# Research Papers — 2026-03 · bundle page 213 of 243

> Full-text markdown of papers #10601–10650 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/213
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/212.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/214.md)

### Weather-Related Crash Risk Forecasting: A Deep Learning Approach for Heterogenous Spatiotemporal Data

Authors: Abimbola Ogungbire, Srinivas Pulugurtha
Published: 2026-03-04
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2603.04551v1

This study introduces a deep learning-based framework for forecasting weather-related traffic crash risk using heterogeneous spatiotemporal data. Given the complex, non-linear relationship between crash occurrence and factors such as road characteristics, and traffic conditions, we propose an ensemble of Convolutional Long Short-Term Memory (ConvLSTM) models trained over overlapping spatial grids. This approach captures both spatial dependencies and temporal dynamics while addressing spatial heterogeneity in crash patterns. North Carolina was selected as the study area due to its diverse weather conditions, with historical crash, weather, and traffic data aggregated at 5-mi by 5-mi grid resolution. The framework was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and spatial cross-K analysis. Results show that the ensembled ConvLSTM significantly outperforms baseline models, including linear regression, ARIMA, and standard ConvLSTM, particularly in high-risk zones. The ensemble approach effectively combines the strengths of multiple ConvLSTM models, resulting in lower MSE and RMSE values across all regions, particularly when data from different crash risk zones are aggregated. Notably, the model performs exceptionally well in volatile high-risk areas (Cluster 1), achieving the lowest MSE and RMSE, while in stable low-risk areas (Cluster 2), it still improves upon simpler models but with slightly higher errors due to challenges in capturing subtle variations.

---

### Adaptive Memory Admission Control for LLM Agents

Authors: Guilin Zhang, Wei Jiang, Xiejiashan Wang, Aisha Behr, Kai Zhao, Jeffrey Friedman, Xu Chu, Amine Anoun
Published: 2026-03-04
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2603.04549v1

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversational content, including hallucinated or obsolete facts, or depend on opaque, fully LLM-driven memory policies that are costly and difficult to audit. As a result, memory admission remains a poorly specified and weakly controlled component in agent architectures. To address this gap, we propose Adaptive Memory Admission Control (A-MAC), a framework that treats memory admission as a structured decision problem. A-MAC decomposes memory value into five complementary and interpretable factors: future utility, factual confidence, semantic novelty, temporal recency, and content type prior. The framework combines lightweight rule-based feature extraction with a single LLM-assisted utility assessment, and learns domain-adaptive admission policies through cross-validated optimization. This design enables transparent and efficient control over long-term memory. Experiments on the LoCoMo benchmark show that A-MAC achieves a superior precision-recall tradeoff, improving F1 to 0.583 while reducing latency by 31% compared to state-of-the-art LLM-native memory systems. Ablation results identify content type prior as the most influential factor for reliable memory admission. These findings demonstrate that explicit and interpretable admission control is a critical design principle for scalable and reliable memory in LLM-based agents.

---

### Oracle-efficient Hybrid Learning with Constrained Adversaries

Authors: Princewill Okoroafor, Robert Kleinberg, Michael P. Kim
Published: 2026-03-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.04546v1

The Hybrid Online Learning Problem, where features are drawn i.i.d. from an unknown distribution but labels are generated adversarially, is a well-motivated setting positioned between statistical and fully-adversarial online learning. Prior work has presented a dichotomy: algorithms that are statistically-optimal, but computationally intractable (Wu et al., 2023), and algorithms that are computationally-efficient (given an ERM oracle), but statistically-suboptimal (Wu et al., 2024). This paper takes a significant step towards achieving statistical optimality and computational efficiency simultaneously in the Hybrid Learning setting. To do so, we consider a structured setting, where the Adversary is constrained to pick labels from an expressive, but fixed, class of functions $R$. Our main result is a new learning algorithm, which runs efficiently given an ERM oracle and obtains regret scaling with the Rademacher complexity of a class derived from the Learner's hypothesis class $H$ and the Adversary's label class $R$. As a key corollary, we give an oracle-efficient algorithm for computing equilibria in stochastic zero-sum games when action sets may be high-dimensional but the payoff function exhibits a type of low-dimensional structure. Technically, we develop a number of tools for the design and analysis of our learning algorithm, including a novel Frank-Wolfe reduction with "truncated entropy regularizer" and a new tail bound for sums of "hybrid" martingale difference sequences.

---

### An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

Authors: Waleed Afandi, Hussein Abdallah, Ashraf Aboulnaga, Essam Mansour
Published: 2026-03-04
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2603.04545v2

Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference queries are computationally expensive and vary in complexity, as each involves a different number of target nodes linked to subgraphs of diverse densities and structures. Existing acceleration methods, such as pruning, quantization, and knowledge distillation, instantiate smaller models but do not adapt them to the structure or semantics of individual queries. They also store models as monolithic files that must be fully loaded, and miss the opportunity to retrieve only the neighboring nodes and corresponding model components that are semantically relevant to the target nodes. These limitations lead to excessive data loading and redundant computation on large KGs. This paper presents KG-WISE, a task-driven inference paradigm for large KGs. KG-WISE decomposes trained GNN models into fine-grained components that can be partially loaded based on the structure of the queried subgraph. It employs large language models (LLMs) to generate reusable query templates that extract semantically relevant subgraphs for each task, enabling query-aware and compact model instantiation. We evaluate KG-WISE on six large KGs with up to 42 million nodes and 166 million edges. KG-WISE achieves up to 28x faster inference and 98% lower memory usage than state-of-the-art systems while maintaining or improving accuracy across both commercial and open-weight LLMs.

---

### InverseNet: Benchmarking Operator Mismatch and Calibration Across Compressive Imaging Modalities

Authors: Chengshuai Yang, Xin Yuan
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04538v1

State-of-the-art EfficientSCI loses 20.58 dB when its assumed forward operator deviates from physical reality in just eight parameters, yet no existing benchmark quantifies operator mismatch, the default condition in deployed compressive imaging systems. We introduce InverseNet, the first cross-modality benchmark for operator mismatch, spanning CASSI, CACTI, and single-pixel cameras. Evaluating 12 methods under a four-scenario protocol (ideal, mismatched, oracle-corrected, blind calibration) across 27 simulated scenes and 9 real hardware captures, we find: (1) deep learning methods lose 10-21 dB under mismatch, eliminating their advantage over classical baselines; (2) performance and robustness are inversely correlated across modalities (Spearman r_s = -0.71, p < 0.01); (3) mask-oblivious architectures recover 0% of mismatch losses regardless of calibration quality, while operator-conditioned methods recover 41-90%; (4) blind grid-search calibration recovers 85-100% of the oracle bound without ground truth. Real hardware experiments confirm that simulation trends transfer to physical data. Code will be released upon acceptance.

---

### How Professional Visual Artists are Negotiating Generative AI in the Workplace

Authors: Harry H. Jiang, Jordan Taylor, William Agnew
Published: 2026-03-04
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.04537v2

Generative AI has been heavily critiqued by artists in both popular media and HCI scholarship. However, more work is needed to understand the impacts of generative AI on professional artists' workplaces and careers. In this paper, we conduct a survey of 378 verified professional visual artists about how generative AI has impacted their careers and workplaces. We find (1) most visual artists are strongly opposed to using generative AI (text or visual) and negotiate their inclusion in the workplace through a variety of refusal strategies (2) there exist a range of factors in artists environments shaping their use of generative AI, including pressure from clients, bosses, and peers and (3) visual artists report overwhelmingly negative impacts of generative AI on their workplaces, leading to added stress and reduced job opportunities. In light of these findings, we encourage HCI researchers to contend more deeply with artists' desires not to use generative AI in the workplace.

---

### A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing

Authors: Hadi Sotoudeh, Pablo Lemos, Laurence Perreault-Levasseur
Published: 2026-03-04
Categories: astro-ph.IM, astro-ph.CO, cs.LG
arXiv: https://arxiv.org/abs/2603.04535v1

We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based inference methods are increasingly needed to extract scientific insights. While diffusion-based approaches offer high-quality generative capabilities, they are hindered by slow sampling speeds. Our method performs posterior sampling an order of magnitude faster than a diffusion baseline. Applied to the problem of CMB delensing, it successfully recovers the unlensed CMB power spectrum from simulated observations. The model also remains robust to shifts in cosmological parameters, demonstrating its potential for out-of-distribution generalization and application to observational cosmological data.

---

### Invariant Causal Routing for Governing Social Norms in Online Market Economies

Authors: Xiangning Yu, Qirui Mi, Xiao Xue, Haoxuan Li, Yiwei Shi, Xiaowei Liu, Mengyue Yang
Published: 2026-03-04
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.04534v1

Social norms are stable behavioral patterns that emerge endogenously within economic systems through repeated interactions among agents. In online market economies, such norms -- like fair exposure, sustained participation, and balanced reinvestment -- are critical for long-term stability. We aim to understand the causal mechanisms driving these emergent norms and to design principled interventions that can steer them toward desired outcomes. This is challenging because norms arise from countless micro-level interactions that aggregate into macro-level regularities, making causal attribution and policy transferability difficult. To address this, we propose \textbf{Invariant Causal Routing (ICR)}, a causal governance framework that identifies policy-norm relations stable across heterogeneous environments. ICR integrates counterfactual reasoning with invariant causal discovery to separate genuine causal effects from spurious correlations and to construct interpretable, auditable policy rules that remain effective under distribution shift. In heterogeneous agent simulations calibrated with real data, ICR yields more stable norms, smaller generalization gaps, and more concise rules than correlation or coverage baselines, demonstrating that causal invariance offers a principled and interpretable foundation for governance.

---

### Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks

Authors: Nathan Kuissi, Suraj Subrahmanyan, Nandan Thakur, Jimmy Lin
Published: 2026-03-04
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.04532v1

Information retrieval (IR) benchmarks typically follow the Cranfield paradigm, relying on static and predefined corpora. However, temporal changes in technical corpora, such as API deprecations and code reorganizations, can render existing benchmarks stale. In our work, we investigate how temporal corpus drift affects FreshStack, a retrieval benchmark focused on technical domains. We examine two independent corpus snapshots of FreshStack from October 2024 and October 2025 to answer questions about LangChain. Our analysis shows that all but one query posed in 2024 remain fully supported by the 2025 corpus, as relevant documents "migrate" from LangChain to competitor repositories, such as LlamaIndex. Next, we compare the accuracy of retrieval models on both snapshots and observe only minor shifts in model rankings, with overall strong correlation of up to 0.978 Kendall $τ$ at Recall@50. These results suggest that retrieval benchmarks re-judged with evolving temporal corpora can remain reliable for retrieval evaluation. We publicly release all our artifacts at https://github.com/fresh-stack/driftbench.

---

### Discovering mathematical concepts through a multi-agent system

Authors: Daattavya Aggarwal, Oisin Kim, Carl Henrik Ek, Challenger Mishra
Published: 2026-03-04
Categories: cs.AI, math.HO
arXiv: https://arxiv.org/abs/2603.04528v2

Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof, and counterexamples. In this paper, we present a new multi-agent model for computational mathematical discovery based on this observation. Our system, conceived with research in mind, poses its own conjectures and then attempts to prove them, making decisions informed by this feedback and an evolving data distribution. Inspired by the history of Euler's conjecture for polyhedra and an open challenge in the literature, we benchmark with the task of autonomously recovering the concept of homology from polyhedral data and knowledge of linear algebra. Our system completes this learning problem. Most importantly, the experiments are ablations, statistically testing the value of the complete dynamic and controlling for experimental setup. They support our main claim: that the optimisation of the right combination of local processes can lead to surprisingly well-aligned notions of mathematical interestingness.

---

### The Volterra signature

Authors: Paul P. Hager, Fabian N. Harang, Luca Pelizzari, Samy Tindel
Published: 2026-03-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.04525v2

Modern approaches for learning from non-Markovian time series, such as recurrent neural networks, neural controlled differential equations or transformers, typically rely on implicit memory mechanisms that can be difficult to interpret or to train over long horizons. We propose the \emph{Volterra signature} $\mathrm{VSig}(x;K)$ as a principled, explicit feature representation for history-dependent systems. By developing the input path $x$ weighted by a temporal kernel $K$ into the tensor algebra, we leverage the associated Volterra--Chen identity to derive rigorous learning-theoretic guarantees. Specifically, we prove an \emph{injectivity} statement (identifiability under augmentation) that leads to a \emph{universal approximation} theorem on the infinite dimensional path space, which in certain cases is achieved by \emph{linear functionals} of $\mathrm{VSig}(x;K)$. Moreover, we demonstrate applicability of the \emph{kernel trick} by showing that the inner product associated with Volterra signatures admits a closed characterization via a two-parameter integral equation, enabling numerical methods from PDEs for computation. For a large class of exponential-type kernels, $\mathrm{VSig}(x;K)$ solves a linear state-space ODE in the tensor algebra. Combined with inherent invariance to time reparameterization, these results position the Volterra signature as a robust, computationally tractable feature map for data science. We demonstrate its efficacy in dynamic learning tasks on real and synthetic data, where it consistently improves classical path signature baselines.

---

### Projected Hessian Learning: Fast Curvature Supervision for Accurate Machine-Learning Interatomic Potentials

Authors: Austin Rodriguez, Justin S. Smith, Sakib Matin, Nicholas Lubbers, Kipton Barros, Jose L. Mendoza-Cortes
Published: 2026-03-04
Categories: physics.chem-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04523v1

The Hessian matrix (second derivatives) encodes far richer local curvature of the potential energy surface than energies and forces alone. However, training machine-learning interatomic potentials (MLIPs) with full Hessians is often impractical because explicitly forming and storing Hessian matrices scales quadratically in cost and memory. We introduce Projected Hessian Learning (PHL), a scalable second-order training framework that injects curvature information using only Hessian-vector products (HVPs). Rather than constructing the Hessian, PHL projects curvature along stochastic probe directions and uses an unbiased stochastic trace-based loss with favorable system-size scaling, enabling curvature-informed training without quadratic memory growth. We benchmark PHL on a chemically diverse dataset of reactants, products, transition states, intrinsic reaction coordinates, and normal-mode sampled geometries computed at omegaB97XD/6-31G(d). We compare energy-force training (E-F), two HVP-based schemes (E-F-HVP with one-hot or randomized probes), and full energy-force-Hessian training (E-F-H). With randomized probes per minibatch, both HVP schemes match full-Hessian training in energy, force, and Hessian accuracy while delivering >24x epoch speedups for the small molecular systems studied. In a fixed-probe regime with one HVP per molecule, randomized projections consistently outperform one-column probing, especially for far-from-equilibrium geometries. Overall, PHL replaces explicit Hessian supervision with force-complexity curvature training, retaining most second-order accuracy gains while scaling to larger, more complex molecular systems.

---

### Augmenting representations with scientific papers

Authors: Nicolò Oreste Pinciroli Vago, Rocco Di Tella, Carolina Cuesta-Lázaro, Michael J. Smith, Cecilia Garraffo, Rafael Martínez-Galarza
Published: 2026-03-04
Categories: cs.LG, astro-ph.IM, cs.AI
arXiv: https://arxiv.org/abs/2603.04516v1

Astronomers have acquired vast repositories of multimodal data, including images, spectra, and time series, complemented by decades of literature that analyzes astrophysical sources. Still, these data sources are rarely systematically integrated. This work introduces a contrastive learning framework designed to align X-ray spectra with domain knowledge extracted from scientific literature, facilitating the development of shared multimodal representations. Establishing this connection is inherently complex, as scientific texts encompass a broader and more diverse physical context than spectra. We propose a contrastive pipeline that achieves a 20% Recall@1% when retrieving texts from spectra, proving that a meaningful alignment between these modalities is not only possible but capable of accelerating the interpretation of rare or poorly understood sources. Furthermore, the resulting shared latent space effectively encodes physically significant information. By fusing spectral and textual data, we improve the estimation of 20 physical variables by 16-18% over unimodal spectral baselines. Our results indicate that a Mixture of Experts (MoE) strategy, which leverages both unimodal and shared representations, yields superior performance. Finally, outlier analysis within the multimodal latent space identifies high-priority targets for follow-up investigation, including a candidate pulsating ULX (PULX) and a gravitational lens system. Importantly, this framework can be extended to other scientific domains where aligning observational data with existing literature is possible.

---

### Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding

Authors: Lipeng Wan, Jianhui Gu, Junjie Ma, Jianguo Huang, Shiguang Sun, Siyuan Li, Xuguang Lan
Published: 2026-03-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.04514v1

Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating refinement control over the denoising process. Existing approaches typically assess refinement necessity from instantaneous, step-level signals under a fixed decoding process. In contrast, whether a token has converged is defined by how its prediction changes along its future refinement trajectory. Moreover, changing the refinement rule reshapes future refinement trajectories, which in turn determine how refinement rules should be formulated, making refinement control inherently dynamic. We propose \emph{Progressive Refinement Regulation} (PRR), a progressive, trajectory-grounded refinement control framework that derives a token-level notion of empirical convergence progress from full decoding rollouts. Based on this signal, PRR learns a lightweight token-wise controller to regulate refinement via temperature-based distribution shaping under a progressive self-evolving training scheme. Experiments show that PRR substantially accelerates diffusion language model decoding while preserving generation quality.

---

### Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living

Authors: Kooshan Hashemifard, Pau Climent-Pérez, Francisco Florez-Revuelta
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04509v1

Recognition of daily activities is a critical element for effective Ambient Assisted Living (AAL) systems, particularly to monitor the well-being and support the independence of older adults in indoor environments. However, developing robust activity recognition systems faces significant challenges, including intra-class variability, inter-class similarity, environmental variability, camera perspectives, and scene complexity. This paper presents a multi-modal approach for the recognition of activities of daily living tailored for older adults within AAL settings. The proposed system integrates visual information processed by a 3D Convolutional Neural Network (CNN) with 3D human pose data analyzed by a Graph Convolutional Network. Contextual information, derived from an object detection module, is fused with the 3D CNN features using a cross-attention mechanism to enhance recognition accuracy. This method is evaluated using the Toyota SmartHome dataset, which consists of real-world indoor activities. The results indicate that the proposed system achieves competitive classification accuracy for a range of daily activities, highlighting its potential as an essential component for advanced AAL monitoring solutions. This advancement supports the broader goal of developing intelligent systems that promote safety and autonomy among older adults.

---

### AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

Authors: Faisal Bin Ashraf, Animesh Ray, Stefano Lonardi
Published: 2026-03-04
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2603.04480v1

Machine learning-based antibody design is emerging as one of the most promising approaches to combat infectious diseases, due to significant advancements in the field of artificial intelligence and an exponential surge in experimental antibody data (in particular related to COVID-19). The ability of an antibody to bind to an antigens (called binding affinity) is one of the the most critical properties in designing neutralizing antibodies. In this study we introduce Ab-Affinity, a new large language model that can accurately predict the binding affinity of antibodies against a target peptide, e.g., the SARS-CoV-2 spike protein. Code and model are available at https://github.com/ucrbioinfo/AbAffinity.

---

### Bayesian Modeling of Collatz Stopping Times: A Probabilistic Machine Learning Perspective

Authors: Nicolò Bonacorsi, Matteo Bordoni
Published: 2026-03-04
Categories: stat.ML, cs.LG, math.PR, math.ST, stat.AP
arXiv: https://arxiv.org/abs/2603.04479v1

We study the Collatz total stopping time $τ(n)$ over $n\le 10^7$ from a probabilistic machine learning viewpoint. Empirically, $τ(n)$ is a skewed and heavily overdispersed count with pronounced arithmetic heterogeneity. We develop two complementary models. First, a Bayesian hierarchical Negative Binomial regression (NB2-GLM) predicts $τ(n)$ from simple covariates ($\log n$ and residue class $n \bmod 8$), quantifying uncertainty via posterior and posterior predictive distributions. Second, we propose a mechanistic generative approximation based on the odd-block decomposition: for odd $m$, write $3m+1=2^{K(m)}m'$ with $m'$ odd and $K(m)=v_2(3m+1)\ge 1$; randomizing these block lengths yields a stochastic approximation calibrated via a Dirichlet-multinomial update. On held-out data, the NB2-GLM achieves substantially higher predictive likelihood than the odd-block generators. Conditioning the block-length distribution on $m\bmod 8$ markedly improves the generator's distributional fit, indicating that low-order modular structure is a key driver of heterogeneity in $τ(n)$.

---

### Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation

Authors: Chenqi Li, Yu Liu, Shuo Zhang, Timothy Denison, Tingting Zhu
Published: 2026-03-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.04478v1

Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired by the success of vision and language foundation models. However, unlike images and text, EEG datasets are notoriously expensive to collect and characterized by low signal-to-noise ratio. These challenges introduce difficulties in scaling the EEG foundation models and capturing the underlying neural semantics through reconstruction. In this work, we ask the question: can we stand on the shoulders of well-established foundation models from well-represented modalities to bootstrap the pretraining of EEG foundation models? We first demonstrate that mainstream foundation models, such as those from vision and time series, transfer surprisingly well to EEG domain. To this end, we propose the Multi-Teacher Distillation Pretraining (MTDP) framework for pretraining EEG foundation models via a two-stage multi-teacher distillation. In the first stage, we introduce a learnable gating network to fuse representations from diverse teachers (e.g., DINOv3 and Chronos) via a masked latent denoising objective. In the second stage, we distill the fused representation into an EEG foundation model. Extensive evaluations across 9 downstream tasks and 12 datasets demonstrate that our MTDP-based EEG foundation model outperforms its self-supervised counterparts while requiring only 25% of the pretraining data.

---

### Activity Recognition from Smart Insole Sensor Data Using a Circular Dilated CNN

Authors: Yanhua Zhao
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04477v1

Smart insoles equipped with pressure sensors, accelerometers, and gyroscopes offer a non-intrusive means of monitoring human gait and posture. We present an activity classification system based on a circular dilated convolutional neural network (CDCNN) that processes multi-modal time-series data from such insoles. The model operates on 160-frame windows with 24 channels (18 pressure, 3 accelerometer, 3 gyroscope axes), achieving 86.42% test accuracy in a subject-independent evaluation on a four-class task (Standing, Walking, Sitting, Tandem), compared with 87.83% for an extreme gradient-boosted tree (XGBoost) model trained on flattened data. Permutation feature importance reveals that inertial sensors (accelerometer and gyroscope) contribute substantially to discrimination. The approach is suitable for embedded deployment and real-time inference.

---

### From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Authors: Yizhe Xie, Congcong Zhu, Xinyue Zhang, Tianqing Zhu, Dayong Ye, Minfeng Qi, Huajie Chen, Wanlei Zhou
Published: 2026-03-04
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2603.04474v2

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach prevents final infection in at least 89% of runs across operating modes and significantly mitigates the cascading spread of minor errors.

---

### Dictionary Based Pattern Entropy for Causal Direction Discovery

Authors: Harikrishnan N B, Shubham Bhilare, Aditi Kathpalia, Nithin Nagaraj
Published: 2026-03-04
Categories: stat.ML, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2603.04473v1

Discovering causal direction from temporal observational data is particularly challenging for symbolic sequences, where functional models and noise assumptions are often unavailable. We propose a novel \emph{Dictionary Based Pattern Entropy ($DPE$)} framework that infers both the direction of causation and the specific subpatterns driving changes in the effect variable. The framework integrates \emph{Algorithmic Information Theory} (AIT) and \emph{Shannon Information Theory}. Causation is interpreted as the emergence of compact, rule based patterns in the candidate cause that systematically constrain the effect. $DPE$ constructs direction-specific dictionaries and quantifies their influence using entropy-based measures, enabling a principled link between deterministic pattern structure and stochastic variability. Causal direction is inferred via a minimum-uncertainty criterion, selecting the direction exhibiting stronger and more consistent pattern-driven organization. As summarized in Table 7, $DPE$ consistently achieves reliable performance across diverse synthetic systems, including delayed bit-flip perturbations, AR(1) coupling, 1D skew-tent maps, and sparse processes, outperforming or matching competing AIT-based methods ($ETC_E$, $ETC_P$, $LZ_P$). In biological and ecological datasets, performance is competitive, while alternative methods show advantages in specific genomic settings. Overall, the results demonstrate that minimizing pattern level uncertainty yields a robust, interpretable, and broadly applicable framework for causal discovery.

---

### Towards Explainable Deep Learning for Ship Trajectory Prediction in Inland Waterways

Authors: Tom Legel, Dirk Söffker, Roland Schätzle, Kathrin Donandt
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04472v1

Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in deep learning promise increased accuracy even for complex scenarios. While the challenge of ship-to-ship awareness is being addressed with growing success, the explainability of these models is often overlooked, potentially obscuring an inaccurate logic and undermining the confidence in their reliability. This study examines an LSTM-based vessel trajectory prediction model by incorporating trained ship domain parameters that provide insight into the attention-based fusion of the interacting vessels' hidden states. This approach has previously been explored in the field of maritime shipping, yet the variety and complexity of encounters in inland waterways allow for a more profound analysis of the model's interpretability. The prediction performance of the proposed model variants are evaluated using standard displacement error statistics. Additionally, the plausibility of the generated ship domain values is analyzed. With an final displacement error of around 40 meters in a 5-minute prediction horizon, the model performs comparably to similar studies. Though the ship-to-ship attention architecture enhances prediction accuracy, the weights assigned to vessels in encounters using the learnt ship domain values deviate from the expectation. The observed accuracy improvements are thus not entirely driven by a causal relationship between a predicted trajectory and the trajectories of nearby ships. This finding underscores the model's explanatory capabilities through its intrinsically interpretable design. Future work will focus on utilizing the architecture for counterfactual analysis and on the incorporation of more sophisticated attention mechanisms.

---

### SimpliHuMoN: Simplifying Human Motion Prediction

Authors: Aadya Agrawal, Alexander Schwing
Published: 2026-03-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.04399v1

Human motion prediction combines the tasks of trajectory forecasting and human pose prediction. For each of the two tasks, specialized models have been developed. Combining these models for holistic human motion prediction is non-trivial, and recent methods have struggled to compete on established benchmarks for individual tasks. To address this, we propose a simple yet effective transformer-based model for human motion prediction. The model employs a stack of self-attention modules to effectively capture both spatial dependencies within a pose and temporal relationships across a motion sequence. This simple, streamlined, end-to-end model is sufficiently versatile to handle pose-only, trajectory-only, and combined prediction tasks without task-specific modifications. We demonstrate that this approach achieves state-of-the-art results across all tasks through extensive experiments on a wide range of benchmark datasets, including Human3.6M, AMASS, ETH-UCY, and 3DPW.

---

### Accurate and Efficient Hybrid-Ensemble Atmospheric Data Assimilation in Latent Space with Uncertainty Quantification

Authors: Hang Fan, Juan Nathaniel, Yi Xiao, Ce Bian, Fenghua Ling, Ben Fei, Lei Bai, Pierre Gentine
Published: 2026-03-04
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2603.04395v1

Data assimilation (DA) combines model forecasts and observations to estimate the optimal state of the atmosphere with its uncertainty, providing initial conditions for weather prediction and reanalyses for climate research. Yet, existing traditional and machine-learning DA methods struggle to achieve accuracy, efficiency and uncertainty quantification simultaneously. Here, we propose HLOBA (Hybrid-Ensemble Latent Observation-Background Assimilation), a three-dimensional hybrid-ensemble DA method that operates in an atmospheric latent space learned via an autoencoder (AE). HLOBA maps both model forecasts and observations into a shared latent space via the AE encoder and an end-to-end Observation-to-Latent-space mapping network (O2Lnet), respectively, and fuses them through a Bayesian update with weights inferred from time-lagged ensemble forecasts. Both idealized and real-observation experiments demonstrate that HLOBA matches dynamically constrained four-dimensional DA methods in both analysis and forecast skill, while achieving end-to-end inference-level efficiency and theoretical flexibility applies to any forecasting model. Moreover, by exploiting the error decorrelation property of latent variables, HLOBA enables element-wise uncertainty estimates for its latent analysis and propagates them to model space via the decoder. Idealized experiments show that this uncertainty highlights large-error regions and captures their seasonal variability.

---

### SELDON: Supernova Explosions Learned by Deep ODE Networks

Authors: Jiezhong Wu, Jack O'Brien, Jennifer Li, M. S. Krafczyk, Ved G. Shah, Amanda R. Wasserman, Daniel W. Apley, Gautham Narayan, Noelle I. Samia
Published: 2026-03-04
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2603.04392v1

The discovery rate of optical transients will explode to 10 million public alerts per night once the Vera C. Rubin Observatory's Legacy Survey of Space and Time comes online, overwhelming the traditional physics-based inference pipelines. A continuous-time forecasting AI model is of interest because it can deliver millisecond-scale inference for thousands of objects per day, whereas legacy MCMC codes need hours per object. In this paper, we propose SELDON, a new continuous-time variational autoencoder for panels of sparse and irregularly time-sampled (gappy) astrophysical light curves that are nonstationary, heteroscedastic, and inherently dependent. SELDON combines a masked GRU-ODE encoder with a latent neural ODE propagator and an interpretable Gaussian-basis decoder. The encoder learns to summarize panels of imbalanced and correlated data even when only a handful of points are observed. The neural ODE then integrates this hidden state forward in continuous time, extrapolating to future unseen epochs. This extrapolated time series is further encoded by deep sets to a latent distribution that is decoded to a weighted sum of Gaussian basis functions, the parameters of which are physically meaningful. Such parameters (e.g., rise time, decay rate, peak flux) directly drive downstream prioritization of spectroscopic follow-up for astrophysical surveys. Beyond astronomy, the architecture of SELDON offers a generic recipe for interpretable and continuous-time sequence modeling in any time domain where data are multivariate, sparse, heteroscedastic, and irregularly spaced.

---

### A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development

Authors: Boyuan Guan, Wencong Cui, Levente Juhasz
Published: 2026-03-04
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.04390v2

WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3-track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), roughly halved trial-to-trial output variance relative to static prompting in a controlled experiment, and prevented common infodemic mapping errors in a 5-condition COVID-19 cartography ablation study. Operationalized via the open-source AgentLoom toolkit, this externalized governance provides the stability necessary for production-level geospatial engineering.

---

### ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Authors: Haian Jin, Rundi Wu, Tianyuan Zhang, Ruiqi Gao, Jonathan T. Barron, Noah Snavely, Aleksander Holynski
Published: 2026-03-04
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04385v3

Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $π^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when applied to large image collections. Sequential-reconstruction approaches reduce this cost but sacrifice reconstruction quality. We introduce ZipMap, a stateful feed-forward model that achieves linear-time, bidirectional 3D reconstruction while matching or surpassing the accuracy of quadratic-time methods. ZipMap employs test-time training layers to zip an entire image collection into a compact hidden scene state in a single forward pass, enabling reconstruction of over 700 frames in under 10 seconds on a single H100 GPU, more than $20\times$ faster than state-of-the-art methods such as VGGT. Moreover, we demonstrate the benefits of having a stateful representation in real-time scene-state querying and its extension to sequential streaming reconstruction.

---

### AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

Authors: Zijian Chen, Xueguang Ma, Shengyao Zhuang, Jimmy Lin, Akari Asai, Victor Zhong
Published: 2026-03-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.04384v3

Deep Research agents are rapidly emerging as primary consumers of modern retrieval systems. Unlike human users who issue and refine queries without documenting their intermediate thought processes, Deep Research agents generate explicit natural language reasoning before each search call, revealing rich intent and contextual information that existing retrievers entirely ignore. To exploit this overlooked signal, we introduce: (1) Reasoning-Aware Retrieval, a retrieval paradigm that jointly embeds the agent's reasoning trace alongside its query; and (2) DR-Synth, a data synthesis method that generates Deep Research retriever training data from standard QA datasets. We demonstrate that both components are independently effective, and their combination yields a trained embedding model, AgentIR-4B, with substantial gains. On the challenging BrowseComp-Plus benchmark, AgentIR-4B achieves 68\% accuracy with the open-weight agent Tongyi-DeepResearch, compared to 50\% with conventional embedding models twice its size, and 37\% with BM25. Code and data are available at: https://texttron.github.io/AgentIR/.

---

### Turning Trust to Transactions: Tracking Affiliate Marketing and FTC Compliance in YouTube's Influencer Economy

Authors: Chen Sun, Yash Vekaria, Zubair Shafiq, Rishab Nithyanand
Published: 2026-03-04
Categories: cs.CY, cs.CR, cs.IR, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2603.04383v2

YouTube has evolved into a powerful platform where creators monetize their influence through affiliate marketing, raising concerns about transparency and ethics, especially when creators fail to disclose their affiliate relationships. Although regulatory agencies like the US Federal Trade Commission (FTC) have issued guidelines to address these issues, non-compliance and consumer harm persist, and the extent of these problems remains unclear. In this paper, we introduce tools, developed with insights from recent advances in Web measurement and NLP research, to examine the state of the affiliate marketing ecosystem on YouTube. We apply these tools to a 10-year dataset of 2 million videos from nearly 540,000 creators, analyzing the prevalence of affiliate marketing on YouTube and the rates of non-compliant behavior. Our findings reveal that affiliate links are widespread, yet disclosure compliance remains low, with most videos failing to meet FTC standards. Furthermore, we analyze the effects of different stakeholders in improving disclosure behavior. Our study suggests that the platform is highly associated with improved compliance through standardized disclosure features. We recommend that regulators and affiliate partners collaborate with platforms to enhance transparency, accountability, and trust in the influencer economy.

---

### TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning

Authors: Maximilian von Klinski, Maximilian Schall
Published: 2026-03-04
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.04380v1

Traditional vision-language models struggle with contrastive fine-grained taxonomic reasoning, particularly when distinguishing between visually similar species within the same genus or family. We introduce TaxonRL, a reinforcement learning approach using Group Relative Policy Optimization with intermediate rewards that decomposes the reasoning process into hierarchical taxonomic predictions. Our method incentivizes models to explicitly reason about species-level, genus-level, and family-level features before making final classifications. This structured approach is designed not only to boost accuracy but also to yield a transparent, verifiable decision-making process. On the challenging Birds-to-Words dataset, TaxonRL achieves 91.7\% average accuracy, exceeding human performance (77.3\%) while generating interpretable reasoning traces. We demonstrate strong cross-domain generalization, showing substantial gains in primate and marine species verification. Our results establish that enforcing structured, hierarchical reasoning provides a powerful and transferable framework for fine-grained visual discrimination.

---

### Helios: Real Real-Time Long Video Generation Model

Authors: Shenghai Yuan, Yuanyang Yin, Zongjian Li, Xinwei Huang, Xiao Yang, Li Yuan
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04379v1

We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We make breakthroughs along three key dimensions: (1) robustness to long-video drifting without commonly used anti-drifting heuristics such as self-forcing, error-banks, or keyframe sampling; (2) real-time generation without standard acceleration techniques such as KV-cache, sparse/linear attention, or quantization; and (3) training without parallelism or sharding frameworks, enabling image-diffusion-scale batch sizes while fitting up to four 14B models within 80 GB of GPU memory. Specifically, Helios is a 14B autoregressive diffusion model with a unified input representation that natively supports T2V, I2V, and V2V tasks. To mitigate drifting in long-video generation, we characterize typical failure modes and propose simple yet effective training strategies that explicitly simulate drifting during training, while eliminating repetitive motion at its source. For efficiency, we heavily compress the historical and noisy context and reduce the number of sampling steps, yielding computational costs comparable to -- or lower than -- those of 1.3B video generative models. Moreover, we introduce infrastructure-level optimizations that accelerate both inference and training while reducing memory consumption. Extensive experiments demonstrate that Helios consistently outperforms prior methods on both short- and long-video generation. We plan to release the code, base model, and distilled model to support further development by the community.

---

### Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization

Authors: Furkan Mumcu, Yasin Yilmaz
Published: 2026-03-04
Categories: cs.LG, cs.AI, cs.CR, cs.MA
arXiv: https://arxiv.org/abs/2603.04378v1

As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear policies induce extreme local curvature in the inner maximization. Standard remedies that enforce global Jacobian bounds are overly conservative, suppressing sensitivity in all directions and inducing a large Price of Robustness. We introduce Adversarially-Aligned Jacobian Regularization (AAJR), a trajectory-aligned approach that controls sensitivity strictly along adversarial ascent directions. We prove that AAJR yields a strictly larger admissible policy class than global constraints under mild conditions, implying a weakly smaller approximation gap and reduced nominal performance degradation. Furthermore, we derive step-size conditions under which AAJR controls effective smoothness along optimization trajectories and ensures inner-loop stability. These results provide a structural theory for agentic robustness that decouples minimax stability from global expressivity restrictions.

---

### $τ$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge

Authors: Quan Shi, Alexandra Zytek, Pedram Razavi, Karthik Narasimhan, Victor Barres
Published: 2026-03-04
Categories: cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2603.04370v1

Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, proprietary, and unstructured corpora during live interactions with users. Yet most existing benchmarks evaluate retrieval or tool use independently of each other, creating a gap in realistic, fully agentic evaluation over unstructured data in long-horizon interactions. We introduce $τ$-Knowledge, an extension of $τ$-Bench for evaluating agents in environments where success depends on coordinating external, natural-language knowledge with tool outputs to produce verifiable, policy-compliant state changes. Our new domain, $τ$-Banking, models realistic fintech customer support workflows in which agents must navigate roughly 700 interconnected knowledge documents while executing tool-mediated account updates. Across embedding-based retrieval and terminal-based search, even frontier models with high reasoning budgets achieve only $\sim$25.5% pass^1, with reliability degrading sharply over repeated trials. Agents struggle to retrieve the correct documents from densely interlinked knowledge bases and to reason accurately over complex internal policies. Overall, $τ$-Knowledge provides a realistic testbed for developing agents that integrate unstructured knowledge in human-facing deployments.

---

### Low-Resource Guidance for Controllable Latent Audio Diffusion

Authors: Zachary Novack, Zack Zukowski, CJ Carr, Julian Parker, Zach Evans, Josiah Taylor, Taylor Berg-Kirkpatrick, Julian McAuley, Jordi Pons
Published: 2026-03-04
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04366v1

Generative audio requires fine-grained controllable outputs, yet most existing methods require model retraining on specific controls or inference-time controls (\textit{e.g.}, guidance) that can also be computationally demanding. By examining the bottlenecks of existing guidance-based controls, in particular their high cost-per-step due to decoder backpropagation, we introduce a guidance-based approach through selective TFG and Latent-Control Heads (LatCHs), which enables controlling latent audio diffusion models with low computational overhead. LatCHs operate directly in latent space, avoiding the expensive decoder step, and requiring minimal training resources (7M parameters and $\approx$ 4 hours of training). Experiments with Stable Audio Open demonstrate effective control over intensity, pitch, and beats (and a combination of those) while maintaining generation quality. Our method balances precision and audio fidelity with far lower computational costs than standard end-to-end guidance. Demo examples can be found at https://zacharynovack.github.io/latch/latch.html.

---

### Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

Authors: Haoyu Liu, Dingcheng Li, Lukas Rutishauser, Zeyu Zheng
Published: 2026-03-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.04364v1

Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversary who injects content into the webpage DOM simultaneously corrupts both observation channels with a consistent deceptive narrative. Our vulnerability analysis on MiniWob++ reveals that attacks including a visual component far outperform text-only injections, exposing critical gaps in text-centric VLM safety training. Motivated by this finding, we propose Dual-Modality Multi-Stage Adversarial Safety Training (DMAST), a framework that formalizes the agent-attacker interaction as a two-player zero-sum Markov game and co-trains both players through a three-stage pipeline: (1) imitation learning from a strong teacher model, (2) oracle-guided supervised fine-tuning that uses a novel zero-acknowledgment strategy to instill task-focused reasoning under adversarial noise, and (3) adversarial reinforcement learning via Group Relative Policy Optimization (GRPO) self-play. On out-of-distribution tasks, DMAST substantially mitigates adversarial risks while simultaneously doubling task completion efficiency. Our approach significantly outperforms established training-based and prompt-based defenses, demonstrating genuine co-evolutionary progress and robust generalization to complex, unseen environments.

---

### Robust Unscented Kalman Filtering via Recurrent Meta-Adaptation of Sigma-Point Weights

Authors: Kenan Majewski, Michał Modzelewski, Marcin Żugaj, Piotr Lichota
Published: 2026-03-04
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2603.04360v1

The Unscented Kalman Filter (UKF) is a ubiquitous tool for nonlinear state estimation; however, its performance is limited by the static parameterization of the Unscented Transform (UT). Conventional weighting schemes, governed by fixed scaling parameters, assume implicit Gaussianity and fail to adapt to time-varying dynamics or heavy-tailed measurement noise. This work introduces the Meta-Adaptive UKF (MA-UKF), a framework that reformulates sigma-point weight synthesis as a hyperparameter optimization problem addressed via memory-augmented meta-learning. Unlike standard adaptive filters that rely on instantaneous heuristic corrections, our approach employs a Recurrent Context Encoder to compress the history of measurement innovations into a compact latent embedding. This embedding informs a policy network that dynamically synthesizes the mean and covariance weights of the sigma points at each time step, effectively governing the filter's trust in the prediction versus the measurement. By optimizing the system end-to-end through the filter's recursive logic, the MA-UKF learns to maximize tracking accuracy while maintaining estimation consistency. Numerical benchmarks on maneuvering targets demonstrate that the MA-UKF significantly outperforms standard baselines, exhibiting superior robustness to non-Gaussian glint noise and effective generalization to out-of-distribution (OOD) dynamic regimes unseen during training.

---

### Dissecting Quantization Error: A Concentration-Alignment Perspective

Authors: Marco Federici, Boris van Breugel, Paul Whatmough, Markus Nagel
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04359v1

Quantization can drastically increase the efficiency of large language and vision models, but typically incurs an accuracy drop. Recently, function-preserving transforms (e.g. rotations, Hadamard transform, channel-wise scaling) have been successfully applied to reduce post-training quantization error, yet a principled explanation remains elusive. We analyze linear-layer quantization via the signal-to-quantization-noise ratio (SQNR), showing that for uniform integer quantization at a fixed bit width, SQNR decomposes into (i) the concentration of weights and activations (capturing spread and outliers), and (ii) the alignment of their dominant variation directions. This reveals an actionable insight: beyond concentration - the focus of most prior transforms (e.g. rotations or Hadamard) - improving alignment between weight and activation can further reduce quantization error. Motivated by this, we introduce block Concentration-Alignment Transforms (CAT), a lightweight linear transformation that uses a covariance estimate from a small calibration set to jointly improve concentration and alignment, approximately maximizing SQNR. Experiments across several LLMs show that CAT consistently matches or outperforms prior transform-based quantization methods at 4-bit precision, confirming the insights gained in our framework.

---

### RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots

Authors: Soroush Nasiriany, Sepehr Nasiriany, Abhiram Maddukuri, Yuke Zhu
Published: 2026-03-04
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04356v1

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remains difficult to gauge how close we are to this vision. The field lacks a reproducible, large-scale benchmark for systematic evaluation. To fill this gap, we present RoboCasa365, a comprehensive simulation benchmark for household mobile manipulation. Built on the RoboCasa platform, RoboCasa365 introduces 365 everyday tasks across 2,500 diverse kitchen environments, with over 600 hours of human demonstration data and over 1600 hours of synthetically generated demonstration data -- making it one of the most diverse and large-scale resources for studying generalist policies. RoboCasa365 is designed to support systematic evaluations for different problem settings, including multi-task learning, robot foundation model training, and lifelong learning. We conduct extensive experiments on this benchmark with state-of-the-art methods and analyze the impacts of task diversity, dataset scale, and environment variation on generalization. Our results provide new insights into what factors most strongly affect the performance of generalist robots and inform strategies for future progress in the field.

---

### Efficient Refusal Ablation in LLM through Optimal Transport

Authors: Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04355v1

Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent these safety mechanisms by applying orthogonal projections to remove refusal directions, but these approaches treat refusal as a one-dimensional phenomenon and ignore the rich distributional structure of model activations. We introduce a principled framework based on optimal transport theory that transforms the entire distribution of harmful activations to match harmless ones. By combining PCA with closed-form Gaussian optimal transport, we achieve efficient computation in high-dimensional representation spaces while preserving essential geometric structure. Across six models (Llama-2, Llama-3.1, Qwen-2.5; 7B-32B parameters), our method achieves up to 11% higher attack success rates than state-of-the-art baselines while maintaining comparable perplexity, demonstrating superior preservation of model capabilities. Critically, we discover that layer-selective intervention (applying optimal transport to 1-2 carefully chosen layers at approximately 40-60% network depth) substantially outperforms full-network interventions, revealing that refusal mechanisms may be localized rather than distributed. Our analysis provides new insights into the geometric structure of safety representations and suggests that current alignment methods may be vulnerable to distributional attacks beyond simple direction removal.

---

### Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading

Authors: Mahindra Rautela, Alexander Most, Siddharth Mansingh, Aleksandra Pachalieva, Bradley Love, Daniel O Malley, Alexander Scheinker, Kyle Hickmann, Diane Oyen, Nathan Debardeleben, Earl Lawrence, Ayan Biswas
Published: 2026-03-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.04354v1

Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-distribution transfer on two discontinuity-dominated regimes in which shocks, evolving interfaces, and fracture produce highly non-smooth fields: shock-driven multi-material interface dynamics (perturbed layered interface or PLI) and dynamic fracture/failure evolution (FRAC). We formulate the downstream task as terminal-state prediction, i.e., learning a long-horizon map that predicts the final state directly from the first snapshot without intermediate supervision. Using a unified training and evaluation protocol, we evaluate two open-source pretrained PDE foundation models, POSEIDON and MORPH, and compare fine-tuning from pretrained weights against training from scratch across training-set sizes to quantify sample efficiency under distribution shift.

---

### A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications

Authors: Ozan Aygün, Vincenzo Norman Vitale, Antonia M. Tulino, Hao Feng, Elza Erkip, Jaime Llorca
Published: 2026-03-04
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2603.04353v1

Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed by the application while minimizing overall resource allocation cost. A large body of work has leveraged stochastic optimization techniques to design efficient dynamic routing and scheduling solutions under average delay constraints; however, these methods fall short when faced with strict per-packet delay requirements. We formulate the minimum-cost delay-constrained network control problem as a constrained Markov decision process and utilize constrained deep reinforcement learning (CDRL) techniques to effectively minimize total resource allocation cost while maintaining timely throughput above a target reliability level. Results indicate that the proposed CDRL-based solution can ensure timely packet delivery even when existing baselines fall short, and it achieves lower cost compared to other throughput-maximizing methods.

---

### FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering

Authors: Tatiana Zemskova, Solomon Andryushenko, Ilya Obrubov, Viktoriia Khoruzhaia, Ekaterina Eroshenko, Ekaterina Derevyanka, Dmitry Yudin
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04349v1

The ability to understand long videos is vital for embodied intelligent agents, because their effectiveness depends on how well they can accumulate, organize, and leverage long-horizon perceptual memories. Recently, multimodal LLMs have been gaining popularity for solving the long video understanding task due to their general ability to understand natural language and to leverage world knowledge. However, as the number of frames provided to an MLLM increases, the quality of its responses tends to degrade, and inference time grows. Therefore, when using MLLMs for long video understanding, a crucial step is selecting key frames from the video to answer user queries. In this work, we develop FocusGraph, a framework for keyframe selection for question answering over long egocentric videos. It leverages a lightweight trainable Scene-Caption LLM Selector that selects query-relevant clips based on their graph-based captions, and a training-free method for selecting keyframes from these clips. Unlike existing methods, the proposed Scene-Caption LLM Selector does not rely on the original sequence of low-resolution frames; instead, it operates on a compact textual representation of the scene. We then design a training-free Patch-wise Sparse-Flow Retention (PSFR) method to select keyframes from the resulting sequence of clips, which are fed into an MLLM to produce the final answer. Together, these components enable FocusGraph to achieve state-of-the-art results on challenging egocentric long-video question answering benchmarks, including FindingDory and HourVideo, while significantly reducing inference time relative to baseline approaches.

---

### RANGER: Sparsely-Gated Mixture-of-Experts with Adaptive Retrieval Re-ranking for Pathology Report Generation

Authors: Yixin Chen, Ziyu Su, Hikmat Khan, Muhammad Khalid Khan Niazi
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.04348v1

Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heterogeneity of Whole Slide Images (WSIs). Existing pathology report generation frameworks typically employ transformer architectures, relying on a homogeneous decoder architecture and static knowledge retrieval integration. Such architectures limit generative specialization and may introduce noisy external guidance during the report generation process. To address these limitations, we propose RANGER, a sparsely-gated Mixture-of-Experts (MoE) framework with adaptive retrieval re-ranking for pathology report generation. Specifically, we integrate a sparsely gated MoE into the decoder, along with noisy top-$k$ routing and load-balancing regularization, to enable dynamic expert specialization across various diagnostic patterns. Additionally, we introduce an adaptive retrieval re-ranking module that selectively refines retrieved memory from a knowledge base before integration, reducing noise and improving semantic alignment based on visual feature representations. We perform extensive experiments on the PathText-BRCA dataset and demonstrate consistent improvements over existing approaches across standard natural language generation metrics. Our full RANGER model achieves optimal performance on PathText dataset, reaching BLEU-1 to BLEU-4 scores of 0.4598, 0.3044, 0.2036, and 0.1435, respectively, with METEOR of 0.1883, and ROUGE-L of 0.3038, validating the effectiveness of dynamic expert routing and adaptive knowledge refinement for semantically grounded pathology report generation.

---

### Underrepresented in Foundation Model Pretraining Data? A One-Shot Probe

Authors: Chris Vorster, Mayug Maniparambil, Noel E. O'Connor, Noel Murphy, Derek Molloy
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04346v1

Large-scale Vision-Language Foundation Models (VLFMs), such as CLIP, now underpin a wide range of computer vision research and applications. VLFMs are often adapted to various domain-specific tasks. However, VLFM performance on novel, specialised, or underrepresented domains remains inconsistent. Evaluating VLFMs typically requires labelled test sets, which are often unavailable for niche domains of interest, particularly those from the Global South. We address this gap by proposing a highly data-efficient method to predict a VLFM's zero-shot accuracy on a target domain using only a single labelled image per class. Our approach uses a Large Language Model to generate plausible counterfactual descriptions of a given image. By measuring the VLFM's ability to distinguish the correct description from these hard negatives, we engineer features that capture the VLFM's discriminative power in its shared embedding space. A linear regressor trained on these similarity scores estimates the VLFM's zero-shot test accuracy across various visual domains with a Pearson-r correlation of 0.96. We demonstrate our method's performance across five diverse datasets, including standard benchmark datasets and underrepresented datasets from Africa. Our work provides a low-cost, reliable tool for probing VLFMs, enabling researchers and practitioners to make informed decisions about data annotation efforts before committing significant resources. The model training code, generated captions and counterfactuals are released here: https://github.com/chris-vorster/PreLabellingProbe.

---

### Enhancing Authorship Attribution with Synthetic Paintings

Authors: Clarissa Loures, Caio Hosken, Luan Oliveira, Gianlucca Zuin, Adriano Veloso
Published: 2026-03-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.04343v1

Attributing authorship to paintings is a historically complex task, and one of its main challenges is the limited availability of real artworks for training computational models. This study investigates whether synthetic images, generated through DreamBooth fine-tuning of Stable Diffusion, can improve the performance of classification models in this context. We propose a hybrid approach that combines real and synthetic data to enhance model accuracy and generalization across similar artistic styles. Experimental results show that adding synthetic images leads to higher ROC-AUC and accuracy compared to using only real paintings. By integrating generative and discriminative methods, this work contributes to the development of computer vision techniques for artwork authentication in data-scarce scenarios.

---

### Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters

Authors: Chris Vorster, Mayug Maniparambil, Noel E. O'Connor, Noel Murphy, Derek Molloy
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04341v1

In many CLIP adaptation methods, a blending ratio hyperparameter controls the trade-off between general pretrained CLIP knowledge and the limited, dataset-specific supervision from the few-shot cases. Most few-shot CLIP adaptation techniques report results by ablation of the blending ratio on the test set or require additional validation sets to select the blending ratio per dataset, and thus are not strictly few-shot. We present a simple, validation-free method for learning the blending ratio in CLIP adaptation. Hold-One-Shot-Out (HOSO) presents a novel approach for CLIP-Adapter-style methods to compete in the newly established validation-free setting. CLIP-Adapter with HOSO (HOSO-Adapter) learns the blending ratio using a one-shot, hold-out set, while the adapter trains on the remaining few-shot support examples. Under the validation-free few-shot protocol, HOSO-Adapter outperforms the CLIP-Adapter baseline by more than 4 percentage points on average across 11 standard few-shot datasets. Interestingly, in the 8- and 16-shot settings, HOSO-Adapter outperforms CLIP-Adapter even with the optimal blending ratio selected on the test set. Ablation studies validate the use of a one-shot hold-out mechanism, decoupled training, and improvements over the naively learnt blending ratio baseline. Code is released here: https://github.com/chris-vorster/HOSO-Adapter

---

### Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study

Authors: Madhura Edirisooriya, Dasuni Kawya, Ishan Kumarasinghe, Isuri Devindi, Mary M. Maleckar, Roshan Ragel, Isuru Nawinne, Vajira Thambawita
Published: 2026-03-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.04340v1

Deep learning in cardiac MRI (CMR) is fundamentally constrained by both data scarcity and privacy regulations. This study systematically benchmarks three generative architectures: Denoising Diffusion Probabilistic Models (DDPM), Latent Diffusion Models (LDM), and Flow Matching (FM) for synthetic CMR generation. Utilizing a two-stage pipeline where anatomical masks condition image synthesis, we evaluate generated data across three critical axes: fidelity, utility, and privacy. Our results show that diffusion-based models, particularly DDPM, provide the most effective balance between downstream segmentation utility, image fidelity, and privacy preservation under limited-data conditions, while FM demonstrates promising privacy characteristics with slightly lower task-level performance. These findings quantify the trade-offs between cross-domain generalization and patient confidentiality, establishing a framework for safe and effective synthetic data augmentation in medical imaging.

---

### ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Authors: Zihao Huang, Tianqi Liu, Zhaoxi Chen, Shaocong Xu, Saining Zhang, Lixing Xiao, Zhiguo Cao, Wei Li, Hao Zhao, Ziwei Liu
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04338v1

Synthesizing physically plausible articulated human-object interactions (HOI) without 3D/4D supervision remains a fundamental challenge. While recent zero-shot approaches leverage video diffusion models to synthesize human-object interactions, they are largely confined to rigid-object manipulation and lack explicit 4D geometric reasoning. To bridge this gap, we formulate articulated HOI synthesis as a 4D reconstruction problem from monocular video priors: given only a video generated by a diffusion model, we reconstruct a full 4D articulated scene without any 3D supervision. This reconstruction-based approach treats the generated 2D video as supervision for an inverse rendering problem, recovering geometrically consistent and physically plausible 4D scenes that naturally respect contact, articulation, and temporal coherence. We introduce ArtHOI, the first zero-shot framework for articulated human-object interaction synthesis via 4D reconstruction from video priors. Our key designs are: 1) Flow-based part segmentation: leveraging optical flow as a geometric cue to disentangle dynamic from static regions in monocular video; 2) Decoupled reconstruction pipeline: joint optimization of human motion and object articulation is unstable under monocular ambiguity, so we first recover object articulation, then synthesize human motion conditioned on the reconstructed object states. ArtHOI bridges video-based generation and geometry-aware reconstruction, producing interactions that are both semantically aligned and physically grounded. Across diverse articulated scenes (e.g., opening fridges, cabinets, microwaves), ArtHOI significantly outperforms prior methods in contact accuracy, penetration reduction, and articulation fidelity, extending zero-shot interaction synthesis beyond rigid manipulation through reconstruction-informed synthesis.

---

### Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection

Authors: Dacheng Qi, Chenyu Wang, Jingwei Xu, Tianzhe Chu, Zibo Zhao, Wen Liu, Wenrui Ding, Yi Ma, Shenghua Gao
Published: 2026-03-04
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.04337v2

Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired the LLM-based CAD generation by representing CAD as command sequences. But these methods struggle in practical scenarios because command sequence representation does not support entity selection (e.g. faces or edges), limiting its ability to support complex editing operations such as chamfer or fillet. Further, the discretization of a continuous variable during sketch and extrude operations may result in topological errors. To address these limitations, we present Pointer-CAD, a novel LLM-based CAD generation framework that leverages a pointer-based command sequence representation to explicitly incorporate the geometric information of B-rep models into sequential modeling. In particular, Pointer-CAD decomposes CAD model generation into steps, conditioning the generation of each subsequent step on both the textual description and the B-rep generated from previous steps. Whenever an operation requires the selection of a specific geometric entity, the LLM predicts a Pointer that selects the most feature-consistent candidate from the available set. Such a selection operation also reduces the quantization error in the command sequence-based representation. To support the training of Pointer-CAD, we develop a data annotation pipeline that produces expert-level natural language descriptions and apply it to build a dataset of approximately 575K CAD models. Extensive experimental results demonstrate that Pointer-CAD effectively supports the generation of complex geometric structures and reduces segmentation error to an extremely low level, achieving a significant improvement over prior command sequence methods, thereby significantly mitigating the topological inaccuracies introduced by quantization error.

---

### SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints

Authors: Andrew Tremante, Yang He, Rocky Klopfenstein, Yuepeng Wang, Nina Narodytska, Haoze Wu
Published: 2026-03-04
Categories: cs.DB, cs.AI, cs.LO, cs.PL
arXiv: https://arxiv.org/abs/2603.04334v3

We present SpotIt+, an open-source tool for evaluating Text-to-SQL systems via bounded equivalence verification. Given a generated SQL query and the ground truth, SpotIt+ actively searches for database instances that differentiate the two queries. To ensure that the generated counterexamples reflect practically relevant discrepancies, we introduce a best-effort constraint-mining pipeline that combines rule-based specification mining with LLM-based validation over example databases. Experimental results on the BIRD dataset show that the mined constraints enable SpotIt+ to generate more realistic differentiating databases, while preserving its ability to efficiently uncover numerous discrepancies between generated and gold SQL queries that are missed by standard test-based evaluation.

---