# Research Papers — 2026-03 · bundle page 30 of 243 > Full-text markdown of papers #1451–1500 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/30 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/29.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/31.md) ### Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling Authors: Ruixing Zhang, Hanzhang Jiang, Leilei Sun, Liangzhe Han, Jibin Wang, Weifeng Lv Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26610v1 Mobile devices continuously interact with cellular base stations, generating massive volumes of signaling records that provide broad coverage for understanding human mobility. However, such records offer only coarse location cues (e.g., serving-cell identifiers) and therefore limit their direct use in applications that require high-precision GPS trajectories. This paper studies the Sig2GPS problem: reconstructing GPS trajectories from cellular signaling. Inspired by domain experts often lay the signaling trace on the map and sketch the corresponding GPS route, unlike conventional solutions that rely on complex multi-stage engineering pipelines or regress coordinates, Sig2GPS is reframed as an image-to-video generation task that directly operates in the map-visual domain: signaling traces are rendered on a map, and a video generation model is trained to draw a continuous GPS path. To support this paradigm, a paired signaling-to-trajectory video dataset is constructed to fine-tune an open-source video model, and a trajectory-aware reinforcement learning-based optimization method is introduced to improve generation fidelity via rewards. Experiments on large-scale real-world datasets show substantial improvements over strong engineered and learning-based baselines, while additional results on next GPS prediction indicate scalability and cross-city transferability. Overall, these results suggest that map-visual video generation provides a practical interface for trajectory data mining by enabling direct generation and refinement of continuous paths under map constraints. --- ### Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders Authors: Sagar Addepalli, Prajita Bhattarai, Abhilasha Dave, Julia Gonski Published: 2026-03-27 Categories: cs.LG, hep-ph, physics.ins-det arXiv: https://arxiv.org/abs/2603.26604v1 Quantum machine learning offers the ability to capture complex correlations in high-dimensional feature spaces, crucial for the challenge of detecting beyond the Standard Model physics in collider events, along with the potential for unprecedented computational efficiency in future quantum processors. Near-term utilization of these benefits can be achieved by developing quantum-inspired algorithms for deployment in classical hardware to enable applications at the "edge" of current scientific experiments. This work demonstrates the use of tensor networks for real-time anomaly detection in collider detectors. A spaced matrix product operator (SMPO) is developed that provides sensitivity to a variety beyond the Standard Model benchmarks, and can be implemented in field programmable gate array hardware with resources and latency consistent with trigger deployment. The cascaded SMPO architecture is introduced as an SMPO variation that affords greater flexibility and efficiency in ways that are key to edge applications in resource-constrained environments. These results reveal the benefit and near-term feasibility of deploying quantum-inspired ML in high energy colliders. --- ### Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence Authors: Eziyo Ehsani, Luca Giamattei, Ivano Malavolta, Roberto Pietrantuono Published: 2026-03-27 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26603v2 The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but this transition encounters a harsh reality: the physical constraints of mobile batteries, thermal limits, and, most importantly, memory constraints. To navigate this landscape, we constructed a replicable and reproducible experimental pipeline to profile the complex interplay between energy consumption, latency, and quality of LLMs on mobile devices. We harness this pipeline to conduct an empirical case study on a flagship Android device, capturing granular metrics across eight LLMs ranging from 0.5B to 9B parameters without requiring root access, ensuring our findings reflect realistic user conditions. The findings highlight the trade-offs between generation quality, performance, power and resource consumption, revealing which LLMs offer the best balance across metrics and under different conditions. Besides, we uncovered a counter-intuitive quantization energy paradox: while modern importance-aware quantization successfully reduces memory footprints to fit larger models into RAM, we found it yields negligible energy savings compared to standard mixed-precision methods. This proves that for battery life, the architecture of the model, not its quantization scheme, is the decisive factor. We further identified that Mixture-of-Experts (MoE) architectures defy the standard size-energy trend, offering the storage capacity of a 7B model while maintaining the lower energy profile of a 1B to 2B model. Finally, an analysis of these multi-objective trade-offs reveals a pragmatic sweet spot of mid-sized models, such as Qwen2.5-3B, that effectively balance response quality with sustainable energy consumption. --- ### VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward Authors: Zhaochong An, Orest Kupyn, Théo Uscidda, Andrea Colaco, Karan Ahuja, Serge Belongie, Mar Gonzalez-Franco, Marta Tintore Gazulla Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26599v2 Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To preserve the pretrained capacity while improving geometric consistency, we propose VGGRPO (Visual Geometry GRPO), a latent geometry-guided framework for geometry-aware video post-training. VGGRPO introduces a Latent Geometry Model (LGM) that stitches video diffusion latents to geometry foundation models, enabling direct decoding of scene geometry from the latent space. By constructing LGM from a geometry model with 4D reconstruction capability, VGGRPO naturally extends to dynamic scenes, overcoming the static-scene limitations of prior methods. Building on this, we perform latent-space Group Relative Policy Optimization with two complementary rewards: a camera motion smoothness reward that penalizes jittery trajectories, and a geometry reprojection consistency reward that enforces cross-view geometric coherence. Experiments on both static and dynamic benchmarks show that VGGRPO improves camera stability, geometry consistency, and overall quality while eliminating costly VAE decoding, making latent-space geometry-guided reinforcement an efficient and flexible approach to world-consistent video generation. --- ### From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning Authors: Yang Liu, Qianqian Xu, Peisong Wen, Siran Dai, Xilin Zhao, Qingming Huang Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26597v1 Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may compromise inter-video semantic separability, i.e., the essential ability to distinguish objects across videos. While reducing the tunable parameters hinders their intra-video temporal consistency, which is required for stable representations of the same object within a video. This dilemma indicates a potential trade-off between the intra-video temporal consistency and inter-video semantic separability during image-to-video transfer. To this end, we propose the Consistency-Separability Trade-off Transfer Learning (Co-Settle) framework, which applies a lightweight projection layer on top of the frozen image-pretrained encoder to adjust representation space with a temporal cycle consistency objective and a semantic separability constraint. We further provide a theoretical support showing that the optimized projection yields a better trade-off between the two properties under appropriate conditions. Experiments on eight image-pretrained models demonstrate consistent improvements across multiple levels of video tasks with only five epochs of self-supervised training. The code is available at https://github.com/yafeng19/Co-Settle. --- ### Characterization and forecasting of national-scale solar power ramp events Authors: Luca Lanzilao, Angela Meyer Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26596v1 The rapid growth of solar energy is reshaping power system operations and increasing the complexity of grid management. As photovoltaic (PV) capacity expands, short-term fluctuations in PV generation introduce substantial operational uncertainty. At the same time, solar power ramp events intensify risks of grid instability and unplanned outages due to sudden large power fluctuations. Accurate identification, forecasting and mitigation of solar ramp events are therefore critical to maintaining grid stability. In this study, we analyze two years of PV power production from 6434 PV stations at 15-minute resolution. We develop quantitative metrics to define solar ramp events and systematically characterize their occurrence, frequency, and magnitude at a national scale. Furthermore, we examine the meteorological drivers of ramp events, highlighting the role of mesoscale cloud systems. In particular, we observe that ramp-up events are typically associated with cloud dissipation during the morning, while ramp-down events commonly occur when cloud cover increases in the afternoon. Additionally, we adopt a recently developed spatiotemporal forecasting framework to evaluate both deterministic and probabilistic PV power forecasts derived from deep learning and physics-based models, including SolarSTEPS, SHADECast, IrradianceNet, and IFS-ENS. The results show that SHADECast is the most reliable model, achieving a CRPS 10.8% lower than that of SolarSTEPS at a two-hour lead time. Nonetheless, state-of-the-art nowcasting models struggle to capture ramp dynamics, with forecast RMSE increasing by up to 50% compared to normal operating conditions. Overall, these results emphasize the need for improved high-resolution spatiotemporal modelling to enhance ramp prediction skill and support the reliable integration of large-scale solar generation into power systems. --- ### PQuantML: A Tool for End-to-End Hardware-aware Model Compression Authors: Roope Niemi, Anastasiia Petrovych, Arghya Ranjan Das, Enrico Lupi, Chang Sun, Dimitrios Danopoulos, Marlon Joshua Helbing, Mia Liu, Sebastian Dittmeier, Michael Kagan, Vladimir Loncar, Maurizio Pierini Published: 2026-03-27 Categories: cs.LG, hep-ex arXiv: https://arxiv.org/abs/2603.26595v1 PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict latency constraints, PQuantML simplifies training of compressed models by providing a unified interface to apply pruning and quantization, either jointly or individually. The library implements multiple pruning methods with different granularities, as well as fixed-point quantization with support for High-Granularity Quantization. We evaluate PQuantML on representative tasks such as the jet substructure classification, so-called jet tagging, an on-edge problem related to real-time LHC data processing. Using various pruning methods with fixed-point quantization, PQuantML achieves substantial parameter and bit-width reductions while maintaining accuracy. The resulting compression is further compared against existing tools, such as QKeras and HGQ. --- ### Evaluating Interactive 2D Visualization as a Sample Selection Strategy for Biomedical Time-Series Data Annotation Authors: Einari Vaaras, Manu Airaksinen, Okko Räsänen Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.26592v2 Reliable machine-learning models in biomedical settings depend on accurate labels, yet annotating biomedical time-series data remains challenging. Algorithmic sample selection may support annotation, but evidence from studies involving real human annotators is scarce. Consequently, we compare three sample selection methods for annotation: random sampling (RND), farthest-first traversal (FAFT), and a graphical user interface-based method enabling exploration of complementary 2D visualizations (2DVs) of high-dimensional data. We evaluated the methods across four classification tasks in infant motility assessment (IMA) and speech emotion recognition (SER). Twelve annotators, categorized as experts or non-experts, performed data annotation under a limited annotation budget, and post-annotation experiments were conducted to evaluate the sampling methods. Across all classification tasks, 2DV performed best when aggregating labels across annotators. In IMA, 2DV most effectively captured rare classes, but also exhibited greater annotator-to-annotator label distribution variability resulting from the limited annotation budget, decreasing classification performance when models were trained on individual annotators' labels; in these cases, FAFT excelled. For SER, 2DV outperformed the other methods among expert annotators and matched their performance for non-experts in the individual-annotator setting. A failure risk analysis revealed that RND was the safest choice when annotator count or annotator expertise was uncertain, whereas 2DV had the highest risk due to its greater label distribution variability. Furthermore, post-experiment interviews indicated that 2DV made the annotation task more interesting and enjoyable. Overall, 2DV-based sampling appears promising for biomedical time-series data annotation, particularly when the annotation budget is not highly constrained. --- ### The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding Authors: Gillian Rosenberg, Skylar Stadhard, Bruce C. Hansen, Michelle R. Greene Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26589v1 What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual cognition. Vision-language models (VLMs) are trained on massive paired text-image corpora but lack embodied experience, making them an ideal test of the distributional hypothesis. We report two experiments comparing descriptions generated by 18 VLMs to those of over 2000 human observers across 15 high-level scene understanding tasks, spanning general knowledge, affordances, sensory experiences, affective responses, and future prediction. Because many tasks lack ground truth answers, we developed a Human-Calibrated Cosine Distance (HCD) metric that measures VLM output similarity to the distribution of human responses, scaled by within-human variability. In Experiment 1, VLMs approached human-level performance on general knowledge tasks, but showed a robust deficit for affordance tasks that resisted prompt engineering and did not improve with newer model releases. In Experiment 2, we tested six mechanistic hypotheses for explaining this affordance gap, finding that the deficit was structural rather than stylistic and was not resolved by providing explicit spatial information. Corpus analyses revealed that image captioning datasets contain sparse agent-addressed affordance language, consistent with Gricean accounts of why embodied knowledge may be systematically underrepresented in language. Together, these findings suggest that distributional learning from images and text is insufficient for affordance-based scene understanding, implying that some dimensions of human visual cognition may require the kind of agent-centered, three-dimensional experience that no photograph or caption can encode. --- ### From Synthetic Data to Real Restorations: Diffusion Model for Patient-specific Dental Crown Completion Authors: Dávid Pukanec, Tibor Kubík, Michal Španěl Published: 2026-03-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.26588v2 We present ToothCraft, a diffusion-based model for the contextual generation of tooth crowns, trained on artificially created incomplete teeth. Building upon recent advancements in conditioned diffusion models for 3D shapes, we developed a model capable of an automated tooth crown completion conditioned on local anatomical context. To address the lack of training data for this task, we designed an augmentation pipeline that generates incomplete tooth geometries from a publicly available dataset of complete dental arches (3DS, ODD). By synthesising a diverse set of training examples, our approach enables robust learning across a wide spectrum of tooth defects. Experimental results demonstrate the strong capability of our model to reconstruct complete tooth crowns, achieving an intersection over union (IoU) of 81.8% and a Chamfer Distance (CD) of 0.00034 on synthetically damaged testing restorations. Our experiments demonstrate that the model can be applied directly to real-world cases, effectively filling in incomplete teeth, while generated crowns show minimal intersection with the opposing dentition, thus reducing the risk of occlusal interference. Access to the code, model weights, and dataset information will be available at: https://github.com/ikarus1211/VISAPP_ToothCraft --- ### EnTaCs: Analyzing the Relationship Between Sentiment and Language Choice in English-Tamil Code-Switching Authors: Paul Bontempo Published: 2026-03-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.26587v1 This paper investigates the relationship between utterance sentiment and language choice in English-Tamil code-switched text, using methods from machine learning and statistical modelling. We apply a fine-tuned XLM-RoBERTa model for token-level language identification on 35,650 romanized YouTube comments from the DravidianCodeMix dataset, producing per-utterance measurements of English proportion and language switch frequency. Linear regression analysis reveals that positive utterances exhibit significantly greater English proportion (34.3%) than negative utterances (24.8%), and mixed-sentiment utterances show the highest language switch frequency when controlling for utterance length. These findings support the hypothesis that emotional content demonstrably influences language choice in multilingual code-switching settings, due to socio-linguistic associations of prestige and identity with embedded and matrix languages. --- ### MA-Bench: Towards Fine-grained Micro-Action Understanding Authors: Kun Li, Jihao Gu, Fei Wang, Zhiliang Wu, Hehe Fan, Dan Guo Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26586v1 With the rapid development of Multimodal Large Language Models (MLLMs), their potential in Micro-Action understanding, a vital role in human emotion analysis, remains unexplored due to the absence of specialized benchmarks. To tackle this issue, we present MA-Bench, a benchmark comprising 1,000 videos and a three-tier evaluation architecture that progressively examines micro-action perception, relational comprehension, and interpretive reasoning. MA-Bench contains 12,000 structured question-answer pairs, enabling systematic assessment of both recognition accuracy and action interpretation. The results of 23 representative MLLMs reveal that there are significant challenges in capturing motion granularity and fine-grained body-part dynamics. To address these challenges, we further construct MA-Bench-Train, a large-scale training corpus with 20.5K videos annotated with structured micro-action captions for fine-tuning MLLMs. The results of Qwen3-VL-8B fine-tuned on MA-Bench-Train show clear performance improvements across micro-action reasoning and explanation tasks. Our work aims to establish a foundation benchmark for advancing MLLMs in understanding subtle micro-action and human-related behaviors. Project Page: https://MA-Bench.github.io --- ### Scene Grounding In the Wild Authors: Tamir Cohen, Leo Segre, Shay Shomer-Chai, Shai Avidan, Hadar Averbuch-Elor Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26584v2 Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input views have little or no overlap. In such cases, existing reconstruction pipelines often produce multiple disconnected partial reconstructions or erroneously merge non-overlapping regions into overlapping geometry. In this work, we propose a framework that grounds each partial reconstruction to a complete reference model of the scene, enabling globally consistent alignment even in the absence of visual overlap. We obtain reference models from dense, geospatially accurate pseudo-synthetic renderings derived from Google Earth Studio. These renderings provide full scene coverage but differ substantially in appearance from real-world photographs. Our key insight is that, despite this significant domain gap, both domains share the same underlying scene semantics. We represent the reference model using 3D Gaussian Splatting, augmenting each Gaussian with semantic features, and formulate alignment as an inverse feature-based optimization scheme that estimates a global 6DoF pose and scale while keeping the reference model fixed. Furthermore, we introduce the WikiEarth dataset, which registers existing partial 3D reconstructions with pseudo-synthetic reference models. We demonstrate that our approach consistently improves global alignment when initialized with various classical and learning-based pipelines, while mitigating failure modes of state-of-the-art end-to-end models. --- ### The Climber's Grip -- Personalized Deep Learning Models for Fear and Muscle Activity in Climbing Authors: Matthias Boeker, Dana Swarbrick, Ulysse T. A. Côté-Allard, Marc T. P. Adam, Hugo L. Hammer, Pål Halvorsen Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26575v1 Climbing is a multifaceted sport that combines physical demands and emotional and cognitive challenges. Ascent styles differ in fall distance with lead climbing involving larger falls than top rope climbing, which may result in different perceived risk and fear. In this study, we investigated the psychophysiological relationship between perceived fear and muscle activity in climbers using a combination of statistical modeling and deep learning techniques. We conducted an experiment with 19 climbers, collecting electromyography (EMG), electrocardiography (ECG) and arm motion data during lead and top rope climbing. Perceived fear ratings were collected for the different phases of the climb. Using a linear mixed-effects model, we analyzed the relationships between perceived fear and physiological measures. To capture the non-linear dynamics of this relationship, we extended our analysis to deep learning models and integrated random effects for a personalized modeling approach. Our results showed that random effects improved model performance of the mean squared error (MSE), mean absolute error (MAE) and root mean squared error (RMSE). The results showed that muscle fatigue correlates significantly with increased fear during \textit{lead climbing}. This study highlights the potential of combining statistical and deep learning approaches for modeling the interplay between psychological and physiological states during climbing. --- ### GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow Authors: Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26571v4 At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory. Modern rectified-flow video models are typically sampled with deterministic ODE solvers, which leave no per-step stochastic channel for transmitting compressed information. GVCC addresses this by converting the deterministic flow sampler into an equivalent marginal-preserving stochastic process, so that information can be transmitted by encoding the per-step stochastic innovations. Unlike images, videos introduce longer temporal dependencies and more diverse conditioning modes. We instantiate GVCC in three practical modes: Text-to-Video (T2V) without a reference frame, autoregressive Image-to-Video (I2V) with tail latent correction, and First-Last-Frame-to-Video (FLF2V) with boundary-sharing Group of Pictures (GOP) chaining. On the seven-sequence UVG dataset, local atom-count sweeps characterize the rate--quality behavior of all three variants. We report full-dataset perceptual and fidelity metrics together with temporal diagnostics, without inferring matched-rate or global RD improvements from these limited local sweeps. --- ### GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow Authors: Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26571v3 At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory. Modern rectified-flow video models are typically sampled with deterministic ODE solvers, which leave no per-step stochastic channel for transmitting compressed information. GVCC addresses this by converting the deterministic flow sampler into an equivalent marginal-preserving stochastic process, so that information can be transmitted by encoding the per-step stochastic innovations. Unlike images, videos introduce longer temporal dependencies and more diverse conditioning modes. We instantiate GVCC in three practical modes: Text-to-Video (T2V) without a reference frame, autoregressive Image-to-Video (I2V) with tail latent correction, and First-Last-Frame-to-Video (FLF2V) with boundary-sharing Group of Pictures (GOP) chaining. On UVG, GVCC achieves the lowest LPIPS among evaluated baselines across three representative bitrate regimes (down to ${\sim}$0.003\,bpp), with 65\% LPIPS reduction over DCVC-RT at matched bitrate. --- ### Machine Unlearning under Retain-Forget Entanglement Authors: Jingpu Cheng, Ping Liu, Qianxiao Li, Chi Zhang Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26569v1 Forgetting a subset in machine unlearning is rarely an isolated task. Often, retained samples that are closely related to the forget set can be unintentionally affected, particularly when they share correlated features from pretraining or exhibit strong semantic similarities. To address this challenge, we propose a novel two-phase optimization framework specifically designed to handle such retai-forget entanglements. In the first phase, an augmented Lagrangian method increases the loss on the forget set while preserving accuracy on less-related retained samples. The second phase applies a gradient projection step, regularized by the Wasserstein-2 distance, to mitigate performance degradation on semantically related retained samples without compromising the unlearning objective. We validate our approach through comprehensive experiments on multiple unlearning tasks, standard benchmark datasets, and diverse neural architectures, demonstrating that it achieves effective and reliable unlearning while outperforming existing baselines in both accuracy retention and removal fidelity. --- ### Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering Authors: Yoseph Berhanu Alebachew, Hunter Leary, Swanand Vaishampayan, Chris Brown Published: 2026-03-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.26567v2 Large Language Models (LLMs) have shown impressive capabilities across software engineering tasks, including question answering (QA). However, most studies and benchmarks focus on isolated functions or single-file snippets, overlooking the challenges of real-world program comprehension, which often spans multiple files and system-level dependencies. In this work, we introduce StackRepoQA, the first multi-project, repository-level question answering dataset constructed from 1,318 real developer questions and accepted answers across 134 open-source Java projects. Using this dataset, we systematically evaluate two widely used LLMs (Claude 3.5 Sonnet and GPT-4o) under both direct prompting and agentic configurations. We compare baseline performance with retrieval-augmented generation methods that leverage file-level retrieval and graph-based representations of structural dependencies. Our results show that LLMs achieve moderate accuracy at baseline, with performance improving when structural signals are incorporated. Nonetheless, overall accuracy remains limited for repository-scale comprehension. The analysis reveals that high scores often result from verbatim reproduction of Stack Overflow answers rather than genuine reasoning. To our knowledge, this is the first empirical study to provide such evidence in repository-level QA. We release StackRepoQA to encourage further research into benchmarks, evaluation protocols, and augmentation strategies that disentangle memorization from reasoning, advancing LLMs as reliable tool for repository-scale program comprehension. --- ### MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference Authors: Joris Köster, Zixuan Liu, Siavash Khajavi, Zizhan Zheng Published: 2026-03-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.26557v3 Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a memory-boosted LLM serving framework that enables a lightweight model to reuse previously generated answers and retrieve relevant supporting information for cheap inference, while selectively escalating difficult or uncertain queries to a stronger model. Unlike standard retrieval-augmented generation, which primarily grounds a single response, MemBoost is designed for interactive settings by supporting answer reuse, continual memory growth, and cost-aware routing. Experiments across multiple models under simulated workloads show that MemBoost substantially reduces expensive large-model invocations and overall inference cost, while maintaining high answer quality comparable to the strong model baseline. --- ### When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models Authors: Juan Gabriel Kostelec, Qinghai Guo Published: 2026-03-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.26556v3 Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint design of both the student architecture and the distillation process. Many prior distillation works evaluate downstream multiple-choice benchmarks by ranking candidate answers with log-likelihood rather than requiring autoregressive generation, which can obscure important differences in model quality. For example, on overlapping benchmarks, we show that a 7B distilled model that nearly matches its teacher to within 0.2 pp under log-likelihood scoring falls behind by 20.8 pp when it must generate answers autoregressively. We investigate this phenomenon with GenDistill, a multi-stage pipeline we designed for distilling a pretrained Transformer into an efficient Hybrid Kimi Delta Attention (Hybrid-KDA) student. Using it as a controlled testbed on Qwen3-0.6B, we systematically ablate six design axes (training objective, loss masking, training duration, dataset selection, parameter freezing, and architecture choice) and evaluate every choice under both log-likelihood and generation-based protocols. We find that log-likelihood-based evaluation consistently underestimates the gap between teacher and student, and can in some cases reverse the ranking of design choices, so conclusions drawn from perplexity-only evaluation may be misleading. Among the factors we study, dataset selection, completion-only masking, and freezing attention layers during post-training have the largest impact on generation quality. Our best distillation recipe, using a Hybrid-KDA model as the student, retains 86-90% of teacher accuracy on knowledge benchmarks while reducing KV cache memory by up to 75% and improving time-to-first-token by 2-4x at 128K-token contexts. --- ### When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models Authors: Juan Gabriel Kostelec, Qinghai Guo Published: 2026-03-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.26556v2 Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint design of both the student architecture and the distillation process. Many prior distillation works evaluate downstream multiple-choice benchmarks by ranking candidate answers with log-likelihood rather than requiring autoregressive generation, which can obscure important differences in model quality. For example, on overlapping benchmarks, we show that a 7B distilled model that nearly matches its teacher to within 0.2 pp under log-likelihood scoring falls behind by 20.8 pp when it must generate answers autoregressively. We investigate this phenomenon with GenDistill, a multi-stage pipeline we designed for distilling a pretrained Transformer into an efficient Hybrid Kimi Delta Attention (Hybrid-KDA) student. Using it as a controlled testbed on Qwen3-0.6B, we systematically ablate six design axes (training objective, loss masking, training duration, dataset selection, parameter freezing, and architecture choice) and evaluate every choice under both log-likelihood and generation-based protocols. We find that log-likelihood-based evaluation consistently underestimates the gap between teacher and student, and can in some cases reverse the ranking of design choices, so conclusions drawn from perplexity-only evaluation may be misleading. Among the factors we study, dataset selection, completion-only masking, and freezing attention layers during post-training have the largest impact on generation quality. Our best distillation recipe, using a Hybrid-KDA model as the student, retains 86-90% of teacher accuracy on knowledge benchmarks while reducing KV cache memory by up to 75% and improving time-to-first-token by 2-4x at 128K-token contexts. --- ### Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory Authors: Juno Kim, Eshaan Nichani, Denny Wu, Alberto Bietti, Jason D. Lee Published: 2026-03-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.26554v2 Spectral optimizers such as Muon have recently shown strong empirical performance in large-scale language model training, but the source and extent of their advantage remain poorly understood. We study this question through the linear associative memory problem, a tractable model for factual recall in transformer-based models. In particular, we go beyond orthogonal embeddings and consider Gaussian inputs and outputs, which allows the number of stored associations to greatly exceed the embedding dimension. Our main result sharply characterizes the recovery rates of one step of Muon, SGD, and Newton's method on the logistic regression loss under a power law frequency distribution. We show that the storage capacity of Muon significantly exceeds that of SGD, and even matches Newton's method while only using first-order information. Moreover, Muon saturates at a larger critical batch size. We further analyze the multi-step dynamics under a thresholded gradient approximation and show that Muon achieves a substantially faster initial recovery rate than SGD, while both methods eventually converge to the information-theoretic limit at comparable speeds. Experiments on synthetic tasks validate the predicted scaling laws. Our analysis provides a quantitative understanding of the signal amplification of spectral preconditioners and lays the groundwork for establishing scaling laws across more practical language modeling tasks and optimizers. --- ### SemConFlow: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching Authors: Lanmiao Liu, Esam Ghaleb, Aslı Özyürek, Zerrin Yumak Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26553v2 While the field of co-speech gesture generation has seen significant advances, producing holistic, semantically grounded gestures remains a challenge. Existing approaches rely on external semantic retrieval methods, which limit their generalisation capability due to dependency on predefined linguistic rules. Flow-matching-based methods produce promising results; however, the network is optimised using only semantically congruent samples without exposure to negative examples, leading to learning rhythmic gestures rather than sparse motion, such as iconic and metaphoric gestures. Furthermore, by modelling body parts in isolation, the majority of methods fail to maintain crossmodal consistency. We introduce a Contrastive Flow Matching-based co-speech gesture generation model that uses mismatched audio-text conditions as negatives, training the velocity field to follow the correct motion trajectory while repelling semantically incongruent trajectories. Our model ensures cross-modal coherence by embedding text, audio, and holistic motion into a composite latent space via cosine and contrastive objectives. Extensive experiments and a user study demonstrate that our proposed approach outperforms state-of-the-art methods on two datasets, BEAT2 and SHOW. --- ### Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones Authors: Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26551v2 Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency, many publications rely on MACs (Multiply Accumulate operations) as a predictor of execution time. In this paper, we experimentally demonstrate the shortcomings of such a metric, especially in the context of edge devices. By contrasting the MAC count and execution time of common architectural design elements, we identify key factors for efficient execution and provide insights to optimize backbone design. Based on these insights, we present LowFormer, a novel vision backbone family. LowFormer features a streamlined macro and micro design that includes Lowtention, a lightweight alternative to Multi-Head Self-Attention. Lowtention not only proves more efficient, but also enables superior results on ImageNet. Additionally, we present an edge GPU version of LowFormer, that can further improve upon its baseline's speed on edge GPU and desktop GPU. We demonstrate LowFormer's wide applicability by evaluating it on smaller image classification datasets, as well as adapting it to several downstream tasks, such as object detection, semantic segmentation, image retrieval, and visual object tracking. LowFormer models consistently achieve remarkable speed-ups across various hardware platforms compared to recent state-of-the-art backbones. Code and models are available at https://github.com/altair199797/LowFormer/blob/main/Beyond_MACs.md. --- ### A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits Authors: Tor Lattimore Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26547v1 We adapt the analysis of policy gradient for continuous time $k$-armed stochastic bandits by Lattimore (2026) to the standard discrete time setup. As in continuous time, we prove that with learning rate $η= O(Δ_{\min}^2/(Δ_{\max} \log(n)))$ the regret is $O(k \log(k) \log(n) / η)$ where $n$ is the horizon and $Δ_{\min}$ and $Δ_{\max}$ are the minimum and maximum gaps. --- ### AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing Authors: Tianyu Liu, Weitao Xiong, Kunming Luo, Manyuan Zhang, Peng Li, Yuan Liu, Ping Tan Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26546v3 Generative video models have significantly advanced the photorealistic synthesis of adverse weather for autonomous driving; however, they consistently demand massive datasets to learn rare weather scenarios. While 3D-aware editing methods alleviate these data constraints by augmenting existing video footage, they are fundamentally bottlenecked by costly per-scene optimization and suffer from inherent geometric and illumination entanglement. In this work, we introduce AutoWeather4D, a feed-forward 3D-aware weather editing framework designed to explicitly decouple geometry and illumination. At the core of our approach is a G-buffer Dual-pass Editing mechanism. The Geometry Pass leverages explicit structural foundations to enable surface-anchored physical interactions, while the Light Pass analytically resolves light transport, accumulating the contributions of local illuminants into the global illumination to enable dynamic 3D local relighting. Extensive experiments demonstrate that AutoWeather4D achieves comparable photorealism and structural consistency to generative baselines while enabling fine-grained parametric physical control, serving as a practical data engine for autonomous driving. --- ### Development of a European Union Time-Indexed Reference Dataset for Assessing the Performance of Signal Detection Methods in Pharmacovigilance using a Large Language Model Authors: Maria Kefala, Jeffery L. Painter, Syed Tauhid Bukhari, Maurizio Sessa Published: 2026-03-27 Categories: cs.CL, q-bio.QM arXiv: https://arxiv.org/abs/2603.26544v1 Background: The identification of optimal signal detection methods is hindered by the lack of reliable reference datasets. Existing datasets do not capture when adverse events (AEs) are officially recognized by regulatory authorities, preventing restriction of analyses to pre-confirmation periods and limiting evaluation of early detection performance. This study addresses this gap by developing a time-indexed reference dataset for the European Union (EU), incorporating the timing of AE inclusion in product labels along with regulatory metadata. Methods: Current and historical Summaries of Product Characteristics (SmPCs) for all centrally authorized products (n=1,513) were retrieved from the EU Union Register of Medicinal Products (data lock: 15 December 2025). Section 4.8 was extracted and processed using DeepSeek V3 to identify AEs. Regulatory metadata, including labelling changes, were programmatically extracted. Time indexing was based on the date of AE inclusion in the SmPC. Results: The database includes 17,763 SmPC versions spanning 1995-2025, comprising 125,026 drug-AE associations. The time-indexed reference dataset, restricted to active products, included 1,479 medicinal products and 110,823 drug-AE associations. Most AEs were identified pre-marketing (74.5%) versus post-marketing (25.5%). Safety updates peaked around 2012. Gastrointestinal, skin, and nervous system disorders were the most represented System Organ Classes. Drugs had a median of 48 AEs across 14 SOCs. Conclusions: The proposed dataset addresses a critical gap in pharmacovigilance by incorporating temporal information on AE recognition for the EU, supporting more accurate assessment of signal detection performance and facilitating methodological comparisons across analytical approaches. --- ### The Multi-AMR Buffer Storage, Retrieval, and Reshuffling Problem: Exact and Heuristic Approaches Authors: Max Disselnmeyer, Thomas Bömer, Laura Dörr, Bastian Amberg, Anne Meyer Published: 2026-03-27 Categories: cs.RO, cs.AI, cs.MA, math.OC arXiv: https://arxiv.org/abs/2603.26542v2 Buffer zones are essential in production systems to decouple sequential processes. In dense floor storage environments, such as space-constrained brownfield facilities, manual operation is increasingly challenged by severe labor shortages and rising operational costs. Automating these zones requires solving the Buffer Storage, Retrieval, and Reshuffling Problem (BSRRP). While previous work has addressed scenarios where the focus is limited to reshuffling and retrieving a fixed set of items, real-world manufacturing necessitates an adaptive approach that also incorporates arriving unit loads. This paper introduces the Multi-AMR BSRRP, coordinating a robot fleet to manage concurrent reshuffling, alongside time-windowed storage and retrieval tasks, within a shared floor area. We formulate a Binary Integer Programming (IP) model to obtain exact solutions for benchmarking purposes. As the problem is NP-hard, rendering exact methods computationally intractable for industrial scales, we propose a hierarchical heuristic. This approach decomposes the problem into an A* search for task-level sequence planning of unit load placements, and a Constraint Programming (CP) approach for multi-robot coordination and scheduling. Experiments demonstrate orders-of-magnitude computation time reductions compared to the exact formulation. These results confirm the heuristic's viability as responsive control logic for high-density production environments. --- ### OVI-MAP:Open-Vocabulary Instance-Semantic Mapping Authors: Zilong Deng, Federico Tombari, Marc Pollefeys, Johanna Wald, Daniel Barath Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26541v1 Incremental open-vocabulary 3D instance-semantic mapping is essential for autonomous agents operating in complex everyday environments. However, it remains challenging due to the need for robust instance segmentation, real-time processing, and flexible open-set reasoning. Existing methods often rely on the closed-set assumption or dense per-pixel language fusion, which limits scalability and temporal consistency. We introduce OVI-MAP that decouples instance reconstruction from semantic inference. We propose to build a class-agnostic 3D instance map that is incrementally constructed from RGB-D input, while semantic features are extracted only from a small set of automatically selected views using vision-language models. This design enables stable instance tracking and zero-shot semantic labeling throughout online exploration. Our system operates in real time and outperforms state-of-the-art open-vocabulary mapping baselines on standard benchmarks. --- ### How Open Must Language Models be to Enable Reliable Scientific Inference? Authors: James A. Michaelov, Catherine Arnett, Tyler A. Chang, Pamela D. Rivière, Samuel M. Taylor, Cameron R. Jones, Sean Trott, Roger P. Levy, Benjamin K. Bergen, Micah Altman Published: 2026-03-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.26539v2 How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this paper, we analyze how restrictions on information about model construction and deployment threaten reliable inference. We argue that current closed models are generally ill-suited for scientific purposes, with some notable exceptions, and discuss ways in which the issues they present to reliable inference can be resolved or mitigated. We recommend that when models are used in research, potential threats to inference should be systematically identified along with the steps taken to mitigate them, and that specific justifications for model selection should be provided. --- ### PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization Authors: Zelin Tan, Zhouliang Yu, Bohan Lin, Zijie Geng, Hejia Geng, Yudong Zhang, Mulei Zhang, Yang Chen, Shuyue Hu, Zhenfei Yin, Chen Zhang, Lei Bai Published: 2026-03-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.26535v4 We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward designs. Outcome reward models (ORM) evaluate only final-answer correctness, treating all correct responses identically regardless of reasoning quality, and gradually lose the advantage signal as groups become uniformly correct. Process reward models (PRM) offer richer supervision, but directly using PRM scores causes reward hacking, where models exploit verbosity to inflate scores while accuracy collapses. PAPO resolves both by composing the advantage from an outcome component Aout, derived from ORM and normalized over all responses, and a process component Aproc, derived from a rubric-based PRM and normalized exclusively among correct responses. This decoupled design ensures that Aout anchors training on correctness while Aproc differentiates reasoning quality without distorting the outcome signal. Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM, reaching 51.3% vs.\ 46.3% on OlympiadBench while continuing to improve as ORM plateaus and declines. --- ### PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization Authors: Zelin Tan, Zhouliang Yu, Bohan Lin, Zijie Geng, Hejia Geng, Yudong Zhang, Mulei Zhang, Yang Chen, Shuyue Hu, Zhenfei Yin, Chen Zhang, Lei Bai Published: 2026-03-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.26535v3 We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward designs. Outcome reward models (ORM) evaluate only final-answer correctness, treating all correct responses identically regardless of reasoning quality, and gradually lose the advantage signal as groups become uniformly correct. Process reward models (PRM) offer richer supervision, but directly using PRM scores causes reward hacking, where models exploit verbosity to inflate scores while accuracy collapses. PAPO resolves both by composing the advantage from an outcome component Aout, derived from ORM and normalized over all responses, and a process component Aproc, derived from a rubric-based PRM and normalized exclusively among correct responses. This decoupled design ensures that Aout anchors training on correctness while Aproc differentiates reasoning quality without distorting the outcome signal. Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM, reaching 51.3% vs.\ 46.3% on OlympiadBench while continuing to improve as ORM plateaus and declines. --- ### Learnable Quantum Efficiency Filters for Urban Hyperspectral Segmentation Authors: Imad Ali Shah, Jiarong Li, Ethan Delaney, Enda Ward, Martin Glavin, Edward Jones, Brian Deegan Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26528v1 Hyperspectral sensing provides rich spectral information for scene understanding in urban driving, but its high dimensionality poses challenges for interpretation and efficient learning. We introduce Learnable Quantum Efficiency (LQE), a physics-inspired, interpretable dimensionality reduction (DR) method that parameterizes smooth high-order spectral response functions that emulate plausible sensor quantum efficiency curves. Unlike conventional methods or unconstrained learnable layers, LQE enforces physically motivated constraints, including a single dominant peak, smooth responses, and bounded bandwidth. This formulation yields a compact spectral representation that preserves discriminative information while remaining fully differentiable and end-to-end trainable within semantic segmentation models (SSMs). We conduct systematic evaluations across three publicly available multi-class hyperspectral urban driving datasets, comparing LQE against six conventional and seven learnable baseline DR methods across six SSMs. Averaged across all SSMs and configurations, LQE achieves the highest average mIoU, improving over conventional methods by 2.45\%, 0.45\%, and 1.04\%, and over learnable methods by 1.18\%, 1.56\%, and 0.81\% on HyKo, HSI-Drive, and Hyperspectral City, respectively. LQE maintains strong parameter efficiency (12--36 parameters compared to 51--22K for competing learnable approaches) and competitive inference latency. Ablation studies show that low-order configurations are optimal, while the learned spectral filters converge to dataset-intrinsic wavelength patterns. These results demonstrate that physics-informed spectral learning can improve both performance and interpretability, providing a principled bridge between hyperspectral perception and data-driven multispectral sensor design for automotive vision systems. --- ### Hyperelastic constitutive model discovery with differentiable finite elements and structure-preserving neural networks Authors: Francesco Regazzoni Published: 2026-03-27 Categories: math.NA, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2603.26517v2 The discovery of constitutive laws from experimentally accessible measurements is a central problem in nonlinear computational mechanics. Many data-driven constitutive identification approaches rely either on paired strain-stress data or on full-field displacement measurements, both of which are difficult to obtain in realistic three-dimensional settings. We present a differentiable finite element framework for the discovery of hyperelastic material laws from partial observations, including boundary-only displacement measurements and global reaction forces. The method embeds the nonlinear finite element equilibrium problem directly into the learning loop, so that candidate strain-energy densities are assessed through the deformation fields and reactions they induce. This formulation enforces mechanical equilibrium as a constraint and allows the loss function to be evaluated only at observed locations. To ensure physical admissibility and promote numerical solvability throughout training, the constitutive response is represented by Hyperelastic Neural Networks, a structure-preserving neural class that enforces residual energy and stress-free conditions, frame indifference, isotropic material symmetry, polyconvexity, coercivity, and controlled volumetric growth by construction. The resulting PDE-constrained learning problem is solved using a quasi-Newton strategy combined with continuation and solver-aware backtracking. Numerical experiments in two- and three-dimensional finite elasticity demonstrate accurate recovery of hyperelastic isotropic responses from boundary-only data, robustness to measurement noise, and generalization across geometries, loading conditions, and boundary conditions. --- ### The internal law of a material can be discovered from its boundary Authors: Francesco Regazzoni Published: 2026-03-27 Categories: math.NA, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2603.26517v1 Since the earliest stages of human civilization, advances in technology have been tightly linked to our ability to understand and predict the mechanical behavior of materials. In recent years, this challenge has increasingly been framed within the broader paradigm of data-driven scientific discovery, where governing laws are inferred directly from observations. However, existing methods require either stress-strain pairs or full-field displacement measurements, which are often inaccessible in practice. We introduce Neural-DFEM, a method that enables unsupervised discovery of hyperelastic material laws even from partial observations, such as boundary-only measurements. The method embeds a differentiable finite element solver within the learning loop, directly linking candidate energy functionals to available measurements. To guarantee thermodynamic consistency and mathematical well-posedness throughout training, the method employs Hyperelastic Neural Networks, a novel structure-preserving neural architecture that enforces frame indifference, material symmetry, polyconvexity, and coercivity by design. The resulting framework enables robust material model discovery in both two- and three-dimensional settings, including scenarios with boundary-only measurements. Neural-DFEM allows for generalization across geometries and loading conditions, and exhibits unprecedented accuracy and strong resilience to measurement noise. Our results demonstrate that reliable identification of material laws is achievable even under partial observability when strong physical inductive biases are embedded in the learning architecture. --- ### ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs Authors: Inês Vieira, Inês Calvo, Iago Paulo, James Furtado, Rafael Ferreira, Diogo Tavares, Diogo Glória-Silva, David Semedo, João Magalhães Published: 2026-03-27 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26516v1 As Large Language Models (LLMs) expand across multilingual domains, evaluating their performance in under-represented languages becomes increasingly important. European Portuguese (pt-PT) is particularly affected, as existing training data and benchmarks are mainly in Brazilian Portuguese (pt-BR). To address this, we introduce ALBA, a linguistically grounded benchmark designed from the ground up to assess LLM proficiency in linguistic-related tasks in pt-PT across eight linguistic dimensions, including Language Variety, Culture-bound Semantics, Discourse Analysis, Word Plays, Syntax, Morphology, Lexicology, and Phonetics and Phonology. ALBA is manually constructed by language experts and paired with an LLM-as-a-judge framework for scalable evaluation of pt-PT generated language. Experiments on a diverse set of models reveal performance variability across linguistic dimensions, highlighting the need for comprehensive, variety-sensitive benchmarks that support further development of tools in pt-PT. --- ### JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems Authors: Guangzhao Yang, Yu Pan, Shi Qiu, Ningjie Bai Published: 2026-03-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.26515v1 Despite recent advances, efficient and robust turn-taking detection remains a significant challenge in industrial-grade Voice AI agent deployments. Many existing systems rely solely on acoustic or semantic cues, leading to suboptimal accuracy and stability, while recent attempts to endow large language models with full-duplex capabilities require costly full-duplex data and incur substantial training and deployment overheads, limiting real-time performance. In this paper, we propose JAL-Turn, a lightweight and efficient speech-only turn-taking framework that adopts a joint acoustic-linguistic modeling paradigm, in which a cross-attention module adaptively integrates pre-trained acoustic representations with linguistic features to support low-latency prediction of hold vs shift states. By sharing a frozen ASR encoder, JAL-Turn enables turn-taking prediction to run fully in parallel with speech recognition, introducing no additional end-to-end latency or computational overhead. In addition, we introduce a scalable data construction pipeline that automatically derives reliable turn-taking labels from large-scale real-world dialogue corpora. Extensive experiments on public multilingual benchmarks and an in-house Japanese customer-service dataset show that JAL-Turn consistently outperforms strong state-of-the-art baselines in detection accuracy while maintaining superior real-time performance. --- ### CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation Authors: Jesse Barkley, Rumi Loghmani, Amir Barati Farimani Published: 2026-03-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.26512v1 Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language. It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation. The outer loop combines exact measurements from the OpenCASCADE kernel (bounding box dimensions, volume, solid validity) with holistic visual assessment from an independent vision-language model Judge. This provides both the numerical precision and the high-level shape awareness needed to converge on the correct geometry. The system uses retrieval-augmented generation over API documentation rather than fine-tuning, maintaining a current database as the underlying CAD library evolves. We evaluate on a custom benchmark of 100 prompts in three difficulty tiers (T1 through T3) with three ablation configurations. Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%), improves the median F1 score from 0.9707 to 0.9846, the median IoU from 0.8085 to 0.9629, and reduces the mean Chamfer Distance from 28.37 to 0.74, demonstrating that closed-loop refinement with programmatic geometric feedback substantially improves the quality and reliability of LLM-generated CAD models. --- ### AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese Authors: Afonso Simplício, Gonçalo Vinagre, Miguel Moura Ramos, Diogo Tavares, Rafael Ferreira, Giuseppe Attanasio, Duarte M. Alves, Inês Calvo, Inês Vieira, Rui Guerra, James Furtado, Beatriz Canaverde et al. Published: 2026-03-27 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26511v1 Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresented in both training data and native evaluation, with machine-translated benchmarks likely missing the variant's linguistic and cultural nuances. We introduce AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages. To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias. Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations, supporting the case for targeted training and native benchmarking for European Portuguese. --- ### Clinical named entity recognition in the Portuguese language: a benchmark of modern BERT models and LLMs Authors: Vinicius Anjos de Almeida, Sandro Saorin da Silva, Josimar Chire, Leonardo Vicenzi, Nícolas Henrique Borges, Helena Kociolek, Sarah Miriã de Castro Rocha, Frederico Nassif Gomes, Júlia Cristina Ferreira, Oge Marques, Lucas Emanuel Silva e Oliveira Published: 2026-03-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.26510v1 Clinical notes contain valuable unstructured information. Named entity recognition (NER) enables the automatic extraction of medical concepts; however, benchmarks for Portuguese remain scarce. In this study, we aimed to evaluate BERT-based models and large language models (LLMs) for clinical NER in Portuguese and to test strategies for addressing multilabel imbalance. We compared BioBERTpt, BERTimbau, ModernBERT, and mmBERT with LLMs such as GPT-5 and Gemini-2.5, using the public SemClinBr corpus and a private breast cancer dataset. Models were trained under identical conditions and evaluated using precision, recall, and F1-score. Iterative stratification, weighted loss, and oversampling were explored to mitigate class imbalance. The mmBERT-base model achieved the best performance (micro F1 = 0.76), outperforming all other models. Iterative stratification improved class balance and overall performance. Multilingual BERT models, particularly mmBERT, perform strongly for Portuguese clinical NER and can run locally with limited computational resources. Balanced data-splitting strategies further enhance performance. --- ### Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays Authors: Martin Rath, Morteza Ghahremani, Yitong Li, Ashkan Taghipour, Marcus Makowski, Christian Wachinger Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26509v2 Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited availability. Standard chest X-rays are cost-effective and widely accessible, but provide only 2D projections with limited pathological information. Reconstructing 3D CT volumes from 2D X-rays could markedly increase diagnostic accessibility, yet existing methods rely predominantly on synthetic X-ray projections, limiting clinical generalization. We propose AXON, a multi-stage diffusion-based framework that reconstructs 3D CT volumes directly from real X-rays with substantially improved fidelity over existing approaches. AXON follows a coarse-to-fine paradigm: a Brownian Bridge diffusion model first captures global anatomical structure, and a ControlNet-guided refinement stage then enhances local intensity detail and anatomical realism. To alleviate the depth ambiguity inherent in 2D-to-3D reconstruction, AXON incorporates bi-planar X-ray views, enabling more accurate spatial reasoning and structural recovery. A dedicated super-resolution module further increases the spatial resolution of the generated volumes. Experiments on public and external datasets show that AXON consistently surpasses state-of-the-art approaches while generalizing across diverse clinical distributions. At our highest-resolution bi-planar setting, AXON achieves an 11.9% improvement in PSNR and an 11.0% increase in SSIM over the strongest baseline evaluated at that resolution. In the $128^3$ single-planar setting, it maintains a lead of 7.8% in PSNR on LIDC-IDRI, with larger margins on the external clinical dataset of 8.0% in PSNR and 16.9% in SSIM. Our code is available at https://github.com/ai-med/AXON/. --- ### Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays Authors: Martin Rath, Morteza Ghahremani, Yitong Li, Ashkan Taghipour, Marcus Makowski, Christian Wachinger Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26509v1 Computed tomography (CT) provides rich 3D anatomical details but is often constrained by high radiation exposure, substantial costs, and limited availability. While standard chest X-rays are cost-effective and widely accessible, they only provide 2D projections with limited pathological information. Reconstructing 3D CT volumes from 2D X-rays offers a transformative solution to increase diagnostic accessibility, yet existing methods predominantly rely on synthetic X-ray projections, limiting clinical generalization. In this work, we propose AXON, a multi-stage diffusion-based framework that reconstructs high-fidelity 3D CT volumes directly from real X-rays. AXON employs a coarse-to-fine strategy, with a Brownian Bridge diffusion model-based initial stage for global structural synthesis, followed by a ControlNet-based refinement stage for local intensity optimization. It also supports bi-planar X-ray input to mitigate depth ambiguities inherent in 2D-to-3D reconstruction. A super-resolution network is integrated to upscale the generated volumes to achieve diagnostic-grade resolution. Evaluations on both public and external datasets demonstrate that AXON significantly outperforms state-of-the-art baselines, achieving a 11.9% improvement in PSNR and a 11.0% increase in SSIM with robust generalizability across disparate clinical distributions. Our code is available at https://github.com/ai-med/AXON. --- ### Identifying Connectivity Distributions from Neural Dynamics Using Flows Authors: Timothy Doyeon Kim, Ulises Pereira-Obilinovic, Yiliu Wang, Eric Shea-Brown, Uygar Sümbül Published: 2026-03-27 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2603.26506v2 Connectivity structure shapes neural computation, but inferring this structure from population recordings is degenerate: multiple connectivity structures can generate identical dynamics. Recent work uses low-rank recurrent neural networks (lrRNNs) to infer low-dimensional latent dynamics and connectivity from observed activity, enabling a mechanistic interpretation of the dynamics. However, standard approaches for training lrRNNs can recover spurious structures irrelevant to the underlying dynamics. We first characterize the identifiability of connectivity structures in lrRNNs and determine conditions under which a unique solution exists. To find such solutions, we develop an inference framework based on maximum entropy and continuous normalizing flows (CNFs), trained via flow matching. Instead of estimating a single connectivity matrix, our method learns a distribution over connection weights that is maximally unbiased over unidentifiable components while matching the observed dynamics. This approach captures complex yet necessary distributions such as heavy-tailed connectivity found in empirical data. We validate our method on synthetic datasets with connectivity structures that generate multistable attractors, limit cycles, and ring attractors, and demonstrate its applicability in recordings from rat frontal cortex during decision-making. Our framework shifts circuit inference from recovering connectivity to identifying which connectivity structures are computationally required, and which are artifacts of underconstrained inference. --- ### Targeted learning of heterogeneous treatment effect curves for right censored or left truncated time-to-event data Authors: Matthew Pryce, Karla Diaz-Ordaz, Ruth H. Keogh, Stijn Vansteelandt Published: 2026-03-27 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2603.26502v1 In recent years, there has been growing interest in causal machine learning estimators for quantifying subject-specific effects of a binary treatment on time-to-event outcomes. Estimation approaches have been proposed which attenuate the inherent regularisation bias in machine learning predictions, with each of these estimators addressing measured confounding, right censoring, and in some cases, left truncation. However, the existing approaches are found to exhibit suboptimal finite-sample performance, with none of the existing estimators fully leveraging the temporal structure of the data, yielding non-smooth treatment effects over time. We address these limitations by introducing surv-iTMLE, a targeted learning procedure for estimating the difference in the conditional survival probabilities under two treatments. Unlike existing estimators, surv-iTMLE accommodates both left truncation and right censoring while enforcing smoothness and boundedness of the estimated treatment effect curve over time. Through extensive simulation studies under both right censoring and left truncation scenarios, we demonstrate that surv-iTMLE outperforms existing methods in terms of bias and smoothness of time-varying effect estimates in finite samples. We then illustrate surv-iTMLE's practical utility by exploring heterogeneity in the effects of immunotherapy on survival among non-small cell lung cancer (NSCLC) patients, revealing clinically meaningful temporal patterns that existing estimators may obscure. --- ### AIRA_2: Overcoming Bottlenecks in AI Research Agents Authors: Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo, Rishi Hazra, Michael Kuchnik, Bassel Al Omari, Thomas Simon Foster, Anton Protopopov, Jean-Christophe Gagnon-Audet, Ishita Mediratta, Kelvin Niu, Michael Shvartsman et al. Published: 2026-03-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.26499v2 Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where validation-based selection causes overfitting and performance to degrade over extended search horizons; and (3) the limited capability of fixed, single-turn LLM operators imposes a ceiling on search performance. We introduce AIRA$_2$, which addresses these bottlenecks through three architectural choices: an asynchronous multi-GPU worker pool that increases experiment throughput linearly; a Hidden Consistent Evaluation protocol that delivers a reliable evaluation signal; and ReAct agents that dynamically scope their actions and debug interactively. On MLE-bench-30, AIRA$^{\dagger}_{2}$ achieves a mean Percentile Rank of 81.5% at 24 hours and 83.1% at 72 hours, outperforming the strongest baseline, which achieves 72.7%. On AIRS-Bench, AIRA$_2$ exceeds human state-of-the-art on 6 out of 20 diverse research tasks. Ablations confirm that each architectural component is necessary, that performance follows a predictable scaling law that transfers across LLM backbones, and that the "overfitting" reported in prior work was driven by evaluation noise rather than true data memorization. --- ### TCM-Serve: Modality-aware Scheduling for Multimodal Large Language Model Inference Authors: Konstantinos Papaioannou, Thaleia Dimitra Doudali Published: 2026-03-27 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.26498v2 Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, and videos. These heterogeneous workloads introduce additional inference stages, such as vision preprocessing and encoding, that inflate latency and memory demand. Existing LLM serving systems, optimized for text-only workloads, fail under multimodality: large requests (e.g., videos) monopolize resources, causing severe head-of-line blocking and performance degradation. Our key insight is that multimodal requests differ by orders of magnitude in resource demands, which we capture through a simple abstraction: videos behave like trucks, images like cars, and text like motorcycles. We design TCM-Serve, a modality-aware scheduler that lets motorcycles flow quickly through cars and trucks, ensuring interactive responsiveness while avoiding starvation. TCM-Serve classifies requests, prioritizes them dynamically, and applies aging to avoid starvation. Evaluation across state-of-the-art MLLMs shows that TCM-Serve reduces, on average, time-to-first-token (TTFT) by 54% overall, and by 78.5% for latency-critical requests, compared to current systems. TCM-Serve delivers LLM-like responsiveness for MLLMs, with modality-aware scheduling and by making the most efficient use of the available resources. --- ### Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models Authors: Nathan Roll Published: 2026-03-27 Categories: quant-ph, cs.CL arXiv: https://arxiv.org/abs/2603.26494v1 Quantum language models have shown competitive performance on sequential tasks, yet whether trained quantum circuits exploit genuinely quantum resources -- or merely embed classical computation in quantum hardware -- remains unknown. Prior work has evaluated these models through endpoint metrics alone, without examining the memory strategies they actually learn internally. We introduce the first mechanistic interpretability study of quantum language models, combining causal gate ablation, entanglement tracking, and density-matrix interchange interventions on a controlled long-range dependency task. We find that single-qubit models are exactly classically simulable and converge to the same geometric strategy as matched classical baselines, while two-qubit models with entangling gates learn a representationally distinct strategy that encodes context in inter-qubit entanglement -- confirmed by three independent causal tests (p < 0.0001, d = 0.89). On real quantum hardware, only the classical geometric strategy survives device noise; the entanglement strategy degrades to chance. These findings open mechanistic interpretability as a tool for the science of quantum language models and reveal a noise-expressivity tradeoff governing which learned strategies survive deployment. --- ### Conditional Neural Bayes Ratio Estimation for Experimental Design Optimisation Authors: S. A. K. Leeney, T. Gessey-Jones, W. J. Handley, E. de Lera Acedo, H. T. J. Bevins, J. L. Tutt Published: 2026-03-27 Categories: astro-ph.IM, astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2603.26489v1 For frontier experiments operating at the edge of detectability, instrument design directly determines the probability of discovery. We introduce Conditional Neural Bayes Ratio Estimation (cNBRE), which extends neural Bayes ratio estimation by conditioning on design parameters, enabling a single trained network to estimate Bayes factors across a continuous design space. Applied to 21-cm radio cosmology with simulations representative of the REACH experiment, the amortised nature of cNBRE enables systematic design space exploration that would be intractable with traditional point-wise methods, while recovering established physical relationships. The analysis demonstrates a ~20 percentage point variation in detection probability with antenna orientation for a single night of observation, a design decision that would be trivial to implement if determined prior to antenna construction. This framework enables efficient, globally-informed experimental design optimisation for a wide range of scientific applications. --- ### ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better Authors: Mriganka Nath, Anurag Das, Jiahao Xie, Bernt Schiele Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26486v1 Large vision-language models (LVLMs) tend to hallucinate, especially when visual inputs are corrupted at test time. We show that such corruptions act as additional distribution shifts, significantly amplifying hallucination rates in real-world applications. To address this, we propose CLIP-guided Test-Time Training (ClipTTT), a method to adapt LVLMs under degraded conditions on the fly with a single test sample. Specifically, we leverage the image-text alignment strength of a pre-trained CLIP model as a stable guidance signal to identify reliable self-supervision targets, enabling rapid adaptation without altering the base LVLMs. Extensive experiments on standard hallucination benchmarks, with 15 common corruptions, demonstrate that ClipTTT effectively mitigates hallucinations and improves descriptive faithfulness under visual corruptions. --- ### EcoFair: Energy-Efficient Inference Routing for Edge AI under Data Degradation Authors: Mostafa Anoosha, Dhavalkumar Thakker, Kuniko Paxton, Koorosh Aslansefat, Bhupesh Kumar Mishra, Baseer Ahmad, Rameez Raja Kureshi Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26483v2 Medical edge-AI systems must operate under a difficult tension: delivering reliable diagnostic inference while running on devices with limited battery capacity, memory, and compute. In dermatology, this problem is amplified by real-world image degradation caused by smartphone capture, poor lighting, blur, compression, and heterogeneous edge sensors. To handle these degraded inputs, deploying a heavyweight model can improve reliability, but it rapidly increases the energy burden on resource-constrained devices. Conversely, always using a lightweight model saves energy but may be less reliable on ambiguous or degraded inputs. This paper introduces EcoFair, a vertically partitioned inference framework for dermatology classification in which image and tabular inputs remain local to edge clients while only learned modality-specific representations are transmitted for server-side fusion. EcoFair first processes each sample using a lightweight image encoder and then decides whether additional heavyweight computation is necessary. Escalation is triggered when the lightweight prediction exhibits high uncertainty, a narrow separation between safe and high-risk classes, or elevated metadata-derived risk from patient age and lesion location. Across HAM10000, BCN20000, and PAD-UFES-20, EcoFair is evaluated using multiple lightweight--heavy backbone pairings to quantify the trade-off between energy consumption, diagnostic performance, and worst-group malignant-case recall. Results show that EcoFair can reduce per-sample image-inference energy by up to 68\% relative to always using the heavyweight encoder, while selectively allocating additional computation under difficult data regimes to support inference reliability. Group-level analysis further shows configuration-dependent effects, with improvements in selected model--dataset settings and mixed behaviour in others. ---