# Research Papers — 2026-04 · bundle page 43 of 233 > Full-text markdown of papers #2101–2150 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/43 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/42.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/44.md) ### Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting Authors: Yiqian Liu, Jiayi Niu, Adam Kelleher, Subhabrata Das Published: 2026-04-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.24788v1 Natural gas is undoubtedly an essential component of the global energy system. Accurate short-term forecasting of natural gas price is challenging due to pronounced volatility driven by seasonal demand patterns, geopolitical developments, and shifting macroeconomic conditions. The nonlinear dynamics and frequent regime changes can limit the effectiveness of traditional time-series models. In this study, we explore the use of Liquid Neural Networks (LNNs) for short-horizon forecasting of the Henry Hub spot price, a primary benchmark for pricing. LNNs are designed to adapt continuously to evolving temporal patterns through dynamic internal state updates, making them well suited for nonstationary price behavior. By improving forecast accuracy in volatile market conditions, this work aims to reduce uncertainty and enhance decision support across energy trading and power market applications. --- ### Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers Authors: Harri Renney, Fouad Trad, Michael Mattarock, Jayden Evetts, Zena Wood Published: 2026-04-24 Categories: cs.AR, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2604.24785v2 Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational technology and defence environments. Advances in model distillation, quantisation, and affordable edge accelerators now make local LLM inference on single-board computers feasible, but the high dimensionality of the configuration space makes identifying optimal deployments difficult without structured evaluation. Existing LLM-specific edge benchmarking efforts rely on CPU-only inference, poor coverage of genuine single-board computers, and generic evaluation tasks that lack multi-dimensional assessment of hardware effectiveness. This paper proposes a multi-dimensional benchmarking methodology that jointly evaluates inference performance and hardware efficiency across four IoT-suitable edge platform configurations testing single-board computers with the latest available hardware accelerators. Our results reveal the benefits of using hardware accelerators such as NPUs and GPUs, along with multi-dimensional evaluations quantifying the trade-offs between power efficiency, physical device size and token throughput; offering practical guidance for deploying generative AI in privacy-sensitive and connectivity-limited environments such as unmanned vehicles and portable, ruggedised operations. --- ### RL Token: Bootstrapping Online RL with Vision-Language-Action Models Authors: Charles Xu, Jost Tobias Springenberg, Michael Equi, Ali Amin, Adnan Esmail, Sergey Levine, Liyiming Ke Published: 2026-04-24 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.23073v2 Vision-language-action (VLA) models can learn to perform diverse manipulation skills "out of the box," but achieving the precision and speed that real-world tasks demand requires further fine-tuning -- for example, via reinforcement learning (RL). We introduce a lightweight method that enables sample-efficient online RL fine-tuning of pretrained VLAs using just a few hours of real-world practice. We (1) adapt the VLA to expose an "RL token," a compact readout representation that preserves task-relevant pretrained knowledge while serving as an efficient interface for online RL, and (2) train a small actor-critic head on this RL token to refine the actions, while anchoring the learned policy to the VLA. Online RL with the RL token (RLT) makes it possible to fine-tune even large VLAs with RL quickly and efficiently. Across four real-robot tasks (screw installation, zip tie fastening, charger insertion, and Ethernet insertion), RLT improves the speed on the hardest part of the task by up to 3x and raises success rates significantly within minutes to a few hours of practice. It can even surpass the speed of human teleoperation on some of the tasks. --- ### Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis Authors: Junyan Cheng, Kyle Richardson, Peter Chin Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23072v1 Large language model (LLM) agents are increasingly tasked with complex real-world analysis (e.g., in financial forecasting, scientific discovery), yet their reasoning suffers from stochastic instability and lacks a verifiable, compositional structure. To address this, we introduce Analytica, a novel agent architecture built on the principle of Soft Propositional Reasoning (SPR). SPR reframes complex analysis as a structured process of estimating the soft truth values of different outcome propositions, allowing us to formally model and minimize the estimation error in terms of its bias and variance. Analytica operationalizes this through a parallel, divide-and-conquer framework that systematically reduces both sources of error. To reduce bias, problems are first decomposed into a tree of subpropositions, and tool-equipped LLM grounder agents are employed, including a novel Jupyter Notebook agent for data-driven analysis, that help to validate and score facts. To reduce variance, Analytica recursively synthesizes these grounded leaves using robust linear models that average out stochastic noise with superior efficiency, scalability, and enable interactive "what-if" scenario analysis. Our theoretical and empirical results on economic, financial, and political forecasting tasks show that Analytica improves 15.84% accuracy on average over diverse base models, achieving 71.06% accuracy with the lowest variance of 6.02% when working with a Deep Research grounder. Our Jupyter Notebook grounder shows strong cost-effectiveness that achieves a close 70.11% accuracy with 90.35% less cost and 52.85% less time. Analytica also exhibits highly noise-resilient and stable performance growth as the analysis depth increases, with a near-linear time complexity, as well as good adaptivity to open-weight LLMs and scientific domains. --- ### ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents Authors: Yating Wu, Yuhao Zhang, Sayan Ghosh, Sourya Basu, Anoop Deoras, Jun Huan, Gaurav Gupta Published: 2026-04-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23069v1 Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured information that later steps rely on. Recent retrieval-based memory systems surface relevant content but still overlook the causal and logical structure needed for multi-step reasoning. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. Unlike prior context management approaches, ContextWeaver supports: (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summarization that condenses root-to-step reasoning paths into reusable units; and (3) a lightweight validation layer that incorporates execution feedback. On the SWE-Bench Verified and Lite benchmarks, ContextWeaver improves performance over a sliding-window baseline in pass@1, while reducing reasoning steps and token usage. Our observations suggest that modeling logical dependencies provides a stable and scalable memory mechanism for LLM agents that use tools. --- ### Training a General Purpose Automated Red Teaming Model Authors: Aishwarya Padmakumar, Leon Derczynski, Traian Rebedea, Christopher Parisien Published: 2026-04-24 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2604.23067v1 Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods are intended for tackling safety and content moderation. Thus, they make use of content safety models as evaluators and optimize for circumventing them, and as such, have not been tested with other adversarial intents not typically captured by these. We propose a pipeline for training a red teaming model that can generalize to arbitrary adversarial goals, including objectives it has not been directly trained on, and that does not depend on the existence of a pre-existing evaluator available at training time. We demonstrate that finetuning small models, such as Qwen3-8B, using this pipeline results in a substantial improvement in their ability to generate attacks for both in and out of domain adversarial goals. --- ### Urban Flood Observations: A hand-labeled training and validation dataset of post-flood inundation Authors: Rohit Mukherjee, Hannah K. Friedrich, Beth Tellman, Ariful Islam, Zhijie Zhang, Jonathan Giezendanner, Upmanu Lall, Venkataraman Lakshmi Published: 2026-04-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.23066v2 Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging due to limited spatial resolution, infrequent acquisitions, and cloud cover. We present Urban Flood Observations (UFO), a global, hand-labeled dataset of post-flood inundation in diverse urban settings. UFO comprises 215 image chips (1024 by 1024 pixels) from 14 flood events between 2017 and 2021, derived from 3 m PlanetScope imagery. Each chip is annotated with two classes: 'inundated' (all visible surface water, including floodwater and pre-existing water bodies (permanent or seasonal)) and 'non-inundated'. To demonstrate the dataset's utility, we trained a segmentation model using leave-one-event-out cross-validation, achieving a mean Intersection over Union (IoU) of 77.3. We also used UFO to evaluate two widely used surface water products, the Sentinel-1-based NASA IMPACT model and Google's 10 m Dynamic World water class, which yielded IoUs of 44.1 and 48.1, respectively. UFO is publicly available to support the development and validation of urban inundation mapping methods. --- ### C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs Authors: Rui Gao, Youngseung Jeon, Swastik Roy, Morteza Ziyadi, Xiang 'Anthony' Chen Published: 2026-04-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.23061v2 Large language models (LLMs) show promise for molecular optimization, but aligning them with selective and competing drug-design constraints remains challenging. We propose C-Moral, a reinforcement learning post-training framework for controllable multi-objective molecular optimization. C-Moral combines group-based relative optimization, property score alignment for heterogeneous objectives, and bottleneck-sensitive non-linear reward aggregation to improve stability across competing molecular properties. Experiments on C-MuMOInstruct and S$^2$-Bench MolOpt show that C-Moral achieves the best performance among compared methods on both benchmarks. On C-MuMOInstruct, C-Moral achieves the best Success Optimized Rate (SOR) of 48.9\% on in-domain tasks and 39.5\% on out-of-domain tasks while preserving scaffold similarity. On S$^2$-Bench MolOpt, it also achieves the strongest results across LogP, MR, and QED optimization tasks. These results suggest that C-Moral is an effective way to align molecular LLMs with continuous and constrained molecular design objectives. Our code and models are publicly available at https://github.com/Rwigie/C-MORAL. --- ### Implicit Framing in Obstetric Counseling Notes: A Grounded LLM Pipeline on a VBAC-Eligible Cohort Authors: Baris Karacan, Barbara Di Eugenio, Patrick Thornton, Joanna Tess, Subhash Kumar Kolar Published: 2026-04-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23059v1 Clinical framing -- the linguistic manner in which clinical information is presented -- can influence patient understanding and decision-making, with important implications for healthcare outcomes. Obstetrics is a high-stakes domain in which physicians counsel patients on delivery mode choices such as vaginal birth after cesarean (VBAC) and repeat cesarean section (RCS), yet counseling language remains underexplored in large-scale clinical text analysis. In this work, we analyze physician counseling language in 2,024 obstetric history and physical narratives for a rigorously defined cohort of patients for whom both VBAC and RCS were clinically viable options. To control for confounding due to medical contraindications, we first construct a VBAC-eligible cohort using structured clinical data supplemented by a large language model (LLM)-based extraction pipeline constrained to grounded, verbatim evidence from free-text narratives. We then apply a zero-shot LLM framework to categorize counseling segments into predefined framing categories capturing how physicians linguistically present delivery options. Our analysis reveals a significant difference in counseling framing distributions between VBAC and RCS notes; risk-focused language accounts for a substantially larger share of counseling segments in RCS documentation than in VBAC, with category-level differences confirmed by statistical testing, highlighting the value of controlled LLM-based framing analysis in obstetric care. --- ### The Security Cost of Intelligence: AI Capability, Cyber Risk, and Deployment Paradox Authors: Sukwoong Choi Published: 2026-04-24 Categories: econ.GN, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.23058v1 Firms are deploying more capable AI systems, but organizational controls often have not kept pace. These systems can generate greater productivity gains, but high-value uses require broader authority exposure -- data access, workflow integration, and delegated authority -- when governance controls have not yet decoupled capability from authority exposure. We develop an analytical model in which a firm jointly chooses AI deployment and cybersecurity investment under this governance-capability gap. The central result shows a deployment paradox: in high-loss environments, better AI can lead a firm to deploy less when capability is deployed through broader authority exposure under weak governance. Optimal deployment also falls below the no-risk benchmark, and this shortfall widens with breach-loss magnitude and with the authority exposure attached to more capable systems. Governance investment that reduces breach-loss magnitude shrinks the paradox region itself, while breach externalities expand the range of environments in which deployment is socially constrained. Governance maturity is therefore not merely a constraint on AI adoption. It is a condition that shapes whether capability improvements translate into productive deployment. --- ### Don't Make the LLM Read the Graph: Make the Graph Think Authors: Yuqi Sun, Tianqin Meng, George Liu, Yashraj Panwar, Lakshya Chaudhry, Munasib Ilham, Aman Chadha Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23057v2 We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four LLM families in the cooperative card game Hanabi, we establish four findings. First, integration architecture determines whether belief graphs provide value: as prompt context, graphs are decorative for strong models and beneficial only for weak models on 2nd-order Theory of Mind (80% vs 10%, p<0.0001, OR=36.0); when graphs gate action selection through ranked shortlists, they become structurally essential even for strong models (100% vs 20% on 2nd-order ToM, p<0.001). Second, we identify "Planner Defiance," a model-family-specific failure where LLMs override correct planner recommendations at partial competence (90% override, replicated N=20); Gemini models show near-zero defiance while Llama 70B shows 90%, and models distinguish factual context (deferred to) from advisory recommendations (overridden). Third, full-game evidence confirms inter-agent conventions (+128% over baseline, p=0.003) outperform all single-agent interventions, and individual belief-graph components must be combined to produce gains. Fourth, preliminary scaling analysis (N=10/cell, exploratory) suggests graph depth has diminishing returns: shallow graphs provide the best cost-benefit ratio, while deeper ToM graphs appear harmful at larger player counts (-1.5 pts at 5-player, p=0.029). --- ### K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning Authors: Zixuan Xia, Quanxi Li Published: 2026-04-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.23056v1 We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for online reward estimation. Instead of relying on fixed heuristics, our method recursively estimates the latent reward mean, smoothing high-variance returns and adapting to non-stationary environments. This approach incurs minimal overhead and requires no modification to existing policy architectures. Experiments on \textit{LunarLander} and \textit{CartPole} demonstrate that Kalman-filtered rewards significantly accelerate convergence and reduce training variance compared to standard normalization techniques. Code is available at https://github.com/Sumxiaa/Kalman_Normalization. --- ### DeepImagine: Clinical Trial Outcome Prediction via Stepwise Local Counterfactual Imaginations Authors: Youze Zheng, Jianyou Wang, Yuhan Chen, Matthew Feng, Longtian Bao, Hanyuan Zhang, Maxim Khan, Aditya K. Sehgal, Christopher D. Rosin, Umber Dube, Ramamohan Paturi Published: 2026-04-24 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.23054v2 Predicting the outcomes of prospective clinical trials remains a major challenge. Clinical trial outcomes result from complex interactions among experimental factors such as drug interventions, participant demographics, and protocols. Here, we introduce DeepImagine, a framework that predicts target trial outcomes through stepwise counterfactual imagination anchored on historical trials with observed results. Starting from a relevant historical trial, DeepImagine sequentially modifies one differing experimental factor at a time. With each step a large language model (LLM) is posed a local counterfactual: how would the current imagined outcome change with this single perturbation? The updated result is carried forward as the input to the next step, until the historical configuration exactly matches the target, yielding the final prediction. Empirically, DeepImagine consistently outperforms direct one-step prediction across several off-the-shelf LLMs, with further gains when multiple imagination pathways, initiated from different historical anchors, are aggregated. We also construct natural counterfactuals augmented with synthetic reasoning traces and train a family of specialized language models, each dedicated to learning one factor's local counterfactual transition. Integrating these learned local operators into DeepImagine yields substantial improvements over general-purpose LLM baselines. Our findings position stepwise counterfactual imagination, distinct from both correlational prediction and explicit structural causal modeling, as a promising direction for clinical trial outcome prediction. All code, training scripts, and evaluation scripts are available at \href{https://github.com/deepimagine-counterfactual/DeepImagine}{https://github.com/deepimagine-counterfactual/DeepImagine}. --- ### ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs Authors: Weimin Huang, Natalie M. Isenberg, Ján Drgoňa, Draguna L Vrabie, Bistra Dilkina Published: 2026-04-24 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2604.23053v3 Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial optimization problems is challenging, primal heuristics have been developed to quickly identify high-quality solutions within a short amount of time. Recently, a growing body of research has also used machine learning to accelerate solution methods for challenging combinatorial optimization problems. Despite the increasing popularity of these ML-guided methods, a large body of work has focused on Mixed-Integer Linear Programs (MILPs). MBQPs are challenging to solve due to the combinatorial complexity coupled with nonlinearities. This work proposes ML-guided primal heuristics for Mixed Binary Quadratic Programs (MBQPs) by adapting and extending existing work on ML-guided MILP solution prediction to MBQPs. We introduce a new neural network architecture for MBQP solution prediction and a new training data collection procedure. Moreover, we extend existing loss functions in solution prediction and propose to combine contrastive and weighted cross-entropy losses. We evaluate the methods on standard and real-world MBQP benchmarks and show that the developed ML-guided methods significantly outperform existing primal heuristics and state-of-the-art solvers. Furthermore, models trained with our proposed extension with combined losses outperform other ML-based methods adapted from MILPs and improve generalization in cross-regional inference on a real-world wind farm layout optimization problem. --- ### Evaluating Temporal Consistency in Multi-Turn Language Models Authors: Yash Kumar Atri, Steven L. Johnson, Tom Hartvigsen Published: 2026-04-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23051v1 Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios, correct behavior requires models to maintain and update implicit temporal assumptions established earlier in a conversation. We study this challenge through the lens of temporal scope stability: the ability to preserve, override, or transfer time-scoped factual context across dialogue turns. We introduce ChronoScope, a large-scale diagnostic benchmark designed to isolate temporal scope behavior in controlled multi-turn interactions, comprising over one million deterministically generated question chains grounded in Wikidata. ChronoScope evaluates whether models can correctly retain inferred temporal scope when follow-up questions omit explicit time references, spanning implicit carryover, explicit scope switching, cross-entity transfer, and longer temporal trajectories. Through extensive evaluation of state-of-the-art language models, we find that temporal scope stability is frequently violated in controlled multi-turn settings, with models often drifting toward present-day assumptions despite correct underlying knowledge. These failures intensify with interaction length and persist even under oracle context conditions, revealing a gap between single-turn factual accuracy and coherent temporal reasoning under sequential interaction. We make our dataset and evaluation suite publicly available at https://github.com/yashkumaratri/ChronoScope --- ### A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows Authors: Edward Cheng, Jeshua Cheng Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23049v1 AI agents are increasingly deployed to execute tasks and make decisions within agentic workflows, introducing new requirements for safe and controlled autonomy. Prior work has established the importance of human oversight for ensuring transparency, accountability, and trustworthiness in such systems. However, existing implementations of Human-in-the-Loop (HITL) mechanisms are typically embedded within application logic, limiting reuse, consistency, and scalability across multi-agent environments. This paper presents a decoupled HITL system architecture that treats human oversight as an independent system component within the agent operating environment. The proposed design separates human interaction management from application workflows through explicit interfaces and a structured execution model. In addition, a design framework is introduced to formalize HITL integration along four dimensions: intervention conditions, role resolution, interaction semantics, and communication channel. This framework enables selective and context-aware human involvement while maintaining system-level consistency. The approach supports alignment with emerging agent communication protocols, allowing HITL to be implemented as a protocol-level concern. By externalizing HITL and structuring its integration, the system provides a foundation for scalable governance and progressive autonomy in agentic workflows. --- ### Shape of Memory: a Geometric Analysis of Machine Unlearning in Second-Order Optimizers Authors: Kennon Stewart Published: 2026-04-24 Categories: cs.LG, cs.IT, cs.SI, stat.ML arXiv: https://arxiv.org/abs/2604.23046v1 We argue that current definitions of machine unlearning are underspecified for second-order optimizers. We compare first-order and second-order learners for their ability to handle the data deletion task with varying degrees of eigendecomposition to mimic the loss model memory. While both first and second-order methods realign with the ideal counterfactul in terms of performance and gradient, the second-order optimizer shows significant volatility in the optimizer state. This indicates residual information, supposedly deleted, that isn't detectable by first-order analysis. Various eigendecay treatments show that stability and information loss is regained only under controlled state pertubation where geometric information (or memory) is erased. --- ### A Differentiable Framework for Global Circulation Model Precipitation Bias Correction Authors: Kamlesh Sawadekar, Seth McGinnis, Peijun Li, Kathryn Lawson, Chaopeng Shen Published: 2026-04-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.23045v3 Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts. --- ### Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning Authors: Haoze He, Xingyuan Ding, Xuan Jiang, Xinkai Zou, Alex Cheng, Yibo Zhao, Juncheng Billy Li, Heather Miller Published: 2026-04-24 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.23036v2 Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fragile. Methods such as DenseMixer and ESFT mitigate router collapse with dense mixing or auxiliary load-balancing losses, but these introduce noisy gradients that often degrade performance. In preliminary experiments, we systematically pruned experts and observed that while certain super experts are activated far more frequently, discarding less used experts still leads to notable performance degradation. This suggests that even rarely activated experts encode non-trivial knowledge useful for downstream tasks. Motivated by this, we propose an auxiliary-loss-free MoE SFT framework that combines bias-driven sparsification with always-active gated condenser experts. Rather than enforcing balanced activation across all experts, our method encourages task-relevant experts to remain active while pushing long-tailed experts toward inactivity. The condenser experts provide a persistent, learnable pathway that alleviates gradient starvation and facilitates consolidation of information that would otherwise remain fragmented across sparsely activated experts. Analysis further suggest that this design better preserves long-tailed expert information under sparse routing. Experiments on large-scale MoE models demonstrate that our approach outperforms state-of-the-art SFT baselines such as DenseMixer and ESFT, achieving average gain of 2.5%+ on both mathematical reasoning and commonsenseQA benchmarks. --- ### Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning Authors: Haoze He, Xingyuan Ding, Xuan Jiang, Xinkai Zou, Alex Cheng, Yibo Zhao, Juncheng Billy Li, Heather Miller Published: 2026-04-24 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.23036v1 Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fragile. Methods such as DenseMixer and ESFT mitigate router collapse with dense mixing or auxiliary load-balancing losses, but these introduce noisy gradients that often degrade performance. In preliminary experiments, we systematically pruned experts and observed that while certain super experts are activated far more frequently, discarding less used experts still leads to notable performance degradation. This suggests that even rarely activated experts encode non-trivial knowledge useful for downstream tasks. Motivated by this, we propose an auxiliary-loss-free MoE SFT framework that combines bias-driven sparsification with always-active gated condenser experts. Rather than enforcing balanced activation across all experts, our method encourages task-relevant experts to remain active while pushing long-tailed experts toward inactivity. The condenser experts provide a persistent, learnable pathway that alleviates gradient starvation and facilitates consolidation of information that would otherwise remain fragmented across sparsely activated experts. Analysis further suggest that this design better preserves long-tailed expert information under sparse routing. Experiments on large-scale MoE models demonstrate that our approach outperforms state-of-the-art SFT baselines such as DenseMixer and ESFT, achieving average gain of 2.5%+ on both mathematical reasoning and commonsenseQA benchmarks. --- ### A Systematic Approach for Large Language Models Debugging Authors: Basel Shbita, Anna Lisa Gentile, Bing Zhang, Sungeun An, Shailja Thakur, Shubhi Asthana, Yi Zhou, Saptha Surendran, Farhan Ahmed, Rohan Kulkarni, Yuya Jeremy Ong, Chad DeLuca et al. Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.23027v1 Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debugging that treats models as observable systems, providing structured, model-agnostic methods from issue detection to model refinement. By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses, refine prompts and model parameters, and adapt data for fine-tuning or assessment, while remaining effective in contexts where standardized benchmarks and evaluation criteria are lacking. We argue that such a structured methodology not only accelerates troubleshooting but also fosters reproducibility, transparency, and scalability in the deployment of LLM-based systems. --- ### Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset Authors: Annan Fu, Hao Pei, Maryam Tanha Published: 2026-04-24 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.23025v2 Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening real-world robustness. We address this by constructing a time-stamped dataset of benign and malicious Android apps and introducing a timestamp-verification procedure to ensure temporal accuracy. We then propose a detection framework that uses Bootstrap Your Own Latent (BYOL) for self-supervised pre-training to learn obfuscation-resilient representations, followed by supervised classification. Under time-aware evaluation, the method attains 98% accuracy and 89% F1. We further characterize malware behavior by analyzing true positives and false negatives using VirusTotal and the MITRE ATT&CK framework. To support reproducibility and further innovation, we release our dataset and source code. --- ### CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems Authors: Nilson Chapagain Published: 2026-04-24 Categories: cs.IR, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.23022v1 Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data support used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly supported generator-item pairs. We propose CASP (Coupled Action-Set Pessimism), a support-aware offline selector for finite libraries of two-stage recommender policies. CASP combines doubly robust value estimation with a support-burden penalty. We show that stagewise rules that ignore downstream continuation value can be arbitrarily suboptimal, and we derive population, finite-class, and reconstructed-propensity guarantees for conservative selection. In simulations and a reconstructed MovieLens 1M application, CASP selects lower-burden policies when estimated value and support credibility are in tension. --- ### Understanding Representation Gaps Across Scales in Tropical Tree Species Classification from Drone Imagery Authors: Sulagna Saha, Arthur Ouaknine, Etienne Laliberté, Carol Altimas, Evan M. Gora, Adriane Esquivel Muelbert, Ian R. McGregor, Cesar Gutierrez, Vanessa E. Rubio, David Rolnick Published: 2026-04-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.23019v1 Accurate classification of tropical tree species from unoccupied aerial vehicle (UAV) imagery remains challenging due to high species diversity and strong visual similarity among species at typical image resolutions (centimeters per pixel). In contrast, models trained on close-up citizen science photographs captured with smartphones achieve strong plant species classification performance. Recent advances in UAV data acquisition now enable the collection of close-up images that are spatially registered with top-view aerial imagery and approach the level of visual detail found in smartphone photographs, with the trade-off that such high-resolution photos cannot be acquired for many trees. In this work, we evaluate the performance of existing methods using paired top-view and close-up UAV imagery collected in a species-rich tropical forest. Through fine-tuning experiments, we quantify the performance gap between vision foundation models and in-domain generalist plant recognition models across both image types (high-resolution close-up versus coarser-resolution top-view imagery). We show that classification performance is consistently higher on close-up images than on top-view aerial imagery, and that this performance gap widens for rare species. Finally, we propose that self-supervised representation alignment across these two spatial scales offers a promising approach for integrating fine-grained visual information into canopy-level species classification models based on top-view UAV imagery. Leveraging high-resolution close-up UAV imagery to enhance canopy-level species classification could substantially improve large-scale monitoring of tropical forest biodiversity. --- ### AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI Authors: Mohammad Sadegh Salehi, Alex Perkins, Igor Maurell, Ashkan Dabbagh, Raymond Wong Published: 2026-04-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.23018v2 Web-scale 3D asset collections are abundant but rarely deployment-ready, suffering from arbitrary metric scaling, incorrect pivots, brittle geometry, and incomplete textures, defects that limit their use in embodied AI, robotics, and spatial computing. We present AmaraSpatial-10K, a dataset of over 10,000 synthetic 3D assets optimised for zero-shot deployment. Each asset ships as a metric-scaled, deterministically anchored .glb with separated PBR maps, a convex collision hull, a paired reference image, and multi-sentence text metadata. Alongside the dataset we introduce a reusable evaluation suite for 3D asset banks, a continuous Scale Plausibility Score (SPS), an LLM Concept Density metric, anchor-error auditing, and a cross-modal CLIP coherence protocol, and apply it to AmaraSpatial-10K alongside matched subsets of Objaverse, HSSD, ABO, and GSO. AmaraSpatial-10K improves CLIP Recall@5 by $3.4\times$ over Objaverse ($0.612$ vs. $0.181$, median rank $267 \rightarrow 3$), achieves a $99.1\%$ physics-stability rate under Habitat-Sim with $\sim 20\times$ wall-time speed-up, and produces zero-overlap scenes when used as a drop-in asset bank for Holodeck. Controlled ablations on the same asset bank attribute the retrieval gain to description richness. --- ### Complex Stochastic Gradient Descent and Directional Bias in Reproducing Kernel Hilbert Spaces Authors: Natanael Alpay, Emeric Battaglia Published: 2026-04-24 Categories: cs.LG, math.CV, math.NA arXiv: https://arxiv.org/abs/2604.23017v2 Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some objectives, such as those found in complex-valued neural networks, benefit from updates like in SGD and Gradient Descent (GD) with a newly defined ``gradient'' that allows for complex parameters. This complex variant of the SGD/GD methods has already been proposed, but convergence guarantees without analyticity constraints have not yet been provided. We propose a variant of SGD (complex SGD) that allows for complex parameters, and we provide convergence guarantees under assumptions that parallel those from the real setting. Notably, these results extend to GD as well, and with the same set of assumptions, we confirm that some directional bias results extend from the real to the complex setting for kernel regression problems. We provide empirical results demonstrating the efficacy of the complex SGD in kernel regression problems utilizing complex reproducing kernel Hilbert spaces. In particular, we demonstrate we may recover superoscillation functions and Blaschke products from the Fock Space and Hardy Space, respectively, as the optimal functions for a particular choice of a loss function. --- ### DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication Authors: Mathias Graf, Marco Willi, Melanie Mathys, Michael Aerni, Christian Schwarzer, Martin Melchior, Michael H. Graber Published: 2026-04-24 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.23016v1 AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat, undermining public trust in image authenticity. We propose DeepSignature, a novel approach that integrates the guarantees of digital signatures with the capabilities of deep neural networks. Neural networks are used both to generate content-encoding watermarks and to embed them imperceptibly into images while ensuring robust extraction. These watermarks are cryptographically verifiable, enabling source attribution and image integrity validation. DeepSignature is compatible with existing image formats and requires no special handling of signed images. It supports client-side verification, requiring only the signer's public key. Additionally, we introduce a novel latent-space verification approach to detect and localize tampering attempts. We evaluate DeepSignature in terms of imperceptibility, robustness to benign transformations, forgery detection, and its resilience against various attack scenarios. Our results highlight the inherent trade-offs between imperceptibility, robustness, and integrity verification. We demonstrate that DeepSignature reliably identifies significant forgery attempts -- achieving near 100\% in our experiments. Finally, we emphasize DeepSignature's modularity and tunable parameters, allowing adaptation to application-specific requirements. Code and model weights will be published. --- ### On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller Authors: Jeremy Ellis Published: 2026-04-24 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.23012v1 This paper presents a complete, end-to-end on-device vision machine learning pipeline, comprising data acquisition, two-layer CNN training with Adam optimization, and real-time inference, executing entirely on a microcontroller-class device costing $15-40 USD. Unlike cloud-based workflows that require external infrastructure and conceal the computational pipeline from the practitioner, this system implements every step of the core ML lifecycle in approximately 1,750 lines of readable C++ that compiles in under one minute using the Arduino IDE, with no external ML dependencies. Running on the Seeed Studio ESP32-S3 XIAO ML Kit (8 MB PSRAM), the firmware achieves three-class 64x64 image classification in approximately 9 minutes per training run, with real-time inference at 6.3 FPS. Key contributions include: correct batch-level gradient accumulation; pre-computed resize lookup tables for inference; dual-format weight export for SD-free baked-in deployment; a three-tier weight priority system (SD binary > baked-in header > He-initialization) resolved automatically at boot; a single-constant network reconfiguration interface; and PSRAM-aware memory management suited to microcontroller constraints. All source code and reference datasets are released under the MIT License at https://github.com/webmcu-ai/on-device-vision-ai --- ### GenAssets: Generating in-the-wild 3D Assets in Latent Space Authors: Ze Yang, Jingkang Wang, Haowei Zhang, Sivabalan Manivasagam, Yun Chen, Raquel Urtasun Published: 2026-04-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.23010v1 High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from in-the-wild data is key for diversity and realism, but existing neural-rendering based reconstruction methods are slow and generate assets that render well only from viewpoints close to the original observations, limiting their usefulness in simulation. Recent diffusion-based generative models build complete and diverse assets, but perform poorly on in-the-wild driving scenes, where observed actors are captured under sparse and limited fields of view, and are partially occluded. In this work, we propose a 3D latent diffusion model that learns on in-the-wild LiDAR and camera data captured by a sensor platform and generates high-quality 3D assets with complete geometry and appearance. Key to our method is a "reconstruct-then-generate" approach that first leverages occlusion-aware neural rendering trained over multiple scenes to build a high-quality latent space for objects, and then trains a diffusion model that operates on the latent space. We show our method outperforms existing reconstruction and generation based methods, unlocking diverse and scalable content creation for simulation. --- ### Chinese-SkillSpan: A Span-Level Dataset for ESCO-Aligned Competency Extraction from Chinese Job Ads Authors: Guojing Li, Zichuan Fu, Junyi Li, Wenxia Zhou, Xinyang Wu, Jinning Yang, Jingtong Gao, Feng Huang, Xiangyu Zhao Published: 2026-04-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.23009v1 Job Skill Named Entity Recognition (JobSkillNER) aims to automatically extract key skill information from large-scale job posting data, which is important for improving talent-market matching efficiency and supporting personalized employment services. To the best of our knowledge, this work presents the first Chinese JobSkillNER dataset for recruitment texts. We propose annotation guidelines tailored to Chinese job postings and an LLM-empowered Macro-Micro collaborative annotation pipeline. The pipeline leverages the contextual understanding ability of large language models (LLMs) for initial annotation and then refines the results through expert sentence-level adjudication. Using this pipeline, we annotate more than 20,000 instances collected from four major recruitment platforms over the period 2014-2025. Based on these efforts, we release Chinese-SkillSpan, the first Chinese JobSkillNER dataset aligned with the ESCO occupational skill standard across four dimensions: knowledge, skill, transversal competence, and language competence (LSKT). Experimental results show that the dataset supports effective model training and evaluation, indicating that Chinese-SkillSpan helps fill a major gap in Chinese JobSkillNER resources and provides a useful benchmark for intelligent recruitment research. Code and data are available at https://sites.google.com/view/cn-skillspan-resources . --- ### Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen Authors: Maciej Sikora, Leszek Siwik, Natalia Leszczyńska, Tomasz Maciej Ciesielski, Eirik Valseth, Manuela Bastidas Olivares, Marcin Łoś, Tomasz Służalec, Jacek Leszczyński, Maciej Paszyński Published: 2026-04-24 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2604.23003v2 In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving emission sources. We formulate a robust variational framework for the time-dependent advection-diffusion problem and establish the boundedness and inf-sup stability of the corresponding discrete weak formulation. Based on this mathematical foundation, we construct a robust loss function that is directly related to the true approximation error, defined as the difference between the neural network approximation and the (unknown) exact solution. Additionally, a collocation-based strategy is introduced to speed up neural network training. We also extend our model to the non-linear Burgers-type equations. As a case study, we investigate pollution propagation caused by snowmobile traffic in Longyearbyen, Spitsbergen, supported by detailed in-field measurements collected using dedicated sensors. The proposed framework is applied to analyze the effects of thermal inversion on pollutant accumulation. Our results demonstrate that thermal inversion traps dense and humid air masses near the ground, significantly enhancing particulate matter (PM) concentration and worsening local air quality. We compare our method to linear computational cost explicit dynamics solver using isogeometric analysis. We show that our method can solve non-linear non-stationary problem four times slower than IGA solver can solve the linear problem. It makes it particularly interesting to investigate the non-linear extensions with similar computational cost as the linear formulation. --- ### Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen Authors: Leszek Siwik, Maciej Sikora, Natalia Leszczyńska, Tomasz Maciej Ciesielski, Eirik Valseth, Manuela Bastidas Olivares, Marcin Łoś, Tomasz Służalec, Jacek Leszczyński, Maciej Paszyński Published: 2026-04-24 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2604.23003v1 In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving emission sources. We formulate a robust variational framework for the time-dependent advection-diffusion problem and establish the boundedness and inf-sup stability of the corresponding discrete weak formulation. Based on this mathematical foundation, we construct a robust loss function that is directly related to the true approximation error, defined as the difference between the neural network approximation and the (unknown) exact solution. Additionally, a collocation-based strategy is introduced to speed up neural network training. As a case study, we investigate pollution propagation caused by snowmobile traffic in Longyearbyen, Spitsbergen, supported by detailed in-field measurements collected using dedicated sensors. The proposed framework is applied to analyze the effects of thermal inversion on pollutant accumulation. Our results demonstrate that thermal inversion traps dense and humid air masses near the ground, significantly enhancing particulate matter (PM) concentration and worsening local air quality. --- ### FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean Authors: Jordan Meadows, Lan Zhang, Andre Freitas Published: 2026-04-24 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.23002v1 Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit{e.g.} Dirac notation, vector calculus) imposes additional formalisation challenges that modern LLMs and agentic approaches have yet to tackle. To aid autoformalisation in scientific domains, we present FormalScience; a domain-agnostic human-in-the-loop agentic pipeline that enables a single domain expert (without deep formal language experience) to produce \textit{syntactically correct} and \textit{semantically aligned} formal proofs of informal reasoning for low economic cost. Applying FormalScience to physics, we construct FormalPhysics, a dataset of 200 university-level (LaTeX) physics problems and solutions (primarily quantum mechanics and electromagnetism), along with their Lean4 formal representations. Compared to existing formal math benchmarks, FormalPhysics achieves perfect formal validity and exhibits greater statement complexity. We evaluate open-source models and proprietary systems on a statement autoformalisation task on our dataset via zero-shot prompting, self-refinement with error feedback, and a novel multi-stage agentic approach, and explore autoformalisation limitations in modern LLM-based approaches. We provide the first systematic characterisation of semantic drift in physics autoformalisation in terms of concepts such as notational collapse and abstraction elevation which reveals what formal language verifies when full semantic preservation is unattainable. We release the codebase together with an interactive UI-based FormalScience system which facilitates autoformalisation and theorem proving in scientific domains beyond physics.https://github.com/jmeadows17/formal-science --- ### Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines Authors: Ziyao Wang, Bingying Wang, Hanrong Zhang, Tingting Du, Tianyang Chen, Guoheng Sun, Yexiao He, Zheyu Shen, Wanghao Ye, Ang Li Published: 2026-04-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.23001v1 Despite remarkable progress in Vision--Language--Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underlies embodied learning. In this survey, we argue that future advances in VLA will depend less on model architecture and more on the co-design of high-fidelity data engines and structured evaluation protocols. To this end, we present a systematic, data-centric analysis of VLA research organized around three pillars: datasets, benchmarks, and data engines. For datasets, we categorize real-world and synthetic corpora along embodiment diversity, modality composition, and action space formulation, revealing a persistent fidelity-cost trade-off that fundamentally constrains large-scale collection. For benchmarks, we analyze task complexity and environment structure jointly, exposing structural gaps in compositional generalization and long-horizon reasoning evaluation that existing protocols fail to address. For data engines, we examine simulation-based, video-reconstruction, and automated task-generation paradigms, identifying their shared limitations in physical grounding and sim-to-real transfer. Synthesizing these analyses, we distill four open challenges: representation alignment, multimodal supervision, reasoning assessment, and scalable data generation. Addressing them, we argue, requires treating data infrastructure as a first-class research problem rather than a background concern. --- ### Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation Authors: Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler, Dmytro Pavlichenko, Fynn Schilke, Rodja Krudewig, Sven Behnke Published: 2026-04-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.22992v1 Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fully supervised training of object detectors requires time-intensive annotations. We present a semi-supervised label propagation approach for household object segmentation. A segment proposer generates class-agnostic masks, and an ensemble of Hopfield networks assigns labels by learning representative embeddings in complementary foundation model embedding spaces (CLIP, ViT, Theia). Our approach scales to 50 object classes with limited annotation overhead and can automatically label 60% of the data in a RoboCup@Home setting, where preparation time is severely constrained. Dataset and code are publicly available at https://github.com/ais-bonn/label_propagation. --- ### Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena Authors: Renjith Prasad, Rishabh Sharma, Andrew E. Shao, Annmary Justine Koomthanam, Shreyas Kulkarni, Suparna Bhattacharya, Martin Foltin, Amit Sheth, David Orozco, Matthew Quinn, Brian Sammuli Published: 2026-04-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22990v2 Subtle visual anomalies such as hairline cracks, sub-millimeter voids, and low-contrast inclusions are structurally atypical yet visually ambiguous, making them both difficult to annotate and easy to overlook during active learning. Standard acquisition heuristics based on discriminative uncertainty or feature diversity often overselect dominant patterns while underexploring sparse yet important regions of the data space. This failure mode is especially severe in industrial defect inspection, where anomalies may be both low-prevalence and difficult to distinguish from surrounding structure. To resolve this, we propose GSAL, an active learning framework for object detection that combines a diffusion-based difficulty signal with a hierarchical semantic coverage prior. The diffusion component scores images and proposals using reconstruction discrepancy and denoising variability, prioritizing visually atypical or ambiguous examples. However, diffusion alone does not prevent acquisition from repeatedly favoring hard samples within dominant semantic modes. The semantic component therefore organizes candidate samples in a three-level concept graph and promotes coverage of underrepresented semantic regions while providing interpretable acquisition rationales. By balancing visual difficulty with semantic coverage, GSAL improves retrieval of subtle and rare targets that are often missed by uncertainty-only selection. Experiments on a proprietary thin-film defect, Pascal VOC and MS COCO dataset show consistent gains in label efficiency and rare-class retrieval over uncertainty-, diversity-, and hybrid-based baselines --- ### CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging Authors: Ashwin Kumar, Robbie Holland, Corey Barrett, Jangwon Kim, Maya Varma, Zhihong Chen, Yunhe Gao, Greg Zaharchuk, Tara Taghavi, Krishnaram Kenthapadi, Akshay Chaudhari Published: 2026-04-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22989v1 Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-style finetuning. This two-stage, decoupled approach introduces a projection layer that can distort visual features. This is especially concerning in medical imaging where subtle cues are essential for accurate diagnoses. In contrast, early-fusion generative approaches such as Chameleon eliminate the projection bottleneck by processing image and text tokens within a single unified sequence, enabling joint representation learning that leverages the inductive priors of language models. We present CheXmix, a unified early-fusion generative model trained on a large corpus of chest X-rays paired with radiology reports. We expand on Chameleon's autoregressive framework by introducing a two-stage multimodal generative pretraining strategy that combines the representational strengths of masked autoencoders with MLLMs. The resulting models are highly flexible, supporting both discriminative and generative tasks at both coarse and fine-grained scales. Our approach outperforms well-established generative models across all masking ratios by 6.0% and surpasses CheXagent by 8.6% on AUROC at high image masking ratios on the CheXpert classification task. We further inpaint images over 51.0% better than text-only generative models and outperform CheXagent by 45% on the GREEN metric for radiology report generation. These results demonstrate that CheXmix captures fine-grained information across a broad spectrum of chest X-ray tasks. Our code is at: https://github.com/StanfordMIMI/CheXmix. --- ### Uncertainty Quantification for LLM Function-Calling Authors: Zihuiwen Ye, Lukas Aichberger, Michael Kirchhof, Sinead Williamson, Luca Zappella, Yarin Gal, Arno Blaas, Adam Golinski Published: 2026-04-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.22985v1 Large Language Models (LLMs) are increasingly deployed to autonomously solve real-world tasks. A key ingredient for this is the LLM Function-Calling paradigm, a widely used approach for equipping LLMs with tool-use capabilities. However, an LLM calling functions incorrectly can have severe implications, especially when their effects are irreversible, e.g., transferring money or deleting data. Hence, it is of paramount importance to consider the LLM's confidence that a function call solves the task correctly prior to executing it. Uncertainty Quantification (UQ) methods can be used to quantify this confidence and prevent potentially incorrect function calls. In this work, we present what is, to our knowledge, the first evaluation of UQ methods for LLM Function-Calling (FC). While multi-sample UQ methods, such as Semantic Entropy, show strong performance for natural language Q&A tasks, we find that in the FC setting, it offers no clear advantage over simple single-sample UQ methods. Additionally, we find that the particularities of FC outputs can be leveraged to improve the performance of existing UQ methods in this setting. Specifically, multi-sample UQ methods benefit from clustering FC outputs based on their abstract syntax tree parsing, while single-sample UQ methods can be improved by selecting only semantically meaningful tokens when calculating logit-based uncertainty scores. --- ### BrickNet: Graph-Backed Generative Brick Assembly Authors: Peter Kulits, Cordelia Schmid Published: 2026-04-24 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.22984v1 We train a language model to generate LEGO-brick build sequences. While prior work has been restricted to discrete, voxel-like towers, we consider a much broader set of pieces, encompassing thousands of part types with diverse connection semantics. To enable this, we first collect a large-scale dataset of over 100,000 human-designed LDraw brick objects and scenes. The complexity of our setting makes it challenging to autoregressively assemble structures that satisfy physical constraints. When predicting block pose directly, build sequences quickly become invalid after a small number of steps. Although pieces are placed in 3D space, it is the spatial relationships of the parts which define the whole. With this in mind, we design a graph-based program representation that parametrizes structure through connectivity, improving the physical grounding of generated sequences. To enable future applications, we make our dataset and models available for research purposes. https://kulits.github.io/BrickNet --- ### Reward Models Are Secretly Value Functions: Temporally Coherent Reward Modeling Authors: Alex Nikulkov Published: 2026-04-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.22981v1 Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed opportunity: a well-trained reward model's output at any token should represent the conditional expectation of the final reward given the response so far. We introduce Temporally Coherent Reward Modeling (TCRM), which induces this property via two regularization terms on top of the standard Bradley-Terry loss, with minimizers provably equal to conditional expectations. The regularizers correspond to Monte Carlo and TD value-learning objectives, establishing a direct connection to RL value functions. TCRM requires zero changes to architecture, data, or inference, yet unlocks three capabilities from one principle: interpretable token-level reward trajectories (middle-token pairwise accuracy improved from 50% to 88.9%, final-token accuracy preserved); state-of-the-art PRM performance on ProcessBench (44.9% average F1) among models trained only on outcome data; and unified reward/value modeling in PPO, reducing peak GPU memory by 27% and step time by 19% with matching LLM quality. --- ### Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction Authors: Luca Cotti, Luca Lavazza, Marco Cominelli, Liying Han, Gaofeng Dong, Francesco Gringoli, Mani B. Srivastava, Trevor Bihl, Erik P. Blasch, Daniel O. Brigham, Kara Combs, Lance M. Kaplan et al. Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.22979v1 We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, symbolic controllability, and direct operation on high-dimensional raw signals. Deep neural models achieve strong predictive performance on CSI-based HAR (CHAR), yet rely on continuous latent representations that are opaque and difficult to modify; purely symbolic approaches, in contrast, cannot process raw CSI streams. We propose a fully automatic and strictly decoupled pipeline in which CSI magnitude windows are compressed by a categorical variational autoencoder with Gumbel-Softmax latent variables under a capacity-controlled objective, yielding a compact discrete representation. The encoder is then frozen and used as a deterministic mapping to one-hot latent trajectories. Causal discovery is performed on these trajectories to estimate class-conditional temporal dependency graphs. Statistically supported lagged dependencies are translated into Linear Temporal Logic (LTL) rules, producing a fully symbolic and deterministic classifier based solely on rule evaluation and aggregation, without any learned discriminative head. Because rules are defined over discrete latent variables, antenna-specific rule sets can in principle be combined at the symbolic level, enabling structured multi-antenna fusion without retraining the encoder. Results from CHAR Latent Temporal Rule Extraction (CHARL-TRE) indicate competitive performance while preserving explicit temporal and causal structure, showing that deterministic symbolic classification grounded in unsupervised discrete latent representations constitutes a viable alternative to end-to-end black-box models for wireless HAR. --- ### Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline Authors: Juergen Dietrich Published: 2026-04-24 Categories: cs.CY, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.22971v1 The TRUST democratic discourse analysis pipeline exposes its large language model (LLM) components to peer model identity through multiple structural channels -- a design feature whose bias implications have not previously been empirically tested. We provide the first systematic measurement of identity-dependent scoring bias across all active identity exposure channels in TRUST, crossing four model families with two anonymization scopes across 30 political statements. The central finding is that single-channel anonymization produces near-zero bias effects, because individual channels act in opposite directions and cancel each other out -- a result that would lead an evaluator to conclude that identity bias is absent when it is not. Only full-pipeline anonymization reveals the true pattern: homogeneous ensembles amplify identity-driven sycophancy when model identity is fully visible, while the heterogeneous production configuration shows the reverse. Model choice matters independently: one tested model exhibits baseline sycophancy two to three times higher than the others and near-zero deliberative conflict on ideological topics, making it structurally unsuitable for pipelines where genuine inter-role disagreement is the intended quality mechanism. Three practical conclusions follow. First, heterogeneous model ensembles are structurally more robust than homogeneous ones, achieving higher consensus rates and lower identity amplification. Second, full-pipeline anonymization is required for valid bias measurement -- partial anonymization is insufficient and actively misleading. Third, these findings have direct implications for the validation of multi-agent LLM systems in quality-critical applications: a system validated under partial anonymization or with a homogeneous ensemble may pass validation while retaining structural identity bias invisible to single-channel measurement. --- ### Rethinking Trust Region Bayesian Optimization in High Dimensions Authors: Wei-Ting Tang, Joel A. Paulson Published: 2026-04-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.22967v1 Trust Region Bayesian Optimization (TuRBO) is an effective strategy for alleviating the curse of dimensionality in high-dimensional black-box optimization. However, inappropriate lengthscale design can cause the local Gaussian process (GP) model within the trust region to degenerate, leading to suboptimal performance in high dimensions. In this work, we show that TuRBO's local GP may remain either excessively complex or overly simple as the dimension $D$ and trust region side length $L$ vary. To address this issue, we propose a straightforward variant, AdaScale-TuRBO, which scales the GP lengthscale with both the problem dimension and trust region size, thereby preserving kernel geometry and maintaining consistent prior complexity. Empirically, we show that AdaScale-TuRBO can robustly outperform standard TuRBO and other popular high-dimensional BO methods on synthetic benchmarks and real-world trajectory planning tasks. --- ### Institutions for the Post-Scarcity of Judgment Authors: Lauri Lovén Published: 2026-04-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.22966v2 Each major technological revolution inverts a particular scarcity and rebuilds institutions around the shift. The near-consensus diagnosis of the AI revolution holds that AI collapses the cost of prediction while judgment remains scarce. This Opinion argues the inversion has now flipped: competent-looking judgment (selecting, ranking, attributing, certifying) is produced at scale and at marginal cost approaching zero, and four complements become scarce: verified signal, legitimacy, authentic provenance, and integration capacity (the community's tolerance for delegated cognition). Because judgment is the substance of institutions, the institutions built to manufacture legitimate judgment (courts, journals, licensing bodies, legislatures) now compete with the technology for the same functional role. The piece traces the pattern across scientific institutions, professional licensing, intellectual property, democratic legitimacy, and foundation-model concentration, and closes with a three-move agenda: reframe AI policy as institutional redesign, build provenance and verification as commons, and develop the formal apparatus for institutional composition under strategic agents. --- ### AnemiaVision: Non-Invasive Anemia Detection via Smartphone Imagery Using EfficientNet-B3 with TrivialAugmentWide, Mixup Augmentation, and Persistent Patient History Management Authors: Rahul Patel Published: 2026-04-24 Categories: cs.CV, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2604.22964v1 Anemia affects over one billion people globally and remains severely under-diagnosed in low-resource regions where laboratory blood tests are inaccessible. This paper presents AnemiaVision, an end-to-end web-based system for non-invasive anemia screening from smartphone photographs of the palpebral conjunctiva and fingernail beds. The proposed pipeline fine-tunes a pre-trained EfficientNet-B3 backbone with a redesigned three-layer classifier head incorporating BatchNorm, GELU activations, and high-rate Dropout (0.45/0.35). Training employs four orthogonal accuracy-boosting techniques: TrivialAugmentWide for policy-free image augmentation, RandomErasing for spatial regularisation, Mixup (alpha=0.2) for inter-class smoothing, and cosine-annealing scheduling with linear warmup. Early stopping is governed by peak validation accuracy rather than validation loss to prevent premature termination on high-variance epochs. The deployed Flask application integrates persistent patient-history management backed by PostgreSQL on Render, with an automated database-migration entrypoint ensuring zero data loss across redeploys. Ablation experiments demonstrate that accuracy-first early stopping contributes +1.6% and Mixup contributes +2.8% to final validation accuracy. Overall, the proposed system achieves a validation accuracy of 96.2% and AUC-ROC of 0.98, compared with 44.9% validation accuracy and AUC-ROC of 0.58 from the three-epoch CPU-only baseline. Sensitivity for the anemic class reaches 0.96, making the system suitable as a first-line screening tool for community health workers in rural settings. The system is publicly accessible and source code is openly available. --- ### On the Existence of an Inverse Solution for Preference-Based Reductions in Argumentation Authors: Alessio Zaninotto, Bruno Yun, Nir Oren, Srdjan Vesic Published: 2026-04-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.22958v1 Preference-based argumentation frameworks (PAFs) extend Dung's approach to abstract argumentation (AAFs) by encoding preferences over arguments. Such preferences control the transformation of attacks into defeats, and different approaches to doing so result in different reductions from a PAF to an AAF. In this paper we consider a PAF inverse problem which takes an argumentation graph, a labelling and a semantics as an input, and outputs a ``yes" or ``no" as to whether there is a preference relation between the arguments which can yield the desired labelling. This inverse problem has applications in areas including preference elicitation and explainability. We consider this problem in the context of the four most widely-used preference based reductions under the complete semantics. We show that in most cases, the problem can be answered in polynomial time. --- ### The Power of Power Law: Asymmetry Enables Compositional Reasoning Authors: Zixuan Wang, Xingyu Dang, Jason D. Lee, Kaifeng Lyu Published: 2026-04-24 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.22951v2 Natural language data follows a power-law distribution, with most knowledge and skills appearing at very low frequency. While a common intuition suggests that reweighting or curating data towards a uniform distribution may help models better learn these long-tail skills, we find a counterintuitive result: across a wide range of compositional reasoning tasks, such as state tracking and multi-step arithmetic, training under power-law distributions consistently outperforms training under uniform distributions. To understand this advantage, we introduce a minimalist skill-composition task and show that learning under a power-law distribution provably requires significantly less training data. Our theoretical analysis reveals that power law sampling induces a beneficial asymmetry that improves the pathological loss landscape, which enables models to first acquire high-frequency skill compositions with low data complexity, which in turn serves as a stepping stone to efficiently learn rare long-tailed skills. Our results offer an alternative perspective on what constitutes an effective data distribution for training models. --- ### Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces Authors: Jie Hu, Lingyun Chen, Geeho Kim, Jinyoung Choi, Bohyung Han, Do Young Eun Published: 2026-04-24 Categories: cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2604.22948v2 History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history through empirical measure on finite state spaces, which is infeasible in high-dimensional discrete configuration spaces or ill-posed in continuous domains. We propose Score-Repellent Monte Carlo (SRMC) framework that summarizes trajectory history by a running average of score evaluations in $\mathbb{R}^d$, where $d$ is the dimension of the score and state representation. This history is converted into a surrogate target through an exponential score tilt, indexed with $α$ that represents the strength of repellence in controlling the magnitude of the history-based repulsion. The surrogate family is normalization-free in the standard MCMC sense, yielding a generic wrapper: at each iteration, any base kernel targeting $π$ can instead be run on the current surrogate $π_{θ_n}$ while the history is updated online. We analyze the coupled evolution of the history recursion and Monte Carlo estimators using stochastic approximation with controlled Markovian noise, establishing almost sure convergence and a joint central limit theorem. We further identify regimes in which the asymptotic covariance decreases as $α$ increases, with scaling $O(1/α)$, extending the near-zero-variance effect of finite-state history-dependent samplers to general state spaces with constant memory. Experiments on continuous targets and discrete energy-based models demonstrate improved estimator variance and mode coverage, while retaining $O(d)$ memory usage and modest per-iteration overhead. --- ### VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation Authors: Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi, Jens Kleesiek, Victor Alves, Jan Egger, André Ferreira Published: 2026-04-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.22942v2 Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM) a framework engineered to maintain generative quality while accelerating inference by several factors. We tested our approach on four tasks (missing MRI, tumor removal, MRI-to-sCT, and CBCT-to-sCT) within the BraTS2025 and SynthRAD2025 challenges. Designed for high efficiency under hardware and time constrains imposed by both challenges. VS-DDPM achieved state-of-the-art (SOTA) performance in missing MRI synthesis, yielding Dice scores of 0.80, 0.83, and 0.88 for the enhancing tumor, tumor core, and whole tumor regions, respectively, alongside a structural similarity index (SSIM) of 0.95. For MRI tumor removal, the model attained a root mean squared error (RMSE) of 0.053, a peak signal-to-noise ratio (PSNR) of 26.77, and an SSIM of 0.918. While the framework demonstrated competitive performance in MRI-to-sCT and CBCT-to-sCT tasks, it did not reach SOTA benchmarks, potentially due to sensitivities in data pre and post-processing pipelines or specific loss function configurations. These results demonstrate that VS-DDPM provides a robust and tunable solution for high-fidelity 3D medical image synthesis. The code is available in https://github.com/andre-fs-ferreira/SynthRAD_by_Faking_it. --- ### Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge Authors: Mengyu Wang, Xiaoying Zhi, Zhiyi Li, Robin Schmucker, Shay B. Cohen, Tiejun Ma, Fran Silavong Published: 2026-04-24 Categories: cs.CL, cs.AI, cs.CV, cs.IR arXiv: https://arxiv.org/abs/2604.22939v1 While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constrains performance on specialized, non-generative tasks. We attribute this performance bottleneck to the LLMs' knowledge expression mechanism, rather than to deficiencies in knowledge acquisition. To address this, we propose Self-Knowledge Re-expression (SKR), a novel, task-agnostic adaptation method. SKR transforms the LLM's output from generic token generation to highly efficient, task-specific expression. SKR is a fully local method that uses only unannotated data, requiring neither human supervision nor model distillation. Experiments on a large financial document dataset demonstrate substantial improvements: over 40% in Recall@1 for information retrieval tasks, over 76% reduction in object detection latency, and over 33% increase in anomaly detection AUPRC. Our results on the MMDocRAG dataset surpass those of leading retrieval models by at least 12.6%. ---