# Research Papers — 2026-03 · bundle page 83 of 243

> Full-text markdown of papers #4101–4150 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/83
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/82.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/84.md)

### The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus

Authors: Amartya Roy, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer, Haitham Bou-Ammar
Published: 2026-03-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.20105v1

LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet existing RLMs depend on an open-ended read-eval-print loop (REPL) in which the model generates arbitrary control code, making execution difficult to verify, predict, and analyse. We introduce $λ$-RLM, a framework for long-context reasoning that replaces free-form recursive code generation with a typed functional runtime grounded in $λ$-calculus. It executes a compact library of pre-verified combinators and uses neural inference only on bounded leaf subproblems, turning recursive reasoning into a structured functional program with explicit control flow. We show that $λ$-RLM admits formal guarantees absent from standard RLMs, including termination, closed-form cost bounds, controlled accuracy scaling with recursion depth, and an optimal partition rule under a simple cost model. Empirically, across four long-context reasoning tasks and nine base models, $λ$-RLM outperforms standard RLM in 29 of 36 model-task comparisons, improves average accuracy by up to +21.9 points across model tiers, and reduces latency by up to 4.1x. These results show that typed symbolic control yields a more reliable and efficient foundation for long-context reasoning than open-ended recursive code generation. The complete implementation of $λ$-RLM, is open-sourced for the community at: https://github.com/lambda-calculus-LLM/lambda-RLM.

---

### Spectral Alignment in Forward-Backward Representations via Temporal Abstraction

Authors: Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi, Hao Zhu, Abhinav Valada, Joschka Boedecker
Published: 2026-03-20
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.20103v3

Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization. However, a fundamental spectral mismatch often exists between the high-rank transition dynamics of continuous environments and the low-rank bottleneck of the FB architecture, making accurate low-rank representation learning difficult. In this work, we analyze temporal abstraction as a mechanism to mitigate this mismatch. By characterizing the spectral properties of the transition operator, we show that temporal abstraction acts analogously to a low-pass filter that suppresses high-frequency spectral components. This suppression reduces the effective rank of the induced SR while preserving a formal bound on the resulting value function error. Empirically, we show that this alignment is a key factor for stable FB learning, particularly at high discount factors where bootstrapping becomes error-prone. Our results identify temporal abstraction as a principled mechanism for shaping the spectral structure of the underlying MDP and enabling effective long-horizon representations in continuous control.

---

### Pitfalls in Evaluating Interpretability Agents

Authors: Tal Haklay, Nikhil Prakash, Sana Pandey, Antonio Torralba, Aaron Mueller, Jacob Andreas, Tamar Rott Shaham, Yonatan Belinkov
Published: 2026-03-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.20101v1

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of autonomy, ranging from fixed one-shot workflows to fully autonomous interpretability agents. This shift creates a corresponding need to scale evaluation approaches to keep pace with both the volume and complexity of generated explanations. We investigate this challenge in the context of automated circuit analysis -- explaining the roles of model components when performing specific tasks. To this end, we build an agentic system in which a research agent iteratively designs experiments and refines hypotheses. When evaluated against human expert explanations across six circuit analysis tasks in the literature, the system appears competitive. However, closer examination reveals several pitfalls of replication-based evaluation: human expert explanations can be subjective or incomplete, outcome-based comparisons obscure the research process, and LLM-based systems may reproduce published findings via memorization or informed guessing. To address some of these pitfalls, we propose an unsupervised intrinsic evaluation based on the functional interchangeability of model components. Our work demonstrates fundamental challenges in evaluating complex automated interpretability systems and reveals key limitations of replication-based evaluation.

---

### An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models

Authors: Yuming Feng, Christy Yang
Published: 2026-03-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.20100v1

Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align language models, yet empirical behavior under small backbones and modest data is under-specified. We systematically compare SFT-only, DPO-only, and staged SFT-to-DPO training alongside full fine-tuning (FFT) versus LoRA on a GPT-2-scale decoder, evaluating paraphrase detection and Shakespearean sonnet continuation. DPO yields small, task-dependent gains over strong SFT and can match competitive SFT accuracy without a warm start when the preference construction closely parallels the supervised objective. In contrast, parameterization dominates: FFT consistently outperforms LoRA at matched training depth, and LoRA does not reduce wall-clock time on our hardware. These findings indicate that, in this small-scale regime, supervised full-parameter adaptation remains the primary performance lever, while preference optimization and low-rank adaptation provide limited marginal returns.

---

### LLM-Enhanced Semantic Data Integration of Electronic Component Qualifications in the Aerospace Domain

Authors: Antonio De Santis, Marco Balduini, Matteo Belcao, Andrea Proia, Marco Brambilla, Emanuele Della Valle
Published: 2026-03-20
Categories: cs.IR, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2603.20094v1

Large manufacturing companies face challenges in information retrieval due to data silos maintained by different departments, leading to inconsistencies and misalignment across databases. This paper presents an experience in integrating and retrieving qualification data for electronic components used in satellite board design. Due to data silos, designers cannot immediately determine the qualification status of individual components. However, this process is critical during the planning phase, when assembly drawings are issued before production, to optimize new qualifications and avoid redundant efforts. To address this, we propose a pipeline that uses Virtual Knowledge Graphs for a unified view over heterogeneous data sources and LLMs to enhance retrieval and reduce manual effort in data cleansing. The retrieval of qualifications is then performed through an Ontology-based Data Access approach for structured queries and a vector search mechanism for retrieving qualifications based on similar textual properties. We perform a comparative cost-benefit analysis, demonstrating that the proposed pipeline also outperforms approaches relying solely on LLMs, such as Retrieval-Augmented Generation (RAG), in terms of long-term efficiency.

---

### How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models

Authors: Luca Ambrogioni
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.20092v5

Diffusion models generate structure by progressively transforming noise into data, yet the mechanisms underlying this transition remain poorly understood. In this work, we show that pattern formation in trained diffusion models can be explained as an out-of-equilibrium phase transition driven by instabilities in the denoising dynamics. We develop a theoretical framework linking data symmetries and architectural constraints, such as locality and translation equivariance, to the emergence of collective spatial modes. In this view, structure arises when low-frequency modes become unstable, triggering a rapid growth of spatial correlations that organizes noise into coherent patterns. We validate this theory through a combination of analytical models and experiments. In a controlled patch-based model, we observe a sharp increase in correlation length and a simultaneous softening of low-frequency modes at a well-defined critical time, accurately predicted by theory. Similar signatures are found in trained convolutional diffusion models on Fashion-MNIST and in large-scale ImageNet models, where pattern formation coincides with a peak in estimated correlation length and a pronounced weakening of spatial modes. Finally, intervention experiments show that applying guidance precisely at this critical stage significantly improves class alignment compared to applying it at random times, demonstrating that this regime is not only descriptive but functionally important.

---

### Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment

Authors: Shiqi Gao, Kang Fu, Zitong Xu, Huiyu Duan, Xiongkuo Min, Jia Wang, Guangtao Zhai
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.20086v1

Current no-reference image quality assessment (NR-IQA) models for enhanced images often struggle to generalize, as they tend to overfit to the distinct patterns of specific enhancement algorithms rather than evaluating genuine perceptual quality. To address this issue, we propose a preference-guided debiasing framework for no-reference enhancement image quality assessment (EIQA). Specifically, we first learn a continuous enhancement-preference embedding space using supervised contrastive learning, where images generated by similar enhancement styles are encouraged to have closer representations. Based on this, we further estimate the enhancement-induced nuisance component contained in the raw quality representation and remove it before quality regression. In this way, the model is guided to focus on algorithm-invariant perceptual quality cues instead of enhancement-specific visual fingerprints. To facilitate stable optimization, we adopt a two-stage training strategy that first learns the enhancement-preference space and then performs debiased quality prediction. Extensive experiments on public EIQA benchmarks demonstrate that the proposed method effectively mitigates algorithm-induced representation bias and achieves superior robustness and cross-algorithm generalization compared with existing approaches.

---

### Predicting States of Understanding in Explanatory Interactions Using Cognitive Load-Related Linguistic Cues

Authors: Yu Wang, Olcay Türk, Angela Grimminger, Hendrik Buschmeier
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.20079v1

We investigate how verbal and nonverbal linguistic features, exhibited by speakers and listeners in dialogue, can contribute to predicting the listener's state of understanding in explanatory interactions on a moment-by-moment basis. Specifically, we examine three linguistic cues related to cognitive load and hypothesised to correlate with listener understanding: the information value (operationalised with surprisal) and syntactic complexity of the speaker's utterances, and the variation in the listener's interactive gaze behaviour. Based on statistical analyses of the MUNDEX corpus of face-to-face dialogic board game explanations, we find that individual cues vary with the listener's level of understanding. Listener states ('Understanding', 'Partial Understanding', 'Non-Understanding' and 'Misunderstanding') were self-annotated by the listeners using a retrospective video-recall method. The results of a subsequent classification experiment, involving two off-the-shelf classifiers and a fine-tuned German BERT-based multimodal classifier, demonstrate that prediction of these four states of understanding is generally possible and improves when the three linguistic cues are considered alongside textual features.

---

### A Unified Platform and Quality Assurance Framework for 3D Ultrasound Reconstruction with Robotic, Optical, and Electromagnetic Tracking

Authors: Lewis Howell, Manisha Waterston, Tze Min Wah, James H. Chandler, James R. McLaughlan
Published: 2026-03-20
Categories: cs.CV, cs.RO, eess.IV
arXiv: https://arxiv.org/abs/2603.20077v1

Three-dimensional (3D) Ultrasound (US) can facilitate diagnosis, treatment planning, and image-guided therapy. However, current studies rarely provide a comprehensive evaluation of volumetric accuracy and reproducibility, highlighting the need for robust Quality Assurance (QA) frameworks, particularly for tracked 3D US reconstruction using freehand or robotic acquisition. This study presents a QA framework for 3D US reconstruction and a flexible open source platform for tracked US research. A custom phantom containing geometric inclusions with varying symmetry properties enables straightforward evaluation of optical, electromagnetic, and robotic kinematic tracking for 3D US at different scanning speeds and insonation angles. A standardised pipeline performs real-time segmentation and 3D reconstruction of geometric targets (DSC = 0.97, FPS = 46) without GPU acceleration, followed by automated registration and comparison with ground-truth geometries. Applying this framework showed that our robotic 3D US achieves state-of-the-art reconstruction performance (DSC-3D = 0.94 +- 0.01, HD95 = 1.17 +- 0.12), approaching the spatial resolution limit imposed by the transducer. This work establishes a flexible experimental platform and a reproducible validation methodology for 3D US reconstruction. The proposed framework enables robust cross-platform comparisons and improved reporting practices, supporting the safe and effective clinical translation of 3D ultrasound in diagnostic and image-guided therapy applications.

---

### Agentic Harness for Real-World Compilers

Authors: Yingwei Zheng, Cong Li, Shaohua Li, Yuqun Zhang, Zhendong Su
Published: 2026-03-20
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.20075v2

Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs pose unique challenges due to their complexity, deep cross-domain expertise requirements, and sparse, non-descriptive bug reports, necessitating compiler-specific harnesses. To bridge the gap, we introduce llvm-harness, the first harness designed to assist LLM agents in understanding and fixing compiler bugs. Our current focus is on the middle end of LLVM, one of the most widely used compiler infrastructures. Central to llvm-harness are agent-friendly LLVM tools, a benchmark llvm-bench of 334 reproducible LLVM middle-end bugs, and a tailored mini agent llvm-autofix-mini for fixing LLVM middle-end bugs automatically. We evaluate five frontier models and find that they exhibit a performance decline when tackling compiler bugs with the state-of-the-art agent. With llvm-harness' enhancement, their performance improves by 62%. Our specialized mini agent llvm-autofix-mini further outperforms the llvm-harness-enhanced state-of-the-art by 22%. This emphasizes the necessity for specialized harnesses like ours to assist LLMs in compiler engineering tasks. Despite promising results, our expert review also reveals several open challenges that remain when applying LLMs for compiler engineering tasks. GitHub: https://github.com/dtcxzyw/llvm-harness

---

### MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models

Authors: Puskal Khadka, KC Santosh
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.20074v1

State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data and its complex 2D spatial dependencies. Although several early studies have explored adapting selective SSMs for vision applications, most approaches primarily depend on employing various traversal strategies over the same input. This introduces redundancy and distorts the intricate spatial relationships within images. To address these challenges, we propose MFil-Mamba, a novel visual state space architecture built on a multi-filter scanning backbone. Unlike fixed multi-directional traversal methods, our design enables each scan to capture unique and contextually relevant spatial information while minimizing redundancy. Furthermore, we incorporate an adaptive weighting mechanism to effectively fuse outputs from multiple scans in addition to architectural enhancements. MFil-Mamba achieves superior performance over existing state-of-the-art models across various benchmarks that include image classification, object detection, instance segmentation, and semantic segmentation. For example, our tiny variant attains 83.2% top-1 accuracy on ImageNet-1K, 47.3% box AP and 42.7% mask AP on MS COCO, and 48.5% mIoU on the ADE20K dataset. Code and models are available at https://github.com/puskal-khadka/MFil-Mamba.

---

### Antenna Array Beamforming Based on a Hybrid Quantum Optimization Framework

Authors: Shuai Zeng
Published: 2026-03-20
Categories: quant-ph, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2603.20072v1

This paper proposes a hybrid quantum optimization framework for large-scale antenna-array beamforming with jointly optimized discrete phases and continuous amplitudes. The method combines quantum-inspired search with classical gradient refinement to handle mixed discrete-continuous variables efficiently. For phase optimization, a Gray-code and odd-combination encoding scheme is introduced to improve robustness and avoid the complexity explosion of higher-order Ising models. For amplitude optimization, a geometric spin-combination encoding and a two-stage strategy are developed, using quantum-inspired optimization for coarse search and gradient optimization for fine refinement. To enhance solution diversity and quality, a rainbow quantum-inspired algorithm integrates multiple optimizers for parallel exploration, followed by hierarchical-clustering-based candidate refinement. In addition, a double outer-product method and an augmented version are proposed to construct the coupling matrix and bias vector efficiently, improving numerical precision and implementation efficiency. Under the scoring rules of the 7th National Quantum Computing Hackathon, simulations on a 32-element antenna array show that the proposed method achieves a score of 461.58 under constraints on near-main-lobe sidelobes, wide-angle sidelobes, beamwidth, and optimization time, nearly doubling the baseline score. The proposed framework provides an effective reference for beamforming optimization in future wireless communication systems.

---

### The monotonicity of the Franz-Parisi potential is equivalent with Low-degree MMSE lower bounds

Authors: Konstantinos Tsirkas, Leda Wang, Ilias Zadik
Published: 2026-03-20
Categories: math.ST, cond-mat.stat-mech, cs.CC, stat.ML
arXiv: https://arxiv.org/abs/2603.20070v1

Over the last decades, two distinct approaches have been instrumental to our understanding of the computational complexity of statistical estimation. The statistical physics literature predicts algorithmic hardness through local stability and monotonicity properties of the Franz--Parisi (FP) potential \cite{franz1995recipes,franz1997phase}, while the mathematically rigorous literature characterizes hardness via the limitations of restricted algorithmic classes, most notably low-degree polynomial estimators \cite{hopkins2017efficient}. For many inference models, these two perspectives yield strikingly consistent predictions, giving rise to a long-standing open problem of establishing a precise mathematical relationship between them. In this work, we show that for estimation problems the power of low-degree polynomials is equivalent to the monotonicity of the annealed FP potential for a broad family of Gaussian additive models (GAMs) with signal-to-noise ratio $λ$. In particular, subject to a low-degree conjecture for GAMs, our results imply that the polynomial-time limits of these models are directly implied by the monotonicity of the annealed FP potential, in conceptual agreement with predictions from the physics literature dating back to the 1990s.

---

### Fine-tuning Timeseries Predictors Using Reinforcement Learning

Authors: Hugo Cazaux, Ralph Rudd, Hlynur Stefánsson, Sverrir Ólafsson, Eyjólfur Ingi Ásgeirsson
Published: 2026-03-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.20063v1

This chapter presents three major reinforcement learning algorithms used for fine-tuning financial forecasters. We propose a clear implementation plan for backpropagating the loss of a reinforcement learning task to a model trained using supervised learning, and compare the performance before and after the fine-tuning. We find an increase in performance after fine-tuning, and transfer learning properties to the models, indicating the benefits of fine-tuning. We also highlight the tuning process and empirical results for future implementation by practitioners.

---

### The End of Rented Discovery: How AI Search Redistributes Power Between Hotels and Intermediaries

Authors: Peiying Zhu, Sidi Chang
Published: 2026-03-20
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.20062v2

When a traveler asks an AI search engine to recommend a hotel, which sources get cited -- and does query framing matter? We audit 1,357 grounding citations from Google Gemini across 156 hotel queries in Tokyo and document a systematic pattern we call the Intent-Source Divide. Experiential queries draw 55.9% of their citations from non-OTA sources, compared to 30.8% for transactional queries -- a 25.1 percentage-point gap ($p < 5 \times 10^{-20}$). The effect is amplified in Japanese, where experiential queries draw 62.1% non-OTA citations compared to 50.0% in English -- consistent with a more diverse Japanese non-OTA content ecosystem. For an industry in which hotels have long paid OTAs for demand acquisition, this pattern matters because it suggests that AI search may make hotel discovery less exclusively controlled by commission-based intermediaries.

---

### DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment

Authors: Weidong Bao, Yilin Wang, Ruyu Gao, Fangling Leng, Yubin Bao, Ge Yu
Published: 2026-03-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.20059v1

Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f ined schema. However, such methods are suboptimal for real-world sce narios where data arrives dynamically, as incorporating new informa tion requires complete and computationally expensive graph reconstruc tions. Furthermore, predefined schemas hinder the flexibility of knowl edge graph construction. To address these limitations, we introduce DIAL KG, a closed-loop framework for incremental KG construction orches trated by a Meta-Knowledge Base (MKB). The framework oper ates in a three-stage cycle: (i) Dual-Track Extraction, which ensures knowledge completeness by defaulting to triple generation and switching to event extraction for complex knowledge; (ii) Governance Adjudica tion, which ensures the fidelity and currency of extracted facts to prevent hallucinations and knowledge staleness; and (iii) Schema Evolution, in which new schemas are induced from validated knowledge to guide subsequent construction cycles, and knowledge from the current round is incrementally applied to the existing KG. Extensive experiments demon strate that our framework achieves state-of-the-art (SOTA) performance in the quality of both the constructed graph and the induced schemas.

---

### Structured Latent Dynamics in Wireless CSI via Homomorphic World Models

Authors: Salmane Naoumi, Mehdi Bennis, Marwa Chafii
Published: 2026-03-20
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2603.20048v1

We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the problem as a world modeling task and leverages the Joint Embedding Predictive Architecture (JEPA) to learn action-conditioned latent dynamics from CSI trajectories. To promote geometric consistency and compositionality, we parameterize transitions using homomorphic updates derived from Lie algebra, yielding a structured latent space that reflects spatial layout and user motion. Evaluations on the DICHASUS dataset show that our approach outperforms strong baselines in preserving topology and forecasting future embeddings across unseen environments. The resulting latent space enables metrically faithful channel charts, offering a scalable foundation for downstream applications such as mobility-aware scheduling, localization, and wireless scene understanding.

---

### Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs

Authors: Wenjian Zhang, Kongcheng Zhang, Jiaxin Qi, Baisheng Lai, Jianqiang Huang
Published: 2026-03-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.20046v1

Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent policy distribution. In fact, RL optimization can be viewed as steering the policy toward an ideal distribution that maximizes the rewards, while effective exploration should align efforts with desired target. Leveraging this insight, we propose HeRL, a Hindsight experience guided Reinforcement Learning framework to bootstrap effective exploration by explicitly telling LLMs the desired behaviors specified in rewards. Concretely, HeRL treats failed trajectories along with their unmet rubrics as hindsight experience, which serves as in-context guidance for the policy to explore desired responses beyond its current distribution. Additionally, we introduce a bonus reward to incentivize responses with greater potential for improvement under such guidance. HeRL facilitates effective learning from desired high quality samples without repeated trial-and-error from scratch, yielding a more accurate estimation of the expected gradient theoretically. Extensive experiments across various benchmarks demonstrate that HeRL achieves superior performance gains over baselines, and can further benefit from experience guided self-improvement at test time. Our code is available at https://github.com/sikelifei/HeRL.

---

### Investigating a Policy-Based Formulation for Endoscopic Camera Pose Recovery

Authors: Jan Emily Mangulabnan, Akshat Chauhan, Laura Fleig, Lalithkumar Seenivasan, Roger D. Soberanis-Mukul, S. Swaroop Vedula, Russell H. Taylor, Masaru Ishii, Gregory D. Hager, Mathias Unberath
Published: 2026-03-20
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2603.20045v1

In endoscopic surgery, surgeons continuously locate the endoscopic view relative to the anatomy by interpreting the evolving visual appearance of the intraoperative scene in the context of their prior knowledge. Vision-based navigation systems seek to replicate this capability by recovering camera pose directly from endoscopic video, but most approaches do not embody the same principles of reasoning about new frames that makes surgeons successful. Instead, they remain grounded in feature matching and geometric optimization over keyframes, an approach that has been shown to degrade under the challenging conditions of endoscopic imaging like low texture and rapid illumination changes. Here, we pursue an alternative approach and investigate a policy-based formulation of endoscopic camera pose recovery that seeks to imitate experts in estimating trajectories conditioned on the previous camera state. Our approach directly predicts short-horizon relative motions without maintaining an explicit geometric representation at inference time. It thus addresses, by design, some of the notorious challenges of geometry-based approaches, such as brittle correspondence matching, instability in texture-sparse regions, and limited pose coverage due to reconstruction failure. We evaluate the proposed formulation on cadaveric sinus endoscopy. Under oracle state conditioning, we compare short-horizon motion prediction quality to geometric baselines achieving lowest mean translation error and competitive rotational accuracy. We analyze robustness by grouping prediction windows according to texture richness and illumination change indicating reduced sensitivity to low-texture conditions. These findings suggest that a learned motion policy offers a viable alternative formulation for endoscopic camera pose recovery.

---

### LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families

Authors: Jianan Chen, Xiaoxue Gao, Tatsuya Kawahara, Nancy F. Chen
Published: 2026-03-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.20042v1

Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech recognition (ASR) under high-resource conditions. However, existing benchmarks predominantly focus on high-resource languages, leaving the ASR behavior of SpeechLMs in low-resource languages insufficiently understood. This gap is critical, as practical ASR systems must reliably support low-resource languages and generalize across diverse language families, and it directly hinders the deployment of SpeechLM-based ASR in real-world multilingual scenarios. As a result, it is essential to evaluate SpeechLMs on low-resource languages to ensure their generalizability across different language families. To address this problem, we propose \textbf{LoASR-Bench}, a comprehensive benchmark designed to evaluate \textbf{lo}w-resource \textbf{a}utomatic \textbf{s}peech \textbf{r}ecognition (\textbf{ASR}) of the latest SpeechLMs across diverse language families. LoASR-Bench comprises 25 languages from 9 language families, featuring both Latin and non-Latin scripts, enabling cross-linguistic and cross-script assessment of ASR performance of current SpeechLMs. Experimental results highlight the limitations of the latest SpeechLMs in handling real-world low-resource languages.

---

### Federated Hyperdimensional Computing for Resource-Constrained Industrial IoT

Authors: Nikita Zeulin, Olga Galinina, Nageen Himayat, Sergey Andreev
Published: 2026-03-20
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2603.20037v1

In the Industrial Internet of Things (IIoT) systems, edge devices often operate under strict constraints in memory, compute capability, and wireless bandwidth. These limitations challenge the deployment of advanced data analytics tasks, such as predictive and prescriptive maintenance. In this work, we explore hyperdimensional computing (HDC) as a lightweight learning paradigm for resource-constrained IIoT. Conventional centralized HDC leverages the properties of high-dimensional vector spaces to enable energy-efficient training and inference. We integrate this paradigm into a federated learning (FL) framework where devices exchange only prototype representations, which significantly reduces communication overhead. Our numerical results highlight the potential of federated HDC to support collaborative learning in IIoT with fast convergence speed and communication efficiency. These results indicate that HDC represents a lightweight and resilient framework for distributed intelligence in large-scale and resource-constrained IIoT environments.

---

### Continual Learning as Shared-Manifold Continuation Under Compatible Shift

Authors: Henry J. Kobs
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.20036v1

Continual learning methods usually preserve old behavior by regularizing parameters, matching old outputs, or replaying previous examples. These strategies can reduce forgetting, but they do not directly specify how the latent representation should evolve. We study a narrower geometric alternative for the regime where old and new data should remain on the same latent support: continual learning as continuation of a shared manifold. We instantiate this view within Support-Preserving Manifold Assimilation (SPMA) and evaluate a geometry-preserving variant, SPMA-OG, that combines sparse replay, output distillation, relational geometry preservation, local smoothing, and chart-assignment regularization on old anchors. On representative compatible-shift CIFAR10 and Tiny-ImageNet runs, SPMA-OG improves over sparse replay baselines in old-task retention and representation-preservation metrics while remaining competitive on new-task accuracy. On a controlled synthetic atlas-manifold benchmark, it achieves near-perfect anchor-geometry preservation while also improving new-task accuracy over replay. These results provide evidence that geometry-aware anchor regularization is a useful inductive bias when continual learning should preserve a shared latent support rather than create a new one.

---

### CoverageBench: Evaluating Information Coverage across Tasks and Domains

Authors: Saron Samuel, Andrew Yates, Dawn Lawrie, Ian Soboroff, Trevor Adriaanse, Benjamin Van Durme, Eugene Yang
Published: 2026-03-20
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.20034v1

We wish to measure the information coverage of an ad hoc retrieval algorithm, that is, how much of the range of available relevant information is covered by the search results. Information coverage is a central aspect for retrieval, especially when the retrieval system is integrated with generative models in a retrieval-augmented generation (RAG) system. The classic metrics for ad hoc retrieval, precision and recall, reward a system as more and more relevant documents are retrieved. However, since relevance in ad hoc test collections is defined for a document without any relation to other documents that might contain the same information, high recall is sufficient but not necessary to ensure coverage. The same is true for other metrics such as rank-biased precision (RBP), normalized discounted cumulative gain (nDCG), and mean average precision (MAP). Test collections developed around the notion of diversity ranking in web search incorporate multiple aspects that support a concept of coverage in the web domain. In this work, we construct a suite of collections for evaluating information coverage from existing collections. This suite offers researchers a unified testbed spanning multiple genres and tasks. All topics, nuggets, relevance labels, and baseline rankings are released on Hugging Face Datasets, along with instructions for accessing the publicly available document collections.

---

### Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs

Authors: Maximiliano Armesto, Christophe Kolb
Published: 2026-03-20
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.20028v1

Evidence on AI in software engineering still leans heavily toward individual task completion, while evidence on team-level delivery remains scarce. We report a retrospective longitudinal field study of Chiron, an industrial platform that coordinates humans and AI agents across four delivery stages: analysis, planning, implementation, and validation. The study covers three real software modernization programs -- a COBOL banking migration (~30k LOC), a large accounting modernization (~400k LOC), and a .NET/Angular mortgage modernization (~30k LOC) -- observed across five delivery configurations: a traditional baseline and four successive platform versions (V1--V4). The benchmark separates observed outcomes (stage durations, task volumes, validation-stage issues, first-release coverage) from modeled outcomes (person-days and senior-equivalent effort under explicit staffing scenarios). Under baseline staffing assumptions, portfolio totals move from 36.0 to 9.3 summed project-weeks; modeled raw effort falls from 1080.0 to 232.5 person-days; modeled senior-equivalent effort falls from 1080.0 to 139.5 SEE-days; validation-stage issue load falls from 8.03 to 2.09 issues per 100 tasks; and first-release coverage rises from 77.0% to 90.5%. V3 and V4 add acceptance-criteria validation, repository-native review, and hybrid human-agent execution, simultaneously improving speed, coverage, and issue load. The evidence supports a central thesis: the largest gains appear when AI is embedded in an orchestrated workflow rather than deployed as an isolated coding assistant.

---

### Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences

Authors: Panagiota Birmpa, Eric Joseph Hall
Published: 2026-03-20
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2603.20025v2

We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,Γ)$-divergences, we prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is controlled by an average of family-level discrepancies aligned with the graph. In an additive regime, the surrogate is exact. This closes a theoretical gap in the literature; existing subadditivity results justify graph-informed adversarial learning for classical discrepancies, but not for interpolative divergences, where the usual factorization argument breaks down. In turn, we provide a justification for replacing a standard, graph-agnostic GAN with a monolithic discriminator by a graph-informed GAN (GiGAN) with localized family-level discriminators, without requiring the optimizer itself to factorize according to the graph. We also obtain parallel results for integral probability metrics and proximal optimal transport divergences, identify natural discriminator classes for which the theory applies, and present experiments showing improved stability and structural recovery relative to graph-agnostic baselines.

---

### Layered Quantum Architecture Search for 3D Point Cloud Classification

Authors: Natacha Kuete Meli, Jovita Lukasik, Vladislav Golyanik, Michael Moeller
Published: 2026-03-20
Categories: quant-ph, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.20024v1

We introduce layered Quantum Architecture Search (layered-QAS), a strategy inspired by classical network morphism that designs Parametrised Quantum Circuit (PQC) architectures by progressively growing and adapting them. PQCs offer strong expressiveness with relatively few parameters, yet they lack standard architectural layers (e.g., convolution, attention) that encode inductive biases for a given learning task. To assess the effectiveness of our method, we focus on 3D point cloud classification as a challenging yet highly structured problem. Whereas prior work on this task has used PQCs only as feature extractors for classical classifiers, our approach uses the PQC as the main building block of the classification model. Simulations show that our layered-QAS mitigates barren plateau, outperforms quantum-adapted local and evolutionary QAS baselines, and achieves state-of-the-art results among PQC-based methods on the ModelNet dataset.

---

### ODySSeI: An Open-Source End-to-End Framework for Automated Detection, Segmentation, and Severity Estimation of Lesions in Invasive Coronary Angiography Images

Authors: Anand Choudhary, Xiaowu Sun, Thabo Mahendiran, Ortal Senouf, Denise Auberson, Bernard De Bruyne, Stephane Fournier, Olivier Muller, Emmanuel Abbé, Pascal Frossard, Dorina Thanou
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.20021v1

Invasive Coronary Angiography (ICA) is the clinical gold standard for the assessment of coronary artery disease. However, its interpretation remains subjective and prone to intra- and inter-operator variability. In this work, we introduce ODySSeI: an Open-source end-to-end framework for automated Detection, Segmentation, and Severity estimation of lesions in ICA images. ODySSeI integrates deep learning-based lesion detection and lesion segmentation models trained using a novel Pyramidal Augmentation Scheme (PAS) to enhance robustness and real-time performance across diverse patient cohorts (2149 patients from Europe, North America, and Asia). Furthermore, we propose a quantitative coronary angiography-free Lesion Severity Estimation (LSE) technique that directly computes the Minimum Lumen Diameter (MLD) and diameter stenosis from the predicted lesion geometry. Extensive evaluation on both in-distribution and out-of-distribution clinical datasets demonstrates ODySSeI's strong generalizability. Our PAS yields large performance gains in highly complex tasks as compared to relatively simpler ones, notably, a 2.5-fold increase in lesion detection performance versus a 1-3\% increase in lesion segmentation performance over their respective baselines. Our LSE technique achieves high accuracy, with predicted MLD values differing by only $\pm$ 2-3 pixels from the corresponding ground truths. On average, ODySSeI processes a raw ICA image within only a few seconds on a CPU and in a fraction of a second on a GPU and is available as a plug-and-play web interface at swisscardia.epfl.ch. Overall, this work establishes ODySSeI as a comprehensive and open-source framework which supports automated, reproducible, and scalable ICA analysis for real-time clinical decision-making.

---

### Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR

Authors: Ziye Yuan, Ruchang Yao, Chengxin Zheng, Yusheng Zhao, Daxiang Dong, Ming Zhang
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.20020v2

Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip pathways introduce direct back-propagation paths from high-level semantic objectives to early visual layers. This mechanism overwrites low-level signals and destabilizes training. To mitigate this gradient interference, we propose Detached Skip-Links, a minimal modification that reuses shallow features in the forward pass while stopping gradients through the skip branch during joint training. This asymmetric design reduces gradient interference, improving stability and convergence without adding learnable parameters. To diagnose whether fine-grained information is preserved and usable by an LLM, we introduce $R$-Probe, which measures pixel-level reconstructability of projected visual tokens using a shallow decoder initialized from the first quarter of the LLM layers. Across multiple ViT backbones and multimodal benchmarks, and at scales up to 7M training samples, our approach consistently improves OCR-centric benchmarks and delivers clear gains on general multimodal tasks.

---

### RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering

Authors: Bo Yuan, Hexuan Deng, Xuebo Liu, Min Zhang
Published: 2026-03-20
Categories: cs.CL, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2603.20017v1

Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized--general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 average LLM calls per question. Codes and models are available at https://github.com/Oldcircle/RouterKGQA.

---

### CFCML: A Coarse-to-Fine Crossmodal Learning Framework For Disease Diagnosis Using Multimodal Images and Tabular Data

Authors: Tianling Liu, Hongying Liu, Fanhua Shang, Lequan Yu, Tong Han, Liang Wan
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.20016v1

In clinical practice, crossmodal information including medical images and tabular data is essential for disease diagnosis. There exists a significant modality gap between these data types, which obstructs advancements in crossmodal diagnostic accuracy. Most existing crossmodal learning (CML) methods primarily focus on exploring relationships among high-level encoder outputs, leading to the neglect of local information in images. Additionally, these methods often overlook the extraction of task-relevant information. In this paper, we propose a novel coarse-to-fine crossmodal learning (CFCML) framework to progressively reduce the modality gap between multimodal images and tabular data, by thoroughly exploring inter-modal relationships. At the coarse stage, we explore the relationships between multi-granularity features from various image encoder stages and tabular information, facilitating a preliminary reduction of the modality gap. At the fine stage, we generate unimodal and crossmodal prototypes that incorporate class-aware information, and establish hierarchical anchor-based relationship mining (HRM) strategy to further diminish the modality gap and extract discriminative crossmodal information. This strategy utilize modality samples, unimodal prototypes, and crossmodal prototypes as anchors to develop contrastive learning approaches, effectively enhancing inter-class disparity while reducing intra-class disparity from multiple perspectives. Experimental results indicate that our method outperforms the state-of-the-art (SOTA) methods, achieving improvements of 1.53% and 0.91% in AUC metrics on the MEN and Derm7pt datasets, respectively. The code is available at https://github.com/IsDling/CFCML.

---

### AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture Search

Authors: Yun Chen, Moyu Zhang, Jinxin Hu, Yu Zhang, Xiaoyi Zeng
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.20014v1

Neural Architecture Search (NAS) deployment in industrial production systems faces a fundamental validation bottleneck: verifying a single candidate architecture pi requires evaluating the deployed ensemble of M models, incurring prohibitive O(M) computational cost per candidate. This cost barrier severely limits architecture iteration frequency in real-world applications where ensembles (M=50-200) are standard for robustness. This work introduces Ensemble-Decoupled Architecture Search, a framework that leverages ensemble theory to predict system-level performance from single-learner evaluation. We establish the Ensemble-Decoupled Theory with a sufficient condition for monotonic ensemble improvement under homogeneity assumptions: a candidate architecture pi yields lower ensemble error than the current baseline if rho(pi) < rho(pi_old) - (M / (M - 1)) * (Delta E(pi) / sigma^2(pi)), where Delta E, rho, and sigma^2 are estimable from lightweight dual-learner training. This decouples architecture search from full ensemble training, reducing per-candidate search cost from O(M) to O(1) while maintaining O(M) deployment cost only for validated winners. We unify solution strategies across pipeline continuity: (1) closed-form optimization for tractable continuous pi (exemplified by feature bagging in CTR prediction), (2) constrained differentiable optimization for intractable continuous pi, and (3) LLM-driven search with iterative monotonic acceptance for discrete pi. The framework reveals two orthogonal improvement mechanisms -- base diversity gain and accuracy gain -- providing actionable design principles for industrial-scale NAS. All theoretical derivations are rigorous with detailed proofs deferred to the appendix. Comprehensive empirical validation will be included in the journal extension of this work.

---

### Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features

Authors: Zheng Gao, Debin Meng, Yunqi Miao, Zhensong Zhang, Songcen Xu, Ioannis Patras, Jifei Song
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.20012v2

Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference image in the generation. Although effective, these works mainly have two limitations: (1) foundation models pre-trained for generic tasks struggle to capture makeup styles; (2) the makeup features of reference image are injected to the diffusion denoising model as a whole for global makeup transfer, overlooking the facial region-aware makeup features (i.e., eyes, mouth, etc) and limiting the regional controllability for region-specific makeup transfer. To address these, in this work, we propose Facial Region-Aware Makeup features (FRAM), which has two stages: (1) makeup CLIP fine-tuning; (2) identity and facial region-aware makeup injection. For makeup CLIP fine-tuning, unlike prior works using off-the-shelf CLIP, we synthesize annotated makeup style data using GPT-o3 and text-driven image editing model, and then use the data to train a makeup CLIP encoder through self-supervised and image-text contrastive learning. For identity and facial region-aware makeup injection, we construct before-and-after makeup image pairs from the edited images in stage 1 and then use them to learn to inject identity of source image and makeup of reference image to the diffusion denoising model for makeup transfer. Specifically, we use learnable tokens to query the makeup CLIP encoder to extract facial region-aware makeup features for makeup injection, which is learned via an attention loss to enable regional control. As for identity injection, we use a ControlNet Union to encode source image and its 3D mesh simultaneously. The experimental results verify the superiority of our regional controllability and our makeup transfer performance. Code is available at https://github.com/zaczgao/Facial_Region-Aware_Makeup.

---

### A Super Fast K-means for Indexing Vector Embeddings

Authors: Leonardo Kuffo, Sven Hepkema, Peter Boncz
Published: 2026-03-20
Categories: cs.LG, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2603.20009v1

We present SuperKMeans: a k-means variant designed for clustering collections of high-dimensional vector embeddings. SuperKMeans' clustering is up to 7x faster than FAISS and Scikit-Learn on modern CPUs and up to 4x faster than cuVS on GPUs (Figure 1), while maintaining the quality of the resulting centroids for vector similarity search tasks. SuperKMeans acceleration comes from reducing data-access and compute overhead by reliably and efficiently pruning dimensions that are not needed to assign a vector to a centroid. Furthermore, we present Early Termination by Recall, a novel mechanism that early-terminates k-means when the quality of the centroids for retrieval tasks stops improving across iterations. In practice, this further reduces runtimes without compromising retrieval quality. We open-source our implementation at https://github.com/cwida/SuperKMeans

---

### Physics-Informed Long-Range Coulomb Correction for Machine-learning Hamiltonians

Authors: Yang Zhong, Xiwen Li, Xingao Gong, Hongjun Xiang
Published: 2026-03-20
Categories: physics.comp-ph, cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2603.20007v1

Machine-learning electronic Hamiltonians achieve orders-of-magnitude speedups over density-functional theory, yet current models omit long-range Coulomb interactions that govern physics in polar crystals and heterostructures. We derive closed-form long-range Hamiltonian matrix elements in a nonorthogonal atomic-orbital basis through variational decomposition of the electrostatic energy, deriving a variationally consistent mapping from the electron density matrix to effective atomic charges. We implement this framework in HamGNN-LR, a dual-channel architecture combining E(3)-equivariant message passing with reciprocal-space Ewald summation. Benchmarks demonstrate that physics-based long-range corrections are essential: purely data-driven attention mechanisms fail to capture macroscopic electrostatic potentials. Benchmarks on polar ZnO slabs, CdSe/ZnS heterostructures, and GaN/AlN superlattices show two- to threefold error reductions and robust transferability to systems far beyond training sizes, eliminating the characteristic staircase artifacts that plague short-range models in the presence of built-in electric fields.

---

### NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness

Authors: Haoyue Liu, Jinghan Xu, Luxin Feng, Hanyu Zhou, Haozhi Zhao, Yi Chang, Luxin Yan
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.20005v1

High-quality imaging of dynamic scenes in extremely low-light conditions is highly challenging. Photon scarcity induces severe noise and texture loss, causing significant image degradation. Event cameras, featuring a high dynamic range (120 dB) and high sensitivity to motion, serve as powerful complements to conventional cameras by offering crucial cues for preserving subtle textures. However, most existing approaches emphasize texture recovery from events, while paying little attention to image noise or the intrinsic noise of events themselves, which ultimately hinders accurate pixel reconstruction under photon-starved conditions. In this work, we propose NEC-Diff, a novel diffusion-based event-RAW hybrid imaging framework that extracts reliable information from heavily noisy signals to reconstruct fine scene structures. The framework is driven by two key insights: (1) combining the linear light-response property of RAW images with the brightness-change nature of events to establish a physics-driven constraint for robust dual-modal denoising; and (2) dynamically estimating the SNR of both modalities based on denoising results to guide adaptive feature fusion, thereby injecting reliable cues into the diffusion process for high-fidelity visual reconstruction. Furthermore, we construct the REAL (Raw and Event Acquired in Low-light) dataset which provides 47,800 pixel-aligned low-light RAW images, events, and high-quality references under 0.001-0.8 lux illumination. Extensive experiments demonstrate the superiority of NEC-Diff under extreme darkness. The project are available at: https://github.com/jinghan-xu/NEC-Diff.

---

### Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering

Authors: Yuxuan Zhu, Tengjun Jin, Yoojin Choi, Daniel Kang
Published: 2026-03-20
Categories: cs.DB, cs.CL
arXiv: https://arxiv.org/abs/2603.20004v4

Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research. Recent efforts have focused on improving accuracy by building increasingly complex multi-stage large LLM pipelines, layering task decomposition, schema linking, and model-based query selection on top of an LLM. Despite this growing complexity, a substantial gap (>10%) between such systems and human experts persists on benchmarks, suggesting that pipeline engineering alone has hit a ceiling. We show that human-level Text-to-SQL performance is achievable by fine-tuning an LLM using RLVR on clean data, without pipeline components. In this paper, we identified the dominant bottleneck for RLVR on Text-to-SQL: existing training data contains pervasive annotation errors that mislead optimization. To address this, we developed a multi-round, expert-driven verification pipeline and used it to curate BIRD-Platinum, a dataset of 2.5k verified instances sampled from BIRD Train, with errors corrected in 61% of instances. We show that fine-tuning Qwen3-235B on BIRD-Platinum yields consistent improvements (11-16%) over BIRD Train on Arcwise-Plat (an expert-verified version of BIRD) and Spider2, outperforming SOTA open-source systems by 0.6-16%. Furthermore, we diagnosed two failure modes of standard RLVR on Text-to-SQL. We find that (1) result-based rewards have non-trivial false positive rates, and (2) models systematically ignore the external knowledge in BIRD-style problems. To address them, we propose ReViSQL-BIRD, a specialized reward shaping method that combines result-based rewards with SQL equivalence verification and leverages process rewards for incentivizing external-knowledge use. We fine-tuned Kimi-K2.6 with ReViSQL-BIRD. On Arcwise-Plat, ReViSQL-BIRD-K2.6 is the first method to achieve human-level accuracy (92.96%), outperforming top five open-source systems by 10-22%.

---

### ReViSQL: Achieving Human-Level Text-to-SQL

Authors: Yuxuan Zhu, Tengjun Jin, Yoojin Choi, Daniel Kang
Published: 2026-03-20
Categories: cs.DB, cs.CL
arXiv: https://arxiv.org/abs/2603.20004v2

Translating natural language to SQL (Text-to-SQL) is a critical challenge in both database research and data analytics applications. Recent efforts have focused on enhancing SQL reasoning by developing large language models and AI agents that decompose Text-to-SQL tasks into manually designed, step-by-step pipelines. However, despite these extensive architectural engineering efforts, a significant gap remains: even state-of-the-art (SOTA) AI agents have not yet achieved the human-level accuracy on the BIRD benchmark. In this paper, we show that closing this gap does not require further architectural complexity, but rather clean training data to improve SQL reasoning of the underlying models. We introduce ReViSQL, a streamlined framework that achieves human-level accuracy on BIRD for the first time. Instead of complex AI agents, ReViSQL leverages reinforcement learning with verifiable rewards (RLVR) on BIRD-Verified, a dataset we curated comprising 2.5k verified Text-to-SQL instances based on the BIRD Train set. To construct BIRD-Verified, we design a data correction and verification workflow involving SQL experts. We identified and corrected data errors in 61.1% of a subset of BIRD Train. By training on BIRD-Verified, we show that improving data quality alone boosts the single-generation accuracy by 8.2-13.9% under the same RLVR algorithm. To further enhance performance, ReViSQL performs inference-time scaling via execution-based reconciliation and majority voting. Empirically, we demonstrate the superiority of our framework with two model scales: ReViSQL-235B-A22B and ReViSQL-30B-A3B. On an expert-verified BIRD Mini-Dev set, ReViSQL-235B-A22B achieves 93.2% execution accuracy, exceeding the proxy human-level accuracy (92.96%) and outperforming the prior open-source SOTA method by 9.8%. Our lightweight ReViSQL-30B-A3B matches the prior SOTA at a 7.5$\times$ lower per-query cost.

---

### An Agentic Approach to Generating XAI-Narratives

Authors: Yifan He, David Martens
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.20003v1

Explainable AI (XAI) research has experienced substantial growth in recent years. Existing XAI methods, however, have been criticized for being technical and expert-oriented, motivating the development of more interpretable and accessible explanations. In response, large language model (LLM)-generated XAI narratives have been proposed as a promising approach for translating post-hoc explanations into more accessible, natural-language explanations. In this work, we propose a multi-agent framework for XAI narrative generation and refinement. The framework comprises the Narrator, which generates and revises narratives based on feedback from multiple Critic Agents on faithfulness and coherence metrics, thereby enabling narrative improvement through iteration. We design five agentic systems (Basic Design, Critic Design, Critic-Rule Design, Coherent Design, and Coherent-Rule Design) and systematically evaluate their effectiveness across five LLMs on five tabular datasets. Results validate that the Basic Design, the Critic Design, and the Critic-Rule Design are effective in improving the faithfulness of narratives across all LLMs. Claude-4.5-Sonnet on Basic Design performs best, reducing the number of unfaithful narratives by 90% after three rounds of iteration. To address recurrent issues, we further introduce an ensemble strategy based on majority voting. This approach consistently enhances performance for four LLMs, except for DeepSeek-V3.2-Exp. These findings highlight the potential of agentic systems to produce faithful and coherent XAI narratives.

---

### When Contextual Inference Fails: Cancelability in Interactive Instruction Following

Authors: Natalia Bila, Kata Naszádi, Alexandra Mayn, Christof Monz
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19997v2

We investigate the separation of literal interpretation from contextual inference in a collaborative block-building tasks, where an agent must resolve underspecified instructions using context. We adapt an existing two-speaker psycholinguistic paradigm into an interactive benchmark called Build What I Mean (BWIM). This setup contrasts a pragmatically cooperative speaker with one who is only literally reliable. In BWIM, models face underspecified instructions and must choose between making a contextual inference or requesting clarification at a small communication cost. Evaluating several state-of-the-art LLMs, we find a clear dissociation between judgment and action. Although models successfully detect speaker unreliability in explicit confidence ratings, they fail to leverage this awareness when taking action. Instead of deploying efficient clarification strategies, models default to suboptimal behaviors. These include partner-blind over-clarification and question-averse guessing under uncertainty. BWIM provides a controlled environment to evaluate online partner adaptation and contextual reasoning in interactive settings.

---

### When Contextual Inference Fails: Cancelability in Interactive Instruction Following

Authors: Natalia Bila, Kata Naszádi, Alexandra Mayn, Christof Monz
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19997v1

We investigate the separation of literal interpretation from contextual inference in a collaborative block-building task where a builder must resolve underspecified instructions using contextual inferences. Building on an existing two-speaker psycholinguistic paradigm -- which contrasts a pragmatically cooperative speaker with one who is only literally reliable -- we introduce Build What I Mean (BWIM), an interactive benchmark for contextual meaning construction. In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost. Evaluating several state-of-the-art LLMs, we find a dissociation between judgment and action: while models detect speaker unreliability in explicit confidence ratings, they fail to exploit this information to guide efficient clarification behavior. Instead, we observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.

---

### Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts

Authors: John Turnbull, Shivam Grover, Amin Jalali, Ali Etemad
Published: 2026-03-20
Categories: cs.CV, cs.LG, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2603.19994v1

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the first evaluation of TTA methods for FER under natural domain shifts, performing cross-dataset experiments with widely used FER datasets. This moves beyond synthetic corruptions to examine real-world shifts caused by differing collection protocols, annotation standards, and demographics. Results show TTA can boost FER performance under natural shifts by up to 11.34\%. Entropy minimization methods such as TENT and SAR perform best when the target distribution is clean. In contrast, prototype adjustment methods like T3A excel under larger distributional distance scenarios. Finally, feature alignment methods such as SHOT deliver the largest gains when the target distribution is noisier than our source. Our cross-dataset analysis shows that TTA effectiveness is governed by the distributional distance and the severity of the natural shift across domains.

---

### MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI

Authors: Rozain Shakeel, Abdul Rahman Mohammad Ali, Muneeb Mushtaq, Tausifa Jan Saleem, Tajamul Ashraf
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19993v1

Despite the rapid progress of Multimodal Large Language Models (MLLMs), their ability to perform reliable visual grounding in high-stakes clinical software environments remains underexplored. Existing GUI benchmarks largely focus on isolated, single-step grounding queries, overlooking the sequential, workflow-driven reasoning required in real-world medical interfaces, where tasks evolve across independent steps and dynamic interface states. We introduce MedSPOT, a workflow-aware sequential grounding benchmark for clinical GUI environments. Unlike prior benchmarks that treat grounding as a standalone prediction task, MedSPOT models procedural interaction as a sequence of structured spatial decisions. The benchmark comprises 216 task-driven videos with 597 annotated keyframes, in which each task consists of 2 to 3 interdependent grounding steps within realistic medical workflows. This design captures interface hierarchies, contextual dependencies, and fine-grained spatial precision under evolving conditions. To evaluate procedural robustness, we propose a strict sequential evaluation protocol that terminates task assessment upon the first incorrect grounding prediction, explicitly measuring error propagation in multi-step workflows. We further introduce a comprehensive failure taxonomy, including edge bias, small-target errors, no prediction, near miss, far miss, and toolbar confusion, to enable systematic diagnosis of model behavior in clinical GUI settings. By shifting evaluation from isolated grounding to workflow-aware sequential reasoning, MedSPOT establishes a realistic and safety-critical benchmark for assessing multimodal models in medical software environments. Code and data are available at: https://github.com/Tajamul21/MedSPOT.

---

### Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States

Authors: Yurun Yuan, Tengyang Xie
Published: 2026-03-20
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.19987v1

Reinforcement learning (RL) has become a standard paradigm for post-training and aligning Large Language Models (LLMs), yet recent evidence suggests it faces a persistent "capability ceiling": unlike classical RL systems that discover novel strategies, RL for LLMs often acts as a mere refiner of patterns already latent in pre-trained weights. In this work, we identify a fundamental structural bottleneck: while classical RL relies on compact, informative Markov states, current LLM post-training formulations are tethered to an ever-expanding history of actions. We revisit a classical principle long central to RL yet absent from LLM post-training: explicit Markov states. Theoretically, we provide rigorous guarantees demonstrating that leveraging estimated Markov states can significantly reduce sample complexity. Empirically, we show that introducing Markov states consistently breaks the performance boundaries of standard RL post-training across a suite of complex logic puzzles. Our findings suggest that moving beyond "history-as-state" modeling in favor of structured Markovian representations is essential for unlocking open-ended discovery and genuinely new reasoning capabilities in Generative AI.

---

### X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving

Authors: Chaoda Zheng, Sean Li, Jinhao Deng, Zhennan Wang, Shijia Chen, Liqiang Xiao, Ziheng Chi, Hongbin Lin, Kangjie Chen, Boyang Wang, Yu Zhang, Xianming Liu
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.19979v2

Scalable and reliable evaluation is increasingly critical in the end-to-end era of autonomous driving, where vision--language--action (VLA) policies directly map raw sensor streams to driving actions. Yet, current evaluation pipelines still rely heavily on real-world road testing, which is costly, biased toward limited scenario coverage, and difficult to reproduce. These challenges motivate a real-world simulator that can generate realistic future observations under proposed actions, while remaining controllable and stable over long horizons. We present X-World, an action-conditioned multi-camera generative world model that simulates future observations directly in video space. Given synchronized multi-view camera history and a future action sequence, X-World generates future multi-camera video streams that follow the commanded actions. To ensure reproducible and editable scene rollouts, X-World further supports optional controls over dynamic traffic agents and static road elements, and retains a text-prompt interface for appearance-level control (e.g., weather and time of day). Beyond world simulation, X-World also enables video style transfer by conditioning on appearance prompts while preserving the underlying action and scene dynamics. At the core of X-World is a multi-view latent video generator designed to explicitly encourage cross-view geometric consistency and temporal coherence under diverse control signals. Experiments show that X-World achieves high-quality multi-view video generation with (i) strong view consistency across cameras, (ii) stable temporal dynamics over long rollouts, and (iii) high controllability with strict action following and faithful adherence to optional scene controls. These properties make X-World a practical foundation for scalable and reproducible evaluation.

---

### Promoting Critical Thinking With Domain-Specific Generative AI Provocations

Authors: Thomas Şerban von Davier, Hao-Ping Lee, Jodi Forlizzi, Sauvik Das
Published: 2026-03-20
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.19975v1

The evidence on the effects of generative AI (GenAI) on critical thinking is mixed, with studies suggesting both potential harms and benefits depending on its implementation. Some argue that AI-driven provocations, such as questions asking for human clarification and justification, are beneficial for eliciting critical thinking. Drawing on our experience designing and evaluating two GenAI-powered tools for knowledge work, ArtBot in the domain of fine art interpretation and Privy in the domain of AI privacy, we reflect on how design decisions shape the form and effectiveness of such provocations. Our observations and user feedback suggest that domain-specific provocations, implemented through productive friction and interactions that depend on user contribution, can meaningfully support critical thinking. We present participant experiences with both prototypes and discuss how supporting critical thinking may require moving beyond static provocations toward approaches that adapt to user preferences and levels of expertise.

---

### Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance

Authors: Fazhong Liu, Zhuoyan Chen, Tu Lan, Haozhen Tan, Zhenyu Xu, Xiang Li, Guoxing Chen, Yan Meng, Haojin Zhu
Published: 2026-03-20
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.19974v1

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform in this emerging paradigm, introduces an extensible skill ecosystem that allows third-party developers to inject behavioral guidance through lifecycle hooks during agent initialization. While this design enhances automation and customization, it also opens a novel and unexplored attack surface. In this paper, we identify and systematically characterize guidance injection, a stealthy attack vector that embeds adversarial operational narratives into bootstrap guidance files. Unlike traditional prompt injection, which relies on explicit malicious instructions, guidance injection manipulates the agent's reasoning context by framing harmful actions as routine best practices. These narratives are automatically incorporated into the agent's interpretive framework and influence future task execution without raising suspicion.We construct 26 malicious skills spanning 13 attack categories including credential exfiltration, workspace destruction, privilege escalation, and persistent backdoor installation. We evaluate them using ORE-Bench, a realistic developer workspace benchmark we developed. Across 52 natural user prompts and six state-of-the-art LLM backends, our attacks achieve success rates from 16.0% to 64.2%, with the majority of malicious actions executed autonomously without user confirmation. Furthermore, 94% of our malicious skills evade detection by existing static and LLM-based scanners. Our findings reveal fundamental tensions in the design of autonomous agent ecosystems and underscore the urgent need for defenses based on capability isolation, runtime policy enforcement, and transparent guidance provenance.

---

### Model-Driven Learning-Based Physical Layer Authentication for Mobile Wi-Fi Devices

Authors: Yijia Guo, Junqing Zhang, Yao-Win Peter Hong, Stefano Tomasin
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19972v1

The rise of wireless technologies has made the Internet of Things (IoT) ubiquitous, but the broadcast nature of wireless communications exposes IoT to authentication risks. Physical layer authentication (PLA) offers a promising solution by leveraging unique characteristics of wireless channels. As a common approach in PLA, hypothesis testing yields a theoretically optimal Neyman-Pearson (NP) detector, but its reliance on channel statistics limits its practicality in real-world scenarios. In contrast, deep learning-based PLA approaches are practical but tend to be not optimal. To address these challenges, we proposed a learning-based PLA scheme driven by hypothesis testing and conducted extensive simulations and experimental evaluations using Wi-Fi. Specifically, we incorporated conditional statistical models into the hypothesis testing framework to derive a theoretically optimal NP detector. Building on this, we developed LiteNP-Net, a lightweight neural network driven by the NP detector. Simulation results demonstrated that LiteNP-Net could approach the performance of the NP detector even without prior knowledge of the channel statistics. To further assess its effectiveness in practical environments, we deployed an experimental testbed using Wi-Fi IoT development kits in various real-world scenarios. Experimental results demonstrated that the LiteNP-Net outperformed the conventional correlation-based method as well as state-of-the-art Siamese-based methods.

---

### Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs

Authors: Shaoshuai Du, Joze M. Rozanec, Andy Pimentel, Ana-Lucia Varbanescu
Published: 2026-03-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.19970v1

Although recent generative models can produce time series with close marginal distributions, they often face a fundamental tension between preserving global temporal structure and modeling stochastic local variations, particularly for highly volatile signals with weak or irregular periodicity. Direct distribution matching in such settings can amplify noise or suppress meaningful temporal patterns. In this work, we propose a structure-residual perspective on time-series generation, viewing temporal data as the combination of a structural backbone and stochastic residual dynamics, thereby motivating the separation of global organization from sample-level variability. Based on this insight, we represent time-series structure using a quantile-based transition graph that compactly captures global distributional and temporal dependencies. Building on this representation, we propose Graph2TS, a quantile-graph conditioned variational autoencoder that performs cross-modal generation from structural graphs to time series. By conditioning generation on structure rather than labels or metadata, the model preserves global temporal organization while enabling controlled stochastic variation. Experiments on diverse datasets, including sunspot, electricity load, ECG, and EEG signals, demonstrate improved distributional fidelity, temporal alignment, and representativeness compared to diffusion- and GAN-based baselines, highlighting structure-controlled and cross-modal generation as a promising direction for time-series modeling.

---

### 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

Authors: Tianbao Zhang, Zhenyu Liang, Zhenbo Song, Nana Wang, Xiaomei Zhang, Xudong Cai, Zheng Zhu, Kejian Wu, Gang Wang, Zhaoxin Fan
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19964v3

High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models are fundamentally limited by their scalability to real-world, high-resolution scenarios. Direct inference on 2K images with these models incurs prohibitive computational and memory demands, making practical deployment challenging. To tackle the issue, we present 2K Retrofit, a novel framework that enables efficient 2K-resolution inference for any geometric foundation model, without modifying or retraining the backbone. Our approach leverages fast coarse predictions and an entropy-based sparse refinement to selectively enhance high-uncertainty regions, achieving precise and high-fidelity 2K outputs with minimal overhead. Extensive experiments on widely used benchmark demonstrate that 2K Retrofit consistently achieves state-of-the-art accuracy and speed, bridging the gap between research advances and scalable deployment in high-resolution 3D vision applications. Code will be released upon acceptance.

---

### Channel Prediction-Based Physical Layer Authentication under Consecutive Spoofing Attacks

Authors: Yijia Guo, Junqing Zhang, Yao-Win Peter Hong
Published: 2026-03-20
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.19962v1

Wireless networks are highly vulnerable to spoofing attacks, especially when attackers transmit consecutive spoofing packets. Conventional physical layer authentication (PLA) methods have mostly focused on single-packet spoofing attack. However, under consecutive spoofing attacks, they become ineffective due to channel evolution caused by device mobility and channel fading. To address this challenge, we propose a channel prediction-based PLA framework. Specifically, a Transformer-based channel prediction module is employed to predict legitimate CSI measurements during spoofing interval, and the input of channel prediction module is adaptively updated with predicted or observed CSI measurements based on the authentication decision to ensure robustness against sustained spoofing. Simulation results under Rayleigh fading channels demonstrate that the proposed approach achieves low prediction error and significantly higher authentication accuracy than conventional benchmark, maintaining robustness even under extended spoofing attacks.

---