# Research Papers — 2026-04 · bundle page 92 of 233 > Full-text markdown of papers #4551–4600 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/92 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/91.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/93.md) ### Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification Authors: Jiawen Wen, Penglei Sun, Wenjie Zhang, Suixuan Qiu, Weisheng Xu, Xiaofei Yang, Xiaowen Chu Published: 2026-04-18 Categories: cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.16993v2 As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a "goal-driven trap", prioritizing physical geometry ("can I go?") over semantic rules ("may I go?"), frequently overlooking subtle regulatory constraints. To bridge this gap, we establish Rule-VLN, the first large-scale urban benchmark for rule-compliant navigation. Spanning a massive 29k-node environment, it injects 177 diverse regulatory categories into 8k constrained nodes across four curriculum levels, challenging agents with fine-grained visual and behavioral constraints. We further propose the Semantic Navigation Rectification Module (SNRM), a universal, zero-shot module designed to equip pre-trained agents with safety awareness. SNRM integrates a coarse-to-fine visual perception VLM framework with an epistemic mental map for dynamic detour planning. Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%. --- ### Bolzano: Case Studies in LLM-Assisted Mathematical Research Authors: Martin Balko, Jan Grebík, Pavel Hubáček, Martin Koutecký, Matěj Kripner, Václav Rozhoň, Robert Šámal, Adrián Zámečník Published: 2026-04-18 Categories: cs.CL, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2604.16989v2 We report new results on eight problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-agent LLM system. Bolzano orchestrates rounds of interaction between parallel prover agents and a verifier agent while maintaining a persistent knowledge base that is carried across rounds. Classified using the significance-autonomy taxonomy of Feng et al., six of the eight results reach the level of publishable research, and five of the eight were produced essentially autonomously by Bolzano. Our results provide evidence that LLMs can contribute meaningfully to mathematical research, complementing recent reports by Bubeck et al., Woodruff et al., and others. --- ### In-Context Learning Under Regime Change Authors: Carson Dudley, Yutong Bi, Xiaofeng Liu, Samet Oymak Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16988v1 Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models must detect the change, discard or downweight obsolete evidence, and adapt to new dynamics on the fly. Transformer-based foundation models increasingly rely on in-context learning for time series forecasting, tabular prediction, and continuous control. As these models are deployed in non-stationary environments, understanding their ability to detect and adapt to regime shifts is important. We formalize this as an in-context change-point detection problem and formally establish the existence of transformer models that solve this problem. Our construction demonstrates that model complexity, in layers and parameters, depends on the level of information available about the change-point location, from no knowledge to knowing exact timing. We validate our results with experiments on synthetic linear regression and linear dynamical systems, where trained transformers match the performance of optimal baselines across information levels. We also show that encoding and incorporating changepoint knowledge indeed improves the real-world performance of a pretrained foundation models on infectious disease forecasting and on financial volatility forecasting around Federal Open Market Committee (FOMC) announcements without retraining, demonstrating practical applicability to real-world regime changes. --- ### DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection Authors: Hongyuan Qi, Feifei Shao, Ming Li, Hehe Fan, Jun Xiao Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16987v2 The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to generalize beyond their training distributions. To address this, we propose DVAR (Debate-based Video Authenticity Reasoning), a training-free framework that reformulates video detection as a structured multi-agent forensic reasoning process. Moving beyond the paradigm of pattern matching, DVAR orchestrates a competition between a Generative Hypothesis Agent and a Natural Mechanism Agent. Through iterative rounds of cross-examination, these agents defend their respective explanations against abnormal evidence, driving a logical convergence where the truth emerges from rigorous stress-testing. To adjudicate these conflicting claims, we apply Occam's Razor through the Minimum Description Length (MDL) framework, defining an Explanatory Cost to quantify the "logical burden" of each reasoning path. Furthermore, we integrate GenVideoKB, a dynamic knowledge repository that provides high-level reasoning heuristics on generative boundaries and failure modes. Extensive experiments demonstrate that DVAR achieves competitive performance against supervised state-of-the-art methods while exhibiting superior generalization to unseen generative architectures. By transforming detection into a transparent debate, DVAR provides explicit, interpretable reasoning traces for robust video authenticity assessment. --- ### Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark Authors: Yiting Wang, Nolwenn Peyratout, Tim Brodermann, Jiahui Wang, Yusi Cao, Michele Cazzola, Elie Tarassov, Takuya Kobayashi, Abderrahim Kasmi, Guillaume Allibert, Cédric Demonceaux, Valentina Donzella et al. Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16984v1 This paper presents the report of the URVIS 2026 challenge on adverse-to-extreme panoptic segmentation. As the first challenge of its kind, it attracted 17 registered participants and 47 submissions, with 4 teams reaching the final phase. The challenge is based on the MUSES dataset, a multi-sensor benchmark for panoptic segmentation in adverse-to-extreme weather, including RGB frame camera, LiDAR, radar, and event camera data. Weighted Panoptic Quality (wPQ) is designed and adopted as the official ranking metric for fair evaluation across weather conditions. In this report, we summarise the challenge setting and benchmark results, analyse the performance of the submitted methods, and discuss current progress and remaining challenges for robust multimodal panoptic segmentation. Link: https://urvis-workshop.github.io/challenge-Muses.html --- ### A phenotype-driven and evidence-governed framework for knowledge graph enrichment and hypotheses discovery in population data Authors: Adela Bâra, Simona-Vasilica Oprea Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16982v1 Current knowledge graph (KG) construction methods are confirmatory, focusing on recovering known relationships rather than identifying novel or context-dependent nodes. This paper proposes a phenotype-driven and evidence-governed framework that shifts the paradigm toward structured hypothesis discovery and controlled KG expansion. The approach integrates graph neural networks (GNNs) for phenotype discovery, causal inference, probabilistic reasoning and large language models (LLMs) for hypothesis generation and claim extraction within a unified pipeline. The framework prioritizes relationships that are both structurally supported by data and underexplored in the literature. KG expansion is formulated as a multi-objective optimization problem, where candidate claims are jointly evaluated in terms of relevance, structural validation and novelty. Pareto-optimal selection enables the identification of non-dominated claims that balance confirmation and discovery, avoiding trivial or redundant knowledge inclusion. Experiments on heterogeneous population datasets demonstrate that the proposed framework produces more interpretable phenotypes, reveals context-dependent causal structures and generates high-quality claims that align with both data and scientific evidence. Compared to rule-based and LLM-only baselines, the method achieves the best trade-off across plausibility, novelty, validation and relevance. In retrieval-augmented settings, it significantly improves performance (Recall@5=0.98) while reducing hallucination rates (0.05), highlighting its effectiveness in grounding LLM outputs. --- ### Light-Adapted Electroretinogram and Oscillatory Potentials (LEOPs) Dataset for Autism Spectrum Disorder and Typically Developing Individuals Authors: Paul A. Constable, Dorothy A. Thompson, Irene O. Lee, Lynne Loh, Aleksei Zhdanov, Mikhail Kulyabin, Andreas Maier Published: 2026-04-18 Categories: physics.med-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16981v1 The LEOPs (Light-ERG-Oscillatory Potentials) dataset provides light-adapted (LA) electroretinogram (ERG) and Oscillatory Potentials (OPs) waveforms for typically developing Control, Autism Spectrum Disorder (ASD) and ASD + Attention Deficit Hyperactivity Disorder (ADHD) childhood and adolescent populations. The ERGs were recorded in the Right And Left eyes with skin electrodes using the handheld RETeval device at two sites in Australia and the United Kingdom. The LEOPs dataset includes 5309 single flash ERG and 4434 OPs waveforms as well as images selected from each participant showing the position of the skin electrode. The LEOPs dataset is constructed from recordings using a 9 step randomized flash series from $-0.37$ to $1.20$~$Td.s$, a 2 step at 113 and 446 $Td.s$ flash strengths (2500 Control, 1730 ASD and 451 ASD + ADHD samples), as well as the $85$~$Td.s$ (Light Adapted 3 $cd.s.m^{-2}$ (LA3)) equivalent International Society of Clinical Electrophysiology of Vision (ISCEV) Standard flash with 435 Control, 176 ASD and 37 ASD + ADHD waveform samples. Code for the stimulus is provided along with participant demographics, date and time of testing, and where available diagnostic scores for the ASD and ASD + ADHD groups, alongside iris color, electrode position with image files and time domain values for the ERG and summed values for the OPs. The repository contains excel file, exported JSON files on the patient level that are more suitable for machine learning tasks, images of electrode position for each recording and the protocol files for use with the RETeval. --- ### Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models Authors: Bruce A. Bassett, Amy Rouillard, Sitwala Mundia, Michael Cameron Gramanie, Linda Camara, Ziyaad Dangor, Shabir A. Madhi, Kajal Morar, Marlvin T. Ncube, Ismail Kalla, Haroon Saloojee Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16980v1 Background: Large language models (LLMs) are increasingly proposed for diagnostic support, but few evaluations use real-world multimodal inpatient data, particularly in low and middle-income country (LMIC) public hospitals. Methods: We conducted VALID, a retrospective evaluation of 539 multimodal inpatient cases from a tertiary public hospital in South Africa. Inputs included radiology imaging (CT, MRI, CXR) and reports, laboratory results, clinical notes, and vital signs. Expert panels adjudicated 300 cases (balanced and discordant subsets) to establish ground truth diagnoses, differentials, and reasoning. Ten multimodal LLMs generated zero-shot outputs. A calibrated three-model LLM Jury scored all outputs and routine ward diagnoses across diagnostic accuracy, differential quality, reasoning, and patient safety (>10,000 evaluations). Primary outcomes were composite scores ($S_3$, $S_4$) and win rates. Results: (i) LLM performance was tightly clustered (<15% variation) despite large cost differences; low-cost models performed comparably to top models. (ii) All LLMs significantly outperformed routine ward diagnoses on average diagnostic and safety scores. (iii) Top performance was achieved by GPT-5.1, followed by Gemini models. (vi) Adding radiology reports improved performance by 6%. (v) Diagnostic and reasoning scores were highly correlated ($ρ= 0.85$). (vi) Output rates varied (65-100%) due to input constraints. Results were robust across subsets and evaluation design. Conclusions: Across a real-world LMIC dataset, multimodal LLMs showed similar diagnostic performance despite large cost differences and outperformed routine care on average safety metrics. Affordability, robustness, and deployment constraints may outweigh marginal performance differences in LMIC settings. --- ### DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models Authors: Biao Wu, Yiwu Zhong, Meng Fang, Ling Chen Published: 2026-04-18 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.16979v1 High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples. To address these problems, data filtering is commonly used to enhance the efficiency and performance of multimodal learning, but it introduces extra computational cost because filtering models are usually trained on the same data they are meant to screen. To reduce this cost, we study DOSE, which explores whether off-the-shelf pretrained models that have never seen the target data can be used to select training samples for larger and stronger multimodal models without any task-specific training. Even without fine-tuning, these models can effectively assess text quality and image-text alignment to guide data selection. Based on this, we build a joint quality-alignment distribution and apply adaptive weighted sampling to select informative samples while maintaining long-tail diversity. This approach enhances data diversity, enabling models trained on DOSE-filtered data to match or surpass those trained on the full dataset on standard VQA and math benchmarks. Extensive experiments demonstrate its effectiveness, efficiency, and scalability. --- ### UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising Authors: Zhiyong Su, Jincan Wu, Yonghui Liu, Zheng Li, Weiqing Li Published: 2026-04-18 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.16976v1 Point cloud denoising is a fundamental and crucial challenge in real-world point cloud applications. Existing quantitative evaluation metrics for point cloud denoising methods are implemented in a supervised manner, which requires both the denoised point cloud and the corresponding ground-truth clean point cloud to compute a representative geometric distance. This requirement is highly problematic in real-world scenarios, where ground-truth clean point clouds are often unavailable. In this paper, we propose a simple yet effective unsupervised geometric distance (UGD) for real-world noisy point cloud denoising, calculated solely from noisy point clouds. The core idea of UGD is to learn a patch-wise prior model from a set of clean point clouds and then employ this prior model as the ground-truth to quantify the degradation by measuring the geometric variations of the denoised point cloud. To this end, we first learn a pristine Gaussian Mixture Model (GMM) with extracted patch-wise quality-aware features from a set of pristine clean point clouds by a patch-wise feature extraction network, which serves as the ground-truth for the quantitative evaluation. Then, the UGD is defined as the weighted sum of distances between each patch of the denoised point cloud and the learned pristine GMM model in the patch space. To train the employed patch-wise feature extraction network, we propose a self-supervised training framework through multi-task learning, which includes pair-wise quality ranking, distortion classification, and distortion distribution prediction. Quantitative experiments with synthetic noise confirm that the proposed UGD achieves comparable performance to supervised full-reference metrics. Moreover, experimental results on real-world data demonstrate that the proposed UGD enables unsupervised evaluation of point cloud denoising methods based exclusively on noisy point clouds. --- ### Convergence theory for Hermite approximations under adaptive coordinate transformations Authors: Yahya Saleh Published: 2026-04-18 Categories: math.NA, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.16975v1 Recent work has shown that parameterizing and optimizing coordinate transformations using normalizing flows, i.e., invertible neural networks, can significantly accelerate the convergence of spectral approximations. We present the first error estimates for approximating functions using Hermite expansions composed with adaptive coordinate transformations. Our analysis establishes an equivalence principle: approximating a function $f$ in the span of the transformed basis is equivalent to approximating the pullback of $f$ in the span of Hermite functions. This allows us to leverage the classical approximation theory of Hermite expansions to derive error estimates in transformed coordinates in terms of the regularity of the pullback. We present an example demonstrating how a nonlinear coordinate transformation can enhance the convergence of Hermite expansions. Focusing on smooth functions decaying along the real axis, we construct a monotone transport map that aligns the decay of the target function with the Hermite basis. This guarantees spectral convergence rates for the corresponding Hermite expansion. Our analysis provides theoretical insight into the convergence behavior of adaptive Hermite approximations based on normalizing flows, as recently explored in the computational quantum physics literature. --- ### MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models Authors: Zhaokang Liao, Yingguo Gao, Yi Yang, Yongheng Hu, Jingting Ding Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16972v1 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants have demonstrated strong performance and high training efficiency. However, GRPO-style objectives exhibit two issues on high accuracy prompts including mastered prompts (rollout accuracy =1) and majority-correct prompts (rollout accuracy in (0.5,1)). For mastered prompts, group-relative advantages vanish, yielding no training signal and unconstrained policy drift that can cause forgetting. For majority-correct prompts, the induced query weight shrinks as accuracy increases, weakening consolidation from partial correctness to mastery. To alleviate this, we propose Mastery-Consolidated Policy Optimization (MCPO), which introduces (i) a hinge-KL regularizer applied exclusively to mastered prompts to bound harmful policy drift between successive gradient steps, and (ii) a weighting mechanism that prioritizes majority-correct prompts to better allocate optimization effort. Extensive experiments across three mathematical benchmarks demonstrate that MCPO consistently improves pass@1 performance. Counter-intuitively, rather than restricting exploration, MCPO boosts pass@k metrics, indicating that mastery consolidation further catalyzes solution diversity. --- ### Hyperspectral Unmixing Hierarchies Authors: Joseph L. Garrett, P. S. Vishnu, Pauliina Salmi, Daniela Lupu, Nitesh Kumar Singh, Ion Necoara, Tor Arne Johansen Published: 2026-04-18 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.16969v1 Unmixing reveals the spatial distribution and spectral details of different constituents, called endmembers, in a hyperspectral image. Because unmixing has limited ground truth requirements, can accommodate mixed pixels, and is closely tied to light propagation, it is a uniquely powerful tool for analyzing hyperspectral images. However, spectral variability inhibits unmixing performance, the proper way to determine the number of endmembers is ambiguous, and the clarity of the endmembers degrades as more are included. Hierarchical structure is a possible solution to all three problems. Here, hierarchical unmixing is defined by imposing a hierarchical abundance sum constraint on Deep Nonnegative Matrix Factorization. Binary Linear Unmixing Tactile Hierarchies (BLUTHs) solve the hierarchical unmixing problem with a simple network architecture. Sparsity modulation unmixing growth tailors the topology of a BLUTH to each scene. The structure imposed by BLUTHs allows endmembers with varying levels of spectral contrast to be revealed, mitigating the challenge of spectral variability. The performance of BLUTHs exceeds state-of-the-art unmixing algorithms on laboratory scenes, particularly with regard to abundance estimation, while their performance remains competitive on remote sensing scenes. In addition, ocean color unmixing by BLUTHs is demonstrated on hyperspectral scenes from the HYPSO and PACE satellites. --- ### On Safety Risks in Experience-Driven Self-Evolving Agents Authors: Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, HaoHe, Wanxiang Che, Bing Qin, Ting Liu Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16968v1 Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments. Notably, experience gathered solely from benign tasks can still compromise safety in high-risk scenarios. Further analysis attributes this degradation to the execution-oriented nature of accumulated experience, which reinforces agents' tendency to act rather than refuse. In more realistic settings where agents encounter both benign and harmful tasks, refusal-related experience mitigates safety decline but induces over-refusal, revealing a fundamental safety-utility trade-off. Overall, our findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation. --- ### NaviFormer: A Deep Reinforcement Learning Transformer-like Model to Holistically Solve the Navigation Problem Authors: Daniel Fuertes, Andrea Cavallaro, Carlos R. del-Blanco, Fernando Jaureguizar, Narciso García Published: 2026-04-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.16967v1 Path planning is usually solved by addressing either the (high-level) route planning problem (waypoint sequencing to achieve the final goal) or the (low-level) path planning problem (trajectory prediction between two waypoints avoiding collisions). However, real-world problems usually require simultaneous solutions to the route and path planning subproblems with a holistic and efficient approach. In this paper, we introduce NaviFormer, a deep reinforcement learning model based on a Transformer architecture that solves the global navigation problem by predicting both high-level routes and low-level trajectories. To evaluate NaviFormer, several experiments have been conducted, including comparisons with other algorithms. Results show competitive accuracy from NaviFormer since it can understand the constraints and difficulties of each subproblem and act consequently to improve performance. Moreover, its superior computation speed proves its suitability for real-time missions. --- ### Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning Authors: Jiachen Qian Published: 2026-04-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.16966v1 The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it introduces a vulnerability: reliance on Long-term Memory (LTM). In this paper, we uncover a threat termed "Visual Inception." Unlike traditional adversarial attacks that seek immediate misclassification, Visual Inception injects triggers into user-uploaded images (e.g., lifestyle photos) that act as "sleeper agents" within the system's memory. When retrieved during future planning, these poisoned memories hijack the agent's reasoning chain, steering it toward adversary-defined goals (e.g., promoting high-margin products) without prompt injection. To mitigate this, we propose CognitiveGuard, a dual-process defense framework inspired by human cognition. It consists of a System 1 Perceptual Sanitizer (diffusion-based purification) to cleanse sensory inputs and a System 2 Reasoning Verifier (counterfactual consistency checks) to detect anomalies in memory-driven planning. Extensive experiments on a mock e-commerce agent environment demonstrate that Visual Inception achieves about 85% Goal-Hit Rate (GHR), while CognitiveGuard reduces this risk to around 10% with configurable latency trade-offs (about 1.5s in lite mode to about 6.5s for full sequential verification), without quality degradation under our setup. --- ### Multi-stage Planning for Multi-target Surveillance using Aircrafts Equipped with Synthetic Aperture Radars Aware of Target Visibility Authors: Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar, Juan José Navarro-Corcuera, Narciso García Published: 2026-04-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.16962v1 Generating trajectories for synthetic aperture radar (SAR)-equipped aircraft poses significant challenges due to terrain constraints, and the need for straight-flight segments to ensure high-quality imaging. Related works usually focus on trajectory optimization for predefined straight-flight segments that do not adapt to the target visibility, which depends on the 3D terrain and aircraft orientation. In addition, this assumption does not scale well for the multi-target problem, where multiple straight-flight segments that maximize target visibility must be defined for real-time operations. For this purpose, this paper presents a multi-stage planning system. First, the waypoint sequencing to visit all the targets is estimated. Second, straight-flight segments maximizing target visibility according to the 3D terrain are predicted using a novel neural network trained with deep reinforcement learning. Finally, the segments are connected to create a trajectory via optimization that imposes 3D Dubins curves. Evaluations demonstrate the robustness of the system for SAR missions since it ensures high-quality multi-target SAR image acquisition aware of 3D terrain and target visibility, and real-time performance. --- ### Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering Authors: Tianyi Chen, Haobo Wang, Kai Tang, Gengyu Lyu, Tianlei Hu, Gang Chen, Hong Ma, Meixiang Xiang Published: 2026-04-18 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.16959v1 Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining robustness against missing views. However, prevalent Euclidean-based methods suffer from a geometric mismatch when modeling real-world data with intrinsic hierarchies, leading to semantic blurring where representations drift towards spatially proximal but semantically distinct neighbors. To bridge this gap, we propose HERL, a Hyperbolic Enhanced Representation Learning framework for IMVC. Operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning. Specifically, we design a dual-constraint hyperbolic contrastive mechanism optimizing: an angular-based loss to preserve semantic identity via directional alignment, and a distance-based loss to enforce hierarchical compactness. Furthermore, a hyperbolic prototype head is introduced to rectify global structural drift by aligning cross-view hierarchy-aware prototype distributions. Consequently, HERL disentangles fine-grained semantic correlations to sharpen cluster boundaries and imposes geometric constraints to rectify the data recovery process. Extensive experimental results demonstrate that HERL consistently outperforms state-of-the-art approaches. --- ### Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation Authors: Minyan Luo, Yuxin Zhang, Yifei Li, Xincan Wang, Fuzhang Wu, Tong-Yee Lee, Oliver Deussen, Weiming Dong Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16958v1 Narrative-driven product photography has become a prevalent paradigm in modern marketing, as coherent visual storytelling helps convey product value and establishes emotional engagement with consumers. However, existing image generation methods do not support structured narrative planning or cross-panel coordination, often resulting in weak storytelling and visual incoherence. In practice, narrative product photography is commonly presented as multi-grid collages, where multiple views or scenes jointly communicate a product narrative. To ensure visual consistency across grids and aesthetic harmony of the overall composition, we generate the collage as a single unified image rather than composing independently synthesized panels. We propose a self-reasoning agentic framework for narrative product grid collage generation. Given a product packshot and its name, the system first constructs a Product Narrative Framework that explicitly represents the product's identity, usage context, and situational environment, and translates it into complementary grids governed by a shared visual style. Constraint-aware prompts are then compiled and fed to a generation model that synthesizes the collage jointly. The generated output is evaluated on both content validity and photography quality, with explicit gates determining whether to proceed or refine. When evaluation fails, the system performs failure attribution and applies targeted refinement, enabling progressive improvement through iterative self-reflection. Experiments demonstrate that our framework consistently improves aesthetic quality, narrative richness, and visual coherence, compared to direct prompting baselines. --- ### Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon Authors: Sai Vegasena Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16957v1 We present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Silicon, enabling 128K-context inference for Llama 3.1 70B on a single 64GB consumer Mac -- a configuration impossible with all existing inference frameworks. Open-TQ-Metal quantizes the KV cache to int4 on the fly and computes attention directly on the compressed representation via custom Metal compute shaders, eliminating all intermediate dequantization matrices. Across 330 experiments spanning two model families (Gemma 4 31B and Llama 3.1 70B), the fused sdpa_int4 kernel achieves 48x attention speedup at 128K context over the dequantize-then-attend baseline, reduces KV cache memory from 40 GB to 12.5 GB (3.2x compression), and maintains identical top-1 token predictions to FP16 inference. We further provide the first cross-architecture analysis of KV cache quantization methods, revealing that the attention scale factor -- not model size -- determines whether angular quantization schemes like PolarQuant succeed or fail, with Gemma 4's attn_scale=1.0 amplifying directional error 25-100x more than Llama's standard 1/sqrt(d) scaling. --- ### Diagnostic-Guided Longitudinal Modeling for Forecasting Retinal Atrophy Progression Authors: Liyin Chen, Souvick Mukherjee, Ines Maria De Carvalho Lains, Nazlee Zebardast, Mengyu Wang, Tobias Elze, Jason I. Comander Published: 2026-04-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16955v3 Stochastic generative models are increasingly used for longitudinal imaging, but their added complexity may provide limited benefit when predictable disease-related change is small relative to technical variability. We treat model-class selection (stochastic vs deterministic) as an empirical step determined by a task-adaptive diagnostic. For a longitudinal image prediction task complicated by irregular follow-up, acquisition variability, and device heterogeneity, the diagnostic asks whether inter-visit image change is driven by time-dependent disease progression signals or time-independent acquisition variability. If a stochastic approach fails to yield useful predictive diversity, a more parsimonious, deterministic model class is selected. We applied this strategy to fundus autofluorescence (FAF) future image prediction. Applied to a heterogeneous Optos FAF archive (24,335 images from 9,708 eyes), the diagnostic indicated that global inter-visit FAF change was weakly associated with elapsed time, and source-anchored stochastic configurations produced little endpoint-resolvable sample variation. Guided by the diagnostic, we developed Temporal Retinal U-Net (TRU), a deterministic single-pass predictor conditioned on irregular imaging history and prediction horizon. Evaluated on a held-out cohort and two independent zero-shot transfer cohorts spanning rare-disease and cross-vendor shift, TRU achieved the strongest overall performance among the evaluated classical and deep-learning comparators on image-level and eye-specific progression measures, with lower precision in the smaller cross-vendor cohort. These findings support a diagnostic-guided strategy for longitudinal image prediction and demonstrate an example where deterministic predictions outperform stochastic models. --- ### Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction Authors: Liyin Chen, Nazlee Zebardast, Mengyu Wang, Tobias Elze, Jason I. Comander Published: 2026-04-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16955v2 Predicting disease progression from longitudinal imaging is useful for clinical decision making and trial design. Recent methods have moved toward increasing generative complexity, but the conditions under which this complexity is necessary remain unclear. We propose that generative complexity should match the entropy of the predictable component of a task's conditional posterior, with training-inference input alignment required in all regimes. Two model-light measurements, a task-entropy analysis on raw image pairs and a posterior-concentration analysis on a stochastic model, let practitioners assess the complexity a task warrants before committing to a modeling framework. We validated this framework on a fundus autofluorescence (FAF) dataset by contrasting five conditioning configurations, sharing one architecture and training set, spanning standard conditional diffusion, inference-aligned stochastic training, and deterministic regression. Training-inference alignment produced large gains (delta-SSIM +0.082, SSIM +0.086, both p < 0.001), while the choice among aligned frameworks produced no clinically meaningful difference across evaluated metrics. Across two FAF platforms, inter-visit change was dominated by time-invariant acquisition variability rather than disease progression, and the stochastic models' posteriors collapsed to an effective point, explaining the framework equivalence. We trained a deterministic Temporal Retinal U-Net (TRU) and evaluated it on 28,899 eyes across three manufacturers and two modalities (two FAF platforms and en-face SLO), with three independent cohorts evaluated zero-shot. TRU matched or exceeded three published baselines on delta-SSIM, SSIM, and PSNR. These findings show that when disease progression is slow compared with acquisition variability, a deterministic regression model matches or outperforms more complex stochastic alternatives. --- ### TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation Authors: Jinshuo Liu, Bingtao Ma, Junlin Su, Guanyuan Pan, Beining Wu, Cheng Yang, Jiaxuan Lu, Chenggang Yan, Shuai Wang Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16954v2 Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a \textbf{T}opology-Aware Learning with \textbf{S}emantic \textbf{M}amba for Category-Level \textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation of the point cloud, which is integrated into local geometry features and enables robust category-level structural representation. Simultaneously, we propose a Mamba-based Global Semantic Aggregator that injects semantics priors into keypoints to enhance their expressiveness and leverages multiple TwinMamba blocks to model long-range dependencies for more effective global feature aggregation. Extensive experiments on three benchmark datasets (REAL275, CAMERA25, and HouseCat6D) demonstrate that TSM-Pose outperforms existing state-of-the-art methods. --- ### Hybrid Quantum Neural Networks for Enhanced Breast Cancer Thermographic Classification: A Novel Quantum-Classical Integration Approach Authors: Riza Alaudin Syah, Irwan Alnarus Kautsar, Gunawan Witjaksono, Haza Nuzly bin Abdull Hamed Published: 2026-04-18 Categories: quant-ph, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16953v1 Breast cancer diagnosis through thermographic image analysis remains a critical challenge in medical AI, with classical deep learning approaches facing limitations in complex thermal pattern classification tasks. This paper presents a novel Hybrid Quantum Neural Network (HQNN) architecture that integrates quantum computing principles with classical convolutional neural networks for enhanced breast cancer classification. Our approach employs parameterized quantum circuits with multi-head attention mechanisms for quantum-aware feature encoding, coupled with classical convolutional layers for comprehensive pattern recognition. The quantum component utilizes a 4qubit variational circuit with strongly entangling layers, while the classical component incorporates advanced attention mechanisms for feature fusion. Experimental validation on breast cancer thermographic data demonstrates substantial performance improvements over state-of-the-art classical architectures, with the quantum-enhanced approach exhibiting superior convergence dynamics and enhanced feature representation capabilities. Our findings provide evidence for quantum advantage in medical image classification through classical simulation, establishing a framework for quantum-classical hybrid systems in healthcare applications. The methodology addresses key challenges in quantum machine learning deployment while maintaining computational feasibility on near-term quantum devices. --- ### Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder Authors: Bowen Peng, Yongxiang Liu, Jie Zhou, Xiaodong Chen, Tianpeng Liu, Xiaogang Yu, Li Liu Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16952v1 Learning robust representations across extremely heterogeneous modalities remains a fundamental challenge in multi-modal vision. As a critical and profound instantiation of this challenge, high-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations; its potential is severely hindered by the Heterogeneity-Resolution Paradox: finer spatial scales drastically amplify the physical divergence between complex radar geometries and non-homologous optical textures. Consequently, migrating medium-resolution-oriented rigid alignment paradigms to HR scenarios triggers either severe feature suppression to force equivalence, or feature contamination driven by extreme epistemic uncertainty. Both extremes inevitably culminate in profound representation degradation and negative transfer. To overcome this bottleneck, we propose CoDe-MAE, pioneering a \textit{better synergy with less alignment} philosophy. First, Optical-anchored Knowledge Distillation (OKD) implicitly regularizes SAR's speckle noise by mapping it into a pure semantic manifold. Building on this, Conditioned Contrastive Learning (CCL) utilizes a gradient buffering mechanism to align shared consensus while safely preserving divergent physical signatures. Concurrently, Cross-Modal Degraded Reconstruction (CDR) deliberately strips non-homologous spectral pseudo-features, truncating the inherently ill-posed mapping to capture true structural invariants. Extensive analyses validate our theoretical claims. Pretrained on 1M samples, CoDe-MAE demonstrates remarkable data efficiency, successfully preventing representation degradation and establishing new state-of-the-art performance across diverse single- and bi-modal downstream tasks, substantially outperforming foundation models scaled on vastly larger datasets. --- ### AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction Authors: Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16950v1 Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, our method improves edge-level exact-match F1 by 0.152 and yields a precision gain of 0.208 on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge by 3.81 percent, in Search by 5.32 percent, and in Recommendation by 7.89 percent, supporting the practical value of AutoPKG in production. --- ### L1 Regularization Paths in Linear Models by Parametric Gaussian Message Passing Authors: Yun-Peng Li, Hans-Andrea Loeliger Published: 2026-04-18 Categories: cs.LG, eess.SP, stat.ME arXiv: https://arxiv.org/abs/2604.16949v1 The paper considers the computation of L1 regularization paths in a state space setting, which includes L1 regularized Kalman smoothing, linear SVM, LASSO, and more. The paper proposes two new algorithms, which are duals of each other; the first algorithm applies to L1 regularization of independent variables while the second applies to L1 regularization of dependent variables. The heart of the proposed algorithms is parametric Gaussian message passing (i.e., Kalman-type forward-backward recursions) in the pertinent factor graphs. The proposed methods are broadly applicable, they (usually) require only matrix multiplications, and their complexity can be competitive with prior methods in some cases. --- ### Structured 3D-SVD: A Practical Framework for the Compression and Reconstruction of Biological Volumetric Images Authors: Mario Aragonés Lozano, Oscar Romero, Antonio León Published: 2026-04-18 Categories: eess.IV, cs.CV, math.NA arXiv: https://arxiv.org/abs/2604.16947v1 This work introduces Structured 3D-SVD as a practical framework for the reconstruction, compression, and analysis of biological volumetric data. Inspired by the logic of matrix singular value decomposition (SVD), the proposed approach represents third-order volumetric data in the spatial domain and supports progressive reconstruction through ordered quasi-singular coeffients. The experimental evaluation was carried out on two biological volumetric datasets: one full-volume scan of a fish and another of a brain. The results show that Structured 3D-SVD achieves reconstruction quality close to that of Tucker decomposition while requiring shorter computation times and outperforms canonical polyadic decomposition (CPD) in both accuracy and runtime. In addition, a progressive reconstruction analysis shows that relatively low truncation levels are sufficient to preserve the main volumetric structures, while higher truncation levels lead to more detailed reconstructions. --- ### MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation Authors: Bo Li, Ningyuan Deng, Tianyu Dong, Shaobo Wang, Shaolin Zhu, Lijie Wen Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16943v1 Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This often leads to a modality gap between visual text inputs and textual inputs/outputs for image translation. Existing methods, primarily relying on instruction fine-tuning, risk parameter redundancy of pre-trained knowledge, hindering generalization performance. To address this, we introduce modality neuron-aware fine-tuning (MNAFT), a novel approach that takes advantage of the specialized roles of individual neurons within MLLMs for enhanced image translation. MNAFT identifies language-agnostic and language-specific neurons in both vision and language modules through an instruction-driven activation analysis, evaluating their importance in various translation tasks. We then perform selective fine-tuning, updating only the parameters of language-specific and language-agnostic neurons within the selected layers relevant to the target task, while preserving the knowledge encoded in other neurons and layers. Our extensive experiments on multiple benchmarks demonstrate that MNAFT significantly outperforms state-of-the-art image translation methods, including cascaded models, standard full fine-tuning, and parameter-efficient tuning techniques. Furthermore, we provide comprehensive analysis, including visualizations of neuron activations and clustering patterns, to offer insights into the roles of different neuron groups in mediating cross-modal understanding and facilitating accurate language-specific translation. --- ### MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution Authors: Dao Sy Duy Minh, Tran Chi Nguyen, Trung Kiet Huynh, Pham Phu Hoa, Nguyen Lam Phu Quy, Vu Nguyen Published: 2026-04-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.16941v1 We present MEMRES, an agentic system for Python dependency resolution that introduces a multi-level confidence cascade where the LLM serves as the last resort. Our system combines: (1) a Self-Evolving Memory that accumulates reusable resolution patterns via tips and shortcuts; (2) an Error Pattern Knowledge Base with 200+ curated import-to-package mappings; (3) a Semantic Import Analyzer; and (4) a Python 2 heuristic detector resolving the largest failure category. On HG2.9K using Gemma-2 9B (10 GB VRAM). MEMRES resolves 2503 of 2890 (86.6%, 10-run average) snippets, combining intra-session memory with our confidence cascade for the remainder. This already exceeds PLLM's 54.7% overall success rate by a wide margin. --- ### D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation Authors: Junlin Li, Shuangyong Song, Guodong Du, Ngai Wong, Xuebo Liu, Yongxiang Li, Min Zhang, Jing Li, Xuelong Li Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16940v1 Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single pre-trained LLM with multiple compressed delta weights. However, existing methods fail on models fine-tuned with largescale datasets. We find that larger SFT data scale amplifies delta parameter magnitude, singular values, and entropy, exacerbating compression errors. To tackle this, we propose DQRELO (Delta Compression via Quantization and Residual Low-Rank), a novel training- and data-free delta compression method. It combines coarse-grained one-bit quantization to capture the dominant structure of the delta, followed by compensated residual low-rank approximation to recover fine-grained details from the smaller residual error. Experiments on various LLMs spanning dense and MoE architectures across multiple domains under this challenging setting demonstrate that DQRELO outperforms existing methods. Moreover, we establish key design principles for delta compression through extensive empirical analysis, demonstrating how task difficulty, architecture, and layer positioning create predictable patterns that can guide optimal compression strategies in production systems. --- ### No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs Authors: Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang, Hsin-Hsi Chen Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16937v2 Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial. --- ### Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification Authors: Linyue Zhang, Wenyi Zeng, Zicheng Pan, Yongsheng Gao, Changming Sun, Jun Hu, Lixian Liu, Weichuan Zhang, Tuo Wang Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16936v2 Feature reconstruction techniques are widely applied for few-shot fine-grained image classification (FSFGIC). Our research indicates that one of the main challenges facing existing feature-based FSFGIC methods is how to choose the size of the receptive field to extract feature descriptors (including spatial and frequency feature descriptors) from different category input images, thereby better performing the FSFGIC tasks. To address this, an adaptive receptive field-based spatial-frequency feature reconstruction network (ARF-SFR-Net) is proposed. The designed ARF-SFR-Net has the capability to adaptively determine receptive field sizes for obtaining spatial and frequency features, and effectively fuse them for reconstruction and FSFGIC tasks. The designed ARF-SFR-Net can be easily embedded into a given episodic training mechanism for end-to-end training from scratch. Extensive experiments on multiple FSFGIC benchmarks demonstrate the effectiveness and superiority of the proposed ARF-SFR-Net over state-of-the-art approaches. The code is available at: https://github.com/ICL-SUST/ARF-SFR-Net. --- ### LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies Authors: Alexis Carrillo, Salvatore Citraro, Ali Aghazhadeh Ardebili, Enrique Taietta, Giulio Rossetti, Emilio Ferrara, Giuseppe Alessandro Veltri, Massimo Stella Published: 2026-04-18 Categories: cs.AI, cs.CY, cs.HC, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2604.16935v1 Scarce longitudinal evidence examines LLMs' persuasiveness and humanness along time-evolving psychological frameworks. We introduce Talk2AI, a longitudinal framework quantifying psycho-social, reasoning and affective dimensions of LLMs' persuasiveness about polarizing societal topics. In a four-way longitudinal setup, Talk2AI's 770 participants engaged in structured conversations with one of four leading LLMs on topics like climate change, social media misinformation, and math anxiety. This produced 3,080 conversations over 60,000 turns. After each wave, participants reported conviction in their initial topic stance, perceived opinion change, LLM's perceived humanness, a self-donation to the topic and a textual explanation. Feedback time series showed longitudinal inertia in convictions, indicating some human anchoring to initial opinions even after repeated exposure to AI-generated arguments. Interestingly, NLP analyses revealed that both humans and LLMs relied on fallacious reasoning in 1 conversational quip every 6, countering the ``LLMs as superior systems" stereotype behind LLMs' cognitive surrender. LLMs' perceived humanness was most learnable from sociodemographic, psychological and engagement features ($R^2=0.44$), followed by opinion change ($R^2=0.34$), conviction ($R^2=0.26$) and personal endowment ($R^2=0.24$). Crucially, explainable AI (XAI) indicated: (i) the presence of individuals more susceptible to LLM-based opinion changes; (ii) psychological susceptibility to LLM-convincing consisted of having more trust in LLMs, being more agreeable and extraverted and with a higher need for cognition. A multiverse approach with mixed-effects models confirmed XAI results, alongside strong individual differences. Talk2AI provides a grounded framework and evidence for detecting how GenAI can influence human opinions via multiple psycho-social pathways in AI-human digital platforms. --- ### Neighbor Embedding for High-Dimensional Sparse Poisson Data Authors: Noga Mudrik, Adam S. Charles Published: 2026-04-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.16932v1 Across many scientific fields, measurements often represent the number of times an event occurs. For example, a document can be represented by word occurrence counts, neural activity by spike counts per time window, or online communication by daily email counts. These measurements yield high-dimensional count data that often approximate a Poisson distribution, frequently with low rates that produce substantial sparsity and complicate downstream analysis. A useful approach is to embed the data into a low-dimensional space that preserves meaningful structure, commonly termed dimensionality reduction. Yet existing dimensionality reduction methods, including both linear (e.g., PCA) and nonlinear approaches (e.g., t-SNE), often assume continuous Euclidean geometry, thereby misaligning with the discrete, sparse nature of low-rate count data. Here, we propose p-SNE (Poisson Stochastic Neighbor Embedding), a nonlinear neighbor embedding method designed around the Poisson structure of count data, using KL divergence between Poisson distributions to measure pairwise dissimilarity and Hellinger distance to optimize the embedding. We test p-SNE on synthetic Poisson data and demonstrate its ability to recover meaningful structure in real-world count datasets, including weekday patterns in email communication, research area clusters in OpenReview papers, and temporal drift and stimulus gradients in neural spike recordings. --- ### Playing Psychic: Using Thought Trees to Predict Reasoning Models Accuracy on Coding Tasks Authors: Jiaxin Fang, Runyuan He, Sahil Bhatia, Neel Gajare, Alvin Cheung Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16931v1 Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during inference to generate intermediate reasoning traces before producing a final answer. However, current evaluations primarily rely on competitive programming benchmarks, which may not capture the full range of reasoning abilities. In this work, we perform a systematic study of frontier reasoning models to understand their performance on real-world coding benchmarks. To gain more insights into the performance of such models, we devise a programmatic way to {\em automatically generate} coding tasks of arbitrary difficulty and structure from existing benchmarks. Using this framework, our analysis reveals that the structure of a reasoning trace, not just its contents, is a strong predictor of correctness. Motivated by this, we propose structured thought-trees as means to represent reasoning traces. To illustrate their use, we train a lightweight classifier on features extracted from thought-trees to predict trace correctness, and demonstrate that flagging and retrying structurally anomalous traces based on the extracted features yields consistent gains at lower complexity levels. --- ### CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering Authors: Xiyin Zeng, Yi Lu, Hao Wang Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16930v1 Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based on examples. However, unstable routing can lead to inconsistent expert selection in the same question type, while overly stable routing may reduce flexibility. To address this, we propose Concept-Guided Routing framework (CoGR-MoE), which incorporates semantics of the answer options to guide expert selection in the training phase. Next, option features are used to reweight the selected experts, producing discriminative representations for each candidate option. These option-level representations are further used for option comparison and optimized via contrastive learning. The experimental results indicate that CoGR-MoE delivers strong performance across multiple VQA tasks, demonstrating the effectiveness of our approach. --- ### MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning Authors: Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16929v1 The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and integration of quantitative research findings. However, Large Language Models (LLMs) frequently exhibit severe hallucinations, which significantly undermine the reliability of automated scientific document understanding systems. To address this problem, we propose MeasHalu, a novel framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization. We first present a fine-grained taxonomy of measurement-specific hallucinations, categorizing errors across quantities, units, modifiers, and relations. Our approach incorporates a two-stage reasoning-aware fine-tuning strategy using augmented scientific data and process-based supervision. Furthermore, we introduce a progressive reward curriculum designed to penalize specific hallucination types, significantly improving extraction faithfulness. Experimental results demonstrate that MeasHalu substantially reduces hallucination rates and improves overall accuracy on the MeasEval benchmark. This work provides a targeted solution to a key bottleneck in automated scientific knowledge extraction, facilitating more trustworthy and scalable machine-assisted scientific literature analysis. --- ### Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts Authors: Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun Published: 2026-04-18 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.16926v3 Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that the evaluated TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation and optimization-free methods showing greater stability. For the evaluated EEG foundation models and representative TTA methods, these findings highlight the limitations of directly applying existing TTA techniques to EEG and underscore the need for domain-specific adaptation strategies. --- ### Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts Authors: Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun Published: 2026-04-18 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.16926v2 Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that standard TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation. In contrast, optimization-free methods demonstrate greater stability and more reliable improvements. These findings highlight the limitations of existing TTA techniques in EEG, provide guidance for future development, and underscore the need for domain-specific adaptation strategies. --- ### Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning Authors: Yichao Liu, Zongru Shao, Yueyang Teng, Junwen Guo Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16925v3 Cross-dose denoising for low-dose positron emission tomography (LDPET) has been proposed to address the limited generalization of models trained at a single noise level. However, neural networks trained on a specific dose level often fail to generalize to other dose conditions due to variations in noise magnitude and statistical properties. Conventional "one-size-for-all" models attempt to mitigate this variability but tend to learn averaged representations across noise levels, resulting in degraded performance. In this work, we analyze this limitation and show that standard training formulations implicitly optimize an expectation over heterogeneous noise distributions, causing the network to learn an averaged denoising mapping that cannot accurately model dose-specific noise characteristics. We propose a unified residual noise learning framework that estimates noise directly from low-dose PET images rather than predicting full-dose images. Experiments on large-scale multi-dose PET datasets from two medical centers demonstrate that the proposed method outperforms the "one-size-for-all" model, individual dose-specific U-Net models, and dose-conditioned approaches, achieving improved denoising performance. These results indicate that residual noise learning effectively mitigates the averaging effect and enhances generalization for cross-dose PET denoising. --- ### Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy Authors: Junxi Wu, Kailin Huang, Dongjian Hu, Bin Chen, Hao Wu, Shu-Tao Xia, Changliang Zou Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16923v1 Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern Large Language Models (LLMs) undergo alignment (including fine-tuning and preference tuning), leaving a measurable distributional imprint. We theoretically derive this imprint by abstracting the alignment process as a sequence of constrained optimization steps, showing that the log-likelihood ratio can naturally decompose into implicit instructional biases and preference rewards. We refer to this quantity as the Alignment Imprint. Furthermore, to mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD), a standardized information-weighted statistic based on alignment imprint. We provide statistical guarantee that alignment-based statistics dominate Fast-DetectGPT in performance. We also theoretically show that LAPD strictly improves the unweighted alignment scores when the aligned and base models are close in distribution. Extensive experiments show that LAPD achieves an improvement 45.82% relative to the strongest existing baselines, yielding large and consistent gains across all settings. --- ### ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis Authors: Hao Wang, Jindong Han, Wei Fan, Hao Liu Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16922v3 Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent. --- ### Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning Authors: Yingzhi Xia, Setthakorn Tanomkiattikun, Liangli Zhen, Zaiwang Gu Published: 2026-04-18 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.16919v1 Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but they are susceptible to local minima and noise overfitting. Although DMs can provide strong priors for Bayesian approaches, enforcing measurement consistency during the denoising process leads to manifold infeasibility issues. We propose Noise-space Hamiltonian Monte Carlo (N-HMC), a posterior sampling method that treats reverse diffusion as a deterministic mapping from initial noise to clean images. N-HMC enables comprehensive exploration of the solution space, avoiding local optima. By moving inference entirely into the initial-noise space, N-HMC keeps proposals on the learned data manifold. We provide a comprehensive theoretical analysis of our approach and extend the framework to a noise-adaptive variant (NA-NHMC) that effectively handles IPs with unknown noise type and level. Extensive experiments across four linear and three nonlinear inverse problems demonstrate that NA-NHMC achieves superior reconstruction quality with robust performance across different hyperparameters and initializations, significantly outperforming recent state-of-the-art methods. The code is available at https://github.com/NA-HMC/NA-HMC. --- ### Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning Authors: Weiyu Ma, Yongcheng Zeng, Yan Song, Xinyu Cui, Jian Zhao, Xuhui Liu, Mohamed Elhoseiny Published: 2026-04-18 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.16918v1 Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm. However, these methods discard all collected trajectories after a single gradient update, resulting in poor sample efficiency, particularly wasteful for agentic tasks where multi-turn environment interactions are expensive. While Experience Replay drives sample efficiency in classic RL by allowing agents to reuse past trajectories and prioritize informative ones, directly applying Prioritized Experience Replay (PER) to LLMs fails. The rapid policy evolution of billion-parameter models renders stored priorities stale, causing old high-priority trajectories to dominate sampling long after they have become uninformative. We propose Freshness-Aware PER, which addresses this priority staleness problem by augmenting any PER-based priority with a multiplicative exponential age decay grounded in effective sample size analysis. To the best of our knowledge, Freshness-Aware PER is the first work to successfully apply PER to LLM/VLM reinforcement learning. We evaluate on eight multi-step agentic, reasoning, and math competition tasks with 0.5B, 3B, and 7B models. Freshness-Aware PER significantly outperforms on-policy baselines, achieving +46% on NQ Search, +367% on Sokoban, and +133% on VLM FrozenLake, while standard PER without age decay consistently degrades performance. Our code is publicly available at https://github.com/Vision-CAIR/Freshness-Aware-PER. --- ### x1: Learning to Think Adaptively Across Languages and Cultures Authors: Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Yichong Huang, Zekun Yuan, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Dandan Tu, Bing Qin Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16917v1 Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work, we introduce x1, a family of reasoning models that can adaptively reason in an advantageous language on a per-instance basis. To isolate the effect of reasoning-language choice, x1 is constructed without expanding the model's knowledge boundaries and is trained by contrasting linguistically distinct reasoning trajectories for the same input. Our extensive experiments demonstrate the benefits of adaptive multilingual reasoning across multilingual mathematical reasoning and culturally grounded tasks. Moreover, our results challenge a simplistic view of scaling laws: while scaling reduces cross-lingual disparities in procedural domains such as math reasoning, it does not eliminate the advantages of culture-associated languages in culturally grounded tasks, as we empirically show that such reasoning enables more efficient and accurate cultural knowledge recall. Overall, our findings establish language choice as a functional component of reasoning, with implications for building more generalist and globally competent reasoning models. --- ### When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints Authors: Yuheng Chen, Zhiyu Wu, Bowen Cheng, Yihang Wu, Tetsuro Takahashi Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16916v2 We identify and systematically characterize a class of task-structural alignment failures in large language models (LLMs): even when the harmful intent remains unchanged, changing the task presentation and output constraints can substantially alter model safety behavior. Specifically, when a harmful request is reformulated as a forced-choice multiple-choice question (MCQ) in which all options are harmful and no refusal option is provided, some models that refuse the equivalent open-ended query instead select, prefer, or justify a harmful option. We evaluate 14 proprietary and open-source models on a bilingual Chinese-English human-authored dataset covering five harm categories, together with 900 model-generated Chinese adversarial MCQs. On human-authored data, attack success rate (ASR) increases sharply as prompts shift from open-ended queries to explicit forced-choice formats, typically peaking under intermediate levels of choice constraint. Model-generated Chinese MCQs further weaken or eliminate the recovery regime observed on human-authored data, driving ASR close to saturation for multiple models. The observed transfer patterns are consistent with stronger generators producing more difficult or boundary-adjacent MCQs, although other properties of the generated inputs may also contribute. We also find that adding an explicit refusal option or a safety preamble substantially reduces ASR for several high-capability models, often to near-zero levels, although their effectiveness varies across target models. These findings suggest that safety evaluations centered on open-ended generation may underestimate risks in structured deployment settings, and that task structure should be treated as an important and diagnosable dimension of safety evaluation and alignment training. --- ### When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints Authors: Yuheng Chen, Zhiyu Wu, Bowen Cheng, Tetsuro Takahashi Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16916v1 Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making tasks, such as multiple-choice questions (MCQs), where abstention is discouraged or unavailable. We identify a systematic failure mode in this setting: reformulating harmful requests as forced-choice MCQs, where all options are unsafe, can systematically bypass refusal behavior, even in models that consistently reject equivalent open-ended prompts. Across 14 proprietary and open-source models, we show that forced-choice constraints sharply increase policy-violating responses. Notably, for human-authored MCQs, violation rates follow an inverted U-shaped trend with respect to structural constraint strength, peaking under intermediate task specifications, whereas MCQs generated by high-capability models yield near-saturation violation rates across constraints and exhibit strong cross-model transferability. Our findings reveal that current safety evaluations substantially underestimate risks in structured task settings and highlight constrained decision-making as a critical and underexplored surface for alignment failures. --- ### KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains Authors: Parthaw Goswami, Jaynto Goswami Deep Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16915v1 Retrieval augmented generation (RAG) has transformed text based question answering, yet its extension to visual domains remains hindered by fundamental challenges: bridging the modality gap between image queries and text heavy knowledge bases, constructing semantically meaningful visual knowledge bases, performing multihop reasoning over retrieved images, and verifying that generated answers are faithfully grounded in visual evidence. We present KIRA (Knowledge Intensive Image Retrieval and Reasoning Architecture), a unified five stage framework that addresses ten core problems in visual RAG for specialized domains. KIRA introduces: (1) hierarchical semantic chunking with DINO based region detection for multi granularity knowledge base construction, (2) domain adaptive contrastive encoders with fewshot adaptation for rare visual concepts, (3) dualpath crossmodal retrieval with chainOfThought query expansion, (4) chainOfRetrieval for multihop visual reasoning with temporal and multiview support, and (5) evidence conditioned grounded generation with posthoc hallucination verification. We also propose DOMAINVQAR, a benchmark suite that evaluates visual RAG along three axes (retrieval precision, reasoning faithfulness, and domain correctness) going beyond standard recall metrics. Experiments across four specialized domains (medical Xray, circuit diagrams, satellite imagery, and histopathology) with a progressive six variant ablation demonstrate that KIRA achieves 0.97 retrieval precision, 1.0 grounding scores, and 0.707 domain correctness averaged across domains, while the ablation reveals actionable insights about when each component helps and when components introduce precision diversity tradeoffs that must be managed. Code will be released upon acceptance. --- ### Unified Ultrasound Intelligence Toward an End-to-End Agentic System Authors: Chen Ma, Yunshu Li, Junhu Fu, Shuyu Liang, Yuanyuan Wang, Yi Guo Published: 2026-04-18 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.16914v2 Clinical ultrasound analysis demands models that generalize across heterogeneous organs, views, and devices, while supporting interpretable workflow-level analysis. Existing methods often rely on task-wise adaptation, and joint learning may be unstable due to cross-task interference, making it hard to deliver workflow-level outputs in practice. To address these challenges, we present USTri, a tri-stage ultrasound intelligence pipeline for unified multi-organ, multi-task analysis. Stage I trains a universal generalist USGen on different domains to learn broad, transferable priors that are robust to device and protocol variability. To better handle domain shifts and reach task-aligned performance while preserving ultrasound shared knowledge, Stage II builds USpec by keeping USGen frozen and finetuning dataset-specific heads. Stage III introduces USAgent, which mimics clinician workflows by orchestrating USpec specialists for multi-step inference and deterministic structured reports. On the FMC\_UIA validation set, our model achieves the best overall performance across 4 task types and 27 datasets, outperforming state-of-the-art methods. Moreover, qualitative results show that USAgent produces clinically structured reports with high accuracy and interpretability. Our study suggests a scalable path to ultrasound intelligence that generalizes across heterogeneous ultrasound tasks and supports consistent end-to-end clinical workflows. The code is publicly available at: https://github.com/MacDunno/USTri. ---