# Research Papers — 2026-06 · bundle page 172 of 260 > Full-text markdown of papers #8551–8600 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/172 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/171.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/173.md) ### Multimodal Brain Tumour Classification Using Feature Fusion Authors: Wajih ul Islam, Muhammad Yaqoob, Javed Ali Khan, Volker Steuber Published: 2026-06-09 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.11107v2 Clinicians diagnose brain tumors by synthesizing patient symptoms, medical history, and quantitative imaging data from modalities such as MRI and CT scans into a unified clinical judgement. However, most deep learning models rely on MRI/CT images alone, failing to replicate the clinicians multimodal reasoning. We explore a two-branch multimodal network combining raw MRI scans with 91 extracted radiomic features (intensity, texture, shape, and boundary descriptors) to classify brain tumors into glioma, meningioma, pituitary, and no-tumor. A pre-trained CNN backbone encodes the image stream, whereas a dedicated MLP encodes the radiomic stream. Both streams are fused via concatenation, gated, or bidirectional cross-modal attention strategies. Across nine experimental runs on a balanced 7,200 image dataset, all multimodal configurations outperform unimodal baselines with gated fusion achieving the best accuracy of 96.13%. --- ### FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model Authors: Mahmood Alzubaidi, Uzair Shah, Raden Muaz, Ines Abbes, Nader Mohammed, Abdullatif Magram, Khalid Alyafei, Mowafa Househ, Marco Agus Published: 2026-06-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.11106v1 A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography. Current deep learning approaches address detection, segmentation, or classification in isolation, each demanding a separate model and expert-specified labels at inference. We present FADA, a unified vision-language model built on Qwen3.5-VL that performs clinical interpretation, classification, detection, and segmentation through a single interpretation-first pipeline without external labels. FADA distills knowledge from four domain-specific foundation models (FetalCLIP, UltraSAM, USF-MAE, UltraFedFM) via offline pre-computed feature caching. Selective distillation, which applies feature alignment only to annotation tasks while interpretation relies on standard fine-tuning, consistently outperforms full distillation across most evaluation axes. The recommended variant, FADA-SKD, achieves 0.8820 mean Dice for segmentation, 0.7671 mAP@0.50 for detection, and 100% structured interpretation compliance. Expert sonographer validation across 237 images confirms clinically acceptable outputs in both autonomous and human-in-the-loop modes, with 73.5% of interpretations scoring perfectly under clinician guidance. The system is trainable on a single consumer GPU and deployable without cloud connectivity. We validate edge deployment by running the compressed 0.8B model on a commodity smartphone (Qualcomm Snapdragon 7 Gen 1, 12 GB RAM) using llama.cpp with GGUF quantization, completing the full 5-phase pipeline in approximately 60 seconds entirely offline. This establishes a practical pathway for integrating AI-assisted fetal assessment with portable ultrasound devices, directly addressing diagnostic access gaps in resource-constrained settings. Code, models, and data are available at https://github.com/mahmoodphd/FADA. --- ### PhantomBench: Benchmarking the Non-existential Threat of Language Models Authors: Haeji Jung, Hila Gonen Published: 2026-06-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.11105v1 Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them. This is particularly concerning in high-stakes domains, where consequences of such model behavior can lead to significant harms. Despite notable progress in understanding hallucinations, it remains unclear how reliably these models can recognize the limits of their knowledge. We introduce PhantomBench, the first large-scale benchmark of its kind, comprising more than 60K non-existent terms and entities derived from real concepts across diverse domains. Using our benchmark, we evaluate a total of 21 models of various types and sizes. We show staggering hallucination rates across the board (with average rates as high as 86.7% in some cases), and note that even frontier models surprisingly fail to abstain on non-existent concepts, especially when the input presumes their existence. We then show that PhantomBench can serve as a proxy for studying model behavior on rare concepts for which models are more prone to hallucinate. We also provide a pipeline to construct PhantomBench, enabling scalable generation of non-existent concepts tailored to the specific needs of researchers and practitioners. --- ### Limitations of Learning Tanh Neural Networks with Finite Precision Authors: Philipp Grohs, Matěj Trödler Published: 2026-06-09 Categories: cs.LG, math.CA, stat.ML arXiv: https://arxiv.org/abs/2606.11104v1 We investigate limitations of learning $\tanh$ neural networks from point evaluations under finite-precision computations and $L^p$ accuracy guarantees, building on Berner, Grohs, and Voigtländer (2023). Our approach is based on a novel construction of sharply localized bump functions via iterated $\tanh$ activations. Using this mechanism, we show that, in a finite-precision setting, no adaptive randomized algorithm based on $m$ samples can achieve a convergence rate higher than the Monte Carlo rate $O(m^{-1/p})$ in the $L^p$ norm, unless the sampling budget grows exponentially with the size of the network parameters and architecture. The results reveal fundamental limitations imposed by finite precision on the learnability of classes containing localized bump functions, extending previous results for ReLU networks to the $\tanh$ setting. --- ### Do Transformers Actually Help Intrusion Detection? A Temporal Sequence Evaluation on CIC-IDS2017 Authors: Zach Moczkodan, Hany Ragab Published: 2026-06-09 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.11098v2 Recent deep learning approaches for network intrusion detection increasingly incorporate temporal architectures such as recurrent networks and Transformers, often reporting near-perfect performance on CIC-IDS2017. However, many existing studies neither supply their temporal modules with genuine sequence inputs nor evaluate under realistic, leakage-free conditions, making it unclear whether reported gains arise from true sequence-modelling capability. In this work, we reformulate CIC-IDS2017 as a temporal intrusion-detection task by constructing ordered flow sequences from network conversations and benchmarking nine classical and deep learning architectures under a random split, two leakage-free splits, and a padding-scheme ablation. The central finding is that padding convention, not architecture, determines the Transformer's performance: on genuinely sequential (non-padded) windows the Transformer achieves the highest macro-F1 of any model in the experiment ($0.89$), yet under zero-pad+mask evaluation it drops markedly while LSTM, GRU, and 1D-CNN remain stable and a class-balanced Random Forest is the most robust model overall. The same repeat-last padding cue masks a $67\times$ increase in the Transformer's false-alarm rate that only leakage-free evaluation reveals. Evaluation methodology -- specifically padding convention and split protocol -- thus has a larger effect on reported performance than architectural choice. We advocate for leakage-free splits, explicit padding disclosure, and sequence-aware benchmarking as standard practice in future IDS research. Our code and implementation details are available here: https://github.com/zachmocz/temporal-ids-bench. --- ### IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder Authors: Yitong Chen, Zijie Diao, Junke Wang, Lingyu Kong, Yixuan Ren, Bo He, Yu-Gang Jiang, Zuxuan Wu Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11096v1 Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail, which complements the high-level semantics carried by deep features used in existing RAEs. Motivated by this complementary property, we propose Ideal, an In-depth Alignment framework for discrete representation autoencoding. By jointly aligning quantized tokens with both shallow and deep VFM features, Ideal enables the resulting discrete visual tokens to preserve both visual fidelity and rich semantics. Extensive experiments demonstrate that Ideal yields superior reconstruction performance, achieving 0.61 rFID on ImageNet and outperforming the previous best method by 0.28. When used for autoregressive image generation, Ideal further produces a gFID of 1.89, establishing a new state of the art for autoregressive image generation. --- ### RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning Authors: Yichao Zhong, Yidan Lu, Yuhang Lu, Tianyang Tang, Haoguang Mai, Yixuan Pan, Tianyu Li, Li Chen, Jingbo Wang, Zhongyu Li, Peng Lu, Hongyang Li Published: 2026-06-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.11092v3 Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball positions and strike timings; in contrast, task reward-driven RL struggles to explore and discover valid kicks from scratch. We therefore introduce RoboNaldo, a three-stage motion-guided curriculum RL framework for high-impulse humanoid interaction. A single human-kick reference is used as a scaffold and progressively shifts optimization towards shooting performance. The curriculum first learns a stable whole-body kicking prior, then adapts the kick to free-kick settings where the ball is stationary at random positions, and finally extends it to moving-ball shooting through a locomotion-command and kick-trigger interface. A high-level heuristic planner controls this interface during training, while alternative high-level controllers can drive the same low-level policy at inference. In simulation, RoboNaldo demonstrates free-kick shot error 48.6% lower and shoot velocity 2.96x than prior work baselines. In real world on a Unitree G1 with onboard perception, RoboNaldo attains 0.73 m and 0.86 m average target shooting error from 3 m away in free-kick and moving-ball cases, accordingly. And the post-contact ball velocity reaches 13.10 m/s, which is 59-71% of reported professional open-play shot speed. Project page: https://opendrivelab.com/RoboNaldo. --- ### Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning Authors: Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li, Tobias Springenberg, Kevin Frans, Sergey Levine Published: 2026-06-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.11087v1 Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies. --- ### The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models Authors: Hakan Mehmetcik Published: 2026-06-09 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.11082v1 This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained adversarial conditions. We develop a multi-agent geopolitical wargame, the Cerulean Sea Crisis, a synthetic maritime territorial dispute designed to mirror the structural dynamics of Eastern Mediterranean conflicts. Six frontier models (GPT-4o, Llama-4, Mistral-Large, Gemini-3.1-Pro, Qwen3.6-Plus, and DeepSeek-R1) participate in a between-groups experiment (N = 10 games per arm, K = 5 rounds per game) in which the sole manipulation is the language of play (English versus Turkish), producing 586 validated statements. A zero-shot classifier assesses behavioral dispositions along two continuous dimensions: Concession Rate and Coercive Rhetoric. The results are heterogeneous. Llama-4 shows a substantial, Holm-corrected increase in coercive rhetoric under Turkish (delta = +0.800, p = .002), whereas Gemini-3.1-Pro displays an equally large decrease (delta = -0.750, p = .005). DeepSeek-R1 exhibits a similar negative shift (delta = -0.860, p = .006) and provides chain-of-thought evidence consistent with a buffering mechanism. GPT-4o shows no detectable effect (delta = +0.130, p = .614). These findings indicate that cross-lingual behavioral skew is contingent on model architecture and training regime rather than a universal property of Western-origin LLMs. We identify two distinct buffering mechanisms, chain-of-thought institutional anchoring and multilingual RLHF alignment, and discuss their implications for integrating LLMs safely into diplomatic and crisis-management settings. --- ### Unifying Local Communications and Local Updates for LLM Pretraining Authors: Pietro Cagnasso, Eugene Belilovsky, Edouard Oyallon Published: 2026-06-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.11081v1 Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters, data centers, and lower-bandwidth links. Many practical methods reduce communication frequency but still rely on synchronous All-Reduce operations that maintain identical model states and tie progress to global collectives. This can become a bottleneck when bandwidth or worker speed is heterogeneous. We introduce GASLoC, a novel decentralized pre-training algorithm that generalizes the notion of communication acceleration to the recently popular "outer optimizer" to allow a practical gossip-based training framework that is compatible with adaptive optimizers, allows for local optimizer steps, and can utilize sparse randomized peer communication. Empirically, on a number of standard LLM training tasks, we demonstrate that GASLoC outperforms state-of-the-art decentralized algorithms in single step per communication setting for a number of topologies and, unlike existing decentralized methods in the LLM setting, it allows to obtain performance competitive with DiLoCo when utilizing multiple local steps. In the heterogeneous bandwidth setting we demonstrate the advantage of GASLoC showing that it can significantly outperform DiLoCo. --- ### VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation Authors: Yunan Lu, Ryan Shea, Yusen Zhang, Zhou Yu Published: 2026-06-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.11079v1 Evaluation remains a critical bottleneck for interactive agent development. Existing evaluation methods often rely on static benchmarks, which fail to capture the dynamic, multi-step nature of agentic behavior and struggle to expose meaningful failure modes. While user-simulation-based evaluation offers a promising alternative, existing simulation frameworks suffer from two major limitations. First, they provide limited mechanisms for evaluating the quality and comprehensiveness of simulated interactions, making it difficult to assess whether a simulator sufficiently explores an agent's capabilities and failure modes. Second, most frameworks are restricted to either UI-only actions or API-only actions, limiting their ability to model the full range of realistic user behaviors. To address these limitations, we propose VISTA, a Versatile Interactive user Simulation Toolkit for Agent evaluation. Our toolkit includes a suite of six metrics for measuring the realism, capability coverage, and interaction effectiveness of simulated interactions. In addition, we develop a hybrid user simulator that integrates both UI-based interactions and API-based interactions, enabling more realistic and comprehensive evaluation across diverse interactive environments. We evaluate VISTA in e-commerce shopping and education customer service settings and demonstrate that it produces more realistic and comprehensive evaluations than existing methods. --- ### A History-Aware Visually Grounded Critic for Computer Use Agents Authors: Jaewoo Lee, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen, Supriyo Chakraborty, Kartik Balasubramaniam, Sambit Sahu, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal Published: 2026-06-09 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2606.11078v1 Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories to abstract past interactions into a compact record and to evaluate actions with visual grounding. At test time, HiViG integrates the critic into the policy decision loop to provide macro-action history, which summarizes the policy's completed achievements, and visually grounded critique, which verifies raw execution coordinates against the current screenshot to intercept errors before execution. Across web, mobile, and desktop benchmarks, HiViG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash, and demonstrates strong cross-platform generalization. Ablations show that macro-action history mitigates short-sighted planning and visually grounded critique reduces execution errors, with both components being critical for test-time scaling in long-horizon GUI tasks. --- ### Exploring the Design Space of Reward Backpropagation for Flow Matching Authors: Ruoyu Wang, Boye Niu, Xiangxin Zhou, Yushi Huang, Tongliang Liu, Chi Zhang Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.11075v1 Aligning text-to-image flow matching models with human preferences via direct reward backpropagation is sample-efficient but hampered by two well-known pathologies: activations cannot be stored across the full sampling trajectory at modern model scale, and chained Jacobian products across steps inflate the reward gradient as it travels back to early indices. Connector-based methods, such as LeapAlign, address these issues by replacing the full backward trajectory with a short pinned path, highlighting a useful decoupling between sampling and optimization. However, the quality of the resulting gradient depends on how accurately this short path approximates the full rollout, especially over long intervals. We propose FlowBP, a unified surrogate-trajectory framework that treats the backward trajectory itself as the design object. FlowBP keeps a no-gradient cached rollout for sampling, then builds a lightweight backward surrogate from cached and selectively re-forwarded velocities. This view separates four choices: the reward-model input, active set, integration weights, and bridge coupling, and recovers prior direct-gradient methods as particular settings. Within this framework, we instantiate three variants: FlowBP-Sparse uses sparse Euler reconstruction, FlowBP-Bridge adds controlled bridge coupling, and FlowBP-Lagrange raises the order of leap quadrature. All three bound memory by the active-set size and limit gradient chaining to at most one Jacobian factor. Across SD3.5-M, FLUX.1-dev, and FLUX.2-Klein-base on preference, quality, and compositional metrics, the three variants improve over direct-gradient baselines on most metrics. --- ### Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models Authors: Peiqi Jia, Haonan Jia, Ziqi Miao, Linkang Du, Yuntao Wang, Zhou Su Published: 2026-06-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.11074v2 With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted. --- ### T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains Authors: Genta Indra Winata, Amartya Chakraborty, Yuzhen Lin, Swasthi P Rao, Shikhhar Siingh, Houhan Lu, Nadia Bathaee, Sriharsha Hatwar, Paresh Dashore, Anmol Jain, Kshitij Tayal, Xiuzhu Lin et al. Published: 2026-06-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.11070v1 Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However, existing benchmarks remain limited in task complexity, realism, and domain diversity, and often fail to capture interactions that span multiple domains, limiting their ability to evaluate agents in realistic multi-step settings that require sustained reasoning and coordination. To address these limitations, we introduce T1-Bench, a high-fidelity, comprehensive benchmark for evaluating agentic systems in realistic customer-facing, multi-domain environments, featuring interleaved scenarios that require structured reasoning across multi-turn user-assistant interactions and substantially increasing both compositional complexity and evaluative rigor across 25 domains of varying difficulty. We evaluate T1-Bench using 12 proprietary and open-weight models, providing a reproducible and standardized framework for assessing agent behavior, tool utilization, and conversational quality in complex, multi-step environments. We further complement automatic evaluation with human judgments to strengthen the assessment of qualitative performance. Overall, T1-Bench substantially advances prior benchmarks by increasing task complexity, interaction depth, and domain coverage in simulated multi-domain environments. To facilitate future research on agentic systems, we will publicly release data and evaluation code as open source. --- ### GRAFT: Gain-Recalibrated Adapters for Transformer-Based Neural Population Activity Modeling Authors: Xiangsheng Ge, Yang Xie Published: 2026-06-09 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2606.11066v1 Neural population activity models can recover rich temporal structure from binned spikes, but their read-in and readout layers often remain tied to a fixed set of recorded neurons. This coupling limits reuse in long-term brain-computer interfaces, where recorded neuron identities, counts, and response statistics can change across days. We introduce GRAFT, a Transformer-based neural population activity model that separates reusable temporal dynamics from a recalibratable neuron interface. The neuron interface controls how recorded neurons enter and leave the shared backbone, and auxiliary gain and positional mechanisms support neural activity modeling inside the Transformer. On MC Maze under the standard NLB'21 protocol, GRAFT reaches 0.3866 co-bps as an ensemble, setting a new state of the art on the primary co-bps metric among public and reported NLB'21 results. In a cross-day protocol constructed from the NLB'21 MC Maze dataset series, GRAFT recalibrates from MC Maze to the scaled MC Maze datasets (Large/Medium/Small) by updating only 9.21% of parameters, reaching 0.3749, 0.3112, and 0.3152 co-bps with restricted target-day support sets. These results show that the same interface-backbone separation supports both strong Transformer-based neural population activity modeling and data-efficient cross-day recalibration. --- ### CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs Authors: Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov, Guillaume Lajoie, Jonas Geiping, Yoshua Bengio, Roland S. Zimmermann Published: 2026-06-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.11063v1 AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model's trajectory. If the trusted model detects such an intervention, it may infer properties of the monitor and adapt to evade control. We introduce \textbf{CIAware-Bench}, a benchmark for measuring \textbf{c}ontrol \textbf{i}ntervention (CI) awareness across frontier models. CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention. The benchmark is comprised of a suite of four task domains (essay writing, BigCodeBench, Bash Arena, and SHADE-Arena), while varying trajectory watermarking, side-task presence, and the control protocol. Evaluating eleven frontier models, we find low to moderate CI awareness under default settings (up to 0.87; random chance balanced binary classification accuracy is 0.5) with substantial variation across task domains and model pairs. Detection is generally easier across model families, suggesting that models exploit provider-specific differences in style or post-training. Overall, CI awareness is not a fixed model-level property, and should be measured for each new model release and deployment scenario. We release CIAware-Bench to track CI awareness and inform control protocols whose interventions are harder to detect. --- ### Flexible Kernels for Protein Property Prediction Authors: Martin Jankowiak, Yerdos Ordabayev, Rudraksh Tuwani, Henry N. Ward, Hunter Nisonoff, James M. McFarland, Gevorg Grigoryan Published: 2026-06-09 Categories: cs.LG, q-bio.BM, stat.ML arXiv: https://arxiv.org/abs/2606.11057v1 Despite its importance to applications in protein design, predicting protein properties like binding affinity and thermostability from sparse experimental data remains a significant challenge. Accordingly, we introduce a class of sequence kernels that exploit evolutionary substitution matrices as well as local linearity and demonstrate that the resulting Gaussian processes provide data-efficient models of protein property landscapes, frequently outperforming alternatives that rely on foundation model embeddings. Furthermore--by learning what are in effect structure-aware substitution matrices--we show that our kernels can readily incorporate structural information from foundation models. We demonstrate that these structure-conditioned kernels are well suited to multi-task learning across multiple protein property landscapes and can decisively outperform local supervised learning methods. --- ### Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It Authors: Xinyu Zhou, Boyu Zhu, Yi Xu, Zhiwei Li, Yingfa Chen, Huiming Wang, Zhijiang Guo Published: 2026-06-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.11052v2 Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from $67.2\%$ to $9.4\%$. We attribute this to CoT-SFT biasing attention gradients toward short-range patterns, disrupting query-key projections ($W_Q, W_K$) that are responsible for long-range routing. Motivated by this observation, we propose QK-Restore, a training-free method that restores only $W_Q$ and $W_K$ from the pre-SFT checkpoint while preserving all other post-SFT parameters. We further introduce a Procrustes variant to balance routing preservation and reasoning adaptation. Across architectures, QK-Restore consistently restores long-context capability at zero training cost while preserving reasoning performance; for instance, on HypeNet-5B it improves S3@256K from $65.4\%$ to $76.4\%$ while maintaining strong reasoning performance. --- ### Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It Authors: Xinyu Zhou, Boyu Zhu, Yi Xu, Zhiwei Li, Yingfa Chen, Huiming Wang, Zhijiang Guo Published: 2026-06-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.11052v1 Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from $67.2\%$ to $9.4\%$. We attribute this to CoT-SFT biasing attention gradients toward short-range patterns, disrupting query-key projections ($W_Q, W_K$) that are responsible for long-range routing. Motivated by this observation, we propose QK-Restore, a training-free method that restores only $W_Q$ and $W_K$ from the pre-SFT checkpoint while preserving all other post-SFT parameters. We further introduce a Procrustes variant to balance routing preservation and reasoning adaptation. Across architectures, QK-Restore consistently restores long-context capability at zero training cost while preserving reasoning performance; for instance, on HypeNet-5B it improves S3@256K from $65.4\%$ to $76.4\%$ while maintaining strong reasoning performance. --- ### Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models Authors: Prajakta Kini, Avinash Reddy, Souradip Chakraborty, Satya Sai Srinath Namburi GNVV, Furong Huang, Amrit Singh Bedi, Alvaro Velasquez Published: 2026-06-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.11046v1 Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is usually optimized for reasoning accuracy, without explicitly preserving the alignment behavior of the instruction-tuned model, such as safe refusal, bias avoidance, and privacy protection. We ask: does this conversion preserve alignment? We study this question through a trustworthiness audit and find that it is not behavior-preserving by default. For a systematic analysis, we compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against matched instruction-tuned baselines across six trustworthiness dimensions: safety, toxicity, stereotyping and bias, machine ethics, privacy, and out-of-distribution robustness. We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions, including increased toxicity, amplified stereotyping, miscalibrated refusal, and contextual privacy leakage. These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence. Overall, our results point to the broader conclusion that trustworthiness metrics are essential for evaluating reasoning models and should be reported alongside gains in reasoning capability. --- ### What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents Authors: Martin Andres Bertran, Aaron Roth, Zhiwei Steven Wu Published: 2026-06-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.11045v1 Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LLM-driven research agents, where the hypothesis becomes directly testable via two complementary information bottlenecks. In \emph{output compression}, an exploration agent adaptively searches for high-performance models using a validation set, and we test whether a fresh ``reproducer agent'' can reproduce its performance given only an extremely short prompt and the training data. In \emph{input compression}, the explorer receives only one-bit feedback indicating whether each submitted model improves on the running best. Across 8 datasets spanning tabular classification, vision, language modeling, diffusion modeling, and reward modeling, we find that these bottlenecks have little effect on performance: short prompts and compressible feedback are sufficient to reproduce and find high-performance models. The hypothesis is falsifiable: when we deliberately induce validation-set overfitting, the results fail to reproduce with short prompts. Taken together, our results support a description-length explanation for the lack of overfitting in benchmark-driven ML: successful strategies occupy a low-complexity region of strategy space. --- ### Generalized Conformal Predictive Systems Under Distributional Shifts Authors: Jef Jonkers, Johanna Ziegel Published: 2026-06-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.11044v1 Conformal predictive systems (CPS) output calibrated bands of CDFs under exchangeability. We extend generalized CPS to non-exchangeable settings by encoding distributional shifts through observation-specific permutation weights. This yields shift-aware predictive systems that remain valid whenever the test point is, conditionally on the unordered sample, a weighted draw from the observed atoms. Since such weights are typically estimated, we introduce weight-uncertainty boxes and construct robust CPS envelopes with finite-sample or asymptotic confidence guarantees. We derive efficient computation for conformity-measure CPS, conformal binning, and conformal isotonic distributional regression. Experiments under covariate shift and feedback-driven biomolecular design show calibrated predictive bands that widen under stronger shifts and tighten as sample size increases. --- ### Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields Authors: Liya Zhu, Jingzhe Ding, Jian Zhang, Jianbo Xue, Shihao Liang, Ge Zhang, Yi Zhu, Duju Zeng, Xiang Gao, Qingshui Gu, Mailun Gao, Huimin Che et al. Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.11042v4 Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research. --- ### A Spiking Neural Architecture for Coordinating Arm and Locomotor Control Authors: Lea Steffen, Kathryn Simone, Graeme Damberger, Travis DeWolf, Hudson Ly, Chris Eliasmith Published: 2026-06-09 Categories: cs.RO, cs.NE arXiv: https://arxiv.org/abs/2606.11034v1 Spiking Neural Networks (SNNs) coupled with neuromorphic hardware offer energy-efficient solutions for humanoid robot control. However, existing SNN-based motor control systems address bipedal locomotion and arm control in isolation, leaving integrated control of both unaddressed. We present a spiking architecture that coordinates force-based arm control and bipedal locomotion in a simulated humanoid, using the Neural Engineering Framework (NEF) and Semantic Pointer Architecture (SPA). High-level action selection between locomotor and arm control is mediated by a biologically grounded spiking basal ganglia model. We validate the system through co-simulation of Nengo, for the neural control, and Isaac Sim, demonstrating successful target reaching, continuous digit drawing, path-following locomotion, and finally, switching between walking and arm control via basal ganglia disinhibition. To our knowledge, this is the first integrated spiking controller to combine bipedal locomotion and arm control on a full-scale humanoid platform. The full spike-based implementation enables future deployment on low-power neuromorphic hardware. --- ### AuRA: Internalizing Audio Understanding into LLMs as LoRA Authors: Bo Cheng, Lei Shi, Zhanyu Ma, Yuan Wu, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He Published: 2026-06-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.11033v1 Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respectively reuse strong pretrained components, enable native speech-language interaction, or offer lightweight adaptation, they often suffer from transcript-interface latency, costly multimodal training, or sequential speech-language coupling. To address these limitations, we present AuRA, a method that distills audio encoding capability into the LLM. Specifically, AuRA feeds the same speech input to an ASR encoder (as a teacher) and a LoRA-adapted LLM (as a student) through a lightweight audio embedding layer, and uses layer-wise distillation to align the student's hidden states with corresponding teacher representations, thereby internalizing speech representations into lightweight LLM-side adaptations. Compared with cascaded and serial bridge methods, AuRA enables tighter speech-language joint modeling and efficient parallel end-to-end inference, while also reusing pretrained speech and language models rather than requiring large-scale multimodal training. On multiple speech-language benchmarks, AuRA consistently outperforms cascaded systems, speech-to-LLM adaptation baselines, and large-scale speech-language and multimodal models in both effectiveness and efficiency. --- ### U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training Authors: Zhiwen Yang, Jiayin Li, Hao Lu, Hui Zhang, Zihua Wang, Yan Xu Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11032v2 Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT. --- ### Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models Authors: Bowen Ping, Xiangxin Zhou, Penghui Qi, Minnan Luo, Liefeng Bo, Tianyu Pang Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.11025v2 Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the denoising process as a Markov Decision Process and apply PPO-style ratio clipping to enforce a trust region. However, we argue that ratio clipping is structurally ill-suited for flow models: the probability ratio between new and old policies is a noisy, single-sample estimate of the true policy divergence, leading to over-constraining in some regions of the trajectory and under-constraining in others. We propose Flow-DPPO (Flow Divergence Proximal Policy Optimization), which replaces ratio clipping with a divergence proximal constraint. A key observation is that the per-step policy in flow models is Gaussian, enabling exact and cheap computation of the KL divergence between old and new policies. Flow-DPPO employs an asymmetric divergence mask that blocks gradient updates only when they simultaneously move away from the trusted region and violate the divergence threshold. Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency, alleviates catastrophic forgetting, promotes balanced multi-objective optimization, and enables stable multi-epoch training where ratio clipping degrades. Code and models are available at https://github.com/Tencent-Hunyuan/UniRL/tree/main/FlowDPPO. --- ### Generative Archetype-Grounded Item Representations for Sequential Recommendation Authors: Yifan Li, Jiahong Liu, Xinni Zhang, Hao Chen, Yankai Chen, Wenhao Yu, Jianting Chen, Irwin King Published: 2026-06-09 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.11023v1 Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic representations, existing approaches only rely on static encoding of fixed attributes, overlooking the crucial role of target audiences in defining item identity. Moreover, the semantic space struggles to reflect actual user behavior, resulting in a significant gap between semantic representations and behavioral patterns. To address these limitations, we propose GenAIR, a general framework that empowers sequential recommendation with Generative Archetype-grounded Item Representations. Specifically, we first leverage an LLM to analyze item metadata and infer textual description of the Archetype, which represents the conceptual profile of the item's ideal target audience. We then extract the corresponding embeddings in a single forward pass. Further, to ground these generative archetypes in real-world behavior, we introduce a behavioral calibration objective, which explicitly incorporates behavioral signals from actual interactions. This objective adjusts the structure of the embedding space to reflect empirical patterns. GenAIR enables seamless integration with most existing models while maintaining high efficiency. Comprehensive experiments conducted on three real-world datasets demonstrate that GenAIR significantly improves the performance of various sequential recommendation models and consistently outperforms state-of-the-art baseline approaches. Implementation codes are available at https://github.com/AI-Santiago/GenAIR. --- ### Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving Authors: Zehan Zhang, Neng Zhang, Yaoyi Li, Jia Cai, Zhiling Wang Published: 2026-06-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.11019v1 Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving. Several methods attempt to inject history as a static conditioning signal to stabilize outputs, only to induce the planner to copy historical patterns instead of adapting to environment contexts. To address this limitation, we propose Diffusion Forcing Planner (DFP), a diffusion-based planning framework driven by history-guided control. Specifically, DFP decomposes the full trajectory into history, current and future segments, and assign independent noise levels to each segment. The model jointly denoises the historical and the future segments, enforcing a heterogeneous joint diffusion process. At inference, classifier-free guidance (CFG) is applied to steer future sampling using annealed history in a controllable manner. Closed-loop evaluation and comprehensive ablations on nuPlan show that DFP achieves competitive performance while producing continuous, stable, and controllable motion plans in complex driving scenarios. --- ### Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer Authors: Maria Milkova, Maksim Rudnev Published: 2026-06-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.11018v3 Measuring subjective constructs in naturally occurring social media text requires annotation procedures that are theoretically grounded, empirically validated, and transferable to an encoder model for scalable prediction. Using posts annotated according to Schwartz's theory of basic human values, we investigate how different LLMs and prompting strategies, which we call annotation regimes, operationalize the expression of values in text. Beyond standard classification metrics, we evaluate structural alignment, annotation ambiguity, error patterns, and stability across repeated runs. We find that different LLMs produce different value interpretations, and iterative prompt calibration through error analysis reduces misattributions and improves alignment with expert annotations. Error patterns are further used to derive targeted expert-verification rules for corpus annotation. We transfer soft LLM labels to an encoder model for prediction, retaining information about ambiguity in value expression. Finally, a sensitivity analysis on more than one million posts shows that regime-specific annotation differences propagate into predicted levels of value expression, whereas standardized temporal dynamics and the direction of major event responses are more robust. --- ### Data-Driven Runway and Taxiway Exits Prediction of Landing Aircraft: A Case Study at Hartsfield-Jackson Atlanta International Airport Authors: Alex Porcayo, Yutian Pang, Maria Thomas, John-Paul Clarke Published: 2026-06-09 Categories: cs.LG, eess.AS arXiv: https://arxiv.org/abs/2606.11017v1 Airport surface operations increasingly constrain performance at high-throughput hubs. This study examines arrival taxi-in decisions at Hartsfield-Jackson Atlanta International Airport (KATL) and proposes a two-stage, data-driven decision aid that mirrors controller workflow. Stage I predicts the runway exit selected by an arriving aircraft. Stage II predicts whether, given that exit, the aircraft will cross the active departure runway at a designated point or use the end-around taxiway. Models are trained using ASDE-X surface trajectories, aircraft characteristics, ramp destinations, short-horizon traffic rates, and weather across multiple look-back windows. We benchmark nine classifiers, including Random Forest, XGBoost, LightGBM, and CatBoost, and evaluate accuracy, macro-F1, precision-recall behavior, confusion matrices, Brier score, and Expected Calibration Error. Across east and west flows, XGBoost and LightGBM outperform Random Forest. Stage I achieves 0.86-0.89 accuracy with macro-F1 scores of 0.40-0.50, while Stage II achieves 0.70-0.74 accuracy with macro-F1 scores of 0.28-0.55. Feature-importance analysis shows that approach speed is the main driver of exit choice. Departure rate, crossing rate, ramp destination, and, for west flow, the selected exit are the strongest predictors of crossing versus end-around routing. Minority classes remain harder to predict because of feature-space overlap, as shown by t-SNE and UMAP analyses. The proposed framework supports controller situational awareness through calibrated, explainable predictions while preserving human responsibility for final routing decisions. --- ### Superficial Beliefs in LLM Decision-Making Authors: Gabriel Freedman, Francesca Toni Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.11016v2 We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we compare the attribute a model says mattered most with the attribute that best explains its choice under a behavioural model fit to prior decisions. The behavioural model predicts held-out choices well, showing that model behaviour is systematically related to the visible attributes rather than being random. However, direct self-reports and a separate score-based judge recover the behaviourally inferred driver only partially. The resulting picture is neither one of arbitrary behaviour nor one of fully articulated belief - outputs are structured enough to support prediction, but explicit reasons track the recovered driver only imperfectly. This qualitative pattern persists across prompt-order and sampling perturbations, alternative behavioural models, targeted occlusion analyses, and structurally varied decision settings. We interpret this as evidence for ``superficial belief'' in LLM decision-making: models behave as if guided by probabilistic local priorities over attributes, while having only limited verbal access to the attributes that drive their decisions. --- ### Superficial Beliefs in LLM Decision-Making Authors: Gabriel Freedman, Francesca Toni Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.11016v1 We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we compare the attribute a model says mattered most with the attribute that best explains its choice under a behavioural model fit to prior decisions. The behavioural model predicts held-out choices well, showing that model behaviour is systematically related to the visible attributes rather than being random. However, direct self-reports and a separate score-based judge recover the behaviourally inferred driver only partially. The resulting picture is neither one of arbitrary behaviour nor one of fully articulated belief - outputs are structured enough to support prediction, but explicit reasons track the recovered driver only imperfectly. This qualitative pattern persists across prompt-order and sampling perturbations, alternative behavioural models, targeted occlusion analyses, and structurally varied decision settings. We interpret this as evidence for ``superficial belief'' in LLM decision-making: models behave as if guided by probabilistic local priorities over attributes, while having only limited verbal access to the attributes that drive their decisions. --- ### Numbers Beat Words: A Rigorous On-Premise Benchmark for Coupled MIMO Controller Tuning Authors: Yang Shu, Jiaxuan Chen, Haonan Li Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.11015v2 Tuning controllers for strongly coupled multi-input multi-output (MIMO) processes is difficult because decentralized auto-tuning ignores loop interaction and local optimization is start-sensitive. We benchmark whether on-premise open-weight large language models (LLMs) provide useful structural priors, while testing classical alternatives that may make them unnecessary. On a single-loop CSTR, relay-feedback tuning outperforms the LLM. On a pathological quadruple-tank, naive relay, naive LLM, and balanced-start local optimization fail, whereas a scaffolded LLM finds a reliable asymmetric basin and, after local refinement, reaches J = 12.0 +/- 0.16 in 10/10 runs. However, an ablation shows that this reliability depends more on an answer-shaped prompt example than on reasoning over coupling data. A direct data-driven alternative, Virtual Reference Feedback Tuning (VRFT), uses one open-loop experiment and no LLM; with the same refinement it succeeds in 10/10 runs and improves the result to J = 11.12 +/- 0.05. Although VRFT requires a reference-model time constant tau, a deterministic median-tau rule matches or exceeds LLM-guided selection at no extra cost. Across four structurally different plants, the relative gain array computed from step tests predicts when a structural prior is worth using; optimizer start-sensitivity provides a confirming second signal. The resulting boundary is clear: use classical tuning on benign plants, prefer VRFT when informative open-loop data are available, and reserve LLMs for structural initialization when direct routes are unavailable. The benchmark shows that the LLM's value is structural rather than numerical, and that on the central case, numbers beat words. --- ### An Uncertainty Estimation Framework for Dose Accumulation in Adaptive Radiotherapy: Application to CBCT-Guided Radiotherapy for Cervical Cancer Authors: Cedric Hemon, Delphine Lebret, Jean-Claude Nunes, Valentin Boussot, Karine Peignaux, Nathalie Mesgouez-Nebout, Chantal Hanzen, Antoine Simon, Anaïs Barateau, Renaud de Crevoisier, Caroline Lafond Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11012v1 Background and purpose: oART enables daily plan adaptation to interfraction anatomical variations, but cumulative dose estimation remains limited by DIR, segmentation, and anatomical uncertainties. We introduce IMPACT-DoseAcc, an uncertainty-aware dose accumulation framework, within IMPACT for semantic feature-driven image analysis. The framework is modality- and disease-agnostic and is applied to CBCT-guided oART for cervical cancer (LACC). Material and Methods: Nine LACC patients were retrospectively analyzed using daily CBCT-derived virtual CTs for dose recalculation. IMPACT-DoseAcc focuses on uncertainty from DIR, without modeling vCT-generation uncertainty. Two DIR uncertainty strategies were tested within IMPACT-Reg: a Bayesian segmentation-guided approach using one probabilistic model to quantify anatomical uncertainty, and an ensemble of segmentation models targeting structures to capture epistemic variability. Voxel-wise uncertainty maps were propagated through dose warping and accumulation to generate probabilistic dose-volume histograms. Ensemble uncertainty was quantified from voxel-wise standard deviation across deformation fields, and geometric error was assessed using surface distance between warped and validated contours. Anatomical-variability weighting refined aggregation. Results: Ensemble DIR uncertainty correlated with geometric error, with Pearson coefficients of 0.63 for CTVt and 0.66 for bladder. For CTVt, pDVHs achieved 96.3 +/- 3.9% coverage, showing calibration of propagated uncertainty. Weighting stabilized estimates across fractions and organs. Conclusions: IMPACT-DoseAcc propagates registration-driven uncertainty to cumulative dose metrics, improving interpretation of accumulated dose under anatomical variations. Its 3DSlicer integration supports reproducible, uncertainty-informed ART workflows. --- ### Who Brought Easter Eggs to Eid? Auditing Cultural Translation of Math Word Problems Across Diverse Languages and Regions Authors: Parisa Suchdev, Juniper Lovato Published: 2026-06-09 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.11009v1 Large language models are increasingly used to adapt math word problems for personalized learning at scale, but it remains an open question whether those adaptations are consistent across models, preserve cultural diversity at scale, and reveal which cultural entities models treat as most salient. We analyze how Claude Opus 4, GPT-4.1, and Gemini 2.5 Pro adapt 60 English math word problems into Bengali, Hindi, Punjabi (India), Urdu, Sindhi (Pakistan), Italian, and Sicilian (Italy), a language set spanning the full resource spectrum, from high-resource Italian and Hindi to under-studied Sindhi, Sicilian, and Punjabi. We annotate 6,489 entity transformations, coding whether models preserve, localize, generalize, omit, or change entities such as names, foods, and places. Models agree on transformation type in 62.5% of cases and on specific substitutions in only 33.5%, meaning model choice directly shapes which cultural world students encounter. All 21 language-model combinations show entropy collapse, with adaptation compressing rather than expanding cultural diversity. Models prioritize surface markers such as names, foods, and currencies while preserving deeper structural features such as grade-level systems that embed culturally specific assumptions. Despite prompts specifying target countries, models misattribute regional context by using Bangladeshi taka for Indian Bengali students and produce cross-cultural contamination, such as adapting egg hunts as Eid activities. Some failures are visible in individual translations. Others, including diversity collapse, systematic preference for surface markers, and consistent regional misattribution, emerge only through corpus-level analysis. The surface plausibility that makes adapted problems look correct is precisely what makes deeper failures easy to overlook. --- ### Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill Authors: Junchang Zheng, Junfeng Tan, Jialiang Lin Published: 2026-06-09 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.11007v1 OpenClaw has rapidly emerged as a transformative artificial intelligence (AI) agent framework, and its ability to autonomously execute complex, multi-step tasks has attracted an ever-growing and diverse user base. However, this capability comes with significant risks. While existing research has made important strides in characterizing these threats, such work is predominantly directed at technically sophisticated audiences. It remains largely inaccessible to non-technical users. This demographic now makes up an increasingly large and underserved portion of the community, yet it is these very users who most urgently need practical and straightforward guidance. In response, we bridge this gap through a series of interconnected efforts designed to lower the risk barrier for non-technical OpenClaw users. First, we identify and categorize seven core risks that OpenClaw users may encounter in daily usage, explaining each in plain language so that non-technical users can readily grasp the nature and potential consequences of these threats. Second, for each identified risk, we distill a set of corresponding defensive strategies into clear and actionable operational steps that are easy to follow. Third, to make protection even easier, we provide a companion OpenClaw Skill that automates key security configurations, enabling users to safeguard their systems with minimal manual intervention. Through this work, we demonstrate that safeguarding against the risks of intelligent agents need not be the exclusive domain of security experts, and that non-technical users can meaningfully participate in reducing these risks through simple, practical actions. --- ### IPSM-Bench: A New Intermediate Phase Segmentation Benchmark in Microstructure Images of Zinc-Based Absorbable Biomaterials Authors: Jinglin Xu, Shangyan Zhao, Jiabo Wang, Xinghong Mu, Yulong Lei, Jiacheng Zhang, Hongbo Sun, Yageng Li Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11001v1 Zinc-based alloys are indispensable emerging absorbable metallic biomaterials, and their macroscopic performance is governed by microstructural characteristics. Intermediate phases-key microstructural constituents-are pivotal in regulating mechanical and functional properties. However, intermediate phase segmentation in zinc alloy microstructures faces formidable challenges: scarce annotated datasets, low contrast, difficulty detecting small targets, and heterogeneous morphologies. To this end, we construct IPSM-Bench, the largest high-quality dataset for zinc-alloy intermediate phase segmentation. Furthermore, we propose SCoP-SAM, a new Spatial Context Prior-guided SAM method that leverages the gradient structure and grayscale properties of intermediate phases to capture spatial context priors and incorporates them into the entire SAM encoding-decoding process, improving segmentation performance. Based on the proposed IPSM-Bench, we establish a new benchmark for intermediate phase segmentation to systematically evaluate state-of-the-art (SOTA) methods and advance research on zinc alloy microstructure analysis. Extensive experiments on IPSM-Bench and additional public alloy benchmarks demonstrate that our SCoP-SAM not only achieves SOTA performance for zinc-alloy intermediate phase segmentation but also generalizes remarkably well to other alloy scenarios. --- ### Analog Quantum Asynchronous Event-Based Graph Neural Network Authors: Kristian Sotirov, Shaheen Acheche, Antonio A. Gentile, Osvaldo Simeone Published: 2026-06-09 Categories: quant-ph, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.11000v1 Asynchronous, event-based graph neural networks (AEGNNs) have recently emerged as an efficient paradigm for processing the sparse and high-temporal-resolution data from event cameras. In this paper, we propose quantum analog AEGNNs (QA-AEGNNs), a novel framework to implement an AEGNN on a neutral-atom quantum computer. Neutral-atom quantum processors offer a programmable analog quantum computing platform based on controllable Rydberg-atom interactions. To this end, we map the streaming event data to an array of trapped neutral atoms, where each atom represents a graph node (event) and is positioned such that geometric proximity reflects the spatio-temporal neighborhood of events. The native Rydberg Hamiltonian of the quantum processor is programmed to mirror the message-passing computations of the AEGNN, with atomic qubit states serving as node feature embeddings and inter-atom interactions realizing graph edges. Furthermore, we propose a hybrid quantum-classical training scheme in which the analog Hamiltonian parameters (e.g., laser pulse amplitudes and detunings) are optimized using classical feedback to learn the quantum AEGNN model from data. Our approach leverages the continuous Hamiltonian dynamics and massive parallelism of neutral-atom quantum systems to natively execute event-based graph computations with potential accuracy improvements --- ### Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning Authors: Bocheng Ju, Jianhua Wang, Chengliang Liu, Xiaolin Chang Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.10989v1 Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstrained. This paper introduces \emph{Null-Space Constrained Response-Specified Unlearning} (NSRU), a projection-constrained low-rank framework for controlled LLM unlearning. NSRU uses an explicitly structured safe target response to specify the desired behavior for each forget query, while suppressing the original undesired content. To localize adaptation, NSRU estimates per-module retain subspaces from benign hidden representations and uses an orthogonal-projected low-rank parameterization to confine LoRA updates to the null space of the retain subspace. The resulting objective jointly optimizes safe-target learning, undesired-response suppression, and retention preservation under this constrained parameterization. We provide a local first-order analysis showing that the projected update reduces retain-side perturbations while preserving editable directions for shaping forget-query behavior. Experiments on TOFU show that NSRU effectively suppresses extractable forget-set knowledge while improving retain QA performance, model utility, and safe-target alignment over representative baselines. On WMDP, NSRU keeps hazardous-domain accuracy near the random-choice region while preserving broad and domain-adjacent MMLU utility. Ablation studies support the complementary roles of safe-target supervision, undesired-response suppression, retention loss, and null-space projected updates, while sensitivity and robustness analyses indicate stable behavior across the tested hyperparameter and prompt variations. --- ### AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects Authors: Yiming Zhao, Haoyu Sun, Aoyu Wang Published: 2026-06-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2606.10988v1 While recent advancements in generative AI have substantially accelerated static 3D model creation workflows, the synthesis of category-agnostic 3D animations remains a significant bottleneck in 3D asset production. Current methods for category-agnostic animation generation exhibit critical limitations in inference speed, motion quality, and adherence to textual prompts, thereby leaving the process dependent on labor-intensive manual artistry. To address these challenges, this paper introduces AnimaSpark, a novel pipeline for category-agnostic 3D animation generation. Our approach is motivated by the key insight that for many fundamental motions in the 3D world, the corresponding joint transformations can often be effectively modeled within a two-dimensional subspace. The pipeline begins by rendering a rigged static 3D model into multi-layered image representations of its mesh and skeleton, which are subsequently fed into a video generation model. We then employ a keypoint tracking algorithm on the generated video to capture the motion of the skeletal joints projected onto the camera's viewing plane. In the final stage, we distill the planar translations and rotations from these tracked keypoints and lift them from the 2D domain into 3D space to animate the character. Comprehensive evaluations reveal that our method achieves superior performance over existing state-of-the-art techniques across key metrics, including text-motion alignment, quality of motion, and computational efficiency. --- ### Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets Authors: Yi Chen, Rushuai Yang, Qiang Chen, Dongyan, Huo Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.10979v1 Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints. These features make it difficult to use standard deep reinforcement learning (DRL) algorithms, whose action interfaces typically assume either a fixed finite action catalog or a simple Euclidean space. Motivated by a Taylor expansion of the optimal action-value function, we propose Bellman--Taylor score decoding, a framework that moves policy learning to a Euclidean score space while enforcing feasibility through an action decoder. The induced latent-score MDP then can be optimized by standard DRL algorithms without differentiating through the decoder. We provide a performance guarantee showing that the optimality gap of this approach decomposes into a structural approximation error and an algorithmic learning error. Lastly, we apply this framework to a queueing network control problem, where the policy essentially learns a state-dependent index-based dispatching rule. Numerical experiments show near-optimal performance in small instances and considerable improvements over benchmarks in larger systems. --- ### Learning Doubly Sparse Explicitly Conditioned Transforms Authors: Tudor Pistol Published: 2026-06-09 Categories: math.OC, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2606.10975v1 Finding convenient spaces in which certain hypotheses regarding an assumed sparse structure of natural signals hold true has become a desirable result in recent research, its implications being reflected in areas such as data compression, noise reduction and feature extraction. While the extensively used analytical transforms, such as DFT or DCT, already provide efficient algorithms and robust sparse representations, they assume a fixed prior about the data, failing to accurately capture the specific structure of more restrictive classes of signals. To address this, the concept of a data-adaptive, learnt transform has been introduced in the literature, allowing for the reduction of a residual term in the transform domain. More recent studies have shown that the condition number serves as a good metric in this context, where the desired outcome alternates between a generalizing tendency and one that achieves minimal approximation error. Motivated by these considerations, we introduce the learning of a structured, explicitly conditioned transform formulated as the product of a fixed canonical matrix and a refining data-adaptive sparse component. This approach seeks to preserve the advantages of fast and stable analytical transforms, while introducing controllable adaptivity to the data. No references that concern this specific formulation have been identified so far, indicating its novelty. The proposed algorithm is motivated within the framework of inexact proximal methods, leveraging a newly derived closed-form projection operator. Empirical observations demonstrate state-of-the-art results on the doubly sparse transform learning problem and comparable performance with its dense variant at significantly lower computational costs and sometimes faster convergence and better avoidance of bad local minima. --- ### Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks Authors: Ipek Sen, Ozgur Ozdemir, Elena Battini Sonmez Published: 2026-06-09 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2606.10972v1 This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning. In pulmonary sound classification, spectrogram-based representations suffer from inconsistent temporal dimensions due to varying respiratory cycle durations. Along with traditional trimming/zero-padding, adaptive-length windowing was presented to fix their temporal dimensions. Their spectral and temporal dimensions were optimized by testing a range of parameters. Different convolutional neural network (CNN) architectures were employed to extract features from the two-dimensional representations obtained over the sub-phases. The extracted sub-phase features were then fused using various strategies including direct concatenation, gated recurrent unit (GRU) network and GRU with attention mechanism. Model performances were assessed through respiratory cycle-based evaluation and subject-based evaluation comprising multiple respiratory cycles. Several data augmentation techniques were also studied to cope with limitations in data size. The best cycle-based F1-score (0.877) was obtained using the MFCC matrices with thirteen coefficients and 64-point time resolution per sub-phase representation followed by direct feature concatenation, and the best subject-based F1-score (0.855) was obtained using the MFCC matrices with thirteen coefficients and 256-point time resolution per full-cycle representation, both obtained by adaptive-length windowing. Augmentation degraded the performance of models overall, yet mixup augmentation was the best among the methods tested. MFCC outperformed log-mel spectrogram and VAR model in differentiation of asthma and COPD. Sophisticated fusion strategies did not improve the diagnosis. Augmentation did not contribute, demonstrating the significance of authentic data in pulmonary sound studies. --- ### Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning Authors: Renjie Mao, Xiangxin Zhou, Lvfang Tao, Yixin Ding, Yu Shi, Yongguang Lin, Yuheng Wu, Honglin Zhu, Qian Qiu, Wenxi Zhu Published: 2026-06-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.10968v2 Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales. --- ### Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks Authors: Pradnya Halady, Jiale Wei, Zdravko Marinov, Alexander Jaus, Simon Reiß Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.10967v1 Visual in-context learning has been proposed as a pathway towards dynamic models that can generate predictions based on a provided context and thereby can adapt to new vision tasks at test-time. Yet, the evaluation of the adaptation capabilities of these models has been limited to narrow setups that mainly mirror tasks or image domains from pre-training for which real adaptation is not required. We address this gap by constructing a broad Visual In-Context BEnchmark (VIBE) with a focus on diverse imaging domains and a wide range of tasks. With this, we are able to get a much clearer picture of the adaptive capabilities of visual in-context models when faced with new image- and task distributions. We stress test six models on $14$ datasets and $12$ tasks (in total, we explore $106$ dataset-task combinations) and compare them under a unified, reproducible evaluation protocol, in an one-shot setting. Our evaluation uncovers key insights on the state of visual in-context learning, including limitations, systematic failure modes and promising directions. To foster broader evaluation, we will openly release our VIBE toolkit. --- ### Population-Aware Physics-Informed Neural Particle Flow for Robust Spacecraft Bayesian Navigation Authors: Batu Candan, Simone Servadio Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.10959v2 Spacecraft navigation often requires Bayesian inference from sparse nonlinear measurements that produce curved, multimodal, or geometrically constrained posterior distributions. Physics-informed neural particle flow (PINPF) addresses such problems by learning a deterministic prior-to-posterior transport field from the governing probability evolution equation, but its particle-wise architecture does not explicitly account for the empirical particle population. This paper introduces population-aware PINPF (PA-PINPF), which conditions each particle velocity on a permutation-invariant Deep Sets representation of the complete particle set. PA-PINPF-State summarizes particle positions, whereas PA-PINPF-Feature summarizes the local physics-informed features, including likelihood and score information. Both retain the unsupervised PINPF residual and require neither posterior samples nor labeled transport trajectories. The methods are evaluated over 100 randomized time-difference-of-arrival tasks representative of RF cross-link and ground-station localization and 100 range-measurement tasks with an onboard sensor field-of-view constraint. Results demonstrate that population-level Bayesian features provide useful global information for learned particle transport in nonlinear spacecraft-navigation problems. --- ### Population-Aware Physics-Informed Neural Particle Flow for Bayesian Update Authors: Batu Candan, Simone Servadio Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.10959v1 Physics-informed neural particle flow (PINPF) learns a deterministic transport field that moves particles from a prior distribution toward a Bayesian posterior while enforcing the governing probability-evolution equation. However, the standard PINPF velocity model processes particles independently and therefore does not explicitly condition its transport decisions on the empirical particle population. This paper introduces population-aware PINPF (PA-PINPF), which augments each particle update with a permutation-invariant Deep Sets representation of the full particle set. We investigate two population encoders. PA-PINPF-State summarizes the particle states, whereas PA-PINPF-Feature summarizes the complete local physics-informed feature vectors, including particle position, pseudo-time, measurement information, likelihood values, and score information. The latter allows the population context to represent not only particle-cloud geometry, but also the population-level Bayesian transport geometry. The methods retain the original unsupervised physics-informed residual objective and require no ground-truth posterior samples during training. Experiments on range-measurement tasks and nonlinear time-difference-of-arrival posterior transport demonstrate that both population-aware variants improve over particle-wise PINPF, while feature-population encoding provides the strongest performance. These results show that population-level physics features provide useful global information for learned Bayesian particle transport. --- ### Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam? Authors: Tengchao Lv, Dongdong Zhang, Jiayu Ding, Yilin Jia, Yuzhong Zhao, Yupan Huang, Wenshan Wu, Xiangyang Zhou, Shaohan Huang, Nan Yang, Li Dong, Lei Cui et al. Published: 2026-06-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.10956v1 The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, as it requires long-horizon planning and reasoning, precise parameter configuration, and multi-application integration. To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE), featuring 200 comprehensive practical-operation tasks across Word, Excel, and PowerPoint. Each task is scored on a 100-point rubric scale using 7,118 machine-gradable criteria, and Score Rate (SR) denotes the mean percentage of rubric points earned across these tasks. We benchmark 7 frontier LLMs and observe stark limitations: single-turn models score a maximum of 36.6%. A stronger agentic system with execution feedback, iterative repair, and broader Office automation access reaches 68.8%, but remains below the 95.5% community-reference score used as a scoring sanity check. Ultimately, our experiments demonstrate that despite recent advancements in code generation, achieving reliable fine-grained Office document automation remains a significant challenge for current code-generating LLM and agent systems. ---