# Research Papers — 2026-05 · bundle page 68 of 326

> Full-text markdown of papers #3351–3400 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/68
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/67.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/69.md)

### Developing a Totally Unimodular Linear Program for Optimal Conformance Checking: When and Why It Complements A*

Authors: Izack Cohen
Published: 2026-05-26
Categories: cs.AI, math.OC
arXiv: https://arxiv.org/abs/2605.26938v1

Alignment-based conformance checking is the state-of-the-art approach for comparing observed process executions with normative process models. The standard exact solution relies on an A*-based heuristic search, which can exhibit exponential runtime in the presence of long traces or substantial deviations. This paper introduces a reformulation of alignment-based conformance checking as a totally unimodular linear program (LP) defined on the reachability graph of the synchronous product. By exploiting the underlying network-flow structure, the proposed formulation guarantees the existence of an integral optimal extreme-point solution through LP relaxation, thereby avoiding the combinatorial overhead associated with integer variables and branch-and-bound search. We conduct an extensive empirical evaluation on more than 2.1 million conformance checking instances derived from real-world and synthetic benchmark datasets. The results show that A* and the LP approach exhibit complementary performance characteristics: the former performs best on short, well-conforming traces, while the LP formulation provides substantial speedups for longer traces with deviations, precisely where conformance checking is most informative. Based on these findings, we derive simple algorithm-selection guidelines that combine both approaches, achieving average runtime savings of 38.6% with 96% selection accuracy compared to always using A*.

---

### Beyond Questions: Evaluating LLM's Knowledge Expression

Authors: Luca Giordano, Simon Razniewski
Published: 2026-05-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.26937v2

Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks typically rely on predefined questions (e.g., "What is the birth date of M.L. King?"), evaluating only knowledge that benchmark designers explicitly choose to query, a problematic availability bias. In this paper, we introduce open knowledge evaluation, a new paradigm for LLM knowledge expression benchmarking. Instead of asking narrow questions, it evaluates models on the knowledge they choose to surface in response to open-ended elicitation prompts (e.g., "Tell me everything you know about M.L. King"). This shifts the focus from predefined answer retrieval toward characterizing the knowledge models naturally express. We instantiate this paradigm with BeQu (Beyond Questions), a benchmark of 10,000 entities paired with reference corpora for statement verification. Using BeQu, we evaluate a broad range of language models and analyze the effects of reasoning effort, model scale, prompt format, and knowledge domain. Data and leaderboard are available on this work's GitHub repository and at the benchmark's website.

---

### Beyond Questions: Evaluating What Large Language Models (Actually) Know

Authors: Luca Giordano, Simon Razniewski
Published: 2026-05-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.26937v1

Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks typically rely on predefined questions (e.g., "What is the birth date of M.L. King?"), evaluating only knowledge that benchmark designers explicitly choose to query, a problematic availability bias. In this paper, we introduce open knowledge evaluation, a new paradigm for LLM knowledge benchmarking. Instead of asking narrow questions, it evaluates models on the knowledge they choose to surface in response to open-ended elicitation prompts (e.g., "Tell me everything you know about M.L. King"). This shifts the focus from predefined answer retrieval toward characterizing the knowledge models naturally express. We instantiate this paradigm with BeQu (Beyond Questions), a benchmark of 10,000 entities paired with reference corpora for statement verification. Using BeQu, we evaluate a broad range of language models and analyze the effects of reasoning effort, model scale, prompt format, and knowledge domain. Data and leaderboard are available on this work's GitHub repository and at the benchmark's website.

---

### DunbaaBERT: From Sacrifice to Semantics

Authors: Iffat Maab, Waleed Jamil, Raphael Schmitt
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26935v1

Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family of Urdu RoBERTa-base models trained from scratch with Byte-BPE vocabularies of 32k, 52k, and 96k tokens on a deduplicated 17GB Urdu corpus. We evaluate DunbaaBERT across intrinsic and downstream Urdu NLP benchmarks covering linguistic acceptability, news classification, offensive language detection, and sentiment analysis while analyzing vocabulary-size effects on performance and efficiency trade-offs. Across benchmarks, the DunbaaBERT variants achieve competitive performance against strong multilingual baselines while consistently maintaining favorable efficiency trade-offs. Interestingly, larger vocabularies do not consistently improve downstream effectiveness, with DunbaaBERT$_{\text{32k}}$ repeatedly providing the strongest overall efficiency profile. Overall, our results demonstrate that carefully curated Urdu-specific encoder models can remain highly competitive despite comparatively compact model and training scales. All models are released under the MIT license.

---

### Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks

Authors: Yihua Zhu, Qianying Liu, Fei Cheng, Jiaxin Wang, Akiko Aizawa, Sadao Kurohashi, Hidetoshi Shimodaira
Published: 2026-05-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.26934v2

Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth alone, and reward is concentrated on forward deductive state tracking. We instead characterize the reasoning space along two dimensions. Difficulty. Beyond reasoning depth, we study environment complexity, where models must identify the correct path amid distractors and interacting structures. Rewarded reasoning form. We consider four abilities core to real-world reasoning: deductive state tracking, abductive recovery of hidden events or facts, inductive rule induction, and analogical transfer. To disentangle these factors, we construct a synthetic knowledge-graph environment with controlled pre- and post-training distributions, where each instance varies along depth, complexity, and task family. Three findings emerge: joint depth-complexity coverage outperforms single-axis recipes; reasoning families respond non-uniformly, with abductive reasoning degrading outside the RL-covered region and task correlations clustering into deductive-abductive and inductive-analogy pairs; and uniform mixing outperforms staged curricula under a fixed budget. We also find that recent off-the-shelf models exhibit the same deductive-over-abductive asymmetry, suggesting that this gap is not merely an artifact of our controlled setup.

---

### Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks

Authors: Yihua Zhu, Qianying Liu, Fei Cheng, Jiaxin Wang, Akiko Aizawa, Sadao Kurohashi, Hidetoshi Shimodaira
Published: 2026-05-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.26934v1

Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth alone, and reward is concentrated on forward deductive state tracking. We instead characterize the reasoning space along two dimensions. Difficulty. Beyond reasoning depth, we study environment complexity, where models must identify the correct path amid distractors and interacting structures. Rewarded reasoning form. We consider four abilities core to real-world reasoning: deductive state tracking, abductive recovery of hidden events or facts, inductive rule induction, and analogical transfer. To disentangle these factors, we construct a synthetic knowledge-graph environment with controlled pre- and post-training distributions, where each instance varies along depth, complexity, and task family. Three findings emerge: joint depth-complexity coverage outperforms single-axis recipes; reasoning families respond non-uniformly, with abductive reasoning degrading outside the RL-covered region and task correlations clustering into deductive-abductive and inductive-analogy pairs; and uniform mixing outperforms staged curricula under a fixed budget. We also find that recent off-the-shelf models exhibit the same deductive-over-abductive asymmetry, suggesting that this gap is not merely an artifact of our controlled setup.

---

### Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking

Authors: Zhengbo Zhang, Zhigang Tu, Junsong Yuan, De Wen Soh, Bo Du
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26933v1

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understanding of semantic and visual structural information within video frames. Text-to-image diffusion models are well known for their ability to generate images that accurately reflect the semantics and structures described in the input prompt, demonstrating a strong grasp of visual semantics and structures. Building on this capability, we approach the unsupervised tracking from a new perspective by exploiting the rich semantic knowledge encoded in pretrained text-to-image diffusion models. To adapt the diffusion models, which are originally developed for image generation, to the tracking task, we reinterpret the models as a bridge between text and image modalities. This connection is realized through the cross-attention mechanism: when both text and an image are input into the models, they highlight the regions of the image that are semantically aligned with the text in the cross-attention maps. We therefore learn a prompt that represents the tracking target and activates its corresponding region in the cross-attention map for each frame, which enables object tracking with the diffusion model. Specifically, our method Diff-Tracking is composed of two main components: an initial prompt learner and an online prompt updater. The initial prompt learner generates a prompt that captures the target object in the first frame, allowing the diffusion model to identify the target. The online prompt updater refines the prompt based on motion information, enabling consistent tracking across video frames. We evaluate our approach on six challenging tracking datasets demonstrate the effectiveness of our approach.

---

### When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study

Authors: Jun Yan, Weiquan Huang, Jiankai Zuo, Yujian Mo, Xi Fang, Chengliang Wu, Zeming Wei
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26929v2

Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective is optimized. In practice, Stochastic Gradient Descent (SGD) optimizer remains the default optimization choice for AT, whereas adaptive optimizers often improve standard training but may yield inferior robustness. Recently, the Muon optimizer, which orthogonalizes matrix-valued updates via an approximate polar decomposition, has achieved notable success in large-scale training at a memory cost comparable to SGD. This raises a security-relevant question: \textit{can orthogonalized optimization improve AT under strong and heterogeneous threat models?} Focusing on this problem, we conduct a comprehensive theoretical and empirical study. Theoretically, we show that Muon imposes a spectral-norm stability ceiling on matrix updates, limiting uncontrolled spectral growth in the training dynamics without explicitly shrinking the learned weights. Empirically, across five architectures and three $\ell_p$ threat models ($\ell_\infty$, $\ell_1$, $\ell_2$) and their union, Muon is competitive with SGD on CNNs and substantially outperforms AdamW on both CNNs and ViTs. These results identify optimizer geometry as a security-relevant factor in adversarial training, while clarifying the empirical regimes in which orthogonalized updates are beneficial. Overall, our findings highlight optimizer design as a security-critical component of AT.

---

### From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework for Legal Indicator Computation

Authors: Youssef Al Mouatamid, Marie Bonnin, Jihad Zahir
Published: 2026-05-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.26926v1

Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the complexity, scale, and interpretive nature of legal language, as well as the variability in available document quality. Existing natural language processing techniques and generative models can assist in legal analysis, but often suffer from high risk of hallucinations and lack the interpretability and evidence grounding required for reliable indicator computation. This paper presents N2I-RAG (From Norms to Indicators), an agentic retrieval-augmented generation framework designed to automate the computation of legal indicators in a transparent and traceable way. We integrate adaptive retrieval, llm-based agents, and validation mechanisms in a modular pipeline, where each component performs a defined role in filtering, retrieving, and assessing evidence, and in producing binary legal outcomes linked to identifiable legal provisions. The framework emphasizes traceability by requiring explicit explanations of intermediate decisions and final indicator assignments. We evaluate N2I-RAG using an in-house constructed French marine environmental law corpus that includes both scanned and digital sources. Comparative experiments with multiple language model families demonstrate that the proposed approach consistently outperforms baseline systems, and generalizes well when tested on 2 different bans. The results indicate that agentic retrieval-augmented generation can bridge open-text legal language and standardized indicator computation, offering a foundation for transparent and scalable legal observatories.

---

### Adaptive Reinforcement Learning for Robust Open Quantum System Control: A Multi-Task Framework with Temporal Optimization

Authors: Haftu W. Fentaw, Steve Campbell, Simon Caton
Published: 2026-05-26
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.26925v1

We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific evolution time T and number of control pulse segments N. Experimental results across 51 Hamiltonian variations demonstrate that the multi-task SAC model is able to generate control pulses that can drive a system, under environment noise, from its initial state to its target state with high fidelities, establishing essential foundations for universal quantum control applicable to realistic noisy quantum devices. Through progressive expansion of the training Hamiltonian set, we investigate if a single multi-task model trained using a given number of sample Hamiltonians can successfully accomplish state-transfer tasks for Hamiltonians drawn from the same Hamiltonian space but not encountered during training. In addition, our Robustness Infidelity Measure (RIM) analysis reveals that SAC trained policies exhibit superior robustness to pulse amplitude perturbations and decoherence rate variations compared to GRAPE-optimized controls.

---

### Learning to Adapt SFT Data for Better Reasoning Generalization

Authors: Lisong Sun, Li Wang, Chen Zhang, Jinyang Wu, Kui Zhang, Tianhao Peng, Wenjun Wu
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26924v1

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages external data to provide dense supervision and enables efficient training. However, directly fine-tuning on expert data can hurt generalization when the data distribution is mismatched with the target model's own distribution. In this work, we propose Data Adaptation for Reasoning Tuning (DART), which formulates the use of a fixed, potentially distributionally misaligned SFT dataset as an optimization problem over demonstration transformations. DART trains a mapper model with reinforcement learning to convert original SFT data into model-adapted supervision that better matches the target model's distribution and learning preferences. The transformed data are then used for SFT, allowing the target model to better exploit external supervision. Experiments across multiple models and datasets show that DART improves generalization, achieves higher training efficiency than direct RL, and helps models surpass standard SFT. Our code is available at https://anonymous.4open.science/r/DART525E50D.

---

### Similarity-based representation factorization for revealing interpretable dimensions in representational data

Authors: Florian P. Mahner, Ka Chun Lam, Francisco Pereira, Martin N. Hebart
Published: 2026-05-26
Categories: cs.CV, q-bio.NC
arXiv: https://arxiv.org/abs/2605.26921v3

The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and using the dimensions underlying representations.

---

### Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates

Authors: Kei Takemura, Ryuta Matsuno, Keita Sakuma
Published: 2026-05-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.26919v2

Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off between robustness and agility. Specifically, to ensure dynamic regret bounds, they must restrict learning rates to small constants (e.g., $O(1)$). This restriction inevitably causes significant adaptation lag during abrupt changes. To resolve this, we propose a novel optimistic online mirror descent that utilizes safeguarded large learning rates up to $Θ(T)$, where $T$ is the number of rounds. Our key technical contribution is a post-hoc penalty mechanism that dynamically monitors unstable updates and excludes learning rates incurring excessive regret, eliminating the need for restrictive a priori constraints. We show that the cumulative penalty remains $O(\log T)$, allowing our algorithm to match near-optimal worst-case guarantees while achieving superior rates in benign cases. Empirical evaluations on three synthetic and eleven diverse real-world datasets demonstrate that our approach reduces the adaptation lag from hundreds of rounds to a few rounds, consistently outperforming tuning-free baselines.

---

### Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation

Authors: Unggi Lee, Hoyoung Ahn, Yoon Choi, Seonmin Eun, Jahyun Jeong, Seonmin Jin, Harmony Jung, Hye Jin Kim, Chaerin Lee, Hyunji Lee, Jeongjin Lee, Soohwan Lee et al.
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26918v1

Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generic safety, or video as a reasoning medium, and none assesses whether the outputs are educationally valid. In this work, we present EduVideoBench, the first balanced benchmark in the education domain, grounded in the Knowledge-Skills-Attitude (KSA) framework so that pedagogical adequacy and educational safety are evaluated jointly rather than as ad-hoc quality dimensions. Across five frontier VGMs, our results show substantial room for improvement across knowledge, skills, and attitude before they are classroom-ready. We complement this with a qualitative analysis of expert comments, finding that educational validity is multi-component, where a single misaligned element such as pacing, legibility, or notation can invalidate an otherwise correct video. We hope EduVideoBench will guide the development of VGMs that are pedagogically grounded and safe for the classroom.

---

### I2PRef: Image-Driven Point Completion with Iterative Refinement

Authors: Azhar Hussian, Marina Ritthaler, André Kaup, Vasileios Belagiannis
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26914v2

We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, with no need for 3D inputs. Additionally, we introduce a transformer-based Point-to-Point (P2P) refinement module that uses self- and cross-attention between point tokens and image features to iteratively refine the coarse I2P output. The I2P module enables the image encoder to learn rich geometric representations, while the P2P module progressively recovers fine-grained details. Unlike existing multimodal methods that rely on auxiliary losses or fusion modules, our explicit I2P task provides a strong, geometry-aware prior based on images alone. Extensive experiments on ShapeNet-ViPC demonstrate state-of-the-art completion performance with a 12.3% relative Chamfer Distance improvement over prior methods. Code is available at: https://github.com/AzharSindhi/I2PRef.git

---

### TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews

Authors: Hanqi Duan, Xiang Li
Published: 2026-05-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.26911v1

LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work either classifies authorship without judging quality, or scores quality with features designed for human-written reviews; no prior system detects deficiencies in LLM-generated reviews at the level of individual defect types. To bridge the gap, we introduce TADDLE, a Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews, together with the first expert-annotated benchmark for this task. Our benchmark comprises 1,800 reviews on 50 ICLR 2025 papers, multi-label-annotated by 18 domain experts against a taxonomy of six defect categories (plus a non-deficient label). TADDLE decomposes detection into four specialized analysis tools -- Verify, Correct, Complete, and Transform -- orchestrated by an agent; an integrator synthesizes their outputs into binary and multi-label classifications via two-stage semi-supervised learning. Extensive experiments show that TADDLE performs strongly on both binary detection and the multi-label classification task. We release the benchmark and code at https://github.com/AquariusAQ/TADDLE.

---

### EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models

Authors: Xianheng Wang, Yige Yang, Damien Coyle
Published: 2026-05-26
Categories: cs.LG, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2605.26910v1

Large EEG Foundation Models (FMs) have shown great potential for decoding EEG signals across diverse cognitive tasks. However, existing EEG-FM studies exhibit three critical limitations: opaque supervised baseline tuning, unverified contributions of complex learning paradigms, and a lack of transparency in model decision-making. To address these, we propose EEG-FM-Audit, a comprehensive evaluation and analysis pipeline designed to systematize the assessment of EEG-FMs. EEG-FM-Audit consists of three primary components: (1) an ASHA-driven benchmarking protocol that ensures fair comparisons by transparently optimizing supervised baselines; (2) paradigm-level ablation studies to evaluate the effectiveness of learning paradigms in FMs; and (3) a neurophysiological probing (NPP) framework, which explores whether FMs leverage valid temporal, spatial, and spectral EEG properties. We apply EEG-FM-Audit to four state-of-the-art EEG-FMs and five representative supervised models across three public datasets. Our results reveal that properly tuned supervised baselines can match or outperform advanced FMs, despite requiring significantly fewer parameters. Furthermore, we find that the effectiveness of learning paradigms of FMs is highly dependent on dataset scale and architecture. Finally, NPP analysis demonstrates how FMs rely on specific physiological features, establishing a framework for more interpretable neural decoding.

---

### On the Detection of Commutative Factors in Factor Graphs: Necessary and Sufficient Conditions

Authors: Malte Luttermann, Ralf Möller, Marcel Gehrke
Published: 2026-05-26
Categories: cs.AI, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2605.26908v2

Exploiting the indistinguishability of objects in a probabilistic graphical model such as a factor graph is key to lifted probabilistic inference algorithms and allows for tractable probabilistic inference problems with respect to domain sizes. A central building block for the exploitation of indistinguishable objects in factor graphs is the identification of commutative factors, i.e., factors whose output values are invariant under permutations of input values assigned to a subset of their arguments. In this paper, we revisit the theoretical foundations underlying the state-of-the-art algorithm to detect commutative factors. Specifically, we show that in its current form, the state-of-the-art algorithm relies on a central theorem that is mistakenly regarded as a sufficient condition to identify commutative factors, while it actually only implies necessary condition. Consequently, the state of the art might, as we show in this paper, deliver incorrect results. To fix the flaws currently present in the state of the art, we prove a slightly modified version of the aforementioned theorem, which serves as a necessary condition to identify commutative factors. Moreover, we present a corrected version of the state-of-the-art algorithm, which keeps its efficiency while ensuring correctness and introduce a complementary algorithm with tighter worst-case bounds.

---

### Practical Anonymous Two-Party Gradient Boosting Decision Tree

Authors: Chenyu Huang, Fan Zhang, Minxin Du, Sherman S. M. Chow, Huangxun Chen, Huaming Rao, Danqing Huang, Bo Qian, Peng Chen
Published: 2026-05-26
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.26903v2

Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutually distrustful parties. High speed and interpretability make GBDTs popular in finance and healthcare, where neural networks may fall short. Enabling secure computation for GBDTs poses unique challenges, requiring secure record alignment for comparison. Relying on private set intersection (PSI) is a de facto approach. Mistaking PSI for a safety measure actually exposes which record identifiers (IDs) are shared between the datasets. Although circuit-PSI could help, it is costly for generic uses. New ideas are needed to efficiently train in a "dark forest". Aiming to hide the IDs, we initiate the study of anonymous GBDT training on split data held by two parties. Dual circuit-PSI in our design lets the parties alternate as receiver to run pick-then-sum over local features. Via oblivious programmable pseudorandom functions, we propagate circuit-PSI outputs as shared state across runs. Avoiding universal alignment, we resolve the neglected dilemma that ID hiding incurs a cost that scales with domain size. Next, we halve the cost of ciphertext packing used to convert single-instruction multiple-data homomorphic encryption from (ring) learning with errors in prior secure GBDT (Usenix Security' 23) and related secure machine-learning computations. Comparative experiments show our protocol remains competitive with leaky approaches in efficiency. Enabling ID-hiding aggregation, our techniques can extend to other vertically partitioned analytics.

---

### ICICLE: Expanding Retrieval with In-Context Documents

Authors: Yu-Chen Den, Yung-Yu Shih, Zhi Rui Tam, Kuan-Yu Chen, Pu-Jen Cheng, Yun-Nung Chen, Eugene Yang
Published: 2026-05-26
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2605.26902v3

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new document-docid associations incurs repeated training and catastrophic forgetting of previously indexed documents. In this work, we revisit incremental GR as an in-context retrieval problem, where newly added documents are supplied as inference-time document-docid evidence. We propose ICICLE, an in-context indexing framework that performs source-aware docid generation over both parametric memory and context-provided document-docid pairs. ICICLE combines a `(COPY)`-based routing mechanism, preference-based calibration, and large context adaptation to distinguish context-grounded retrieval from parametric retrieval. Experiments on MS MARCO and NQ320K show that ICICLE improves retrieval of newly introduced documents while preserving seen-document retention without corpus-specific retraining. Our analysis further shows that high-shot degradation is mainly caused by routing failure, highlighting source-selection calibration as a key bottleneck for scaling in-context generative retrieval.

---

### ICICLE: Expanding Retrieval with In-Context Documents

Authors: Yu-Chen Den, Yung-Yu Shih, Zhi Rui Tam, Kuan-Yu Chen, Pu-Jen Cheng, Yun-Nung Chen, Eugene Yang
Published: 2026-05-26
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2605.26902v2

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new document-docid associations incurs repeated training and catastrophic forgetting of previously indexed documents. In this work, we revisit incremental GR as an in-context retrieval problem, where newly added documents are supplied as inference-time document-docid evidence. We propose ICICLE, an in-context indexing framework that performs source-aware docid generation over both parametric memory and context-provided document-docid pairs. ICICLE combines a `(COPY)`-based routing mechanism, preference-based calibration, and large context adaptation to distinguish context-grounded retrieval from parametric retrieval. Experiments on MS MARCO and NQ320K show that ICICLE improves retrieval of newly introduced documents while preserving seen-document retention without corpus-specific retraining. Our analysis further shows that high-shot degradation is mainly caused by routing failure, highlighting source-selection calibration as a key bottleneck for scaling in-context generative retrieval.

---

### SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

Authors: Léo Nicollier, Max Dunitz, Marc Pic, Pablo Musé, Enric Meinhardt-Llopis, Gabriele Facciolo
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26900v1

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream prediction risk in Euclidean spaces. However, the corresponding problem for distributions supported on lower-dimensional manifolds, such as the hypersphere, remains unexplored. In this work, we demonstrate that extending this minimax analysis to smooth distributions on Riemannian manifolds fundamentally changes the optimal solution. We show that, under a worst-case formulation, both k-nearest neighbors and kernel ridge regression induce hyperspherical uniformity. More precisely, we show that uniform distributions on manifolds are optimal for k-nearest neighbors, and that the uniform distribution on the sphere is optimal for kernel ridge regression with both the exponential dot-product kernel and the linear kernel. This theoretical insight reveals a fundamental limitation of Gaussian embeddings: their non-uniform density induces anisotropic k-NN neighborhoods, severely biasing the estimator. To correct this, we introduce SPHERE-JEPA, a theoretically grounded SSL framework. We adapt LeJEPA's Cram{é}r-Wold projection mechanism to enforce hyperspherical uniformity rather than a Gaussian prior. Empirically, SPHERE-JEPA yields significant improvements, boosting texture retrieval mAP by over 6%, while consistently matching or outperforming LeJEPA on standard benchmarks-including a +1.8% linear probing gain on ImageNet-1K (ViT-B/14).

---

### Strategies for Guiding LLMs to Use Software Design Patterns: A Case of Singleton

Authors: Viktor Kjellberg, Farnaz Fotrousi, Miroslaw Staron
Published: 2026-05-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.26898v1

Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level architectural structures or design patterns. Since LLMs are increasingly used in software engineering, their ability to apply established design principles to generated code is crucial to the long-term success of software products. Therefore, the goal of this paper is to identify strategies for guiding LLMs to incorporate design patterns into the generated source code. We designed a computational experiment to evaluate the ability of 13 LLMs to generate code that follows the Singleton design pattern, using four prompting strategies: instructions, binary automated feedback, extensive automated feedback, and extensive feedback with few-shot prompts, in 164 Java coding challenges from HumanEval-X. Our results shows that the optimal strategy to guide LLMs to include design patterns depends heavily on the type of model. Still, overall, iterative binary feedback provides the best alignment with Singleton while preserving or improving the code's functionality. With guiding with instructions, Llama 3.3 generated Singleton classes in 100% of cases and improved code functionality, increasing the number of tests passed by 34.1 percentage points. It achieved a similar result with guidance through instructions and binary feedback. Qwen 3 (8B) increased the alignment with Singleton to 99.2% and the functionality to 58.6% using binary feedback. Our result suggests that even simple strategies can be used to guide LLMs to use design patterns.

---

### Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models

Authors: Mingze Wang, Shuchen Zhu, Yuxin Fang, Binghui Li, Kai Shen, Shu Zhong
Published: 2026-05-26
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.26895v2

Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has been extensively studied, the scale vector remains poorly understood despite its ubiquitous use. In this work, we present a systematic study of scale vectors in LLMs from the perspectives of expressivity, optimization, and architectural structure. First, we show empirically that although scale vectors constitute only a negligible fraction of model parameters, removing them substantially degrades LLM pre-training. Our theory further shows that, in Pre-Norm architectures, scale vectors do not increase expressivity; instead, they improve optimization through a self-amplifying preconditioning effect on subsequent linear mappings. Second, we investigate the role of weight decay for scale vectors. By distinguishing Input-Norm and Output-Norm layers, we theoretically show that weight decay is beneficial for the former but harmful for the latter, due to their distinct roles in optimization and expressivity. Third, motivated by this understanding, we propose three lightweight and complementary improvements to scale vectors: branch-specific heterogeneity, improved placement around linear mappings, and magnitude-direction reparameterization. Both theory and experiments show that each improvement yields consistent gains. Finally, we combine these improvements into a unified scale-vector strategy and evaluate it through extensive LLM pre-training experiments on dense and mixture-of-experts models ranging from 0.12B to 2B parameters, across multiple optimizers and learning rate schedules, under industrial-scale token budgets. The unified strategy consistently achieves lower terminal loss than well-tuned baselines and exhibits more favorable scaling behavior, while adding negligible parameter and computational overhead.

---

### Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models

Authors: Mingze Wang, Shuchen Zhu, Yuxin Fang, Binghui Li, Kai Shen, Shu Zhong
Published: 2026-05-26
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.26895v1

Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has been extensively studied, the scale vector remains poorly understood despite its ubiquitous use. In this work, we present a systematic study of scale vectors in LLMs from the perspectives of expressivity, optimization, and architectural structure. First, we show empirically that although scale vectors constitute only a negligible fraction of model parameters, removing them substantially degrades LLM pre-training. Our theory further shows that, in Pre-Norm architectures, scale vectors do not increase expressivity; instead, they improve optimization through a self-amplifying preconditioning effect on subsequent linear mappings. Second, we investigate the role of weight decay for scale vectors. By distinguishing Input-Norm and Output-Norm layers, we theoretically show that weight decay is beneficial for the former but harmful for the latter, due to their distinct roles in optimization and expressivity. Third, motivated by this understanding, we propose three lightweight and complementary improvements to scale vectors: branch-specific heterogeneity, improved placement around linear mappings, and magnitude-direction reparameterization. Both theory and experiments show that each improvement yields consistent gains. Finally, we combine these improvements into a unified scale-vector strategy and evaluate it through extensive LLM pre-training experiments on dense and mixture-of-experts models ranging from 0.12B to 2B parameters, across multiple optimizers and learning rate schedules, under industrial-scale token budgets. The unified strategy consistently achieves lower terminal loss than well-tuned baselines and exhibits more favorable scaling behavior, while adding negligible parameter and computational overhead.

---

### SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising

Authors: Chengwei Zhang, Xueyi Zhang, Tao Jiang, Xinhao Xu, Wenjie Li, Fubo Zhang, Longyong Chen
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26894v1

In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across noisy variants via noise or optimal transport, but suffer from correspondence ambiguity. In this work, we propose Self-Induced Mirror-Point Consistency (SIMPC) to learn deterministic correspondences between points and the underlying surface in an unsupervised manner. For each noisy point, SIMPC generates a mirror-point on the opposite side of the underlying surface, guided by geometric priors during the denoising process. By encouraging consistency between the denoising targets of the original point and its mirror counterpart, SIMPC effectively localizes the position of underlying surface. Extensive experiments on synthetic and real-world datasets demonstrate that SIMPC significantly outperforms state-of-the-art unsupervised methods and surpasses several strong supervised counterparts.

---

### GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought

Authors: Weijiang Lv, Wentong Zhao, Jiayu Wang, Yuhao Wu, Jiaheng Wei, Xiaobo Xia
Published: 2026-05-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.26893v1

Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We propose GeoFaith, a spatio-temporal framework that leverages latent geometric structure and entropy dynamics to diagnose and enforce faithful reasoning. We develop a scalable bootstrapping pipeline expanding step-level annotations from 1k to 20k samples across four domains, train an 8B faithfulness detector outperforming GPT-5 on standard benchmarks, and design a faithfulness-aware reinforcement learning framework jointly optimizing outcome correctness, process faithfulness, and trajectory consistency. Experiments show the proposed method achieves superior performance on both faithfulness detection and downstream reasoning, producing shorter, more interpretable chains without sacrificing accuracy. Our code will be made available publicly.

---

### Telenor Nordics Customer Service self-help corpus

Authors: Mike Riess
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26891v2

This paper presents a multilingual customer service self-help corpus comprising 1,122 manually validated documents in Finnish, Danish, Norwegian, and Swedish, totaling 274,599 words and 1,884,833 characters. The documents have been sourced from the public self-help pages of four Nordic telecommunications operators and subsequently filtered for person-identifiable information and relevance through a combined LLM and human annotation pipeline. Domain-specific datasets for Nordic languages remain scarce, particularly in customer service: a domain of growing importance for retrieval-augmented generation, cross-lingual transfer learning, and emerging agent-based service architectures. An analysis of the corpus reveals substantial variation in document length and structure across operators, reflecting distinct editorial strategies, as well as broad topical coverage spanning network hardware, mobile services, TV and streaming, billing, and account management. The dataset is publicly available under a CC-BY-NC-SA-4.0 license at https://zenodo.org/records/20732652, intended to support reproducible research in Nordic NLP and information retrieval.

---

### Nonlinear and Heavy-Tailed Predictability in Transition-Energy Financial Markets

Authors: Kpante Emmanuel Gnandi, Fredy Pokou, Jules Sadefo Kamdem
Published: 2026-05-26
Categories: q-fin.CP, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2605.26890v1

Transition-related financial markets are increasingly exposed to abrupt repricing episodes, elevated volatility, and heterogeneous macro-financial shocks. Under such conditions, conventional Gaussian-linear forecasting frameworks may provide an incomplete representation of the dependence structure linking fossil-energy, renewable-energy, technology, and utility-sector assets. This paper investigates whether transition-related financial returns exhibit residual non-linear predictability after controlling for heavy-tailed multivariate linear dynamics. To address this question, we develop a hybrid forecasting framework combining Student-t Vector Autoregressions with nonlinear recurrent residual learning architectures. The empirical analysis considers six major exchange-traded funds representing broad equity markets and key transition-sensitive sectors. The results reveal substantial departures from Gaussian-linear behavior, including excess kurtosis, volatility clustering, and remaining nonlinear dependence after econometric filtering. Out-of-sample forecasting experiments show that the proposed framework consistently improves predictive accuracy relative to conventional VAR models, standalone machine-learning methods, and alternative hybrid specifications. The forecasting gains become more pronounced during periods of macro-financial stress, particularly during the COVID-19 crisis and the Ukraine-related energy shock. Overall, the findings suggest that transition-related financial systems exhibit regime-sensitive and heavy-tailed predictive dynamics that are insufficiently captured by standard Gaussian-linear models alone.

---

### Parsimonious Learning-Augmented Online Metric Matching

Authors: Yongho Shin, Phanu Vajanopath
Published: 2026-05-26
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2605.26886v1

Learning-augmented algorithms have received significant attention in recent years, particularly in the context of online optimization. Motivated by the high computational cost of generating predictions, a growing line of work studies the tradeoff between performance guarantees and the number of predictions used in learning-augmented algorithms for problems such as caching and metrical task systems. In this paper, we extend this line of research to online metric matching by developing parsimonious learning-augmented algorithms and establishing lower bounds on their performance. Our approach extends the Follow-the-Prediction framework to the parsimonious setting by filling in a virtual prediction in the absence of an actual prediction, using an online metric matching algorithm that maintains good intermediate matchings throughout its execution. We complement our theoretical results with an empirical evaluation, demonstrating the practical effectiveness of our approach.

---

### Small Object Detection in Industrial Recycling: A New Dataset and YOLO Performance Evaluation

Authors: Oussama Messai, Abbass Zein-Eddine, Abdelouahid Bentamou, Mickael Picq, Nicolas Duquesne, Stéphane Puydarrieux, Yann Gavet
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26884v1

In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewing proposed methods based on deep learning supervised approaches. We provide a detailed comparison of these systems on a new dataset of more than 10k images and 120k instances, highlighting their performance, accuracy, and computational efficiency in the industrial recycling process use case. Through this comparative analysis, we identify the most reliable systems currently available and the specific challenges they are designed to tackle. Furthermore, we explore the benefits of data augmentation and synthetic images. Based on our analysis, we also propose potential future directions and innovative solutions that could enhance the effectiveness of small, dense and overlapped object detection systems. The scope of our investigations encompasses object detection, length measurement, and anomaly detection within the context of the recycling process. The anomaly detection strategy is robust against variations in image resolution and zoom levels, ensuring reliable performance in industrial applications. The repository of the proposed dataset, methods and evaluation codes can be found at: https://github.com/o-messai/SDOOD

---

### Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos

Authors: Dingkun Wei, Zehong Shen, Yan Xia, Georgios Pavlakos, Yujun Shen, Xiaowei Zhou
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26879v1

Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limitation stems from the absence of reliable high-order temporal cues -- velocity and acceleration -- which are essential for reconstructing motion that exhibits realistic momentum, timing, and high-frequency detail. We introduce HTD-Refine, a post-processing framework that augments existing Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics. At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video. These predicted dynamics serve as soft yet informative constraints in a global optimization procedure that refines world-space trajectories, significantly reducing jitter, suppressing over-smoothing, and restoring physically plausible motion. Extensive experiments on challenging in-the-wild benchmarks show that HTD-Refine consistently improves state-of-the-art HMR methods, yielding more accurate global trajectories and substantially more natural motion dynamics. Our results highlight the critical role of high-order temporal modeling in advancing monocular human motion recovery.

---

### Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation

Authors: Lulu Zheng, Wenjin Yang, Xiangwen Zhang, Rong Yin, Yulan Hu, Zheng Pan, Xin Li
Published: 2026-05-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.26878v1

Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility aggregation, yielding unstable implicit weights. We show empirically and theoretically that this aggregation-specific \emph{weighting noise} can create large score shifts when stakeholder satisfaction is dispersed; in our experiments, these weight-induced shifts also increase with stakeholder count. We propose \textsc{DecompR}: counterfactual-calibrated weights are fixed from query structure before candidate scoring, while per-role utilities are estimated independently, removing candidate-dependent weight drift and reducing estimation noise.

---

### Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

Authors: Madhulatha Mandarapu, Sandeep Kunkunuru
Published: 2026-05-26
Categories: cs.DB, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.26874v3

LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes that GPT-4 agents achieve 65% on 139 industrial maintenance scenarios, and compares LLM orchestration paradigms (Agent-As-Tool vs. Plan-Execute) on a fixed data layer. We ask the orthogonal question: how much does the data model behind the tools matter? We treat a typed knowledge graph as a grounding substrate and route each question by how it is best answered: (i) LLM-generated Cypher for structured retrieval, which lifts the same GPT-4 model from 65% to 82-83%; (ii) native graph and optimization primitives, with no LLM, reaching 99% on graph-answerable scenarios; and (iii) generation-augmented knowledge (GAK) for answers absent from the data -- the engine's agent materializes the missing facts as provenance-tagged graph nodes, then answers. A recurring theme is inverted LLM usage: we constrain the LLM to query generation or one-shot enrichment from a typed schema and let the graph execute deterministically. On the 88 real AssetOpsBench failure-mode scenarios the benchmark itself flags non-deterministic -- ten equipment types absent from the graph -- GAK lifts answerability from zero to 100% of equipment types and answers 81.8% of scenarios, every materialized fact tagged source:LLM-derived for auditability. We also contribute 40 graph-native scenarios. For structured operational domains the data layer -- not the LLM orchestration -- is the primary lever, and a typed knowledge graph serves as a grounding substrate between raw industrial data and LLM reasoning.

---

### When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection

Authors: Zhengyu Hu, Zheyuan Xiao, Linxin Song, Fengqing Jiang, Yuetai Li, Zhihan Xiong, Yue Liu, Junhao Lin, Yao Su, Lijie Hu, Kaize Ding, Teng Xiao et al.
Published: 2026-05-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.26872v5

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the highest-performing teacher to generate student training data, implicitly treating teacher test performance as a proxy for teaching quality. We show that this assumption can fail: even when multiple teachers provide correct answers to the same question, the answer from the strongest teacher is not necessarily the best supervision for a given student. To address this gap, we propose Student-Centric Answer Sampling (SCAS), a framework that selects from verified teacher-generated answers according to their estimated student-centric learning cost. Motivated by a token-wise gradient decomposition, we derive an efficient forward-only proxy for this cost and use it to guide answer selection during training. Experiments across 30 teacher models, 6 student base models, and 6 tasks show that SCAS consistently improves student performance, suggesting that effective distillation should prioritize supervision matched to the current student rather than teacher strength alone.

---

### The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection

Authors: Zhengyu Hu, Zheyuan Xiao, Linxin Song, Fengqing Jiang, Yuetai Li, Zhihan Xiong, Yue Liu, Junhao Lin, Yao Su, Lijie Hu, Kaize Ding, Teng Xiao et al.
Published: 2026-05-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.26872v3

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the highest-performing teacher to generate student training data, implicitly treating teacher test performance as a proxy for teaching quality. We show that this assumption can fail: even when multiple teachers provide correct answers to the same question, the answer from the strongest teacher is not necessarily the best supervision for a given student. To address this gap, we propose Student-Centric Answer Sampling (SCAS), a framework that selects from verified teacher-generated answers according to their estimated student-centric learning cost. Motivated by a token-wise gradient decomposition, we derive an efficient forward-only proxy for this cost and use it to guide answer selection during training. Experiments across 30 teacher models, 6 student base models, and 6 tasks show that SCAS consistently improves student performance, suggesting that effective distillation should prioritize supervision matched to the current student rather than teacher strength alone.

---

### Persistent AI Agents in Academic Research: A Single-Investigator Implementation Case Study

Authors: Anas H. Alzahrani
Published: 2026-05-26
Categories: cs.MA, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2605.26870v1

Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persistently in a real academic research environment with durable memory, local files, external tools, scheduled routines, delegated roles, and explicit safety protocols. Methods: A structured self-observed implementation case study was conducted from January 31 to May 25, 2026. The unit of analysis was the persistent human-agent environment: researcher, agent runtime, memory layer, tools, repositories, scheduled jobs, specialized agent roles, and governance rules. Outcomes were organized using PARE-M (Persistent Agentic Research Environment Measurement), a measurement framework covering architecture, utilization, artifact production, resource use, reproducibility, and governance. Results: Recoverable main-agent telemetry contained 75,671 de-duplicated records across 96 active days, with 8,059 user-role and 23,710 assistant-role messages. The workspace included 502 memory-related files, 17 configured agent directories, and 57 skill files. Active system time was 579.7 hours (30-minute capped-gap estimate). Memory-derived records identified 482 output-proxy events and 889 failure, verification, correction, or protocol-proxy events. A strict May 2026 trajectory subset captured 627 model-completed events and 73.95 million recorded tokens, of which 82.9% were cache reads. Conclusions: The workflow was cache-dominant, suggesting that persistent agentic environments may shift the economic unit from cost per token to cost per completed artifact. Future evaluations should use artifact-level denominators, reproducible parsing rules, correction taxonomies, and independent coding of governance events.

---

### RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction

Authors: Chenxu Peng, Chenxu Wang, Yimian Dai, Yongxiang Liu, Ming-Ming Cheng, Xiang Li
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26862v1

Accurate road segmentation from aerial imagery is fundamental to many geospatial applications. However, existing datasets often suffer from limited scene diversity, low semantic granularity, and poor structural continuity, restricting their generalization across environments. To address these challenges, we introduce WorldRoadSeg-360K, the largest and most diverse road segmentation dataset to date, comprising 366,947 high-resolution images collected from 38 countries and 223 cities across various terrains and continents. WorldRoadSeg-360K serves as a comprehensive benchmark and reveals key challenges in handling diverse and structurally complex scenes. Automated approaches often struggle to preserve road connectivity, while current interactive methods lack efficient, topology-sensitive tools for real-world road editing. To this end, we present RoadGIE, establishing a novel interactive paradigm for road extraction in remote sensing. Unlike prior point- or box-based prompting strategies, RoadGIE supports connectivity-aware prompts, including clicks and scribbles, which inherently align with the topology of road networks. To improve structural consistency and mitigate performance degradation during iterative interactions, RoadGIE integrates an expert-guided prompting strategy and adapts the skeleton-based recall loss for interactive scenarios. RoadGIE achieves state-of-the-art performance in both segmentation accuracy and topological consistency on WorldRoadSeg-360K and other benchmarks, while maintaining efficient operation with only 3.7M parameters. The code are publicly available at: https://github.com/chaineypung/RoadGIE

---

### REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization

Authors: Yong Li, Furong Jia, Dacheng Yin, Kang Rong, Fengyun Rao, Jing Lyu, Fan Zhang
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26861v1

Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts typically solve it through an iterative workflow: they inspect informative regions, form location hypotheses, seek external evidence, and revise their judgments as new clues appear. Existing methods only partially capture this process: direct prediction methods bypass evidence acquisition altogether, while retrieval-augmented methods introduce external evidence but usually provide limited supervision on the intermediate decisions of where to search, how to query, and how to filter noisy results. We present REVERSE, a framework that reinforces the interplay between evidence search and verification to enable multi-turn agentic reasoning. REVERSE teaches three intermediate decisions: where to look, what to query, and what evidence to trust. To support this, we construct tool-grounded trajectories with annotated region selections, search observations, and geo-informative evidence labels, and introduce process rewards for visual grounding, query utility, and evidence discrimination. An offline search cache makes retrieval observations stable and reusable during reinforcement learning, enabling dense supervision over noisy search results. With a 4B model, REVERSE outperforms strong retrieval-augmented baselines and rivals substantially larger models on Im2GPS3k and YFCC4k. Code is available at https://github.com/yonglleee/REVERSE.

---

### Generalist Graph Anomaly Detection via Prototype-Based Distillation

Authors: Yiming Xu, Zihan Chen, Zhen Peng, Song Wang, Bin Shi, Bo Dong, Chao Shen
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26857v2

Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs, has recently gained growing attention. However, existing methods often rely on scarce and costly annotations for training and sometimes even require few-shot support at inference, which limits their robustness to diverse and unseen anomaly patterns. To address this limitation, we introduce ProMoS, the first unsupervised generalist GAD framework, which detects anomalies by modeling the abundant normality in unlabeled data. ProMoS adopts a knowledge-distillation paradigm to distill normality priors from a frozen self-supervised graph neural network (GNN) teacher to a mixture-of-students model with shared global and lightweight personalized branches, enabling efficient and expressive normality modeling without learning from scratch. We further propose prototype-guided soft-label distillation to align teacher and student in a shared prototype space, enhancing cross-graph generalizability. During inference, ProMoS performs zero-shot anomaly detection on unseen graphs via distillation bias and prototype geometric deviation. Extensive experiments show the effectiveness and efficiency of ProMoS, charting a practical path toward label-free, zero-shot generalist GAD.

---

### Generalist Graph Anomaly Detection via Prototype-Based Distillation

Authors: Yiming Xu, Zihan Chen, Zhen Peng, Song Wang, Bin Shi, Bo Dong, Chao Shen
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26857v1

Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs, has recently gained growing attention. However, existing methods often rely on scarce and costly annotations for training and sometimes even require few-shot support at inference, which limits their robustness to diverse and unseen anomaly patterns. To address this limitation, we introduce ProMoS, the first unsupervised generalist GAD framework, which detects anomalies by modeling the abundant normality in unlabeled data. ProMoS adopts a knowledge-distillation paradigm to distill normality priors from a frozen self-supervised graph neural network (GNN) teacher to a mixture-of-students model with shared global and lightweight personalized branches, enabling efficient and expressive normality modeling without learning from scratch. We further propose prototype-guided soft-label distillation to align teacher and student in a shared prototype space, enhancing cross-graph generalizability. During inference, ProMoS performs zero-shot anomaly detection on unseen graphs via distillation bias and prototype geometric deviation. Extensive experiments show the effectiveness and efficiency of ProMoS, charting a practical path toward label-free, zero-shot generalist GAD.

---

### The Sensation Modulating Network:Haltability as the architectural ground for object-directed phenomenology

Authors: G. Nagarjuna, Durgaprasad Karnam
Published: 2026-05-26
Categories: q-bio.NC, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.26856v2

We propose the Sensation Modulating Network (SMN): the cognitive agent as the whole body, organized at every scale by opponent dynamics, built from Sensation Modulators -- tissue that senses and acts through one substrate -- paired into Coordinated Action Zones routed by a body-wide broadcast. It is an inclusive model of the body, in which gravity, elasticity, and the body's topology and geometry do constructive cognitive work. The paper is scoped to what such a body constructs at its foundation -- a self-model, a world-model in that self's frame, and object-directedness -- each built by the body's physics, not assumed as a primitive. The architecture is generative: one small kit of primitives whose morphological variations (chain, sheet, tube, layered, appendicular) construct experience by the same mechanism, an invariance shown for the self-model across body plans and scales. The central thesis: haltability -- the active holding of an opponent equilibrium -- is the architectural condition object-directed phenomenology requires; a second principle, that an object is a bundle of more than one property, carries it from felt resistance to a genuine object. A companion bench realizes each construction as a runnable, falsifiable experiment with a pre-registered order parameter and matched foil. We place the principal competing accounts -- sensorimotor enactivism, active inference, and ecological and affordance-based theories -- as limiting cases within a wider landscape, stating in each case the criterion that would tell them apart, and give systems and cognitive neuroscience its place: the nervous system as the integrating core that makes the body one, not a commander over it. On this account, the cognitivism-4E impasse reflects an incomplete architecture of the embodied agent: its resolution begins not with the brain alone but with the whole body.

---

### Receipt Replay OOD: A Small Benchmark for Screen Replay Detection Under Domain Shift

Authors: Alexander Vinogradov
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.26855v1

Public datasets such as DLC-2021, SynID, and KID34K have significantly contributed to research on presentation attack detection for identity documents, including screen replay attacks. However, evaluation of out-of-domain (OOD) robustness remains insufficiently explored, especially under realistic domain shifts. In this work, we introduce Receipt Replay OOD, a small out-of-domain benchmark for screen replay detection. Receipts share several characteristics with identity documents, including planar geometry, curved corners, wear-and-tear artifacts, and text or logo patterns, while avoiding personally identifiable information constraints commonly associated with identity documents. We evaluate document replay detection models under cross-domain conditions and demonstrate the impact of domain shift on generalization performance. The dataset is publicly available.

---

### RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections

Authors: Yali Fink, Ido Ben-Yair, Lars Ruthotto, Eran Treister
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26854v2

The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its performance is severely constrained by the trade-off between the sparsity and convergence quality of coarse-grid operators. Classical AMG heuristics struggle to balance these objectives, often sacrificing stability or performance for sparsity. We propose RAPNet, a graph neural network (GNN) framework that resolves this trade-off by learning to generate sparse, robust coarse operators directly from the sparse algebraic system. Key to our approach is a level-wise training strategy that enables learning from small subgraphs and generalization to million-node domains, bypassing the bottlenecks of prior neural AMG attempts. RAPNet executes exclusively during the solver setup phase, ensuring that the solve phase retains its favorable computational properties. We show that our method outperforms classical non-Galerkin baselines on diverse PDE discretizations and graph Laplacians, making it particularly effective for multi-query tasks such as eigenproblems, time-dependent simulations, and inverse or design problems.

---

### Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences

Authors: Hanlin Yu, RuiKang OuYang, Partha Kaushik, Arto Klami, Michael U. Gutmann, Omar Chehab
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26850v1

Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matching for training energy-based diffusion models, use stochastic interpolants to corrupt data samples at different noise levels indexed by a time variable. This defines a joint density over both the data space and time, and most methods learn its energy through either spatial or temporal differences. We identify distinct failure modes for both of these approaches. To solve them, we propose Spatiotemporal Noise-Contrastive Estimation (stNCE), a framework for learning the energy through joint spatiotemporal differences. stNCE unifies many existing methods and leads to new training objectives. Experiments on images and molecules demonstrate performance competitive with state-of-the-art density estimation methods.

---

### Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning

Authors: Manh Nguyen, Sunil Gupta, Hung Le
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26849v1

Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB), a concave integer optimization framework that reallocates a fixed sampling budget based on per-question uncertainty estimated at no additional inference cost. In Phase 1, every question receives one generation; its average negative log-likelihood (ANLL), extracted directly from output log-probabilities, serves as a difficulty signal while the generation contributes to the final vote. In Phase 2, the remaining budget is allocated by a marginal-greedy algorithm that solves a concave coverage-maximization surrogate exactly: uncertain questions receive more sampling budget while confident questions receive fewer additional samples. Evaluated on six open-weight and black-box models spanning 1.5B to 27B parameters and five reasoning benchmarks covering math, logic, and preference tasks, UAB outperforms baselines by up to +3% in average accuracy and up to +5% on individual benchmarks, with the largest gains in low-resource settings, requiring no auxiliary model or additional LLM call. Code is publicly available at https://github.com/manhitv/UAB.

---

### Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Authors: Yuanyi Wang, Su Lu, Yanggan Gu, Pengkai Wang, Yifan Yang, Zhaoyi Yan, Congkai Xie, Jianmin Wu, Hongxia Yang
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.26844v1

On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We revisit this principle and ask: which token-level teacher signals are actually learnable? Using a fixed-context diagnostic that measures same-context teacher-student KL reduction, we show that raw KL disagreement is a coarse proxy for learning value. It conflates learnable disagreement, where the teacher assigns corrective mass to the student's top-K candidates, with incompatible disagreement, where the teacher places mass mostly off the student's current support. We formalize this local compatibility as token teachability and show that it better predicts fixed-context improvement than raw KL alone. Motivated by this finding, we propose Teachability-Aware OPD (TA-OPD), a lightweight token-position selection method that applies OPD loss to high-teachability positions without reward models or verifiers. Across Qwen2.5 and Qwen 3 teacher-student settings, TA-OPD often surpasses full-token OPD with only 5% retained tokens and improves over entropy- and divergence-based baselines. Our results reframe selective OPD as selecting learnable teacher signals rather than merely salient tokens.

---

### MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training

Authors: Jiacheng Li, Jianchao Tan, Hongtao Xu, Jiaqi Zhang, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai
Published: 2026-05-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.26842v2

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become trapped in sharp local minima. In this work, we present MONA, an optimizer that bridges Muon's orthogonalization framework with curvature-aware acceleration. MONA adds an acceleration term directly into Muon's gradient processing pipeline. This term is calculated from the exponential moving average of gradient differences. We provide a detailed convergence analysis for MONA, showing that the acceleration term introduces curvature-sensitive corrections while preserving Muon's spectral-norm regularization. Empirically, MONA achieves better convergence and downstream task performance compared to both Muon and AdamW across three scales of Mixture-of-Experts pretraining, spanning from 1B to 68B parameters, with the largest model trained on 1 trillion tokens. Furthermore, we conduct supervised fine-tuning on the MOE-68B-A3B model and evaluate it on general capability, mathematical reasoning, and code generation benchmarks, where MONA achieves SOTA performance.

---

### MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training

Authors: Jiacheng Li, Jianchao Tan, Hongtao Xu, Jiaqi Zhang, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai
Published: 2026-05-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.26842v1

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become trapped in sharp local minima. In this work, we present MONA, an optimizer that bridges Muon's orthogonalization framework with curvature-aware acceleration. MONA adds an acceleration term directly into Muon's gradient processing pipeline. This term is calculated from the exponential moving average of gradient differences. We provide a detailed convergence analysis for MONA, showing that the acceleration term enables escape from sharp minima while preserving Muon's spectral-norm regularization. Empirically, MONA achieves better convergence and downstream task performance compared to both Muon and AdamW across three scales of Mixture-of-Experts pretraining, spanning from 1B to 68B parameters, with the largest model trained on 1 trillion tokens. Furthermore, we conduct supervised fine-tuning on the MOE-68B-A3B model and evaluate it on general capability, mathematical reasoning, and code generation benchmarks, where MONA achieves SOTA performance.

---

### Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics

Authors: Yuxuan Ye, Raul Santos-Rodriguez, Edwin Simpson
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.26840v1

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting their effectiveness as signals for shaping model behaviour.While individual factuality metrics are unreliable, their combination can more effectively capture diverse factual errors. We leverage this insight to introduce an automated training pipeline that improves factual consistency in summaries by aggregating scores from different weak metrics. Our approach avoids the need for complex reward shaping by mapping scores to preferences and filtering out cases with high disagreement between metrics. For each source document, we generate lexically similar summary pairs by varying decoding strategies, enabling the model to learn from factual differences caused by subtle lexical differences. This approach constructs a high-quality preference dataset using only source documents.Experiments demonstrate consistent factuality gains across models, ranging from early encoder-decoder architectures to modern large language models, with smaller models reaching comparable factuality to larger ones.

---