retrieval and prompt-based language generation. EEG signals are locally mapped to a discrete textual space to extract a non-sensitive Bag-of-Words (BoW), which conditions an off-the-shelf LLM to synthesize fluent text in a zero-shot manner. The EEG-to-keyword module contains only ~6M parameters and runs fully on-device, ensuring raw neural signals remain local while only abstract semantic cues interact with language models. Evaluated on a 128-channel EEG dataset across six subjects, SENSE matches or surpasses the generative quality of fully fine-tuned baselines such as Thought2Text while substantially reducing computational overhead. By localizing neural decoding and sharing only derived textual cues, SENSE provides a scalable and privacy-aware retrieval-augmented architecture for next-generation BCIs. --- ### LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience Authors: Nafis Fuad, Xiaodong Qian Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17108v2 Urban flooding poses an escalating threat to transportation network continuity, yet no operational system currently provides real-time, street-level flood depth information at the centimeter resolution required for dynamic routing, electric vehicle (EV) safety, and autonomous vehicle (AV) operations. This study presents FloodLlama, a fine-tuned open-source vision-language model (VLM) for continuous flood depth estimation from single street-level images, supported by a multimodal sensing pipeline using TikTok data. A synthetic dataset of approximately 190000 images was generated, covering seven vehicle types, four weather conditions, and 41 depth levels (0-40 cm at 1 cm resolution). Progressive curriculum training enabled coarse-to-fine learning, while LLaMA 3.2-11B Vision was fine-tuned using QLoRA. Evaluation across 34797 trials reveals a depth-dependent prompt effect: simple prompts perform better for shallow flooding, whereas chain-of-thought (CoT) reasoning improves performance at greater depths. FloodLlama achieves a mean absolute error (MAE) below 0.97 cm and Acc@5cm above 93.7% for deep flooding, exceeding 96.8% for shallow depths. A five-phase mechanistic interpretability framework identifies layer L23 as the critical depth-encoding transition and enables selective fine-tuning that reduces trainable parameters by 76-80% while maintaining accuracy. The Tier 3 configuration achieves 98.62% accuracy on real-world data and shows strong robustness under visual occlusion. A TikTok-based data pipeline, validated on 676 annotated flood frames from Detroit, demonstrates the feasibility of real-time, crowd-sourced flood sensing. The proposed framework provides a scalable, infrastructure-free solution with direct implications for EV safety, AV deployment, and resilient transportation management. --- ### When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents Authors: Lu Yan, Xuan Chen, Xiangyu Zhang Published: 2026-03-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.17104v1 Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents. --- ### Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency Authors: Lucas Bandarkar, Alan Ansell, Trevor Cohn Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17102v1 Modern LLMs continue to exhibit significant variance in behavior across languages, such as being able to recall factual information in some languages but not others. While typically studied as a problem to be mitigated, in this work, we propose leveraging this cross-lingual inconsistency as a tool for interpretability in mixture-of-experts (MoE) LLMs. Our knowledge localization framework contrasts routing for sets of languages where the model correctly recalls information from languages where it fails. This allows us to isolate model components that play a functional role in answering about a piece of knowledge. Our method proceeds in two stages: (1) querying the model with difficult factual questions across a diverse set of languages to generate "success" and "failure" activation buckets and then (2) applying a statistical contrastive analysis to the MoE router logits to identify experts important for knowledge. To validate the necessity of this small number of experts for answering a knowledge question, we deactivate them and re-ask the question. We find that despite only deactivating about 20 out of 6000 experts, the model no longer answers correctly in over 40% of cases. Generally, this method provides a realistic and scalable knowledge localization approach to address increasingly complex LLMs. --- ### An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation Authors: Kushankur Ghosh, Mehar Klair, Kian Kyars, Euijin Choo, Jörg Sander Published: 2026-03-17 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.17100v1 Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as attacks. However, existing approaches rely on brittle, manually engineered rules to build provenance graphs, lack functional context for system entities, and provide limited support for analyst investigation. We present Auto-Prov, an adaptive, end-to-end framework that leverages large language models (LLMs) to automatically construct provenance graphs from heterogeneous and evolving logs, embed system-level functional attributes into the graph, enable provenance graph-based anomaly detectors to learn from these enriched graphs, and summarize the detected attacks to assist an analyst's investigation. Auto-Prov clusters unseen log types and efficiently extracts provenance edges and entity-level information via automatically generated rules. It further infers system-level functional context for both known and previously unseen system entities using a combination of LLM inference and behavior-based estimation. Attacks detected by provenance-graph-based anomaly detectors trained on Auto-Prov's graphs are then summarized into natural-language text. We evaluate Auto-Prov with four state-of-the-art provenance graph-based detectors across diverse logs. Results show that Auto-Prov consistently enhances detection performance, generalizes across heterogeneous log formats, and produces stable, interpretable attack summaries that remain robust under system evolution. --- ### Accurate Shift Invariant Convolutional Neural Networks Using Gaussian-Hermite Moments Authors: Jaspreet Singh, Petra Bosilj, Grzegorz Cielniak Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17098v1 The convolutional neural networks (CNNs) are not inherently shift invariant or equivariant. The downsampling operation, used in CNNs, is one of the key reasons which breaks the shift invariant property of a CNN. Conversely, downsampling operation is important to improve computational efficiency and increase the area of the receptive field for more contextual information. In this work, we propose Gaussian-Hermite Sampling (GHS), a novel downsampling strategy designed to achieve accurate shift invariance. GHS leverages Gaussian-Hermite polynomials to perform shift-consistent sampling, enabling CNN layers to maintain invariance to arbitrary spatial shifts prior to training. When integrated into standard CNN architectures, the proposed method embeds shift invariance directly at the layer level without requiring architectural modifications or additional training procedures. We evaluate the proposed approach on CIFAR-10, CIFAR-100, and MNIST-rot datasets. Experimental results demonstrate that GHS significantly improves shift consistency, achieving 100% classification consistency under spatial shifts, while also improving classification accuracy compared to baseline CNN models. --- ### Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction Authors: Ryo Kamoi, Ameya Godbole, Binglin Zhou, Xiaoxin Lu, Longqi Yang, Rui Zhang, Mengting Wan, Pei Zhou Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.17094v2 Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This paper reconsiders the evaluation of simulated conversations by explicitly recognizing that human conversations inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Since these behaviors contribute to the complexity of human social interaction, we argue that LLM-simulated conversations should reproduce them at frequencies comparable to those observed in human conversations. To support a detailed and interpretable evaluation of these behaviors, we introduce CoCoEval, a framework consisting of an evaluation scheme based on turn-level detection of 10 types of inconsistent and uncollaborative behaviors and a benchmark for simulating conversations in professional scenarios involving collaboration and conflict. Using CoCoEval, we compare human conversations with those simulated by GPT-4.1, GPT-5.1, and Claude Opus 4. The results show that (1) LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations under vanilla prompting, and (2) prompt engineering and supervised fine-tuning do not provide reliable control over these behaviors, often leading to the overproduction of specific behaviors. CoCoEval identifies gaps between human and LLM-simulated conversations that are not captured by conventional evaluation based on conversation-level Likert scales, raising concerns about the use of LLMs as proxies for human social interaction. --- ### Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction Authors: Ryo Kamoi, Ameya Godbole, Longqi Yang, Rui Zhang, Mengting Wan, Pei Zhou Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.17094v1 Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. However, simulating human conversations is challenging because they inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Analysis comparing inconsistent and uncollaborative behaviors in human- and LLM-generated conversations remains limited, although reproducing these behaviors is integral to simulating human-like and complex social interaction. In this work, we introduce CoCoEval, an evaluation framework that analyzes LLM-simulated conversations by detecting 10 types of inconsistent and uncollaborative behaviors at the turn level using an LLM-as-a-Judge. Using CoCoEval, we evaluate GPT-4.1, GPT-5.1, and Claude Opus 4 by comparing the frequencies of detected behaviors in conversations simulated by each model and in human conversations across academic, business, and governmental meetings, as well as debates. Our analysis shows that (1) under vanilla prompting, LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations; (2) prompt engineering does not provide reliable control over these behaviors, as our results show that different prompts lead to their under- or overproduction; and (3) supervised fine-tuning on human conversations can lead LLMs to overproduce a narrow set of behaviors, such as repetition. Our findings highlight the difficulty of simulating human conversations, raising concerns about the use of LLMs as a proxy for human social interaction. --- ### Ensemble Self-Training for Unsupervised Machine Translation Authors: Ido Aharon, Jonathan Shaki, Sarit Kraus Published: 2026-03-17 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.17087v1 We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but differ in an auxiliary language, inducing structured diversity across models. We then generate pseudo-translations for the primary pair using token-level ensemble decoding, averaging model predictions in both directions. These ensemble outputs are used as synthetic parallel data to further train each model, allowing the models to improve via shared supervision. At deployment time, we select a single model by validation performance, preserving single-model inference cost. Experiments show statistically significant improvements over single-model UNMT baselines, with mean gains of 1.7 chrF when translating from English and 0.67 chrF when translating into English. --- ### ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models Authors: M. Arda Aydın, Melih B. Yilmaz, Aykut Koç, Tolga Çukur Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17079v1 The success of CLIP-like vision-language models (VLMs) on natural images has inspired medical counterparts, yet existing approaches largely fall into two extremes: specialist models trained on single-domain data, which capture domain-specific details but generalize poorly, and generalist medical VLMs trained on multi-domain data, which retain broad semantics but dilute fine-grained diagnostic cues. Bridging this specialization-generalization trade-off remains challenging. To address this problem, we propose ACE-LoRA, a parameter-efficient adaptation framework for generalist medical VLMs that maintains robust zero-shot generalization. ACE-LoRA integrates Low-Rank Adaptation (LoRA) modules into frozen image-text encoders and introduces an Attention-based Context Enhancement Hypergraph Neural Network (ACE-HGNN) module that captures higher-order contextual interactions beyond pairwise similarity to enrich global representations with localized diagnostic cues, addressing a key limitation of prior Parameter-Efficient Fine-Tuning (PEFT) methods that overlook fine-grained details. To further enhance cross-modal alignment, we formulate a label-guided InfoNCE loss to effectively suppress false negatives between semantically related image-text pairs. Despite adding only 0.95M trainable parameters, ACE-LoRA consistently outperforms state-of-the-art medical VLMs and PEFT baselines across zero-shot classification, segmentation, and detection benchmarks spanning multiple domains. Our code is available at https://github.com/icon-lab/ACE-LoRA. --- ### CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning Authors: Weikun K. Zhang, Rohan Pandey, Bhaumik Mehta, Kaijie Jin, Naomi Morato, Archit Ganapule, Michael Ruofan Zeng, Jarod Alper Published: 2026-03-17 Categories: cs.LG, cs.AI, cs.CC arXiv: https://arxiv.org/abs/2603.17075v1 Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game, where an RL agent attempts to build the circuit within a fixed number of operations. We implement an AlphaZero-style training loop and compare two approaches: Proximal Policy Optimization with Monte Carlo Tree Search (PPO+MCTS) and Soft Actor-Critic (SAC). SAC achieves the highest success rates on two-variable targets, while PPO+MCTS scales to three variables and demonstrates steady improvement on harder instances. These results suggest that polynomial circuit synthesis is a compact, verifiable setting for studying self-improving search policies. --- ### PRISM: Demystifying Retention and Interaction in Mid-Training Authors: Bharat Runwal, Ashish Agrawal, Anurag Roy, Rameswar Panda Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17074v3 We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and attention-Mamba hybrid), and scales from 3B to 24B parameters, we show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance. The full PRISM to RL pipeline improves macro-average across six reasoning benchmarks from under 12 to 29-42 (a 3-4x improvement), whereas RL applied directly to most of the base models remains substantially less effective, with AIME scores near zero. Data composition matters most at mid-training, not RL: including science data during mid-training unlocks +17 to +28 point GPQA-Diamond gains during RL, while changing the RL mix produces less than 2 point differences. Mechanistically, mid-training densely restructures over 90% of model weights, while RL makes sparse, front-loaded refinements to approximately 5% of parameters. Representation analysis (CKA) confirms that RL consistently preserves mid-training's representational geometry (over 0.998 CKA) across architectures. Crucially, RL applies identical weight changes regardless of starting point, yet only succeeds on mid-trained models, consistent with mid-training placing the model in a configuration from which RL can effectively improve performance. Our results demonstrate that retention-aware mid-training is highly effective for reliable reasoning enhancement and provide practical guidance for designing robust mid-training pipelines. --- ### Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts Authors: Lucas Bandarkar, Alan Ansell, Trevor Cohn Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17070v2 In this work, we analyze shortcomings in cross-lingual knowledge transfer in large, modern reasoning LLMs. We demonstrate that the perceived gap in knowledge transfer is primarily a script barrier. First, we conduct an observational data analysis on the performance of thinking models on two datasets with local knowledge from around the world, ECLeKTic and MultiLoKo. Our regression analysis shows that script match - not language or family - is the primary predictor of knowledge transfer failure once model capability and question difficulty are accounted for. We further this finding by providing the LLMs with the key entities of the questions in their source language and find that this disproportionately improves cross-script questions. We then posit that these LLMs could be reasoning better at test-time. To evaluate this, we develop a synthetic generation pipeline to design SFT samples to encourage the model to better reason about transliteration ambiguities when trying to fetch parametric knowledge at inference-time. We show that teaching two models to reason better reduces the cross-script transfer gap. As a result, we conclude that there is potential to improve cross-lingual parametric knowledge transfer during post-training. --- ### Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts Authors: Lucas Bandarkar, Alan Ansell, Trevor Cohn Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17070v1 In this work, we analyze shortcomings in cross-lingual knowledge transfer in large, modern reasoning LLMs. We demonstrate that the perceived gap in knowledge transfer is primarily a script barrier. First, we conduct an observational data analysis on the performance of thinking models on two datasets with local knowledge from around the world, ECLeKTic and MultiLoKo. Our regression analysis shows that script match - not language or family - is the primary predictor of knowledge transfer failure once model capability and question difficulty are accounted for. We further this finding by providing the LLMs with the key entities of the questions in their source language and find that this disproportionately improves cross-script questions. We then posit that these LLMs could be reasoning better at test-time. To evaluate this, we develop a synthetic generation pipeline to design SFT samples to encourage the model to better reason about transliteration ambiguities when trying to fetch parametric knowledge at inference-time. We show that teaching two models to reason better reduces the cross-script transfer gap. As a result, we conclude that there is potential to improve cross-lingual parametric knowledge transfer during post-training. --- ### Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection Authors: Haitian Wang, Yiren Wang, Xinyu Wang, Sheldon Fung, Atif Mansoor Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17069v2 Falls in wet bathroom environments are a major safety risk for seniors living alone. Recent work has shown that mmWave-only, vibration-only, and existing multimodal schemes, such as vibration-triggered radar activation, early feature concatenation, and decision-level score fusion, can support privacy-preserving, non-intrusive fall detection. However, these designs still treat motion and impact as loosely coupled streams, depending on coarse temporal alignment and amplitude thresholds, and do not explicitly encode the causal link between radar-observed collapse and floor impact or address timing drift, object drop confounders, and latency and energy constraints on low-power edge devices. To this end, we propose a two-stream architecture that encodes radar signals with a Motion--Mamba branch for long-range motion patterns and processes floor vibration with an Impact--Griffin branch that emphasizes impact transients and cross-axis coupling. Cross-conditioned fusion uses low-rank bilinear interaction and a Switch--MoE head to align motion and impact tokens and suppress object-drop confounders. The model keeps inference cost suitable for real-time execution on a Raspberry Pi 4B gateway. We construct a bathroom fall detection benchmark dataset with frame-level annotations, comprising more than 3~h of synchronized mmWave radar and triaxial vibration recordings across eight scenarios under running water, together with subject-independent training, validation, and test splits. On the test split, our model attains 96.1% accuracy, 94.8% precision, 88.0% recall, a 91.1% macro F1 score, and an AUC of 0.968. Compared with the strongest baseline, it improves accuracy by 2.0 percentage points and fall recall by 1.3 percentage points, while reducing latency from 35.9 ms to 15.8 ms and lowering energy per 2.56 s window from 14200 mJ to 10750 mJ on the Raspberry Pi 4B gateway. --- ### TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects Authors: Yeheng Zong, Yizhou Chen, Alexander Bowler, Chia-Tung Yang, Ram Vasudevan Published: 2026-03-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.17068v2 Structured 3D representations such as keypoints and meshes offer compact, expressive descriptions of deformable objects, jointly capturing geometric and topological information useful for downstream tasks such as dynamics modeling and motion planning. However, robustly extracting such representations remains challenging, as current perception methods struggle to handle complex deformations. Moreover, large-scale 3D data collection remains a bottleneck: existing approaches either require prohibitive data collection efforts, such as labor-intensive annotation or expensive motion capture setups, or rely on simplifying assumptions that break down in unstructured environments. As a result, large-scale 3D datasets and benchmarks for deformable objects remain scarce. To address these challenges, this paper presents an affordable and autonomous framework for collecting 3D datasets of deformable objects using only RGB-D cameras. The proposed method identifies 3D keypoints and robustly tracks their trajectories, incorporating motion consistency constraints to produce temporally smooth and geometrically coherent data. TrackDeform3D is evaluated against several state-of-the-art tracking methods across diverse object categories and demonstrates consistent improvements in both geometric and tracking accuracy. Using this framework, this paper presents a high-quality, large-scale dataset consisting of 6 deformable objects, totaling 110 minutes of trajectory data. Project page: https://roahmlab.github.io/trackDeform3D-core-tracking/ --- ### Evaluating Ill-Defined Tasks in Large Language Models Authors: Yi Zhou, Basel Shbita Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17067v1 Many evaluations of Large Language Models (LLMs) target tasks that are inherently ill-defined, with unclear input and output spaces and ambiguous success criteria. We analyze why existing evaluation benchmarks and metrics fail to provide reliable or diagnostic signals of model capability for such tasks. We examine two case studies: Complex Instruction Following (CIF), where we identify recurring issues including limited coverage of real-world instruction complexity, sensitivity to instruction phrasing, inconsistent and non-comparable metrics, and instability introduced by LLM-based judges; and Natural Language to Mermaid Sequence Diagrams (NL2Mermaid), where we show how multi-faceted evaluation criteria can yield actionable insights beyond aggregate scores. Together, these case studies show that current evaluations frequently conflate distinct failure modes, yielding scores that are unstable, non-diagnostic, and difficult to act upon. Our findings expose fundamental limitations in existing evaluation practices for ill-defined tasks and motivate more robust, interpretable evaluation designs. --- ### Transformers are Bayesian Networks Authors: Gregory Coppola Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17063v1 Transformers are the dominant architecture in AI, yet why they work remains poorly understood. This paper offers a precise answer: a transformer is a Bayesian network. We establish this in five ways. First, we prove that every sigmoid transformer with any weights implements weighted loopy belief propagation on its implicit factor graph. One layer is one round of BP. This holds for any weights -- trained, random, or constructed. Formally verified against standard mathematical axioms. Second, we give a constructive proof that a transformer can implement exact belief propagation on any declared knowledge base. On knowledge bases without circular dependencies this yields provably correct probability estimates at every node. Formally verified against standard mathematical axioms. Third, we prove uniqueness: a sigmoid transformer that produces exact posteriors necessarily has BP weights. There is no other path through the sigmoid architecture to exact posteriors. Formally verified against standard mathematical axioms. Fourth, we delineate the AND/OR boolean structure of the transformer layer: attention is AND, the FFN is OR, and their strict alternation is Pearl's gather/update algorithm exactly. Fifth, we confirm all formal results experimentally, corroborating the Bayesian network characterization in practice. We also establish the practical viability of loopy belief propagation despite the current lack of a theoretical convergence guarantee. We further prove that verifiable inference requires a finite concept space. Any finite verification procedure can distinguish at most finitely many concepts. Without grounding, correctness is not defined. Hallucination is not a bug that scaling can fix. It is the structural consequence of operating without concepts. Formally verified against standard mathematical axioms. --- ### Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization Authors: Isaac Robledo, Alberto Vilariño, Arnau Miró, Oriol Lehmkuhl, Carlos Sanmiguel Vila, Rodrigo Castellanos Published: 2026-03-17 Categories: physics.flu-dyn, cs.LG, cs.NE, math.OC arXiv: https://arxiv.org/abs/2603.17057v2 Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-consistent aerodynamic metrics. The framework couples a low-fidelity-informed Gaussian process regression transfer model with uncertainty-triggered sampling and a synchronized elitism rule embedded in a hybrid genetic algorithm. Low-fidelity XFOIL evaluations provide inexpensive features, while sparse RANS simulations are adaptively allocated when predictive uncertainty exceeds a threshold; elite candidates are mandatorily validated at high fidelity, and the population is re-evaluated to prevent evolutionary selection based on outdated fitness values produced by earlier surrogate states. The method is demonstrated for a two-point problem at $Re=6\times10^6$ with cruise at $α=2^\circ$ (maximize $E=L/D$) and take-off at $α=10^\circ$ (maximize $C_L$) using a 12-parameter CST representation. Independent multi-fidelity surrogates per flight condition enable decoupled refinement. The optimized design improves cruise efficiency by 41.05% and take-off lift by 20.75% relative to the best first-generation individual. Over the full campaign, RANS evaluations were required for only 14.78% and 9.5% of the condition-specific candidate evaluations at cruise and take-off, respectively. These percentages quantify the reduction in high-fidelity usage relative to the fixed automated RANS workflow adopted as the high-fidelity reference in this study. --- ### DesertFormer: Transformer-Based Semantic Segmentation for Off-Road Desert Terrain Classification in Autonomous Navigation Systems Authors: Yasaswini Chebolu Published: 2026-03-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.17056v1 Reliable terrain perception is a fundamental requirement for autonomous navigation in unstructured, off-road environments. Desert landscapes present unique challenges due to low chromatic contrast between terrain categories, extreme lighting variability, and sparse vegetation that defy the assumptions of standard road-scene segmentation models. We present DesertFormer, a semantic segmentation pipeline for off-road desert terrain analysis based on SegFormer B2 with a hierarchical Mix Transformer (MiT-B2) backbone. The system classifies terrain into ten ecologically meaningful categories -- Trees, Lush Bushes, Dry Grass, Dry Bushes, Ground Clutter, Flowers, Logs, Rocks, Landscape, and Sky -- enabling safety-aware path planning for ground robots and autonomous vehicles. Trained on a purpose-built dataset of 4,176 annotated off-road images at 512x512 resolution, DesertFormer achieves a mean Intersection-over-Union (mIoU) of 64.4% and pixel accuracy of 86.1%, representing a +24.2% absolute improvement over a DeepLabV3 MobileNetV2 baseline (41.0% mIoU). We further contribute a systematic failure analysis identifying the primary confusion patterns -- Ground Clutter to Landscape and Dry Grass to Landscape -- and propose class-weighted training and copy-paste augmentation for rare terrain categories. Code, checkpoints, and an interactive inference dashboard are released at https://github.com/Yasaswini-ch/Vision-based-Desert-Terrain-Segmentation-using-SegFormer. --- ### PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning Authors: Yijian Wang, Qingsen Yan, Jiantao Zhou, Duwei Dai, Wei Dong Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17055v1 Image Restoration (IR) agents, leveraging multimodal large language models to perceive degradation and invoke restoration tools, have shown promise in automating IR tasks. However, existing IR agents typically lack an insight summarization mechanism for past interactions, which results in an exhaustive search for the optimal IR tool. To address this limitation, we propose a portrait-aware IR agent, dubbed PaAgent, which incorporates a self-evolving portrait bank for IR tools and Retrieval-Augmented Generation (RAG) to select a suitable IR tool for input. Specifically, to construct and evolve the portrait bank, the PaAgent continuously enriches it by summarizing the characteristics of various IR tools with restored images, selected IR tools, and degraded images. In addition, the RAG is employed to select the optimal IR tool for the input image by retrieving relevant insights from the portrait bank. Furthermore, to enhance PaAgent's ability to perceive degradation in complex scenes, we propose a subjective-objective reinforcement learning strategy that considers both image quality scores and semantic insights in reward generation, which accurately provides the degradation information even under partial and non-uniform degradation. Extensive experiments across 8 IR benchmarks, covering six single-degradation and eight mixed-degradation scenarios, validate PaAgent's superiority in addressing complex IR tasks. Our project page is \href{https://wyjgr.github.io/PaAgent.html}{PaAgent}. --- ### Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization Authors: Wenhao Zhao, Qiran Zou, Rushi Shah, Yudi Wu, Zhouhan Lin, Dianbo Liu Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17052v1 Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and other generative models. Despite its prevalence, the characteristics and behaviors of vector quantization in generative models remain largely underexplored. In this study, we systematically investigate the issue of collapses in vector quantization, where collapsed representations are observed across discrete codebook tokens and continuous latent embeddings. By leveraging both synthetic and real datasets, we identify the severity of each type of collapses and triggering conditions. Our analysis reveals that random initialization and limited encoder capacity result in tokens collapse and embeddings collapse. Building on these findings, we propose potential solutions aimed at mitigating each collapse. To the best of our knowledge, this is the first comprehensive study examining representation collapsing problems in vector quantization. --- ### Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Authors: Songchun Zhang, Zeyue Xue, Siming Fu, Jie Huang, Xianghao Kong, Y Ma, Haoyang Huang, Nan Duan, Anyi Rao Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17051v1 Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution. --- ### Attractor-Keyed Memory Authors: Natalia G. Berloff Published: 2026-03-17 Categories: physics.optics, cond-mat.dis-nn, cs.ET, cs.IT, cs.NE arXiv: https://arxiv.org/abs/2603.17049v2 Physical selectors (lasers choosing a mode, Ising machines settling on a ground state, condensates occupying a spin state) produce high-dimensional signatures at the moment of decision: full field amplitudes, multimode interference patterns, or scattering responses. These signatures are richer than the winner's index, yet they are routinely discarded. We show that when the signatures are repeatable across trials (stereotyped) and linearly independent across routes, a single linear decoder compiled from calibration data maps them to arbitrary payloads, merging selection and memory access into one event and eliminating the fetch that dominates latency and energy in sparse routing architectures. The construction requires one SVD of measured device responses, which certifies capability and bounds worst-case error for any downstream payload before the task is chosen. Runtime error separates into two independently diagnosable channels, decoding fidelity (controlled by dictionary conditioning $σ_{\min}(Φ)$) and routing reliability (controlled by the margin-to-noise ratio $Δ/T_{\mathrm{eff}}$), each with a distinct physical origin and targeted remedy. We derive the full error decomposition, give Ising-machine selector constructions, and validate the predicted scalings on synthetic speckle-signature simulations across three measurement modalities. No hardware demonstration exists; we provide a falsifiable four-step experimental protocol specifying what a first experiment must measure. Whether real device signatures satisfy stereotypy is the central open question. --- ### SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models Authors: Ahmed Zeid, Sidney Bender Published: 2026-03-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.17048v1 Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictions by identifying minimal input changes that alter model outputs. However, existing CFE methods often rely on dataset-specific generative models and incur substantial computational cost, limiting their scalability to high-resolution data. We propose SCE-LITE-HQ, a scalable framework for counterfactual generation that leverages pretrained generative foundation models without task-specific retraining. The method operates in the latent space of the generator, incorporates smoothed gradients to improve optimization stability, and applies mask-based diversification to promote realistic and structurally diverse counterfactuals. We evaluate SCE-LITE-HQ on natural and medical datasets using a desiderata-driven evaluation protocol. Results show that SCE-LITE-HQ produces valid, realistic, and diverse counterfactuals competitive with or outperforming existing baselines, while avoiding the overhead of training dedicated generative models. --- ### Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models Authors: Abinav Rao, Sujan Rachuri Published: 2026-03-17 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.17044v2 Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B and 7B parameters under seven training strategies and two post-hoc methods. The central finding is negative: generation quality resists DPO alignment across all tested conditions on this architecture. No method improves generation CLIPScore at 7B (|Delta| < 0.2, p > 0.5 at n=200 per seed, 3 seeds); at 1B, all methods degrade generation, and the result holds across preference data types (real-vs-generated and model-vs-model) and the data volumes tested (150-288 pairs). Gradient analysis reveals why: understanding and generation gradients are near-orthogonal (cos ~ 0) with ~11-14x magnitude imbalance driven by VQ token count asymmetry (576 generation tokens vs. ~30-100 text tokens). This imbalance is the dominant interference mechanism in multi-task DPO; magnitude-balancing yields directionally positive understanding deltas (+0.01-0.04 VQA, though individually not significant), but the generation gap persists regardless. We identify discrete VQ tokenization as a likely structural bottleneck -- supported by the generation DPO loss converging to ln(2) -- and provide practical guidance for practitioners working with VQ-based unified models. --- ### OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials Authors: Sankalp Pandey, Thanh-Dat Truong, Xuan-Bac Nguyen, Hoang-Quan Nguyen, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17043v2 Physics-aware multimodal large language models (MLLMs) can localize and characterize two-dimensional (2D) material flakes from optical microscopy images, producing rich candidate observations and scientific reasoning. However, downstream workflows also require reliable operations over these outputs, including counting, selection, measurement, and rendering. We present OpenQlaw, a tool-using agentic artificial intelligence (AI) system that connects a general vision-language orchestrator with Physics-Aware Instruction Tuning (QuPAINT), a physics-aware domain expert. Through evaluation on fully reviewed optical microscopy images, we show that summary counts derived from longer free-form candidate enumerations can become inconsistent with the underlying returned observations. Controlled replay experiments further show that structuring the same observations alone does not resolve this behavior, while deterministic delegation returns the exact requested record count in all cohort trials. To address this, we introduce \textbf{State-Grounded OpenQlaw}, which converts expert outputs into image-scoped observation records and performs deterministic scientific operations over explicitly identified records with refusal conditions when required information is unavailable. This preserves the expert's original analysis while making downstream operations exact over the selected record and independently evaluable from candidate-list discrepancies. --- ### OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials Authors: Sankalp Pandey, Xuan-Bac Nguyen, Hoang-Quan Nguyen, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17043v1 The transition from optical identification of 2D quantum materials to practical device fabrication requires dynamic reasoning beyond the detection accuracy. While recent domain-specific Multimodal Large Language Models (MLLMs) successfully ground visual features using physics-informed reasoning, their outputs are optimized for step-by-step cognitive transparency. This yields verbose candidate enumerations followed by dense reasoning that, while accurate, may induce cognitive overload and lack immediate utility for real-world interaction with researchers. To address this challenge, we introduce OpenQlaw, an agentic orchestration system for analyzing 2D materials. The architecture is built upon NanoBot, a lightweight agentic framework inspired by OpenClaw, and QuPAINT, one of the first Physics-Aware Instruction Multi-modal platforms for Quantum Material Discovery. This allows accessibility to the lab floor via a variety of messaging channels. OpenQlaw allows the core Large Language Model (LLM) agent to orchestrate a domain-expert MLLM,with QuPAINT, as a specialized node, successfully decoupling visual identification from reasoning and deterministic image rendering. By parsing spatial data from the expert, the agent can dynamically process user queries, such as performing scale-aware physical computation or generating isolated visual annotations, and answer in a naturalistic manner. Crucially, the system features a persistent memory that enables the agent to save physical scale ratios (e.g., 1 pixel = 0.25 μm) for area computations and store sample preparation methods for efficacy comparison. The application of an agentic architecture, together with the extension that uses the core agent as an orchestrator for domain-specific experts, transforms isolated inferences into a context-aware assistant capable of accelerating high-throughput device fabrication. --- ### When Marginals Match but Structure Fails: Covariance Fidelity in Generative Models Authors: Nazia Riasat Published: 2026-03-17 Categories: stat.ML, cs.AI, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.17041v2 Generative models are increasingly deployed as substitutes for real data in downstream scientific workflows, yet standard evaluation criteria remain focused on marginal distribution matching. We argue that this represents a fundamental gap: downstream inference is rarely a marginal operation, and a model that passes every univariate diagnostic can still produce structurally unreliable synthetic data. We introduce covariance-level dependence fidelity, measured by D_Sigma(P,Q) = ||Sigma_P - Sigma_Q||_F, as a principled, computable criterion for evaluating whether a generative model preserves the joint structure of data beyond its univariate marginals. Three results formalise this criterion. First, marginal fidelity provides no constraint on dependence structure: D_Sigma can be made arbitrarily large while all univariate marginals match exactly. Second, covariance divergence induces quantifiable downstream instability, including sign reversals in population regression coefficients. Third, bounding D_Sigma provides positive stability guarantees for dependence-sensitive procedures such as PCA via Davis-Kahan-type bounds. Empirical validation across three domains, image data (Fashion-MNIST VAE, n = 60,000), bulk RNA-seq (TCGA-BRCA, n = 1,111), and a small-sample stress test (Alzheimer's gene expression, n = 113), shows that D_Sigma/delta consistently distinguishes structure-discarding from structure-preserving generators in cases where standard marginal diagnostics show little separation, confirming that covariance-level fidelity provides information orthogonal to existing evaluation metrics across domains and sample sizes. --- ### Shared Representation Learning for Reference-Guided Targeted Sound Detection Authors: Shubham Gupta, Adarsh Arigala, B. R. Dilleswari, Sri Rama Murty Kodukula Published: 2026-03-17 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2603.17025v1 Human listeners exhibit the remarkable ability to segregate a desired sound from complex acoustic scenes through selective auditory attention, motivating the study of Targeted Sound Detection (TSD). The task requires detecting and localizing a target sound in a mixture when a reference audio of that sound is provided. Prior approaches, rely on generating a sound-discriminative conditional embedding vector for the reference and pairing it with a mixture encoder, jointly optimized with a multi-task learning approach. In this work, we propose a unified encoder architecture that processes both the reference and mixture audio within a shared representation space, promoting stronger alignment while reducing architectural complexity. This design choice not only simplifies the overall framework but also enhances generalization to unseen classes. Following the multi-task training paradigm, our method achieves substantial improvements over prior approaches, surpassing existing methods and establishing a new state-of-the-art benchmark for targeted sound detection, with a segment-level F1 score of 83.15% and an overall accuracy of 95.17% on the URBAN-SED dataset. --- ### HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning Authors: Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin Published: 2026-03-17 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.17024v2 Vision-language models (VLMs) show strong multimodal capabilities but still struggle with fine-grained vision-language reasoning. We find that long chain-of-thought (CoT) reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for reinforcement learning with verifiable rewards (RLVR) does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B under two RLVR settings: the original data alone, and the original data plus HopChain's multi-hop data, and compare them across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized for any specific benchmark, it improves 20 of 24 benchmarks on both models, indicating broad and generalizable gains. Consistently, replacing full chained queries with half-multi-hop or single-hop variants reduces the average score across five representative benchmarks from 70.4 to 66.7 and 64.3, respectively. Notably, multi-hop gains peak in long-CoT vision-language reasoning, exceeding 50 points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning. --- ### Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty Authors: Zhihao Pei, Nir Lipovetzky, Angela M. Rojas-Arevalo, Fjalar J. de Haan, Enayat A. Moallemi Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17021v2 Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model-based planning approaches, this problem conceptualization process often relies on participatory modeling to translate stakeholders' natural-language descriptions into a quantitative model, making this process complex and time-consuming. To facilitate this process, we propose a templated workflow that uses large language models for an initial conceptualization process. During the workflow, researchers can use large language models to identify the essential model components from stakeholders' intuitive problem descriptions, explore their diverse perspectives approaching the problem, assemble these components into a unified model, and eventually implement the model in Python through iterative communication. These results will facilitate the subsequent socio-environmental planning under deep uncertainty steps. Using ChatGPT 5.2 Instant, we demonstrated this workflow on the lake problem and an electricity market problem, both of which demonstrate socio-environmental planning problems. In both cases, acceptable outputs were obtained after a few iterations with human verification and refinement. These experiments indicated that large language models can serve as an effective tool for facilitating participatory modeling in the problem conceptualization process in socio-environmental planning. ---