# Research Papers — 2026-04 · bundle page 184 of 233 > Full-text markdown of papers #9151–9200 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/184 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/183.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/185.md) ### From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection Authors: Hongxu Zhou Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06066v1 Intrinsic self-correction in Large Language Models (LLMs) frequently fails in open-ended reasoning tasks due to ``hallucination snowballing,'' a phenomenon in which models recursively justify early errors during free-text reflection. While structured feedback can mitigate this issue, existing approaches often rely on externally trained critics or symbolic tools, reducing agent autonomy. This study investigates whether enforcing structured reflection purely through Outlines-based constrained decoding can disrupt error propagation without additional training. Evaluating an 8-billion-parameter model (Qwen3-8B), we show that simply imposing structural constraints does not improve self-correction performance. Instead, it triggers a new failure mode termed ``structure snowballing.'' We find that the cognitive load required to satisfy strict formatting rules pushes the model into formatting traps. This observation helps explain why the agent achieves near-perfect superficial syntactic alignment yet fails to detect or resolve deeper semantic errors. These findings expose an ``alignment tax'' inherent to constrained decoding, highlighting a tension between structural granularity and internal model capacity in autonomous workflows. Code and raw logs are available in the GitHub repository: https://github.com/hongxuzhou/agentic_llm_structured_self_critique. --- ### Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities Authors: Arthur Stéphanovitch Published: 2026-04-07 Categories: math.ST, math.PR, stat.ML arXiv: https://arxiv.org/abs/2604.06065v1 Under general assumptions on the target distribution $p^\star$, we establish a sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores, with optimal dependence on time and dimension. As applications, we obtain Wasserstein discretization bounds for Euler-type samplers in dimension $d$: with $N$ discretization steps, the error achieves the optimal rate $\sqrt{d}/N$ up to logarithmic factors. Moreover, the constants do not deteriorate exponentially with the spatial extent of $p^\star$. We also show that the one-sided Lipschitz control yields a globally Lipschitz transport map from the standard Gaussian to $p^\star$, which implies Poincaré and log-Sobolev inequalities for a broad class of probability measures. --- ### Value Mirror Descent for Reinforcement Learning Authors: Zhichao Jia, Guanghui Lan Published: 2026-04-07 Categories: math.OC, cs.LG, math.PR arXiv: https://arxiv.org/abs/2604.06039v2 Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy optimization approaches, particularly in their dependence on the discount factor. In practice, they are often employed for offline training. In this paper, we consider discounted Markov decision processes with state space S, action space A, discount factor $γ\in(0,1)$ and costs in $(0,1)$. We introduce a novel value optimization method, termed value mirror descent (VMD), which integrates mirror descent from convex optimization into the classical value iteration framework. In the deterministic setting with known transition kernels, we show that VMD converges linearly. For the stochastic setting with a generative model, we develop a stochastic variant, SVMD, which incorporates variance reduction commonly used in stochastic value iteration-type methods. For RL problems with general convex regularizers, SVMD attains a near-optimal sample complexity of $\tilde{O}(|S||A|(1-γ)^{-3}ε^{-2})$. Moreover, we establish that the Bregman divergence between the generated and optimal policies remains bounded throughout the iterations, even under the presence of model misspecification. This property is absent in existing stochastic value iteration-type methods but is important for enabling effective online (continual) learning following offline training. Under a strongly convex regularizer, SVMD achieves sample complexity of $\tilde{O}(|S||A|(1-γ)^{-5}ε^{-1})$, improving performance in the high-accuracy regime. Furthermore, we prove convergence of the generated policy to the optimal policy. Overall, the proposed method, its analysis, and the resulting guarantees, constitute new contributions to the RL and optimization literature. --- ### Value Mirror Descent for Reinforcement Learning Authors: Zhichao Jia, Guanghui Lan Published: 2026-04-07 Categories: math.OC, cs.LG, math.PR arXiv: https://arxiv.org/abs/2604.06039v1 Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy optimization approaches, particularly in their dependence on the discount factor. In practice, they are often employed for offline training or in simulated environments. In this paper, we consider discounted Markov decision processes with state space S, action space A, discount factor $γ\in(0,1)$ and costs in $(0,1)$. We introduce a novel value optimization method, termed value mirror descent (VMD), which integrates mirror descent from convex optimization into the classical value iteration framework. In the deterministic setting with known transition kernels, we show that VMD converges linearly. For the stochastic setting with a generative model, we develop a stochastic variant, SVMD, which incorporates variance reduction commonly used in stochastic value iteration-type methods. For RL problems with general convex regularizers, SVMD attains a near-optimal sample complexity of $\tilde{O}(|S||A|(1-γ)^{-3}ε^{-2})$. Moreover, we establish that the Bregman divergence between the generated and optimal policies remains bounded throughout the iterations. This property is absent in existing stochastic value iteration-type methods but is important for enabling effective online (continual) learning following offline training. Under a strongly convex regularizer, SVMD achieves sample complexity of $\tilde{O}(|S||A|(1-γ)^{-5}ε^{-1})$, improving performance in the high-accuracy regime. Furthermore, we prove convergence of the generated policy to the optimal policy. Overall, the proposed method, its analysis, and the resulting guarantees, constitute new contributions to the RL and optimization literature. --- ### CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference Authors: Yulin Zou, Wenyan Chen, Yan Chen, Anya Rajan, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, Dmitrii Ustiugov Published: 2026-04-07 Categories: cs.DC, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.06036v4 Continuous inference over concurrent video streams imposes substantial compute and memory demands on vision-language model (VLM) serving. Streaming inference uses sliding windows to maintain a bounded context of recent video, but processing each window independently repeats visual encoding and large language model (LLM) prefilling for similar and overlapping content. Existing optimizations provide limited coordination across these stages and often rely on model-specific training, profiling, or model-generated signals. We present CodecSight, a streaming VLM serving system that uses codec metadata as shared runtime guidance across visual encoding and LLM prefilling, without model-specific training or offline profiling. Codec-derived change signals guide patch pruning before visual encoding, reducing both visual computation and the number of downstream visual tokens. Codec-defined frame types guide selective key-value (KV) refresh across windows, while positional correction enables reuse of the remaining cached keys. Across three VLMs and four video workloads, our vLLM-based implementation supports up to $3.3\times$ as many concurrent streams and achieves up to a $5.3\times$ speedup in average time-to-first-token relative to the state-of-the-art baselines. It also reduces executed FLOPs by up to 93%, with a maximum task-quality decrease of 4.64 percentage points. --- ### CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference Authors: Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, Dmitrii Ustiugov Published: 2026-04-07 Categories: cs.DC, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.06036v3 Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video streams, but they target either the vision transformer (ViT) or the LLM with a limited view, leaving end-to-end opportunities untapped. Moreover, existing methods incur significant overhead to identify redundancy, either through offline profiling and training or costly online computation, making them ill-suited for dynamic real-time streams. We present CodecSight, a codec-guided streaming video analytics system, built on a key observation that video codecs already extract the temporal and spatial structure of each stream as a byproduct of compression. CodecSight treats this codec metadata as a low-cost runtime signal to unify optimization across video decoding, visual processing, and LLM prefilling, with transmission reduction as an inherent benefit of operating directly on compressed bitstreams. This drives codec-guided patch pruning before ViT encoding and selective key-value cache refresh during LLM prefilling, both of which are fully online and do not require offline training. Experiments show that CodecSight achieves an improvement in throughput of up to 3$\times$, and a reduction of up to 87% in GPU compute over state-of-the-art baselines, maintaining competitive accuracy with only 0$\sim$8% F1 drop. --- ### Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification Authors: Courtney Franzen, Farhad Pourkamali-Anaraki Published: 2026-04-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.06032v1 Neural network classifiers trained with cross-entropy loss achieve strong predictive accuracy but lack the capability to provide inherent predictive uncertainty estimates, thus requiring external techniques to obtain these estimates. In addition, softmax scores for the true class can vary substantially across independent training runs, which limits the reliability of uncertainty-based decisions in downstream tasks. Evidential Deep Learning aims to address these limitations by producing uncertainty estimates in a single pass, but evidential training is highly sensitive to design choices including loss formulation, prior regularization, and activation functions. Therefore, this work introduces an alternative Dirichlet parameter estimation strategy by applying a method of moments estimator to ensembles of softmax outputs, with an optional maximum-likelihood refinement step. This ensemble-based construction decouples uncertainty estimation from the fragile evidential loss design while also mitigating the variability of single-run cross-entropy training, producing explicit Dirichlet predictive distributions. Across multiple datasets, we show that the improved stability and predictive uncertainty behavior of these ensemble-derived Dirichlet estimates translate into stronger performance in downstream uncertainty-guided applications such as prediction confidence scoring and selective classification. --- ### A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models Authors: Maria Mahbub, Gregory M. Dams, Josh Arnold, Caitlin Rizy, Sudarshan Srinivasan, Elliot M. Fielstein, Minu A. Aghevli, Kamonica L. Craig, Elizabeth M. Oliva, Joseph Erdos, Jodie Trafton, Ioana Danciu Published: 2026-04-07 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2604.06028v1 Large language models (LLMs) show promise for extracting clinically meaningful information from unstructured health records, yet their translation into real-world settings is constrained by the lack of scalable and trustworthy validation approaches. Conventional evaluation methods rely heavily on annotation-intensive reference standards or incomplete structured data, limiting feasibility at population scale. We propose a multi-stage validation framework for LLM-based clinical information extraction that enables rigorous assessment under weak supervision. The framework integrates prompt calibration, rule-based plausibility filtering, semantic grounding assessment, targeted confirmatory evaluation using an independent higher-capacity judge LLM, selective expert review, and external predictive validity analysis to quantify uncertainty and characterize error modes without exhaustive manual annotation. We applied this framework to extraction of substance use disorder (SUD) diagnoses across 11 substance categories from 919,783 clinical notes. Rule-based filtering and semantic grounding removed 14.59% of LLM-positive extractions that were unsupported, irrelevant, or structurally implausible. For high-uncertainty cases, the judge LLM's assessments showed substantial agreement with subject matter expert review (Gwet's AC1=0.80). Using judge-evaluated outputs as references, the primary LLM achieved an F1 score of 0.80 under relaxed matching criteria. LLM-extracted SUD diagnoses also predicted subsequent engagement in SUD specialty care more accurately than structured-data baselines (AUC=0.80). These findings demonstrate that scalable, trustworthy deployment of LLM-based clinical information extraction is feasible without annotation-intensive evaluation. --- ### BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection Authors: Zhongxing Zhang, Emily K. Vraga, Jisu Huh, Jaideep Srivastava Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06022v2 Incorrect information poses significant challenges by disrupting content veracity and integrity, yet most detection approaches struggle to jointly balance textual content verification with external knowledge modification under collapsed attention geometries. To address this issue, we propose a dual-head reasoning framework, BiMind, which disentangles content-internal reasoning from knowledge-augmented reasoning. In BiMind, we introduce three core innovations: (i) an attention geometry adapter that reshapes attention logits via token-conditioned offsets and mitigates attention collapse; (ii) a self-retrieval knowledge mechanism, which constructs an in-domain semantic memory through kNN retrieval and injects retrieved neighbors via feature-wise linear modulation; (iii) the uncertainty-aware fusion strategies, including entropy-gated fusion and a trainable agreement head, stabilized by a symmetric Kullback-Leibler agreement regularizer. To quantify the knowledge contributions, we define a novel metric, Value-of-eXperience (VoX), to measure instance-wise logit gains from knowledge-augmented reasoning. Experiment results on public datasets demonstrate that our BiMind model outperforms advanced detection approaches and provides interpretable diagnostics on when and why knowledge matters. --- ### CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments Authors: Gustav Keppler, Moritz Gstür, Veit Hagenmeyer Published: 2026-04-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.06019v1 The advancement of Large Language Models (LLMs) has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology (IT) environments, failing to capture the constraints, and specialized protocols of Operational Technology (OT). To address this gap, we introduce CritBench, a novel framework designed to evaluate the cybersecurity capabilities of LLM agents within IEC 61850 Digital Substation environments. We assess five state-of-the-art models, including OpenAI's GPT-5 suite and open-weight models, across a corpus of 81 domain-specific tasks spanning static configuration analysis, network traffic reconnaissance, and live virtual machine interaction. To facilitate industrial protocol interaction, we develop a domain-specific tool scaffold. Our empirical results show that agents reliably execute static structured-file analysis and single-tool network enumeration, but their performance degrades on dynamic tasks. Despite demonstrating explicit, internalized knowledge of the IEC 61850 standards terminology, current models struggle with the persistent sequential reasoning and state tracking required to manipulate live systems without specialized tools. Equipping agents with our domain-specific tool scaffold significantly mitigates this operational bottleneck. Code and evaluation scripts are available at: https://github.com/GKeppler/CritBench --- ### Governance and Regulation of Artificial Intelligence in Developing Countries: A Case Study of Nigeria Authors: Uloma Okoro, Tammy Mackenzie, Branislav Radeljic Published: 2026-04-07 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.06018v2 This study examines the perception of legal professionals on the governance of AI in developing countries, using Nigeria as a case study. The study focused on ethical risks, regulatory gaps, and institutional readiness. The study adopted a qualitative case study design. Data were collected through 27 semi-structured interviews with legal practitioners in Nigeria. A focus group discussion was also held with seven additional legal practitioners across sectors such as finance, insurance, and corporate law. Thematic analysis was employed to identify key patterns in participant responses. Findings showed that there were concerns about data privacy risks and the lack of enforceable legal frameworks. Participants expressed limited confidence in institutional capacity and emphasized the need for locally adapted governance models rather than direct adoption of foreign frameworks. While some expressed optimism about AI's potential, this was conditional on the presence of strong legal oversight and public accountability. The study contributes to the growing discourse on AI governance in developing countries by focusing on the perspectives of legal professionals. It highlights the importance of regulatory approaches that are context-specific, inclusive, and capable of bridging the gap between global ethical principles and local realities. These insights offer practical guidance for policymakers, regulators, and scholars working to shape responsible AI governance in similar environments. --- ### Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNIST Authors: Michael Karnes, Alper Yilmaz Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06017v1 While deep learning has achieved remarkable success in medical imaging, the "black-box" nature of backpropagation-based models remains a significant barrier to clinical adoption. To bridge this gap, we propose Aristotelian Rapid Object Modeling (A-ROM), a framework built upon the Platonic Representation Hypothesis (PRH). This hypothesis posits that models trained on vast, diverse datasets converge toward a universal and objective representation of reality. By leveraging the generalizable metric space of pretrained Vision Transformers (ViTs), A-ROM enables the rapid modeling of novel medical concepts without the computational burden or opacity of further gradient-based fine-tuning. We replace traditional, opaque decision layers with a human-readable concept dictionary and a k-Nearest Neighbors (kNN) classifier to ensure the model's logic remains interpretable. Experiments on the MedMNIST v2 suite demonstrate that A-ROM delivers performance competitive with standard benchmarks while providing a simple and scalable, "few-shot" solution that meets the rigorous transparency demands of modern clinical environments. --- ### How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism Authors: Elisabetta Rocchetti, Alfio Ferrara Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.06015v2 Instruction tuning is commonly assumed to endow language models with a domain-general ability to follow instructions, yet the underlying mechanism remains poorly understood. Does instruction-following rely on a universal mechanism or compositional skill deployment? We investigate this through diagnostic probing across nine diverse tasks in three instruction-tuned models. Our analysis provides converging evidence against a universal mechanism. First, general probes trained across all tasks show selective rather than uniform deficits relative to task-specific specialists, indicating that representational sharing is partial and structured rather than global. Second, cross-task transfer is weak and clustered by skill similarity. Third, causal ablation reveals sparse asymmetric dependencies rather than shared representations. Tasks also stratify by complexity across layers, with structural constraints emerging early and semantic tasks emerging late. Finally, temporal analysis shows that the constraint signal becomes decodable only once generation is under way, and remains so throughout the response. These findings indicate that instruction-following is better characterized as skillful coordination of diverse linguistic capabilities rather than deployment of a single abstract constraint-checking process. --- ### How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism Authors: Elisabetta Rocchetti, Alfio Ferrara Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.06015v1 Instruction tuning is commonly assumed to endow language models with a domain-general ability to follow instructions, yet the underlying mechanism remains poorly understood. Does instruction-following rely on a universal mechanism or compositional skill deployment? We investigate this through diagnostic probing across nine diverse tasks in three instruction-tuned models. Our analysis provides converging evidence against a universal mechanism. First, general probes trained across all tasks consistently underperform task-specific specialists, indicating limited representational sharing. Second, cross-task transfer is weak and clustered by skill similarity. Third, causal ablation reveals sparse asymmetric dependencies rather than shared representations. Tasks also stratify by complexity across layers, with structural constraints emerging early and semantic tasks emerging late. Finally, temporal analysis shows constraint satisfaction operates as dynamic monitoring during generation rather than pre-generation planning. These findings indicate that instruction-following is better characterized as skillful coordination of diverse linguistic capabilities rather than deployment of a single abstract constraint-checking process. --- ### Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating Authors: Dipan Maity, Suman Mondal, Arindam Roy Published: 2026-04-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.06014v2 We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT), augmented by input-dependent gating. Self-attention is decomposed into consecutive width-wise and height-wise retention passes within each shifted window, where per-head exponential decay masks provide a two-dimensional locality prior without learned positional biases. Two variants are proposed.Gated-SwinRMT-SWAT substitutes softmax with sigmoid activation, implements balanced ALiBi slopes with multiplicative post-activation spatial decay, and gates the value projection via SwiGLU; the Normalized output implicitly suppresses uninformative attention scores. \textbf{Gated-SwinRMT-Retention} retains softmax-normalized retention with an additive log-space decay bias and incorporates an explicit G1 sigmoid gate -- projected from the block input and applied after local context enhancement (LCE) but prior to the output projection~$W_O$ -- to alleviate the low-rank $W_V \!\cdot\! W_O$ bottleneck and enable input-dependent suppression of attended outputs. We assess both variants on Mini-ImageNet ($224{\times}224$, 100 classes) and CIFAR-10 ($32{\times}32$, 10 classes) under identical training protocols, utilizing a single GPU due to resource limitations. At ${\approx}77$--$79$\,M parameters, Gated-SwinRMT-SWAT achieves $80.22\%$ and Gated-SwinRMT-Retention $78.20\%$ top-1 test accuracy on Mini-ImageNet, compared with $73.74\%$ for the RMT baseline. On CIFAR-10 -- where small feature maps cause the adaptive windowing mechanism to collapse attention to global scope -- the accuracy advantage compresses from $+6.48$\,pp to $+0.56$\,pp. --- ### Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis Authors: Michael Cuccarese Published: 2026-04-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.06013v1 This paper presents epistemic blinding in the context of an agentic system that uses large language models to reason across multiple biological datasets for drug target prioritization. During development, it became apparent that LLM outputs silently blend data-driven inference with memorized priors about named entities - and the blend is invisible: there is no way to determine, from a single output, how much came from the data on the page and how much came from the model's training memory. Epistemic blinding is a simple inference-time protocol that replaces entity identifiers with anonymous codes before prompting, then compares outputs against an unblinded control. The protocol does not make LLM reasoning deterministic, but it restores one critical axis of auditability: measuring how much of an output came from the supplied data versus the model's parametric knowledge. The complete target identification system is described - including LLM-guided evolutionary optimization of scoring functions and blinded agentic reasoning for target rationalization - with demonstration that both stages operate without access to entity identity. In oncology drug target prioritization across four cancer types, blinding changes 16% of top-20 predictions while preserving identical recovery of validated targets. The contamination problem is shown to generalize beyond biology: in S&P 500 equity screening, brand-recognition bias reshapes 30-40% of top-20 rankings across five random seeds. To lower the barrier to adoption, the protocol is released as an open-source tool and as a Claude Code skill that enables one-command epistemic blinding within agentic workflows. The claim is not that blinded analysis produces better results, but that without blinding, there is no way to know to what degree the agent is adhering to the analytical process the researcher designed. --- ### OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control Authors: Yukun Wang, Ruihuang Li, Jiale Tao, Shiyuan Yang, Liyi Chen, Zhantao Yang, Handz, Yulan Guo, Shuai Shao, Qinglin Lu Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06010v2 Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this work, we introduce OmniCamera, a unified framework designed to explicitly disentangle and command these two dimensions. This compositional approach enables flexible video generation by allowing arbitrary pairings of camera and content conditions, unlocking unprecedented creative control. To overcome the fundamental challenges of modality conflict and data scarcity inherent in such a system, we present two key innovations. First, we construct OmniCAM, a novel hybrid dataset combining curated real-world videos with synthetic data that provides diverse paired examples for robust multi-task learning. Second, we propose a Dual-level Curriculum Co-Training strategy that mitigates modality interference and synergistically learns from diverse data sources. This strategy operates on two levels: first, it progressively introduces control modalities by difficulties (condition-level), and second, trains for precise control on synthetic data before adapting to real data for photorealism (data-level). As a result, OmniCamera achieves state-of-the-art performance, enabling flexible control for complex camera movements while maintaining superior visual quality. --- ### OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control Authors: Yukun Wang, Ruihuang Li, Jiale Tao, Shiyuan Yang, Liyi Chen, Zhantao Yang, Handz, Yulan Guo, Shuai Shao, Qinglin Lu Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.06010v1 Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this work, we introduce OmniCamera, a unified framework designed to explicitly disentangle and command these two dimensions. This compositional approach enables flexible video generation by allowing arbitrary pairings of camera and content conditions, unlocking unprecedented creative control. To overcome the fundamental challenges of modality conflict and data scarcity inherent in such a system, we present two key innovations. First, we construct OmniCAM, a novel hybrid dataset combining curated real-world videos with synthetic data that provides diverse paired examples for robust multi-task learning. Second, we propose a Dual-level Curriculum Co-Training strategy that mitigates modality interference and synergistically learns from diverse data sources. This strategy operates on two levels: first, it progressively introduces control modalities by difficulties (condition-level), and second, trains for precise control on synthetic data before adapting to real data for photorealism (data-level). As a result, OmniCamera achieves state-of-the-art performance, enabling flexible control for complex camera movements while maintaining superior visual quality. --- ### Disentangling MLP Neuron Weights in Vocabulary Space Authors: Asaf Avrahamy, Yoav Gur-Arieh, Mor Geva Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06005v2 Interpreting the information encoded in language model weights remains a fundamental challenge in mechanistic interpretability. In this work, we introduce ROTATE (Rotation-Optimized Token Alignment in weighT spacE), a data-free method requiring no forward passes that disentangles MLP neurons directly in weight space. Our approach relies on a key statistical observation: neurons that encode coherent, monosemantic concepts exhibit high kurtosis when projected onto the model's vocabulary. By optimizing rotations of neuron weights to maximize their vocabulary-space kurtosis, our method recovers sparse, interpretable directions which we name vocabulary channels. Experiments on Llama-3.1-8B-Instruct and Gemma-2-2B-it demonstrate that ROTATE consistently recovers vocabulary channels that are faithful to the neuron's behavior; ablating individual channels selectively disables corresponding input activations or the promotion of specific concepts. Moreover, aggregating channel-level descriptions yields comprehensive neuron descriptions that outperform optimized activation-based baselines by 2-3x in head-to-head comparisons. By providing a data-free decomposition of neuron weights, ROTATE offers a scalable, fine-grained building block for interpreting language models. --- ### A deep learning framework for jointly solving transient Fokker-Planck equations with arbitrary parameters and initial distributions Authors: Xiaolong Wang, Jing Feng, Qi Liu, Chengli Tan, Yuanyuan Liu, Yong Xu Published: 2026-04-07 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2604.06001v2 Efficiently solving the Fokker-Planck equation (FPE) is central to analyzing complex parameterized stochastic systems. However, current numerical methods lack parallel computation capabilities across varying conditions, severely limiting comprehensive parameter exploration and transient analysis. This paper introduces a deep learning-based pseudo-analytical probability solution (PAPS) that, via a single training process, simultaneously resolves transient FPE solutions for arbitrary multi-modal initial distributions, system parameters, and time points. The core idea is to unify initial, transient, and stationary distributions via Gaussian mixture distributions (GMDs) and develop a constraint-preserving autoencoder that bijectively maps constrained GMD parameters to unconstrained, low-dimensional latent representations. In this representation space, the panoramic transient dynamics across varying initial conditions and system parameters can be modeled by a single evolution network. Extensive experiments on paradigmatic systems demonstrate that the proposed PAPS maintains high accuracy while achieving inference speeds four orders of magnitude faster than GPU-accelerated Monte Carlo simulations. This efficiency leap enables previously intractable real-time parameter sweeps and systematic investigations of stochastic bifurcations. By decoupling representation learning from physics-informed transient dynamics, our work establishes a scalable paradigm for probabilistic modeling of multi-dimensional, parameterized stochastic systems. --- ### The Model Agreed, But Didn't Learn: Diagnosing Surface Compliance in Large Language Models Authors: Xiaojie Gu, Ziying Huang, Weicong Hong, Jian Xie, Renze Lou, Kai Zhang Published: 2026-04-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.05995v1 Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal representations is imperative for trustworthy real-world deployment. Knowledge editing offers a pivotal paradigm for surgically modifying memory without retraining. However, while recent editors demonstrate high success rates on standard benchmarks, it remains questionable whether current evaluation frameworks that rely on assessing output under specific prompting conditions can reliably authenticate genuine memory modification. In this work, we introduce a simple diagnostic framework that subjects models to discriminative self-assessment under in-context learning (ICL) settings that better reflect real-world application environments, specifically designed to scrutinize the subtle behavioral nuances induced by memory modifications. This probing reveals a pervasive phenomenon of Surface Compliance, where editors achieve high benchmark scores by merely mimicking target outputs without structurally overwriting internal beliefs. Moreover, we find that recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model's memory state. These insights underscore the risks of current editing paradigms and highlight the pivotal role of robust memory modification in building trustworthy, long-term sustainable LLM systems. Code is available at https://github.com/XiaojieGu/SA-MCQ. --- ### Data Distribution Valuation Using Generalized Bayesian Inference Authors: Cuong N. Nguyen, Cuong V. Nguyen Published: 2026-04-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.05993v1 We investigate the data distribution valuation problem, which aims to quantify the values of data distributions from their samples. This is a recently proposed problem that is related to but different from classical data valuation and can be applied to various applications. For this problem, we develop a novel framework called Generalized Bayes Valuation that utilizes generalized Bayesian inference with a loss constructed from transferability measures. This framework allows us to solve, in a unified way, seemingly unrelated practical problems, such as annotator evaluation and data augmentation. Using the Bayesian principles, we further improve and enhance the applicability of our framework by extending it to the continuous data stream setting. Our experiment results confirm the effectiveness and efficiency of our framework in different real-world scenarios. --- ### Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains Authors: Eranga Bandara, Ross Gore, Sachin Shetty, Piumi Siyambalapitiya, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Ravi Mukkamala, Peter Foytik, Safdar H. Bouk, Abdul Rahman, Xueping Liang et al. Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.05987v1 Retail supply chain operations in supermarket chains involve continuous, high-volume manual workflows spanning demand forecasting, procurement, supplier coordination, and inventory replenishment, processes that are repetitive, decision-intensive, and difficult to scale without significant human effort. Despite growing investment in data analytics, the decision-making and coordination layers of these workflows remain predominantly manual, reactive, and fragmented across outlets, distribution centers, and supplier networks. This paper introduces Flowr, a novel agentic AI framework for automating end-to-end retail supply chain workflows in large-scale supermarket operations. Flowr systematically decomposes manual supply chain operations into specialized AI agents, each responsible for a clearly defined cognitive role, enabling automation of processes previously dependent on continuous human coordination. To ensure task accuracy and adherence to responsible AI principles, the framework employs a consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM. Central to the framework is a human-in-the-loop orchestration model in which supply chain managers supervise and intervene across workflow stages via a Model Context Protocol (MCP)-enabled interface, preserving accountability and organizational control. Evaluation demonstrates that Flowr significantly reduces manual coordination overhead, improves demand-supply alignment, and enables proactive exception handling at a scale unachievable through manual processes. The framework was validated in collaboration with a large-scale supermarket chain and is domain-independent, offering a generalizable blueprint for agentic AI-driven supply chain automation across large-scale enterprise settings. --- ### Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design Authors: Shuqing Zhao Published: 2026-04-07 Categories: cs.PL, cs.CL arXiv: https://arxiv.org/abs/2604.05983v3 We present Arch (AI-native Register-transfer Clocked Hardware), a hardware description language for micro-architecture specification and AI-assisted code generation. Arch provides first-class constructs for pipelines, FSMs, FIFOs, arbiters, register files, buses with handshake channels, clock-domain crossings, and multi-cycle threads -- structures that existing HDLs express only as user-defined patterns prone to subtle errors. A central design choice is that clocks and resets are parameterized types (Clock<D>, Reset<S,P,D?>) rather than ordinary nets, converting CDC and reset-domain analysis from external linter passes into compile-time typing rules. Bit widths, port directions, single-driver ownership, and combinational acyclicity are tracked in the same pass, catching latches, width mismatches, loops, and unsynchronized crossings before simulation. A guard clause on reg declarations captures the valid-data pattern declaratively, catching the producer bug where a valid flag asserts before data is written. Every syntactic choice is governed by an AI-generatability contract: an LL(1) grammar, no preprocessor, a uniform declaration schema, named block endings, and a todo! escape hatch let LLMs produce structurally correct, type-safe Arch from natural-language specs without fine-tuning. The compiler emits lint-clean IEEE 1800-2017 SystemVerilog and auto-generates safety properties (FIFO no-overflow, counter range, FSM legal-state, handshake protocol) verified with Verilator -- assert and EBMC, plus direct AST-to-SMT-LIB2 bounded model checking via arch formal. An integrated simulator compiles designs to native C++ with Python cocotb support. Case studies: L1 cache and AXI DMA (Yosys/OpenSTA, Sky130); 428/431 tests pass on VerilogEval and CVDP. --- ### Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family Authors: Oscar Chew, Hsiao-Ying Huang, Kunal Jain, Tai-I Chen, Khoa D Doan, Kuan-Hao Huang Published: 2026-04-07 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.05971v2 Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While a growing body of work has sought to address this limitation, we identify a distinct failure mode in the CLIP family, which we term center bias, that persists even in recent model variants. Specifically, CLIP tends to disproportionately focus on the central region of an image, overlooking important objects located near the boundaries. This limitation is fundamental as failure to recognize relevant objects makes it difficult to perform any sophisticated tasks that depend on those objects. To understand the underlying causes of the limitation, we conduct analyses from both representation and attention perspectives. Using interpretability methods, i.e., embedding decomposition and attention map analysis, we find that relevant concepts especially those associated with off-center objects vanish from the model's embedding in the final representation due to information loss during the aggregation of visual embeddings, particularly the reliance on pooling mechanisms. Finally, we show that this bias can be alleviated with training-free strategies such as visual prompting and attention redistribution by redirecting models' attention to off-center regions. --- ### Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family Authors: Oscar Chew, Hsiao-Ying Huang, Kunal Jain, Tai-I Chen, Khoa D Doan, Kuan-Hao Huang Published: 2026-04-07 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.05971v1 Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While a growing body of work has sought to address this limitation, we identify a distinct failure mode in the CLIP family, which we term center bias, that persists even in recent model variants. Specifically, CLIP tends to disproportionately focus on the central region of an image, overlooking important objects located near the boundaries. This limitation is fundamental as failure to recognize relevant objects makes it difficult to perform any sophisticated tasks that depend on those objects. To understand the underlying causes of the limitation, we conduct analyses from both representation and attention perspectives. Using interpretability methods, i.e., embedding decomposition and attention map analysis, we find that relevant concepts especially those associated with off-center objects vanish from the model's embedding in the final representation due to information loss during the aggregation of visual embeddings, particularly the reliance on pooling mechanisms. Finally, we show that this bias can be alleviated with training-free strategies such as visual prompting and attention redistribution by redirecting models' attention to off-center regions. --- ### A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms Authors: Nirajan Acharya, Gaurav Kumar Gupta Published: 2026-04-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.05969v1 The Model Context Protocol (MCP), introduced by Anthropic in November 2024 and now governed by the Linux Foundation's Agentic AI Foundation, has rapidly become the de facto standard for connecting large language model (LLM)-based agents to external tools and data sources, with over 97 million monthly SDK downloads and more than 177000 registered tools. However, this explosive adoption has exposed a critical gap: the absence of a unified, formal security framework capable of systematically characterizing, analyzing, and mitigating the diverse threats facing MCP-based agent ecosystems. Existing security research remains fragmented across individual attack papers, isolated benchmarks, and point defense mechanisms. This paper presents MCPSHIELD, a comprehensive formal security framework for MCP-based AI agents. We make four principal contributions: (1) a hierarchical threat taxonomy comprising 7 threat categories and 23 distinct attack vectors organized across four attack surfaces, grounded in the analysis of over 177000 MCP tools; (2) a formal verification model based on labeled transition systems with trust boundary annotations that enables static and runtime analysis of MCP tool interaction chains; (3) a systematic comparative evaluation of 12 existing defense mechanisms, identifying coverage gaps across our threat taxonomy; and (4) a defense in depth reference architecture integrating capability based access control, cryptographic tool attestation, information flow tracking, and runtime policy enforcement. Our analysis reveals that no existing single defense covers more than 34 percent of the identified threat landscape, whereas MCPSHIELD's integrated architecture achieves theoretical coverage of 91 percent. We further identify seven open research challenges that must be addressed to secure the next generation of agentic AI systems. --- ### On Dominant Manifolds in Reservoir Computing Networks Authors: Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva Published: 2026-04-07 Categories: cs.LG, math.DS, math.OC arXiv: https://arxiv.org/abs/2604.05967v3 Understanding how training shapes the geometry of recurrent network dynamics is a central problem in time-series modeling. We study the emergence of low-dimensional dominant manifolds in the training of Reservoir Computing (RC) networks for temporal forecasting tasks. For a general linear continuous-time reservoir in the infinite-data limit, we show that the training data generate an invariant subspace of the trained reservoir, whose dimension equals the number of dominant modes. We then specialize to a simplified diagonal linear reservoir, where we link the dominant eigenvalues and eigenvectors to the spectrum of a backward Dynamic Mode Decomposition matrix, which yields a finite-dimensional approximation of the backward-time Koopman operator of the system generating the training data. We illustrate the emergence of these dominant modes during training in simulation, and discuss how the analysis may be extended to nonlinear RC via tangent dynamics and differential p-dominance. --- ### On Dominant Manifolds in Reservoir Computing Networks Authors: Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva Published: 2026-04-07 Categories: cs.LG, math.DS, math.OC arXiv: https://arxiv.org/abs/2604.05967v1 Understanding how training shapes the geometry of recurrent network dynamics is a central problem in time-series modeling. We study the emergence of low-dimensional dominant manifolds in the training of Reservoir Computing (RC) networks for temporal forecasting tasks. For a simplified linear and continuous-time reservoir model, we link the dimensionality and structure of the dominant modes directly to the intrinsic dimensionality and information content of the training data. In particular, for training data generated by an autonomous dynamical system, we relate the dominant modes of the trained reservoir to approximations of the Koopman eigenfunctions of the original system, illuminating an explicit connection between reservoir computing and the Dynamic Mode Decomposition algorithm. We illustrate the eigenvalue motion that generates the dominant manifolds during training in simulation, and discuss generalization to nonlinear RC via tangent dynamics and differential p-dominance. --- ### FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures Authors: Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Georgiev, Ayesha Gull, Muhammad Usman Safder et al. Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.05966v2 Financial reporting systems increasingly leverage Large Language Models (LLMs) to extract and summarize corporate disclosures. However, most existing approaches assume a single-market setting and overlook structural differences across jurisdictions. Variations in accounting taxonomies, tagging infrastructures (e.g., XBRL vs.\ PDF), and aggregation conventions introduce substantial challenges for semantic alignment and reliable verification. Here, we aim to bridge this gap. We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting. The system constructs a unified canonical ontology spanning the income statement, balance sheet, and cash flow statement, and decomposes reporting into auditable stages, including filing acquisition, extraction, canonical mapping, and anomaly logging. Rather than treating LLMs as free-form generators, FinReporting employs them as constrained verifiers operating under explicit decision rules with evidence grounding. Evaluated on annual filings from the USA, Japan, and China, FinReporting improves consistency and reliability under heterogeneous reporting regimes. We further release an interactive demo that enables cross-market inspection and supports structured export of localized financial statements. Our demo is available at url{https://huggingface.co/spaces/BoomQ/FinReporting-Demo. A video describing our system is available at https://www.youtube.com/watch?v=f65jdEL31Kk. --- ### Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment Authors: Renxuan Tan, Rongpeng Li, Zhifeng Zhao, Honggang Zhang Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.05965v1 Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or rigid gradient projection to navigate these trade-offs. However, by enforcing strict conflict avoidance or simultaneous descent, these paradigms often prematurely converge to local stationary points. While mathematically stable, these points represent a conservative compromise where the model sacrifices potential global Pareto improvements to avoid transient local trade-offs. To break this deadlock, we propose Pareto-Lenient Consensus (PLC), a game-theoretic framework that reimagines alignment as a dynamic negotiation process. Unlike rigid approaches, PLC introduces consensus-driven lenient gradient rectification, which dynamically tolerates local degradation provided there is a sufficient dominant coalition surplus, thereby empowering the optimization trajectory to escape local suboptimal equilibrium and explore the distal Pareto-optimal frontier. Theoretical analysis validates PLC can facilitate stalemate escape and asymptotically converge to a Pareto consensus equilibrium. Moreover, extensive experiments show that PLC surpasses baselines in both fixed-preference alignment and global Pareto frontier quality. This work highlights the potential of negotiation-driven alignment as a promising avenue for MPA. Our codes are available at https://anonymous.4open.science/r/aaa-6BB8. --- ### QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization Authors: Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo et al. Published: 2026-04-07 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2604.05963v1 Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct code while fixing only buggy parts. Building on this insight, we propose PRepair, a framework that mitigates over-editing and improves repair accuracy. PRepair has two components: Self-Breaking, which generates diverse buggy programs via controlled bug injection and min-max sampling, and Self-Repairing, which trains models with Edit-Aware Group Relative Policy Optimization (EA-GRPO) using an edit-aware reward to encourage minimal yet correct edits. Experiments show that PRepair improves repair precision by up to 31.4% under $\mathrm{fix}_1@1$, a metric that jointly considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing, demonstrating its potential for precise and practical code repair. --- ### HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation Authors: Tao Hu, Varun Jampani Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.05961v1 Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In this paper, we propose a new framework for human video generation, HumANDiff, which enhances the human motion control with three key designs: 1) Articulated motion-consistent noise sampling that correlates the spatiotemporal distribution of latent noise and replaces the unstructured random Gaussian noise with 3D articulated noise sampled on the dense surface manifold of a statistical human body template. It inherits body topology priors for spatially and temporally consistent noise sampling. 2) Joint appearance-motion learning that enhances the standard training objective of video diffusion models by jointly predicting pixel appearances and corresponding physical motions from the articulated noises. It enables high-fidelity human video synthesis, e.g., capturing motion-dependent clothing wrinkles. 3) Geometric motion consistency learning that enforces physical motion consistency across frames via a novel geometric motion consistency loss defined in the articulated noise space. HumANDiff enables scalable controllable human video generation by fine-tuning video diffusion models with articulated noise sampling. Consequently, our method is agnostic to diffusion model design, and requires no modifications to the model architecture. During inference, HumANDiff enables image-to-video generation within a single framework, achieving intrinsic motion control without requiring additional motion modules. Extensive experiments demonstrate that our method achieves state-of-the-art performance in rendering motion-consistent, high-fidelity humans with diverse clothing styles. Project page: https://taohuumd.github.io/projects/HumANDiff/ --- ### A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis Authors: Sk Miraj Ahmed, Yuewei Lin, Chuntian Cao, Shinjae Yoo, Xinpei Wu, Won-Il Lee, Nikhil Tiwale, Dan N. Le, Thi Thu Huong Chu, Jiyoung Kim, Kevin G. Yager, Chang-Yong Nam Published: 2026-04-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.05960v1 Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional investigations. However, SEM imaging remains constrained by task-specific models and labor-intensive acquisition processes that limit its scalability across diverse applications. Here, we introduce the first foundation model for SEM images, pretrained on a large corpus of multi-instrument, multi-condition scientific micrographs, enabling generalization across diverse material systems and imaging conditions. Leveraging a self-supervised transformer architecture, our model learns rich and transferable representations that can be fine-tuned or adapted to a wide range of downstream tasks. As a compelling demonstration, we focus on defocus-to-focus image translation-an essential yet underexplored challenge in automated microscopy pipelines. Our method not only restores focused detail from defocused inputs without paired supervision but also outperforms state-of-the-art techniques across multiple evaluation metrics. This work lays the groundwork for a new class of adaptable SEM models, accelerating materials discovery by bridging foundational representation learning with real-world imaging needs. --- ### Multi-Modal Landslide Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Multi-Encoder Vision Transformers and Ensemble Learning Authors: Ioannis Nasios Published: 2026-04-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.05959v1 Landslides represent a major geohazard with severe impacts on human life, infrastructure, and ecosystems, underscoring the need for accurate and timely detection approaches to support disaster risk reduction. This study proposes a modular, multi-model framework that fuses Sentinel-2 optical imagery with Sentinel-1 Synthetic Aperture Radar (SAR) data, for robust landslide detection. The methodology leverages multi-encoder vision transformers, where each data modality is processed through separate lightweight pretrained encoders, achieving strong performance in landslide detection. In addition, the integration of multiple models, particularly the combination of neural networks and gradient boosting models (LightGBM and XGBoost), demonstrates the power of ensemble learning to further enhance accuracy and robustness. Derived spectral indices, such as NDVI, are integrated alongside original bands to enhance sensitivity to vegetation and surface changes. The proposed methodology achieves a state-of-the-art F1 score of 0.919 on landslide detection, addressing a patch-based classification task rather than pixel-level segmentation and operating without pre-event Sentinel-2 data, highlighting its effectiveness in a non-classical change detection setting. It also demonstrated top performance in a machine learning competition, achieving a strong balance between precision and recall and highlighting the advantages of explicitly leveraging the complementary strengths of optical and radar data. The conducted experiments and research also emphasize scalability and operational applicability, enabling flexible configurations with optical-only, SAR-only, or combined inputs, and offering a transferable framework for broader natural hazard monitoring and environmental change applications. Full training and inference code can be found in https://github.com/IoannisNasios/sentinel-landslide-cls. --- ### Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution Authors: Kai Yu, Zhenhao Zhou, Junhao Zeng, Ying Wang, Xueying Du, Zhiqiang Yuan, Junwei Liu, Ziyu Zhou, Yujia Wang, Chong Wang, Xin Peng Published: 2026-04-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.05955v1 Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with project-specific design constraints, such as architectural conventions, error-handling policies, and maintainability requirements, which are rarely encoded in tests and are often documented only implicitly in code review discussions. This paper introduces \textit{design-aware issue resolution} and presents \bench{}, a benchmark that makes such implicit design constraints explicit and measurable. \bench{} is constructed by mining and validating design constraints from real-world pull requests, linking them to issue instances, and automatically checking patch compliance using an LLM-based verifier, yielding 495 issues and 1,787 validated constraints across six repositories, aligned with SWE-bench-Verified and SWE-bench-Pro. Experiments with state-of-the-art agents show that test-based correctness substantially overestimates patch quality: fewer than half of resolved issues are fully design-satisfying, design violations are widespread, and functional correctness exhibits negligible statistical association with design satisfaction. While providing issue-specific design guidance reduces violations, substantial non-compliance remains, highlighting a fundamental gap in current agent capabilities and motivating design-aware evaluation beyond functional correctness. --- ### Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences Authors: Pasin Manurangsi, Krzysztof Sornat Published: 2026-04-07 Categories: cs.GT, cs.AI, cs.DS, cs.MA arXiv: https://arxiv.org/abs/2604.05953v1 We present a polynomial-time algorithm for computing an optimal committee of size $k$ under any given Thiele voting rule for elections on the Voter Interval domain (i.e., when voters can be ordered so that each candidate is approved by a consecutive voters). Our result extends to the Generalized Thiele rule, in which each voter has an individual weight (scoring) sequence. This resolves a 10-year-old open problem that was originally posed for Proportional Approval Voting and later extended to every Thiele rule (Elkind and Lackner, IJCAI 2015; Peters, AAAI 2018). Our main technical ingredient is a new structural result -- a concavity theorem for families of intervals. It shows that, given two solutions of different sizes, one can construct a solution of any intermediate size whose score is at least the corresponding linear interpolation of the two scores. As a consequence, on Voter Interval profiles, the optimal total Thiele score is a concave function of the committee size. We exploit this concavity within an optimization framework based on a Lagrangian relaxation of a natural integer linear program formulation, obtained by moving the cardinality constraint into the objective. On Voter Interval profiles, the resulting constraint matrix is totally unimodular, so it can be solved in polynomial time. Our main algorithm and its proof were obtained via human--AI collaboration. In particular, a slightly simplified version of the main structural theorem used by the algorithm was obtained in a single call to Gemini Deep Think. --- ### Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration Authors: Yi Yuan, Xuhong Wang, Shanzhe Lei Published: 2026-04-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.05952v1 As agent-based systems continue to evolve, deep research agents are capable of automatically generating research-style reports across diverse domains. While these agents promise to streamline information synthesis and knowledge exploration, existing evaluation frameworks-typically based on subjective dimensions-fail to capture a critical aspect of report quality: trustworthiness. In open-ended research scenarios where ground-truth answers are unavailable, current evaluation methods cannot effectively measure the epistemic confidence of generated content, making calibration difficult and leaving users susceptible to misleading or hallucinated information. To address this limitation, we propose a novel deep research agent that incorporates progressive confidence estimation and calibration within the report generation pipeline. Our system leverages a deliberative search model, featuring deep retrieval and multi-hop reasoning to ground outputs in verifiable evidence while assigning confidence scores to individual claims. Combined with a carefully designed workflow, this approach produces trustworthy reports with enhanced transparency. Experimental results and case studies demonstrate that our method substantially improves interpretability and significantly increases user trust. --- ### Mixture-of-Modality-Experts with Holistic Token Learning for Fine-Grained Multimodal Visual Analytics in Driver Action Recognition Authors: Tianyi Liu, Yiming Li, Wenqian Wang, Jiaojiao Wang, Chen Cai, Yi Wang, Kim-Hui Yap Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.05947v1 Robust multimodal visual analytics remains challenging when heterogeneous modalities provide complementary but input-dependent evidence for decision-making.Existing multimodal learning methods mainly rely on fixed fusion modules or predefined cross-modal interactions, which are often insufficient to adapt to changing modality reliability and to capture fine-grained action cues. To address this issue, we propose a Mixture-of-Modality-Experts (MoME) framework with a Holistic Token Learning (HTL) strategy. MoME enables adaptive collaboration among modality-specific experts, while HTL improves both intra-expert refinement and inter-expert knowledge transfer through class tokens and spatio-temporal tokens. In this way, our method forms a knowledge-centric multimodal learning framework that improves expert specialization while reducing ambiguity in multimodal fusion.We validate the proposed framework on driver action recognition as a representative multimodal understanding taskThe experimental results on the public benchmark show that the proposed MoME framework and the HTL strategy jointly outperform representative single-modal and multimodal baselines. Additional ablation, validation, and visualization results further verify that the proposed HTL strategy improves subtle multimodal understanding and offers better interpretability. --- ### MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Authors: Maria Nesterova, Mikhail Kolosov, Anton Andreychuk, Egor Cherepanov, Oleg Bulichev, Alexey Kovalev, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik Published: 2026-04-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.05943v1 Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology that makes it possible for a single GPT-based model to learn and perform well across diverse MARL environments and tasks, including StarCraft Multi-Agent Challenge, Google Research Football and POGEMA. Our method, MARL-GPT, applies offline reinforcement learning to train at scale on the expert trajectories (400M for SMACv2, 100M for GRF, and 1B for POGEMA) combined with a single transformer-based observation encoder that requires no task-specific tuning. Experiments show that MARL-GPT achieves competitive performance compared to specialized baselines in all tested environments. Thus, our findings suggest that it is, indeed, possible to build a multi-task transformer-based model for a wide variety of (significantly different) multi-agent problems paving the way to the fundamental MARL model (akin to ChatGPT, Llama, Mistral etc. in natural language modeling). --- ### BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs Authors: Abbas Ghaddar, Ivan Kobyzev, Boxing Chen, Yufei Cui Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.05942v1 Post-training hybridization of large language models (LLMs) often replaces quadratic self-attention with sliding-window attention (SWA) to reduce KV cache usage and improve latency. Existing hybridization schemes are typically defined either at the layer level (e.g., interleaving) or at the head level via static rankings from local to global. Layer-level schemes ignore that local and global dependencies are routed through heads within the same layer, while static head-level rankings suffer from entanglement: a head's local/global behavior can change after hybridization. We propose BOSCH, Black-box Binary Optimization for Short-context Head Selection, a training-free method that formulates the problem as a Large Neighborhood Search and decomposes it into three subproblems: (i) layer-importance detection via small-budget black-box probes, (ii) adaptive per-layer SWA-ratio assignment based on these sensitivities, and (iii) grouped head-level optimization within ratio buckets. Extensive experiments on 4 LLMs ranging from 1.7B to 30B parameters, across 4 SWA ratios, show that BOSCH consistently outperforms layer-level heuristics and 6 strong static head-level methods, with larger gains at higher SWA ratios. Under continual pretraining, BOSCH recover original long-context performance faster and to a higher level. Analysis of the selected heads reveals substantial turnover for BOSCH across different SWA ratios, underscoring the importance of performing head-level selection for each target ratio rather than relying on fixed locality rankings. --- ### Context-Value-Action Architecture for Value-Driven Large Language Model Agents Authors: TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang, Zhiqiang Wu, Guojie Song Published: 2026-04-07 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.05939v1 Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations. By evaluating against empirical ground truth, we reveal a counter-intuitive phenomenon: increasing the intensity of prompt-driven reasoning does not enhance fidelity but rather exacerbates value polarization, collapsing population diversity. To address this, we propose the Context-Value-Action (CVA) architecture, grounded in the Stimulus-Organism-Response (S-O-R) model and Schwartz's Theory of Basic Human Values. Unlike methods relying on self-verification, CVA decouples action generation from cognitive reasoning via a novel Value Verifier trained on authentic human data to explicitly model dynamic value activation. Experiments on CVABench, which comprises over 1.1 million real-world interaction traces, demonstrate that CVA significantly outperforms baselines. Our approach effectively mitigates polarization while offering superior behavioral fidelity and interpretability. --- ### Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction Authors: Ahmet Rasim Emirdagi, Süleyman Aslan, Mısra Yavuz, Görkay Aydemir, Yunus Bilge Kurt, Nasrin Rahimi, Burak Can Biner, M. Akın Yılmaz Published: 2026-04-07 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.05934v1 Metal artifacts from high-attenuation implants severely degrade CT image quality, obscuring critical anatomical structures and posing a challenge for standard deep learning methods that require extensive paired training data. We propose a paradigm shift: reframing artifact reduction as an in-context reasoning task by adapting a general-purpose vision-language diffusion foundation model via parameter-efficient Low-Rank Adaptation (LoRA). By leveraging rich visual priors, our approach achieves effective artifact suppression with only 16 to 128 paired training examples reducing data requirements by two orders of magnitude. Crucially, we demonstrate that domain adaptation is essential for hallucination mitigation; without it, foundation models interpret streak artifacts as erroneous natural objects (e.g., waffles or petri dishes). To ground the restoration, we propose a multi-reference conditioning strategy where clean anatomical exemplars from unrelated subjects are provided alongside the corrupted input, enabling the model to exploit category-specific context to infer uncorrupted anatomy. Extensive evaluation on the AAPM CT-MAR benchmark demonstrates that our method achieves state-of-the-art performance on perceptual and radiological-feature metrics . This work establishes that foundation models, when appropriately adapted, offer a scalable alternative for interpretable, data-efficient medical image reconstruction. Code is available at https://github.com/ahmetemirdagi/CT-EditMAR. --- ### SonoSelect: Efficient Ultrasound Perception via Active Probe Exploration Authors: Yixin Zhang, Yunzhong Hou, Longqi Li, Zhenyue Qin, Yang Liu, Yue Yao Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.05933v3 Ultrasound perception typically requires multiple scan views through probe movement to reduce diagnostic ambiguity, mitigate acoustic occlusions, and improve anatomical coverage. However, not all probe views are equally informative. Exhaustively acquiring a large number of views can introduce substantial redundancy, increase scanning and processing costs. To address this, we define an active view exploration task for ultrasound and propose SonoSelect, an ultrasound-specific method that adaptively guides probe movement based on current observations. Specifically, we cast ultrasound active view exploration as a sequential decision-making problem. Each new 2D ultrasound view is fused into a 3D spatial memory of the observed anatomy, which guides the next probe position. On top of this formulation, we propose an ultrasound-specific objective that favors probe movements with greater organ coverage, lower reconstruction uncertainty, and less redundant scanning. Experiments on the ultrasound simulator show that SonoSelect achieves promising multi-view organ classification accuracy using only 2 out of N views. Furthermore, for a more difficult kidney cyst detection task, it reaches 54.56% kidney coverage and 35.13% cyst coverage, with short trajectories consistently centered on the target cyst. --- ### Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning Authors: Jingbo Sun, Qichao Zhang, Songjun Tu, Xing Fang, Yupeng Zheng, Haoran Li, Ke Chen, Dongbin Zhao Published: 2026-04-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.05931v1 Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervision. Among existing approaches, successor representations (SR) have emerged as a prominent paradigm due to their effectiveness in structured, low-dimensional settings. However, SR methods struggle to scale to high-dimensional visual environments. Through empirical analysis, we identify two key limitations of SR in visual URL: (1) SR objectives often lead to suboptimal representations that attend to dynamics-irrelevant regions, resulting in inaccurate successor measures and degraded task generalization; and (2) these flawed representations hinder SR policies from modeling multi-modal skill-conditioned action distributions and ensuring skill controllability. To address these limitations, we propose Saliency-Guided Representation with Consistency Policy Learning (SRCP), a novel framework that improves zero-shot generalization of SR methods in visual URL. SRCP decouples representation learning from successor training by introducing a saliency-guided dynamics task to capture dynamics-relevant representations, thereby improving successor measure and task generalization. Moreover, it integrates a fast-sampling consistency policy with URL-specific classifier-free guidance and tailored training objectives to improve skill-conditioned policy modeling and controllability. Extensive experiments on 16 tasks across 4 datasets from the ExORL benchmark demonstrate that SRCP achieves state-of-the-art zero-shot generalization in visual URL and is compatible with various SR methods. --- ### "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns? Authors: Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou, Yuyuan Li, Tianyu Du, Jun Wang, Zhihui Fu, Jinbao Li, Shouling Ji Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.05930v1 Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning. --- ### ReLU Networks for Exact Generation of Similar Graphs Authors: Mamoona Ghafoor, Tatsuya Akutsu Published: 2026-04-07 Categories: cs.LG, cs.AI, cs.DM arXiv: https://arxiv.org/abs/2604.05929v1 Generation of graphs constrained by a specified graph edit distance from a source graph is important in applications such as cheminformatics, network anomaly synthesis, and structured data augmentation. Despite the growing demand for such constrained generative models in areas including molecule design and network perturbation analysis, the neural architectures required to provably generate graphs within a bounded graph edit distance remain largely unexplored. In addition, existing graph generative models are predominantly data-driven and depend heavily on the availability and quality of training data, which may result in generated graphs that do not satisfy the desired edit distance constraints. In this paper, we address these challenges by theoretically characterizing ReLU neural networks capable of generating graphs within a prescribed graph edit distance from a given graph. In particular, we show the existence of constant depth and O(n^2 d) size ReLU networks that deterministically generate graphs within edit distance d from a given input graph with n vertices, eliminating reliance on training data while guaranteeing validity of the generated graphs. Experimental evaluations demonstrate that the proposed network successfully generates valid graphs for instances with up to 1400 vertices and edit distance bounds up to 140, whereas baseline generative models fail to generate graphs with the desired edit distance. These results provide a theoretical foundation for constructing compact generative models with guaranteed validity. --- ### The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model Authors: Hongxu Zhou Published: 2026-04-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.05923v1 State space models (SSMs) have been shown to possess the theoretical capacity to model both star-free sequential tasks and bounded hierarchical structures Sarrof et al. (2024). However, formal expressivity results do not guarantee that gradient-based optimisation will reliably discover the corresponding solutions. Existing benchmarks probe either monotonic state tracking, as in the standard Flip-Flop task, or structural nesting, as in the Dyck languages, but neither isolates reversible semantic state retrieval. We introduce the UNDO Flip-Flop task to fill this gap. By extending the standard Flip-Flop with an UNDO, the task requires a model to maintain an implicit bounded stack and recover historical states under non-monotonic update sequences. We evaluate one-layer and two-layer Mamba-2 under this framework. Both variants fail to acquire the provably expressible stack-based rollback mechanism, converging instead on a local toggle heuristic that inverts the current state rather than retrieving stored history. Under an adversarial retraction pressure test held within the training length distribution, the two-layer model collapses to 41.10% accuracy, which is below random chance. The results confirm systematic rather than incidental failure. Causal ablation shows that the bottleneck lies in retrieval, not storage. These results draw a clear line between what an architecture can in principle represent and what gradient descent reliably learns, a distinction that theoretical expressivity analyses alone cannot capture. --- ### FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Authors: Michael Krumdick, Varshini Reddy, Shivani Chaudhary, William Day, Maarij Ahmed, Hayan Haqqi, Muhammad Ahsen Fahim, Hanzallah Amjad, Ahmad Orakzai, Aqsa Gul, Chris Tanner Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.05912v1 As concerns surrounding AI-driven labor displacement intensify in knowledge-intensive sectors, existing benchmarks fail to measure performance on tasks that define practical professional expertise. Finance, in particular, has been identified as a domain with high AI exposure risk, yet lacks robust benchmarks to track real-world developments. This gap is compounded by the absence of clear accountability mechanisms in current Large Language Model (LLM) deployments. To address this, we introduce FrontierFinance, a long-horizon benchmark of 25 complex financial modeling tasks across five core finance models, requiring an average of over 18 hours of skilled human labor per task to complete. Developed with financial professionals, the benchmark reflects industry-standard financial modeling workflows and is paired with detailed rubrics for structured evaluation. We engage human experts to define the tasks, create rubrics, grade LLMs, and perform the tasks themselves as human baselines. We demonstrate that our human experts both receive higher scores on average, and are more likely to provide client-ready outputs than current state-of-the-art systems. --- ### Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction Authors: Yangyi Xiao, Siting Zhu, Baoquan Yang, Tianchen Deng, Yongbo Chen, Hesheng Wang Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.05908v1 Multi-traversal scene reconstruction is important for high-fidelity autonomous driving simulation and digital twin construction. This task involves integrating multiple sequences captured from the same geographical area at different times. In this context, a primary challenge is the significant appearance inconsistency across traversals caused by varying illumination and environmental conditions, despite the shared underlying geometry. This paper presents ADM-GS (Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction), a framework that applies an explicit appearance decomposition to the static background to alleviate appearance entanglement across traversals. For the static background, we decompose the appearance into traversal-invariant material, representing intrinsic material properties, and traversal-dependent illumination, capturing lighting variations. Specifically, we propose a neural light field that utilizes a frequency-separated hybrid encoding strategy. By incorporating surface normals and explicit reflection vectors, this design separately captures low-frequency diffuse illumination and high-frequency specular reflections. Quantitative evaluations on the Argoverse 2 and Waymo Open datasets demonstrate the effectiveness of ADM-GS. In multi-traversal experiments, our method achieves a +0.98 dB PSNR improvement over existing latent-based baselines while producing more consistent appearance across traversals. Code will be available at https://github.com/IRMVLab/ADM-GS. ---