# Research Papers — 2026-03 · bundle page 129 of 243

> Full-text markdown of papers #6401–6450 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/129
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/128.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/130.md)

### RenderMem: Rendering as Spatial Memory Retrieval

Authors: JooHyun Park, HyeongYeop Kang
Published: 2026-03-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.14669v1

Embodied reasoning is inherently viewpoint-dependent: what is visible, occluded, or reachable depends critically on where the agent stands. However, existing spatial memory systems for embodied agents typically store either multi-view observations or object-centric abstractions, making it difficult to perform reasoning with explicit geometric grounding. We introduce RenderMem, a spatial memory framework that treats rendering as the interface between 3D world representations and spatial reasoning. Instead of storing fixed observations, RenderMem maintains a 3D scene representation and generates query-conditioned visual evidence by rendering the scene from viewpoints implied by the query. This enables embodied agents to reason directly about line-of-sight, visibility, and occlusion from arbitrary perspectives. RenderMem is fully compatible with existing vision-language models and requires no modification to standard architectures. Experiments in the AI2-THOR environment show consistent improvements on viewpoint-dependent visibility and occlusion queries over prior memory baselines.

---

### Comparative Analysis of 3D Convolutional and 2.5D Slice-Conditioned U-Net Architectures for MRI Super-Resolution via Elucidated Diffusion Models

Authors: Hendrik Chiche, Ludovic Corcos, Logan Rouge
Published: 2026-03-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14667v1

Magnetic resonance imaging (MRI) super-resolution (SR) methods that computationally enhance low-resolution acquisitions to approximate high-resolution quality offer a compelling alternative to expensive high-field scanners. In this work we investigate an elucidated diffusion model (EDM) framework for brain MRI SR and compare two U-Net backbone architectures: (i) a full 3D convolutional U-Net that processes volumetric patches with 3D convolutions and multi-head self-attention, and (ii) a 2.5D slice-conditioned U-Net that super-resolves each slice independently while conditioning on an adjacent slice for inter-slice context. Both models employ continuous-sigma noise conditioning following Karras et al. and are trained on the NKI cohort of the FOMO60K dataset. On a held-out test set of 5 subjects (6 volumes, 993 slices), the 3D model achieves 37.75 dB PSNR, 0.997 SSIM, and 0.020 LPIPS, improving on the off-the-shelf pretrained EDSR baseline (35.57 dB / 0.024 LPIPS) and the 2.5D variant (35.82 dB) across all three metrics under the same test data and degradation pipeline.

---

### EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Models

Authors: Jiayi Chen, Yasmeen George, Winston Chong, Jianfei Cai
Published: 2026-03-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14666v1

Deploying foundational medical Segment Anything Models (SAMs) via test-time adaptation (TTA) is challenging under large distribution shifts, where test-time supervision is often unreliable. While active test-time adaptation (ATTA) introduces limited expert feedback to improve reliability, existing ATTA methods still suffer from unreliable uncertainty estimation and inefficient utilization of sparse annotations. To address these issues, we propose Evidential Active Test-Time Adaptation (EviATTA), which is, to our knowledge, the first ATTA framework tailored for medical SAMs. Specifically, we adopt the Dirichlet-based Evidential Modeling to decompose overall predictive uncertainty into distribution uncertainty and data uncertainty. Building on this decomposition, we design a Hierarchical Evidential Sampling strategy, where image-wise distribution uncertainty is used to select informative shifted samples, while distance-aware data uncertainty guides sparse pixel annotations to resolve data ambiguities. We further introduce Dual Consistency Regularization, which enforces progressive prompt consistency on sparsely labeled samples to better exploit sparse supervision and applies variational feature consistency on unlabeled samples to stabilize adaptation. Extensive experiments on six medical image segmentation datasets demonstrate that EviATTA consistently improves adaptation reliability with minimal expert feedback under both batch-wise and instance-wise test-time adaptation settings.

---

### Gradient Atoms: Unsupervised Discovery, Attribution and Steering of Model Behaviors via Sparse Decomposition of Training Gradients

Authors: J Rosser
Published: 2026-03-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.14665v2

Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. Moreover, existing TDA methods are supervised -- they require a predefined query behavior, then score every training document against it -- making them both expensive and unable to surface behaviors the user did not think to ask about. We present Gradient Atoms, an unsupervised method that decomposes per-document training gradients into sparse components ("atoms") via dictionary learning in a preconditioned eigenspace. Each atom captures a shared update direction induced by a cluster of functionally similar documents, directly recovering the collective structure that per-document methods do not address. Among 500 discovered atoms, the highest-coherence ones recover interpretable task-type behaviors -- refusal, arithmetic, yes/no classification, trivia QA -- without any behavioral labels. These atoms double as effective steering vectors: applying them as weight-space perturbations produces large, controllable shifts in model behavior (e.g., bulleted-list generation 33% to 94%; systematic refusal 50% to 0%). The method requires no query--document scoring stage, and scales independently of the number of query behaviors of interest. Code is available at https://github.com/jrosseruk/gradient_atoms.

---

### Punctuated Equilibria in Artificial Intelligence: The Institutional Scaling Law and the Speciation of Sovereign AI

Authors: Mark Baciak, Thomas A. Cellucci, Deanna M. Falkowski
Published: 2026-03-15
Categories: cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2603.14664v1

The dominant narrative of artificial intelligence development assumes that progress is continuous and that capability scales monotonically with model size. We challenge both assumptions. Drawing on punctuated equilibrium theory from evolutionary biology, we show that AI development proceeds not through smooth advancement but through extended periods of stasis interrupted by rapid phase transitions that reorganize the competitive landscape. We identify five such eras since 1943 and four epochs within the current Generative AI Era, each initiated by a discontinuous event -- from the transformer architecture to the DeepSeek Moment -- that rendered the prior paradigm subordinate. To formalize the selection pressures driving these transitions, we develop the Institutional Fitness Manifold, a mathematical framework that evaluates AI systems along four dimensions: capability, institutional trust, affordability, and sovereign compliance. The central result is the Institutional Scaling Law, which proves that institutional fitness is non-monotonic in model scale. Beyond an environment-specific optimum, scaling further degrades fitness as trust erosion and cost penalties outweigh marginal capability gains. This directly contradicts classical scaling laws and carries a strong implication: orchestrated systems of smaller, domain-adapted models can mathematically outperform frontier generalists in most institutional deployment environments. We derive formal conditions under which this inversion holds and present supporting empirical evidence spanning frontier laboratory dynamics, post-training alignment evolution, and the rise of sovereign AI as a geopolitical selection pressure.

---

### VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Authors: Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal
Published: 2026-03-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14659v2

Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.

---

### VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Authors: Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal
Published: 2026-03-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14659v1

Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.

---

### Human-AI Ensembles Improve Deepfake Detection in Low-to-Medium Quality Videos

Authors: Marco Postiglione, Isabel Gortner, V. S. Subrahmanian
Published: 2026-03-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14658v1

Deepfake detection is widely framed as a machine learning problem, yet how humans and AI detectors compare under realistic conditions remains poorly understood. We evaluate 200 human participants and 95 state-of-the-art AI detectors across two datasets: DF40, a standard benchmark, and CharadesDF, a novel dataset of videos of everyday activities. CharadesDF was recorded using mobile phones leading to low/moderate quality videos compared to the more professionally captured DF40. Humans outperform AI detectors on both datasets, with the gap widening in the case of CharadesDF where AI accuracy collapses to near chance (0.537) while humans maintain robust performance (0.784). Human and AI errors are complementary: humans miss high-quality deepfakes while AI detectors flag authentic videos as fake, and hybrid human-AI ensembles reduce high-confidence errors. These findings suggest that effective real-world deepfake detection, especially in non-professionally produced videos, requires human-AI collaboration rather than AI algorithms alone.

---

### EARCP: Self-Regulating Coherence-Aware Ensemble Architecture for Sequential Decision Making -- Ensemble Auto-Regule par Coherence et Performance

Authors: Mike Amega
Published: 2026-03-15
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.14651v1

We present EARCP (Ensemble Auto-Régulé par Cohérence et Performance), a novel ensemble architecture that dynamically weights heterogeneous expert models based on both their individual performance and inter-model coherence. Unlike traditional ensemble methods that rely on static or offline-learned combinations, EARCP continuously adapts model weights through a principled online learning mechanism that balances exploitation of high-performing models with exploration guided by consensus signals. The architecture combines theoretical foundations from multiplicative weight update algorithms with a novel coherence-based regularization term, providing both theoretical guarantees through regret bounds and practical robustness in non-stationary environments. We formalize the EARCP framework, prove sublinear regret bounds of O(sqrt(T log M)) under standard assumptions, and demonstrate its effectiveness through empirical evaluation on sequential prediction tasks including time series forecasting, activity recognition, and financial prediction. The architecture is designed as a general-purpose framework applicable to any domain requiring ensemble learning with temporal dependencies. An open-source implementation is available at https://github.com/Volgat/earcp and via PyPI (pip install earcp).

---

### A Methodology for Thermal Limit Bias Predictability Through Artificial Intelligence

Authors: Anirudh Tunga, Michael J. Mueterthies, Jonathan Nistor
Published: 2026-03-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.14648v1

Nuclear power plant operators face significant challenges due to unpredictable deviations between offline and online thermal limits, a phenomenon known as thermal limit bias, which leads to conservative design margins, increased fuel costs, and operational inefficiencies. This work presents a deep learning based methodology to predict and correct this bias for Boiling Water Reactors (BWRs), focusing on the Maximum Fraction of Limiting Power Density (MFLPD) metric used to track the Linear Heat Generation Rate (LHGR) limit. The proposed model employs a fully convolutional encoder decoder architecture, incorporating a feature fusion network to predict corrected MFLPD values closer to online measurements. Evaluated across five independent fuel cycles, the model reduces the mean nodal array error by 74 percent, the mean absolute deviation in limiting values by 72 percent, and the maximum bias by 52 percent compared to offline methods. These results demonstrate the model's potential to meaningfully improve fuel cycle economics and operational planning, and a commercial variant has been deployed at multiple operating BWRs.

---

### TopoCL: Topological Contrastive Learning for Medical Imaging

Authors: Guangyu Meng, Pengfei Gu, Peixian Liang, John P. Lalor, Erin Wolf Chambers, Danny Z. Chen
Published: 2026-03-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14647v1

Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g., connectivity patterns, boundary configurations, cavity formations) that provide valuable cues for medical image analysis. To address this limitation, we propose a new topological CL framework (TopoCL) that explicitly exploits topological structures during contrastive learning for medical imaging. Specifically, we first introduce topology-aware augmentations that control topological perturbations using a relative bottleneck distance between persistence diagrams, preserving medically relevant topological properties while enabling controlled structural variations. We then design a Hierarchical Topology Encoder that captures topological features through self-attention and cross-attention mechanisms. Finally, we develop an adaptive mixture-of-experts (MoE) module to dynamically integrate visual and topological representations. TopoCL can be seamlessly integrated with existing CL methods. We evaluate TopoCL on five representative CL methods (SimCLR, MoCo-v3, BYOL, DINO, and Barlow Twins) and five diverse medical image classification datasets. The experimental results show that TopoCL achieves consistent improvements: an average gain of +3.26% in linear probe classification accuracy with strong statistical significance, verifying its effectiveness.

---

### Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models

Authors: Thuy Ngoc Nguyen, Duy Nhat Phan, Cleotilde Gonzalez
Published: 2026-03-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.14646v1

Theory of Mind (ToM) is central to social cognition and human-AI interaction, and Large Language Models (LLMs) have been used to help understand and represent ToM. However, most evaluations treat ToM as a static judgment at a single moment, primarily relying on tests of false beliefs. This overlooks a key dynamic dimension of ToM: the ability to represent, update, and retrieve others' beliefs over time. We investigate dynamic ToM as a temporally extended representational memory problem, asking whether LLMs can track belief trajectories across interactions rather than only inferring current beliefs. We introduce DToM-Track, an evaluation framework to investigate temporal belief reasoning in controlled multiturn conversations, testing the recall of beliefs held prior to an update, the inference of current beliefs, and the detection of belief change. Using LLMs as computational probes, we find a consistent asymmetry: models reliably infer an agent's current belief but struggle to maintain and retrieve prior belief states once updates occur. This pattern persists across LLM model families and scales, and is consistent with recency bias and interference effects well documented in cognitive science. These results suggest that tracking belief trajectories over time poses a distinct challenge beyond classical false-belief reasoning. By framing ToM as a problem of temporal representation and retrieval, this work connects ToM to core cognitive mechanisms of memory and interference and exposes the implications for LLM models of social reasoning in extended human-AI interactions.

---

### Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion

Authors: Mang Ning, Mingxiao Li, Le Zhang, Lanmiao Liu, Matthew B. Blaschko, Albert Ali Salah, Itir Onal Ertugrul
Published: 2026-03-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14645v1

In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial frequencies, and that the power-law power spectral density (PSD) of natural images makes this bias perceptually beneficial. Motivated by this result, we propose the \emph{Spectrum Matching Hypothesis}: latents with superior diffusability should (i) follow a flattened power-law PSD (\emph{Encoding Spectrum Matching}, ESM) and (ii) preserve frequency-to-frequency semantic correspondence through the decoder (\emph{Decoding Spectrum Matching}, DSM). In practice, we apply ESM by matching the PSD between images and latents, and DSM via shared spectral masking with frequency-aligned reconstruction. Importantly, Spectrum Matching provides a unified view that clarifies prior observations of over-noisy or over-smoothed latents, and interprets several recent methods as special cases (e.g., VA-VAE, EQ-VAE). Experiments suggest that Spectrum Matching yields superior diffusion generation on CelebA and ImageNet datasets, and outperforms prior approaches. Finally, we extend the spectral view to representation alignment (REPA): we show that the directional spectral energy of the target representation is crucial for REPA, and propose a DoG-based method to further improve the performance of REPA. Our code is available https://github.com/forever208/SpectrumMatching.

---

### LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol

Authors: Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci
Published: 2026-03-15
Categories: eess.IV, cs.CV, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2603.14644v3

Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical annotations, and vendor diversity, hindering the development of robust models. We introduce LUMINA, a curated, multi-vendor FFDM dataset that explicitly encodes acquisition energy and vendor metadata to capture clinically relevant appearance variations often overlooked in existing benchmarks. This dataset contains 1824 images from 468 patients (960 benign, 864 malignant), with pathology-confirmed labels, BI-RADS assessments, and breast-density annotations. LUMINA spans six acquisition systems and includes both high- and low-energy imaging styles, enabling systematic analysis of vendor- and energy-induced domain shifts. To address these variations, we propose a foreground-only pixel-space alignment method (''energy harmonization'') that maps images to a low-energy reference while preserving lesion morphology. We benchmark CNN and transformer models on three clinically relevant tasks: diagnosis (benign vs. malignant), BI-RADS classification, and density estimation. Two-view models consistently outperform single-view models. EfficientNet-B0 achieves an AUC of 93.54% for diagnosis, while Swin-T achieves the best macro-AUC of 89.43% for density prediction. Harmonization improves performance across architectures and produces more localized Grad-CAM responses. Overall, LUMINA provides (1) a vendor-diverse benchmark and (2) a model-agnostic harmonization framework for reliable and deployable mammography AI.

---

### Argumentation for Explainable and Globally Contestable Decision Support with LLMs

Authors: Adam Dejl, Matthew Williams, Francesca Toni
Published: 2026-03-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.14643v2

Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has taken meaningful steps towards addressing these issues by augmenting LLMs with post-hoc reasoning based on computational argumentation, providing faithful explanations and enabling users to contest incorrect decisions. However, this paradigm is limited to pre-defined binary choices and only supports local contestation for specific instances, leaving the underlying decision logic unchanged and prone to repeated mistakes. In this paper, we introduce ArgEval, a framework that shifts from instance-specific reasoning to structured evaluation of general decision options. Rather than mining arguments solely for individual cases, ArgEval systematically maps task-specific decision spaces, builds corresponding option ontologies, and constructs general argumentation frameworks (AFs) for each option. These frameworks can then be instantiated to provide explainable recommendations for specific cases while still supporting global contestability through modification of the shared AFs. We investigate the effectiveness of ArgEval on treatment recommendation for glioblastoma, an aggressive brain tumour, and show that it can produce explainable guidance aligned with clinical practice.

---

### Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection

Authors: Seoyoung Lee, Shaekh Mohammad Shithil, Durgakant Pushp, Lantao Liu, Zhangyang Wang
Published: 2026-03-15
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.14639v2

Inspection of confined infrastructure such as culverts often requires accessing hidden spaces whose entrances are reachable primarily from elevated viewpoints. Aerial-ground cooperation enables a UAV to deploy a compact UGV for interior exploration, but selecting a suitable deployment region from aerial observations requires metric terrain reasoning involving scale ambiguity, reconstruction uncertainty, and terrain semantics. We present a metric RGB-based geometric-semantic reconstruction and traversability analysis framework for aerial-to-ground hidden space inspection. A feed-forward multi-view RGB reconstruction backbone produces dense geometry, while temporally consistent semantic segmentation yields a 3D semantic map. To enable deployment-relevant measurements without requiring LiDAR-based dense mapping, we introduce an embodied motion prior that recovers metric scale by aligning predicted camera motion with onboard platform egomotion. From the metrically grounded reconstruction, we construct a confidence-aware geometric-semantic traversability map and evaluate candidate deployment zones under reachability constraints. Experiments on a tethered UAV-UGV platform demonstrate reliable deployment-zone identification in hidden space scenarios.

---

### Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

Authors: Lok-Lam Ieong, Chia-Chien Chen, Chih-Kai Yang, Yu-Han Huang, An-Yu Cheng, Hung-yi Lee
Published: 2026-03-15
Categories: cs.SD, cs.AI, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2603.14636v1

Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free approach to improve LALM reasoning. We introduce three strategies using diverse information sources and evaluate them across four LALMs and four benchmarks. Results show general accuracy gains up to 4.4% over CoT prompting. Notably, we identify a cross-modal transfer where steering vectors derived from few text samples effectively guide speech-based reasoning, demonstrating high data efficiency. We also examine hyperparameter sensitivity to understand the robustness of these approaches. Our findings position model steering as a practical direction for strengthening LALM reasoning.

---

### Compute Allocation for Reasoning-Intensive Retrieval Agents

Authors: Sreeja Apparaju, Nilesh Gupta
Published: 2026-03-15
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.14635v2

As agents operate over long horizons, their memory stores grow continuously, making retrieval critical to accessing relevant information. Many agent queries require reasoning-intensive retrieval, where the connection between query and relevant documents is implicit and requires inference to bridge. LLM-augmented pipelines address this through query expansion and candidate re-ranking, but introduce significant inference costs. We study computation allocation in reasoning-intensive retrieval pipelines using the BRIGHT benchmark and Gemini 2.5 model family. We vary model capacity, inference-time thinking, and re-ranking depth across query expansion and re-ranking stages. We find that re-ranking benefits substantially from stronger models (+7.5 NDCG@10) and deeper candidate pools (+21% from $k$=10 to 100), while query expansion shows diminishing returns beyond lightweight models (+1.1 NDCG@10 from weak to strong). Inference-time thinking provides minimal improvement at either stage. These results suggest that compute should be concentrated on re-ranking rather than distributed uniformly across pipeline stages.

---

### Continual Few-shot Adaptation for Synthetic Fingerprint Detection

Authors: Joseph Geo Benjamin, Anil K. Jain, Karthik Nandakumar
Published: 2026-03-15
Categories: cs.CV, cs.IT
arXiv: https://arxiv.org/abs/2603.14632v2

The quality and realism of synthetically generated fingerprint images have increased significantly over the past decade fueled by advancements in generative artificial intelligence (GenAI). This has exacerbated the vulnerability of fingerprint recognition systems to data injection attacks, where synthetic fingerprints are maliciously inserted during enrollment or authentication. Hence, there is an urgent need for methods to detect if a fingerprint image is real or synthetic. While it is straightforward to train deep neural network (DNN) models to classify images as real or synthetic, often such DNN models overfit the training data and fail to generalize well when applied to synthetic fingerprints generated using unseen GenAI models. In this work, we formulate synthetic fingerprint detection as a continual few-shot adaptation problem, where the objective is to rapidly evolve a base detector to identify new types of synthetic data. To enable continual few-shot adaptation, we employ a combination of binary cross-entropy and supervised contrastive (applied to the feature representation) losses and replay a few samples from previously known styles during fine-tuning to mitigate catastrophic forgetting. Experiments based on several DNN backbones (as feature extractors) and a variety of real and synthetic fingerprint datasets indicate that the proposed approach achieves a good trade-off between fast adaptation for detecting unseen synthetic styles and forgetting of known styles.

---

### Anterior's Approach to Fairness Evaluation of Automated Prior Authorization System

Authors: Sai P. Selvaraj, Khadija Mahmoud, Anuj Iravane
Published: 2026-03-15
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.14631v1

Increasing staffing constraints and turnaround-time pressures in Prior authorization (PA) have led to increasing automation of decision systems to support PA review. Evaluating fairness in such systems poses unique challenges because legitimate clinical guidelines and medical necessity criteria often differ across demographic groups, making parity in approval rates an inappropriate fairness metric. We propose a fairness evaluation framework for prior authorization models based on model error rates rather than approval outcomes. Using 7,166 human-reviewed cases spanning 27 medical necessity guidelines, we assessed consistency in sex, age, race/ethnicity, and socioeconomic status. Our evaluation combined error-rate comparisons, tolerance-band analysis with a predefined $\pm$5 percentage-point margin, statistical power evaluation, and protocol-controlled logistic regression. Across most demographics, model error rates were consistent, and confidence intervals fell within the predefined tolerance band, indicating no meaningful performance differences. For race/ethnicity, point estimates remain small, but subgroup sample sizes were limited, resulting in wide confidence intervals and underpowered tests, with inconclusive evidence within the dataset we explored. These findings illustrate a rigorous and regulator-aligned approach to fairness evaluation in administrative healthcare AI systems.

---

### ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting

Authors: Peng Zhang
Published: 2026-03-15
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.14629v1

ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv, extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware related-work section. The system combines FastAPI, Next.js, DSPy, SQLite, and Qdrant in a local-first architecture that supports bring-your-own-key model access and remote-or-local embeddings. This paper describes the system design, typed agent interfaces, persistence and history-search mechanisms, and the engineering tradeoffs involved in building a transparent research assistant. Rather than claiming algorithmic novelty, we present ResearchPilot as a systems contribution and evaluate it through automated tests and end-to-end local runs. We discuss limitations including external API rate limits, abstract-only extraction, incomplete corpus coverage, and the lack of citation verification.

---

### s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs

Authors: Balaji Rao, John Harrison, Soonho Kong, Juneyoung Lee, Carlo Lipizzi
Published: 2026-03-15
Categories: cs.PL, cs.AI, cs.CR, cs.LO
arXiv: https://arxiv.org/abs/2603.14628v2

Neurosymbolic approaches leveraging Large Language Models (LLMs) with formal methods have recently achieved strong results on mathematics-oriented theorem-proving benchmarks. However, success on competition-style mathematics does not by itself demonstrate the ability to construct proofs about real-world implementations. We address this gap with a benchmark derived from an industrial cryptographic library whose assembly routines are already verified in HOL Light. s2n-bignum is a library used at AWS for providing fast assembly routines for cryptography, and its correctness is established by formal verification. The task of formally verifying this library has been a significant achievement for the Automated Reasoning Group. It involved two tasks: (1) precisely specifying the correct behavior of a program as a mathematical proposition, and (2) proving that the proposition is correct. In the case of s2n-bignum, both tasks were carried out by human experts. In \textit{s2n-bignum-bench}, we provide the formal specification and ask the LLM to generate a proof script that is accepted by HOL Light within a fixed proof-check timeout. To our knowledge, \textit{s2n-bignum-bench} is the first public benchmark focused on machine-checkable proof synthesis for industrial low-level cryptographic assembly routines in HOL Light. This benchmark provides a challenging and practically relevant testbed for evaluating LLM-based theorem proving beyond competition mathematics. The code to set up and use the benchmark is available here: \href{https://github.com/kings-crown/s2n-bignum-bench}{s2n-bignum-bench}.

---

### EcoFair-CH-MARL: Scalable Constrained Hierarchical Multi-Agent RL with Real-Time Emission Budgets and Fairness Guarantees

Authors: Saad Alqithami
Published: 2026-03-15
Categories: cs.MA, cs.AI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2603.14625v1

Global decarbonisation targets and tightening market pressures demand maritime logistics solutions that are simultaneously efficient, sustainable, and equitable. We introduce EcoFair-CH-MARL, a constrained hierarchical multi-agent reinforcement learning framework that unifies three innovations: (i) a primal-dual budget layer that provably bounds cumulative emissions under stochastic weather and demand; (ii) a fairness-aware reward transformer with dynamically scheduled penalties that enforces max-min cost equity across heterogeneous fleets; and (iii) a two-tier policy architecture that decouples strategic routing from real-time vessel control, enabling linear scaling in agent count. New theoretical results establish O(\sqrt{T}) regret for both constraint violations and fairness loss. Experiments on a high-fidelity maritime digital twin (16 ports, 50 vessels) driven by automatic identification system traces, plus an energy-grid case study, show up to 15% lower emissions, 12% higher through-put, and a 45% fair-cost improvement over state-of-the-art hierarchical and constrained MARL baselines. In addition, EcoFair-CH-MARL achieves stronger equity (lower Gini and higher min-max welfare) than fairness-specific MARL baselines (e.g., SOTO, FEN), and its modular design is compatible with both policy- and value-based learners. EcoFair-CH-MARL therefore advances the feasibility of large-scale, regulation-compliant, and socially responsible multi-agent coordination in safety-critical domains.

---

### Proactive Routing to Interpretable Surrogates with Distribution-Free Safety Guarantees

Authors: Iqtedar Uddin, Mazin Khider, André Bauer
Published: 2026-03-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.14623v1

Model routing determines whether to use an accurate black-box model or a simpler surrogate that approximates it at lower cost or greater interpretability. In deployment settings, practitioners often wish to restrict surrogate use to inputs where its degradation relative to a reference model is controlled. We study proactive (input-based) routing, in which a lightweight gate selects the model before either runs, enabling distribution-free control of the fraction of routed inputs whose degradation exceeds a tolerance τ. The gate is trained to distinguish safe from unsafe inputs, and a routing threshold is chosen via Clopper-Pearson conformal calibration on a held-out set, guaranteeing that the routed-set violation rate is at most α with probability 1-δ. We derive a feasibility condition linking safe routing to the base safe rate π and risk budget α, along with sufficient AUC thresholds ensuring that feasible routing exists. Across 35 OpenML datasets and multiple black-box model families, gate-based conformal routing maintains controlled violation while achieving substantially higher coverage than regression conformal and naive baselines. We further show that probabilistic calibration primarily affects routing efficiency rather than distribution-free validity.

---

### A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans

Authors: Aadit Nilay, Bhavesh Thapar, Anant Agrawal, Mohammad Nayeem Teli
Published: 2026-03-15
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2603.14621v1

The COVID-19 pandemic exposed critical limitations in diagnostic workflows: RT-PCR tests suffer from slow turnaround times and high false-negative rates, while CT-based screening offers faster complementary diagnosis but requires expert radiological interpretation. Deploying automated CT analysis across multiple hospital centres introduces further challenges, as differences in scanner hardware, acquisition protocols, and patient populations cause substantial domain shift that degrades single-model performance. To address these challenges, we present a heterogeneous ensemble of nine models spanning three inference paradigms: (1) a self-supervised DINOv2 Vision Transformer with slice-level sigmoid aggregation, (2) a RadImageNet-pretrained DenseNet-121 with slice-level sigmoid averaging, and (3) seven Gated Attention Multiple Instance Learning models using EfficientNet-B3, ConvNeXt-Tiny, and EfficientNetV2-S backbones with scan-level softmax classification. Ensemble diversity is further enhanced through random-seed variation and Stochastic Weight Averaging. We address severe overfitting, reducing the validation-to-training loss ratio from 35x to less than 3x, through a combination of Focal Loss, embedding-level Mixup, and domain-aware augmentation. Model outputs are fused via score-weighted probability averaging and calibrated with per-source threshold optimization. The final ensemble achieves an average macro F1 of 0.9280 across four hospital centres, outperforming the best single model (F1=0.8969) by +0.031, demonstrating that heterogeneous architectures combined with source-aware calibration are essential for robust multi-site medical image classification.

---

### LLM-Augmented Release Intelligence: Automated Change Summarization and Impact Analysis in Cloud-Native CI/CD Pipelines

Authors: Happy Bhati
Published: 2026-03-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.14619v1

Cloud-native software delivery platforms orchestrate releases through complex, multi-stage pipelines composed of dozens of independently versioned tasks. When code is promoted between environments -- development to staging, staging to production -- engineering teams need timely, accurate communication about what changed and what downstream components are affected. Manual preparation of such release communication is slow, inconsistent, and particularly error-prone in repositories where a single promotion may bundle contributions from many authors across numerous pipeline tasks. We present a framework for AI-augmented release intelligence that combines three capabilities: (1) automated commit collection with semantic filtering to surface substantive changes while suppressing routine maintenance, (2) structured large language model summarization that produces categorized, stakeholder-oriented promotion reports, and (3) static task-pipeline dependency analysis that maps modified tasks to every pipeline they participate in, quantifying the blast radius of each change. The framework is integrated directly into the CI/CD promotion workflow and operates as a post-promotion step triggered by GitHub Actions. We describe the architecture and implementation within a production Kubernetes-native release platform that manages over sixty Tekton tasks across more than twenty release pipelines. Through concrete walkthrough examples and qualitative comparison with recent tools such as SmartNote and VerLog, we discuss the distinctive requirements of internal promotion communication versus user-facing release notes and identify open challenges for LLM-driven release engineering.

---

### Make it SING: Analyzing Semantic Invariants in Classifiers

Authors: Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa
Published: 2026-03-15
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2603.14610v2

All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal vision language models. This allows us to obtain natural language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.

---

### GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data

Authors: Roger Ferrod, Maël Lecene, Krishna Sapkota, George Leifman, Vered Silverman, Genady Beryozkin, Sylvain Lobry
Published: 2026-03-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14609v2

Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal Large Language Models exhibit critical deficiencies in fine-grained spatial understanding within Remote Sensing, primarily due to a reliance on limited or repurposed legacy datasets. To bridge this gap, we introduce a large-scale dataset grounded in verifiable cadastral vector data, comprising 3.8 million annotated objects across 510k high-resolution images with 135 granular semantic categories. We validate this resource through a comprehensive instruction-tuning benchmark spanning seven spatial reasoning tasks. Our evaluation establishes a robust baseline using a standard LLaVA architecture. We show that while current RS-specialized and commercial models (e.g., Gemini) struggle in zero-shot settings, high-fidelity supervision effectively bridges this gap, enabling standard architectures to master fine-grained spatial grounding without complex architectural modifications.

---

### Delightful Policy Gradient

Authors: Ian Osband
Published: 2026-03-15
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2603.14608v1

Standard policy gradients weight each sampled action by advantage alone, regardless of how likely that action was under the current policy. This creates two pathologies: within a single decision context (e.g. one image or prompt), a rare negative-advantage action can disproportionately distort the update direction; across many such contexts in a batch, the expected gradient over-allocates budget to contexts the policy already handles well. We introduce the \textit{Delightful Policy Gradient} (DG), which gates each term with a sigmoid of \emph{delight}, the product of advantage and action surprisal (negative log-probability). For $K$-armed bandits, DG provably improves directional accuracy in a single context and, across multiple contexts, shifts the expected gradient strictly closer to the supervised cross-entropy oracle. This second effect is not variance reduction: it persists even with infinite samples. Empirically, DG outperforms REINFORCE, PPO, and advantage-weighted baselines across MNIST, transformer sequence modeling, and continuous control, with larger gains on harder tasks.

---

### Tactile Modality Fusion for Vision-Language-Action Models

Authors: Charlotte Morissette, Amin Abyaneh, Wei-Di Chang, Anas Houssaini, David Meger, Hsiu-Chin Lin, Jonathan Tremblay, Gregory Dudek
Published: 2026-03-15
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.14604v2

We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While advances in VLAs have introduced robot policies that are both generalizable and semantically grounded, these models mainly rely on vision-based perception. Vision alone, however, cannot capture the complex interaction dynamics that occur during contact-rich manipulation, including contact forces, surface friction, compliance, and shear. While recent attempts to integrate tactile signals into VLA models often increase complexity through token concatenation or large-scale pretraining, the heavy computational demands of behaviour models necessitate lightweight fusion strategies. To address these challenges, TacFiLM outlines a post-training finetuning approach that conditions intermediate visual features on pretrained tactile representations using feature-wise linear modulation (FiLM). Experimental results on insertion and drawer opening tasks demonstrate consistent improvements in success rate, direct task performance, completion time, and force stability across both in-distribution and out-of-distribution tasks. Together, these results support our method as an effective approach to integrating tactile signals into VLA models, improving contact-rich manipulation behaviours. Project page: https://charliem7.github.io/projects/TacFilm/

---

### PA3: Policy-Aware Agent Alignment through Chain-of-Thought

Authors: Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya
Published: 2026-03-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.14602v3

Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the 'needle-in-a-haystack' problem. To address these challenges, we propose a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context. Furthermore, we introduce a novel Policy Recall reward based on the Jaccard score and a Hallucination Penalty for GRPO training. Altogether, our best model outperforms the baseline by 16 points and surpasses comparable in-context baselines of similar model size by 3 points, while using 40% fewer words.

---

### PA3: Policy-Aware Agent Alignment through Chain-of-Thought

Authors: Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya
Published: 2026-03-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.14602v2

Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "needle-in-the-haystack" problem. To address these challenges, we propose a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context. Furthermore, we introduce a novel PolicyRecall reward based on the Jaccard score and a Hallucination Penalty for GRPO training. Altogether, our best model outperforms the baseline by 16 points and surpasses comparable in-context baselines of similar model size by 3 points, while using 40% fewer words.

---

### $K-$means with learned metrics

Authors: Pablo Groisman, Matthieu Jonckheere, Jordan Serres, Mariela Sued
Published: 2026-03-15
Categories: math.ST, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2603.14601v2

We study the Fréchet $k-$means of a metric measure space when both the measure and the distance are unknown and have to be estimated. We prove a general result that states that the $k-$means are continuous with respect to the measured Gromov-Hausdorff topology. In this situation, we also prove a stability result for the Voronoi clusters they determine. We do not assume uniqueness of the set of $k-$means, but when it is unique, the results are stronger. This framework provides a unified approach to proving consistency for a wide range of metric learning procedures. As concrete applications, we obtain new consistency results for several important estimators that were previously unestablished, even when $k=1$. These include $k-$means based on: (i) Isomap and Fermat geodesic distances on manifolds, (ii) difussion distances, (iii) Wasserstein distances computed with respect to learned ground metrics. Finally, we consider applications beyond the statistical inference paradigm like (iv) first passage percolation and (v) discrete approximations of length spaces.

---

### A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study

Authors: Jingyi Liu, Jian Guo, Eberhard Gill
Published: 2026-03-15
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.14600v1

Reinforcement learning algorithms have been widely used in dynamic and control systems. However, interpreting their internal learning behavior remains a challenge. In the authors' previous work, a critic match loss landscape visualization method was proposed to study critic training. This study extends that method into a framework which provides a multi-perspective view of the learning dynamics, clarifying how value estimation, policy optimization, and temporal-difference (TD) signals interact during training. The proposed framework includes four complementary components; a three-dimensional reconstruction of the critic match loss surface that shows how TD targets shape the optimization geometry; an actor loss landscape under a frozen critic that reveals how the policy exploits that geometry; a trajectory combining time, Bellman error, and policy weights that indicates how updates move across the surface; and a state-TD map that identifies the state regions that drive those updates. The Action-Dependent Heuristic Dynamic Programming (ADHDP) algorithm for spacecraft attitude control is used as a case study. The framework is applied to compare several ADHDP variants and shows how training stabilizers and target updates change the optimization landscape and affect learning stability. Therefore, the proposed framework provides a systematic and interpretable tool for analyzing reinforcement learning behavior across algorithmic designs.

---

### D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing

Authors: Yuru Song, Qi Xin
Published: 2026-03-15
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2603.14597v1

Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired architecture that decouples short-term interaction from cognitive restructuring via a Fast/Slow routing system based on Reward Prediction Error (RPE). A lightweight Critic Router evaluates stimuli for Surprise and Utility. Routine, low-RPE inputs are bypassed or cached in an O(1) fast-access buffer. Conversely, high-RPE inputs, such as factual contradictions or preference shifts, trigger a "dopamine" signal, activating the O(N) memory evolution pipeline to reshape the agent's knowledge graph. To evaluate performance under realistic conditions, we introduce the LoCoMo-Noise benchmark, which injects controlled conversational noise into long-term sessions. Evaluations demonstrate that D-MEM reduces token consumption by over 80%, eliminates O(N^2) bottlenecks, and outperforms baselines in multi-hop reasoning and adversarial resilience. By selectively gating cognitive restructuring, D-MEM provides a scalable, cost-efficient foundation for lifelong agentic memory.

---

### Scaling the Explanation of Multi-Class Bayesian Network Classifiers

Authors: Yaofang Zhang, Adnan Darwiche
Published: 2026-03-15
Categories: cs.AI, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2603.14594v1

We propose a new algorithm for compiling Bayesian network classifier (BNC) into class formulas. Class formulas are logical formulas that represent a classifier's input-output behavior, and are crucial in the recent line of work that uses logical reasoning to explain the decisions made by classifiers. Compared to prior work on compiling class formulas of BNCs, our proposed algorithm is not restricted to binary classifiers, shows significant improvement in compilation time, and outputs class formulas as negation normal form (NNF) circuits that are OR-decomposable, which is an important property when computing explanations of classifiers.

---

### Parameter-Efficient Quality Estimation via Frozen Recursive Models

Authors: Umar Abubacar, Roman Bauer, Diptesh Kanojia
Published: 2026-03-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.14593v1

Tiny Recursive Models (TRM) achieve strong results on reasoning tasks through iterative refinement of a shared network. We investigate whether these recursive mechanisms transfer to Quality Estimation (QE) for low-resource languages using a three-phase methodology. Experiments on $8$ language pairs on a low-resource QE dataset reveal three findings. First, TRM's recursive mechanisms do not transfer to QE. External iteration hurts performance, and internal recursion offers only narrow benefits. Next, representation quality dominates architectural choices, and lastly, frozen pretrained embeddings match fine-tuned performance while reducing trainable parameters by 37$\times$ (7M vs 262M). TRM-QE with frozen XLM-R embeddings achieves a Spearman's correlation of 0.370, matching fine-tuned variants (0.369) and outperforming an equivalent-depth standard transformer (0.336). On Hindi and Tamil, frozen TRM-QE outperforms MonoTransQuest (560M parameters) with 80$\times$ fewer trainable parameters, suggesting that weight sharing combined with frozen embeddings enables parameter efficiency for QE. We release the code publicly for further research. Code is available at https://github.com/surrey-nlp/TRMQE.

---

### A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions

Authors: Yiming Lei, Qiannan Shen, Junhao Song
Published: 2026-03-15
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2603.14592v1

Financial fraud detection in transaction networks involves modeling sparse anomalies, dynamic patterns, and severe class imbalance in the presence of temporal drift in the data. In real-world transaction systems, a suspicious transaction is rarely isolated: rather, legitimate and suspicious transactions are often connected through accounts, intermediaries or through temporal transaction sequences. Attribute-based or randomly partitioned learning pipelines are therefore insufficient to detect relationally structured fraud. STC-MixHop, a graph-based framework combining spatial multi-resolution propagation with lightweight temporal consistency modeling for anomaly and fraud detection in dynamic transaction networks. It integrates three components: a MixHop-inspired multi-scale neighborhood diffusion encoder a multi-scale neighborhood diffusion MixHop-based encoder for learning structural patterns; a spatial-temporal attention module coupling current and preceding graph snapshots to stabilize representations; and a temporally informed self-supervised pretraining strategy exploiting unlabeled transaction interactions to improve representation quality. We evaluate the framework primarily on the PaySim dataset under strict chronological splits, supplementing the analysis with Porto Seguro and FEMA data to probe cross-domain component behavior. Results show that STC-MixHop is competitive among graph methods and achieves strong screening-oriented recall under highly imbalanced conditions. The experiments also reveal an important boundary condition: when node attributes are highly informative, tabular baselines remain difficult to outperform. Graph structure contributes most clearly where hidden relational dependencies are operationally important. These findings support a stability-focused view of graph learning for financial fraud detection.

---

### FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference

Authors: Wilhelm Tranheden, Shahnawaz Ahmed, Devdatt Dubhashi, Jonna Matthiesen, Hannes von Essen
Published: 2026-03-15
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.14591v1

Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabulary sizes continue to grow rapidly, making the classification head a critical bottleneck that accounts for up to 60\% of model parameters, and 50\% of inference compute. We introduce FlashHead, the first efficient drop-in replacement for the dense classification head that is training-free and hardware-friendly. FlashHead builds on principles from information retrieval, reframing that computation at the output head as a retrieval problem rather than a dense classification over the full vocabulary. FlashHead introduces four key innovations: (1) a balanced clustering scheme that structures vocabulary partitions into compact hardware-efficient tensors, (2) extending multiprobe retrieval to language model heads, enabling thousands of clusters to be scored in parallel, (3) a novel inference-time sampling mechanism that extends retrieval beyond top tokens, enabling probabilistic sampling across the full vocabulary, and (4) selective quantization, enabling effective low-bit computation in the head. Experiments on Llama-3.2, Gemma-3, and Qwen-3 show that FlashHead delivers model-level inference speedups of up to \textbf{1.75x} which maintaining output accuracy compared to the original head. By overcoming the classification head bottleneck, FlashHead establishes a new benchmark for efficient inference and removes a key barrier to developing smaller, capable models for consumer hardware.

---

### Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning

Authors: Jingyi Liu, Jian Guo, Eberhard Gill
Published: 2026-03-15
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.14589v1

This work extends an established critic match loss landscape visualization method from online to off-policy reinforcement learning (RL), aiming to reveal the optimization geometry behind critic learning. Off-policy RL differs from stepwise online actor-critic learning in its replay-based data flow and target computation. Based on these two structural differences, the critic match loss landscape visualization method is adapted to the Soft Actor-Critic (SAC) algorithm by aligning the loss evaluation with its batch-based data flow and target computation, using a fixed replay batch and precomputed critic targets from the selected policy. Critic parameters recorded during training are projected onto a principal component plane, where the critic match loss is evaluated to form a 3-D landscape with an overlaid 2-D optimization path. Applied to a spacecraft attitude control problem, the resulting landscapes are analyzed both qualitatively and quantitatively using sharpness, basin area, and local anisotropy metrics, together with temporal landscape snapshots. Comparisons between convergent SAC, divergent SAC, and divergent Action-Dependent Heuristic Dynamic Programming (ADHDP) cases reveal distinct geometric patterns and optimization behaviors under different algorithmic structures. The results demonstrate that the adapted critic match loss visualization framework serves as a geometric diagnostic tool for analyzing critic optimization dynamics in replay-based off-policy RL-based control problems.

---

### SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory

Authors: Varun Pratap Bhardwaj
Published: 2026-03-15
Categories: cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.14588v1

Persistent memory is a central capability for AI agents, yet the mathematical foundations of memory retrieval, lifecycle management, and consistency remain unexplored. Current systems employ cosine similarity for retrieval, heuristic decay for salience, and provide no formal contradiction detection. We establish information-geometric foundations through three contributions. First, a retrieval metric derived from the Fisher information structure of diagonal Gaussian families, satisfying Riemannian metric axioms, invariant under sufficient statistics, and computable in O(d) time. Second, memory lifecycle formulated as Riemannian Langevin dynamics with proven existence and uniqueness of the stationary distribution via the Fokker-Planck equation, replacing hand-tuned decay with principled convergence guarantees. Third, a cellular sheaf model where non-trivial first cohomology classes correspond precisely to irreconcilable contradictions across memory contexts. On the LoCoMo benchmark, the mathematical layers yield +12.7 percentage points over engineering baselines across six conversations, reaching +19.9 pp on the most challenging dialogues. A four-channel retrieval architecture achieves 75% accuracy without cloud dependency. Cloud-augmented results reach 87.7%. A zero-LLM configuration satisfies EU AI Act data sovereignty requirements by architectural design. To our knowledge, this is the first work establishing information-geometric, sheaf-theoretic, and stochastic-dynamical foundations for AI agent memory systems.

---

### Texel Splatting: Perspective-Stable 3D Pixel Art

Authors: Dylan Ebert
Published: 2026-03-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14587v1

Rendering 3D scenes as pixel art requires that discrete pixels remain stable as the camera moves. Existing methods snap the camera to a grid. Under orthographic projection, this works: every pixel shifts by the same amount, and a single snap corrects all of them. Perspective breaks this. Pixels at different depths drift at different rates, and no single snap corrects all depths. Texel splatting avoids this entirely. Scene geometry is rendered into a cubemap from a fixed point in the world, and each texel is splatted to the screen as a world-space quad. Cubemap indexing gives rotation invariance. Grid-snapping the origin gives translation invariance. The primary limitation is that a fixed origin cannot see all geometry; disocclusion at probe boundaries remains an open tradeoff.

---

### The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation

Authors: Ilya Ilyankou, Stefano Cavazzi, James Haworth
Published: 2026-03-15
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.14586v1

As pedestrian navigation increasingly experiments with Generative AI, and in particular Large Language Models, the nature of routing risks transforming from a verifiable geometric task into an opaque, persuasive dialogue. While conversational interfaces promise personalisation, they introduce risks of manipulation and misplaced trust. We categorise these risks using a 2x2 framework based on intent and origin, distinguishing between intentional manipulations (dark patterns) and unintended harms (explainability pitfalls). We propose seamful design strategies to mitigate these harms. We suggest that one robust way to operationalise trustworthy conversational navigation is through neuro-symbolic architecture, where verifiable pathfinding algorithms ground GenAI's persuasive capabilities, ensuring systems explain their limitations and incentives as clearly as they explain the route.

---

### Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage

Authors: Rahul Bera, Rakesh Nadig, Onur Mutlu
Published: 2026-03-15
Categories: cs.AR, cs.AI, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2603.14583v1

Despite the data-rich environment in which memory systems of modern computing platforms operate, many state-of-the-art architectural policies employed in the memory system rely on static, human-designed heuristics that fail to truly adapt to the workload and system behavior via principled learning methodologies. In this article, we propose a fundamentally different design approach: using lightweight and practical machine learning (ML) methods to enable adaptive, data-driven control throughout the memory hierarchy. We present three ML-guided architectural policies: (1) Pythia, a reinforcement learning-based data prefetcher for on-chip caches, (2) Hermes, a perceptron learning-based off-chip predictor for multi-level cache hierarchies, and (3) Sibyl, a reinforcement learning-based data placement policy for hybrid storage systems. Our evaluation shows that Pythia, Hermes, and Sibyl significantly outperform the best-prior human-designed policies, while incurring modest hardware overheads. Collectively, this article demonstrates that integrating adaptive learning into memory subsystems can lead to intelligent, self-optimizing architectures that unlock performance and efficiency gains beyond what is possible with traditional human-designed approaches.

---

### Medical Image Spatial Grounding with Semantic Sampling

Authors: Andrew Seohwan Yu, Mohsen Hariri, Kunio Nakamura, Mingrui Yang, Xiaojuan Li, Vipin Chaudhary
Published: 2026-03-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.14579v3

Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs represent a bridge between object detection and segmentation, and report understanding and generation. However, spatial grounding of anatomical structures in the three-dimensional space of medical images poses many unique challenges. In this study, we examine image modalities, slice directions, and coordinate systems as differentiating factors for vision components of VLMs, and the use of anatomical, directional, and relational terminology as factors for the language components. We then demonstrate that visual and textual prompting systems such as labels, bounding boxes, and mask overlays have varying effects on the spatial grounding ability of VLMs. To enable measurement and reproducibility, we introduce MIS-Ground, a benchmark that comprehensively tests a VLM for vulnerabilities against specific modes of Medical Image Spatial Grounding. We release MIS-Ground to the public at github.com/asy51/mis-ground. In addition, we present MIS-SemSam, a low-cost, inference-time, and model-agnostic optimization of VLMs that improves their spatial grounding ability with the use of Semantic Sampling. We find that MIS-SemSam improves the accuracy of Qwen3-VL-32B on MIS-Ground by 13.06%.

---

### Power-Law Spectrum of the Random Feature Model

Authors: Elliot Paquette, Ke Liang Xiao, Yizhe Zhu
Published: 2026-03-15
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2603.14578v1

Scaling laws for neural networks, in which the loss decays as a power-law in the number of parameters, data, and compute, depend fundamentally on the spectral structure of the data covariance, with power-law eigenvalue decay appearing ubiquitously in vision and language tasks. A central question is whether this spectral structure is preserved or destroyed when data passes through the basic building block of a neural network: a random linear projection followed by a nonlinear activation. We study this question for the random feature model: given data $x \sim N(0,H)\in \mathbb{R}^v$ where $H$ has $α$-power-law spectrum ($λ_j(H ) \asymp j^{-α}$, $α> 1$), a Gaussian sketch matrix $W \in \mathbb{R}^{v\times d}$, and an entrywise monomial $f(y) = y^{p}$, we characterize the eigenvalues of the population random-feature covariance $\mathbb{E}_{x }(\frac{1}{d}f(W^\top x )^{\otimes 2})$. We prove matching upper and lower bounds: for all $1 \leq j \leq c_1 d \log^{-(p+1)}(d)$, the $j$-th eigenvalue is of order $\left(\log^{p-1}(j+1)/j\right)^α$. For $ c_1 d \log^{-(p+1)}(d)\leq j\leq d$, the $j$-th eigenvalue is of order $j^{-α}$ up to a polylog factor. That is, the power-law exponent $α$ is inherited exactly from the input covariance, modified only by a logarithmic correction that depends on the monomial degree $p$. The proof combines a dyadic head-tail decomposition with Wick chaos expansions for higher-order monomials and random matrix concentration inequalities.

---

### Covariance-Guided Resource Adaptive Learning for Efficient Edge Inference

Authors: Ahmad N. L. Nabhaan, Zaki Sukma, Rakandhiya D. Rachmanto, Muhammad Husni Santriaji, Byungjin Cho, Arief Setyanto, In Kee Kim
Published: 2026-03-15
Categories: cs.DC, cs.CV
arXiv: https://arxiv.org/abs/2603.14577v1

For deep learning inference on edge devices, hardware configurations achieving the same throughput can differ by 2$\times$ in power consumption, yet operators often struggle to find the efficient ones without exhaustive profiling. Existing approaches often rely on inefficient static presets or require expensive offline profiling that must be repeated for each new model or device. To address this problem, we present CORAL, an online optimization method that discovers near-optimal configurations without offline profiling. CORAL leverages distance covariance to statistically capture the non-linear dependencies between hardware settings, e.g., DVFS and concurrency levels, and performance metrics. Unlike prior work, we explicitly formulate the challenge as a throughput-power co-optimization problem to satisfy power budgets and throughput targets simultaneously. We evaluate CORAL on two NVIDIA Jetson devices across three object detection models ranging from lightweight to heavyweight. In single-target scenarios, CORAL achieves 96% $\unicode{x2013}$ 100% of the optimal performance found by exhaustive search. In strict dual-constraint scenarios where baselines fail or exceed power budgets, CORAL consistently finds proper configurations online with minimal exploration.

---

### IQP Born Machines under Data-dependent and Agnostic Initialization Strategies

Authors: Sacha Lerch, Joseph Bowles, Ricard Puig, Erik Armengol, Zoë Holmes, Supanut Thanasilp
Published: 2026-03-15
Categories: quant-ph, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.14576v1

Quantum circuit Born machines based on instantaneous quantum polynomial-time (IQP) circuits are natural candidates for quantum generative modeling, both because of their probabilistic structure and because IQP sampling is provably classically hard in certain regimes. Recent proposals focus on training IQP-QCBMs using Maximum Mean Discrepancy (MMD) losses built from low-body Pauli-$Z$ correlators, but the effect of initialization on the resulting optimization landscape remains poorly understood. In this work, we address this by first proving that the MMD loss landscape suffers from barren plateaus for random full-angle-range initializations of IQP circuits. We then establish lower bounds on the loss variance for identity and an unbiased data-agnostic initialization. We then additionally consider a data-dependent initialization that is better aligned with the target distribution and, under suitable assumptions, yields provable gradients and generally converges quicker to a good minimum (as indicated by our training of circuits with 150 qubits on genomic data). Finally, as a by-product, the developed variance lower bound framework is applicable to a general class of non-linear losses, offering a broader toolset for analyzing warm-starts in quantum machine learning.

---

### CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad

Authors: Yongqiang Chen, Chenxi Liu, Zhenhao Chen, Tongliang Liu, Bo Han, Kun Zhang
Published: 2026-03-15
Categories: cs.LG, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2603.14575v2

Evolve-based agent such as AlphaEvolve is one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite the success, existing evolve-based agents lack targeted guidance for evolution and effective mechanisms for organizing and utilizing knowledge acquired from past evolutionary experience. Consequently, they suffer from decreasing evolution efficiency and exhibit oscillatory behavior when approaching known performance boundaries. To mitigate the gap, we develop CausalEvolve, equipped with a causal scratchpad that leverages LLMs to identify and reason about guiding factors for evolution. At the beginning, CausalEvolve first identifies outcome-level factors that offer complementary inspirations in improving the target objective. During the evolution, CausalEvolve also inspects surprise patterns during the evolution and abductive reasoning to hypothesize new factors, which in turn offer novel directions. Through comprehensive experiments, we show that CausalEvolve effectively improves the evolutionary efficiency and discovers better solutions in 4 challenging open-ended scientific tasks.

---

### Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method

Authors: Yatin Dandi, David Gamarnik, Francisco Pernice, Lenka Zdeborová
Published: 2026-03-15
Categories: cond-mat.dis-nn, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2603.14573v1

Dynamical Mean Field Theory (DMFT) provides an asymptotic description of the dynamics of macroscopic observables in certain disordered systems. Originally pioneered in the context of spin glasses by Sompolinsky and Zippelius (1982), it has since been used to derive asymptotic dynamical equations for a wide range of models in physics, high-dimensional statistics and machine learning. One of the main tools used by physicists to obtain these equations is the dynamical cavity method, which has remained largely non-rigorous. In contrast, existing mathematical formalizations have relied on alternative approaches, including Gaussian conditioning, large deviations over paths, or Fourier analysis. In this work, we formalize the dynamical cavity method and use it to give a new proof of the DMFT equations for General First Order Methods, a broad class of dynamics encompassing algorithms such as Gradient Descent and Approximate Message Passing.

---