# Research Papers — 2026-04 · bundle page 218 of 233 > Full-text markdown of papers #10851–10900 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/218 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/217.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/219.md) ### Beyond the Fold: Quantifying Split-Level Noise and the Case for Leave-One-Dataset-Out AU Evaluation Authors: Saurabh Hinduja, Gurmeet Kaur, Maneesh Bilalpur, Jeffrey Cohn, Shaun Canavan Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02162v1 Subject-exclusive cross-validation is the standard evaluation protocol for facial Action Unit (AU) detection, yet reported improvements are often small. We show that cross-validation itself introduces measurable stochastic variance. On BP4D+, repeated 3-fold subject-exclusive splits produce an empirical noise floor of $\pm 0.065$ in average F1, with substantially larger variation for low-prevalence AUs. Operating-point metrics such as F1 fluctuate more than threshold-independent measures such as AUC, and model ranking can change under different fold assignments. We further evaluate cross-dataset robustness using a Leave-One-Dataset-Out (LODO) protocol across five AU datasets. LODO removes partition randomness and exposes domain-level instability that is not visible under single-dataset cross-validation. Together, these results suggest that gains often reported in cross-fold validation may fall within protocol variance. Leave-one-dataset-out cross-validation yields more stable and interpretable findings --- ### CoRegOVCD: Consistency-Regularized Open-Vocabulary Change Detection Authors: Weidong Tang, Hanbin Sun, Zihan Li, Yikai Wang, Feifan Zhang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02160v1 Remote sensing change detection (CD) aims to identify where land-cover semantics change across time, but most existing methods still assume a fixed label space and therefore cannot answer arbitrary user-defined queries. Open-vocabulary change detection (OVCD) instead asks for the change mask of a queried concept. In the fully training-free setting, however, dense concept responses are difficult to compare directly across dates: appearance variation, weak cross-concept competition, and the spatial continuity of many land-cover categories often produce noisy, fragmented, and semantically unreliable change evidence. We propose Consistency-Regularized Open-Vocabulary Change Detection (CoRegOVCD), a training-free dense inference framework that reformulates concept-specific change as calibrated posterior discrepancy. Competitive Posterior Calibration (CPC) and the Semantic Posterior Delta (SPD) convert raw concept responses into competition-aware queried-concept posteriors and quantify their cross-temporal discrepancy, making semantic change evidence more comparable without explicit instance matching. Geometry-Token Consistency Gate (GeoGate) and Regional Consensus Discrepancy (RCD) further suppress unsupported responses and improve spatial coherence through geometry-aware structural verification and regional consensus. Across four benchmarks spanning building-oriented and multi-class settings, CoRegOVCD consistently improves over the strongest previous training-free baseline by 2.24 to 4.98 F1$_C$ points and reaches a six-class average of 47.50% F1$_C$ on SECOND. --- ### A Practical Two-Stage Framework for GPU Resource and Power Prediction in Heterogeneous HPC Systems Authors: Beste Oztop, Dhruva Kulkarni, Zhengji Zhao, Ayse Kivilcim Coskun, Kadidia Konate Published: 2026-04-02 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2604.02158v1 Efficient utilization of GPU resources and power has become critical with the growing demand for GPUs in high-performance computing (HPC). In this paper, we analyze GPU utilization and GPU memory utilization, as well as the power consumption of the Vienna ab initio Simulation Package (VASP), using the Slurm workload manager historical logs and GPU performance metrics collected by NVIDIA's Data Center GPU Manager (DCGM). VASP is a widely used materials science application on Perlmutter at NERSC, an HPE Cray EX system based on NVIDIA A100 GPUs. Using our insights from the resource utilization analysis of VASP applications, we propose a resource prediction framework to predict the average GPU power, maximum GPU utilization, and maximum GPU memory utilization values of heterogeneous HPC system applications to enable more efficient scheduling decisions and power-aware system operation. Our prediction framework consists of two stages: 1) using only the Slurm accounting logs as training data and 2) augmenting the training data with historical GPU profiling metrics collected with DCGM. The maximum GPU utilization predictions using only the Slurm submission features achieve up to 97% accuracy. Furthermore, features engineered from GPU-compute and memory activity metrics exhibit good correlations with average power utilization, and our runtime power usage prediction experiments result in up to 92% prediction accuracy. These findings demonstrate the effectiveness of DCGM metrics in capturing application characteristics and highlight their potential for developing predictive models to support dynamic power management in HPC systems. --- ### AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics Authors: Atilla Kaan Alkan, Felix Grezes, Sergi Blanco-Cuaresma, Jennifer Lynn Bartlett, Daniel Chivvis, Anna Kelbert, Kelly Lockhart, Alberto Accomazzi Published: 2026-04-02 Categories: cs.CL, astro-ph.IM, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.02156v1 Scientific multi-label text classification suffers from extreme class imbalance, where specialized terminology exhibits severe power-law distributions that challenge standard classification approaches. Existing scientific corpora lack comprehensive controlled vocabularies, focusing instead on broad categories and limiting systematic study of extreme imbalance. We introduce AstroConcepts, a corpus of English abstracts from 21,702 published astrophysics papers, labeled with 2,367 concepts from the Unified Astronomy Thesaurus. The corpus exhibits severe label imbalance, with 76% of concepts having fewer than 50 training examples. By releasing this resource, we enable systematic study of extreme class imbalance in scientific domains and establish strong baselines across traditional, neural, and vocabulary-constrained LLM methods. Our evaluation reveals three key patterns that provide new insights into scientific text classification. First, vocabulary-constrained LLMs achieve competitive performance relative to domain-adapted models in astrophysics classification, suggesting a potential for parameter-efficient approaches. Second, domain adaptation yields relatively larger improvements for rare, specialized terminology, although absolute performance remains limited across all methods. Third, we propose frequency-stratified evaluation to reveal performance patterns that are hidden by aggregate scores, thereby making robustness assessment central to scientific multi-label evaluation. These results offer actionable insights for scientific NLP and establish benchmarks for research on extreme imbalance. --- ### Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents Authors: Xuan Qi Published: 2026-04-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.02155v1 How much should a language agent think before taking action? Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains poorly understood. We present a systematic study of CoT budget effects on function-calling agents, sweeping six token budgets (0--512) across 200 tasks from the Berkeley Function Calling Leaderboard v3 Multiple benchmark. Our central finding is a striking non-monotonic pattern on Qwen2.5-1.5B-Instruct: brief reasoning (32 tokens) dramatically improves accuracy by 45% relative over direct answers, from 44.0% to 64.0%, while extended reasoning (256 tokens) degrades performance well below the no-CoT baseline, to 25.0% (McNemar p < 0.001). A three-way error decomposition reveals the mechanism. At d = 0, 30.5% of tasks fail because the model selects the wrong function from the candidate set; brief CoT reduces this to 1.5%, effectively acting as a function-routing step, while long CoT reverses the gain, yielding 28.0% wrong selections and 18.0% hallucinated functions at d = 256. Oracle analysis shows that 88.6% of solvable tasks require at most 32 reasoning tokens, with an average of 27.6 tokens, and a finer-grained sweep indicates that the true optimum lies at 8--16 tokens. Motivated by this routing effect, we propose Function-Routing CoT (FR-CoT), a structured brief-CoT method that templates the reasoning phase as "Function: (name) / Key args: (...)," forcing commitment to a valid function name at the start of reasoning. FR-CoT achieves accuracy statistically equivalent to free-form d = 32 CoT while reducing function hallucination to 0.0%, providing a structural reliability guarantee without budget tuning. --- ### Auction-Based Online Policy Adaptation for Evolving Objectives Authors: Guruprerana Shabadi, Kaushik Mallik Published: 2026-04-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.02151v2 We consider multi-objective reinforcement learning problems where objectives come from an identical family -- such as the class of reachability objectives -- and may appear or disappear at runtime. Our goal is to design adaptive policies that can efficiently adjust their behaviors as the set of active objectives changes. To solve this problem, we propose a modular framework where each objective is supported by a selfish local policy, and coordination is achieved through a novel auction-based mechanism: policies bid for the right to execute their actions, with bids reflecting the urgency of the current state. The highest bidder selects the action, enabling a dynamic and interpretable trade-off among objectives. Going back to the original adaptation problem, when objectives change, the system adapts by simply adding or removing the corresponding policies. Moreover, as objectives arise from the same family, identical copies of a parameterized policy can be deployed, facilitating immediate adaptation at runtime. We show how the selfish local policies can be computed by turning the problem into a general-sum Markov game, where the policies compete against each other to fulfill their own objectives. To succeed, each policy must not only optimize its own objective, but also reason about the presence of other goals and learn to produce calibrated bids that reflect relative priority. Under mild assumptions, we prove the existence of Nash equilibria where dishonest bidding leads to suboptimal outcome, and the most urgent objectives win control automatically. In our implementation, the policies are trained concurrently using proximal policy optimization (PPO). We evaluate on two Atari games and a gridworld-based path-planning task with dynamic targets. Our method achieves substantially better performance than monolithic policies trained with PPO. --- ### Samplet limits and multiwavelets Authors: Gianluca Giacchi, Michael Multerer, Jacopo Quizi Published: 2026-04-02 Categories: math.NA, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2604.02150v2 Samplets are data adapted multiresolution analyses of localized discrete signed measures. They can be constructed on scattered data sites in arbitrary dimension such that they exhibit vanishing moments with respect to any prescribed set of primitives. We consider the samplet construction in a probabilistic framework and show that, if choosing polynomials as primitives, the resulting samplet basis converges to signed measures with broken polynomial densities in the infinite data limit. These densities amount to multiwavelets with respect to a hierarchical partition of the region containing the data sites. As a byproduct, we therefore obtain a construction of general multiwavelets that allows for a flexible prescription of vanishing moments going beyond tensor product constructions. For congruent partitions we particularly recover classical multiwavelets with scale- and partition- independent filter coefficients. The theoretical findings are complemented by numerical experiments that illustrate the convergence results in case of random as well as low-discrepancy data sites. --- ### AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection Authors: Vickson Ferrel Published: 2026-04-02 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.02149v1 As TLS 1.3 encryption limits traditional Deep Packet Inspection (DPI), the security community has pivoted to Euclidean Transformer-based classifiers (e.g., ET-BERT) for encrypted traffic analysis. However, these models remain vulnerable to byte-level adversarial morphing -- recent pre-padding attacks reduced ET-BERT accuracy to 25.68%, while VLESS Reality bypasses certificate-based detection entirely. We introduce AEGIS: an Adversarial Entropy-Guided Immune System powered by a Thermodynamic Variance-Guided Hyperbolic Liquid State Space Model (TVD-HL-SSM). Rather than competing in the Euclidean payload-reading domain, AEGIS discards payload bytes in favor of 6-dimensional continuous-time flow physics projected into a non-Euclidean Poincare manifold. Liquid Time-Constants measure microsecond IAT decay, and a Thermodynamic Variance Detector computes sequence-wide Shannon Entropy to expose automated C2 tunnel anomalies. A pure C++ eBPF Harvester with zero-copy IPC bypasses the Python GIL, enabling a linear-time O(N) Mamba-3 core to process 64,000-packet swarms at line-rate. Evaluated on a 400GB, 4-tier adversarial corpus spanning backbone traffic, IoT botnets, zero-days, and proprietary VLESS Reality tunnels, AEGIS achieves an F1-score of 0.9952 and 99.50% True Positive Rate at 262 us inference latency on an RTX 4090, establishing a new state-of-the-art for physics-based adversarial network defense. --- ### TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns Authors: Zhongbo Wang, Zhiyu Lin, Zhu Wang, Haizhou Wang Published: 2026-04-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.02147v1 Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance on single-modality signals, insufficient sensitivity to the specific generative patterns of Artificial Intelligence-Generated Content (AIGC), and a failure to adequately model the interplay between linguistic patterns and behavioral dynamics. To address these limitations, we propose TRACE-Bot, a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns. TRACE-Bot constructs fine-grained representations from heterogeneous sources, including personal information data, interaction behavior data and tweet data. A dual-channel architecture captures linguistic representations via a pretrained language model and behavioral irregularities via multidimensional activity features augmented with signals from state-of-the-art (SOTA) AIGC detectors. The fused representations are then classified through a lightweight prediction head. Experiments on two public LLM-driven social bot datasets demonstrate SOTA performance, achieving accuracies of 98.46% and 97.50%, respectively. The results further indicate strong robustness against advanced bot strategies, highlighting the effectiveness of jointly leveraging implicit semantic representations and AIGC-enhanced behavioral patterns for emerging LLM-driven social bot detection. --- ### MTI: A Behavior-Based Temperament Profiling System for AI Agents Authors: Jihoon Jeong Published: 2026-04-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.02145v1 AI models of equivalent capability can exhibit fundamentally different behavioral patterns, yet no standardized instrument exists to measure these dispositional differences. Existing approaches either borrow human personality dimensions and rely on self-report (which diverges from actual behavior in LLMs) or treat behavioral variation as a defect rather than a trait. We introduce the Model Temperament Index (MTI), a behavior-based profiling system that measures AI agent temperament across four axes: Reactivity (environmental sensitivity), Compliance (instruction-behavior alignment), Sociality (relational resource allocation), and Resilience (stress resistance). Grounded in the Four Shell Model from Model Medicine, MTI measures what agents do, not what they say about themselves, using structured examination protocols with a two-stage design that separates capability from disposition. We profile 10 small language models (1.7B-9B parameters, 6 organizations, 3 training paradigms) and report five principal findings: (1) the four axes are largely independent among instruction-tuned models (all |r| < 0.42); (2) within-axis facet dissociations are empirically confirmed -- Compliance decomposes into fully independent formal and stance facets (r = 0.002), while Resilience decomposes into inversely related cognitive and adversarial facets; (3) a Compliance-Resilience paradox reveals that opinion-yielding and fact-vulnerability operate through independent channels; (4) RLHF reshapes temperament not only by shifting axis scores but by creating within-axis facet differentiation absent in the unaligned base model; and (5) temperament is independent of model size (1.7B-9B), confirming that MTI measures disposition rather than capability. --- ### Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors Authors: M. Lo Verso, C. Introini, E. Cervi, L. Savoldi, J. N. Kutz, A. Cammi Published: 2026-04-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.02139v1 Magnetohydrodynamic (MHD) phenomena play a pivotal role in the design and operation of nuclear fusion systems, where electrically conducting fluids (such as liquid metals or molten salts employed in reactor blankets) interact with magnetic fields of varying intensity and orientation, influencing the resulting flow dynamics. The numerical solution of MHD models entails the resolution of highly nonlinear, multiphysics systems of equations, which can become computationally demanding, particularly in multi-query, parametric, or real-time contexts. This study investigates a fully data-driven framework for MHD state reconstruction that integrates dimensionality reduction through Singular Value Decomposition (SVD) with the SHallow REcurrent Decoder (SHRED), a neural network architecture designed to reconstruct the full spatio-temporal state from sparse time-series measurements of selected observables, including previously unseen parametric configurations. The SHRED methodology is applied to a three-dimensional geometry representative of a portion of a WCLL blanket cell, in which lead-lithium flows around a water-cooled tube. Multiple magnetic field configurations are examined, including constant toroidal fields, combined toroidal-poloidal fields, and time-dependent magnetic fields. Across all considered scenarios, SHRED achieves high reconstruction accuracy, robustness, and generalization to magnetic field intensities, orientations, and temporal evolutions not seen during training. Notably, in the presence of time-varying magnetic fields, the model accurately infers the temporal evolution of the magnetic field itself using temperature measurements alone. Overall, the findings identify SHRED as a computationally efficient, data-driven, and flexible approach for MHD state reconstruction, with significant potential for real-time monitoring, diagnostics and control in fusion reactor systems. --- ### GaelEval: Benchmarking LLM Performance for Scottish Gaelic Authors: Peter Devine, William Lamb, Beatrice Alex, Ignatius Ezeani, Dawn Knight, Mícheál J. Ó Meachair, Paul Rayson, Martin Wynne Published: 2026-04-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.02135v1 Multilingual large language models (LLMs) often exhibit emergent 'shadow' capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. This is particularly acute for morphosyntactically rich minority languages such as Scottish Gaelic, where translation benchmarks fail to capture structural competence. We introduce GaelEval, the first multi-dimensional benchmark for Gaelic, comprising: (i) an expert-authored morphosyntactic MCQA task; (ii) a culturally grounded translation benchmark and (iii) a large-scale cultural knowledge Q&A task. Evaluating 19 LLMs against a fluent-speaker human baseline ($n=30$), we find that Gemini 3 Pro Preview achieves $83.3\%$ accuracy on the linguistic task, surpassing the human baseline ($78.1\%$). Proprietary models consistently outperform open-weight systems, and in-language (Gaelic) prompting yields a small but stable advantage (+$2.4\%$). On the cultural task, leading models exceed $90\%$ accuracy, though most systems perform worse under Gaelic prompting and absolute scores are inflated relative to the manual benchmark. Overall, GaelEval reveals that frontier models achieve above-human performance on several dimensions of Gaelic grammar, demonstrates the effect of Gaelic prompting and shows a consistent performance gap favouring proprietary over open-weight models. --- ### Intelligent Cloud Orchestration: A Hybrid Predictive and Heuristic Framework for Cost Optimization Authors: Heet Nagoriya, Komal Rohit Published: 2026-04-02 Categories: cs.DC, cs.AI, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2604.02131v1 Cloud computing allows scalable resource provisioning, but dynamic workload changes often lead to higher costs due to over-provisioning. Machine learning (ML) approaches, such as Long Short-Term Memory (LSTM) networks, are effective for predicting workload patterns at a higher level, but they can introduce delays during sudden traffic spikes. In contrast, mathematical heuristics like Game Theory provide fast and reliable scheduling decisions, but they do not account for future workload changes. To address this trade-off, this paper proposes a hybrid orchestration framework that combines LSTM-based predictive scaling with heuristic task allocation. The results show that this approach reduces infrastructure costs close to ML-based models while maintaining fast response times similar to heuristic methods. This work presents a practical approach for improving cost efficiency in cloud resource management. --- ### SEAL: An Open, Auditable, and Fair Data Generation Framework for AI-Native 6G Networks Authors: Sunder Ali Khowaja, Kapal Dev, Engin Zeydan, Madhusanka Liyanage Published: 2026-04-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.02128v1 AI-native 6G networks promise to transform the telecom industry by enabling dynamic resource allocation, predictive maintenance, and ultra-reliable low-latency communications across all layers, which are essential for applications such as smart cities, autonomous vehicles, and immersive XR. However, the deployment of 6G systems results in severe data scarcity, hindering the training of efficient AI models. Synthetic data generation is extensively used to fill this gap; however, it introduces challenges related to dataset bias, auditability, and compliance with regulatory frameworks. In this regard, we propose the Synthetic Data Generation with Ethics Audit Loop (SEAL) framework, which extends baseline modular pipelines with an Ethical and Regulatory Compliance by Design (ERCD) module and a Federated Learning (FL) feedback system. The ERCD integrates fairness, bias detection, and standardized audit trails for regulatory mapping, while the FL enables privacy-preserving calibration using aggregated insights from real testbeds to close the reality-simulation gap. Results show that the SEAL framework outperforms existing methods in terms of Frechet Inception Distance, equalized odds, and accuracy. These results validate the framework's ability to generate auditable and bias-mitigated synthetic data for responsible AI-native 6G development. --- ### Gradient estimators for parameter inference in discrete stochastic kinetic models Authors: Ludwig Burger, Annalena Kofler, Lukas Heinrich, Ulrich Gerland Published: 2026-04-02 Categories: physics.comp-ph, cond-mat.stat-mech, cs.LG, physics.bio-ph, physics.chem-ph arXiv: https://arxiv.org/abs/2604.02121v2 Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging. For deterministic models, parameter inference often relies on gradients, which can be obtained efficiently through automatic differentiation (AD). However, AD cannot be applied directly to the Gillespie stochastic simulation algorithm (SSA), since sampling from a discrete set of reactions introduces non-differentiable operations. In this work, we adopt three gradient estimators from machine learning for the Gillespie SSA: the Gumbel-Softmax Straight-Through (GS-ST) estimator, the Score Function estimator, and the Alternative Path estimator. We use the estimators to evaluate gradients of steady-state and time-dependent observables, and compare their performance in representative biophysical systems with relaxation dynamics (bimolecular association) and oscillatory dynamics (repressilator). We find that the GS-ST estimator generally yields well-behaved gradient estimates, but exhibits diverging variance in challenging parameter regimes, which can cause parameter inference to fail. In these cases, other estimators provide more robust, lower variance gradients. Our results demonstrate that gradient-based parameter inference can be effectively combined with the Gillespie SSA, with different estimators offering complementary advantages. --- ### AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression Authors: Atul Kumar Sinha, François Fleuret Published: 2026-04-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.02119v1 We introduce a fast low-rank factorization-based framework for compressing large language models that enables rapid compression of billion-parameter models without retraining. Unlike existing factorization-based approaches that optimize only on the original inputs, ignoring distribution shifts from upstream compression and thus propagating errors forward, or those that rely only on shifted inputs and risk drifting away from the original outputs, our approach accounts for both. Beyond individual layer compression, we further refine each transformer block end-to-end, minimizing block-level output distortion and allowing compressed layers to jointly compensate for accumulated errors. By anchoring each compressed layer to the original outputs while explicitly modeling input distribution shifts, our method finds a low-rank approximation that maintains functional equivalence with the original model. Experiments on large language models show that our method consistently outperforms existing SVD-based baselines across compression ratios, with the advantage becoming increasingly pronounced at aggressive compression budgets, where competing methods degrade substantially or collapse entirely, offering a practical solution for efficient, large-scale model deployment. --- ### TSQueryBench: LLM-as-a-Judge for Time Series Explanations Authors: Preetham Sivalingam, Murari Mandal, Dhruv Kumar, Saurabh Deshpande Published: 2026-04-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.02118v2 Natural language explanations of time series data are increasingly produced by foundation models in high stakes domains, making factual correctness critical. Evaluating such explanations differs fundamentally from standard natural language generation: correctness requires verifying numerical claims against structured data rather than similarity to reference text. While LLM as a Judge has emerged as a scalable paradigm for text evaluation, its applicability to numerically grounded time series explanations remains unstudied. We introduce TSQueryBench, a controlled synthetic benchmark of 500 time series instances across 10 query types, each paired with correct, partially correct, and incorrect explanations. We evaluate six large language models across four tasks: explanation generation, relative ranking, independent scoring, and multi anomaly detection. Our central finding is a consistent generation evaluation asymmetry: models that fail to generate numerically correct explanations nonetheless reliably identify or score correct ones. These results show that rubric guided LLM evaluation is substantially more reliable than generation for time series reasoning, supporting LLM judges as scalable evaluators in numerically grounded settings. Code and data: https://github.com/Prxxthxm/TSQueryBench/ --- ### LLM-as-a-Judge for Time Series Explanations Authors: Preetham Sivalingam, Murari Mandal, Saurabh Deshpande, Dhruv Kumar Published: 2026-04-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.02118v1 Evaluating factual correctness of LLM generated natural language explanations grounded in time series data remains an open challenge. Although modern models generate textual interpretations of numerical signals, existing evaluation methods are limited: reference based similarity metrics and consistency checking models require ground truth explanations, while traditional time series methods operate purely on numerical values and cannot assess free form textual reasoning. Thus, no general purpose method exists to directly verify whether an explanation is faithful to underlying time series data without predefined references or task specific rules. We study large language models as both generators and evaluators of time series explanations in a reference free setting, where given a time series, question, and candidate explanation, the evaluator assigns a ternary correctness label based on pattern identification, numeric accuracy, and answer faithfulness, enabling principled scoring and comparison. To support this, we construct a synthetic benchmark of 350 time series cases across seven query types, each paired with correct, partially correct, and incorrect explanations. We evaluate models across four tasks: explanation generation, relative ranking, independent scoring, and multi anomaly detection. Results show a clear asymmetry: generation is highly pattern dependent and exhibits systematic failures on certain query types, with accuracies ranging from 0.00 to 0.12 for Seasonal Drop and Volatility Shift, to 0.94 to 0.96 for Structural Break, while evaluation is more stable, with models correctly ranking and scoring explanations even when their own outputs are incorrect. These findings demonstrate feasibility of data grounded LLM based evaluation for time series explanations and highlight their potential as reliable evaluators of data grounded reasoning in the time series domain. --- ### Reliable Control-Point Selection for Steering Reasoning in Large Language Models Authors: Haomin Zhuang, Hojun Yoo, Xiaonan Luo, Kehan Guo, Xiangliang Zhang Published: 2026-04-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.02113v1 Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors that can be toggled via prompts, this is straightforward. However, many reasoning behaviors -- such as self-reflection -- emerge spontaneously and resist prompt-level control. Current methods detect these behaviors through keyword matching in chain-of-thought traces, implicitly assuming that every detected boundary encodes a genuine behavioral signal. We show that this assumption is overwhelmingly wrong: across 541 keyword-detected boundaries, 93.3\% are behaviorally unstable, failing to reproduce the detected behavior under re-generation from the same prefix. We develop a probabilistic model that formalizes intrinsic reasoning behaviors as stochastic events with context-dependent trigger probabilities, and show that unstable boundaries dilute the steering signal. Guided by this analysis, we propose stability filtering, which retains only boundaries where the model consistently reproduces the target behavior. Combined with a content-subspace projection that removes residual question-specific noise, our method achieves 0.784 accuracy on MATH-500 (+5.0 over the strongest baseline). The resulting steering vectors transfer across models in the same architecture family without re-extraction, improving Nemotron-Research-Reasoning-1.5B (+5.0) and DeepScaleR-1.5B-Preview (+6.0). Code is available at https://github.com/zhmzm/stability-steering. --- ### Cross-Modal Visuo-Tactile Object Perception Authors: Anirvan Dutta, Simone Tasciotti, Claudia Cusseddu, Ang Li, Panayiota Poirazi, Julijana Gjorgjieva, Etienne Burdet, Patrick van der Smagt, Mohsen Kaboli Published: 2026-04-02 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2604.02108v1 Estimating physical properties is critical for safe and efficient autonomous robotic manipulation, particularly during contact-rich interactions. In such settings, vision and tactile sensing provide complementary information about object geometry, pose, inertia, stiffness, and contact dynamics, such as stick-slip behavior. However, these properties are only indirectly observable and cannot always be modeled precisely (e.g., deformation in non-rigid objects coupled with nonlinear contact friction), making the estimation problem inherently complex and requiring sustained exploitation of visuo-tactile sensory information during action. Existing visuo-tactile perception frameworks have primarily emphasized forceful sensor fusion or static cross-modal alignment, with limited consideration of how uncertainty and beliefs about object properties evolve over time. Inspired by human multi-sensory perception and active inference, we propose the Cross-Modal Latent Filter (CMLF) to learn a structured, causal latent state-space of physical object properties. CMLF supports bidirectional transfer of cross-modal priors between vision and touch and integrates sensory evidence through a Bayesian inference process that evolves over time. Real-world robotic experiments demonstrate that CMLF improves the efficiency and robustness of latent physical properties estimation under uncertainty compared to baseline approaches. Beyond performance gains, the model exhibits perceptual coupling phenomena analogous to those observed in humans, including susceptibility to cross-modal illusions and similar trajectories in learning cross-sensory associations. Together, these results constitutes a significant step toward generalizable, robust and physically consistent cross-modal integration for robotic multi-sensory perception. --- ### DenOiS: Dual-Domain Denoising of Observation and Solution in Ultrasound Image Reconstruction Authors: Can Deniz Bezek, Orcun Goksel Published: 2026-04-02 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2604.02105v1 Medical imaging aims to recover underlying tissue properties, using inexact (simplified/linearized) imaging models and often from inaccurate and incomplete measurements. Analytical reconstruction methods rely on hand-crafted regularization, sensitive to noise assumptions and parameter tuning. Among deep learning alternatives, plug-and-play (PnP) approaches learn regularization while incorporating imaging physics during inference, outperforming purely data-driven methods. The performance of all these approaches, however, still strongly depends on measurement quality and imaging model accuracy. In this work, we propose DenOiS, a framework that denoises both input observations and resulting solution in their respective domains. It consists of an observation refinement strategy that corrects degraded measurements while compensating for imaging model simplifications, and a diffusion-based PnP reconstruction approach that remains robust under missing measurements. DenOiS enables generalization to real data from training only in simulations, resulting in high-fidelity image reconstruction with noisy observations and inexact imaging models. We demonstrate this for speed-of-sound imaging as a challenging setting of quantitative ultrasound image reconstruction. --- ### BoundInk: Boundary-Aware Online Handwriting Generation Authors: Jinsu Shin, Sungeun Hong, JinYeong Bak Published: 2026-04-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.02103v3 Realistic online handwriting depends not only on individual character shapes, but also on how a writer connects, spaces, and aligns adjacent characters. Existing methods rely primarily on long-range sequence modeling and capture these inter-character behaviors only implicitly. This often produces plausible glyphs accompanied by broken cursive joins, inconsistent spacing, or writer-inconsistent transitions. We introduce BoundInk, a writer-conditioned framework that treats inter-character boundaries as explicit generation units. By jointly modeling local transitions and surrounding text context, BoundInk preserves writer-specific glyph appearance while improving connectivity and spacing across complete text lines. We further introduce a boundary-aware evaluation framework that directly assesses cursive continuity and spatial relationships between characters beyond conventional trajectory similarity. Across three benchmark-matched settings, BoundInk improves all applicable boundary-quality measures and reduces normalized dynamic time warping by 17.6--47.8%. In blind human evaluations, BoundInk outputs are preferred in 78.0--82.6% of valid criterion-wise judgments. --- ### CASHG: Context-Aware Stylized Online Handwriting Generation Authors: Jinsu Shin, Sungeun Hong, JinYeong Bak Published: 2026-04-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.02103v2 Online handwriting represents strokes as time-ordered trajectories, which makes handwritten content easier to transform and reuse in a wide range of applications. However, generating natural sentence-level online handwriting that faithfully reflects a writer's style remains challenging, since sentence synthesis demands context-dependent characters with stroke continuity and spacing. Prior methods treat these boundary properties as implicit outcomes of sequence modeling, which becomes unreliable at the sentence scale and under limited compositional diversity. We propose CASHG, a context-aware stylized online handwriting generator that explicitly models inter-character connectivity for style-consistent sentence-level trajectory synthesis. CASHG uses a Character Context Encoder to obtain character identity and sentence-dependent context memory and fuses them in a bigram-aware sliding-window Transformer decoder that emphasizes local predecessor--current transitions, complemented by gated context fusion for sentence-level context.Training proceeds through a three-stage curriculum from isolated glyphs to full sentences, improving robustness under sparse transition coverage. We further introduce Connectivity and Spacing Metrics (CSM), a boundary-aware evaluation suite that quantifies cursive connectivity and spacing similarity. Under benchmark-matched evaluation protocols, CASHG consistently improves CSM over comparison methods while remaining competitive in DTW-based trajectory similarity, with gains corroborated by a human evaluation. --- ### Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations Authors: Haitong Sun, Stephen McIntosh, Kwanghee Choi, Eunjung Yeo, Daisuke Saito, Nobuaki Minematsu Published: 2026-04-02 Categories: cs.CL, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2604.02102v2 Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discrimination task has been used to measure phonemic contrast in S3M representations via minimal pairs. We introduce prosodic ABX, an extension of this framework to evaluate prosodic contrast with only a handful of examples and no explicit labels. Also, we build and release a dataset of English and Japanese minimal pairs and use it along with a Mandarin dataset to evaluate contrast in English stress, Japanese pitch accent, and Mandarin tone. Finally, we show that model and layer rankings are often preserved across several experimental conditions, making it practical for low-resource settings. --- ### Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations Authors: Haitong Sun, Stephen McIntosh, Kwanghee Choi, Eunjung Yeo, Daisuke Saito, Nobuaki Minematsu Published: 2026-04-02 Categories: cs.CL, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2604.02102v1 Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discrimination task has been used to measure phonemic contrast in S3M representations via minimal pairs. We introduce prosodic ABX, an extension of this framework to evaluate prosodic contrast with only a handful of examples and no explicit labels. Also, we build and release a dataset of English and Japanese minimal pairs and use it along with a Mandarin dataset to evaluate contrast in English stress, Japanese pitch accent, and Mandarin tone. Finally, we show that model and layer rankings are often preserved across several experimental conditions, making it practical for low-resource settings. --- ### LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model Authors: Jiachun Jin, Zetong Zhou, Xiao Yang, Hao Zhang, Pengfei Liu, Jun Zhu, Zhijie Deng Published: 2026-04-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.02097v1 Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and valuable, e.g., for solving understanding problems that require dense visual thinking, improving visual generation through self-reflection, or modeling visual dynamics of the physical world guided by stepwise action interventions. However, existing UMs necessitate pixel decoding as a bridge due to their disjoint visual representations for understanding and generation, which is both ineffective and inefficient. In this paper, we introduce LatentUM, a novel unified model that represents all modalities within a shared semantic latent space, eliminating the need for pixel-space mediation between visual understanding and generation. This design naturally enables flexible interleaved cross-modal reasoning and generation. Beyond improved computational efficiency, the shared representation substantially alleviates codec bias and strengthens cross-modal alignment, allowing LatentUM to achieve state-of-the-art performance on the Visual Spatial Planning benchmark, push the limits of visual generation through self-reflection, and support world modeling by predicting future visual states within the shared semantic latent space. --- ### GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding Authors: Rong Fan, Kaiyan Xiao, Minghao Zhu, Liuyi Wang, Kai Dai, Zhao Yang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02093v1 Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of key frames and the loss of crucial temporal cues. To address this limitation, we propose Grounded Visual Token Sampling (GroundVTS), a Vid-LLM architecture that focuses on the most informative temporal segments. GroundVTS employs a fine-grained, query-guided mechanism to filter visual tokens before feeding them into the LLM, thereby preserving essential spatio-temporal information and maintaining temporal coherence. Futhermore, we introduce a progressive optimization strategy that enables the LLM to effectively adapt to the non-uniform distribution of visual features, enhancing its ability to model temporal dependencies and achieve precise video localization. We comprehensively evaluate GroundVTS on three standard VTG benchmarks, where it outperforms existing methods, achieving a 7.7-point improvement in mIoU for moment retrieval and 12.0-point improvement in mAP for highlight detection. Code is available at https://github.com/Florence365/GroundVTS. --- ### Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning Authors: Yuhang Wu, Xiangqing Shen, Fanfan Wang, Cangqi Zhou, Zhen Wu, Xinyu Dai, Rui Xia Published: 2026-04-02 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2604.02091v2 Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process. This isolation leads to a fundamental misalignment: documents identified as topically relevant by information retrieval metrics often fail to provide the actual utility required by the LLM for precise answer generation. To bridge this gap, we introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality. By formulating reranking as a sequential decision-making process, RRPO optimizes for context utility using LLM feedback, thereby eliminating the need for expensive human annotations. To ensure training stability, we further introduce a reference-anchored deterministic baseline. Extensive experiments on knowledge-intensive benchmarks demonstrate that RRPO significantly outperforms strong baselines, including the powerful list-wise reranker RankZephyr. Further analysis highlights the versatility of our framework: it generalizes seamlessly to diverse readers (e.g., GPT-4o), integrates orthogonally with query expansion modules like Query2Doc, and remains robust even when trained with noisy supervisors. --- ### Center-Aware Detection with Swin-based Co-DETR Framework for Cervical Cytology Authors: Yan Kong, Yuan Yin, Hongan Chen, Yuqi Fang, Caifeng Shan Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02090v1 Automated analysis of Pap smear images is critical for cervical cancer screening but remains challenging due to dense cell distribution and complex morphology. In this paper, we present our winning solution for the RIVA Cervical Cytology Challenge, achieving 1st place in Track B and 2nd place in Track A. Our approach leverages a powerful baseline, integrating the Co-DINO framework with a Swin-Large backbone for robust multi-scale feature extraction. To address the dataset's unique fixed-size bounding box annotations, we formulate the detection task as a center-point prediction problem. Tailoring our approach to this formulation, we introduce a center-preserving data augmentation strategy and an analytical geometric box optimization to effectively absorb localization jitter. Finally, we apply track-specific loss tuning to adapt the loss weights for each task. Experiments demonstrate that our targeted optimizations improve detection performance, providing an effective pipeline for cytology image analysis. Our code is available at https://github.com/YanKong0408/Center-DETR. --- ### FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition Authors: Taichi Endo, Guoqing Hao, Kazuhiko Sumi Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02088v1 Continuous image editing aims to provide slider-style control of edit strength while preserving source-image fidelity and maintaining a consistent edit direction. Existing learning-based slider methods typically rely on auxiliary modules trained with synthetic or proxy supervision. This introduces additional training overhead and couples slider behavior to the training distribution, which can reduce reliability under distribution shifts in edits or domains. We propose \textit{FlowSlider}, a training-free method for continuous editing in Rectified Flow that requires no post-training. \textit{FlowSlider} decomposes FlowEdit's update into (i) a fidelity term, which acts as a source-conditioned stabilizer that preserves identity and structure, and (ii) a steering term that drives semantic transition toward the target edit. Geometric analysis and empirical measurements show that these terms are approximately orthogonal, enabling stable strength control by scaling only the steering term while keeping the fidelity term unchanged. As a result, \textit{FlowSlider} provides smooth and reliable control without post-training, improving continuous editing quality across diverse tasks. --- ### Country-wide, high-resolution monitoring of forest browning with Sentinel-2 Authors: Samantha Biegel, David Brüggemann, Francesco Grossi, Michele Volpi, Konrad Schindler, Benjamin D. Stocker Published: 2026-04-02 Categories: stat.AP, cs.CV arXiv: https://arxiv.org/abs/2604.02074v1 Natural and anthropogenic disturbances are impacting the health of forests worldwide. Monitoring forest disturbances at scale is important to inform conservation efforts. Here, we present a scalable approach for country-wide mapping of forest greenness anomalies at the 10 m resolution of Sentinel-2. Using relevant ecological and topographical context and an established representation of the vegetation cycle, we learn a predictive quantile model of the normalised difference vegetation index (NDVI) derived from Sentinel-2 data. The resulting expected seasonal cycles are used to detect NDVI anomalies across Switzerland between April 2017 and August 2025. Goodness-of-fit evaluations show that the conditional model explains 65% of the observed variations in the median seasonal cycle. The model consistently benefits from the local context information, particularly during the green-up period. The approach produces coherent spatial anomaly patterns and enables country-wide quantification of forest browning. Case studies with independent reference data from known events illustrate that the model reliably detects different types of disturbances. --- ### PLUME: Latent Reasoning Based Universal Multimodal Embedding Authors: Chenwei He, Xiangzhao Hao, Tianyu Yang, Yuxiang Ma, Yuheng Jia, Lingxiang Wu, Chaoyang Zhao, Haiyun Guo, Jinqiao Wang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02073v3 Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thought (CoT) rationales before extracting embeddings, enabling multimodal large language models to better infer complex query intent. However, explicit CoT incurs substantial inference overhead and can compress rich multimodal evidence into a narrow textual bottleneck. We propose PLUME, a latent reasoning framework that advances UME by replacing verbalized CoT with a short autoregressive rollout of continuous latent states. To support diverse multimodal queries, PLUME further introduces a semantic-anchor-guided transition adapter that steers latent rollout along different reasoning trajectories under the same fixed computation budget. To stabilize training, PLUME adopts a progressive explicit-to-latent curriculum that uses verbalized reasoning only as a temporary training scaffold and gradually transfers this behavior into hidden-state computation, eliminating explicit CoT at inference. On the 78-task MMEB-v2 benchmark, PLUME outperforms strong explicit-CoT UME baselines while reducing reasoning from hundreds of generated tokens to fewer than 10 latent steps, delivering over 30x faster inference. PLUME is especially well suited to retrieval settings where relevant evidence is dense, structurally complex, and difficult to organize through verbalized intermediate rationales, such as video and visual document retrieval. These results show that structured latent computation can preserve the benefits of intermediate reasoning without the overhead of explicit rationale generation, providing a stronger and more efficient paradigm for practical retrieval systems. --- ### Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection Authors: Soo Won Seo, KyungChae Lee, Hyungchan Cho, Taein Son, Nam Ik Cho, Jun Won Choi Published: 2026-04-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.02071v1 Human-Object Interaction (HOI) detection aims to localize human-object pairs and classify their interactions from a single image, a task that demands strong visual understanding and nuanced contextual reasoning. Recent approaches have leveraged Vision-Language Models (VLMs) to introduce semantic priors, significantly improving HOI detection performance. However, existing methods often fail to fully capitalize on the diverse contextual cues distributed across the entire scene. To overcome these limitations, we propose the Instance-centric Context Mining Network (InCoM-Net)-a novel framework that effectively integrates rich semantic knowledge extracted from VLMs with instance-specific features produced by an object detector. This design enables deeper interaction reasoning by modeling relationships not only within each detected instance but also across instances and their surrounding scene context. InCoM-Net comprises two core components: Instancecentric Context Refinement (ICR), which separately extracts intra-instance, inter-instance, and global contextual cues from VLM-derived features, and Progressive Context Aggregation (ProCA), which iteratively fuses these multicontext features with instance-level detector features to support high-level HOI reasoning. Extensive experiments on the HICO-DET and V-COCO benchmarks show that InCoM-Net achieves state-of-the-art performance, surpassing previous HOI detection methods. Code is available at https://github.com/nowuss/InCoM-Net. --- ### Network Structure in UK Payment Flows: Evidence on Economic Interdependencies and Implications for Real-Time Measurement Authors: Aditya Humnabadkar Published: 2026-04-02 Categories: cs.CV, econ.EM arXiv: https://arxiv.org/abs/2604.02068v1 Network analysis of inter-industry payment flows reveals structural economic relationships invisible to traditional bilateral measurement approaches, with significant implications for real-time economic monitoring. Analysing 532,346 UK payment records (2017--2024) across 89 industry sectors, we demonstrate that graph-theoretic features which include centrality measures and clustering coefficients improve payment flow forecasting by 8.8 percentage points beyond traditional time-series methods. Critically, network features prove most valuable during economic disruptions: during the COVID-19 pandemic, when traditional forecasting accuracy collapsed (R2} falling from 0.38 to 0.19), network-enhanced models maintained substantially better performance, with network contributions reaching +13.8 percentage points. The analysis identifies Financial Services, Wholesale Trade, and Professional Services as structurally central industries whose network positions indicate systemic importance beyond their transaction volumes. Network density increased 12.5\% over the sample period, with visible disruption during 2020 followed by recovery exceeding pre-pandemic integration levels. These findings suggest payment network monitoring could enhance official statistics production by providing leading indicators of structural economic change and improving nowcasting accuracy during periods when traditional temporal patterns prove unreliable. --- ### Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions Authors: Pengcheng Lyu, Chaokun Zhang, Gong Chen, Tao Tang, Zhaoxiang Luo Published: 2026-04-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.02061v1 Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence. However, real-world sensor and communication corruptions severely undermine this advantage. Crucially, existing approaches treat corruptions as static perturbations or passively conform to corrupted inputs, failing to actively recover the underlying clean semantics. To address this limitation, we introduce Diff-KD, a framework that integrates diffusion-based generative refinement into teacher-student knowledge distillation for robust collaborative perception. Diff-KD features two core components: (i) Progressive Knowledge Distillation (PKD), which treats local feature restoration as a conditional diffusion process to recover global semantics from corrupted observations; and (ii) Adaptive Gated Fusion (AGF), which dynamically weights neighbors based on ego reliability during fusion. Evaluated on OPV2V and DAIR-V2X under seven corruption types, Diff-KD achieves state-of-the-art performance in both detection accuracy and calibration robustness. --- ### CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects Authors: Jingliang Li, Jindou Jia, Tuo An, Chuhao Zhou, Xiangyu Chen, Shilin Shan, Boyu Ma, Bofan Lyu, Gen Li, Jianfei Yang Published: 2026-04-02 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.02060v2 When told to "cut the cake," a robot must choose the knife over nearby scissors, despite both objects affording the same cutting function. In real-world scenes, multiple objects may share identical affordances, yet only one is appropriate under the given task context. We call such cases confusing pairs. However, existing 3D affordance methods largely sidestep this challenge by evaluating isolated single objects, often with explicit category names provided in the query. We formalize Intent-Driven Confusable Affordance Grounding, a new 3D affordance setting that requires predicting a per-point affordance mask on the correct object within a multi-object point cloud, conditioned on implicit natural language intent. To study this problem, we construct CompassAD, the first benchmark centered on implicit intent in confusing multi-object compositions. It comprises 30 confusing object pairs spanning 16 affordance types, 6,422 compositions, and 88K+ query-answer pairs. Furthermore, we propose CompassNet, a framework that incorporates two dedicated modules tailored to this task. Instance-bounded Cross Injection (ICI) constrains language-geometry alignment within object boundaries to prevent cross-object semantic leakage. Bi-level Contrastive Refinement (BCR) enforces discrimination at both geometric-group and point levels, sharpening distinctions between target and confusable surfaces. Extensive experiments demonstrate state-of-the-art results on both seen and unseen queries, and deployment on a robotic manipulator confirms effective transfer to real-world grasping in confusing multi-object compositions. --- ### COMPASS: Fusion-Matched Supervision for Missing-Modality Human Sensing Authors: Hao Wang, Yanyu Qian, Pengcheng Weng, Zixuan Xia, William Dan, Yangxin Xu, Fei Wang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02056v3 Multimodal human activity recognition (HAR) and human pose estimation (HPE) must cope with modalities missing at inference. Completions generated for a fixed fusion model must preserve the fusion readout: what fusion uses from each modality. We propose COMPASS, a completion-and-fusion framework in which each modality occupies a fixed slot filled by an observed representation or a completion inferred from available inputs. Its core principle, fusion-matched supervision, supervises completions with same-sample real targets at readout granularity: token means for HAR, where fusion averages tokens, and per-joint representations for HPE, where fusion preserves joint structure. Trained with complete multimodal samples, COMPASS improves subset-averaged performance over the strongest baselines on XRF55 and MM-Fi for HAR and on MM-Fi for HPE. At fixed architecture, fusion-matched supervision outperforms full-token and centered-token matching in HAR, and joint-mean matching and no matching in HPE. The code is available at: https://github.com/haowangcoder/COMPASS. --- ### COMPASS: Complete Multimodal Fusion via Proxy Tokens and Shared Spaces for Ubiquitous Sensing Authors: Hao Wang, Yanyu Qian, Pengcheng Weng, Zixuan Xia, William Dan, Yangxin Xu, Fei Wang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02056v2 Missing modalities in multimodal sensing cause not only information loss but also a fusion-interface mismatch: a fusion head trained on a canonical set of modality slots must operate on changing observed subsets at inference time. We propose Compass, an interface-complete fusion framework that restores this canonical slot structure before prediction. Each modality is assigned a fixed fusion slot. Observed modalities populate their slots with real representations, while absent modalities are filled with target-slot completion representations estimated from the observed sources. Multiple source-specific estimates for the same missing slot are aggregated into a single slot filler, allowing the same lightweight fusion operator to be applied under arbitrary missing-modality patterns. Training uses synthetic modality masking, slot-compatibility supervision, and representation-space stabilization to make completed slots compatible with real modality representations and useful for downstream recognition. Across XRF55, MM-Fi, and OctoNet, Compass improves robustness under diverse single- and multiple-missing settings, including controlled comparisons against imputation, distillation, and translation-style baselines. These results suggest that preserving the fusion interface is a simple and effective principle for robust multimodal sensing. --- ### True to Tone? Quantifying Skin Tone Fidelity and Bias in Photographic-to-Virtual Human Pipelines Authors: Gabriel Ferri Schneider, Erick Menezes, Rafael Mecenas, Paulo Knob, Victor Araujo, Soraia Raupp Musse Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02055v1 Accurate reproduction of facial skin tone is essential for realism, identity preservation, and fairness in Virtual Human (VH) rendering. However, most accessible avatar creation pipelines rely on photographic inputs that lack colorimetric calibration, which can introduce inconsistencies and bias. We propose a fully automatic and scalable methodology to systematically evaluate skin tone fidelity across the VH generation pipeline. Our approach defines a full workflow that integrates skin color and illumination extraction, texture recolorization, real-time rendering, and quantitative color analysis. Using facial images from the Chicago Face Database (CFD), we compare skin tone extraction strategies based on cheek-region sampling, following the literature, and multidimensional masking derived from full-face analysis. Additionally, we test both strategies with lighting isolation, using the pre-trained TRUST framework, employed without any training or optimization within our pipeline. Extracted skin tones are applied to MetaHuman textures and rendered under multiple lighting configurations. Skin tone consistency is evaluated objectively in the CIELAB color space using the $ΔE$ metric and the Individual Typology Angle (ITA). The proposed methodology operates without manual intervention and, with the exception of pre-trained illumination compensation modules, the pipeline does not include learning or training stages, enabling low computational cost and large-scale evaluation. Using this framework, we generate and analyze approximately 19,848 rendered instances. Our results show phenotype-dependent behavior of extraction strategies and consistently higher colorimetric errors for darker skin tones. --- ### Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation Authors: Jaber Jaber, Osama Jaber Published: 2026-04-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.02051v1 Recursive transformers reuse a shared weight block across multiple depth steps, trading parameters for compute. A core limitation: every step applies the same transformation, preventing the model from composing distinct operations across depth. We present Ouroboros, a system that attaches a compact Controller hypernetwork to a recursive transformer block. The Controller observes the current hidden state, produces a per-step diagonal modulation vector, and applies it to frozen SVD-initialized LoRA bases, making each recurrence step input-dependent. We combine this with gated recurrence (bias-initialized to 88% retention) and per-step LayerNorm for stable deep iteration. On Qwen2.5-3B split into a Prelude/Recurrent/Coda architecture (17 of 36 layers retained), Ouroboros reduces training loss by 43.4% over the unmodified 17-layer baseline, recovering 51.3% of the performance gap caused by layer removal. The full system adds only 9.2M trainable parameters (Controller, gate, and per-step norms) yet outperforms equivalently-sized static per-step LoRA by 1.44 loss points at depth 1 and remains ahead across all tested depths (1, 4, 8, 16) and ranks (8, 32, 64). We also find that gated recurrence is essential: without it, recursive layer application makes the model strictly worse. These gains are measured on the training distribution; on held-out text, the Controller does not yet improve over the baseline, a limitation we attribute to frozen downstream layers and discuss in detail. Code: https://github.com/RightNow-AI/ouroboros --- ### Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models Authors: Issa Sugiura, Keito Sasagawa, Keisuke Nakao, Koki Maeda, Ziqi Yin, Zhishen Yang, Shuhei Kurita, Yusuke Oda, Ryoko Tokuhisa, Daisuke Kawahara, Naoaki Okazaki Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02048v2 Developing vision-language models (VLMs) that generalize across diverse tasks requires large-scale training datasets with diverse content. In English, such datasets are typically constructed by aggregating and curating numerous existing visual question answering (VQA) resources. However, this strategy does not readily extend to other languages, where VQA datasets remain limited in both scale and domain coverage. In this work, we introduce Jagle, the largest Japanese multimodal post-training dataset to date, comprising approximately 9.2 million instances across diverse tasks. Rather than relying on existing VQA datasets, we collect heterogeneous source data, including images, image-text pairs, and PDF documents, and generate VQA pairs through multiple strategies such as VLM-based QA generation, translation, and text rendering. Experiments demonstrate that a 2.2B model trained with Jagle surpasses InternVL3.5-2B in average score across ten Japanese evaluation tasks and comes within five points of Qwen3-VL-2B-Instruct. Moreover, combining Jagle with FineVision improves English performance over training with FineVision alone. These benefits generalize across model backbones and scales: LLM-jp-4-VL 9B beta, a 9B-scale model built on the Japanese-centric LLM-jp-4-8B-instruct, achieves Japanese performance comparable to Qwen3-VL-8B-Instruct. To facilitate reproducibility and future research, we release the dataset, models, and code. --- ### Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models Authors: Issa Sugiura, Keito Sasagawa, Keisuke Nakao, Koki Maeda, Ziqi Yin, Zhishen Yang, Shuhei Kurita, Yusuke Oda, Ryoko Tokuhisa, Daisuke Kawahara, Naoaki Okazaki Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02048v1 Developing vision-language models (VLMs) that generalize across diverse tasks requires large-scale training datasets with diverse content. In English, such datasets are typically constructed by aggregating and curating numerous existing visual question answering (VQA) resources. However, this strategy does not readily extend to other languages, where VQA datasets remain limited in both scale and domain coverage, posing a major obstacle to building high-quality multilingual and non-English VLMs. In this work, we introduce Jagle, the largest Japanese multimodal post-training dataset to date, comprising approximately 9.2 million instances across diverse tasks. Rather than relying on existing VQA datasets, we collect heterogeneous source data, including images, image-text pairs, and PDF documents, and generate VQA pairs through multiple strategies such as VLM-based QA generation, translation, and text rendering. Experiments demonstrate that a 2.2B model trained with Jagle achieves strong performance on Japanese tasks, surpassing InternVL3.5-2B in average score across ten Japanese evaluation tasks and approaching within five points of Qwen3-VL-2B-Instruct. Furthermore, combining Jagle with FineVision does not degrade English performance; instead, it improves English performance compared to training with FineVision alone. To facilitate reproducibility and future research, we release the dataset, trained models, and code. --- ### Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding Authors: Tao Jin, Phuong Minh Nguyen, Naoya Inoue Published: 2026-04-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.02047v2 Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding depth requires sacrificing breadth (fallback options) under a fixed verification budget. Existing training-free methods draft from a single token source and shape their trees without distinguishing candidate quality across origins. We observe that two common training-free token sources -- n-gram matches copied from the input context, and statistical predictions from prior forward passes -- differ sharply in acceptance rate (~6x median gap, range 2-18x across five models and five benchmarks). We prove that when such a quality gap exists, the optimal tree is anisotropic (asymmetric): reliable tokens should form a deep chain while unreliable tokens spread as wide branches, raising the depth ceiling of balanced trees. We realize this structure in GOOSE, a training-free framework that builds an adaptive spine tree: a deep chain of high-acceptance context-matched tokens with wide branches of low-acceptance alternatives at each node. The resulting tree provably accepts at least as many tokens per step as either source alone. On five LLMs (7B-33B) and five benchmarks, GOOSE achieves 1.9-4.3x lossless speedup, outperforming balanced-tree baselines by 12-33% under the same budget. --- ### Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding Authors: Tao Jin, Phuong Minh Nguyen, Naoya Inoue Published: 2026-04-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.02047v1 Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding depth requires sacrificing breadth (fallback options) under a fixed verification budget. Existing training-free methods draft from a single token source and shape their trees without distinguishing candidate quality across origins. We observe that two common training-free token sources - n-gram matches copied from the input context, and statistical predictions from prior forward passes - differ dramatically in acceptance rate (~6x median gap, range 2-18x across five models and five benchmarks). We prove that when such a quality gap exists, the optimal tree is anisotropic (asymmetric): reliable tokens should form a deep chain while unreliable tokens spread as wide branches, breaking through the depth limit of balanced trees. We realize this structure in GOOSE, a training-free framework that builds an adaptive spine tree - a deep chain of high-acceptance context-matched tokens with wide branches of low-acceptance alternatives at each node. We prove that the number of tokens accepted per step is at least as large as that of either source used alone. On five LLMs (7B-33B) and five benchmarks, GOOSE achieves 1.9-4.3x lossless speedup, outperforming balanced-tree baselines by 12-33% under the same budget. --- ### BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs Authors: Nicolas Boizard, Théo Deschamps-Berger, Hippolyte Gisserot-Boukhlef, Céline Hudelot, Pierre Colombo Published: 2026-04-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.02045v1 Transforming causal generative language models into bidirectional encoders offers a powerful alternative to BERT-style architectures. However, current approaches remain limited: they lack consensus on optimal training objectives, suffer from catastrophic forgetting at scale, and fail to flexibly integrate the vast ecosystem of specialized generative models. In this work, through systematic ablations on the Gemma3 and Qwen3 families, we identify the key factors driving successful adaptation, highlighting the critical role of an often-omitted prior masking phase. To scale this process without original pre-training data, we introduce a dual strategy combining linear weight merging with a lightweight multi-domain data mixture that mitigates catastrophic forgetting. Finally, we augment our encoders by merging them with specialized causal models, seamlessly transferring modality- and domain-specific capabilities. This open-source recipe, designed for any causal decoder LLM, yields BidirLM, a family of five encoders that outperform alternatives on text, vision, and audio representation benchmarks. --- ### Tracking the emergence of linguistic structure in self-supervised models learning from speech Authors: Marianne de Heer Kloots, Martijn Bentum, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen, Willem Zuidema Published: 2026-04-02 Categories: cs.CL, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2604.02043v1 Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model training? We study the encoding of a wide range of linguistic structures, across layers and intermediate checkpoints of six Wav2Vec2 and HuBERT models trained on spoken Dutch. We find that different levels of linguistic structure show notably distinct layerwise patterns as well as learning trajectories, which can partially be explained by differences in their degree of abstraction from the acoustic signal and the timescale at which information from the input is integrated. Moreover, we find that the level at which pre-training objectives are defined strongly affects both the layerwise organization and the learning trajectories of linguistic structures, with greater parallelism induced by higher-order prediction tasks (i.e. iteratively refined pseudo-labels). --- ### Efficient Reasoning via Thought Compression for Language Segmentation Authors: Qing Zhou, Shiyu Zhang, Yuyu Jia, Junyu Gao, Weiping Ni, Junzheng Wu, Qi Wang Published: 2026-04-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.02040v1 Chain-of-thought (CoT) reasoning has significantly improved the performance of large multimodal models in language-guided segmentation, yet its prohibitive computational cost, stemming from generating verbose rationales, limits real-world applicability. We introduce WISE (Wisdom from Internal Self-Exploration), a novel paradigm for efficient reasoning guided by the principle of \textit{thinking twice -- once for learning, once for speed}. WISE trains a model to generate a structured sequence: a concise rationale, the final answer, and then a detailed explanation. By placing the concise rationale first, our method leverages autoregressive conditioning to enforce that the concise rationale acts as a sufficient summary for generating the detailed explanation. This structure is reinforced by a self-distillation objective that jointly rewards semantic fidelity and conciseness, compelling the model to internalize its detailed reasoning into a compact form. At inference, the detailed explanation is omitted. To address the resulting conditional distribution shift, our inference strategy, WISE-S, employs a simple prompting technique that injects a brevity-focused instruction into the user's query. This final adjustment facilitates the robust activation of the learned concise policy, unlocking the full benefits of our framework. Extensive experiments show that WISE-S achieves state-of-the-art zero-shot performance on the ReasonSeg benchmark with 58.3 cIoU, while reducing the average reasoning length by nearly \textbf{5$\times$} -- from 112 to just 23 tokens. Code is available at \href{https://github.com/mrazhou/WISE}{WISE}. --- ### Reinforcement Learning for Speculative Trading under Exploratory Framework Authors: Yun Zhao, Alex S. L. Tse, Harry Zheng Published: 2026-04-02 Categories: q-fin.MF, cs.LG, math.OC, q-fin.CP, q-fin.TR arXiv: https://arxiv.org/abs/2604.02035v1 We study a speculative trading problem within the exploratory reinforcement learning (RL) framework of Wang et al. (2020). The problem is formulated as a sequential optimal stopping problem over entry and exit times under general utility function and price process. We first consider a relaxed version of the problem in which the stopping times are modeled by the jump times of Cox processes driven by bounded, non-randomized intensity controls. Under the exploratory formulation, the agent's randomized control is characterized via the probability measure over the jump intensities, and their objective function is regularized by Shannon's differential entropy. This yields a system of the exploratory HJB equations and Gibbs distributions in closed-form as the optimal policy. Error estimates and convergence of the RL objective to the value function of the original problem are established. Finally, an RL algorithm is designed, and its implementation is showcased in a pairs-trading application. --- ### AI in Insurance: Adaptive Questionnaires for Improved Risk Profiling Authors: Diogo Silva, João Teixeira, Bruno Lima Published: 2026-04-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.02034v1 Insurance application processes often rely on lengthy and standardized questionnaires that struggle to capture individual differences. Moreover, insurers must blindly trust users' responses, increasing the chances of fraud. The ARQuest framework introduces a new approach to underwriting by using Large Language Models (LLMs) and alternative data sources to create personalized and adaptive questionnaires. Techniques such as social media image analysis, geographic data categorization, and Retrieval Augmented Generation (RAG) are used to extract meaningful user insights and guide targeted follow-up questions. A life insurance system integrated into an industry partner mobile app was tested in two experiments. While traditional questionnaires yielded slightly higher accuracy in risk assessment, adaptive versions powered by GPT models required fewer questions and were preferred by users for their more fluid and engaging experience. ARQuest shows great potential to improve user satisfaction and streamline insurance processes. With further development, this approach may exceed traditional methods regarding risk accuracy and help drive innovation in the insurance industry. --- ### IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline Authors: Sebastian-Ion Nae, Radu Moldoveanu, Alexandra Stefania Ghita, Adina Magda Florea Published: 2026-04-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.02032v1 Understanding human behaviour in crowded indoor environments is central to surveillance, smart buildings, and human-robot interaction, yet existing datasets rarely capture real-world indoor complexity at scale. We introduce IndoorCrowd, a multi-scene dataset for indoor human detection, instance segmentation, and multi-object tracking, collected across four campus locations (ACS-EC, ACS-EG, IE-Central, R-Central). It comprises $31$ videos ($9{,}913$ frames at $5$fps) with human-verified, per-instance segmentation masks. A $620$-frame control subset benchmarks three foundation-model auto-annotators: SAM3, GroundingSAM, and EfficientGroundingSAM, against human labels using Cohen's $κ$, AP, precision, recall, and mask IoU. A further $2{,}552$-frame subset supports multi-object tracking with continuous identity tracks in MOTChallenge format. We establish detection, segmentation, and tracking baselines using YOLOv8n, YOLOv26n, and RT-DETR-L paired with ByteTrack, BoT-SORT, and OC-SORT. Per-scene analysis reveals substantial difficulty variation driven by crowd density, scale, and occlusion: ACS-EC, with $79.3\%$ dense frames and a mean instance scale of $60.8$px, is the most challenging scene. The project page is available at https://sheepseb.github.io/IndoorCrowd/. ---