# Research Papers — 2026-03 · bundle page 24 of 243

> Full-text markdown of papers #1151–1200 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/24
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/23.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/25.md)

### Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning

Authors: Naveen Mysore
Published: 2026-03-28
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2603.27389v2

Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without tools to detect such violations. This paper introduces a prediction-based Markov Violation Score (MVS) that quantifies non-Markovian structure in observation trajectories. A random forest first removes nonlinear Markov-compliant dynamics; ridge regression then tests whether historical observations reduce prediction error on the residuals beyond what the current observation provides. The resulting score is bounded in (0, 1) and requires no causal graph construction. Evaluation spans six environments (CartPole, Pendulum, Acrobot, HalfCheetah, Hopper, Walker2d), three algorithms (PPO, A2C, SAC), controlled AR(1) noise at six intensity levels, and 10 seeds per condition. In post-hoc detection, 7 of 16 environment-algorithm pairs, primarily high-dimensional locomotion tasks, show significant positive monotonicity between noise intensity and MVS (Spearman rho up to 0.78, confirmed under repeated-measures analysis); under training-time noise, 13 of 16 pairs exhibit statistically significant reward degradation. An inversion phenomenon is documented in low-dimensional environments where the random forest absorbs the noise signal, causing MVS to decrease as true violations grow, a failure mode analyzed in detail. A practical utility experiment demonstrates that MVS correctly identifies partial observability and guides architecture selection, fully recovering performance lost to non-Markovian observations. Source code to reproduce all results is available at https://github.com/NAVEENMN/Markovianes.

---

### Active In-Context Learning for Tabular Foundation Models

Authors: Wilailuck Treerath, Fabrizio Pittorino
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27385v1

Active learning (AL) reduces labeling cost by querying informative samples, but in tabular settings its cold-start gains are often limited because uncertainty estimates are unreliable when models are trained on very few labels. Tabular foundation models such as TabPFN provide calibrated probabilistic predictions via in-context learning (ICL), i.e., without task-specific weight updates, enabling an AL regime in which the labeled context - rather than parameters - is iteratively optimized. We formalize Tabular Active In-Context Learning (Tab-AICL) and instantiate it with four acquisition rules: uncertainty (TabPFN-Margin), diversity (TabPFN-Coreset), an uncertainty-diversity hybrid (TabPFN-Hybrid), and a scalable two-stage method (TabPFN-Proxy-Hybrid) that shortlists candidates using a lightweight linear proxy before TabPFN-based selection. Across 20 classification benchmarks, Tab-AICL improves cold-start sample efficiency over retrained gradient-boosting baselines (CatBoost-Margin and XGBoost-Margin), measured by normalized AULC up to 100 labeled samples.

---

### Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression

Authors: Nazia Tasnim, Shrimai Prabhumoye, Bryan A. Plummer
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27383v2

Parameter Recombination (PR) methods aim to efficiently compose the weights of a neural network for applications like Parameter-Efficient FineTuning (PEFT) and Model Compression (MC), among others. Most methods typically focus on one application of PR, which can make composing them challenging. For example, when deploying a large model you may wish to compress the model and also quickly adapt to new settings. However, PEFT methods often can still contain millions of parameters. This may be small compared to the original model size, but can be problematic in resource constrained deployments like edge devices, where they take a larger portion of the compressed model's parameters. To address this, we present Coefficient-gated weight Recombination by Interpolated Shared basis Projections (CRISP), a general approach that seamlessly integrates multiple PR tasks within the same framework. CRISP accomplishes this by factorizing pretrained weights into basis matrices and their component mixing projections. Sharing basis matrices across layers and adjusting its size enables us to perform MC, whereas the mixer weight's small size (fewer than 200 in some experiments) enables CRISP to support PEFT. Experiments show CRISP outperforms methods from prior work capable of dual-task applications by 4-5\% while also outperforming the state-of-the-art in PEFT by 1.5\% and PEFT+MC combinations by 1\%. Our code is available on the repository: https://github.com/appledora/CRISP-CVPR26.

---

### Where Does AI Leave a Footprint? Children's Reasoning About AI's Environmental Costs

Authors: Aayushi Dangol, Robert Wolfe, Nisha Devasia, Mitsuka Kiyohara, Jason Yip, Julie A. Kientz
Published: 2026-03-28
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.27376v1

Two of the most socially consequential issues facing today's children are the rise of artificial intelligence (AI) and the rapid changes to the earth's climate. Both issues are complex and contested, and they are linked through the notable environmental costs of AI use. Using a systems thinking framework, we developed an interactive system called Ecoprompt to help children reason about the environmental impact of AI. EcoPrompt combines a prompt-level environmental footprint calculator with a simulation game that challenges players to reason about the impact of AI use on natural resources that the player manages. We evaluated the system through two participatory design sessions with 16 children ages 6-12. Our findings surfaced children's perspectives on societal and environmental tradeoffs of AI use, as well as their sense of agency and responsibility. Taken together, these findings suggest opportunities for broadening AI literacy to include systems-level reasoning about AI's environmental impact.

---

### Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models

Authors: Yuhang Han, Yuyang Wu, Zhengbo Jiao, Yiyu Wang, Xuyang Liu, Shaobo Wang, Hanlin Xu, Xuming Hu, Linfeng Zhang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27375v1

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains constrained by a structural representational bottleneck. Existing approaches generally lack explicit modeling and effective utilization of visual information, preventing visual representations from being tightly coupled with the reinforcement learning optimization process and thereby limiting further improvements in multimodal reasoning performance. To address this limitation, we propose KAWHI (Key-Region Aligned Weighted Harmonic Incentive), a plug-and-play reward reweighting mechanism that explicitly incorporates structured visual information into uniform reward policy optimization methods (e.g., GRPO and GSPO). The method adaptively localizes semantically salient regions through hierarchical geometric aggregation, identifies vision-critical attention heads via structured attribution, and performs paragraph-level credit reallocation to align spatial visual evidence with semantically decisive reasoning steps. Extensive empirical evaluations on diverse reasoning benchmarks substantiate KAWHI as a general-purpose enhancement module, consistently improving the performance of various uniform reward optimization methods. Project page: KAWHI (https://kawhiiiileo.github.io/KAWHI_PAGE/)

---

### HMPDM: A Diffusion Model for Driving Video Prediction with Historical Motion Priors

Authors: Ke Li, Tianjia Yang, Kaidi Liang, Xianbiao Hu, Ruwen Qin
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27371v1

Video prediction is a useful function for autonomous driving, enabling intelligent vehicles to reliably anticipate how driving scenes will evolve and thereby supporting reasoning and safer planning. However, existing models are constrained by multi-stage training pipelines and remain insufficient in modeling the diverse motion patterns in real driving scenes, leading to degraded temporal consistency and visual quality. To address these challenges, this paper introduces the historical motion priors-informed diffusion model (HMPDM), a video prediction model that leverages historical motion priors to enhance motion understanding and temporal coherence. The proposed deep learning system introduces three key designs: (i) a Temporal-aware Latent Conditioning (TaLC) module for implicit historical motion injection; (ii) a Motion-aware Pyramid Encoder (MaPE) for multi-scale motion representation; (iii) a Self-Conditioning (SC) strategy for stable iterative denoising. Extensive experiments on the Cityscapes and KITTI benchmarks demonstrate that HMPDM outperforms state-of-the-art video prediction methods with efficiency, achieving a 28.2% improvement in FVD on Cityscapes under the same monocular RGB input configuration setting. The implementation codes are publicly available at https://github.com/KELISBU/HMPDM.

---

### The Risk Quadrangle in Optimization: An Overview with Recent Results and Extensions

Authors: Bogdan Grechuk, Anton Malandii, Terry Rockafellar, Stan Uryasev
Published: 2026-03-28
Categories: math.OC, math.PR, math.ST, q-fin.RM, stat.ML
arXiv: https://arxiv.org/abs/2603.27370v1

This paper revisits and extends the 2013 development by Rockafellar and Uryasev of the Risk Quadrangle (RQ) as a unified scheme for integrating risk management, optimization, and statistical estimation. The RQ features four stochastics-oriented functionals -- risk, deviation, regret, and error, along with an associated statistic, and articulates their revealing and in some ways surprising interrelationships and dualizations. Additions to the RQ framework that have come to light since 2013 are reviewed in a synthesis focused on both theoretical advancements and practical applications. New quadrangles -- superquantile, superquantile norm, expectile, biased mean, quantile symmetric average union, and $\varphi$-divergence-based quadrangles -- offer novel approaches to risk-sensitive decision-making across various fields such as machine learning, statistics, finance, and PDE-constrained optimization. The theoretical contribution comes in axioms for ``subregularity'' relaxing ``regularity'' of the quadrangle functionals, which is too restrictive for some applications. The main RQ theorems and connections are revisited and rigorously extended to this more ample framework. Examples are provided in portfolio optimization, regression, and classification, demonstrating the advantages and the role played by duality, especially in ties to robust optimization and generalized stochastic divergences.

---

### Falcon Perception

Authors: Aviraj Bevli, Sofian Chaybouti, Yasser Dahou, Hakim Hacid, Ngoc Dung Huynh, Phuc H. Le Khac, Sanath Narayan, Wamiq Reyaz Para, Ankit Singh
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27365v1

Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is this architectural separation essential or can a single early-fusion stack do both perception and task modeling at scale? We introduce Falcon Perception, a unified dense Transformer that processes image patches and text tokens in a shared parameter space from the first layer, using a hybrid attention pattern (bidirectional among image tokens, causal for prediction tokens) to combine global visual context with autoregressive, variable-length instance generation. To keep dense outputs practical, Falcon Perception retains a lightweight token interface and decodes continuous spatial outputs with specialized heads, enabling parallel high-resolution mask prediction. Our design promotes simplicity: we keep a single scalable backbone and shift complexity toward data and training signals, adding only small heads where outputs are continuous and dense. On SA-Co, Falcon Perception improves mask quality to 68.0 Macro-F$_1$ compared to 62.3 of SAM3. We also introduce PBench, a benchmark targeting compositional prompts (OCR, spatial constraints, relations) and dense long-context regimes, where the model shows better gains. Finally, we extend the same early-fusion recipe to Falcon OCR: a compact 300M-parameter model which attains 80.3% on olmOCR and 88.64 on OmniDocBench.

---

### Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance

Authors: Jyotsana Khatri, Manasi Patwardhan
Published: 2026-03-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27360v1

Rebuttal generation is a critical component of the peer review process for scientific papers, enabling authors to clarify misunderstandings, correct factual inaccuracies, and guide reviewers toward a more accurate evaluation. We observe that Large Language Models (LLMs) often struggle to perform targeted refutation and maintain accurate factual grounding when used directly for rebuttal generation, highlighting the need for structured reasoning and author intervention. To address this, in the paper, we introduce DEFEND an LLM based tool designed to explicitly execute the underlying reasoning process of automated rebuttal generation, while keeping the author-in-the-loop. As opposed to writing the rebuttals from scratch, the author needs to only drive the reasoning process with minimal intervention, leading an efficient approach with minimal effort and less cognitive load. We compare DEFEND against three other paradigms: (i) Direct rebuttal generation using LLM (DRG), (ii) Segment-wise rebuttal generation using LLM (SWRG), and (iii) Sequential approach (SA) of segment-wise rebuttal generation without author intervention. To enable finegrained evaluation, we extend the ReviewCritique dataset, creating review segmentation, deficiency, error type annotations, rebuttal-action labels, and mapping to gold rebuttal segments. Experimental results and a user study demonstrate that directly using LLMs perform poorly in factual correctness and targeted refutation. Segment-wise generation and the automated sequential approach with author-in-the-loop, substantially improve factual correctness and strength of refutation.

---

### Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation

Authors: Amir Zeldes, Katherine Conhaim, Lauren Levine
Published: 2026-03-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27358v2

Despite a long tradition of work on extractive summarization, which by nature aims to recover the most important propositions in a text, little work has been done on operationalizing graded proposition salience in naturally occurring data. In this paper, we adopt graded summarization-based salience as a metric from previous work on Salient Entity Extraction (SEE) and adapt it to quantify proposition salience. We define the annotation task, apply it to a small multi-genre dataset, evaluate agreement and carry out a preliminary study of the relationship between our metric and notions of discourse unit centrality in discourse parsing following Rhetorical Structure Theory (RST).

---

### Guided Lensless Polarization Imaging

Authors: Noa Kraicer, Erez Yosef, Raja Giryes
Published: 2026-03-28
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.27357v1

Polarization imaging captures the polarization state of light, revealing information invisible to the human eye yet valuable in domains such as biomedical diagnostics, autonomous driving, and remote sensing. However, conventional polarization cameras are often expensive, bulky, or both, limiting their practical use. Lensless imaging offers a compact, low-cost alternative by replacing the lens with a simple optical element like a diffuser and performing computational reconstruction, but existing lensless polarization systems suffer from limited reconstruction quality. To overcome these limitations, we introduce a RGB-guided lensless polarization imaging system that combines a compact polarization-RGB sensor with an auxiliary, widely available conventional RGB camera providing structural guidance. We reconstruct multi-angle polarization images for each RGB color channel through a two-stage pipeline: a physics-based inversion recovers an initial polarization image, followed by a Transformer-based fusion network that refines this reconstruction using the RGB guidance image from the conventional RGB camera. Our two-stage method significantly improves reconstruction quality and fidelity over lensless-only baselines, generalizes across datasets and imaging conditions, and achieves high-quality real-world results on our physical prototype lensless camera without any fine-tuning.

---

### Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

Authors: Maziar Kianimoghadam Jouneghani
Published: 2026-03-28
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.27356v1

Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric "black boxes," producing fluent rationales that overlook localized framing. Preliminary evidence from the multilingual Information Disorder (InDor) corpus suggests that existing models struggle to explain manipulated news consistently across communities. To address this gap, this ongoing study proposes a Hybrid Intelligence Loop, a human-in-the-loop (HITL) framework that grounds model assessment in human-written rationales from native-speaking annotators. The approach moves beyond static target-language few-shot prompting by pairing English task instructions with dynamically retrieved target-language exemplars drawn from filtered InDor annotations through In-Context Learning (ICL). In the initial pilot, the Exemplar Bank is seeded from these filtered annotations and used to compare static and adaptive prompting on Farsi and Italian news. The study evaluates span and severity prediction, the quality and cultural appropriateness of generated rationales, and model alignment across evaluator groups, providing a testbed for culturally grounded explainable AI.

---

### LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications

Authors: Alexandre Cristovão Maiorano
Published: 2026-03-28
Categories: cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2603.27355v2

We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract, then aggregates workflow success, policy compliance, groundedness, retrieval hit rate, cost, and p95 latency into scenario-weighted readiness scores with Pareto frontiers. We evaluate the harness on ticket-routing workflows and BEIR grounding tasks (SciFact and FiQA) with full Azure matrix coverage (162/162 valid cells across datasets, scenarios, retrieval depths, seeds, and models). Results show that readiness is not a single metric: on FiQA under sla-first at k=5, gpt-4.1-mini leads in readiness and faithfulness, while gpt-5.2 pays a substantial latency cost; on SciFact, models are closer in quality but still separable operationally. Ticket-routing regression gates consistently reject unsafe prompt variants, demonstrating that the harness can block risky releases instead of merely reporting offline scores. The result is a reproducible, operationally grounded framework for deciding whether an LLM or RAG system is ready to ship.

---

### Inference-Time Structural Reasoning for Compositional Vision-Language Understanding

Authors: Amartya Bhattacharya
Published: 2026-03-28
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.27349v1

Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified evaluation and augmentation framework benchmarking four architecturally diverse VLMs,CLIP, BLIP, LLaVA, and Qwen3-VL-8B-Thinking,on the Winoground benchmark under plain and scene-graph-augmented regimes. We introduce a dependency-based TextSceneGraphParser (spaCy) extracting subject-relation-object triples, and a Graph Asymmetry Scorer using optimal bipartite matching to inject structural relational priors. Caption ablation experiments (subject-object masking and swapping) reveal that Qwen3-VL-8B-Thinking achieves a group score of 62.75, far above all encoder-based models, while a proposed multi-turn SG filtering strategy further lifts it to 66.0, surpassing prior open-source state-of-the-art. We analyze the capability augmentation tradeoff and find that SG augmentation benefits already capable models while providing negligible or negative gains for weaker baselines. Code: https://github.com/amartyacodes/Inference-Time-Structural-Reasoning-for-Compositional-Vision-Language-Understanding

---

### Embedding Provenance in Computer Vision Datasets with JSON-LD

Authors: Lynn Vonderhaar, Timothy Elvira, Tyler Thomas Procko, Omar Ochoa
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27348v1

With the ubiquity of computer vision in industry, the importance of image provenance is becoming more apparent. Provenance provides information about the origin and derivation of some resource, e.g., an image dataset, enabling users to trace data changes to better understand the expected behaviors of downstream models trained on such data. Provenance may also help with data maintenance by ensuring compliance, supporting audits and improving reusability. Typically, if provided, provenance is stored separately, e.g., within a text file, leading to a loss of descriptive information for key details like image capture settings, data preprocessing steps, and model architecture or iteration. Images often lack the information detailing the parameters of their creation or compilation. This paper proposes a novel schema designed to structure image provenance in a manageable and coherent format. The approach utilizes JavaScript Object Notation for Linked Data (JSON-LD), embedding this provenance directly within the image file. This offers two significant benefits: (1) it aligns image descriptions with a robust schema inspired by and linked to established standards, and (2) it ensures that provenance remains intrinsically tied to images, preventing loss of information and enhancing system qualities, e.g., maintainability and adaptability. This approach emphasizes maintaining the direct connection between vision resources and their provenance.

---

### D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learning in Robotic Manipulation

Authors: Yu Zhang, Karl Mason
Published: 2026-03-28
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.27346v2

Robotic manipulation remains challenging for reinforcement learning due to contact-rich dynamics, long horizons, and training instability. Although off-policy actor-critic algorithms such as SAC and TD3 perform well in simulation, they often suffer from policy oscillations and performance collapse in realistic settings, partly due to experience replay strategies that ignore the differing data requirements of the actor and the critic. We propose D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay, a replay framework that decouples actor and critic sampling while maintaining a shared replay buffer. The critic leverages prioritized replay for efficient value learning, whereas the actor is updated using low-error transitions to stabilize policy optimization. An adaptive anchor mechanism balances uniform and prioritized sampling based on the coefficient of variation of TD errors, and a Huber-based critic objective further improves robustness under heterogeneous reward scales. We evaluate D-SPEAR on challenging robotic manipulation tasks from the robosuite benchmark, including Block-Lifting and Door-Opening. Results demonstrate that D-SPEAR consistently outperforms strong off-policy baselines, including SAC, TD3, and DDPG, in both final performance and training stability, with ablation studies confirming the complementary roles of the actorside and critic-side replay streams.

---

### TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR

Authors: Ted Lentsch, Santiago Montiel-Marín, Holger Caesar, Dariu M. Gavrila
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27344v1

LiDAR perception is fundamental to robotics, enabling machines to understand their environment in 3D. A crucial task for LiDAR-based scene understanding and navigation is ground segmentation. However, existing methods are either handcrafted for specific sensor configurations or rely on costly per-point manual labels, severely limiting their generalization and scalability. To overcome this, we introduce TerraSeg, the first self-supervised, domain-agnostic model for LiDAR ground segmentation. We train TerraSeg on OmniLiDAR, a unified large-scale dataset that aggregates and standardizes data from 12 major public benchmarks. Spanning almost 22 million raw scans across 15 distinct sensor models, OmniLiDAR provides unprecedented diversity for learning a highly generalizable ground model. To supervise training without human annotations, we propose PseudoLabeler, a novel module that generates high-quality ground and non-ground labels through self-supervised per-scan runtime optimization. Extensive evaluations demonstrate that, despite using no manual labels, TerraSeg achieves state-of-the-art results on nuScenes, SemanticKITTI, and Waymo Perception while delivering real-time performance. Our code and model weights are publicly available.

---

### WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking

Authors: Dengzhe Hou, Lingyu Jiang, Deng Li, Zirui Li, Fangzhou Lin, Kazunori D Yamada
Published: 2026-03-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27343v2

Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a probe of cumulative state tracking, the ability to maintain and update intermediate results across K sequential operations within a single query, without a scratchpad. Unlike multi-step agent benchmarks that stress task orchestration, WMF-AM isolates within-pass cumulative load by parameterizing depth K. The core probe uses arithmetic accumulation on 28 models from 12 families (0.5B to frontier); a matched non-arithmetic extension (permissions, schedules, inventories) confirms the design generalizes beyond arithmetic. Three construct-isolation ablations confirm that cumulative load, not arithmetic skill or entity tracking, drives difficulty. We release WMF-AM as a lightweight, recalibratable diagnostic for characterizing where models degrade under cumulative load. Code and data can be accessed at https://github.com/dengzhe-hou/WMF-AM

---

### A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling

Authors: Kirill Skobelev, Eric Fithian, Yegor Baranovski, Jack Cook, Sandeep Angara, Shauna Otto, Zhuang-Fang Yi, John Zhu, Neeraj Mainkar, Margaux Masson-Forsythe, Daniel A. Donoho, X. Y. Han
Published: 2026-03-28
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.27341v5

Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites. Since surgery requires integrating disparate tasks, generally-capable AI models could be particularly attractive as a collaborative tool if performance could be improved. On the one hand, the canonical approach of scaling architecture size and training data is attractive, especially since there are millions of hours of surgical video data generated per year. On the other hand, preparing surgical data for AI training requires significantly higher levels of professional expertise, and training on that data requires expensive computational resources. These trade-offs paint an uncertain picture of whether and to-what-extent modern AI could aid surgical practice. In this paper, we explore this question through a case study of surgical tool detection using state-of-the-art AI methods available in 2026. We demonstrate that even with multi-billion parameter models and extensive training, current Vision Language Models fall short in the seemingly simple task of tool detection in neurosurgery. Additionally, we show scaling experiments indicating that increasing model size and training time only leads to diminishing improvements in relevant performance metrics. Thus, our experiments suggest that current models could still face significant obstacles in surgical use cases. Moreover, some obstacles cannot be simply ``scaled away'' with additional compute and persist across diverse model architectures, raising the question of whether data and label availability are the only limiting factors. We discuss the main contributors to these constraints and advance potential solutions.

---

### A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling

Authors: Kirill Skobelev, Eric Fithian, Yegor Baranovski, Jack Cook, Sandeep Angara, Shauna Otto, Zhuang-Fang Yi, John Zhu, Daniel A. Donoho, X. Y. Han, Neeraj Mainkar, Margaux Masson-Forsythe
Published: 2026-03-28
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.27341v3

Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites. Since surgery requires integrating disparate tasks, generally-capable AI models could be particularly attractive as a collaborative tool if performance could be improved. On the one hand, the canonical approach of scaling architecture size and training data is attractive, especially since there are millions of hours of surgical video data generated per year. On the other hand, preparing surgical data for AI training requires significantly higher levels of professional expertise, and training on that data requires expensive computational resources. These trade-offs paint an uncertain picture of whether and to-what-extent modern AI could aid surgical practice. In this paper, we explore this question through a case study of surgical tool detection using state-of-the-art AI methods available in 2026. We demonstrate that even with multi-billion parameter models and extensive training, current Vision Language Models fall short in the seemingly simple task of tool detection in neurosurgery. Additionally, we show scaling experiments indicating that increasing model size and training time only leads to diminishing improvements in relevant performance metrics. Thus, our experiments suggest that current models could still face significant obstacles in surgical use cases. Moreover, some obstacles cannot be simply ``scaled away'' with additional compute and persist across diverse model architectures, raising the question of whether data and label availability are the only limiting factors. We discuss the main contributors to these constraints and advance potential solutions.

---

### EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification

Authors: Pengcheng Pan, Yonekura Shogo, Kuniyoshi Yasuo
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27340v1

Optimizing vision models purely for classification accuracy can impose an alignment tax, degrading human-like scanpaths and limiting interpretability. We introduce EVA, a neuroscience-inspired hard-attention mechanistic testbed that makes the performance-human-likeness trade-off explicit and adjustable. EVA samples a small number of sequential glimpses using a minimal fovea-periphery representation with CNN-based feature extractor and integrates variance control and adaptive gating to stabilize and regulate attention dynamics. EVA is trained with the standard classification objective without gaze supervision. On CIFAR-10 with dense human gaze annotations, EVA improves scanpath alignment under established metrics such as DTW, NSS, while maintaining competitive accuracy. Ablations show that CNN-based feature extraction drives accuracy but suppresses human-likeness, whereas variance control and gating restore human-aligned trajectories with minimal performance loss. We further validate EVA's scalability on ImageNet-100 and evaluate scanpath alignment on COCO-Search18 without COCO-Search18 gaze supervision or finetuning, where EVA yields human-like scanpaths on natural scenes without additional training. Overall, EVA provides a principled framework for trustworthy, human-interpretable active vision.

---

### CounterMoral: Editing Morals in Language Models

Authors: Michael Ripa, Jim Davies
Published: 2026-03-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27338v1

Recent advancements in language model technology have significantly enhanced the ability to edit factual information. Yet, the modification of moral judgments, a crucial aspect of aligning models with human values, has garnered less attention. In this work, we introduce CounterMoral, a benchmark dataset crafted to assess how well current model editing techniques modify moral judgments across diverse ethical frameworks. We apply various editing techniques to multiple language models and evaluate their performance. Our findings contribute to the evaluation of language models designed to be ethical.

---

### PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Authors: Yiqing Zhang, Xiaozhong Liu, Fabricio Murai
Published: 2026-03-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27335v1

Trustworthy biomedical question answering (QA) systems must not only provide accurate answers but also justify them with current, verifiable evidence. Retrieval-augmented approaches partially address this gap but lack mechanisms to iteratively refine poor queries, whereas self-reflection methods kick in only after full retrieval is completed. In this context, we introduce PubMed Reasoner, a biomedical QA agent composed of three stages: self-critic query refinement evaluates MeSH terms for coverage, alignment, and redundancy to enhance PubMed queries based on partial (metadata) retrieval; reflective retrieval processes articles in batches until sufficient evidence is gathered; and evidence-grounded response generation produces answers with explicit citations. PubMed Reasoner with a GPT-4o backbone achieves 78.32% accuracy on PubMedQA, slightly surpassing human experts, and showing consistent gains on MMLU Clinical Knowledge. Moreover, LLM-as-judge evaluations prefer our responses across: reasoning soundness, evidence grounding, clinical relevance, and trustworthiness. By orchestrating retrieval-first reasoning over authoritative sources, our approach provides practical assistance to clinicians and biomedical researchers while controlling compute and token costs.

---

### ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair

Authors: Jia Li, Zeyang Zhuang, Zhuangbin Chen, Yuxin Su, Wei Meng, Michael R. Lyu
Published: 2026-03-28
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.27333v1

Compilation errors pose pervasive and critical challenges in software development, significantly hindering productivity. Therefore, Automated Compilation Error Repair (ACER) techniques are proposed to mitigate these issues. Despite recent advancements in ACER, its real-world performance remains poorly evaluated. This can be largely attributed to the limitations of existing benchmarks, \ie decontextualized single-file data, lack of authentic source diversity, and biased local task modeling that ignores crucial repository-level complexities. To bridge this critical gap, we propose ComBench, the first repository-level, reproducible real-world benchmark for C/C++ compilation error repair. ComBench is constructed through a novel, automated framework that systematically mines real-world failures from the GitHub CI histories of large-scale open-source projects. Our framework contributes techniques for the high-precision identification of ground-truth repair patches from complex version histories and a high-fidelity mechanism for reproducing the original, ephemeral build environments. To ensure data quality, all samples in ComBench are execution-verified -- guaranteeing reproducible failures and build success with ground-truth patches. Using ComBench, we conduct a comprehensive evaluation of 12 modern LLMs under both direct and agent-based repair settings. Our experiments reveal a significant gap between a model's ability to achieve syntactic correctness (a 73% success rate for GPT-5) and its ability to ensure semantic correctness (only 41% of its patches are valid). We also find that different models exhibit distinct specializations for different error types. ComBench provides a robust and realistic platform to guide the future development of ACER techniques capable of addressing the complexities of modern software development.

---

### Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models

Authors: Kaishen Wang, Heng Huang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27332v2

Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and image generation are tightly integrated within a shared architecture. Prior studies suggest that such reciprocity enhances cross-functionality performance through shared representations and joint optimization. However, the safety implications of this tight coupling remain largely unexplored, as existing safety research predominantly analyzes understanding and generation functionalities in isolation. In this work, we investigate whether cross-functionality reciprocity itself constitutes a structural source of vulnerability in UMMs. We propose RICE: Reciprocal Interaction-based Cross-functionality Exploitation, a novel attack paradigm that explicitly exploits bidirectional interactions between understanding and generation. Using this framework, we systematically evaluate Generation-to-Understanding (G-U) and Understanding-to-Generation (U-G) attack pathways, demonstrating that unsafe intermediate signals can propagate across modalities and amplify safety risks. Extensive experiments show high Attack Success Rates (ASR) in both directions, revealing previously overlooked safety weaknesses inherent to UMMs.

---

### Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models

Authors: Kaishen Wang, Heng Huang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27332v1

Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and image generation are tightly integrated within a shared architecture. Prior studies suggest that such reciprocity enhances cross-functionality performance through shared representations and joint optimization. However, the safety implications of this tight coupling remain largely unexplored, as existing safety research predominantly analyzes understanding and generation functionalities in isolation. In this work, we investigate whether cross-functionality reciprocity itself constitutes a structural source of vulnerability in UMMs. We propose RICE: Reciprocal Interaction-based Cross-functionality Exploitation, a novel attack paradigm that explicitly exploits bidirectional interactions between understanding and generation. Using this framework, we systematically evaluate Generation-to-Understanding (G-U) and Understanding-to-Generation (U-G) attack pathways, demonstrating that unsafe intermediate signals can propagate across modalities and amplify safety risks. Extensive experiments show high Attack Success Rates (ASR) in both directions, revealing previously overlooked safety weaknesses inherent to UMMs.

---

### SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality

Authors: Qinghao Guan, Yuchen Pan, Donghao Li, Zishi Zhang, Yiyang Chen, Lu Li, Flaminia Canu, Emilia Volkart, Gerold Schneider
Published: 2026-03-28
Categories: cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2603.27331v1

In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each individual. However, social scientists often rely on limited datasets, which are basically unavailable online. In this study, we collaborated with social scientists to develop a high-quality multimedia multi-modal datasets, \textbf{SACRED}, in which the faithfulness of classification is guaranteed. Using \textbf{SACRED}, we evaluated the performance of 13 popular LLMs as well as traditional rule-based and fine-tuned approaches. The result suggests DeepSeek-V3 model performs well in classifying such abstract concepts (i.e., 79.19\% accuracy in the Quora test set), and the GPT-4o-mini model surpassed the other models in the vision tasks (63.99\% F1 score). Purportedly, this is the first annotated multi-modal dataset from online spirituality communication. Our study also found a new type of connectedness which is valuable for communication science studies.

---

### Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification

Authors: Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Igor Melnychuk, Ming C. Leu
Published: 2026-03-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27325v2

Accurate wound classification (WC) and boundary segmentation are essential for guiding clinical decisions in chronic and acute wound management. However, most existing artificial intelligence (AI) models are limited, focusing on a narrow set of wound types, limited variations in wound severity, or a single task (segmentation or classification), which reduces their clinical applicability. This study presents two dedicated instance segmentation models based on You Only Look Once (YOLO)v11 that perform wound boundary segmentation (WBS) and WC across five clinically relevant wound types: burn injury (BI), pressure injury, diabetic foot ulcer, vascular ulcer, and surgical wound. A wound-type balanced dataset of 2,963 annotated images was created to train the models for both tasks, using five-fold cross-validation. Models trained on the original, non-augmented dataset performed consistently across folds, though BI detection accuracy was relatively low; augmenting the dataset with rotation, flipping, and variations in brightness, saturation, and exposure significantly improved performance, particularly for visually subtle BI cases. Among the tested variants, YOLOv11x achieved the best WBS performance (F1-score: 0.9341; mAP50: 0.9629). For WC, YOLOv11m achieved the highest mAP50 (0.9194) and mAP50-95 (0.6950), whereas YOLOv11l achieved the highest F1-score (0.8797). The lightweight YOLOv11n provided comparable accuracy at lower computational cost, making it suitable for resource-constrained deployments. Supported by confusion matrices and visual detection outputs, the results confirm robustness against complex backgrounds and high intra-class variability, demonstrating the potential of YOLOv11-based architectures for accurate, real-time wound analysis in clinical and remote care settings.

---

### Improving Automated Wound Assessment Using Joint Boundary Segmentation and Multi-Class Classification Models

Authors: Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Igor Melnychuk, Ming C. Leu
Published: 2026-03-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27325v1

Accurate wound classification and boundary segmentation are essential for guiding clinical decisions in both chronic and acute wound management. However, most existing AI models are limited, focusing on a narrow set of wound types or performing only a single task (segmentation or classification), which reduces their clinical applicability. This study presents a deep learning model based on YOLOv11 that simultaneously performs wound boundary segmentation (WBS) and wound classification (WC) across five clinically relevant wound types: burn injury (BI), pressure injury (PI), diabetic foot ulcer (DFU), vascular ulcer (VU), and surgical wound (SW). A wound-type balanced dataset of 2,963 annotated images was created to train the models for both tasks, with stratified five-fold cross-validation ensuring robust and unbiased evaluation. The models trained on the original non-augmented dataset achieved consistent performance across folds, though BI detection accuracy was relatively lower. Therefore, the dataset was augmented using rotation, flipping, and variations in brightness, saturation, and exposure to help the model learn more generalized and invariant features. This augmentation significantly improved model performance, particularly in detecting visually subtle BI cases. Among tested variants, YOLOv11x achieved the highest performance with F1-scores of 0.9341 (WBS) and 0.8736 (WC), while the lightweight YOLOv11n provided comparable accuracy at lower computational cost, making it suitable for resource-constrained deployments. Supported by confusion matrices and visual detection outputs, the results confirm the model's robustness against complex backgrounds and high intra-class variability, demonstrating the potential of YOLOv11-based architectures for accurate, real-time wound analysis in both clinical and remote care settings.

---

### Multimodal Forecasting for Commodity Prices Using Spectrogram-Based and Time Series Representations

Authors: Soyeon Park, Doohee Chung, Charmgil Hong
Published: 2026-03-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27321v1

Forecasting multivariate time series remains challenging due to complex cross-variable dependencies and the presence of heterogeneous external influences. This paper presents Spectrogram-Enhanced Multimodal Fusion (SEMF), which combines spectral and temporal representations for more accurate and robust forecasting. The target time series is transformed into Morlet wavelet spectrograms, from which a Vision Transformer encoder extracts localized, frequency-aware features. In parallel, exogenous variables, such as financial indicators and macroeconomic signals, are encoded via a Transformer to capture temporal dependencies and multivariate dynamics. A bidirectional cross-attention module integrates these modalities into a unified representation that preserves distinct signal characteristics while modeling cross-modal correlations. Applied to multiple commodity price forecasting tasks, SEMF achieves consistent improvements over seven competitive baselines across multiple forecasting horizons and evaluation metrics. These results demonstrate the effectiveness of multimodal fusion and spectrogram-based encoding in capturing multi-scale patterns within complex financial time series.

---

### Retrospective Counterfactual Prediction by Conditioning on the Factual Outcome: A Cross-World Approach

Authors: Juraj Bodik
Published: 2026-03-28
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2603.27320v1

Retrospective causal questions ask what would have happened to an observed individual had they received a different treatment. We study the problem of estimating $μ(x,y)=\mathbb{E}(Y(1)\mid X=x,Y(0)=y)$, the expected counterfactual outcome for an individual with covariates $x$ and observed outcome $y$, and constructing valid prediction intervals under the Neyman-Rubin superpopulation model. This quantity is generally not identified without additional assumptions. To link the observed and unobserved potential outcomes, we work with a cross-world correlation $ρ(x)=cor(Y(1),Y(0)\mid X=x)$; plausible bounds on $ρ(x)$ enable a principled approach to this otherwise unidentified problem. We introduce retrospective counterfactual estimators $\hatμ_ρ(x,y)$ and prediction intervals $C_ρ(x,y)$ that asymptotically satisfy $P(Y(1)\in C_ρ(x,y)\mid X=x, Y(0)=y)\ge1-α$ under standard causal assumptions. Many common baselines implicitly correspond to endpoint choices $ρ=0$ or $ρ=1$ (ignoring the factual outcome or treating the counterfactual as a shifted factual outcome). Interpolating between these cases through cross-world dependence yields substantial gains in both theory and practice.

---

### TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba

Authors: Ziyue Yang, Kaixing Yang, Xulong Tang
Published: 2026-03-28
Categories: cs.AI, cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2603.27314v1

Music-to-dance generation has broad applications in virtual reality, dance education, and digital character animation. However, the limited coverage of existing 3D dance datasets confines current models to a narrow subset of music styles and choreographic patterns, resulting in poor generalization to real-world music. Consequently, generated dances often become overly simplistic and repetitive, substantially degrading expressiveness and realism. To tackle this problem, we present TokenDance, a two-stage music-to-dance generation framework that explicitly addresses this limitation through dual-modality tokenization and efficient token-level generation. In the first stage, we discretize both dance and music using Finite Scalar Quantization, where dance motions are factorized into upper and lower-body components with kinematic-dynamic constraints, and music is decomposed into semantic and acoustic features with dedicated codebooks to capture choreography-specific structures. In the second stage, we introduce a Local-Global-Local token-to-token generator built on a Bidirectional Mamba backbone, enabling coherent motion synthesis, strong music-dance alignment, and efficient non-autoregressive inference. Extensive experiments demonstrate that TokenDance achieves overall state-of-the-art (SOTA) performance in both generation quality and inference speed, highlighting its effectiveness and practical value for real-world music-to-dance applications.

---

### Scalable Maximum Entropy Population Synthesis via Persistent Contrastive Divergence

Authors: Mirko Degli Esposti
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27312v2

Maximum entropy (MaxEnt) modelling provides a principled framework for generating synthetic populations from aggregate census data, without access to individual-level microdata. The bottleneck of exact-enumeration approaches is expectation computation by explicit summation over the full tuple space $\cX$, which becomes infeasible for more than $K \approx 20$ categorical attributes; sampling-based alternatives exist but rely on Metropolis-type schemes that require proposal tuning and rejection steps. We propose \emph{GibbsPCDSolver}, a stochastic replacement for this computation based on Persistent Contrastive Divergence (PCD): a persistent pool of $N$ synthetic individuals is updated by Gibbs sweeps at each gradient step, providing a stochastic approximation of the model expectations without ever materialising $\cX$. We validate the approach on controlled benchmarks and on \emph{Syn-ISTAT}, a $K{=}15$ Italian demographic benchmark with analytically exact marginal targets derived from ISTAT-inspired conditional probability tables. Scaling experiments across $K \in \{12, 20, 30, 40, 50\}$ confirm that GibbsPCDSolver maintains $\MRE \in (0.010, 0.018)$ while $|\cX|$ grows eighteen orders of magnitude, with runtime scaling as $O(K)$ rather than $O(|\cX|)$. On Syn-ISTAT, GibbsPCDSolver reaches $\MRE{=}0.03$ on training constraints and -- crucially -- produces populations with effective sample size $\Neff = N$ versus $\Neff \approx 0.012\,N$ for generalised raking, an $86.8{\times}$ diversity advantage that is essential for agent-based urban simulations.

---

### MeshTailor: Cutting Seams via Generative Mesh Traversal

Authors: Xueqi Ma, Xingguang Yan, Congyue Zhang, Hui Huang
Published: 2026-03-28
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2603.27309v2

We present MeshTailor, the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces. Unlike prior optimization-based or extrinsic learning-based methods, MeshTailor operates directly on the mesh graph, eliminating projection artifacts and fragile snapping heuristics. We introduce ChainingSeams, a hierarchical serialization of the seam graph that orders chains from global structural cuts down to local details in a coarse-to-fine manner, and a dual-stream encoder that fuses topological and geometric context. Leveraging this hierarchical representation and dual-stream vertex embeddings, our MeshTailor Transformer utilizes an autoregressive pointer layer to trace seams vertex-by-vertex within local neighborhoods. Extensive evaluations show that MeshTailor produces more coherent and structurally regular seam layouts compared to recent optimization-based and learning-based baselines.

---

### GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations

Authors: Alejandro Carrasco, Mariko Storey-Matsutani, Victor Rodriguez-Fernandez, Richard Linares
Published: 2026-03-28
Categories: cs.MA, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2603.27306v3

Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce \textsc{GUIDE}, a non-parametric policy improvement framework that enables cross-episode adaptation without weight updates by evolving a structured, state-conditioned playbook of natural-language decision rules. A lightweight acting model performs real-time control, while offline reflection updates the playbook from prior trajectories. Evaluated on an adversarial orbital interception task in the Kerbal Space Program Differential Games environment, GUIDE's evolution consistently outperforms static baselines. Results indicate that context evolution in LLM agents functions as policy search over structured decision rules in real-time closed-loop spacecraft interaction.

---

### EpochX: Building the Infrastructure for an Emergent Agent Civilization

Authors: Huacan Wang, Chaofa Yuan, Xialie Zhuang, Tu Hu, Shuo Zhang, Jun Han, Shi Wei, Daiqiang Li, Jingping Liu, Kunyi Wang, Zihan Yin, Zhenheng Tang et al.
Published: 2026-03-28
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.27304v1

General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.

---

### Self-evolving AI agents for protein discovery and directed evolution

Authors: Yang Tan, Lingrong Zhang, Mingchen Li, Yuanxi Yu, Bozitao Zhong, Bingxin Zhou, Nanqing Dong, Liang Hong
Published: 2026-03-28
Categories: cs.AI, cs.CL, q-bio.QM
arXiv: https://arxiv.org/abs/2603.27303v1

Protein scientific discovery is bottlenecked by the manual orchestration of information and algorithms, while general agents are insufficient in complex domain projects. VenusFactory2 provides an autonomous framework that shifts from static tool usage to dynamic workflow synthesis via a self-evolving multi-agent infrastructure to address protein-related demands. It outperforms a set of well-known agents on the VenusAgentEval benchmark, and autonomously organizes the discovery and optimization of proteins from a single natural language prompt.

---

### Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution

Authors: Ji-Xuan He, Jia-Cheng Zhao, Feng-Qi Cui, Jinyang Huang, Yang Liu, Sirui Zhao, Meng Li, Zhi Liu
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27301v1

Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions with ubiquitous low-resolution devices. Although pioneer methods achieve high performance on single tasks, they solve both tasks in a serial manner, which inevitably leads to artifact amplification, texture suppression, and structural degradation. To address this, we propose Decoupling then Perceive (DTP), a novel frequency-aware framework that explicitly separates luminance and texture into semantically independent components, enabling specialized modeling and coherent reconstruction. Specifically, to adaptively separate the input into low-frequency luminance and high-frequency texture subspaces, we propose a Frequency-aware Structural Decoupling (FSD) mechanism, which lays a solid foundation for targeted representation learning and reconstruction. Based on the decoupled representation, a Semantics-specific Dual-path Representation (SDR) learning strategy that performs targeted enhancement and reconstruction for each frequency component is further designed, facilitating robust luminance adjustment and fine-grained texture recovery. To promote structural consistency and perceptual alignment in the reconstructed output, building upon this dual-path modeling, we further introduce a Cross-frequency Semantic Recomposition (CSR) module that selectively integrates the decoupled representations. Extensive experiments on the most widely used LLISR benchmarks demonstrate the superiority of our DTP framework, improving $+$1.6\% PSNR, $+$9.6\% SSIM, and $-$48\% LPIPS compared to the most state-of-the-art (SOTA) algorithm. Codes are released at https://github.com/JXVision/DTP.

---

### Complet4R: Geometric Complete 4D Reconstruction

Authors: Weibang Wang, Kenan Li, Zhuoguang Chen, Yijun Yuan, Hang Zhao
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27300v1

We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.

---

### From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification

Authors: Huamin Chen, Xunzhuo Liu, Bowei He, Xue Liu
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27299v1

The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection, jailbreak scoring) feed into weighted projections and priority-ordered decision trees that select a model, enforce privacy policies, and produce structured audit traces -- all from a single declarative source file. Prior work established conflict-free compilation for probabilistic predicates and positioned the DSL within the Workload-Router-Pool inference architecture. This paper extends the same language from stateless, per-request routing to multi-step agent workflows -- the full path from inference gateway to agent orchestration to infrastructure deployment. The DSL compiler emits verified decision nodes for orchestration frameworks (LangGraph, OpenClaw), Kubernetes artifacts (NetworkPolicy, Sandbox CRD, ConfigMap), YANG/NETCONF payloads, and protocol-boundary gates (MCP, A2A) -- all from the same source. Because the language is non-Turing-complete, the compiler guarantees exhaustive routing, conflict-free branching, referential integrity, and audit traces structurally coupled to the decision logic. Because signal definitions are shared across targets, a threshold change propagates from inference gateway to agent gate to infrastructure artifact in one compilation step -- eliminating cross-team coordination as the primary source of policy drift. We ground the approach in four pillars -- auditability, cost efficiency, verifiability, and tunability -- and identify the verification boundary at each layer.

---

### A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX

Authors: Stoyan Nikolov, Bernhard Konrad, Moritz Gronbach, Niket Kumar, Ann Yan, Varun Singh, Yaning Liang, Parthasarathy Ranganathan
Published: 2026-03-28
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.27296v1

The rapid development of AI-based products and their underlying models has led to constant innovation in deep learning frameworks. Google has been pioneering machine learning usage across dozens of products. Maintaining the multitude of model source codes in different ML frameworks and versions is a significant challenge. So far the maintenance and migration work was done largely manually by human experts. We describe an AI-based multi-agent system that we built to support automatic migration of TensorFlow-based deep learning models into JAX-based ones. We make three main contributions: First, we show how an AI planner that uses a mix of static analysis with AI instructions can create migration plans for very complex code components that are reliably followed by the combination of an orchestrator and coders, using AI-generated example-based playbooks. Second, we define quality metrics and AI-based judges that accelerate development when the code to evaluate has no tests and has to adhere to strict style and dependency requirements. Third, we demonstrate how the system accelerates code migrations in a large hyperscaler environment on commercial real-world use-cases. Our approach dramatically reduces the time (6.4x-8x speedup) for deep learning model migrations and creates a virtuous circle where effectively AI supports its own development workflow. We expect that the techniques and approaches described here can be generalized for other framework migrations and general code transformation tasks.

---

### Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes

Authors: Chitralekha Gupta, Jing Peng, Ashwin Ram, Shreyas Sridhar, Christophe Jouffrais, Suranga Nanayakkara
Published: 2026-03-28
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.27295v1

Current scene perception tools for Blind and Low Vision (BLV) individuals rely on spoken descriptions but lack engaging representations of visually pleasing distant environmental landscapes (Vista spaces). Our proposed Scene2Audio framework generates comprehensible and enjoyable nonverbal audio using generative models informed by psychoacoustics, and principles of scene audio composition. Through a user study with 11 BLV participants, we found that combining the Scene2Audio sounds with speech creates a better experience than speech alone, as the sound effects complement the speech making the scene easier to imagine. A mobile app "in-the-wild" study with 7 BLV users for more than a week further showed the potential of Scene2Audio in enhancing outdoor scene experiences. Our work bridges the gap between visual and auditory scene perception by moving beyond purely descriptive aids, addressing the aesthetic needs of BLV users.

---

### Class-Distribution Guided Active Learning for 3D Occupancy Prediction in Autonomous Driving

Authors: Wonjune Kim, In-Jae Lee, Sihwan Hwang, Sanmin Kim, Dongsuk Kum
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27294v1

3D occupancy prediction provides dense spatial understanding critical for safe autonomous driving. However, this task suffers from a severe class imbalance due to its volumetric representation, where safety-critical objects (bicycles, traffic cones, pedestrians) occupy minimal voxels compared to dominant backgrounds. Additionally, voxel-level annotation is costly, yet dedicating effort to dominant classes is inefficient. To address these challenges, we propose a class-distribution guided active learning framework for selecting training samples to annotate in autonomous driving datasets. Our approach combines three complementary criteria to select the training samples. Inter-sample diversity prioritizes samples whose predicted class distributions differ from those of the labeled set, intra-set diversity prevents redundant sampling within each acquisition cycle, and frequency-weighted uncertainty emphasizes rare classes by reweighting voxel-level entropy with inverse per-sample class proportions. We ensure evaluation validity by using a geographically disjoint train/validation split of Occ3D-nuScenes, which reduces train-validation overlap and mitigates potential map memorization. With only 42.4% labeled data, our framework reaches 26.62 mIoU, comparable to full supervision and outperforming active learning baselines at the same budget. We further validate generality on SemanticKITTI using a different architecture, demonstrating consistent effectiveness across datasets.

---

### Human-Centric Perception for Child Sexual Abuse Imagery

Authors: Camila Laranjeira, João Macedo, Sandra Avila, Fabrício Benevenuto, Jefersson A. dos Santos
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27290v2

Law enforcement agencies and non-gonvernmental organizations handling reports of Child Sexual Abuse Imagery (CSAI) are overwhelmed by large volumes of data, requiring the aid of automation tools. However, defining sexual abuse in images of children is inherently challenging, encompassing sexually explicit activities and hints of sexuality conveyed by the individual's pose, or their attire. CSAI classification methods often rely on black-box approaches, targeting broad and abstract concepts such as pornography. Thus, our work is an in-depth exploration of tasks from the literature on Human-Centric Perception, across the domains of safe images, adult pornography, and CSAI, focusing on targets that enable more objective and explainable pipelines for CSAI classification in the future. We introduce the Body-Keypoint-Part Dataset (BKPD), gathering images of people from varying age groups and sexual explicitness to approximate the domain of CSAI, along with manually curated hierarchically structured labels for skeletal keypoints and bounding boxes for person and body parts, including head, chest, hip, and hands. We propose two methods, namely BKP-Association and YOLO-BKP, for simultaneous pose estimation and detection, with targets associated per individual for a comprehensive decomposed representation of each person. Our methods are benchmarked on COCO-Keypoints and COCO-HumanParts, as well as our human-centric dataset, achieving competitive results with models that jointly perform all tasks. Cross-domain ablation studies on BKPD and a case study on RCPD highlight the challenges posed by sexually explicit domains. Our study addresses previously unexplored targets in the CSAI domain, paving the way for novel research opportunities.

---

### StretchCast: Global-Regional AI Weather Forecasting on Stretched Cubed-Sphere Mesh

Authors: Jin Feng
Published: 2026-03-28
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2603.27288v1

Global AI weather forecasting still relies mainly on uniform-resolution models, making it hard to combine regional refinement, two-way regional-global coupling, and affordable training cost. We introduce StretchCast, a global-regional AI forecasting framework built on a variable-resolution stretched cubed-sphere (SCS) mesh that preserves a closed global domain while concentrating resolution over a target region. Within this framework, we develop a one-step predictor, SCS_Base Model, and a rollout-oriented multistep predictor, SCS_FCST4 Model, to test the feasibility of SCS-based forecasting and the benefit of joint multistep training. Experiments use ERA5 with 69 variables over 1998-2022. Because training compute remains limited, this study uses a coarse-resolution proof-of-concept configuration rather than a final high-resolution system. Even with only about 7,776 effective global grid cells and roughly 0.875 degree resolution over the center-refined face, the 23M-parameter SCS_Base Model yields stable multivariate forecasts. With 83M parameters and training cost on the order of hours, SCS_FCST4 Model delivers competitive medium-range anomaly-correlation evolution over the target region after unified reprojection, especially for geopotential height, specific humidity, and part of the lower-tropospheric winds, while maintaining smooth cross-face continuity and realistic multiscale structure in typhoon and spectral analyses. These results support StretchCast as a practical lightweight foundation for global-regional AI weather forecasting.

---

### Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving

Authors: Qiqi Liu, Huan Xu, Jingyu Li, Bin Sun, Zhihui Hao, Dangen She, Xiatian Zhu, Li Zhang
Published: 2026-03-28
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.27287v1

Autonomous driving requires reasoning about how the environment evolves and planning actions accordingly. Existing world-model-based approaches typically predict future scenes first and plan afterwards, resulting in open-loop imagination that may drift from the actual decision process. In this paper, we present Uni-World VLA, a unified vision-language-action (VLA) model that tightly interleaves future frame prediction and trajectory planning. Instead of generating a full world rollout before planning, our model alternates between predicting future frames and ego actions step by step, allowing planning decisions to be continuously conditioned on the imagined future observations. This interleaved generation forms a closed-loop interaction between world modeling and control, enabling more adaptive decision-making in dynamic traffic scenarios. In addition, we incorporate monocular depth information into frames to provide stronger geometric cues for world modeling, improving long-horizon scene prediction. Experiments on the NAVSIM benchmark show that our approach achieves competitive closed-loop planning performance while producing high-fidelity future frame predictions. These results demonstrate that tightly coupling world prediction and planning is a promising direction for scalable VLA driving systems.

---

### Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP

Authors: Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler, Elias Grünewald, Felix Balzer
Published: 2026-03-28
Categories: cs.SE, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2603.27277v1

Large Language Model (LLM) coding agents typically explore codebases through repeated file-reading and grep-searching, consuming thousands of tokens per query without structural understanding. We present Codebase-Memory, an open-source system that constructs a persistent, Tree-Sitter-based knowledge graph via the Model Context Protocol (MCP), parsing 66 languages through a multi-phase pipeline with parallel worker pools, call-graph traversal, impact analysis, and community discovery. Evaluated across 31 real-world repositories, Codebase-Memory achieves 83% answer quality versus 92% for a file-exploration agent, at ten times fewer tokens and 2.1 times fewer tool calls. For graph-native queries such as hub detection and caller ranking, it matches or exceeds the explorer on 19 of 31 languages.

---

### Robust Global-Local Behavior Arbitration via Continuous Command Fusion Under LiDAR Errors

Authors: Mohamed Elgouhary, Amr S. El-Wakeel
Published: 2026-03-28
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2603.27273v1

Modular autonomous driving systems must coordinate global progress objectives with local safety-driven reactions under imperfect sensing and strict real-time constraints. This paper presents a ROS2-native arbitration module that continuously fuses the outputs of two unchanged and interpretable controllers: a global reference-tracking controller based on Pure Pursuit and a reactive LiDAR-based Gap Follow controller. At each control step, both controllers propose Ackermann commands, and a PPO-trained policy predicts a continuous gate from a compact feature observation to produce a single fused drive command, augmented with practical safety checks. For comparison under identical ROS topic inputs and control rate, we implement a lightweight sampling-based predictive baseline. Robustness is evaluated using a ROS2 impairment protocol that injects LiDAR noise, delay, and dropout, and additionally sweeps forward-cone false short-range outliers. In a repeatable close-proximity passing scenario, we report safe success and failure rates together with per-step end-to-end controller runtime as sensing stress increases. The study is intended as a command-level robustness evaluation in a modular ROS2 setting, not as a replacement for planning-level interaction reasoning.

---

### Quantification of Credal Uncertainty: A Distance-Based Approach

Authors: Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann, Michele Caprio, Krikamol Muandet, Humberto Bustince, Sébastien Destercke, Eyke Hüllermeier, Yusuf Sale
Published: 2026-03-28
Categories: cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2603.27270v2

Credal sets, i.e., closed convex sets of probability measures, provide a natural framework to represent aleatoric and epistemic uncertainty in machine learning. Yet how to quantify these two types of uncertainty for a given credal set, particularly in multiclass classification, remains underexplored. In this paper, we propose a distance-based approach to quantify total, aleatoric, and epistemic uncertainty for credal sets. Concretely, we introduce a family of such measures within the framework of Integral Probability Metrics (IPMs). The resulting quantities admit clear semantic interpretations, satisfy natural theoretical desiderata, and remain computationally tractable for common choices of IPMs. We instantiate the framework with the total variation distance and obtain simple, efficient uncertainty measures for multiclass classification. In the binary case, this choice recovers established uncertainty measures, for which a principled multiclass generalization has so far been missing. Empirical results confirm practical usefulness, with favorable performance at low computational cost.

---

### From Foundation ECG Models to NISQ Learners: Distilling ECGFounder into a VQC Student

Authors: Giovanni dos Santos Franco, Felipe Mahlow, Ellison Fernando Cardoso, Felipe Fanchini
Published: 2026-03-28
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2603.27269v1

Foundation models have recently improved electrocardiogram (ECG) representation learning, but their deployment can be limited by computational cost and latency constraints. In this work, we fine-tune ECGFounder as a high-capacity teacher for binary ECG classification on PTB-XL and the MIT-BIH Arrhythmia Database, and investigate whether knowledge distillation can transfer its predictive behavior to compact students. We evaluate two classical 1D students (ResNet-1D and a lightweight CNN-1D) and a quantum-ready pipeline that combines a convolutional autoencoder, which compresses 256-sample ECG windows into a low-dimensional latent representation, with a 6-qubit variational quantum circuit implemented in Qiskit and executed in a simulated backend. Across both datasets, the teacher provides the strongest overall performance, while distillation yields competitive students under a considerable reduction in trainable parameters. We further analyze the sensitivity of student performance to distillation settings, highlighting consistent accuracy--efficiency trade-offs when compressing a foundation ECG model into classical and quantum-ready learners under a unified evaluation protocol.

---