# Research Papers — 2026-04 · bundle page 163 of 233 > Full-text markdown of papers #8101–8150 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/163 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/162.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/164.md) ### KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation Authors: Tongbo Chen, Zhengxi Lu, Zhan Xu, Guocheng Shao, Shaohan Zhao, Fei Tang, Yong Du, Kaitao Song, Yizhou Liu, Yuchen Yan, Wenqi Zhang, Xu Tan et al. Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08455v1 Personalized mobile agents that infer user preferences and calibrate proactive assistance hold great promise as everyday digital assistants, yet existing benchmarks fail to capture what this requires. Prior work evaluates preference recovery from static histories or intent prediction from fixed contexts. Neither tests whether an agent can elicit missing preferences through interaction, nor whether it can decide when to intervene, seek consent, or remain silent in a live GUI environment. We introduce KnowU-Bench, an online benchmark for personalized mobile agents built on a reproducible Android emulation environment, covering 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks. Unlike prior work that treats user preferences as static context, KnowU-Bench hides the user profile from the agent and exposes only behavioral logs, forcing genuine preference inference rather than context lookup. To support multi-turn preference elicitation, it instantiates an LLM-driven user simulator grounded in structured profiles, enabling realistic clarification dialogues and proactive consent handling. Beyond personalization, KnowU-Bench provides comprehensive evaluation of the complete proactive decision chain, including grounded GUI execution, consent negotiation, and post-rejection restraint, evaluated through a hybrid protocol combining rule-based verification with LLM-as-a-Judge scoring. Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions requiring user preference inference or intervention calibration, even for frontier models like Claude Sonnet 4.6. The core bottlenecks are not GUI navigation but preference acquisition and intervention calibration, exposing a fundamental gap between competent interface operation and trustworthy personal assistance. --- ### Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks Authors: Haokai Ma, Lee Yan Zhen, Gang Yang, Yunshan Ma, Ee-Chien Chang, Tat-Seng Chua Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08454v1 Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause severe real-world harm, bringing the previously overlooked issue of confidence faithfulness back to the forefront. A promising solution is to jointly optimize unsupervised Reinforcement Learning from Internal Feedback (RLIF) with reasoning-trace-guided Reasoning Distillation (RD), which may face three persistent challenges: scarcity of high-quality training corpora, factually unwarranted overconfidence and indiscriminate fusion that amplifies erroneous updates. Inspired by the human confidence accumulation from uncertainty to certainty, we propose Progressive Reasoning Gain (PRG) to measure whether reasoning steps progressively strengthen support for the final answer. Furthermore, we introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF via a PRG-style metric, using scarce supervised reasoning traces as a stable anchor while exploiting abundant unlabeled queries for scalability. Experiments on several domain-specific and general benchmarks demonstrate that HyTuning improves accuracy while achieving confidence faithfulness under limited supervision, supporting a practical "Less Approximates More" effect. --- ### AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages Authors: Lilian Wanzare, Cynthia Amol, Ezekiel Maina, Nelson Odhiambo, Hope Kerubo, Leila Misula, Vivian Oloo, Rennish Mboya, Edwin Onkoba, Edward Ombui, Joseph Muguro, Ciira wa Maina et al. Published: 2026-04-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.08448v2 AfriVoices-KE is a large-scale multilingual speech dataset comprising approximately 3,000 hours of audio across five Kenyan languages: Dholuo, Kikuyu, Kalenjin, Maasai, and Somali. The dataset includes 750 hours of scripted speech and 2,250 hours of spontaneous speech, collected from 4,777 native speakers across diverse regions and demographics. This work addresses the critical underrepresentation of African languages in speech technology by providing a high-quality, linguistically diverse resource. Data collection followed a dual methodology: scripted recordings drew from compiled text corpora, translations, and domain-specific generated sentences spanning eleven domains relevant to the Kenyan context, while unscripted speech was elicited through textual and image prompts to capture natural linguistic variation and dialectal nuances. A customized mobile application enabled contributors to record using smartphones. Quality assurance operated at multiple layers, encompassing automated signal-to-noise ratio validation prior to recording and human review for content accuracy. Though the project encountered challenges common to low-resource settings, including unreliable infrastructure, device compatibility issues, and community trust barriers, these were mitigated through local mobilizers, stakeholder partnerships, and adaptive training protocols. AfriVoices-KE provides a foundational resource for developing inclusive automatic speech recognition and text-to-speech systems, while advancing the digital preservation of Kenya's linguistic heritage. --- ### Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond Authors: Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08438v3 The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $Θ(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper query complexities for existing unbiased randomized algorithms. Within this framework, we systematically develop a linear-space algorithm that requires $O(\frac{n}{ε^{2}}\log\frac{1}δ)$ utility queries to ensure $P(\|\hat{\boldsymbolφ}-\boldsymbolφ\|_{2}\geqε)\leq δ$ for all commonly used semi-values. In particular, our framework naturally bridges OFA, unbiased kernelSHAP, SHAP-IQ and the regression-adjusted approach, and definitively characterizes when paired sampling is beneficial. Moreover, our algorithm allows explicit minimization of the mean squared error $\mathbb{E}(\|\hat{\boldsymbolφ}-\boldsymbolφ\|_{2}^{2})$ for each specific utility function. Accordingly, we introduce the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean squared error. All of our theoretical findings are experimentally validated. Our code is available at https://github.com/watml/adalina. --- ### Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond Authors: Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08438v2 The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $Θ(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper query complexities for existing unbiased randomized algorithms. Within this framework, we systematically develop a linear-space algorithm that requires $O(\frac{n}{ε^{2}}\log\frac{1}δ)$ utility queries to ensure $P(\|\hat{\boldsymbolφ}-\boldsymbolφ\|_{2}\geqε)\leq δ$ for all commonly used semi-values. In particular, our framework naturally bridges OFA, unbiased kernelSHAP, SHAP-IQ and the regression-adjusted approach, and definitively characterizes when paired sampling is beneficial. Moreover, our algorithm allows explicit minimization of the mean squared error $\mathbb{E}(\|\hat{\boldsymbolφ}-\boldsymbolφ\|_{2}^{2})$ for each specific utility function. Accordingly, we introduce the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean squared error. All of our theoretical findings are experimentally validated. Our code is available at https://github.com/watml/adalina. --- ### HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment Authors: Changdao Chen, Qinqiuhong Ye, Hao Chen, Jinyu Wang Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08435v2 It remains challenging to assess driver fatigue from untrimmed videos under constrained computational budgets, due to the difficulty of modeling long-range temporal dependencies in subtle facial expressions. Some existing approaches rely on computationally heavy architectures, whereas others employ traditional lightweight pairwise graph networks, despite their limited capacity to model high-order synergies and global temporal context. Therefore, we propose HST-HGN, a novel Heterogeneous Spatial-Temporal Hypergraph Network driven by Bidirectional State Space Models. Spatially, we introduce a hierarchical hypergraph network to fuse pose-disentangled geometric topologies with multi-modal texture patches dynamically. This formulation encapsulates high-order synergistic facial deformations, effectively overcoming the limitations of conventional methods. In temporal terms, a Bi-Mamba module with linear complexity is applied to perform bidirectional sequence modeling. This explicit temporal-evolution filtering enables the network to distinguish highly ambiguous transient actions, such as yawning versus speaking, while encompassing their complete physiological lifecycles. Extensive evaluations across diverse fatigue benchmarks demonstrate that HST-HGN achieves state-of-the-art performance. In particular, our method strikes a balance between discriminative power and computational efficiency, making it well-suited for real-time in-cabin edge deployment. --- ### Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules Authors: Luca Nogueira Calçado, Sergei K. Turitsyn, Egor Manuylovich Published: 2026-04-09 Categories: physics.optics, cs.AI arXiv: https://arxiv.org/abs/2604.08432v2 Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities, reintroducing optical-electrical-optical bottlenecks. Here we introduce small-scale photonic Kolmogorov-Arnold networks (SSP-KANs) implemented entirely with standard telecommunications components. Each network edge employs a trainable nonlinear module composed of a Mach-Zehnder interferometer, semiconductor optical amplifier, and variable optical attenuators, providing a four-parameter transfer function derived from gain saturation and interferometric mixing. Despite the constrained functional form of these optical nonlinearities, SSP-KANs comprising only a few optical modules achieve strong nonlinear inference performance across classification, regression, and image recognition tasks, approaching software baselines with significantly fewer parameters. A four-module network achieves $94.3$\% (IQR: $90.3$--$97.4$\%, 10~seeds) accuracy on nonlinear classification benchmarks; a seven-module network attains $R^2 = 0.986 \pm 0.015$ on six-input regression. Performance remains robust under realistic hardware impairments, maintaining high accuracy down to 6-bit input resolution and 14 dB signal-to-noise ratio. By using a fully differentiable physics model for end-to-end optimisation of optical parameters, this work establishes a practical pathway from simulation to experimental demonstration of photonic KANs using commodity telecom hardware. --- ### KV Cache Offloading for Context-Intensive Tasks Authors: Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev, Vyacheslav Zhdanovskiy, Yegor Yershov Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08426v5 With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising approach to reduce memory footprint and inference latency while preserving accuracy. Prior evaluations have largely focused on tasks that do not require extracting large amounts of information from the context. In this work, we study KV-cache offloading on context-intensive tasks: problems where the solution requires looking up a lot of information from the input prompt. We create and release the Text2JSON benchmark, a highly context-intensive task that requires extracting structured knowledge from raw text. We evaluate modern KV offloading on Text2JSON and other context-intensive tasks and find significant performance degradation on both Llama 3 and Qwen 3 models. Our analysis identifies two key reasons for poor accuracy: low-rank projection of keys and unreliable landmarks, and proposes a simpler alternative strategy that significantly improves accuracy across multiple LLM families and benchmarks. These findings highlight the need for a comprehensive and rigorous evaluation of long-context compression techniques. --- ### KV Cache Offloading for Context-Intensive Tasks Authors: Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev, Vyacheslav Zhdanovskiy, Yegor Yershov Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08426v4 With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising approach to reduce memory footprint and inference latency while preserving accuracy. Prior evaluations have largely focused on tasks that do not require extracting large amounts of information from the context. In this work, we study KV-cache offloading on context-intensive tasks: problems where the solution requires looking up a lot of information from the input prompt. We create and release the Text2JSON benchmark, a highly context-intensive task that requires extracting structured knowledge from raw text. We evaluate modern KV offloading on Text2JSON and other context-intensive tasks and find significant performance degradation on both Llama 3 and Qwen 3 models. Our analysis identifies two key reasons for poor accuracy: low-rank projection of keys and unreliable landmarks, and proposes a simpler alternative strategy that significantly improves accuracy across multiple LLM families and benchmarks. These findings highlight the need for a comprehensive and rigorous evaluation of long-context compression techniques. --- ### Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM Authors: Samay U. Shetty, Tharindu Cyril Weerasooriya, Deepak Pandita, Christopher M. Homan Published: 2026-04-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08425v1 When humans label subjective content, they disagree, and that disagreement is not noise. It reflects genuine differences in perspective shaped by annotators' social identities and lived experiences. Yet standard practice still flattens these judgments into a single majority label, and recent LLM-based approaches fare no better: we show that prompted large language models, even with chain-of-thought reasoning, fail to recover the structure of human disagreement. We introduce DiADEM, a neural architecture that learns "how much each demographic axis matters" for predicting who will disagree and on what. DiADEM encodes annotators through per-demographic projections governed by a learned importance vector $\boldsymbolα$, fuses annotator and item representations via complementary concatenation and Hadamard interactions, and is trained with a novel item-level disagreement loss that directly penalizes mispredicted annotation variance. On the DICES conversational-safety and VOICED political-offense benchmarks, DiADEM substantially outperforms both the LLM-as-a-judge and neural model baselines across standard and perspectivist metrics, achieving strong disagreement tracking ($r{=}0.75$ on DICES). The learned $\boldsymbolα$ weights reveal that race and age consistently emerge as the most influential demographic factors driving annotator disagreement across both datasets. Our results demonstrate that explicitly modeling who annotators are not just what they label is essential for NLP systems that aim to faithfully represent human interpretive diversity. --- ### On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities Authors: Lorenzo Capelli, Leandro de Souza Rosa, Maurizio De Tommasi, Livia Manovi, Andriy Enttsel, Mauro Mangia, Riccardo Rovatti, Ilaria Pinci, Carlo Ciancarelli, Eleonora Mariotti, Gianluca Furano Published: 2026-04-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08424v1 The increasing autonomy of spacecraft demands fault-detection systems that are both reliable and explainable. This work addresses eXplainable Artificial Intelligence for onboard Fault Detection, Isolation and Recovery within the Attitude and Orbit Control Subsystem by introducing a framework that enhances interpretability in neural anomaly detectors. We propose a method to derive low-dimensional, semantically annotated encodings from intermediate neural activations, called peepholes. Applied to a convolutional autoencoder, the framework produces interpretable indicators that enable the identification and localization of anomalies in reaction-wheel telemetry. Peepholes analysis further reveals bias detection and supports fault localization. The proposed framework enables the semantic characterization of detected anomalies while requiring only a marginal increase in computational resources, thus supporting its feasibility for on-board deployment. --- ### Synthetic Data for any Differentiable Target Authors: Tristan Thrush, Sung Min Park, Herman Brunborg, Luke Bailey, Marcel Roed, Neil Band, Christopher Potts, Tatsunori Hashimoto Published: 2026-04-09 Categories: cs.CL, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.08423v1 What are the limits of controlling language models via synthetic training data? We develop a reinforcement learning (RL) primitive, the Dataset Policy Gradient (DPG), which can precisely optimize synthetic data generators to produce a dataset of targeted examples. When used for supervised fine-tuning (SFT) of a target model, these examples cause the target model to do well on a differentiable metric of our choice. Our approach achieves this by taking exact data attribution via higher-order gradients and using those scores as policy gradient rewards. We prove that this procedure closely approximates the true, intractable gradient for the synthetic data generator. To illustrate the potential of DPG, we show that, using only SFT on generated examples, we can cause the target model's LM head weights to (1) embed a QR code, (2) embed the pattern $\texttt{67}$, and (3) have lower $\ell^2$ norm. We additionally show that we can cause the generator to (4) rephrase inputs in a new language and (5) produce a specific UUID, even though neither of these objectives is conveyed in the generator's input prompts. These findings suggest that DPG is a powerful and flexible technique for shaping model properties using only synthetic training examples. --- ### Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction Authors: Marco Gabriele Fedozzi, Yukie Nagai, Francesco Rea, Alessandra Sciutti Published: 2026-04-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.08418v1 Inspired by the human ability to understand and predict others, we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics. Following recent results regarding the ontogeny of the Mirror Neuron System (MNS), we focus on the preliminary objective of self-actions prediction. We find a good MNS-inspired model in the existing Deep Modality Blending Network (DMBN), able to reconstruct the visuo-motor sensory signal during a partially observed action sequence by leveraging the probabilistic generation of CNP. After a qualitative and quantitative evaluation, we highlight its difficulties in generalizing to unseen action sequences, and identify the cause in its inner representation of time. Therefore, we propose a revised version, termed DMBN-Positional Time Encoding (DMBN-PTE), that facilitates learning a more robust representation of temporal information, and provide preliminary results of its effectiveness in expanding the applicability of the architecture. DMBN-PTE figures as a first step in the development of robotic systems that autonomously learn to forecast actions on longer time scales refining their predictions with incoming observations. --- ### Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI Authors: David Joohun Kim, Daniyal Anjum, Bonny Banerjee, Omar Abbasi Published: 2026-04-09 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2604.08412v1 We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker environments with temporally ambiguous utterances, this task is more effectively modelled as a sequential routing problem over interaction history than as an utterance-local classification task. We formalize this as Sequential Device-Addressed Routing (SDAR) and present the Selective Attention System (SAS), an on-device implementation that instantiates this formulation. On a held-out 60-hour multi-speaker English test set, the primary audio-only configuration achieves F1=0.86 (precision=0.89, recall=0.83); with an optional camera, audio+video fusion raises F1 to 0.95 (precision=0.97, recall=0.93). Removing causal interaction history (Stage~3) reduced F1 from 0.95 to 0.57+/-0.03 in the audio+video configuration under our evaluation protocol. Among the tested components, this was the largest observed ablation effect, indicating that short-horizon interaction history carries substantial decision-relevant information in the evaluated setting. SAS runs fully on-device on ARM Cortex-A class hardware (<150 ms latency, <20 MB footprint). All results are from internal evaluation on a proprietary dataset evaluated primarily in English; a 5-hour evaluation subset may be shared for independent verification (Section 8.8). --- ### What a Comfortable World: Ergonomic Principles Guided Apartment Layout Generation Authors: Piotr Nieciecki, Aleksander Plocharski, Przemyslaw Musialski Published: 2026-04-09 Categories: cs.GR, cs.LG arXiv: https://arxiv.org/abs/2604.08411v1 Current data-driven floor plan generation methods often reproduce the ergonomic inefficiencies found in real-world training datasets. To address this, we propose a novel approach that integrates architectural design principles directly into a transformer-based generative process. We formulate differentiable loss functions based on established architectural standards from literature to optimize room adjacency and proximity. By guiding the model with these ergonomic priors during training, our method produces layouts with significantly improved livability metrics. Comparative evaluations show that our approach outperforms baselines in ergonomic compliance while maintaining high structural validity. --- ### BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields Authors: Fan Yang, Wenrui Chen, Guorun Yan, Ruize Liao, Wanjun Jia, Dongsheng Luo, Jiacheng Lin, Kailun Yang, Zhiyong Li, Yaonan Wang Published: 2026-04-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.08410v2 In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localization, and physically interpretable execution. Modular hierarchical methods are more controllable and interpretable than end-to-end VLA approaches, but existing ones still rely on predefined affordance labels and lack the tight semantic--pose coupling needed for functional dexterous manipulation. To address this, we propose BLaDA (Bridging Language to Dexterous Actions in 3DGS fields), an interpretable zero-shot framework that grounds open-vocabulary instructions as perceptual and control constraints for functional dexterous manipulation. BLaDA establishes an interpretable reasoning chain by first parsing natural language into a structured sextuple of manipulation constraints via a Knowledge-guided Language Parsing (KLP) module. To achieve pose-consistent spatial reasoning, we introduce the Triangular Functional Point Localization (TriLocation) module, which utilizes 3D Gaussian Splatting as a continuous scene representation and identifies functional regions under triangular geometric constraints. Finally, the 3D Keypoint Grasp Matrix Transformation Execution (KGT3D+) module decodes these semantic-geometric constraints into physically plausible wrist poses and finger-level commands. Extensive experiments on complex benchmarks demonstrate that BLaDA significantly outperforms existing methods in both affordance grounding precision and the success rate of functional manipulation across diverse categories and tasks. Code will be publicly available at https://github.com/PopeyePxx/BLaDA. --- ### SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation Authors: Wenli Zhang, Xianglong Shi, Sirui Zhao, Xinqi Chen, Guo Cheng, Yifan Xu, Tong Xu, Yong Liao Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08405v3 Diffusion-based audio-driven talking-head generation enables realistic portrait animation, but also introduces risks of misuse, such as fraud and misinformation. Existing protection methods are largely limited to a single modality, and neither image-only nor audio-only attacks can effectively suppress speech-driven facial dynamics. To address this gap, we propose SyncBreaker, a stage-aware multimodal protection framework that jointly perturbs portrait and audio inputs under modality-specific perceptual constraints. Our key contributions are twofold. First, for the image stream, we introduce nullifying supervision with Multi-Interval Sampling (MIS) across diffusion stages to steer the generation toward the static reference portrait by aggregating guidance from multiple denoising intervals. Second, for the audio stream, we propose Cross-Attention Fooling (CAF), which suppresses interval-specific audio-conditioned cross-attention responses. Both streams are optimized independently and combined at inference time to enable flexible deployment. We evaluate SyncBreaker in a white-box proactive protection setting. Extensive experiments demonstrate that SyncBreaker more effectively degrades lip synchronization and facial dynamics than strong single-modality baselines, while preserving input perceptual quality and remaining robust under purification. Code: https://github.com/kitty384/SyncBreaker. --- ### Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization Authors: Simon Zhang, Ryan P. DeMilt, Kun Jin, Cathy H. Xia Published: 2026-04-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.08404v2 Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice when training and testing data come from different environments. Covariate shift is a type of distribution shift that occurs only in the input data, while the concept distribution stays invariant. We propose RIA - Regularization for Invariance with Adversarial training, a new method for OoD generalization under convariate shift. Motivated by an analogy to $Q$-learning, it performs an adversarial exploration for counterfactual data environments. These new environments are induced by adversarial label invariant data augmentations that prevent a collapse to an in-distribution trained learner. It works with many existing OoD generalization methods for covariate shift that can be formulated as constrained optimization problems. We develop an alternating gradient descent-ascent algorithm to solve the problem in the context of causally generated graph data, and perform extensive experiments on OoD graph classification for various kinds of synthetic and natural distribution shifts. We demonstrate that our method can achieve high accuracy compared with OoD baselines. --- ### Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing Authors: Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu, Xuehe Wang, Edith Cheuk Han Ngai Published: 2026-04-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08401v1 In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing unsupported beliefs repeatedly stored and propagated across decision steps, leading to systematic behavioral drift in long-horizon agentic systems. Most existing strategies rely on the consensus mechanism, conflating agreement with faithfulness. In this paper, inspired by the vulnerability of unfaithful intermediate reasoning trajectories, we propose \textbf{S}elf-\textbf{A}udited \textbf{Ve}rified \textbf{R}easoning (\textsc{SAVeR}), a novel framework that enforces verification over internal belief states within the agent before action commitment, achieving faithful reasoning. Concretely, we structurally generate persona-based diverse candidate beliefs for selection under a faithfulness-relevant structure space. To achieve reasoning faithfulness, we perform adversarial auditing to localize violations and repair through constraint-guided minimal interventions under verifiable acceptance criteria. Extensive experiments on six benchmark datasets demonstrate that our approach consistently improves reasoning faithfulness while preserving competitive end-task performance. --- ### Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks Authors: Mayuka Jayawardhana, Nihal Sharma, Kazem Meidani, Bayan Bruss, Tom Goldstein, Doron Bergman Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08400v1 Tabular foundation models, particularly Prior-data Fitted Networks like TabPFN have emerged as the leading contender in a myriad of tasks ranging from data imputation to label prediction on the tabular data format surpassing the historical successes of tree-based models. This has led to investigations on their applicability to forecasting time series data which can be formulated as a tabular problem. While recent work to this end has displayed positive results, most works have limited their treatment of multivariate time series problems to several independent univariate time series forecasting subproblems, thus ignoring any inter-channel interactions. Overcoming this limitation, we introduce a generally applicable framework for multivariate time series forecasting using tabular foundation models. We achieve this by recasting the multivariate time series forecasting problem as a series of scalar regression problems which can then be solved zero-shot by any tabular foundation model with regression capabilities. We present results of our method using the TabPFN-TS backbone and compare performance with the current state of the art tabular methods. --- ### ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification Authors: Paul Quinlan, Qingguo Li, Xiaodan Zhu Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08398v1 Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have shown great promise in one-to-many scenarios, where a model is pre-trained on one dataset and fine-tuned on a downstream dataset, they have struggled to generalize to new datasets when more datasets are added during pre-training. This is a fundamental challenge in building foundation models for time-series data, as it limits the ability to develop models that can learn from a large variety of diverse datasets available. To address this challenge, we present a new pre-training paradigm for time-series data called ADAPT, which can efficiently align the physical properties of data in the time-series domain, enabling mixed-batch pre-training despite the extreme discrepancies in the input sizes and channel dimensions of pre-training data. We trained on 162 time-series classification datasets and set new state-of-the-art performance for classification benchmarks. We successfully train a model within the time-series domain on a wide range of datasets simultaneously, which is a major building block for building generalist foundation models in time-series domains. --- ### Phantasia: Context-Adaptive Backdoors in Vision Language Models Authors: Nam Duong Tran, Phi Le Nguyen Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08395v1 Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs, particularly their vulnerability to backdoor attacks, remains significantly underexplored. Existing backdoor attacks on VLMs are still in an early stage of development, with most current methods relying on generating poisoned responses that contain fixed, easily identifiable patterns. In this work, we make two key contributions. First, we demonstrate for the first time that the stealthiness of existing VLM backdoor attacks has been substantially overestimated. By adapting defense techniques originally designed for other domains (e.g., vision-only and text-only models), we show that several state-of-the-art attacks can be detected with surprising ease. Second, to address this gap, we introduce Phantasia, a context-adaptive backdoor attack that dynamically aligns its poisoned outputs with the semantics of each input. Instead of producing static poisoned patterns, Phantasia encourages models to generate contextually coherent yet malicious responses that remain plausible, thereby significantly improving stealth and adaptability. Extensive experiments across diverse VLM architectures reveal that Phantasia achieves state-of-the-art attack success rates while maintaining benign performance under various defensive settings. --- ### Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover Authors: Jui-Hui Chung, Hongzhou Lin, Lai Jiang, Shange Tang, Chi Jin Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08388v1 Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily trained on 1.8 million formal-math examples. After domain specialization, the model almost completely loses its ability to produce valid tool calls, even when explicitly instructed to use tools, dropping from 89.4% function-calling accuracy in the base model to nearly 0%. We ask whether this agentic collapse is permanent or instead reversible. To answer this question, we fine-tune the specialized model on a small amount of Lean-specific tool-use data. Remarkably, as few as 100 agentic traces are sufficient to restore strong tool-calling behavior. Importantly, this recovery is not the result of reward hacking or benchmark-specific optimization: the recovery data is entirely drawn from the Lean setting, where the model uses natural-language queries to search the Mathlib library for relevant theorems and lemmas, yet the regained capability transfers well beyond that domain. In particular, these same 100 Lean-specific traces improve performance on the Berkeley Function Calling Leaderboard from near zero to 83.8%, approaching the base model's 89.4% despite the mismatch in task distribution and protocol. The recovered capability is also practically useful in-domain. On ProofNet, pass@32 improves from 21.51% to 25.81%. Together, these results show that heavy domain supervised fine-tuning can suppress general tool-use ability without permanently erasing it, and that a small amount of domain-specific agentic data can awaken dormant tool-use capabilities. --- ### TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Authors: Jing Peng, Chenghao Wang, Yi Yang, Lirong Qian, Junjie Li, Yu Xi, Shuai Wang, Kai Yu Published: 2026-04-09 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2604.08384v1 Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text-only alignment methods such as TASU reduce this burden by simulating CTC posteriors from transcripts, but they provide limited control over uncertainty and error rate, making curriculum design largely heuristic. We propose \textbf{TASU2}, a controllable CTC simulation framework that simulates CTC posterior distributions under a specified WER range, producing text-derived supervision that better matches the acoustic decoding interface. This enables principled post-training curricula that smoothly vary supervision difficulty without TTS. Across multiple source-to-target adaptation settings, TASU2 improves in-domain and out-of-domain recognition over TASU, and consistently outperforms strong baselines including text-only fine-tuning and TTS-based augmentation, while mitigating source-domain performance degradation. --- ### A GAN and LLM-Driven Data Augmentation Framework for Dynamic Linguistic Pattern Modeling in Chinese Sarcasm Detection Authors: Wenxian Wang, Xiaohu Luo, Junfeng Hao, Xiaoming Gu, Xingshu Chen, Zhu Wang, Haizhou Wang Published: 2026-04-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08381v1 Sarcasm is a rhetorical device that expresses criticism or emphasizes characteristics of certain individuals or situations through exaggeration, irony, or comparison. Existing methods for Chinese sarcasm detection are constrained by limited datasets and high construction costs, and they mainly focus on textual features, overlooking user-specific linguistic patterns that shape how opinions and emotions are expressed. This paper proposes a Generative Adversarial Network (GAN) and Large Language Model (LLM)-driven data augmentation framework to dynamically model users' linguistic patterns for enhanced Chinese sarcasm detection. First, we collect raw data from various topics on Sina Weibo. Then, we train a GAN on these data and apply a GPT-3.5 based data augmentation technique to synthesize an extended sarcastic comment dataset, named SinaSarc. This dataset contains target comments, contextual information, and user historical behavior. Finally, we extend the BERT architecture to incorporate multi-dimensional information, particularly user historical behavior, enabling the model to capture dynamic linguistic patterns and uncover implicit sarcastic cues in comments. Experimental results demonstrate the effectiveness of our proposed method. Specifically, our model achieves the highest F1-scores on both the non-sarcastic and sarcastic categories, with values of 0.9138 and 0.9151 respectively, which outperforms all existing state-of-the-art (SOTA) approaches. This study presents a novel framework for dynamically modeling users' long-term linguistic patterns in Chinese sarcasm detection, contributing to both dataset construction and methodological advancement in this field. --- ### SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Authors: Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang, Yong Wang, Yiming Hu, Tongwen Huang, Xiangxiang Chu Published: 2026-04-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08377v2 Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios. --- ### SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Authors: Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang, Yong Wang, Yiming Hu, Tongwen Huang, Xiangxiang Chu Published: 2026-04-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08377v1 Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios. --- ### SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction Authors: Chensheng Dai, Shengjun Zhang, Min Chen, Yueqi Duan Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08370v1 3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based reconstruction pipelines that achieve precise and complete surface extractions. However, these approaches typically require dense input views and high time consumption for per-scene optimization. To address these limitations, we propose SurfelSplat, a feed-forward framework that generates efficient and generalizable pixel-aligned Gaussian surfel representations from sparse-view images. We observe that conventional feed-forward structures struggle to recover accurate geometric attributes of Gaussian surfels because the spatial frequency of pixel-aligned primitives exceeds Nyquist sampling rates. Therefore, we propose a cross-view feature aggregation module based on the Nyquist sampling theorem. Specifically, we first adapt the geometric forms of Gaussian surfels with spatial sampling rate-guided low-pass filters. We then project the filtered surfels across all input views to obtain cross-view feature correlations. By processing these correlations through a specially designed feature fusion network, we can finally regress Gaussian surfels with precise geometry. Extensive experiments on DTU reconstruction benchmarks demonstrate that our model achieves comparable results with state-of-the-art methods, and predict Gaussian surfels within 1 second, offering a 100x speedup without costly per-scene training. --- ### Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents Authors: Khushal Sethi Published: 2026-04-09 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.08369v1 Inference-time compute scaling has emerged as a powerful technique for improving the reliability of large language model (LLM) agents, but existing methods apply compute uniformly: every decision step receives the same budget regardless of its difficulty. We introduce TrACE (Trajectorical Adaptive Compute via agrEement), a training-free controller that allocates LLM calls adaptively across agent timesteps by measuring inter-rollout action agreement. At each step, TrACE samples a small set of candidate next actions and measures how consistently the model commits to the same action. High agreement signals an easy decision; the controller commits immediately. Low agreement signals uncertainty; the controller samples additional rollouts up to a configurable cap before committing to the plurality action. No learned components, no external verifier, and no human labels are required. We evaluate TrACE against greedy decoding and fixed-budget self-consistency (SC-4, SC-8) on two benchmarks spanning single-step reasoning (GSM8K, n=50) and multi-step household navigation (MiniHouse, n=30), using a Qwen 2.5 3B Instruct model running on CPU. TrACE-4 matches SC-4 accuracy while using 33% fewer LLM calls on GSM8K and 39% fewer on MiniHouse. TrACE-8 matches SC-8 accuracy with 55% fewer calls on GSM8K and 65% fewer on MiniHouse. We further show that inter-rollout agreement is a reliable signal of step-level success, validating the core hypothesis that the model's own output consistency encodes difficulty information that can be exploited without training. TrACE is the first training-free, per-timestep adaptive-compute controller for LLM agents to be evaluated on multi-step sequential decision tasks. --- ### SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization Authors: Seyed Mahmoud Sajjadi Mohammadabadi, Xiaolong Ma, Lei Yang, Feng Yan, Junshan Zhang Published: 2026-04-09 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.08368v1 Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, enable scalable adaptation of foundation models by injecting low-rank adapters. However, their communication and storage costs remain a major bottleneck in resource-constrained settings. We propose SOLAR (Subspace-Oriented Latent Adapter Reparameterization), a post-training compression framework that substantially reduces the communication cost (i.e., the number of parameters to transmit or store) of PEFT adapters. SOLAR expresses each PEFT update as a linear combination of basis vectors formed from the foundation model's singular vectors with controlled random perturbations. By exploiting the subspace similarity (the alignment of principal directions) between the foundation model and task-specific fine-tuned updates, SOLAR decouples the adapter size from PEFT structure and ensures compact yet expressive representations. It is model-agnostic and compatible with existing PEFT methods, including LoRA, AdaLoRA, and other adapter modules. We theoretically establish a bound on the reconstruction error. Experiments on language and vision tasks using LLaMA, GPT, and ViT models demonstrate that SOLAR preserves task performance while significantly reducing model representation sizes, offering an effective and communication-efficient solution for deployment in distributed systems and edge devices. --- ### Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems Authors: Tolga Dimlioglu, Nadine Chang, Maying Shen, Rafid Mahmood, Jose M. Alvarez Published: 2026-04-09 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.08366v1 Large-scale deep learning models for physical AI applications depend on diverse training data collection efforts. These models and correspondingly, the training data, must address different evaluation criteria necessary for the models to be deployable in real-world environments. Data selection policies can guide the development of the training set, but current frameworks do not account for the ambiguity in how data points affect different metrics. In this work, we propose Mixture Optimization via Scaling-Aware Iterative Collection (MOSAIC), a general data selection framework that operates by: (i) partitioning the dataset into domains; (ii) fitting neural scaling laws from each data domain to the evaluation metrics; and (iii) optimizing a data mixture by iteratively adding data from domains that maximize the change in metrics. We apply MOSAIC to autonomous driving (AD), where an End-to-End (E2E) planner model is evaluated on the Extended Predictive Driver Model Score (EPDMS), an aggregate of driving rule compliance metrics. Here, MOSAIC outperforms a diverse set of baselines on EPDMS with up to 80\% less data. --- ### MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Authors: Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun, Yuanpeng Tu, Fei Shen, Weidong Zhang, Cairong Zhao, Jun Zhang Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08364v2 In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We achieve this by leveraging the consistent text-to-image style mapping capability of current large generative models, which can generate images in the same style from a given style description. Building on this foundation, we curate a diverse and balanced prompt gallery with 170K style prompts and 400K content prompts, and generate a large-scale style dataset MegaStyle-1.4M via content-style prompt combinations. With MegaStyle-1.4M, we propose style-supervised contrastive learning to fine-tune a style encoder MegaStyle-Encoder for extracting expressive, style-specific representations, and we also train a FLUX-based style transfer model MegaStyle-FLUX. Extensive experiments demonstrate the importance of maintaining intra-style consistency, inter-style diversity and high-quality for style dataset, as well as the effectiveness of the proposed MegaStyle-1.4M. Moreover, when trained on MegaStyle-1.4M, MegaStyle-Encoder and MegaStyle-FLUX provide reliable style similarity measurement and generalizable style transfer, making a significant contribution to the style transfer community. More results are available at our project website https://jeoyal.github.io/MegaStyle/. --- ### Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces Authors: Jiawei Chen, Ruoxi Xu, Boxi Cao, Ruotong Pan, Yunfei Zhang, Yifei Hu, Yong Du, Tingting Gao, Yaojie Lu, Yingfei Sun, Xianpei Han, Le Sun et al. Published: 2026-04-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08362v2 The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenarios, narrow action spaces, or synthetic data, failing to capture the holistic nature of authentic human behavior. To bridge this gap, we introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data, integrating long-horizon, cross-scenario, and heterogeneous behavioral patterns into a unified framework. Based on this benchmark, we first provide empirical evidence that previous datasets with isolated scenarios suffer from tunnel vision, whereas real-world decision-making relies on long-term, cross-scenario causal chains. Extensive evaluations of state-of-the-art LLMs reveal that current models struggle to accurately simulate these complex behaviors, with performance plateauing even as context windows expand. Crucially, a systematic comparison between simulated and authentic behaviors uncovers a fundamental structural bias: LLMs tend to converge toward a positive average person, exhibiting hyper-activity, persona homogenization, and a utopian bias. This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research. --- ### Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation Authors: Andi Gu, J. Pablo Bonilla Ataides, Mikhail D. Lukin, Susanne F. Yelin Published: 2026-04-09 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08358v1 Quantum error correction (QEC) is essential for scalable quantum computing. However, it requires classical decoders that are fast and accurate enough to keep pace with quantum hardware. While quantum low-density parity-check codes have recently emerged as a promising route to efficient fault tolerance, current decoding algorithms do not allow one to realize the full potential of these codes in practical settings. Here, we introduce a convolutional neural network decoder that exploits the geometric structure of QEC codes, and use it to probe a novel "waterfall" regime of error suppression, demonstrating that the logical error rates required for large-scale fault-tolerant algorithms are attainable with modest code sizes at current physical error rates, and with latencies within the real-time budgets of several leading hardware platforms. For example, for the $(144, 12, 12)$ Gross code, the decoder achieves logical error rates up to $\sim 17$x below existing decoders - reaching logical error rates $\sim 10^{-10}$ at physical error $p=0.1\%$ - with 3-5 orders of magnitude higher throughput. This decoder also produces well-calibrated confidence estimates that can significantly reduce the time overhead of repeat-until-success protocols. Taken together, these results suggest that the space-time costs associated with fault-tolerant quantum computation may be significantly lower than previously anticipated. --- ### Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training Authors: Constantin Le Cleï, Nils Thuerey, Xiaoxiang Zhu Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08357v2 Conditional Diffusion Models are powerful surrogates for emulating complex spatiotemporal dynamics, yet they often fail to match the accuracy of deterministic neural emulators for high-precision tasks. In this work, we address two critical limitations of autoregressive PDE diffusion models: their sub-optimal single-step accuracy and the prohibitive computational cost of unrolled training. First, we characterize the relationship between the noise schedule, the reconstruction error reduction rate and the diffusion exposure bias, demonstrating that standard schedules lead to suboptimal reconstruction error. Leveraging this insight, we propose an \textit{Adaptive Noise Schedule} framework that minimizes inference reconstruction error by dynamically constraining the model's exposure bias. We further show that this optimized schedule enables a fast \textit{Proxy Unrolled Training} method to stabilize long-term rollouts without the cost of full Markov Chain sampling. Both proposed methods enable significant improvements in short-term accuracy and long-term stability over diffusion and deterministic baselines on diverse benchmarks, including forced Navier-Stokes, Kuramoto-Sivashinsky and Transonic Flow. --- ### ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer Authors: Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08355v2 Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer, they are often constrained by predefined, discrete class systems, limiting their adaptability to novel or compositional task variations. We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning via a text-conditioned Variational Autoencoder (VAE). Our core innovation utilizes a Large Language Model (LLM) as a dynamic \textit{semantic operator} at test time. Rather than relying on rigid rules, our agent queries the LLM to semantically remap the description of the current observation to align with the source task. This source-aligned caption conditions the VAE to generate an imagined state compatible with the agent's original training, enabling direct policy reuse. By harnessing the flexible reasoning capabilities of LLMs, our approach achieves zero-shot transfer across a broad spectrum of complex and truly novel analogous tasks, moving beyond the limitations of fixed category mappings. Code and videos are available \href{https://anonymous.4open.science/r/ASPECT-85C3/}{here}. --- ### Human-AI Collaboration Reconfigures Group Regulation from Socially Shared to Hybrid Co-Regulation Authors: Yujing Zhang, Xianghui Meng, Shihui Feng, Jionghao Lin Published: 2026-04-09 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.08344v1 Generative AI (GenAI) is increasingly used in collaborative learning, yet its effects on how groups regulate collaboration remain unclear. Effective collaboration depends not only on what groups discuss, but on how they jointly manage goals, participation, strategy use, monitoring, and repair through co-regulation and socially shared regulation. We compared collaborative regulation between Human-AI and Human-Human groups in a parallel-group randomised experiment with 71 university students completing the same collaborative tasks with GenAI either available or unavailable. Focusing on human discourse, we used statistical analyses to examine differences in the distribution of collaborative regulation across regulatory modes, regulatory processes, and participatory focuses. Results showed that GenAI availability shifted regulation away from predominantly socially shared forms towards more hybrid co-regulatory forms, with selective increases in directive, obstacle-oriented, and affective regulatory processes. Participatory-focus distributions, however, were broadly similar across conditions. These findings suggest that GenAI reshapes the distribution of regulatory responsibility in collaboration and offer implications for the human-centred design of AI-supported collaborative learning. --- ### EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment Authors: Qiance Tang, Ziqi Wang, Jieyu Lin, Ziyun Li, Barbara De Salvo, Sai Qian Zhang Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08342v2 Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of its most important application domains. Nevertheless, the task remains highly challenging due to the need for reasoning over extended temporal contexts and diverse, unstructured activities. Although several benchmarks exist, most egocentric datasets rely on human worn cameras and focus mainly on visual content, with limited consideration of underlying user behavior when forming video-related queries. EgoEverything is a benchmark that explicitly considers human behavior by leveraging human attention signals, abstracted from gaze data, when generating questions. It comprises over 5,000 multiple choice question answer pairs, spanning more than 100 hours of video. By integrating human attention signals during question generation, it more faithfully captures natural human behavior and offers a realistic evaluation setting for long-context egocentric video understanding in AR. --- ### Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time Authors: Ruizhi Zhang, Ye Huang, Yuangang Pan, Chuanfu Shen, Zhilin Liu, Ting Xie, Haijun Lei, Lixin Duan Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08340v2 While artificial intelligence has mastered structured games like chess and Go, vision-language agents still struggle in visually-driven 3D games without access to game states. Existing game environments typically evaluate a fixed agent configuration, rather than an agent's ability to improve its configuration across consecutive episodes of the same task---a paradigm known as test-time learning (TTL). Furthermore, current TTL methods typically optimize single modalities---such as text prompts or actions---in isolation, ignoring the synergy between perception, reasoning, and control. To bridge these gaps, we first introduce \textbf{PokeGym}, a long-horizon benchmark built upon the 3D open-world game Pokémon Legends: Z-A, where agents act from visual observations without access to game states, designed to evaluate an agent's ability to learn and adapt across consecutive episodes of the task. To tackle this challenging environment, we propose Graph-Guided Evolutionary Multimodal Agent Configuration (\textbf{G-EvoMAC}), a graph-guided framework that jointly optimizes visual perception, strategy, and action set synergistically. Extensive experiments show that G-EvoMAC achieves a 60.18\% average success rate on PokeGym, outperforming the strongest baseline by over 11 percentage points, validating the power of cross-modal co-evolution. --- ### InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding Authors: Ashutosh Kumar, Rajat Saini, Jingjing Pan, Mustafa Erdogan, Mingfang Zhang, Betty Le Dem, Norimasa Kobori, Quan Kong Published: 2026-04-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.08337v1 Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions to specific spatial-temporal regions. To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions. On the InstVL benchmark, InstAP substantially outperforms existing VLP models on instance-level retrieval, and also surpasses a strong VLP baseline trained on the exact same data corpus, isolating the benefit of our instance-aware objective. Moreover, instance-centric pre-training improves global understanding: InstAP achieves competitive zero-shot performance on multiple video benchmarks, including MSR-VTT and DiDeMo. Qualitative visualizations further show that InstAP localizes textual mentions to the correct instances, while global-only models exhibit more diffuse, scene-level attention. --- ### Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers Authors: Danit Yanowsky, Daphna Weinshall Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08336v2 Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most existing approaches construct memory buffers using embeddings learned under supervised objectives. However, class-agnostic, self-supervised representations often encode rich, class-relevant semantics that are overlooked. We propose a new method, Multiple Embedding Replay Selection, MERS, which replaces the buffer selection module with a graph-based approach that integrates both supervised and self-supervised embeddings. Empirical results show consistent improvements over SOTA selection strategies across a range of continual learning algorithms, with particularly strong gains in low-memory regimes. On CIFAR-100 and TinyImageNet, MERS outperforms single-embedding baselines without adding model parameters or increasing replay volume, making it a practical, drop-in enhancement for replay-based continual learning. --- ### Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers Authors: Danit Yanowsky, Daphna Weinshall Published: 2026-04-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08336v1 Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most existing approaches construct memory buffers using embeddings learned under supervised objectives. However, class-agnostic, self-supervised representations often encode rich, class-relevant semantics that are overlooked. We propose a new method, Multiple Embedding Replay Selection, MERS, which replaces the buffer selection module with a graph-based approach that integrates both supervised and self-supervised embeddings. Empirical results show consistent improvements over SOTA selection strategies across a range of continual learning algorithms, with particularly strong gains in low-memory regimes. On CIFAR-100 and TinyImageNet, MERS outperforms single-embedding baselines without adding model parameters or increasing replay volume, making it a practical, drop-in enhancement for replay-based continual learning. --- ### Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models Authors: Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08335v2 We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through a shared continuous latent space via learned linear projections. Building on recent work demonstrating geometric compatibility between independently trained LLM latent spaces~\cite{armstrong2026thinking}, we extend this finding from static two-model steering to end-to-end trainable multi-node graphs, where projection matrices are optimized jointly via backpropagation through residual stream injection hooks. Three small frozen models (Llama-3.2-1B, Qwen2.5-1.5B, Gemma-2-2B) encode the input into a shared latent space whose aggregate signal is injected into two larger frozen models (Phi-3-mini, Mistral-7B), whose representations feed a lightweight cross-attention output node. With only 17.6M trainable parameters against approximately 12B frozen, the architecture achieves 87.3\% on ARC-Challenge, 82.8\% on OpenBookQA, and 67.2\% on MMLU, outperforming the best single constituent model by 11.4, 6.2, and 1.2 percentage points respectively, and outperforming parameter-matched learned classifiers on frozen single models by 9.1, 5.2, and 6.7 points. Gradient flow through multiple frozen model boundaries is empirically verified to be tractable, and the output node develops selective routing behavior across layer-2 nodes without explicit supervision. --- ### Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models Authors: Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee Published: 2026-04-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.08335v1 We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through a shared continuous latent space via learned linear projections. Building on recent work demonstrating geometric compatibility between independently trained LLM latent spaces~\cite{armstrong2026thinking}, we extend this finding from static two-model steering to end-to-end trainable multi-node graphs, where projection matrices are optimized jointly via backpropagation through residual stream injection hooks. Three small frozen models (Llama-3.2-1B, Qwen2.5-1.5B, Gemma-2-2B) encode the input into a shared latent space whose aggregate signal is injected into two larger frozen models (Phi-3-mini, Mistral-7B), whose representations feed a lightweight cross-attention output node. With only 17.6M trainable parameters against approximately 12B frozen, the architecture achieves 87.3\% on ARC-Challenge, 82.8\% on OpenBookQA, and 67.2\% on MMLU, outperforming the best single constituent model by 11.4, 6.2, and 1.2 percentage points respectively, and outperforming parameter-matched learned classifiers on frozen single models by 9.1, 5.2, and 6.7 points. Gradient flow through multiple frozen model boundaries is empirically verified to be tractable, and the output node develops selective routing behavior across layer-2 nodes without explicit supervision. --- ### Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification Authors: Xun Zhu, Fanbin Mo, Xi Chen, Kaili Zheng, Shaoshuai Yang, Yiming Shi, Jian Gao, Miao Li, Ji Wu Published: 2026-04-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08333v1 The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However, as one of the earliest and most fundamental tasks integrated into this paradigm, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to traditional deep learning models, despite their overwhelming advantages in pre-training data and model parameters. This paradox prompts a critical rethinking: where exactly does the performance degradation originate? In this paper, we conduct extensive experiments on 14 open-source medical MLLMs across three representative image classification datasets. Moving beyond superficial performance benchmarking, we employ feature probing to track the information flow of visual features module-by-module and layer-by-layer throughout the entire MLLM pipeline, enabling explicit visualization of where and how classification signals are distorted, diluted, or overridden. As the first attempt to dissect classification performance degradation in medical MLLMs, our findings reveal four failure modes: 1) quality limitation in visual representation, 2) fidelity loss in connector projection, 3) comprehension deficit in LLM reasoning, and 4) misalignment of semantic mapping. Meanwhile, we introduce quantitative scores that characterize the healthiness of feature evolution, enabling principled comparisons across diverse MLLMs and datasets. Furthermore, we provide insightful discussions centered on the critical barriers that prevent current medical MLLMs from fulfilling their promised clinical potential. We hope that our work provokes rethinking within the community-highlighting that the road from high expectations to clinically deployable MLLMs remains long and winding. --- ### ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection Authors: He Geng, Yangmin Huang, Lixian Lai, Qianyun Du, Hui Chu, Zhiyang He, Jiaxue Hu, Xiaodong Tao Published: 2026-04-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.08326v1 Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals and the complex, multi-dimensional nature of clinical protocols. To bridge this gap, we introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria. We first construct ProMedical-Preference-50k, a dataset generated via a human-in-the-loop pipeline that augments medical instructions with rigorous, physician-derived rubrics. Leveraging this corpus, we propose the Explicit Criteria Injection paradigm to train a multi-dimensional reward model. Unlike traditional scalar reward models, our approach explicitly disentangles safety constraints from general proficiency, enabling precise guidance during reinforcement learning. To rigorously validate this framework, we establish ProMedical-Bench, a held-out evaluation suite anchored by double-blind expert adjudication. Empirical evaluations demonstrate that optimizing the Qwen3-8B base model via ProMedical-RM-guided GRPO yields substantial gains, improving overall accuracy by 22.3% and safety compliance by 21.7%, effectively rivaling proprietary frontier models. Furthermore, the aligned policy generalizes robustly to external benchmarks, demonstrating performance comparable to state-of-the-art models on UltraMedical. We publicly release our datasets, reward models, and benchmarks to facilitate reproducible research in safety-aware medical alignment. --- ### Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization Authors: Benjamin Léger, Kazem Meidani, Christian Gagné Published: 2026-04-09 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2604.08324v4 Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to learn the phenotype-genotype mapping, enabling optimization in the numeric space to implicitly guide symbolic search. However, this relies on fine-grained cross-modal alignment, whereas literature on similar models like CLIP reveals that such an alignment is typically coarse-grained. In this paper, we investigate whether SNIP delivers on its promise of effective bi-modal optimization for SR. Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space. These findings reveal that while multi-modal LSO holds significant potential for SR, effective alignment-guided optimization remains unrealized in practice, highlighting fine-grained alignment as a critical direction for future work. --- ### Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data Authors: Yuchuan Deng, Qijie Wei, Kaiheng Qian, Jiazhen Liu, Zijie Xin, Bangxiang Lan, Jingyu Liu, Jianfeng Dong, Xirong Li Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08322v1 Fundus imaging such as CFP, OCT and UWF is crucial for the early detection of retinal anomalies and diseases. Fundus image understanding, due to its knowledge-intensive nature, poses a challenging vision-language task. An emerging approach to addressing the task is to post-train a generic multimodal large language model (MLLM), either by supervised finetuning (SFT) or by reinforcement learning with verifiable rewards (RLVR), on a considerable amount of in-house samples paired with high-quality clinical reports. However, these valuable samples are not publicly accessible, which not only hinders reproducibility but also practically limits research to few players. To overcome the barrier, we make a novel attempt to train a reasoning-enhanced fundus-reading MLLM, which we term Fundus-R1, using exclusively public datasets, wherein over 94\% of the data are annotated with only image-level labels. Our technical contributions are two-fold. First, we propose a RAG-based method for composing image-specific, knowledge-aware reasoning traces. Such auto-generated traces link visual findings identified by a generic MLLM to the image labels in terms of ophthalmic knowledge. Second, we enhance RLVR with a process reward that encourages self-consistency of the generated reasoning trace in each rollout. Extensive experiments on three fundus-reading benchmarks, i.e., FunBench, Omni-Fundus and GMAI-Fundus, show that Fundus-R1 clearly outperforms multiple baselines, including its generic counterpart (Qwen2.5-VL) and a stronger edition post-trained without using the generated traces. This work paves the way for training powerful fundus-reading MLLMs with publicly available data. --- ### Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow Authors: Richard Petersen, Fredrik Kahl, Jennifer Alvén Published: 2026-04-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08313v2 Dense annotations, such as segmentation masks, are expensive and time-consuming to obtain, especially for 3D medical images where expert voxel-wise labeling is required. Weakly supervised approaches aim to address this limitation, but often rely on attribution-based methods that struggle to accurately capture small structures such as lung nodules. In this paper, we propose a weakly-supervised segmentation method for lung nodules by combining pretrained state-of-the-art rectified flow and predictor models in a plug-and-play manner. Our approach uses training-free guidance of a 3D rectified flow model, requiring only fine-tuning of the predictor using image-level labels and no retraining of the generative model. The proposed method produces improved-quality segmentations for two separate predictors, consistently detecting lung nodules of varying size and shapes. Experiments on LUNA16 demonstrate improvements over baseline methods, highlighting the potential of generative foundation models as tools for weakly supervised 3D medical image segmentation. --- ### HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology Authors: Aasim Bin Saleem, Amr Ahmed, Ardhendu Behera, Hafeezullah Amin, Iman Yi Liao, Mahmoud Khattab, Pan Jia Wern, Haslina Makmur Published: 2026-04-09 Categories: eess.IV, cs.AI, cs.CV, cs.ET, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.08305v1 Immunohistochemistry (IHC) is essential for assessing specific immune biomarkers like Human Epidermal growth-factor Receptor 2 (HER2) in breast cancer. However, the traditional protocols of obtaining IHC stains are resource-intensive, time-consuming, and prone to structural damages. Virtual staining has emerged as a scalable alternative, but it faces significant challenges in preserving fine-grained cellular structures while accurately translating biochemical expressions. Current state-of-the-art methods still rely on Generative Adversarial Networks (GANs) or standard convolutional U-Net diffusion models that often struggle with "structure and staining trade-offs". The generated samples are either structurally relevant but blurry, or texturally realistic but have artifacts that compromise their diagnostic use. In this paper, we introduce HistDiT, a novel latent conditional Diffusion Transformer (DiT) architecture that establishes a new benchmark for visual fidelity in virtual histological staining. The novelty introduced in this work is, a) the Dual-Stream Conditioning strategy that explicitly maintains a balance between spatial constraints via VAE-encoded latents and semantic phenotype guidance via UNI embeddings; b) the multi-objective loss function that contributes to sharper images with clear morphological structure; and c) the use of the Structural Correlation Metric (SCM) to focus on the core morphological structure for precise assessment of sample quality. Consequently, our model outperforms existing baselines, as demonstrated through rigorous quantitative and qualitative evaluations. ---