# Research Papers — 2026-03 · bundle page 2 of 243 > Full-text markdown of papers #51–100 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/2 [← Previous bundle](https://aipod.dev/papers/archive/2026-03.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/3.md) ### Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings Authors: Thomas Manuel Rost, Martina Figlia, F. Morgado-Dias, Marko Radeta Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00313v3 Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific model development. We investigate whether frozen general-purpose foundation-model embeddings can reduce these requirements by extracting DINOv3 ViT-B/16 embeddings and training only a logistic regression classifier on the AQUA20 benchmark. We evaluate the approach across a range of annotation budgets, a repeated 80% training-subsample evaluation, and a full-training refit. With only 13 labelled images per category, corresponding to approximately 4% of the benchmark's official training partition, mean macro F1 reaches 81.8%; with 144 images per category it reaches 88.5%, compared to the published fully supervised ConvNeXt point estimate of 88.9% obtained with the complete training set (benchmark results reported without run-to-run variability). Using all official training labels, macro F1 reaches 91.5% (bootstrap 95% CI: 89.0-93.7%). Sensitivity analyses show that the main findings remain stable across ordinary downstream implementation choices, and persist after removing duplicate and near-duplicate test images identified in an audit of the official split. Preliminary evaluation on a second dataset suggests that overall performance level and the shape of the label efficiency curve are not unique to the AQUA20 dataset. Because the DINOv3 backbone remains frozen and only the downstream classifier is fitted, the approach avoids task-specific neural-network training and can be executed on commodity hardware. These findings establish linear classification on frozen foundation-model embeddings as a practical baseline for label-efficient underwater image classification. --- ### Label-efficient underwater species classification with logistic regression on frozen foundation model embeddings Authors: Thomas Manuel Rost Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00313v2 Automated species classification from underwater imagery is bottlenecked by the cost of expert annotation, and supervised models trained on one dataset rarely transfer to new conditions. We investigate whether a simple classifier operating on frozen foundation model embeddings can close this gap. Using frozen DINOv3 ViT-B/16 embeddings with no fine-tuning, we train a logistic regression classifier and evaluate on the AQUA20 benchmark (20 marine species). At full supervision, logistic regression achieves 88.5% macro F1 compared to ConvNeXt's 88.9%, a gap of 0.4 percentage points, while outperforming the supervised baseline on 8 of 20 species. Under label scarcity, with 21 labeled examples per class (approximately 6% of training labels), macro F1 exceeds 80%. The near-parity with end-to-end supervised learning demonstrates that these general-purpose, frozen representations exhibit strong linear separability at the species level in the underwater domain. Our approach requires no deep learning training, no domain-specific data engineering, and no underwater-adapted models, establishing a practical, immediately deployable baseline for label-efficient marine species recognition. All results are reported on the held-out test set over 100 random seed initialisations. This is a preliminary report; further evaluations and ablations are forthcoming. --- ### CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment Authors: Anurag Kumar, Raghuveer Peri, Jon Burnsky, Alexandru Nelus, Rohit Paturi, Srikanth Vishnubhotla, Yanjun Qi Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00310v2 Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more modalities. We propose a simple conditional decoding strategy, CASA (Classification Augmented with Safety Attention) that uses internal representations of MLLMs to predict a binary safety token before response generation. The classification is guided by a safety attention mechanism that computes attention between a dedicated query prompt and the input to scale the classification logits, sharpening the model's ability to detect malicious queries. Our design ensures robust safety alignment without relying on any external classifier or auxiliary head, and without modality-specific safety fine-tuning. Unlike prior safety-decoding methods that attach an external classifier or moderation head, or rescale every generated token with a reward model, CASA makes a single, internal, attention-gated safety decision over the shared multimodal representation, which is precisely what lets safety learned from text-only training transfer to image and audio inputs. Compared against 4 baseline models across 7 attack types spanning text, image, and audio modalities, evaluated on benchmarks such as MM-SafetyBench, JailbreakV-28k, and adversarial audio tests, CASA lowers the average attack success rate by >90% relative when paired with a standard safety prompt (applied to all baselines for fair comparison), and by 54--61% using its internal safety mechanism alone. Our empirical evaluations also show that CASA~maintains strong utility on benign inputs, validated through both automated and human evaluations (via 13 trained annotators). Together, these results highlight CASA as a simple and generalizable framework to improve multimodal LLM safety. --- ### Robust Multimodal Safety via Conditional Decoding Authors: Anurag Kumar, Raghuveer Peri, Jon Burnsky, Alexandru Nelus, Rohit Paturi, Srikanth Vishnubhotla, Yanjun Qi Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00310v1 Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more modalities. In this work, we propose a simple conditional decoding strategy, CASA (Classification Augmented with Safety Attention) that utilizes internal representations of MLLMs to predict a binary safety token before response generation. We introduce a novel safety attention module designed to enhance the model's ability to detect malicious queries. Our design ensures robust safety alignment without relying on any external classifier or auxiliary head, and without the need for modality-specific safety fine-tuning. On diverse benchmarks such as MM-SafetyBench, JailbreakV-28k, and adversarial audio tests, CASA lowers the average attack success rate by more than 97% across modalities and across attack types. Our empirical evaluations also show that CASA maintains strong utility in benign inputs, a result validated through both automated and human evaluations (via 13 trained annotators). Together, these results highlight CASA as a simple and generalizable framework to improve multimodal LLM safety. --- ### Vocal Prognostic Digital Biomarkers in Monitoring Chronic Heart Failure: A Longitudinal Observational Study Authors: Fan Wu, Matthias P. Nägele, Daryush D. Mehta, Elgar Fleisch, Frank Ruschitzka, Andreas J. Flammer, Filipe Barata Published: 2026-03-31 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2604.00308v1 Objective: This study aimed to evaluate which voice features can predict health deterioration in patients with chronic HF. Background: Heart failure (HF) is a chronic condition with progressive deterioration and acute decompensations, often requiring hospitalization and imposing substantial healthcare and economic burdens. Current standard-of-care (SoC) home monitoring, such as weight tracking, lacks predictive accuracy and requires high patient engagement. Voice is a promising non-invasive biomarker, though prior studies have mainly focused on acute HF stages. Methods: In a 2-month longitudinal study, 32 patients with HF collected daily voice recordings and SoC measures of weight and blood pressure at home, with biweekly questionnaires for health status. Acoustic analysis generated detailed vowel and speech features. Time-series features were extracted from aggregated lookback windows (e.g., 7 days) to predict next-day health status. Explainable machine learning with nested cross-validation identified top vocal biomarkers, and a case study illustrated model application. Results: A total of 21,863 recordings were analyzed. Acoustic vowel features showed strong correlations with health status. Time-series voice features within the lookback window outperformed corresponding standard care measures, achieving peak sensitivity and specificity of 0.826 and 0.782 versus 0.783 and 0.567 for SoC metrics. Key prognostic voice features identifying deterioration included delayed energy shift, low energy variability, and higher shimmer variability in vowels, along with reduced speaking and articulation rate, lower phonation ratio, decreased voice quality, and increased formant variability in speech. Conclusion: Voice-based monitoring offers a non-invasive approach to detect early health changes in chronic HF, supporting proactive and personalized care. --- ### SAGE: Subsurface AI-driven Geostatistical Extraction with proxy posterior Authors: Huseyin Tuna Erdinc, Ipsita Bhar, Rafael Orozco, Thales Souza, Felix J. Herrmann Published: 2026-03-31 Categories: cs.LG, physics.geo-ph, stat.ML arXiv: https://arxiv.org/abs/2604.00307v1 Recent advances in generative networks have enabled new approaches to subsurface velocity model synthesis, offering a compelling alternative to traditional methods such as Full Waveform Inversion. However, these approaches predominantly rely on the availability of large-scale datasets of high-quality, geologically realistic subsurface velocity models, which are often difficult to obtain in practice. We introduce SAGE, a novel framework for statistically consistent proxy velocity generation from incomplete observations, specifically sparse well logs and migrated seismic images. During training, SAGE learns a proxy posterior over velocity models conditioned on both modalities (wells and seismic); at inference, it produces full-resolution velocity fields conditioned solely on migrated images, with well information implicitly encoded in the learned distribution. This enables the generation of geologically plausible and statistically accurate velocity realizations. We validate SAGE on both synthetic and field datasets, demonstrating its ability to capture complex subsurface variability under limited observational constraints. Furthermore, samples drawn from the learned proxy distribution can be leveraged to train downstream networks, supporting inversion workflows. Overall, SAGE provides a scalable and data-efficient pathway toward learning geological proxy posterior for seismic imaging and inversion. Repo link: https://github.com/slimgroup/SAGE. --- ### Set-Based Value Function Characterization and Neural Approximation of Stabilization Domains for Input-Constrained Discrete-Time Systems Authors: Mohamed Serry, S. Sivaranjani, Jun Liu Published: 2026-03-31 Categories: eess.SY, cs.NE, math.DS, math.OC arXiv: https://arxiv.org/abs/2604.00305v2 Analyzing nonlinear systems with stabilizable controlled invariant sets (CISs) requires accurate estimation of their domains of stabilization (DOS) together with associated stabilizing controllers. Despite extensive research, estimating DOSs for general nonlinear systems remains challenging due to fundamental theoretical and computational limitations. In this paper, we propose a novel framework for estimating DOSs for controlled input-constrained discrete-time systems. The DOS is characterized via newly introduced value functions defined on metric spaces of compact sets. We establish the fundamental properties of these value functions and derive the associated Bellman-type (Zubov-type) functional equations. Building on this characterization, we develop a physics-informed neural network (NN) framework that learns the value functions by embedding the derived functional equations directly into the training process. The proposed methodology is demonstrated through two numerical examples, illustrating its ability to accurately estimate DOSs and synthesize stabilizing controllers from the learned value functions. --- ### Set-Based Value Function Characterization and Neural Approximation of Stabilization Domains for Input-Constrained Discrete-Time Systems Authors: Mohamed Serry, S. Sivaranjani, Jun Liu Published: 2026-03-31 Categories: eess.SY, cs.NE, math.DS, math.OC arXiv: https://arxiv.org/abs/2604.00305v1 Analyzing nonlinear systems with stabilizable controlled invariant sets (CISs) requires accurate estimation of their domains of stabilization (DOS) together with associated stabilizing controllers. Despite extensive research, estimating DOSs for general nonlinear systems remains challenging due to fundamental theoretical and computational limitations. In this paper, we propose a novel framework for estimating DOSs for controlled input-constrained discrete-time systems. The DOS is characterized via newly introduced value functions defined on metric spaces of compact sets. We establish the fundamental properties of these value functions and derive the associated Bellman-type (Zubov-type) functional equations. Building on this characterization, we develop a physics-informed neural network (NN) framework that learns the value functions by embedding the derived functional equations directly into the training process. The proposed methodology is demonstrated through two numerical examples, illustrating its ability to accurately estimate DOSs and synthesize stabilizing controllers from the learned value functions. --- ### Asymmetric Actor-Critic for Multi-turn LLM Agents Authors: Shuli Jiang, Zhaoyang Zhang, Yi Zhang, Shuo Yang, Wei Xia, Stefano Soatto Published: 2026-03-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00304v1 Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-world applications, agents must succeed in one-shot settings where retries are impossible. Existing approaches either rely on reflection or post-hoc evaluation, which require additional attempts, or assume fully trainable models that cannot leverage proprietary LLMs. We propose an asymmetric actor-critic framework for reliable conversational agents. A powerful proprietary LLM acts as the actor, while a smaller open-source critic provides runtime supervision, monitoring the actor's actions and intervening within the same interaction trajectory. Unlike training-based actor-critic methods, our framework supervises a fixed actor operating in open-ended conversational environments. The design leverages a generation-verification asymmetry: while high-quality generation requires large models, effective oversight can often be achieved by smaller ones. We further introduce a data generation pipeline that produces supervision signals for critic fine-tuning without modifying the actor. Experiments on $τ$-bench and UserBench show that our approach significantly improves reliability and task success over strong single-agent baselines. Moreover, lightweight open-source critics rival or surpass larger proprietary models in the critic role, and critic fine-tuning yields additional gains over several state-of-the-art methods. --- ### SANA I2I: A Text Free Flow Matching Framework for Paired Image to Image Translation with a Case Study in Fetal MRI Artifact Reduction Authors: Italo Felix Santos, Gilson Antonio Giraldi, Heron Werner Junior Published: 2026-03-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.00298v1 We propose SANA-I2I, a text-free high-resolution image-to-image generation framework that extends the SANA family by removing textual conditioning entirely. In contrast to SanaControlNet, which combines text and image-based control, SANA-I2I relies exclusively on paired source-target images to learn a conditional flow-matching model in latent space. The model learns a conditional velocity field that maps a target image distribution to another one, enabling supervised image translation without reliance on language prompts. We evaluate the proposed approach on the challenging task of fetal MRI motion artifact reduction. To enable paired training in this application, where real paired data are difficult to acquire, we adopt a synthetic data generation strategy based on the method proposed by Duffy et al., which simulates realistic motion artifacts in fetal magnetic resonance imaging (MRI). Experimental results demonstrate that SANA-I2I effectively suppresses motion artifacts while preserving anatomical structure, achieving competitive performance few inference steps. These results highlight the efficiency and suitability of our proposed flow-based, text-free generative models for supervised image-to-image tasks in medical imaging. --- ### SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection Authors: Hochan Son, Xiaofeng Lin, Jason Ni, Guang Cheng Published: 2026-03-31 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.00293v1 Deep generative models for tabular data (GANs, diffusion models, and LLM-based generators) exhibit highly non-uniform behavior across datasets; the best-performing synthesizer family depends strongly on distributional stressors such as long-tailed marginals, high-cardinality categorical, Zipfian imbalance, and small-sample regimes. This brittleness makes practical deployment challenging, especially when users must balance competing objectives of fidelity, privacy, and utility. We study {intent-conditioned tabular synthesis selection}: given a dataset and a user intent expressed as a preference over evaluation metrics, the goal is to select a synthesizer that minimizes regret relative to an intent-specific oracle. We propose {stress profiling}, a synthesis-specific meta-feature representation that quantifies dataset difficulty along four interpretable stress dimensions, and integrate it into {SYNTHONY}, a selection framework that matches stress profiles against a calibrated capability registry of synthesizer families. Across a benchmark of 7 datasets, 10 synthesizers, and 3 intents, we demonstrate that stress-based meta-features are highly predictive of synthesizer performance: a $k$NN selector using these features achieves strong Top-1 selection accuracy, substantially outperforming zero-shot LLM selectors and random baselines. We analyze the gap between meta-feature-based and capability-based selection, identifying the hand-crafted capability registry as the primary bottleneck and motivating learned capability representations as a direction for future work. --- ### MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control Authors: Sahil Kumar, Namrataben Patel, Honggang Wang, Youshan Zhang Published: 2026-03-31 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2604.00292v1 MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or improving quality under controlled conditions. MVC combines a gated bidirectional Mamba text encoder, a Temporal Bi-Mamba supervised by a lightweight alignment teacher discarded after training, and an Expressive Mamba with AdaLN modulation, yielding linear-time O(T) conditioning with bounded activation memory and practical finite look-ahead streaming. Unlike prior Mamba-TTS systems that remain hybrid at inference, MVC removes attention-based duration and style modules under a fixed StyleTTS2 mel-diffusion-vocoder backbone. Trained on LJSpeech/LibriTTS and evaluated on VCTK, CSS10 (ES/DE/FR), and long-form Gutenberg passages, MVC achieves modest but statistically reliable gains over StyleTTS2, VITS, and Mamba-attention hybrids in MOS/CMOS, F0 RMSE, MCD, and WER, while reducing encoder parameters to 21M and improving throughput by 1.6x. Diffusion remains the dominant latency source, but SSM-only conditioning improves memory footprint, stability, and deployability. --- ### Frege in the Flesh: Biolinguistics and the Neural Enforcement of Syntactic Structures Authors: Elliot Murphy Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00291v1 Biolinguistics is the interdisciplinary scientific study of the biological foundations, evolution, and genetic basis of human language. It treats language as an innate biological organ or faculty of the mind, rather than a cultural tool, and it challenges a behaviorist conception of human language acquisition as being based on stimulus-response associations. Extracting its most essential component, it takes seriously the idea that mathematical, algebraic models of language capture something natural about the world. The syntactic structure-building operation of MERGE is thought to offer the scientific community a "real joint of nature", "a (new) aspect of nature" (Mukherji 2010), not merely a formal artefact. This mathematical theory of language is then seen as being able to offer biologists, geneticists and neuroscientists clearer instructions for how to explore language. The argument of this chapter proceeds in four steps. First, I clarify the object of inquiry for biolinguistics: not speech, communication, or generic sequence processing, but the internal computational system that generates hierarchically structured expressions. Second, I argue that this formal characterization matters for evolutionary explanation, because different conceptions of syntax imply different standards of what must be explained. Third, I suggest that a sufficiently explicit algebraic account of syntax places non-trivial constraints on candidate neural mechanisms. Finally, I consider how recent neurocomputational work begins to transform these constraints into empirically tractable hypotheses, while also noting the speculative and revisable character of the present program. --- ### Improvisational Games as a Benchmark for Social Intelligence of AI Agents: The Case of Connections Authors: Gaurav Rajesh Parikh, Angikar Ghosal Published: 2026-03-31 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.00284v1 We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other agents. We show how the game serves as a good benchmark for social intelligence abilities of language model based agents that go beyond the agents' own memory and deductive reasoning and also involve gauging the understanding capabilities of other agents. Finally, we show how through communication with other agents in a constrained environment, AI agents must demonstrate social awareness and intelligence in games involving collaboration. --- ### Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees Authors: Yanliang Huang, Peng Xie, Wenyuan Wu, Zhuoqi Zeng, Amr Alanwar Published: 2026-03-31 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.00283v1 We present a data-driven framework for reachability analysis of nonlinear dynamical systems that requires no explicit model. A denoising diffusion probabilistic model learns the time-evolving state distribution of a dynamical system from trajectory data alone. The predicted reachable set takes the form of a sublevel set of a nonconformity score derived from the reconstruction error, with the threshold calibrated via the Learn Then Test procedure so that the probability of excluding a reachable state is bounded with high probability. Experiments on three nonlinear systems, a forced Duffing oscillator, a planar quadrotor, and a high-dimensional reaction-diffusion system, confirm that the empirical miss rate remains below the Probably Approximately Correct (PAC) bound while scaling to state dimensions beyond the reach of classical grid-based and polynomial methods. --- ### Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education Authors: Mark Dranias, Adam Whitley Published: 2026-03-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.00281v1 Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses frequently emphasize tool-specific prompting practices, limiting durability as AI platforms evolve. This paper adopts a human-centered stance, treating human-in-the-loop (HITL) control as a stable educational problem rather than a transitional step toward AI autonomy. Drawing on systems engineering and control-theoretic concepts, we frame objectives and world models as operational artifacts that students configure to stabilize AI-assisted work. We propose a pilot undergraduate CS laboratory curriculum that explicitly separates planning from execution and trains students to specify acceptance criteria and architectural constraints prior to code generation. In selected labs, the curriculum also introduces deliberate, concept-aligned drift to support diagnosis and recovery from specification violations. We report a sensitivity power analysis for a three-arm pilot design comparing unstructured AI use, structured planning, and structured planning with injected drift, establishing detectable effect sizes under realistic section-level constraints. The contribution is a theory-driven, methodologically explicit foundation for HITL pedagogy that renders control competencies teachable across evolving AI tools. --- ### Spec-Harness: Measuring and Improving Behavioral Adequacy of LLM-Synthesized Formal Specifications Authors: Md Rakib Hossain Misu, Iris Ma, Cristina V. Lopes Published: 2026-03-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.00280v2 Formal specifications play a central role in ensuring software reliability, yet automatically synthesizing high-quality specifications remains difficult and often requires domain expertise. Recent work has applied large language models to generate specifications in the Java Modeling Language (JML), reporting high verifier pass rates. But passing a verifier only confirms that an implementation is consistent with a specification, not that the specification is meaningful. A trivial postcondition such as ensures true satisfies any verifier while saying nothing about the code. How much behavior, then, does a verifier-accepted specification actually capture? In this work, we first compare classical and prompt-based JML synthesis approaches under a unified setup, and find that prompt optimization through verification feedback raises pass rates but reaches a clear ceiling. We then introduce Spec-Harness, a framework that measures the behavioral adequacy of a specification along four dimensions of precondition and postcondition correctness and completeness, using Hoare-triple based symbolic verification and input/output mutation. Spec-Harness reveals that many verifier-accepted specifications, including optimized ones, are behaviorally weak, over- or under-constraining inputs and outputs in ways the verifier cannot see. Finally, we show that Spec-Harness works as a feedback signal that helps coding agents synthesize specifications with higher behavioral adequacy, including general-purpose agents such as Codex CLI and Claude Code, as well as VeriAct, a JML-specialized agent we build for this study. --- ### VeriAct: Beyond Verifiability -- Agentic Synthesis of Correct and Complete Formal Specifications Authors: Md Rakib Hossain Misu, Iris Ma, Cristina V. Lopes Published: 2026-03-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.00280v1 Formal specifications play a central role in ensuring software reliability and correctness. However, automatically synthesizing high-quality formal specifications remains a challenging task, often requiring domain expertise. Recent work has applied large language models to generate specifications in Java Modeling Language (JML), reporting high verification pass rates. But does passing a verifier mean that the specification is actually correct and complete? In this work, we first conduct a comprehensive evaluation comparing classical and prompt-based approaches for automated JML specification synthesis. We then investigate whether prompt optimization can push synthesis quality further by evolving prompts through structured verification feedback. While optimization improves verifier pass rates, we find a clear performance ceiling. More critically, we propose Spec-Harness, an evaluation framework that measures specification correctness and completeness through symbolic verification, revealing that a large fraction of verifier-accepted specifications, including optimized ones, are in fact incorrect or incomplete, over- or under-constraining both inputs and outputs in ways invisible to the verifier. To push beyond this ceiling, we propose VeriAct, a verification-guided agentic framework that iteratively synthesizes and repairs specifications through a closed loop of LLM-driven planning, code execution, verification, and Spec-Harness feedback. Our experiments on two benchmark datasets show that VeriAct outperforms both prompt-based and prompt-optimized baselines, producing specifications that are not only verifiable but also correct and complete. --- ### The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment Authors: Hongyuan Liu, Qinli Yang, Wen Li, Zhong Zhang, Jiaming Liu, Wei Han, Zhili Qin, Jinxia Guo, Junming Shao Published: 2026-03-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.00279v1 Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal interchangeability, such as captioning and joint clustering. Existing post-processing approaches can partially improve cross-modal compatibility; however, we show through geometric analysis that they primarily reduce the global centroid offset while leaving the underlying distributional mismatch intact. We decompose the modality gap into a Centroid Gap and a Distribution Gap, and demonstrate that the Distribution Gap is the true predictor of cross-modal task quality ($R^2 = 0.986$), whereas the commonly used Raw Gap is misleading ($R^2 = 0.691$). Motivated by this observation, we propose TPC-CMA (Three-Phase Curriculum for Cross-Modal Alignment), a fine-tuning framework that explicitly reduces both components. The proposed CMA jointly mitigates centroid offsets and reshapes the distributional structure, while a three-phase curriculum with gradient-aware scheduling progressively introduces alignment during training to enable stable optimization. Experiments demonstrate that our method significantly improves cross-modal alignment. With $α_{\text{target}}{=}0.05$, the modality gap is reduced by 66.6\% with only 4.84\% accuracy drop. Under stronger alignment ($α_{\text{target}}{=}0.5$), the gap is reduced by 82.3\%, clustering ARI improves from 0.318 to 0.516, and captioning CIDEr increases by 57.1\% over the original model. Our code and pre-trained models will be made publicly available upon acceptance. --- ### Hybrid Energy-Based Models for Physical AI: Provably Stable Identification of Port-Hamiltonian Dynamics Authors: Simone Betteti, Luca Laurenti Published: 2026-03-31 Categories: eess.SY, cs.AI, cs.LG, math.DS arXiv: https://arxiv.org/abs/2604.00277v2 Energy-based models (EBMs) implement inference as gradient descent on a learned Lyapunov function, yielding interpretable, structure-preserving alternatives to black-box neural ODEs and aligning naturally with physical AI. Yet their use in system identification remains limited, and existing architectures lack formal stability guarantees that globally preclude unstable modes. We address this gap by introducing an EBM framework for system identification with stable, dissipative, absorbing invariant dynamics. Unlike classical global Lyapunov stability, absorbing invariance expands the class of stability-preserving architectures, enabling more flexible and expressive EBMs. We extend EBM theory to nonsmooth activations by establishing negative energy dissipation via Clarke derivatives and deriving new conditions for radial unboundedness, exposing a stability-expressivity tradeoff in standard EBMs. To overcome this, we introduce a hybrid architecture with a dynamical visible layer and static hidden layers, prove absorbing invariance under mild assumptions, and show that these guarantees extend to port-Hamiltonian EBMs. Experiments on metric-deformed multi-well and ring systems validate the approach, showcasing how our hybrid EBM architecture combines expressivity with sound and provable safety guarantees by design. --- ### Excite, Attend and Segment (EASe): Domain-Agnostic Fine-Grained Mask Discovery with Feature Calibration and Self-Supervised Upsampling Authors: Deepank Singh, Anurag Nihal, Vedhus Hoskere Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00276v1 Unsupervised segmentation approaches have increasingly leveraged foundation models (FM) to improve salient object discovery. However, these methods often falter in scenes with complex, multi-component morphologies, where fine-grained structural detail is indispensable. Many state-of-the-art unsupervised segmentation pipelines rely on mask discovery approaches that utilize coarse, patch-level representations. These coarse representations inherently suppress the fine-grained detail required to resolve such complex morphologies. To overcome this limitation, we propose Excite, Attend and Segment (EASe), an unsupervised domain-agnostic semantic segmentation framework for easy fine-grained mask discovery across challenging real-world scenes. EASe utilizes novel Semantic-Aware Upsampling with Channel Excitation (SAUCE) to excite low-resolution FM feature channels for selective calibration and attends across spatially-encoded image and FM features to recover full-resolution semantic representations. Finally, EASe segments the aggregated features into multi-granularity masks using a novel training-free Cue-Attentive Feature Aggregator (CAFE) which leverages SAUCE attention scores as a semantic grouping signal. EASe, together with SAUCE and CAFE, operate directly at pixel-level feature representations to enable accurate fine-grained dense semantic mask discovery. Our evaluation demonstrates superior performance of EASe over previous state-of-the-arts (SOTAs) across major standard benchmarks and diverse datasets with complex morphologies. Code is available at https://ease-project.github.io --- ### OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning Authors: Taiting Lu, Kaiyuan Lin, Yuxin Tian, Mingjia Wang, Yubo Wang, Muchuan Wang, Sharique Khatri, Akshit Kartik, Yixi Wang, Amey Santosh Rane, Yida Wang, Sung-Liang Chen et al. Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00270v4 Recent large multimodal models (LMMs) have made rapid progress in visual grounding, document understanding, and diagram reasoning tasks. However, their ability to convert Printed Circuit Board (PCB) schematic diagrams into machine-readable spatially weighted netlist graphs, jointly capturing component attributes, connectivity, and geometry, remains largely underexplored, despite such graph representations are the backbone of practical electronic design automation (EDA) workflows. To bridge this gap, we introduce OmniSch, the first comprehensive benchmark designed to assess LMMs on schematic understanding and spatial netlist graph construction. OmniSch contains 1,854 real-world schematic diagrams and includes four tasks: (1) visual grounding for schematic entities, with 109.9K grounded instances aligning 423.4K diagram semantic labels to their visual regions; (2) diagram-to-graph reasoning, understanding topological relationship among diagram elements; (3) geometric reasoning, constructing layout-dependent weights for each connection; and (4) tool-augmented agentic reasoning for visual search, invoking external tools to accomplish (1)-(3). Our results reveal substantial gaps of current LMMs in interpreting schematic engineering artifacts, including unreliable fine-grained grounding, brittle layout-to-graph parsing, inconsistent global connectivity reasoning and inefficient visual exploration. --- ### Omni-MMSI: Toward Identity-attributed Social Interaction Understanding Authors: Xinpeng Li, Bolin Lai, Hardy Chen, Shijian Deng, Cihang Xie, Yuyin Zhou, James Matthew Rehg, Yapeng Tian Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00267v1 We introduce Omni-MMSI, a new task that requires comprehensive social interaction understanding from raw audio, vision, and speech input. The task involves perceiving identity-attributed social cues (e.g., who is speaking what) and reasoning about the social interaction (e.g., whom the speaker refers to). This task is essential for developing AI assistants that can perceive and respond to human interactions. Unlike prior studies that operate on oracle-preprocessed social cues, Omni-MMSI reflects realistic scenarios where AI assistants must perceive and reason from raw data. However, existing pipelines and multi-modal LLMs perform poorly on Omni-MMSI because they lack reliable identity attribution capabilities, which leads to inaccurate social interaction understanding. To address this challenge, we propose Omni-MMSI-R, a reference-guided pipeline that produces identity-attributed social cues with tools and conducts chain-of-thought social reasoning. To facilitate this pipeline, we construct participant-level reference pairs and curate reasoning annotations on top of the existing datasets. Experiments demonstrate that Omni-MMSI-R outperforms advanced LLMs and counterparts on Omni-MMSI. Project page: https://sampson-lee.github.io/omni-mmsi-project-page. --- ### Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation Authors: Edoardo Zorzi, Francesco Taioli, Yiming Wang, Marco Cristani, Alessandro Farinelli, Alberto Castellini, Loris Bazzani Published: 2026-03-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.00265v1 We propose Question-Asking Navigation (QAsk-Nav), the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN) that enables an explicit, separate assessment of embodied navigation and collaborative question asking. CoIN tasks an embodied agent with reaching a target specified in free-form natural language under partial observability, using only egocentric visual observations and interactive natural-language dialogue with a human, where the dialogue can help to resolve ambiguity among visually similar object instances. Existing CoIN benchmarks are primarily focused on navigation success and offer no support for consistent evaluation of collaborative interaction. To address this limitation, QAsk-Nav provides (i) a lightweight question-asking protocol scored independently of navigation, (ii) an enhanced navigation protocol with realistic, diverse, high-quality target descriptions, and (iii) an open-source dataset, that includes 28,000 quality-checked reasoning and question-asking traces for training and analysis of interactive capabilities of CoIN models. Using the proposed QAsk-Nav benchmark, we develop Light-CoNav, a lightweight unified model for collaborative navigation that is 3x smaller and 70x faster than existing modular methods, while outperforming state-of-the-art CoIN approaches in generalization to unseen objects and environments. Project page at https://benchmarking-interaction.github.io/ --- ### Autonomous Adaptive Solver Selection for Chemistry Integration via Reinforcement Learning Authors: Eloghosa Ikponmwoba, Opeoluwa Owoyele Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.00264v1 The computational cost of stiff chemical kinetics remains a dominant bottleneck in reacting-flow simulation, yet hybrid integration strategies are typically driven by hand-tuned heuristics or supervised predictors that make myopic decisions from instantaneous local state. We introduce a constrained reinforcement learning (RL) framework that autonomously selects between an implicit BDF integrator (CVODE) and a quasi-steady-state (QSS) solver during chemistry integration. Solver selection is cast as a Markov decision process. The agent learns trajectory-aware policies that account for how present solver choices influence downstream error accumulation, while minimizing computational cost under a user-prescribed accuracy tolerance enforced through a Lagrangian reward with online multiplier adaptation. Across sampled 0D homogeneous reactor conditions, the RL-adaptive policy achieves a mean speedup of approximately $3\times$, with speedups ranging from $1.11\times$ to $10.58\times$, while maintaining accurate ignition delays and species profiles for a 106-species \textit{n}-dodecane mechanism and adding approximately $1\%$ inference overhead. Without retraining, the 0D-trained policy transfers to 1D counterflow diffusion flames over strain rates $10$--$2000~\mathrm{s}^{-1}$, delivering consistent $\approx 2.2\times$ speedup relative to CVODE while preserving near-reference temperature accuracy and selecting CVODE at only $12$--$15\%$ of space-time points. Overall, the results demonstrate the potential of the proposed reinforcement learning framework to learn problem-specific integration strategies while respecting accuracy constraints, thereby opening a pathway toward adaptive, self-optimizing workflows for multiphysics systems with spatially heterogeneous stiffness. --- ### Feature-level Site Leakage Reduction for Cross-Hospital Chest X-ray Transfer via Self-Supervised Learning Authors: Ayoub Louaye Bouaziz, Lokmane Chebouba Published: 2026-03-31 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2604.00263v1 Cross-hospital failure in chest X-ray models is often attributed to domain shift, yet most work assumes invariance without measuring it. This paper studies how to measure site leakage directly and how that measurement changes conclusions about transfer methods. We study multi-site self-supervised learning (SSL) and feature-level adversarial site confusion for cross-hospital transfer. We pretrain a ResNet-18 on NIH and CheXpert without pathology labels. We then freeze the encoder and train a linear pneumonia classifier on NIH only, evaluating transfer to RSNA. We quantify site leakage using a post hoc linear probe that predicts acquisition site from frozen backbone features $f$ and projection features $z$. Across 3 random seeds, multi-site SSL improves RSNA AUC from 0.6736 $\pm$ 0.0148 (ImageNet initialization) to 0.7804 $\pm$ 0.0197. Adding adversarial site confusion on $f$ reduces measured leakage but does not reliably improve AUC and increases variance. On $f$, site probe accuracy drops from 0.9890 $\pm$ 0.0021 (SSL-only) to 0.8504 $\pm$ 0.0051 (CanonicalF), where chance is 0.50. On $z$, probe accuracy drops from 0.8912 $\pm$ 0.0092 to 0.7810 $\pm$ 0.0250. These results show that measuring leakage changes how transfer methods should be interpreted: multi-site SSL drives transfer, while adversarial confusion exposes the limits of invariance assumptions. --- ### Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Study Authors: Zaifu Zhan, Mengyuan Cui, Rui Zhang Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00261v2 Large language models (LLMs) have achieved strong performance on medical question answering (medical QA), and chain-of-thought (CoT) prompting has further improved results by eliciting explicit intermediate reasoning; meanwhile, self-reflective (self-corrective) prompting has been widely claimed to enhance model reliability by prompting LLMs to critique and revise their own reasoning, yet its effectiveness in safety-critical medical settings remains unclear. In this work, we conduct an exploratory analysis of self-reflective reasoning for medical multiple-choice question answering: using GPT-4o and GPT-4o-mini, we compare standard CoT prompting with an iterative self-reflection loop and track how predictions evolve across reflection steps on three widely used medical QA benchmarks (MedQA, HeadQA, and PubMedQA). We analyze whether self-reflection leads to error correction, error persistence, or the introduction of new errors. Our results show that self-reflective prompting does not consistently improve accuracy and its impact is highly dataset- and model-dependent: it yields modest gains on MedQA but provides limited or negative benefits on HeadQA and PubMedQA, and increasing the number of reflection steps does not guarantee better performance. These findings highlight a gap between reasoning transparency and reasoning correctness, suggesting that self-reflective reasoning is better viewed as an analytical tool for understanding model behavior rather than a standalone solution for improving medical QA reliability. --- ### Learning to Shuffle: Block Reshuffling and Reversal Schemes for Stochastic Optimization Authors: Lam M. Nguyen, Dzung T. Phan, Jayant Kalagnanam Published: 2026-03-31 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2604.00260v1 Shuffling strategies for stochastic gradient descent (SGD), including incremental gradient, shuffle-once, and random reshuffling, are supported by rigorous convergence analyses for arbitrary within-epoch permutations. In particular, random reshuffling is known to improve optimization constants relative to cyclic and shuffle-once schemes. However, existing theory offers limited guidance on how to design new data-ordering schemes that further improve optimization constants or stability beyond random reshuffling. In this paper, we design a pipeline using a large language model (LLM)-guided program evolution framework to discover an effective shuffling rule for without-replacement SGD. Abstracting from this instance, we identify two fundamental structural components: block reshuffling and paired reversal. We analyze these components separately and show that block reshuffling strictly reduces prefix-gradient variance constants within the unified shuffling framework, yielding provable improvements over random reshuffling under mild conditions. Separately, we show that paired reversal symmetrizes the epoch map and cancels the leading order-dependent second-order term, reducing order sensitivity from quadratic to cubic in the step size. Numerical experiments with the discovered algorithm validate the theory and demonstrate consistent gains over standard shuffling schemes across convex and nonconvex benchmarks. --- ### LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias Authors: Filip J. Kucia, Anirban Chakraborty, Anna Wróblewska Published: 2026-03-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00259v1 Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open essay-scoring datasets (ASAP 2.0, ELLIPSE, and DREsS) that cover both holistic and analytic scoring. We analyze agreement with human consensus scores, directional bias, and the stability of bias estimates. Our results show that strong open-weight models achieve moderate to high agreement with humans on holistic scoring (Quadratic Weighted Kappa about 0.6), but this does not transfer uniformly to analytic scoring. In particular, we observe large and stable negative directional bias on Lower-Order Concern (LOC) traits, such as Grammar and Conventions, meaning that models often score these traits more harshly than human raters. We also find that concise keyword-based prompts generally outperform longer rubric-style prompts in multi-trait analytic scoring. To quantify the amount of data needed to detect these systematic deviations, we compute the minimum sample size at which a 95% bootstrap confidence interval for the mean bias excludes zero. This analysis shows that LOC bias is often detectable with very small validation sets, whereas Higher-Order Concern (HOC) traits typically require much larger samples. These findings support a bias-correction-first deployment strategy: instead of relying on raw zero-shot scores, systematic score offsets can be estimated and corrected using small human-labeled bias-estimation sets, without requiring large-scale fine-tuning. --- ### Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards Authors: Md Mirajul Islam, Rajesh Debnath, Adittya Soukarjya Saha, Min Chi Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00258v1 While apprenticeship learning has shown promise for inducing effective pedagogical policies directly from student interactions in e-learning environments, most existing approaches rely on optimal or near-optimal expert demonstrations under a fixed reward. Real-world student interactions, however, are often inherently imperfect and evolving: students explore, make errors, revise strategies, and refine their goals as understanding develops. In this work, we argue that imperfect student demonstrations are not noise to be discarded, but structured signals-provided their relative quality is ranked. We introduce HALIDE, Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards, which not only leverages sub-optimal student demonstrations, but ranks them within a hierarchical learning framework. HALIDE models student behavior at multiple levels of abstraction, enabling inference of higher-level intent and strategy from suboptimal actions while explicitly capturing the temporal evolution of student reward functions. By integrating demonstration quality into hierarchical reward inference,HALIDE distinguishes transient errors from suboptimal strategies and meaningful progress toward higher-level learning goals. Our results show that HALIDE more accurately predicts student pedagogical decisions than approaches that rely on optimal trajectories, fixed rewards, or unranked imperfect demonstrations. --- ### Informed Machine Learning with Knowledge Landmarks Authors: Chuyi Dai, Witold Pedrycz, Suping Xu, Ding Liu, Xianmin Wang Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.00256v1 Informed Machine Learning has emerged as a viable generalization of Machine Learning (ML) by building a unified conceptual and algorithmic setting for constructing models on a unified basis of knowledge and data. Physics-informed ML involving physics equations is one of the developments within Informed Machine Learning. This study proposes a novel direction of Knowledge-Data ML, referred to as KD-ML, where numeric data are integrated with knowledge tidbits expressed in the form of granular knowledge landmarks. We advocate that data and knowledge are complementary in several fundamental ways: data are precise (numeric) and local, usually confined to some region of the input space, while knowledge is global and formulated at a higher level of abstraction. The knowledge can be represented as information granules and organized as a collection of input-output information granules called knowledge landmarks. In virtue of this evident complementarity, we develop a comprehensive design process of the KD-ML model and formulate an original augmented loss function L, which additively embraces the component responsible for optimizing the model based on available numeric data, while the second component, playing the role of a granular regularizer, so that it adheres to the granular constraints (knowledge landmarks). We show the role of the hyperparameter positioned in the loss function, which balances the contribution and guiding role of data and knowledge, and point to some essential tendencies associated with the quality of data (noise level) and the level of granularity of the knowledge landmarks. Experiments on two physics-governed benchmarks demonstrate that the proposed KD model consistently outperforms data-driven ML models. --- ### PRISM: Differentiable Analysis-by-Synthesis for Fixel Recovery in Diffusion MRI Authors: Mohamed Abouagour, Atharva Shah, Eleftherios Garyfallidis Published: 2026-03-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.00250v1 Diffusion MRI microstructure fitting is nonconvex and often performed voxelwise, which limits fiber peak recovery in narrow crossings. This work introduces PRISM, a differentiable analysis-by-synthesis framework that fits an explicit multi-compartment forward model end-to-end over spatial patches. The model combines cerebrospinal fluid (CSF), gray matter, up to K white-matter fiber compartments (stick-and-zeppelin), and a restricted compartment, with explicit fiber directions and soft model selection via repulsion and sparsity priors. PRISM supports a fast MSE objective and a Rician negative log-likelihood (NLL) that jointly learns sigma without oracle information. A lightweight nuisance calibration module (smooth bias field and per-measurement scale/offset) is included for robustness and regularized to identity in clean-data tests. On synthetic crossing-fiber data (SNR=30; five methods, 16 crossing angles), PRISM achieves 3.5 degrees best-match angular error with 95% recall, which is 1.9x lower than the best baseline (MSMT-CSD, 6.8 degrees, 83% recall); in NLL mode with learned sigma, error drops to 2.3 degrees with 99% recall, resolving crossings down to 20 degrees. On the DiSCo1 phantom (NLL mode), PRISM improves connectivity correlation over CSD baselines at all four tracking angles (best r=.934 at 25 degrees vs. .920 for MSMT-CSD). Whole-brain HCP fitting (~741k voxels, MSE mode) completes in ~12 min on a single GPU with near-identical results across random seeds. --- ### A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation Authors: Ha Na Cho Published: 2026-03-31 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.00249v1 Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM framework designed to simulate supportive behavioral health dialogue through coordinated, role-differentiated agents. Conversational responsibilities are decomposed across specialized agents, including empathy-focused, action-oriented, and supervisory roles, while a prompt-based controller dynamically activates relevant agents and enforces continuous safety auditing. Using semi-structured interview transcripts from the DAIC-WOZ corpus, we evaluate the framework with scalable proxy metrics capturing structural quality, functional diversity, and computational characteristics. Results illustrate clear role differentiation, coherent inter-agent coordination, and predictable trade-offs between modular orchestration, safety oversight, and response latency when compared to a single-agent baseline. This work emphasizes system design, interpretability, and safety, positioning the framework as a simulation and analysis tool for behavioral health informatics and decision-support research rather than a clinical intervention. --- ### REM-CTX: Automated Peer Review via Reinforcement Learning with Auxiliary Context Authors: Pawin Taechoyotin, Daniel E. Acuna Published: 2026-03-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00248v1 Most automated peer review systems rely on textual manuscript content alone, leaving visual elements such as figures and external scholarly signals underutilized. We introduce REM-CTX, a reinforcement-learning system that incorporates auxiliary context into the review generation process via correspondence-aware reward functions. REM-CTX trains an 8B-parameter language model with Group Relative Policy Optimization (GRPO) and combines a multi-aspect quality reward with two correspondence rewards that explicitly encourage alignment with auxiliary context. Experiments on manuscripts across Computer, Biological, and Physical Sciences show that REM-CTX achieves the highest overall review quality among six baselines, outperforming other systems with substantially larger commercial models, and surpassing the next-best RL baseline across both quality and contextual grounding metrics. Ablation studies confirm that the two correspondence rewards are complementary: each selectively improves its targeted correspondence reward while preserving all quality dimensions, and the full model outperforms all partial variants. Analysis of training dynamics reveals that the criticism aspect is negatively correlated with other metrics during training, suggesting that future studies should group multi-dimension rewards for review generation. --- ### UCell: rethinking generalizability and scaling of bio-medical vision models Authors: Nicholas Kuang, Vanessa Scalon, Ji Yu Published: 2026-03-31 Categories: cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2604.00243v1 The modern deep learning field is a scale-centric one. Larger models have been shown to consistently perform better than smaller models of similar architecture. In many sub-domains of biomedical research, however, the model scaling is bottlenecked by the amount of available training data, and the high cost associated with generating and validating additional high quality data. Despite the practical hurdle, the majority of the ongoing research still focuses on building bigger foundation models, whereas the alternative of improving the ability of small models has been under-explored. Here we experiment with building models with 10-30M parameters, tiny by modern standards, to perform the single-cell segmentation task. An important design choice is the incorporation of a recursive structure into the model's forward computation graph, leading to a more parameter-efficient architecture. We found that for the single-cell segmentation, on multiple benchmarks, our small model, UCell, matches the performance of models 10-20 times its size, and with a similar generalizability to unseen out-of-domain data. More importantly, we found that ucell can be trained from scratch using only a set of microscopy imaging data, without relying on massive pretraining on natural images, and therefore decouples the model building from any external commercial interests. Finally, we examined and confirmed the adaptability of ucell by performing a wide range of one-shot and few-shot fine tuning experiments on a diverse set of small datasets. Implementation is available at https://github.com/jiyuuchc/ucell --- ### FGR-ColBERT: Identifying Fine-Grained Relevance Tokens During Retrieval Authors: Antonín Jarolím, Martin Fajčík Published: 2026-03-31 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2604.00242v1 Document retrieval identifies relevant documents but does not provide fine-grained evidence cues, such as specific relevant spans. A possible solution is to apply an LLM after retrieval; however, this introduces significant computational overhead and limits practical deployment. We propose FGR-ColBERT, a modification of ColBERT retrieval model that integrates fine-grained relevance signals distilled from an LLM directly into the retrieval function. Experiments on MS MARCO show that FGR-ColBERT (110M) achieves a token-level F1 of 64.5, exceeding the 62.8 of Gemma 2 (27B), despite being approximately 245 times smaller. At the same time, it preserves retrieval effectiveness (99% relative Recall@50) and remains efficient, incurring only a ~1.12x latency overhead compared to the original ColBERT. --- ### Softmax gradient policy for variance minimization and risk-averse multi armed bandits Authors: Gabriel Turinici Published: 2026-03-31 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2604.00241v2 Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and numerically. While most classical approaches aim to identify the arm with the highest expected reward, we focus on a risk-aware setting where the goal is to select the arm with the lowest variance, favoring stability over potentially high but uncertain returns. To model the decision process, we consider a softmax parameterization of the policy; we propose a new algorithm to select the minimal variance (or minimal risk) arm and prove its convergence under natural conditions. The algorithm constructs an unbiased estimate of the objective by using two independent draws from the selected arm's distribution. We provide numerical experiments that illustrate the practical behavior of these algorithms and offer guidance on implementation choices. The setting also covers general risk-aware problems where there is a trade-off between maximizing the average reward and minimizing its variance. --- ### Softmax gradient policy for variance minimization and risk-averse multi armed bandits Authors: Gabriel Turinici Published: 2026-03-31 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2604.00241v1 Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and numerically. While most classical approaches aim to identify the arm with the highest expected reward, we focus on a risk-aware setting where the goal is to select the arm with the lowest variance, favoring stability over potentially high but uncertain returns. To model the decision process, we consider a softmax parameterization of the policy; we propose a new algorithm to select the minimal variance (or minimal risk) arm and prove its convergence under natural conditions. The algorithm constructs an unbiased estimate of the objective by using two independent draws from the current's arm distribution. We provide numerical experiments that illustrate the practical behavior of these algorithms and offer guidance on implementation choices. The setting also covers general risk-aware problems where there is a trade-off between maximizing the average reward and minimizing its variance. --- ### A Taxonomy of Programming Languages for Code Generation Authors: Nishat Raihan, Christian Newman, Marcos Zampieri Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00239v3 The world's 7,000+ languages vary widely in the availability of resources for NLP, motivating efforts to systematically categorize them by their degree of resourcefulness (Joshi et al., 2020). A similar disparity exists among programming languages (PLs); however, no resource-tier taxonomy has been established for code. As large language models (LLMs) grow increasingly capable of generating code, such a taxonomy becomes essential. To fill this gap, we present the first reproducible PL resource classification, grouping 646 languages into four tiers. We show that only 1.9% of languages (Tier 3, High) account for 74.6% of all tokens in seven major corpora, while 71.7% of languages (Tier 0, Scarce) contribute just 1.0%. Statistical analyses of within-tier inequality, dispersion, and distributional skew confirm that this imbalance is both extreme and systematic. Our results provide a principled framework for dataset curation and tier-aware evaluation of multilingual LLMs. --- ### A Taxonomy of Programming Languages for Code Generation Authors: Nishat Raihan, Christian Newman, Marcos Zampieri Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00239v2 The world's 7,000+ languages vary widely in the availability of resources for NLP, motivating efforts to systematically categorize them by their degree of resourcefulness (Joshi et al., 2020). A similar disparity exists among programming languages (PLs); however, no resource-tier taxonomy has been established for code. As large language models (LLMs) grow increasingly capable of generating code, such a taxonomy becomes essential. To fill this gap, we present the first reproducible PL resource classification, grouping 646 languages into four tiers. We show that only 1.9% of languages (Tier 3, High) account for 74.6% of all tokens in seven major corpora, while 71.7% of languages (Tier 0, Scarce) contribute just 1.0%. Statistical analyses of within-tier inequality, dispersion, and distributional skew confirm that this imbalance is both extreme and systematic. Our results provide a principled framework for dataset curation and tier-aware evaluation of multilingual LLMs. --- ### AI-Mediated Explainable Regulation for Justice Authors: Thomas Hofweber, Andreas Sudmann, Evangelos Pournaras Published: 2026-03-31 Categories: cs.CY, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.00237v1 Present practice of deciding on regulation faces numerous problems that make adopted regulations static, unexplained, unduly influenced by powerful interest groups, and stained with a perception of illegitimacy. These well-known problems with the regulatory process can lead to injustice and have substantial negative effects on society and democracy. We discuss a new approach that utilizes distributed artificial intelligence (AI) to make a regulatory recommendation that is explainable and adaptable by design. We outline the main components of a system that can implement this approach and show how it would resolve the problems with the present regulatory system. This approach models and reasons about stakeholder preferences with separate preference models, while it aggregates these preferences in a value sensitive way. Such recommendations can be updated due to changes in facts or in values and are inherently explainable. We suggest how stakeholders can make their preferences known to the system and how they can verify whether they were properly considered in the regulatory decision. The resulting system promises to support regulatory justice, legitimacy, and compliance. --- ### Hierarchical Discrete Flow Matching for Graph Generation Authors: Yoann Boget, Pablo Strasser, Alexandros Kalousis Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.00236v1 Denoising-based models, including diffusion and flow matching, have led to substantial advances in graph generation. Despite this progress, such models remain constrained by two fundamental limitations: a computational cost that scales quadratically with the number of nodes and a large number of function evaluations required during generation. In this work, we introduce a novel hierarchical generative framework that reduces the number of node pairs that must be evaluated and adopts discrete flow matching to significantly decrease the number of denoising iterations. We empirically demonstrate that our approach more effectively captures graph distributions while substantially reducing generation time. --- ### MAC-Attention: a Match-Amend-Complete Scheme for Fast and Accurate Attention Computation Authors: Jinghan Yao, Sam Adé Jacobs, Walid Krichene, Masahiro Tanaka, Dhabaleswar K Panda Published: 2026-03-31 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.00235v1 Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can degrade delayed recall and long-form generation. We introduce MAC-Attention, a fidelity- and access-preserving alternative that accelerates decoding by reusing prior attention computations for semantically similar recent queries. It starts with a match stage that performs pre-RoPE L2 matching over a short local window; an amend stage rectifies the reused attention by recomputing a small band near the match boundary; and a complete stage fuses the rectified results with fresh attention computed on the KV tail through a numerically stable merge. On a match hit, the compute and bandwidth complexity is constant regardless of context length. The method is model-agnostic and composes with IO-aware kernels, paged-KV managers, and MQA/GQA. Across LongBench v2 (120K), RULER (120K), and LongGenBench (16K continuous generation), compared to the latest FlashInfer library, MAC-Attention reduces KV accesses by up to 99%, cuts token generation latency by over 60% at 128K, and achieves over 14.3x attention-phase speedups, up to 2.6x end-to-end, while maintaining full-attention quality. By reusing computation, MAC-Attention delivers long-context inference that is both fast and faithful. Code is available here: https://github.com/YJHMITWEB/MAC-Attention.git --- ### Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold Authors: Anamika Paul Rupa Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.00230v3 Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised. We identify a simple and predictive regularity: NC occurs when the mean feature norm reaches a model-dataset-specific critical value, fn*, that is largely invariant to training conditions. This value concentrates tightly within each (model, dataset) pair (CV < 8%); training dynamics primarily affect the rate at which fn approaches fn*, rather than the value itself. In standard training trajectories, the crossing of fn below fn* consistently precedes NC onset, providing a practical predictor with a mean lead time of 62 epochs (MAE 24 epochs). A direct intervention experiment confirms fn* is a stable attractor of the gradient flow -- perturbations to feature scale are self-corrected during training, with convergence to the same value regardless of direction (p>0.2). Completing the (architecture)x(dataset) grid reveals the paper's strongest result: ResNet-20 on MNIST gives fn* = 5.867 -- a +458% architecture effect versus only +68% on CIFAR-10. The grid is strongly non-additive; fn* cannot be decomposed into independent architecture and dataset contributions. Four structural regularities emerge: (1) depth has a non-monotonic effect on collapse speed; (2) activation jointly determines both collapse speed and fn*; (3) weight decay defines a three-regime phase diagram -- too little slows, an optimal range is fastest, and too much prevents collapse; (4) width monotonically accelerates collapse while shifting fn* by at most 13%. These results establish feature-norm dynamics as an actionable diagnostic for predicting NC timing, suggesting that norm-threshold behaviour is a general mechanism underlying delayed representational reorganisation in deep networks. --- ### Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries Authors: Tanay Gondil Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00228v1 Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal behavior, then respond in a fresh context. Across 3754 datapoints spanning 300 requests, we evaluate four frontier models: Claude Sonnet 4, Claude Sonnet 4.5, GPT-5.2, and Llama 3.1 405B. Using signal detection theory (SDT), we find that all models exhibit high introspective sensitivity (d' = 2.4-3.5), but sensitivity drops substantially at safety boundaries. We observe generational improvement within Claude (Sonnet 4.5: 95.7 percent accuracy vs Sonnet 4: 93.0 percent), while GPT-5.2 shows lower accuracy (88.9 percent) with more variable behavior. Llama 405B achieves high sensitivity but exhibits strong refusal bias and poor calibration, resulting in lower overall accuracy (80.0 percent). Topic-wise analysis reveals weapons-related queries are consistently hardest for introspection. Critically, confidence scores provide actionable signal: restricting to high-confidence predictions yields 98.3 percent accuracy for well-calibrated models, enabling practical confidence-based routing for safety-critical deployments. --- ### Pupil Design for Computational Wavefront Estimation Authors: Ali Almuallem, Nicholas Chimitt, Bole Ma, Qi Guo, Stanley H. Chan Published: 2026-03-31 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2604.00225v1 Establishing a precise connection between imaged intensity and the incident wavefront is essential for emerging applications in adaptive optics, holography, computational microscopy, and non-line-of-sight imaging. While prior work has shown that breaking symmetries in pupil design enables wavefront recovery from a single intensity measurement, there is little guidance on how to design a pupil that improves wavefront estimation. In this work we introduce a quantitative asymmetry metric to bridge this gap and, through an extensive empirical study and supporting analysis, demonstrate that increasing asymmetry enhances wavefront recoverability. We analyze the trade-offs in pupil design, and the impact on light throughput along with performance in noise. Both large-scale simulations and optical bench experiments are carried out to support our findings. --- ### Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation Authors: Hoang-Chau Luong, Dat Ba Tran, Lingwei Chen Published: 2026-03-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00223v1 Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and significant teacher-student capacity mismatch, where RKL focuses learning on dominant modes rather than enforcing dense alignment. However, RKL introduces a structural limitation that drives the student toward overconfident predictions. We first provide an analysis of RKL by decomposing its gradients into target and non-target components, and show that non-target gradients consistently push the target logit upward even when the student already matches the teacher, thereby reducing output diversity. In addition, RKL provides weak supervision over non-target classes, leading to poor tail alignment. To address these issues, we propose Diversity-aware RKL (DRKL), which removes this gradient effect and strengthens non-target supervision while preserving the optimization benefits of RKL. Extensive experiments across datasets and model families demonstrate that DRKL consistently outperforms FKL, RKL, and other state-of-the-art distillation objectives, achieving better performance and a superior fidelity-diversity trade-off. --- ### Risk-Aware Batch Testing for Performance Regression Detection Authors: Ali Sayedsalehi, Peter C. Rigby, Gregory Mierzwinski Published: 2026-03-31 Categories: cs.SE, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2604.00222v1 Performance regression testing is essential in large-scale continuous-integration (CI) systems, yet executing full performance suites for every commit is prohibitively expensive. Prior work on performance regression prediction and batch testing has shown independent benefits, but each faces practical limitations: predictive models are rarely integrated into CI decision-making, and conventional batching strategies ignore commit-level heterogeneity. We unify these strands by introducing a risk-aware framework that integrates machine-learned commit risk with adaptive batching. Using Mozilla Firefox as a case study, we construct a production-derived dataset of human-confirmed regressions aligned chronologically with Autoland, and fine-tune ModernBERT, CodeBERT, and LLaMA-3.1 variants to estimate commit-level performance regression risk, achieving up to 0.694 ROC-AUC with CodeBERT. The risk scores drive a family of risk-aware batching strategies, including Risk-Aged Priority Batching and Risk-Adaptive Stream Batching, evaluated through realistic CI simulations. Across thousands of historical Firefox commits, our best overall configuration, Risk-Aged Priority Batching with linear aggregation (RAPB-la), yields a Pareto improvement over Mozilla's production-inspired baseline. RAPB-la reduces total test executions by 32.4%, decreases mean feedback time by 3.8%, maintains mean time-to-culprit at approximately the baseline level, reduces maximum time-to-culprit by 26.2%, and corresponds to an estimated annual infrastructure cost savings of approximately $491K under our cost model. These results demonstrate that risk-aware batch testing can reduce CI resource consumption while improving diagnostic timeliness. To support reproducibility and future research, we release a complete replication package containing all datasets, fine-tuning pipelines, and implementations of our batching algorithms. --- ### Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations Authors: Haoran Wang, Li Xiong, Kai Shu Published: 2026-03-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00209v2 Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where humans would exercise discretion. This raises a fundamental question: do LLMs internally encode contextual privacy norms, and if so, why do violations persist? We present the first systematic study of contextual privacy as a structured latent representation in LLMs, grounded in contextual integrity (CI) theory. Probing multiple models, we find that the three norm-determining CI parameters (information type, recipient, and transmission principle) are encoded as linearly separable and functionally independent directions in activation space. Despite this internal structure, models still leak private information in practice, revealing a clear gap between concept representation and model behavior. To bridge this gap, we introduce CI-parametric steering, which independently intervenes along each CI dimension. This structured control reduces privacy violations more effectively and predictably than monolithic steering. Our results demonstrate that contextual privacy failures arise from misalignment between representation and behavior rather than missing awareness, and that leveraging the compositional structure of CI enables more reliable contextual privacy control, shedding light on potential improvement of contextual privacy understanding in LLMs. --- ### Similarity of Neural Network Representations in Superposition Authors: Sunny Liu, Habon Issa, André Longon, Liv Gorton, Meenakshi Khosla, Alex Williams, David Klindt Published: 2026-03-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.00208v2 Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational Similarity Analysis, Centered Kernel Alignment, and linear regression) are frequently applied to neural activity coordinates rather than on the underlying features. We show this matters when neural systems operate in superposition, encoding more features than they have neurons via linear compression. Closed-form derivations prove that these metrics depend on the Gram matrices of each system's projection, not on the latent features themselves: alignment thus combines what a system represents with how it is encoded. For those interested in what features two systems share, this is a problem: Two networks can have identical feature content yet appear more dissimilar than networks exhibiting partial feature overlap. This apparent misalignment need not reflect lost information as compressed sensing guarantees sparse features remain recoverable from the compressed activity. We confirm this by training supervised TopK sparse autoencoders that realize solvable compressed sensing by construction, finding alignment on recovered latents restored even when raw-activation alignment remains deflated. We extend the result to unsupervised SAEs trained without ground-truth latents, and to pretrained vision and language model SAEs, where SAE-latent alignment exceeds raw-activation alignment, consistent with superposition in real systems. ---