# Research Papers — 2026-05 · bundle page 24 of 326 > Full-text markdown of papers #1151–1200 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/24 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/23.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/25.md) ### KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning Authors: Dominik Soós, Meng Jiang, Jian Wu Published: 2026-05-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.31099v1 Science news is an important medium to communicate discoveries between the research communities and the public. Yet, most metrics for generated or summarized text evaluate semantic similarity and factual consistency, but do not measure how much knowledge readers learn from the news. We introduce KnowledgeGain, a metric that evaluates the quality of science news by measuring how much knowledge readers gained after reading it. To evaluate the metric, we first performed a controlled human study and showed that the metric successfully captures the differential knowledge gained by human readers reading different types of science media. The data allowed us to calibrate a prompt-only LLM reader simulator. We use it to rank and filter candidate articles before human evaluation. A second human study shows that articles selected with this simulator improve post-reading accuracy and normalized KnowledgeGain over a strong generation baseline. Our work is a step toward generating science news that better meets the knowledge and comprehension goals of Bloom's Taxonomy. --- ### SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition Authors: Yunkai Lou, Longbin Lai, Shunyang Li, Zhengping Qian, Ying Zhang Published: 2026-05-29 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2605.31097v1 Mainstream relational databases ship a uniform feature set across deployments, although individual workloads exercise only a fraction of the available subsystems. We investigate whether a database can instead be generated on demand with a feature set matched to the target workload. We present SpecDB, a system that uses large language models (LLMs) to synthesize customized relational databases. We survey 9 production systems and decompose them into 10 functional modules, each further divided into implementation variants. To capture cross-module dependencies, including cases where implementations in disjoint subtrees must be co-designed, we adopt the FODA feature model and extend it with a cooperate edge, yielding a dependency graph DBGraph. SpecDB operationalizes DBGraph through a layered module-construction pipeline in which each module is generated, validated, and integrated by a dedicated subagent (driven by three inner agents: Main, Tester, Architect), and a Refining Agent that iteratively repairs and tunes the assembled database against a user-supplied refining harness with read-only access to existing database source code. A companion selection component translates a natural-language workload description into a set of implementation variants, providing an end-to-end pipeline from workload description to deployable database. We evaluate SpecDB on TPC-C with BenchmarkSQL. The generated database (23,779 lines of Rust) completes 60-minute TPC-C at 1 and 10 warehouses with zero errors. At 10 warehouses it reaches tpmC=130, compared to 128 for PostgreSQL and 127 for MySQL, with comparable latency at ~3% of their code size. Because the agent operates at module-specification level rather than product source, it can in principle combine techniques across system boundaries. Paired with falling LLM costs, generating a purpose-built database for a target workload is becoming straightforward. --- ### iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning Authors: Chang-Bin Zhang, Yujie Zhong, Qiang Zhang, Kai Han Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31096v1 While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy during the inference phase remains underexplored. In this work, we empirically find that mandating explicit object boxes in visually grounded CoT during inference often degrades performance compared to standard textual CoT, which reasons without explicit visual grounding. We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding introduces unnecessary interference with the model's primary objective of answer prediction. To address this problem, we propose Internalizing Visually Grounded Reasoning (\textbf{iVGR}), a novel reinforcement learning framework that transfers localization capabilities into the textual reasoning process. We employ a dual-stream training strategy, where a textual stream is aligned with a high-quality visually grounded stream via a proposed consistency reward, enabling the model to localize accurately without explicit grounding during inference. Extensive experiments demonstrate that our method significantly outperforms existing baselines on fine-grained benchmarks, while maintaining the flexibility to support tool-assisted inference workflows. --- ### Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation Authors: Erik Großkopf, Soumya Snigdha Kundu, Hendrik Möller, Nicolas Münster, Mehdi Astaraki, Paula Tamara Buzduga, Kerstin Ritter, Benedikt Wiestler, Jan Kirschke, Jonathan Shapey, Tom Vercauteren, Florian Kofler Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.31094v1 The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between predicted and ground truth segments, which is only straightforward when the IoU threshold exceeds 0.5. Below 0.5, multiple matching strategies emerge in a poorly explored problem space. We systematically elucidate this space by recasting segment matching as a constrained bipartite assignment problem. Independently bounding the prediction- and ground-truth-side degrees yields four matching strategies: One-to-One, Many-to-One, One-to-Many, and Many-to-Many. We show that the first three are well-defined within the PQ framework, while Many-to-Many falls outside it. These strategies become relevant when instances are fragmented, adjacent objects are difficult to delineate, or annotations are noisy. Central to our framework is a vertex-based accounting of TP, FN, and FP, anchored to ground truth and predicted segments rather than to matching edges. We further show that the framework extends naturally to part-aware panoptic segmentation, and we explore part-aware evaluation on biomedical data. Across configurable case studies we report how different combinations of thresholds and matching strategies behave in practice. We release a unified open-source package built on Panoptica. It exposes Voronoi-based region-wise analysis, part-aware evaluation, and Area Under Threshold Curve computations as configurable options. --- ### Cross-Modal Clinical Knowledge Integration for Mammography Report Generation Authors: Jiayi Zhu, Fuxiang Huang, Yu Xie, Xi Wang, Zhixuan Chen, Yuan Guo, Qingcong Kong, Zhenhui Li, Qiong Luo, Hao Chen Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31093v1 Breast cancer is a major global health concern, and mammography screening plays a central role in early detection. The large volume of screening examinations creates a substantial workload for radiologists, making accurate and consistent report generation a critical clinical challenge. Existing automated mammography report generation methods primarily focus on direct visual-to-text mapping, while overlooking the structured clinical reasoning process followed by radiologists in real-world practice. To address this limitation, we propose MammoRG, a mammography report generation framework that explicitly simulates the clinical reporting workflow by following the BI-RADS guideline and incorporating prior clinical knowledge to produce diagnostic reports. Specifically, MammoRG adopts a two-stage training framework. In the first stage, the model learns to integrate clinically relevant prior knowledge from a patient's four-view mammograms through classification-based supervision. In the second stage, a terminology-aware supervised fine-tuning strategy is introduced to model mammography-specific clinical terms as atomic semantic units, enabling the generation of high-quality reports with improved clinical consistency. To facilitate clinical efficacy evaluation of generated reports, we further develop MammoRGTool, a dedicated mammography report parsing tool that extracts structured clinical information from free-text reports. Extensive experiments demonstrate that MammoRG consistently outperforms existing methods across multiple clinical efficacy metrics, particularly in diagnosis-related BI-RADS F1, where it surpasses the second-best model by 2.73%, 2.04%, 1.90%, and 3.27% on the internal, external 1, external 2, and VinDr-Mammo datasets, respectively. --- ### On Revisiting Entropy for Identifying Mislabeled Images Authors: Chunlei Li, Zixuan Zheng, Yilei Shi, Guanglu Dong, Pengfei Li, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.31090v1 Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labels. We address this challenge by proposing a novel approach for mislabeled data detection that leverages training dynamics. Our method is grounded in the key observation that correctly labeled samples exhibit consistent entropy decrease during training, while mislabeled samples maintain relatively high entropy throughout the training process. Building on this insight, we introduce a signed entropy integral (SEI) statistic that captures both the magnitude and temporal trend of prediction entropy across training epochs. SEI is broadly applicable to classification networks and demonstrates particular effectiveness when integrated with contrastive language-image pretraining (CLIP) architectures. Through extensive experiments on four medical imaging datasets -- a domain particularly susceptible to labeling errors due to diagnostic complexity -- spanning diverse modalities and pathologies, we demonstrate that SEI achieves state-of-the-art performance in mislabeled data identification, outperforming existing methods while maintaining computational efficiency and implementation simplicity. Our code is available at https://github.com/MedAITech/SEI. --- ### On couplings for kinetic Langevin diffusions Authors: Nawaf Bou-Rabee, Sonja Cox, Roy Schieven Published: 2026-05-29 Categories: math.PR, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2605.31088v1 For the kinetic Langevin diffusion and its splitting discretizations, the hypoelliptic noise structure makes the relationship between couplings and total variation (TV) bounds more subtle than in the elliptic case. We establish that, for the kinetic Langevin equation with quadratic potential, no Markovian coupling (continuous or discrete) captures the asymptotic decay rate of the TV distance between two solutions with different initial values; the canonical iterated one-shot (or sticky) coupling, for which we derive an exact contraction formula, saturates this lower bound. On the constructive side, we show that the recent sharp TV bounds obtained by Chak and Monmarché admit a natural interpretation through an explicit non-Markovian coupling, built from an optimal coalescence trajectory characterized by a classical minimum-energy control problem. For the OBABO splitting scheme, this approach additionally eliminates the Hessian-Lipschitz, step-size, and final-time assumptions in the work of Chak and Monmarché. --- ### Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory Authors: Han Zhang, Zihao Tang, Xin Yu, Xiao Liu, Yeyun Gong, Haizhen Huang, Yan Lu, Weiwei Deng, Feng Sun, Qi Zhang, Hanfang Yang Published: 2026-05-29 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.31086v2 In existing memory benchmarks for Large Language Models (LLMs), the evaluated dialogue sessions often lack long-term semantic consistency, and the underlying personas tend to be flat and static. Furthermore, in real-world scenarios, interactions between users and assistants involve more diverse, heterogeneous data streams, such as documents and emails. These shortcomings significantly limit the realism and effectiveness of current evaluations. To address these limitations, we introduce RHELM (Realistic, Heterogeneous, and Evolving Long-term Memory). Driven by meticulously crafted user profiles and a novel LOOP (pLan-rOllout-evOlve-Prune) module, we construct realistic dialogues across diverse interaction scenarios that exhibit dynamic temporal evolution and long-term coherence. Crucially, these dialogues are deeply integrated with heterogeneous external sources synchronized with the user's temporal event trajectory. The resulting benchmark encompasses challenging question-answer pairs spanning seven inquiry types, with each question mapping to at least one of 27 critical memory characteristics that we identify as essential yet underexplored in current research. Comprehensive experiments across full-context models, retrieval-augmented generation (RAG) methods, and representative memory frameworks reveal that contemporary approaches still expose critical weaknesses in complex, real-world settings, particularly in resolving multi-source aggregation and real-world contextual reasoning. --- ### A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models Authors: Iosif Tsangko, Andreas Triantafyllopoulos, George Margetis, Ioana Crihana, Björn W. Schuller Published: 2026-05-29 Categories: cs.MM, cs.AI, cs.CL, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2605.31080v1 Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy and intellectual-property constraints may favour small on-premise vision-language models (VLMs). This pilot study investigates curator-guided multilingual art description with Qwen2.5-VL-3B-Instruct for German, Romanian, and Serbian. We construct a parallel BLV-oriented caption corpus from artwork images and metadata, and compare language-specific LoRA adapters with a single multilingual adapter under a fixed backbone and training budget. Evaluation combines automatic lexical and embedding-based metrics with an LLM-as-Judge protocol calibrated against a small Romanian BLV pilot study. Under our pilot setup, language-specific adapters show more stable controllability and visually grounded description quality for Romanian and Serbian, while multilingual adaptation remains competitive in German. We frame these findings as deployment-oriented evidence for small on-premise VLMs, and highlight the need for larger BLV user studies and broader language coverage before drawing general conclusions about multilingual accessibility. --- ### Forecasting threshold exceedance of atmospheric variables at a specific location Authors: Roberta Baggio, Jean-François Muzy Published: 2026-05-29 Categories: physics.ao-ph, physics.data-an, stat.ML arXiv: https://arxiv.org/abs/2605.31079v2 Accurate short-term forecasting of extreme weather events is important for early warning and risk mitigation. We compare two approaches for predicting site-specific threshold exceedances of weather variables: direct binary probabilistic models trained on thresholded outcomes and full-distribution parametric models trained on the continuous target. Using an analytically tractable Gaussian random-location model, in which the distribution is predictably shifted by the covariates, we quantify the consequences of the information loss induced by thresholding and derive the rare-event behavior of prediction errors and forecast skill. The analysis predicts an increasing relative advantage of the full-distribution approach as event probability decreases, because binarization progressively discards information contained in the continuous response. We then compare the two approaches to forecast wind speed and accumulated rainfall at various weather station sites over southeastern France using the same hybrid neural-network architecture. Although wind speed and rainfall depart from the toy-model assumptions, its main qualitative predictions are recovered for both variables: the relative advantage of distributional modeling increases toward rarer thresholds. This agreement further suggests that a substantial fraction of the forecastable signal associated with extreme events arises from predictable shifts in the conditional distribution. For the reasonably suitable parametric families examined, the results show limited sensitivity to the selected class of distribution. Overall, the results highlight the statistical advantage of training on continuous observations rather than on thresholded binary outcomes when forecasting rare threshold exceedances. --- ### Forecasting threshold exceedance of atmospheric variables at a specific location Authors: Roberta Baggio, Jean-François Muzy Published: 2026-05-29 Categories: physics.ao-ph, physics.data-an, stat.ML arXiv: https://arxiv.org/abs/2605.31079v1 This study compares two methodological approaches for predicting, at a given site, threshold exceedances of atmospheric variables such as temperature and wind speed: (i) direct probabilistic methods, which treat exceedance as a binary classification problem, and (ii) full distribution probabilistic methods, which model the complete conditional probability law of the target variable. Using theoretical analysis and numerical simulations on a toy model, alongside real-world data from the MeteoNet dataset (2016--2018) for southeastern France, we demonstrate that the full distribution approach consistently outperforms the direct method for rare, extreme events. This advantage arises because the full distribution approach effectively learns the parameters of the conditional distribution from moderate and mild intensity events, thereby achieving better calibration and discrimination in the tails. We find that the specific parametric shape of the chosen distribution plays a secondary role compared to accurately capturing predictable shifts in its bulk properties (i.e., mean and variance). This empirical indistinguishability is also informative about the physical mechanics driving atmospheric extremes, suggesting that extreme exceedances are primarily driven by significant conditional displacements of the entire distribution rather than by unpredictable, fat-tailed anomalies within a static climatology. Our results are validated for both strong surface wind speeds and intense hourly rainfall, with performance evaluated using proper scoring rules (Brier score, logarithmic score) and deterministic skill scores (Peirce Skill Score, CSI, HSS). These findings highlight the critical importance of modeling the full probability distribution for rare-event forecasting and provide practical guidance for improving extreme weather prediction in operational meteorology. --- ### Task-Focused Memorization for Multimodal Agents Authors: Tao Zou, Yichen He, Tian Qiu, Yuan Lin, Hang Li Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31075v1 Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memorize. Multimodal agents, such as embodied agents, continuously perceive, reason, and act in real or virtual environments, receiving an unbounded stream of multimodal observations. From this combinatorial explosion of information, an agent must selectively retain content that is relevant to its role in the environment and valuable for future tasks. To bridge this gap, we frame memory generation as a learnable memorization policy and introduce TaskMem (Task-focused Memorization Policy Learning), a reinforcement-learning-based framework that enables the policy to dynamically adjust its focus to the demands of real tasks encountered in the environment. TaskMem adopts a two-phase training paradigm: Phase One learns how to memorize by optimizing memory quality under fundamental fidelity requirements; Phase Two occurs after deployment, where the agent learns what to memorize by tuning an adapter on its base MLLM, using recent environment tasks to define a reward model that guides the memorization policy toward task-relevant content. To evaluate our approach, we reformulate VideoMME, EgoLife, and EgoTempo into streaming benchmarks that simulate a realistic setting in which an agent processes streaming observations and handles tasks arriving online. To isolate memory assessment, the questions must be answered using only the agent's memory, without access to raw video. Built on Qwen3-VL-30B-A3B, TaskMem improves VQA accuracy by 6.3%, 7.0%, and 5.3% on these benchmarks, respectively. --- ### ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails Authors: Yan Wang, Zhixuan Chu, Zihao Xue, Zhen Bi, Bingyu Zhu, YueFeng Chen, Zeyu Yang, Jungang Lou, Longtao Huang, Ningyu Zhang, Kui Ren, Hui Xue Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.31073v1 Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful enforcement: a model may recognize a harmful intent in its reasoning but still predict a safe label, or issue an unsafe decision without policy-grounded justification. We identify this safety-critical failure mode as the deliberation-to-enforcement gap. Unlike general chain-of-thought faithfulness, guardrail reliability requires policy execution consistency: the generated reasoning should be grounded in the safety policy, and the final decision should be entailed by that reasoning. We propose ConsisGuard, a consistency-aware framework for reasoning-based LLM guardrails. ConsisGuard performs Policy-to-Decision Trajectory Distillation and Functional Coupling Alignment, aligning the internal coupling between safety deliberation and decision enforcement. Experiments on prompt and response harmfulness detection benchmarks show that ConsisGuard improves detection performance while reducing policy execution failures. These results suggest that reliable reasoning-based guardrails require accurate faithful execution of safety policies. --- ### Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach Authors: Marius Potfer, Cheng Wan, Pierre Gruet Published: 2026-05-29 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2605.31070v1 Bidding in the European Frequency Containment Reserve (FCR) market is challenging for flexibility providers because competing offers are hidden and bidders observe only partial feedback form the market, such as, clearing price and awarded quantity. For a participant active in a single country, we show that the multi-country FCR clearing problem can be recast as a repeated multi-unit uniform-price auction against an endogenous vector of opposing bids. This reformulation yields an online learning problem and allows us to adapt a Best-of-Both-Worlds combinatorial semi-bandit algorithm implementable from this standard market feedback. The resulting bidder achieves logarithmic pseudo-regret in stochastic environments and $\mathcal{O}(\sqrt{T})$ regret in adversarial ones. Synthetic experiments confirm the expected scaling, and backtests on historical European FCR data show competitive performance in practice: the method performs especially well on stable products, while EXP3-type baselines can be safer under stronger non-stationarity. Overall, the results show that learning-based bidding in FCR markets is theoretically grounded and practically useful when the learning rule matches product-level market stability. --- ### Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining Authors: Bo Peng, YuanJie Lyu, PengGang Qin, Tong Xu Published: 2026-05-29 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.31069v1 Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has primarily focused on text or short-video scenarios, long-video event prediction, characterized by vast multimodal context and more complex narratives, remains underexplored. Meanwhile, although recent Long-Video Language Models (LVLMs), built on Large Language Models (LLMs) and Vision-Language Models (VLMs), have shown promise in long-video question answering and summarization, they struggle to generalize to event prediction, as they can neither precisely extract event-related details nor perform fine-grained analysis of event development. To address this gap, we propose VISTA, a multi-level event semantics mining framework for long-video event prediction. Initially, VISTA applies a character-centric visual prompt to precisely extract event-related visual details, enhancing detail-level semantics; subsequently, it employs a knowledge-enhanced iterative retrieval strategy, guiding the LLM to progressively construct logically coherent event chains, thereby improving event-level narratives; ultimately, VISTA adopts a human-like propose-then-retrieve strategy to generate diverse future-oriented proposals and integrate multi-level clues, producing robust and accurate predictions. Extensive experiments on real-world datasets validate the effectiveness of VISTA for long-video event prediction. --- ### HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning Authors: Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh, Biplab Banerjee Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31068v1 We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The proposed framework extends JEPA-style masked latent prediction to paired Sentinel-1 and Sentinel-2 imagery by predicting masked target representations from visible context regions while aligning heterogeneous modality features in a shared embedding space. To improve representation quality, HQ-JEPA combines four complementary objectives: latent token prediction, cross-modal token alignment, SIGReg-based Gaussian regularization in the fused latent space, and a differentiable SWAP-test-based Fidelity Quantum Similarity (FQS) loss. Unlike pixel reconstruction methods, HQ-JEPA learns semantic representations directly in latent space and uses quantum state-overlap-based similarity as an additional regularization signal. We evaluate the pretrained encoder on GeoBench classification and segmentation tasks under linear probing and fine-tuning settings. Results show that HQ-JEPA achieves competitive and often superior performance over strong self-supervised and remote sensing foundation-model baselines, demonstrating the benefit of integrating predictive self-supervision, cross-modal geometric regularization, and quantum fidelity-based representation learning for remote sensing applications. --- ### DRIFT: Joint Channel Estimation and Prediction Towards Pilotless 6G Non-Terrestrial Networks Authors: Bruno De Filippo, Carla Amatetti, Alessandro Vanelli-Coralli Published: 2026-05-29 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.31065v2 Non-terrestrial networks (NTNs) are expected to play a pivotal role in sixth-generation (6G) systems by enabling ubiquitous connectivity and massive communication. In this context, channel prediction emerges as a key technique to improve the spectrum utilization efficiency by limiting the pilot overhead. However, many proposed predictors based on artificial intelligence (AI) are characterized by high inference complexity, posing challenges to onboard implementation. In this paper, we address the challenge of designing accurate yet computationally efficient channel prediction techniques tailored to low Earth orbit (LEO) NTNs, where strict power constraints limit model complexity, to enable spectral efficiency gains. We propose an iterative joint channel estimation and prediction framework in the context of 6G NTNs that significantly reduces pilot overhead by transmitting pilots only in the initial slot and relying on data-driven processing for subsequent slots. We introduce Data-driven Refinement and Iterative Forecast for wireless channel Tracking (DRIFT), a lightweight architecture that refines data-aided channel estimates and predicts future channel frequency responses with low computational cost and reduced error propagation. Two predictor variants based on convolutional and long short-term memory layers are investigated. Simulation results in an end-to-end simulation of an uplink LEO NTN scenario show that the proposed approach achieves up to 12% spectral efficiency gain compared to conventional pilot-based systems, with robustness to training-test mismatches and consistent performance across different channel models. Moreover, DRIFT requires fewer than 200k multiply-accumulate operations, making it suitable for on-board satellite implementation under stringent power constraints. --- ### DRIFT: Joint Channel Estimation and Prediction Towards Pilotless 6G Non-Terrestrial Networks Authors: Bruno De Filippo, Carla Amatetti, Alessandro Vanelli-Coralli Published: 2026-05-29 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.31065v1 Non-terrestrial networks (NTNs) are expected to play a pivotal role in sixth-generation (6G) systems by enabling ubiquitous connectivity and massive communication. In this context, channel prediction emerges as a key technique to improve the spectrum utilization efficiency by limiting the pilot overhead. However, many proposed predictors based on artificial intelligence (AI) are characterized by high inference complexity, posing challenges to onboard implementation. In this paper, we address the challenge of designing accurate yet computationally efficient channel prediction techniques tailored to low Earth orbit (LEO) NTNs, where strict power constraints limit model complexity, to enable spectral efficiency gains. We propose an iterative joint channel estimation and prediction framework in the context of 6G NTNs that significantly reduces pilot overhead by transmitting pilots only in the initial slot and relying on data-driven processing for subsequent slots. We introduce Data-driven Refinement and Iterative Forecast for wireless channel Tracking (DRIFT), a lightweight architecture that refines data-aided channel estimates and predicts future channel frequency responses with low computational cost and reduced error propagation. Two predictor variants based on convolutional and long short-term memory layers are investigated. Simulation results in an end-to-end simulation of an uplink LEO NTN scenario show that the proposed approach achieves up to 12% spectral efficiency gain compared to conventional pilot-based systems, with robustness to training-test mismatches and consistent performance across different channel models. Moreover, DRIFT requires fewer than 200k multiply-accumulate operations, making it suitable for on-board satellite implementation under stringent power constraints. --- ### Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA Authors: Hao Chen, Xing Tang, Qirui Liu, Weijie Shi, Shiwei Li, Fuyuan Lyu, Weihong Luo, Xiku Du, Xiuqiang He Published: 2026-05-29 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.31064v1 Large Language Models (LLMs) have significantly advanced online data services, particularly in the domain of financial question answering (FinQA). However, such systems remain susceptible to numerical reasoning hallucinations, which critically undermine reliability in high-stakes financial applications. Although retrieval-augmented generation (RAG) has been widely adopted to ground responses in external knowledge, it introduces three persistent challenges: noise sensitivity, calculation fragility, and an auditability crisis. Existing model-centric approaches, which primarily focus on optimizing either the retriever or generator in isolation, still struggle to address these issues in an integrated manner. In this work, we pioneer a data-centric paradigm and propose a novel framework, the Data-centric Reasoning Compiler (DCRC). The framework operates through three cohesive phases: (1) adversarial data construction, which synthesizes training examples with controlled noise to teach robustness; (2) multi-stage training that cultivates a Data-centric Structuring Agent (DSA) capable of explicit evidence auditing and program synthesis; and (3) a compile-and-execute inference process, where the DSA transforms user queries and retrieved documents into verifiable, executable reasoning programs. This data-driven framework ensures faithful numerical reasoning by design. We conduct extensive experiments on established offline benchmarks and further validate our framework through deployment in a real-world online financial QA system. --- ### Free energy Estimation on Any State Space Authors: Jiajun He, Zijing Ou, Francisco Vargas, Yingzhen Li, José Miguel Hernández-Lobato, Carles Domingo-Enrich, Yuanqi Du Published: 2026-05-29 Categories: stat.ML, cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2605.31063v1 Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimation, quasistatic integration, to finite-time averaging. Recent work (He and Du et al., 2025) learns neural transports to significantly accelerate the efficiency in the finite-time regime. In this paper, we generalize this framework to arbitrary state spaces. Building on this view, we develop a generalized neural transport learning approach for efficient estimation. Experiments validate the effectiveness and efficiency of the proposed method beyond continuous settings, extending to discrete and multimodal spaces as well as autoregressive settings. Beyond free energy estimation, we establish algebraic identities and reveal a group-theoretic structure linking infinitesimal time reversal and generalized Doob's $h$-transforms, showing that their compositions form a generalized dihedral group. --- ### AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering Authors: Yuxin Wang, Jiahao Lu, Qifeng Wu, Shicheng Fang, Chuanyuan Tan, Yining Zheng, Xuanjing Huang, Xipeng Qiu Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.31062v1 Large Language Models (LLMs) have achieved remarkable performance in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, this approach often leads to ``over-thinking,'' where models generate unnecessarily long reasoning traces for simple queries and incur avoidable inference cost. While recent work has explored adaptive reasoning, existing methods typically make a single query-level decision about whether to reason. This overlooks the dynamic nature of multi-step tasks, where the need for explicit reasoning varies across intermediate stages. To address this limitation, we introduce AdaptR1, a Reinforcement Learning (RL) based framework for adaptive interleaved thinking in multi-hop Question Answering (QA). Unlike previous approaches that require Supervised Fine-Tuning (SFT) for cold-start initialization, AdaptR1 uses a fully RL-based strategy with a quality-gated efficiency reward to dynamically allocate reasoning budgets at each step. Under the Graph-R1 setting, AdaptR1 reduces average think tokens by 69.71\%, with a 90.35\% reduction on HotpotQA, while maintaining performance comparable to or better than standard baselines. Furthermore, our analysis reveals that overthinking in multi-hop reasoning is not uniformly distributed but occurs predominantly during the initial planning stages, highlighting the effectiveness of step-wise adaptive budget allocation. --- ### STEP: Learning STructured Embeddings for Progressive Time Series Authors: Lucas Thil, Jesse Read, Rim Kaddah, Guillaume Doquet Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.31061v1 We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised contrastive objective to learn a low-dimensional latent space whose geometry is itself the interpretation: each observation becomes a point on a manifold anchored between two fixed orthogonal prototype vectors, and a trajectory becomes a path across that manifold. From this structure we read a latent compass, the polar coordinates (θ, r) of the latent vector, in which θ tracks the progression of the underlying state (e.g., from healthy to failed) and r identifies the active mode (e.g., the operating condition), without any proxy labels. We evaluate the approach against the state of the art on diverse domains, including industrial degradation, robotic tasks, and neural activity, validating three key capabilities: (1) end-state prediction, (2) multi-step forecasting, and (3) interpretable phase separation. Our method matches or improves over black-box counterparts on all of these while providing transparency about the underlying mechanisms. A simple linear regressor on top of the latent compass coordinates is competitive with deep architectures, direct quantitative evidence that the underlying state is encoded in a geometrically accessible form. --- ### Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination Authors: Jiasheng Zheng, Boxi Cao, Boxi Yu, Yuzhong Zhang, Jialun Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun Published: 2026-05-29 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2605.31058v1 Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However, the scalability of RLVR is severely constrained by the scarcity of sufficiently challenging verifiable code tasks that target near the model's edge of competence. Prior studies often rely on heuristic seed expansions for data synthesis, which severely limits both novelty and difficulty. Consequently, the training value of such data fails to scale proportionally with the size of its synthesis. To this end, we propose Atomic Decomposition and Recombination (ADR), a novel framework that generates verifiable code tasks via decomposition into atomic elements and controlled recombination, thereby enabling the generation of genuinely novel and challenging verifiable code tasks. Experiments and analysis demonstrate that ADR achieves superior originality, difficulty, diversity, and test quality over existing baselines, and consistently delivers greater improvements in code ability across RLVR in diverse downstream domains, including algorithmic programming, tool usage, and data science. Our work sheds light on a new paradigm for novel code task synthesis and scalable RLVR training. --- ### LVSA: Training-Free Sparse Attention for Long Video Diffusion Authors: Gael Glorian, Ioannis Lamprou, Zhen Zhang, Yujie Yuan, Hongsheng Liu Published: 2026-05-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.31057v1 Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and beyond the training horizon the model converges to near-static output, that is, "frozen" repetitive video. State of the art approaches are either too costly, e.g., they require retraining, or fail to satisfy both performance and quality objectives in a scalable manner. To this end, we introduce Long Video Sparse Attention (LVSA), a training-free model-agnostic block-sparse attention for video diffusion transformers that combines a structured window pattern with rotating global anchors, thus removing the fixed-grid bias which causes long-range temporal artifacts. LVSA, combined with a FlashInfer kernel, reduces compute up to 3.17x on Wan 2.1 1.3B at a 6x horizon, 2.98x on Wan 2.1 14B at a 6x horizon, and 3.33x on HunyuanVideo 1.5 at a 1.5x horizon, compared to dense attention. Beyond reducing compute, LVSA enables HunyuanVideo 1.5 generation at a 2x horizon, which is otherwise out-of-memory on a single GPU. Moreover, LVSA provides speedups up to 2.41x compared to RIFLEx and 3.27x compared to UltraViCo on Wan 2.1 1.3B. To demonstrate applicability across diverse platforms, we apply LVSA on NPUs and achieve speedups up to 2.71x on Wan 2.2 A14B and 3.24x on Wan 2.1 1.3B compared to dense attention. To evaluate quality in a fair way, we introduce VQeval, a tool properly scoring loopy video failures, which instead are rewarded in state of the art evaluators like VBench-Long. LVSA is quality-neutral for generation at training horizon length and quality-positive at extended lengths. --- ### How Much Do LLMs Know About Chinese Zero Pronouns? Authors: Yifei Li, Guanyi Chen, Tingting He Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.31056v1 Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and have long posed a challenge for natural language processing systems. Although Large Language Models (LLMs) perform well on many Chinese language tasks, their ability to process ZPs remains poorly understood. We conduct a systematic investigation of LLMs' handling of Chinese ZPs through a sequence of linguistically motivated tasks, including identification, referentiality classification, referential type classification, resolution, and translation. A diverse set of LLMs is evaluated across all tasks. Our results show that Chinese ZPs remain highly challenging for current LLMs, particularly for upstream tasks such as identification and referentiality classification. Performance on downstream tasks, such as ZP translation, is also consistently low: even state-of-the-art reasoning-oriented LLMs correctly translate fewer than half of Chinese ZPs into English. --- ### AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing Authors: Chih-Heng Chang, Keng-Seng Ho, Chih-Yu Tsai, Kuan-Lin Chen, Yi-Hsuan Yang, Jian-Jiun Ding Published: 2026-05-29 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2605.31053v1 Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challenged by a semantic-structural entanglement: steering methods often degrade structure to achieve editing performance, while structural adaptors suppress semantic responsiveness. We propose AnchorSteer, a framework that disentangles this tension by coupling structural anchoring with self-discovered semantic steering. The proposed approach probes internal representations to extract interpretable, label-free concept vectors via a self-supervised reconstruction objective, isolating attributes without curated data. During editing, these portable, plug-and-play concept vectors are injected into diffusion hidden manifolds while a structural adaptor enforces consistency. Variants for unconditioned and conditioned injections are provided to balance robustness and semantic strength. Experiments on ZoME-Bench and subjective tests show that the proposed framework outperforms both steering-only and anchoring-only baselines, enabling significant semantic transformations with high-fidelity structural preservation. --- ### Linear Ordering Problem: Time for a Change Authors: Fabrizio Fagiolo, Marco Baioletti, Valentino Santucci Published: 2026-05-29 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2605.31051v2 The Linear Ordering Problem (LOP) is a fundamental combinatorial optimization problem with important applications in areas such as economics, social choice, and machine learning. Its most prominent use is the triangulation of economic input-output tables, which helps identify critical industries in an economy. Most existing algorithms have been evaluated on benchmarks derived from outdated macroeconomic data, which no longer reflect the structure of contemporary economies. Furthermore, LOP instances often exhibit many distinct global optima that can differ substantially from one another, creating challenges for applications that rely on a single solution. To address these limitations, we introduce a novel benchmark suite derived from up-to-date real-world economic data and an algorithmic scheme that leverages state-of-the-art LOP metaheuristics to generate diverse sets of high-quality solutions, together with metrics for assessing both quality and diversity. Experiments were conducted to report results on the proposed benchmark suite under both the traditional single-solution setting and the newly introduced multi-solution scenario --- ### Best-Arm Identification-Based Trust Region Selection for Bayesian Optimization on Multimodal Functions Authors: Nobuo Namura, Sho Takemori Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31050v1 Gaussian process-based Bayesian optimization (BO) is a popular approach for expensive black-box optimization, but its performance often degrades on complex multimodal or high-dimensional problems. Trust region-based BO mitigates this issue by focusing on local regions, and recent studies suggest that selecting an effective region can be formulated as a multi-armed bandit problem. We propose a trajectory-aware framework that integrates best-arm identification (BAI) with trust region-based BO to efficiently solve multimodal optimization problems. Our method extrapolates the optimization trajectories of multiple locally initialized optimizers to predict their final performance and progressively eliminates suboptimal candidates via BAI. We theoretically show that the proposed BAI-guided BO converges faster to the global optimum than conventional BO under mild assumptions, and demonstrate its effectiveness through extensive experiments on synthetic and real-world benchmarks. --- ### Learning to Solve and Optimize by Evolving Code Authors: Veronika Semmelrock, Benedetta Strizzolo, Francesco Zuccato, Gerhard Friedrich, Patrick Rodler, Konstantin Schekotihin Published: 2026-05-29 Categories: cs.LG, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2605.31049v1 Combinatorial and optimization problems are fundamental to many industrial AI applications. Solving large-scale real-world instances of such problems typically requires careful problem formalization, specialized solvers, and expert-designed heuristics. Thus, experts need to specify not only what solutions are, but also how they are derived. By introducing the tool CHECKMATE, we show that algorithm generation via code evolution represents a paradigm shift by eliminating the need to formulate the how. CHECKMATE solely relies on the what. Specifically, a formal specification ensures solutions' correctness and enables systematic performance evaluation of the generated programs, while a natural language description guides the evolutionary process. The effectiveness of our method is demonstrated on selected problems from two industrial domains: configuration and scheduling. In all cases, the evolved algorithms consistently outperform state-of-the-art solvers. This underscores the potential of formal methods in guiding code evolution for automatically solving complex real-world problems. --- ### Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling Authors: Shipeng Liu, Liang Zhao, Dengfeng Chen, Weihua Zhang Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31048v1 Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, and auxiliary enhancement branches. Although effective, this raises whether stronger generic feature mixing is the most suitable direction for crack segmentation. We instead formulate crack segmentation as sparse structural recovery. Cracks have limited category-level semantics but strong morphological regularities, being thin, sparse, anisotropic, locally fragmented, and easily confused with textures or shadows. Thus, the key bottleneck lies in preserving weak structural evidence, recovering directional continuity, and suppressing background coupling. We propose RIFT, a compact family of morphology-aligned crack segmentation models. Rather than compressing a complex generic architecture, RIFT is simple by design, preserving local evidence, aggregating cooperative directional continuity, and restoring crack structures through lightweight multi-scale fusion. Experiments on four public benchmarks show that RIFT achieves the best or tied-best results across the 16 main metrics against reproduced representative baselines. RIFT-B gives the strongest overall accuracy, while RIFT-T provides the best deployment efficiency with only 0.47M parameters and high inference speed. Topology-aware evaluation, ablations, transfer experiments, and visualizations further verify that task-aligned simplicity can match or surpass complex hybrid architectures when its inductive bias fits crack morphology. Code: https://github.com/xauat-liushipeng/RIFT --- ### The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems Authors: Tobias Lademann, Théo Vincent, Jan Peters, Matthias Weigold Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31044v2 Reinforcement learning has shown promising results for optimizing the control of industrial energy systems, yet most existing studies remain limited to the application in simulation environments. We investigate the challenges of deploying reinforcement learning in a real-world industrial energy system, considering a thermal heating network as a use case. We formulate the task as a Markov Decision Process and systematically analyze the associated challenges along the structure of the formal description, including partial observability, action space design, reward design, and the simulation-to-reality gap. The challenges are grounded in an existing real-world deployment, where reinforcement learning achieves operational stability but shows a significant performance gap compared to simulation. --- ### The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems Authors: Tobias Lademann, Théo Vincent, Jan Peters, Matthias Weigold Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31044v1 Reinforcement learning has shown promising results for optimizing the control of industrial energy systems, yet most existing studies remain limited to the application in simulation environments. We investigate the challenges of deploying reinforcement learning in a real-world industrial energy system, considering a thermal heating network as a use case. We formulate the task as a Markov Decision Process and systematically analyze the associated challenges along the structure of the formal description, including partial observability, action space design, reward design, and the simulation-to-reality gap. The challenges are grounded in an existing real-world deployment, where reinforcement learning achieves operational stability but shows a significant performance gap compared to simulation. --- ### Routing on the Stiefel Manifold: When Does Adaptive Subspace Selection Help for Cross-Domain EEG Decoding? Authors: Isabella Costa Maia, Pedro L. C. Rodrigues, Salem Said, Marco Congedo Published: 2026-05-29 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.31043v1 Cross-domain EEG decoding remains challenging despite advances in Riemannian deep learning: covariance matrices from different subjects occupy systematically distinct regions of the SPD manifold, yet existing domain adaptation methods either require target-domain calibration data or learn subject-specific components that cannot generalise across domains. We propose dynamic Stiefel routing: a pool of $K$ expert projection filters on the Stiefel manifold, each specialised for a different region of the SPD manifold, with each input covariance routed to the most appropriate filter via cross-attention, adapting the subspace projection per sample. A central finding is that this approach, implemented naively, provably collapses to ensemble averaging: when routing weights are uniform, the adaptive filter reduces exactly to an equal-contribution combination of experts, indistinguishable from a single fixed filter. Three structural properties break this degeneracy: a symmetric anchor $W_{\mathrm{base}} \in \mathrm{St}(n,k)$ that removes proximity bias among experts; a frozen domain-discriminative query encoder that decouples routing from task optimisation; and a decoupled key alignment loss that trains expert keys toward stable domain attractors. Together they produce the first genuinely committed and domain-structured routing on SPD manifolds, with consistent gains across three datasets: balanced accuracy improves from $0.773\to 0.823$, $0.757\to 0.809$, and $0.801\to 0.839$, with the alignment strategy determined automatically by a single data-driven rule and no dataset-specific hyperparameter search. --- ### From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors Authors: Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu, Yiruo Cheng, Xiaoxi Li, Ji-Rong Wen Published: 2026-05-29 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.31042v1 LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write files, call tools, and reuse workspace state across sessions. While such capabilities enhance utility, they also expose a new attack surface for attackers. Attackers can embed a prompt injection within a file or tool output. Agents may read this hidden instruction, store it, and execute it later. In this multi-step trojan attack paradigm, no individual step appears malicious on its own, but these steps can collectively turn untrusted text into persistent control content. However, existing defenses often inspect each step in isolation. As a result, they can block a clear harmful action, but fail to detect the earlier write operation that plants the backdoor. To reveal this threat, we introduce ClawTrojan, a benchmark designed to identify multi-step trojan attacks in local agentic harnesses. In an OpenClaw-style simulated workspace with GPT-5.4, ClawTrojan reaches a 95.5% attack success rate (ASR), while existing single-turn prompt-injection attacks produce near-zero ASR on the same model. To address this threat, we propose DASGuard, which scans control-like text in sensitive local files, traces its origin, and removes control content that does not originate from a trusted source. Our results show that DASGuard achieves strong dynamic defense by combining runtime attack blocking with sanitized commits to the workspace. --- ### Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior? Authors: Jingtao He, Hongliang Lu, Xiaoyun Qiu, Yixuan Wang, Xinhu Zheng Published: 2026-05-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.31041v1 Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning. However, how current VLA-based driving behavior is grounded in visual information remains poorly understood. Existing evaluation protocols mainly focus on aggregate performance metrics, lacking structured and practical diagnostics to quantify visual-behavior dependency. In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in VLA-based driving models systematically. The framework organizes controlled visual perturbations along three complementary dimensions: channellevel degradation, information-level disruption, and structurelevel modification. We apply it to VLA-based driving systems and evaluate behavioral responses under both open-loop trajectory prediction and interactive closed-loop safety evaluation. Experimental results reveal evaluation-dependent dependency patterns and uneven visual grounding across abstraction levels. These findings call for more structured analyses and principled design of VLA driving models to better understand how visual information shapes behavior and develop safer, more robust systems. --- ### UniRTL: Unifying Code and Graph for Robust RTL Representation Learning Authors: Yi Liu, Hongji Zhang, Lei Chen, Mingxuan Yuan, Qiang Xu Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31040v1 Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approaches, however, typically rely on a single data modality, either the RTL code or its associated graph-based representation, limiting the expressiveness and generalization ability of the learned representations. For RTL, the control data flow graph (CDFG) offers a comprehensive structural representation that preserves complete information, while the code modality explicitly encodes semantic and functional information. We argue that integrating these complementary modalities is essential for a thorough understanding of RTL designs. To this end, we propose UniRTL, a multimodal pretraining framework that learns unified RTL representations by jointly leveraging code and CDFG. UniRTL achieves fine-grained alignment between code and graph through mutual masked modeling and employs a hierarchical training strategy that incorporates a pretrained graph-aware tokenizer and staged alignment of text (i.e., functional summary) and code prior to graph integration. We evaluate UniRTL on two downstream tasks, performance prediction and code retrieval, under multiple settings. Experimental results show that UniRTL consistently outperforms prior methods, establishing it as a more robust and powerful foundation for advancing hardware design automation. --- ### GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration Authors: Xiangtao Kong, Jixin Zhao, Lingchen Sun, Rongyuan Wu, Lei Zhang Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31039v2 Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models. --- ### Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes? Authors: Ashwinkumar Badanidiyuru Published: 2026-05-29 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2605.31036v1 Online advertising platforms rely on machine learning models to predict click-through rates (pCTR) and conversion rates (pCVR) for auction mechanisms. We introduce a novel framework to study the interaction between recommender system model quality, auction format, and autobidder behavior. We formalize when model improvements -- defined via a refinement relation inspired by filtrations in probability theory -- lead to improvements in platform-level Evaluation Criteria Metrics (ECM) such as revenue, welfare, or liquid welfare. Our main contributions are: (1) a formal definition of model improvement based on cluster refinement, and (2) a systematic characterization of ECM monotonicity across different combinations of bidder types (tCPA, max-CPA), auction formats (first-price, second-price, VCG), and budget constraints. We show that first-price auctions with uniform bidding guarantee revenue monotonicity for tCPA bidders without budgets (via Jensen's inequality), while second-price auctions and budget constraints can break this property. We provide full numerical constructions for the non-monotonicity results. Our findings have practical implications for advertising platforms seeking to align model improvements with business outcomes. --- ### Annealed Softmax Greedy in Many-Armed Bayesian Bandits Authors: William Overman, Mohsen Bayati Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.31034v3 Reinforcement learning with verifiable rewards and group-based policy optimization methods update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward. These updates, unline the exploration mechanism in Thompson sampling and UCB, do not include explicit mechanisms that track epistemic uncertainty. This paper studies a stylized explanation for why such uncertainty-agnostic updates can nevertheless be effective. We analyze an annealed softmax policy that selects actions according to a softmax of empirical mean rewards in a many-armed Bayesian Bernoulli bandit. Under a linear upper-tail condition on the prior, which implies an abundance of near-optimal arms, we prove that annealed softmax greedy achieves Bayes regret $\tilde{O}(m + T/m)$, and in particular $\tilde{O}(\sqrt{T})$ when the number of arms scales as $m = Θ(\sqrt{T})$. This is the near-optimal Bayes regret rate in this regime, attained also by empirical-mean greedy. Under the upper-tail condition, many arms keep empirical means near the optimum throughout learning, so the probability that softmax places away from the empirical best falls mostly on other near-optimal arms. By contrast, with a small number of arms, the same kind of softmax policy can suffer linear regret (Cesa-Bianchi et al., 2017). The result also provides a structural analogy to RLVR, where a base policy with a non-negligible probability of producing a correct completion plays the role of the tail condition. Simulations support the theory and motivate prior-anchored variants of greedy and annealed softmax that score arms by the Beta posterior mean and skip the forced initialization; with an arm-specific prior, accurate or noisy, these variants outperform baselines, including Thompson Sampling, when the number of arms is large. --- ### Annealed Softmax Greedy in Many-Armed Bayesian Bandits Authors: William Overman, Mohsen Bayati Published: 2026-05-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.31034v1 Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward, regularized by a KL penalty toward a reference policy. These updates do not include explicit mechanisms that track epistemic uncertainty. This paper studies a stylized explanation for why such uncertainty-agnostic updates can nevertheless be effective. We analyze an annealed softmax (Boltzmann) policy that selects actions according to a softmax of empirical mean rewards in a many-armed Bayesian Bernoulli bandit. Under a linear upper-tail condition on the prior (the $β=1$ case of $β$-regularity), which implies an abundance of near-optimal arms, we prove that annealed softmax greedy achieves Bayes regret $\tilde{O}(m + T/m)$, and in particular $\tilde{O}(\sqrt{T})$ when the number of arms scales as $m = Θ(\sqrt{T})$. This is the near-optimal Bayes regret rate in this regime, attained also by empirical-mean greedy. Under $β$-regularity, many arms maintain empirical means close to the optimum throughout learning, so when softmax samples an arm other than the empirically best, that arm tends to be another near-optimal one rather than a clearly inferior one. By contrast, with a small number of arms, the same kind of softmax policy can suffer linear regret. The result also provides a structural analogy to RLVR, where a base policy with a non-negligible probability of producing a correct completion plays the role of $β$-regularity. --- ### SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation Authors: Weijia Dou, Hui Li, Jiahao Cui, Lei Zhou, Jingdong Wang, Siyu Zhu Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31033v1 Streaming video generation models typically rely on temporal-centric memory, which organizes historical context as raw frames, chunk segments, or unclustered tokens. This organization frequently leads to identity drift and semantic inconsistency when entities exit the frame or during interactive prompt transitions. To address these limitations, we propose SlotMemory, an object-centric Key-Value memory mechanism for streaming video diffusion. Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold into discrete, reusable semantic slots. By utilizing these slots as routing addresses to index and store high-fidelity key-value tokens, we enable entity-level persistence and prompt-aware retrieval across long horizons. Evaluated on 60-second interactive narratives using the Wan2.1-T2V-1.3B backbone, SlotMemory achieves a state-of-the-art quality score of 81.61 and a 22.8 percent relative improvement in dynamic consistency over the strongest existing streaming baseline. Our results demonstrate that structured semantic representation, rather than raw temporal capacity, is the essential primitive for persistent long-form video synthesis. Our codes and checkpoints are available at https://tj12323.github.io/SlotMemory/. --- ### GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning Authors: Saku Peltonen, August Bøgh Rønberg, Andreas Plesner, Roger Wattenhofer Published: 2026-05-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.31031v1 Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce GraphARC, a benchmark for abstract reasoning on graph-structured data. GraphARC generalizes the few-shot transformation learning paradigm of the Abstraction and Reasoning Corpus (ARC). Each task requires inferring a transformation rule from a few input-output pairs and applying it to a new test graph, covering local, global, and hierarchical graph transformations. Unlike grid-based ARC, GraphARC instances can be generated at scale across diverse graph families and sizes, enabling systematic evaluation of generalization abilities. We evaluate state-of-the-art language models on GraphARC and observe clear limitations. Models can answer questions about graph properties but often fail to solve the full graph transformation task, revealing a comprehension-execution gap. Performance further degrades on larger instances, exposing scaling barriers. More broadly, by combining aspects of node classification, link prediction, and graph generation within a single framework, GraphARC provides a promising testbed for future graph foundation models. --- ### PEEK: Picking Essential frames via Efficient Knowledge distillation Authors: Killian Steunou, Anas Filali Razzouki, Khalil Guetari, Mounîm A. El-Yacoubi, Yannis Tevissen Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31029v2 Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on uniform sampling, which is computationally cheap but agnostic to visual content. Adaptive frame sampling selects the most informative frames from a video, but existing methods remain computationally expensive. We introduce PEEK, an efficient dynamic frame sampling method that distills caption-conditioned frame relevance rankings from a stronger teacher model into a lightweight temporal model that operates only on visual content. On ActivityNet Captions and MSR-VTT, PEEK outperforms state-of-the-art methods across all evaluated downstream vision language models, obtaining the best CIDEr for most frame budgets, especially when only one or two frames are selected, winning 14 out of 16 configurations on ActivityNet Captions. Zero-shot on MSR-VTT, it transfers best at low frame budgets, while results at four and eight frames are more mixed as temporal coverage and visual diversity become increasingly competitive. Compared with recent adaptive baselines, PEEK is both more accurate in the low-budget regime and more efficient: it adds only $5.2\%$ to the captioning time, compared with $65.4\%$ for CSTA and $211.9\%$ for MaxInfo. We release our code and pre-trained checkpoint at https://github.com/momentslab/peek. --- ### PEEK: Picking Essential frames via Efficient Knowledge distillation Authors: Killian Steunou, Anas Filali Razzouki, Khalil Guetari, Mounîm A. El-Yacoubi, Yannis Tevissen Published: 2026-05-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.31029v1 Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on uniform sampling, which is computationally cheap but agnostic to visual content. Adaptive frame sampling has recently emerged as a promising approach for selecting the most informative frames from a video; however, existing methods remain computationally expensive. We introduce PEEK, an efficient dynamic frame sampling method that distills caption-conditioned frame relevance rankings from a stronger teacher model into a lightweight temporal model that operates only on visual content. We find that, overall, on ActivityNet Captions and MSR-VTT, our method outperforms state-of-the-art methods across all evaluated downstream vision language models, especially when only one or two frames are selected for captioning, obtaining the best CIDEr for most frame budgets. On ActivityNet Captions, PEEK is particularly strong, winning 14 out of 16 configurations. Zero-shot evaluation on MSR-VTT shows that our model transfers best at low frame budgets, while results at four and eight frames are more mixed as temporal coverage and visual diversity become increasingly competitive. Compared with recent adaptive baselines, PEEK is both more accurate in the low-budget regime and more efficient: it adds only $5.2\%$ to the captioning time, compared with $65.4\%$ for CSTA and $211.9\%$ for MaxInfo. We release our code and pre-trained checkpoint at https://github.com/momentslab/peek. --- ### Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs Authors: Qihong Yang, Qiaolin He Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31027v4 Solving high-frequency partial differential equations (PDEs) with neural networks is notoriously difficult due to the spectral bias of conventional architectures. We propose the Multi-Scale Separable Fourier Neural Network (MS-SFNN), a framework designed to overcome this limitation by explicitly encoding multi-scale Fourier features within a separable representation. The network factorizes the solution into $d$ single-coordinate subnetworks with fixed, randomly initialized weights; these subnetworks are combined via element-wise products to form a rich set of basis functions. This separable construction scales linearly with the problem dimension, thus inherently alleviating the curse of dimensionality. Crucially, each subnetwork is equipped with trainable scaling factors coupled with cosine activations, providing an adaptive mechanism for multi-scale frequency selection that endows the model with strong spectral approximation capability. The PDE solution is expressed as a linear combination of these learned basis functions, and the combination coefficients are determined by solving a large-scale least-squares system. To resolve the memory bottleneck in high-frequency or three-dimensional settings, we replace automatic differentiation (AD) with analytical derivatives of the basis functions and use a memory-efficient batched QR decomposition for solving the least-squares systems efficiently. Extensive numerical experiments demonstrate that MS-SFNN achieves superior accuracy and substantially outperforms state-of-the-art methods, including Physics-Informed Neural Network (PINN) and the Separated-Variable Spectral Neural Network (SV-SNN). --- ### TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning Authors: Xiaosong Han, Ke Chen, Xindi Dai, Di Liang, Minlong Peng, Wei Pang, Fausto Giunchiglia, Xiaoyue Feng, Yonghao Liu, Renchu Guan Published: 2026-05-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.31025v1 In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. However, indiscriminately mixing tasks can dilute task specialization, while sequential fine-tuning (full-parameter or low rank adaptation) often causes catastrophic forgetting due to destructive overwriting. Replay-based continual tuning and maintaining separate task-specific adapters can mitigate forgetting, but introduce additional compute, storage, and management overhead. Recognizing the redundancy of LLM parameters for any single task, we reframe continual task adaptation as task-specific parameter discovery via adaptation-aware probing: a short warm-start probe exposes a task's adaptation trace, enabling us to identify and isolate the small subset of parameters essential for each task to mitigate catastrophic forgetting. Building on this view, we introduce TRACE, a novel approach for discovering Task-specific paRameters via Adaptation-aware probing for Continual finE-tuning. We perform a short warm-start fine-tune to derive task-specific core parameters by comparing the warm-started and pre-trained models. Core parameters are identified via two strategies: importance scoring (L$_2$ norm and Fisher Information) and specificity analysis (cosine similarity of parameter updates). In continual fine-tuning settings, only the active task's core parameters are updated while others remain frozen, preserving prior knowledge. We conduct extensive experiments across multiple standard benchmarks to demonstrate the superior performance of our proposed method. Additionally, we validate the generalization of our method through a cross-model and scale transferability study, demonstrating a "small-to-large" paradigm that guides the fine-tuning of large-scale models under resource constraints. --- ### HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster Authors: Mohamad A. Hady, Muhammad Anwar Masum, Siyi Hu, Mahardhika Pratama, Jimmy Cao, Ryszard Kowalczyk Published: 2026-05-29 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.31023v1 This work addresses the problem of autonomous resource management in heterogeneous satellite cluster conducting Earth Observation (EO) missions including optical and Synthetic Aperture Radar (SAR) satellites. In autonomous operation mode, satellites are equipped with intelligent capabilities enabling real-time decision-making based on the latest conditions, while requiring minimal interaction with ground operators. Traditional scheduling approaches typically rely on mathematical models to represent satellite mission and resource management. Then, this problem is solved by using optimization algorithms. However, such solutions become less effective when the underlying models are not available, over complex, and inaccurate due to dynamic changes and uncertainties inherent in the space mission environment. A promising alternative is to reformulate the problem as a sequential decision-making process and apply model-free reinforcement learning techniques to enable adaptive and real-time resource management. To this end, we propose a novel transformer-based architecture tailored for heterogeneous satellite cluster autonomous EO Mission with relational observations-actions tokenization and differential attention mechanism. Our experimental results demonstrate significant performance improvements compared to the available baselines. Moreover, the proposed architecture exhibits strong adaptability and transferability with respect to varying numbers of satellite clusters. --- ### Augmented Lagrangian Predictive Coding Authors: Jeffrey Seely, Julian Gould Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31022v1 Predictive coding (PC) is a local-learning alternative to backpropagation (BP), training deep networks via local energy-minimization dynamics rather than a global backward pass. We introduce Augmented Lagrangian Predictive Coding (PC-ALM), which maintains PC's inference budget but aligns each weight update toward BP by accumulating per-layer constraint errors into a layer-local Lagrange multiplier. In linear PC networks, PC-ALM converges to an equilibrium with exact BP gradients distributed across the network via only layer-local updates. We analyze PC-ALM in nonlinear PC networks up to depth 128 and show that it matches BP performance across all width-depth regimes, notably in deep narrow networks where PC underperforms. PC-ALM introduces recurrent dynamics in each layer's activations. Compared to PC's heat flow on a scalar energy, PC-ALM dynamics are driven by dual ascent on the augmented Lagrangian. We observe "ballistic" credit propagation across very deep networks, with credit signals evenly distributed across layers, compared to PC's slow, diffusive credit propagation. Beyond the algorithm itself, the augmented Lagrangian framework offers a generalization of PC, and may yield insights into how distributed systems could compute and propagate BP-like credit signals through purely local dynamics. --- ### A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI Authors: Atahan Karagoz Published: 2026-05-29 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.31021v1 Current alignment paradigms for generative artificial intelligence rely predominantly on monolithic benchmarking frameworks that reduce the plurality of human judgment to aggregated statistical baselines, thereby obscuring cultural, demographic, and contextual variability in evaluation. We introduce a state-space constrained emulation framework for AI evaluation that replaces singular assessment functions with a structured manifold of synthetic cognitive profiles representing diverse human perspectives. We show that modern generative architectures can instantiate and maintain these evaluative personas with high consistency, enabling a form of pluralistic, perspective-dependent benchmarking that more closely reflects real-world consensus variability. However, we further analyze the stability of these simulated evaluators under sequential inference and stochastic prompt perturbations, revealing systematic degradation in persona coherence that manifests as state-space drift and semantic inconsistency. These findings suggest that static alignment constraints are insufficient for sustaining robust evaluative behavior over time. Instead, we argue for the necessity of embedding dynamic, viability-driven regulatory mechanisms within generative systems to preserve coherent cognitive emulation. By framing persona-based evaluation as a structured dynamical system over latent representation manifolds, this study provides a foundation for more adaptive, human-aligned, and context-sensitive approaches to AI evaluation. --- ### An Efficient and Scalable Graph Condensation with Structure-Preserving Authors: Yulin Hu, Fuyan Ou, Ye Yuan Published: 2026-05-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.31016v1 Graph condensation (GC) is pivotal for enabling Graph Neural Networks (GNNs) deployment in resource-constrained scenarios by compressing large-scale graphs into compact synthetic counterparts. Existing GC methods commonly suffer from computational inefficiency due to coupled optimization as well as encountering poor generalization across GNN architectures. To address these challenges, this study proposes an Efficient and Scalable Graph Condensation with Structure-Preserving (SP-ESGC), which possesses a decoupled design that separates node condensation from graph structure generation. Specifically, it first employs heat kernel feature propagation to generate node representation via spectral graph theory-inspired diffusion. Further, a novel hybrid clustering strategy is designed to extracts discriminative intra-class centroids from the node representation. Finally, a pre-trained edge predictor infers transferable structural patterns from the original graph, ensuring accurate synthetic graph generation. Extensive experiments on real-world graph datasets demonstrate that the proposed SP-ESGC implementes a precise GC with significantly high computational efficiency. Moreover, SP-ESGC also generalizes well across diverse GNN architectures. ---