# Research Papers — 2026-05 · bundle page 4 of 326

> Full-text markdown of papers #151–200 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/4
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/3.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/5.md)

### BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

Authors: Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao, Ziheng Zhou, Mert Cemri, Shu Liu, Yuran Xiu, Chenxiao Yan, Haikun Zhao, Bin Yu, Ion Stoica et al.
Published: 2026-05-31
Categories: cs.SE, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.01286v1

The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal. For instance, on LiveCodeBench, frontier models achieve over 99% Pass@1 on easy splits and exceed 90% Pass@1 on average across difficulty levels. Constructing new, challenging datasets typically requires substantial human effort, creating a bottleneck for progress. We introduce BenchEvolver, a solution-centric evolutionary framework that automatically transforms existing coding problems into harder variants. Rather than generating problems from scratch, BenchEvolver evolves reference solutions through structured transformations and derives corresponding statements and tests from the evolved solutions. This design grounds generation in executable semantics, enabling scalable construction of high-quality, diverse, and difficult tasks with verifiable correctness. Applying BenchEvolver to LiveCodeBench and SciCode, we obtain evolved tasks that are substantially harder while maintaining validity, reference correctness, and diversity. We further curate LiveCodeBench-Plus, a 91-problem benchmark combining evolved and difficult original LCB-v6 tasks, where frontier-model Pass@1 ranges from 27.5% to 62.6%, restoring clear discrimination among strong coding models. Importantly, evolved tasks remain challenging even for the model that generates them, enabling self-improvement. We further show that RL on evolved LCB tasks improves held-out coding performance: for gpt-oss-20b, seed+evolved training achieves +8.7 and +8.3 Pass@1 gains on LCB v6 Hard and LCB-Pro Easy, exceeding seed-only gains by 70.7% and 34.8%, respectively. Our results show that BenchEvolver can convert saturated benchmarks into frontier-level evaluation suites and reusable training signal.

---

### Knowledge-Intensive Video Generation

Authors: Chenxu Wang, Mingda Chen
Published: 2026-05-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.01285v2

Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To evaluate this setting, we construct KIVI-Bench, a benchmark of 1,080 prompts, and propose automatic metrics for factuality and helpfulness. Human evaluation shows that our metrics significantly better align with human annotations than existing alternatives. Experiments on seven state-of-the-art video generation models show that current systems still lag behind human performance, especially on visual properties, procedural operations, and clear information presentation. These results highlight KIVI as a challenging direction for factual and instructionally useful video generation.

---

### Knowledge-Intensive Video Generation

Authors: Chenxu Wang, Mingda Chen
Published: 2026-05-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.01285v1

Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To evaluate this setting, we construct KIVI-Bench, a benchmark of 1,080 prompts, and propose automatic metrics for factuality and helpfulness. Human evaluation shows that our metrics significantly better align with human annotations than existing alternatives. Experiments on seven state-of-the-art video generation models show that current systems still lag behind human performance, especially on visual properties, procedural operations, and clear information presentation. These results highlight KIVI as a challenging direction for factual and instructionally useful video generation.

---

### AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

Authors: Zhongyue Zhang, Guangyin Jin, Yuxuan Liang, Suwan Yin, Yuankai Wu
Published: 2026-05-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.01283v1

Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based kernels with predefined parameters, which restricts model capacity. Although generic adaptive mechanisms (e.g., Graph Attention Networks) offer flexibility, they often fail to capture the underlying geometric structure, performing worse than distance-based models in data-sparse scenarios. Addressing this, we revisit the kernel parameterization problem and theoretically prove that misspecified kernel parameters introduce unavoidable approximation errors in GNNs. To overcome this, we propose AdaKernel, a simple yet effective approach that learns adaptive kernel parameters within the neural network. Unlike methods that learn graph structures from scratch, AdaKernel adopts a structure-preserving strategy that optimizes the scale of physical interactions rather than discarding them. Extensive experiments on Kriging, Imputation, and Forecasting demonstrate that AdaKernel consistently improves various GNN architectures and outperforms model-agnostic adaptive baselines, validating that accurately learned kernel parameters are superior to both fixed priors and fully latent graph structures.

---

### KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation

Authors: Farbod Davoodi, Seyed Reza Tavakoli Shiyadeh, Pooria Safaei, Sana Harighi, Parsa Gholami, Amirali Amini, Kimia Vanaei, Emad Firoozi, Parham Abed Azad, Babak Khalaj, Siavash Ahmadi, Amir Hossein Payberah et al.
Published: 2026-05-31
Categories: cs.CV, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2606.01282v1

Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale. Existing mitigations either require costly retraining, infeasible for the closed-source backbones that dominate consumer products, or rely on fixed demographic templates that ignore cultural context. We present KG-FairDiff, a model-agnostic, inference-time framework that formalises fairness-aware prompt refinement as a constrained optimisation problem and operationalises it as a closed-loop pipeline: a knowledge graph of ~1,200 culture- and bias-related triples retrieves structured context, an LLM rewriter proposes refinements, and a validator accepts only prompts that reduce a divergence-based fairness loss while preserving semantic fidelity to the user's original intent. We prove a finite-termination bound for the refinement loop, contribute a mathematically consistent evaluation suite linking Bias-P/Bias-W to divergence from target distributions and ENS to KL divergence, and audit eight widely-deployed backbone generators. KG-FairDiff substantially reduces gender, race, age, and intersectional disparities while preserving prompt semantics, offering a practical, deployment-ready route to more equitable generative AI.

---

### RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Authors: Yixiu Mao, Yun Qu, Qi Wang, Heming Zou, Xiangyang Ji
Published: 2026-05-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.01281v1

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, its effectiveness is substantially hindered by the prevalence of ineffective training data: many sampled prompts yield response groups that are either entirely correct or entirely incorrect, resulting in zero-variance rewards and limited learning signals. Recent state-of-the-art methods address this issue through extensive LLM rollouts to filter ineffective samples, but at the cost of considerable computational overhead. Alternative approaches, including predictive sampling and trajectory replay, aim to improve data efficiency but often remain insufficient and may introduce additional issues such as systematic bias or suboptimal constraints. To address these limitations, we propose Group Prioritized Off-Policy Optimization (POPO), a simple yet effective framework that fully exploits effective training batches without additional rollout overhead. POPO comprises two key components: prioritized group replay and decoupled off-policy optimization. The former replaces ineffective on-policy groups with effective off-policy groups via a recency-based replay mechanism that jointly considers sample quality and the degree of off-policiness. To further mitigate the off-policy gap, POPO employs decoupled importance sampling to correct off-policy bias while maintaining stable policy updates under consistent trust-region constraints. Empirical evaluations across diverse reasoning tasks, including mathematics, planning, and visual geometry, demonstrate that POPO substantially accelerates RL finetuning and achieves strong reasoning performance with significantly fewer rollouts.

---

### Event-Based Vision in Space: Applications, Trends, and Future Directions

Authors: Luigi Capogrosso, Pietro Bonazzi, Michele Magno
Published: 2026-05-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.01280v1

Earth Observation (EO) is undergoing a significant transformation driven by the deployment of novel sensing technologies. Traditional frame-based optical sensors often struggle with motion blur, high power consumption, and extreme data redundancy in challenging orbital environments. In contrast, event-based sensors, also known as neuromorphic cameras, offer a bio-inspired asynchronous approach. By capturing only local illumination changes, they provide microsecond temporal resolution, an extremely high dynamic range, and exceptional energy efficiency. Although the use of these sensors is rapidly expanding from terrestrial systems to orbital platforms, the scientific literature surrounding their space-based applications remains heavily fragmented. To bridge this gap, this article presents a comprehensive review of the state-of-the-art in event-based vision in the space domain. Based on the retrieved literature, we introduce a taxonomy structured around four primary domains: 1) atmospheric and high-speed observation; 2) environmental monitoring and change detection; 3) operational support and onboard processing; and 4) geospatial modeling and predictive analysis. As a result, this survey highlights that neuromorphic engineering is far more than a supplementary imaging technique; it is a paradigm shift that can be used to directly address critical bottlenecks in modern remote sensing and sustainable space exploration.

---

### ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment

Authors: Zhengyang Zhao, Shengjie Ye, Lu Ma, Hao Liang, Hengyi Feng, Wentao Zhang
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01279v1

AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into aligned assistants. However, recent evaluations reveal that even frontier agents struggle to perform this task. While the success of post-training fundamentally relies on acquiring high-quality data, relying on agents to autonomously curate targeted training datasets from the open web introduces severe challenges. Executing the long-horizon tasks of searching, filtering, and balancing data within noisy web environments frequently overwhelms an agent's limited context, ultimately leading to degraded dataset quality and suboptimal downstream training performance. To bridge this gap, we introduce Andes (Agent Native Data Evolving Synthesis), a framework that reimagines data generation as a plug-and-play \emph{agent skill}. Rather than forcing agents to devise complex data-gathering strategies from scratch, \textsc{Andes} provides an intelligent abstraction layer. By leveraging a self-evolving World Tree routing mechanism and actionable diagnostic reports, it allows trainer agents to dynamically steer data synthesis through an interactive, closed-loop interface. We demonstrate that under strict compute constraints, equipping foundationally weaker agents with Andes improves automated alignment, securing state-of-the-art performance on PostTrainBench and robust cross-task generalization. Our project is available at https://github.com/zzy1127/ANDES.

---

### DeepIPCv3: Event-Aware Multi-Modal Sensor Fusion for Sudden Pedestrian Crossing Avoidance

Authors: Oskar Natan, Andi Dharmawan, Aufaclav Zatu Kusuma Frisky, Jazi Eko Istiyanto, Jun Miura
Published: 2026-05-31
Categories: cs.RO, cs.AI, cs.CV, eess.IV, eess.SY
arXiv: https://arxiv.org/abs/2606.01277v1

Current end-to-end autonomous driving systems predominantly rely on frame-based sensors, which suffer from inherent perception latency and motion blur during highly dynamic encounters, specifically sudden pedestrian crossings. To address this critical safety vulnerability, we propose DeepIPCv3, a novel multi-modal autonomous navigation framework that synergizes the dense 3D spatial geometry of LiDAR point clouds with the microsecond-level asynchronous event streams of a Dynamic Vision Sensor (DVS). We introduce a Transformer-inspired cross-modal attention mechanism to dynamically correlate these distinct modalities, allowing the network to instantaneously prioritize high-speed dynamic updates without sacrificing structural scene awareness. The fused latent representations are then mapped to safe local waypoints and executable control commands via a hybrid policy network that blends heuristic trajectory tracking with direct neural predictions. Due to the severe physical risks associated with live testing of these sudden crossing scenarios, the framework is rigorously evaluated offline using a custom multi-modal dataset collected across both well-illuminated noon and challenging evening conditions. Extensive comparative and ablation studies demonstrate that DeepIPCv3 achieves state-of-the-art predictive performance. By effectively eliminating exposure failures and motion blur, the proposed LiDAR and DVS fusion yields the lowest trajectory and control command errors, enabling highly reactive, mathematically bounded evasive maneuvers regardless of ambient illumination. To support future research, we will release the codes to our GitHub repo at https://github.com/oskarnatan/DeepIPCv3.

---

### Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination

Authors: Xiaoqi He, Kaixin Lan, Mu You, Tao Fang, Lidia S. Chao, Derek F. Wong
Published: 2026-05-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.01276v1

Large language model (LLM)-based machine translation has advanced cross-cultural communication, yet it still struggles with culture-loaded words (CLWs) in ancient Chinese texts. The challenge extends beyond lexical alignment to deciding when and how culture-dependent knowledge should be explicated for readers lacking relevant background. Literal translation often preserves surface forms while missing underlying concepts, whereas over-explicitation harms conciseness and readability. To address this problem, we formulate CLW translation as a selective explicitation task and propose \textbf{MACAT}, a \textbf{M}ulti-\textbf{A}gent \textbf{C}ulture-\textbf{A}ware \textbf{T}ranslation framework that dynamically identifies culturally salient phrases and injects concise explanatory knowledge when necessary. MACAT further incorporates a quality-aware reranking module for candidate selection and a multi-round evaluation agent that assesses translations across terminological precision, readability, fidelity, cultural preservation, and cultural explicitation. Experiments on traditional Chinese medicine (TCM) classics and the \textit{Analects} show that, under a unified GPT-5.4 evaluation setting, MACAT consistently outperforms both the backbone model and general-purpose MT baselines on 100 TCM documents and a 20-chapter subset of the \textit{Analects}.

---

### GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes

Authors: Guanyu Zhou, Yao Liu, Yanglei Gan, Yuxiang Cai, Peng He, Run Lin, Yuxiang Liu, Qiao Liu
Published: 2026-05-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.01273v1

Spatio-temporal point processes (STPPs) provide a principled framework for modeling asynchronous events in continuous time and space. Recent diffusion-based approaches offer a flexible alternative to deterministic prediction by modeling complex conditional distributions, but their application to STPPs remains challenging: reverse sampling from pure noise is costly, and weak structural constraints in sparse spatial domains can lead to poorly localized probability mass. We propose \textbf{GLIDE} (Graph-guided Leap Inference for Diffusion Estimation), a conditional diffusion framework for next-event modeling in STPPs. GLIDE organizes historical events into a multi-scale historical graph and encodes temporal evolution and spatial topology through a dual-stream architecture, yielding a structured conditioning context for a dual-branch diffusion denoiser. It further introduces a prior-guided leap inference mechanism, in which a lightweight mean predictor provides a deterministic anchor and the reverse process starts from an intermediate diffusion step instead of from pure Gaussian noise. Experiments on multiple real-world datasets show that GLIDE improves both distribution fitting and next-event prediction, with the largest gains appearing on the spatial side. The results also indicate that prior-guided leap inference substantially reduces reverse-sampling cost while preserving the stochastic generation capability of diffusion models.

---

### Exploiting In-Sensor Computing for Energy-Efficient Earth Observation

Authors: Luigi Capogrosso, Pietro Bonazzi, Loris Hoxhaj, Michele Magno
Published: 2026-05-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.01271v1

The rapid growth of the satellite industry has driven a significant increase in geospatial data acquisition, highlighting a critical bottleneck: the severe disparity between the volume of collected sensor data and the limited downlink bandwidth available to ground stations. While On-Board Computing (OBC) has helped address this by pre-processing data in orbit, this article further advances the paradigm by introducing an in-sensor computing framework. We present an optimized end-to-end Earth Observation (EO) pipeline tailored for strict computational constraints by integrating TinyML techniques with the Sony IMX500 Intelligent Vision Sensor. Specifically, our approach shifts processing directly to the sensor level, offloading the computation from the primary embedded device, and effectively mitigating the downlink transmission of noisy or irrelevant data. We evaluated several efficient Convolutional Neural Networks (ConvNets), i.e., SqueezeNet, ShuffleNetV2, and MCUNetV1, on the EuroSAT dataset. Experimental results show that, despite the optimizations required for deployment on the IMX500 platform, our models maintain a competitive 96.68% accuracy while operating within its 8 MB constraints. Specifically, the models reach an average processing throughput of 17.40 FPS with a latency of 27.43 ms. Furthermore, our system profile exhibits high energy efficiency, with a low energy footprint of 14.19 mJ per inference and an efficiency rating of 42.26 GMAC/J, demonstrating its viability for in-sensor deployment.

---

### Emergent Ordinal Geometry in Transformers Trained on Local Comparisons

Authors: Nishit Singh
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01269v2

Transitive inference is the challenge of inferring that A < C from knowing only adjacent relations (A < B, B < C). It is solved by humans and animals not through logical chaining but via an analogue mental number line, whose signature is the symbolic distance effect: distant comparisons are easier than nearby ones. We ask whether Transformers acquire the same primitive, training small models exclusively on adjacent comparisons from a hidden total order and evaluating generalization to unseen distant pairs. We find that out-of-distribution generalization emerges alongside a striking geometric reorganization: entity embeddings collapse onto a one-dimensional manifold whose principal axis recovers the hidden rank order with near-perfect fidelity, and this structure is sensitive to optimization in ways that produce grokking-like transient dynamics. Critically, even when accuracy is at ceiling, decision confidence and geometric separation both scale monotonically with rank distance, directly mirroring the symbolic distance effect observed across decades of behavioural experiments on humans, primates, and rodents. We further show the same rank-aligned geometry in a pretrained large language model, where it tracks the topology of each ordinal relation: linear for sizes and digits, cyclic for months. These results ground a 50-year-old behavioural regularity in the geometry of learned representations, offering a mechanistic account of transitive inference that bridges cognitive science and modern neural networks.

---

### PALTO: Physics-Informed Active Learning for Tri-Gate FinFET Design Optimization for Vertical Power Delivery

Authors: Ayoub Sadeghi, Leonid Popryho, Inna Partin-Vaisband
Published: 2026-05-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.01265v1

This paper demonstrates the effectiveness of machine learning-driven optimization for designing application-specific GaN tri-gate FinFETs in vertical power delivery systems. Conventional TCAD-based approaches are computationally intensive and insufficient for navigating the high-dimensional, nonlinear design space of advanced GaN devices. To address this, a physics-informed active learning framework is used to intelligently guide simulations, accelerating convergence while preserving accuracy. This ML-guided approach enables the discovery of optimal configurations by efficiently exploring key structural parameters -- most notably the GaN-to-AlGaN thickness ratio -- a long-standing focus of debate in device design. By systematically exploring key structural parameters, two optimized devices with aggressively scaled gate-to-drain lengths are identified. Single-fin, multi-channel simulations show that device~D2, with a thinner GaN channel relative to the AlGaN barrier, achieves higher drive current. However, in a 300-fin configuration, device~D1 outperforms device~D2 by delivering 3.3\,A at 0.49~ohm on-resistance -- approximately 2$\times$ better -- despite slightly higher parasitics. Both devices operate in a normally-off mode. Based on an application-specific figure of merit, device~D1 achieves 5\,pC$\cdot$ohm, demonstrating 2$\times$ greater switching efficiency than device~D2, while both designs outperform industrial benchmarks from different performance standpoints.

---

### IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages

Authors: Ikhlasul Akmal Hanif, Muhammad Falensi Azmi, Filbert Aurelian Tjiaranata, Eryawan Presma Yulianrifat, Fajri Koto
Published: 2026-05-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.01260v1

Despite being home to more than 1300 ethnic groups and 700 indigenous languages, bias in Large Language Models has not been fully studied in Indonesia, thus leaving a critical gap in evaluating representational fairness and localized stereotypes within its uniquely vast, multilingual, and diverse sociocultural landscape. To address this, we introduce IndoBias as a culturally-grounded bias benchmark to assess LLMs bias in Indonesian and three local languages: Javanese, Sundanese, and Makasar. IndoBias features dual perspective evaluation tracks: depth-oriented (with contrastive-pairs) and breadth-oriented (with generation-based), where the latter is grounded in social science frameworks (SPI, O*NET, and WGI). Our results show that existing LLMs -- particularly decoder models -- exhibit strong bias towards prototypical sentences in Indonesian, while local languages suffer higher bias under Ideology and Religion category. We also find that LLMs responses exhibit a non-uniform Stereotype Polarity when prompted with various local entities. Finally, we discover that, in Indonesian, Common Crawl texts introduce more bias during pretraining, compared to human-reviewed article texts (e.g., Wikipedia, News), whereas introducing local languages to pretraining generally increases bias. This work highlights the importance of studying bias in culture-specific context. Warning: This paper contains example data that may be offensive, harmful, or biased.

---

### Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding

Authors: Athanasios Zeris
Published: 2026-05-31
Categories: cs.LG, cs.CL, eess.SP
arXiv: https://arxiv.org/abs/2606.01258v1

Standard positional encodings for transformers - sinusoidal and rotary (RoPE) - treat every position as equally local: they encode where a token is, but not how far its positional influence should extend. We propose that the Morlet wavelet, which simultaneously minimises uncertainty in position and frequency, is the natural basis for positional encoding, and introduce Morlet Positional Encoding (MoPE): each embedding dimension learns its own frequency and locality bandwidth from data. The main theoretical result is a unification: sinusoidal PE and the RoPE correlation kernel both emerge as limiting cases of MoPE when locality is switched off (sigma_i -> infinity). The phase of MoPE recovers the RoPE rotation angle exactly; the amplitude adds a learned Gaussian locality kernel that standard encodings lack. Empirically, MoPE combined with Energy-Gated Attention achieves +0.119 improvement over standard attention on TinyShakespeare, outperforming either component alone. Analysis of the learned parameters reveals that all 128 frequency-bandwidth pairs converge to the wavelet admissibility boundary - an empirical observation consistent with a companion result on energy gating, suggesting a reproducible property of character-level language signals that warrants further investigation.

---

### Statistical Inference on Gradient Flows

Authors: Tongyu Li, Alexander Giessing
Published: 2026-05-31
Categories: math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2606.01257v1

Gradient-based algorithms are central to modern statistical estimation, yet their statistical analysis is often restricted to fixed-time behavior, such as convergence to a population target or fluctuations at a prescribed iteration. In many applications, however, uncertainty quantification is needed along the entire optimization path, especially when the stopping time is data-dependent or divergent. In this paper, we develop a theory for time-uniform statistical inference on gradient flows arising from empirical risk minimization. We prove a uniform central limit theorem that characterizes the deviation between empirical and population gradient flows as a continuous-time Gaussian process over the entire nonnegative real line. Building on this result, we introduce an algorithm-aware covariance estimator that evolves jointly with the gradient flow and avoids matrix inversion, resampling, or sample splitting. We show that the covariance estimator is uniformly consistent over time and use it to construct confidence intervals for the target parameter with asymptotically valid coverage. Our results connect optimization dynamics with statistical inference and provide practical tools for uncertainty quantification in gradient-based methods.

---

### Distribution-free changepoint localization after sequential change detection

Authors: Aytijhya Saha, Aaditya Ramdas
Published: 2026-05-31
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2606.01256v2

This paper introduces a distribution-free framework for constructing post-detection confidence sets for changepoints after stopping a sequential change detection procedure. It is well known that conformal test martingales can be used to sequentially detect changes in distribution, but by themselves provide no inference for the time at which a proclaimed change occurred. Past work on post-detection inference requires pre- and post-change classes of distributions to be known, but this paper accomplishes localization of the changepoint without any distributional assumptions. We establish finite-sample coverage guarantees (conditional on correct detection). We provide non-asymptotic bounds on the conditional expected size of the confidence sets. Under suitable asymptotic regimes, we prove that the conditional expected size of the confidence set remains uniformly bounded and demonstrate strong empirical performance on simulated and real data. To the best of our knowledge, this is the first general distribution-free framework for sequential changepoint localization with valid post-detection coverage.

---

### Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement

Authors: Simon Löwe, Emily Silcock
Published: 2026-05-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.01255v1

Recent text-clustering methods use large language models to propose a cluster taxonomy from a corpus and then assign each text to it. These pipelines are fundamentally programmatic: the sequence of LLM calls and the rules for stopping, merging, and splitting clusters are fixed in code in advance, so they generalise poorly across corpora of different structure and cannot easily incorporate user-supplied constraints such as a target cluster count or a clustering intent. We propose an agentic alternative in which an orchestrator LLM inspects the state of the discovery process at each step and dispatches one of a small set of specialised agents - proposer, synthesizer, auditor, investigator, and critic - adapting the pipeline to the corpus rather than executing a fixed one. On seven public text-clustering benchmarks the method achieves state-of-the-art performance, beating the strongest prior LLM baseline by up to 32% in ARI.

---

### Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

Authors: Sangwon Ryu, Yihong Liu, Mingyang Wang, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee, Hinrich Schuetze
Published: 2026-05-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.01252v1

Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as users consume content in diverse languages, but remains underexplored. To address this gap, we introduce multi-target cross-lingual element-aware (MEA), a new MTXLS benchmark covering 24 target languages. We benchmark end-to-end and pipeline approaches across various LLMs and show that MTXLS performance still substantially lags behind English monolingual summarization. To better understand MTXLS in LLMs, we propose a layer-wise analysis framework for investigating how LLMs internally perform MTXLS. Our analyses suggest that translation and summarization behaviors emerge jointly within later layers rather than as distinctly decomposed stages. Most task-relevant processing occurs within these layers, and errors also tend to arise at similar depths. Motivated by these findings, we introduce an inference-time activation steering method that leverages hidden representations from English summarization to guide MTXLS generation. Experiments show that our method consistently improves MTXLS quality across target languages.

---

### Trust Region On-Policy Distillation

Authors: Xingrun Xing, Haoqing Wang, Boyan Gao, Ziheng Li, Yehui Tang
Published: 2026-05-31
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2606.01249v3

On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhancement, and model compression. However, OPD training becomes unstable when the teacher and student distributions differ substantially, as teacher supervision on student-generated tokens may yield unreliable policy gradients and even cause optimization failure. This work addresses reliable on-policy token-level supervision through credit assignment strategies, and proposes Trust Region On-Policy Distillation, TrOPD. It features the following characteristics: 1) Trust-Region On-Policy Learning: TrOPD performs OPD only in regions where the teacher provides reliable supervision, mitigating the optimization difficulty of the K1 reverse-KL estimator under distribution mismatch. 2) Outlier Estimation: For outlier regions, we explore gradient clipping, masking, and forward-KL estimation to reduce the adverse effects of unreliable supervision. 3) Off-Policy Guidance: The student continues generation from teacher prefixes and uses forward KL to imitate off-policy guidance, encouraging on-policy exploration toward reliable regions. Experiments show that TrOPD consistently outperforms SoTA OPD baselines, including OPD, EOPD, and REOPOLD, across mathematical reasoning, code generation, and general-domain benchmarks.

---

### Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

Authors: Liyang Li, Muzhi Zhu, Zhiyue Zhao, Hengyu Zhao, Ke Liu, Linhao Zhong, Hao Chen, Chunhua Shen
Published: 2026-05-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.01247v1

Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passive understanding of pre-collected observations. We introduce Target Viewpoint Reproduction (TVR) -- an active task where an agent adjusts its viewpoint in a 3D environment until its observation matches a given target image -- and TVRBench, an indoor-simulation benchmark spanning scene scale and target-view visual richness. TVR is far from solved: on the evaluation split, the strongest open-source and closed-source models reach only 7.8% and 12.0% success. Fine-grained analysis identifies two consistent bottlenecks: off-the-shelf models struggle with multi-turn visual history, and performance drops sharply when viewpoint reproduction requires body translation rather than in-place rotation, exposing a gap in mapping spatial discrepancies to embodied movement. To study reducing this gap, we build a unified TVR post-training framework covering expert-trajectory SFT, rationale-supervised CoT-SFT, offline Single-turn GRPO, and on-policy Multi-turn GRPO from live simulator rollouts. Visual-action SFT supplies the main gain, raising a 9B open-source model to 50.8% success; Multi-turn GRPO provides targeted multi-room refinement and reaches 51.4% overall, while CoT supervision and Single-turn GRPO degrade closed-loop performance. These results establish TVRBench as a testbed for measuring and training foundation models that actively perceive and act in 3D environments. Our code, data, and models are available at https://github.com/aim-uofa/TVRBench.

---

### SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

Authors: Leo Luo, Haining Xie, Siqi Shen, Zhipeng Ma, Rui Ling, Hang Xu, Hefeng Jiang, Dingwei Chen, Yang Li, Peng Chen, Jie Jiang
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01246v1

Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough, because the multi-candidate recipe has three coupled weaknesses: 1) sampling more from a single generator produces increasingly redundant candidates, 2) existing pipelines apply one generic correction to every non-clean execution result, while runtime errors, timeouts, and empty results each indicate a different distance from correctness, and 3) existing selectors rely on a single angle such as result-majority voting or pairwise SQL comparison, missing what other angles would have caught. We present SIRIUS-SQL, which addresses all three weaknesses. A difficulty-smoothing RL recipe trains SIRIUS-32B to generate diverse executable SQL candidates, paired with a generalist LLM that fills in gaps left by the specialist. An execution-grounded lifecycle classifies each outcome and applies targeted repair before candidates re-enter the pool. A confidence-gated hybrid selector combines execution-result agreement with pairwise SQL-form judgment, escalating only near-tied cases to a deterministic structural check. SIRIUS-SQL reaches 75.88% on BIRD dev and 91.20% on SPIDER test. Two of three generalist pairings surpass Agentar-Scale-SQL, the strongest published multi-candidate system on BIRD dev.

---

### Variation Spaces for Encoder--Decoder Neural Operators: Approximation and Generalization

Authors: Jia-Qi Yang, Lei Shi
Published: 2026-05-31
Categories: stat.ML, cs.LG, math.FA, math.NA, math.ST
arXiv: https://arxiv.org/abs/2606.01244v2

Inspired by the function-space theory of neural networks, we formulate and analyze a variation space for nonlinear operators between Hilbert spaces, defined through vector-valued Borel measures of bounded variation. We characterize its unit ball as the closed convex hull of a vector-valued single-neuron dictionary in Bochner spaces. For the ReLU activation, the bounded linear operators in this space are precisely the Schatten-$1$ operators, with equivalent norms. For operators in this space, we establish encoder--decoder approximation bounds in the Bochner $L^q$-norm, where the error decomposes into input and output encoding errors and a finite-width term of order $N^{-1/2}$. Under sub-Gaussian assumptions on the input and noise, we further derive high-probability generalization bounds for empirical least squares over path-norm-constrained encoder--decoder networks; the finite-sample contribution to the squared prediction error is of order $K^{-1/2}$ up to logarithmic factors. The finite-width and finite-sample constants are independent of the encoding dimensions and bases, with the latter also independent of the network width. When the encoding errors decay algebraically, these bounds yield algebraic approximation and learning rates, in contrast to the complexity barriers for Lipschitz and Fréchet differentiable operator classes.

---

### Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces

Authors: Jia-Qi Yang, Lei Shi
Published: 2026-05-31
Categories: stat.ML, cs.LG, math.FA, math.NA, math.ST
arXiv: https://arxiv.org/abs/2606.01244v1

We study operator learning using encoder--decoder neural networks. Inspired by the function-space theory of neural networks, we introduce a variation space as an infinite-dimensional structural class for nonlinear operators. This space is defined through vector-valued measures directly on the input and output spaces. For operators in this space, we establish approximation bounds for encoder--decoder two-layer networks in the Bochner $L^q$ norm. The resulting error bound decomposes into the input encoding error, the output encoding error, and a finite-width approximation term of order $N^{-1/2}$, with a constant independent of the input and output encoding dimensions. When the input and output encoding errors decay polynomially in the encoding dimensions, these estimates yield algebraic approximation and learning rates. The results provide an theoretical guarantees for efficient neural operator learning beyond general Lipschitz or Fréchet differentiable operator classes.

---

### Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention

Authors: Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu
Published: 2026-05-31
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.01243v1

Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper bridges the gap between mechanistic interpretability and actionable control. We first present a systematic analysis using structural, causal, and geometric probes, revealing that latent vectors encode compressed, faithful representations of reasoning steps, with early vectors acting as critical causal hubs. Building on this, we operationalize these interpretability insights into a suite of training-free, decode-time interventions that refine the latent reasoning process by imposing the identified geometric and semantic priors. Extensive experiments across multiple model scales and diverse task domains demonstrate that our approaches consistently improve reasoning accuracy. Our interpretability-guided interventions consistently unlock latent capabilities and improve reasoning accuracy without any parameter updates.

---

### Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking

Authors: Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang, Zhicheng Wang, Hafiz Shakeel Ahmad Awan, Rizwan Qureshi, Jewon Lee, Tae-Ho Kim, Yang Yang
Published: 2026-05-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.01240v1

The demand for powerful instruction following and reasoning capability of large language models (LLMs) has promoted rapid development of retrieval-augmented generation (RAG). The RAG system assists LLM generation by retrieving chunks of query-fit supplementary knowledge from an external database. Conventional RAG systems, however, suffer from information insufficiency due to two factors, which are intent-agnostic retrieval and information fragmentation. Our work proposes a RAG framework, termed InSemRAG, that addresses these challenges via an iterative retrieve-and-check mechanism with two supporting modules, an intention-aware retriever (IAR) and semantics-preserving chunking (SPC). IAR implements a dynamic hybrid retrieval method that adaptively weights the retrieval channels based on the query intent, while SPC performs detection and reparation to the damaged evidence chunks to preserve the semantic integrity. To alleviate the computational latency brought by our iterative mechanism, we leverage small language models (SLMs). Extensive experiments across several benchmark datasets consistently demonstrate the competitiveness of our method against recent state-of-the-art RAG mechanisms. Particularly, our method achieves significant gains on multi-hop and evidence-sensitive tasks, with a 2.65-point improvement in F1 on HotPotQA and a 1.5-point increase in accuracy on FEVER. Our method also achieves competitive performance to Multi-Hop RAG with 4.32$\times$ lower latency with the utilization of SLM.

---

### Functional Clustering of Survival Data via Smoothed Log-Hazard Trajectories: A Risk-Dynamics Perspective

Authors: Anna De Magistris, Elvira Romano, Fabrizio Maturo
Published: 2026-05-31
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2606.01239v1

This paper investigates clustering in survival data by shifting the analytical focus from cumulative survival probabilities to instantaneous risk, as characterized by the hazard function. We model smoothed log-hazard trajectories as functional objects that capture the temporal evolution of risk and propose a clustering framework based on Functional Principal Component Analysis applied to B-spline smoothed log-hazard trajectories. The number of retained functional principal components is selected before clustering using a 95% cumulative explained-variance rule, and clustering is then performed on the unstandardized FPCA scores. The proposed methodology is evaluated through simulation studies covering progressively complex scenarios, including overlapping and crossing hazard functions, cohort imbalance, heterogeneous risk profiles, and outlier contamination. The framework is further illustrated on two real-world clinical datasets, the German Breast Cancer Study and the Primary Biliary Cirrhosis dataset. Results show that the proposed log-hazard-based functional clustering framework provides an interpretable representation of relative temporal risk dynamics, with competitive internal cohesion and explicit robustness diagnostics when compared with cumulative-survival-based benchmarks.

---

### Training-Free Imitation Learning with Closed-Form Diffusion Policies

Authors: Raghav Mishra, Ian R. Manchester
Published: 2026-05-31
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2606.01238v1

While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy deployment loop. We introduce Closed-Form Diffusion Policies, a class of training-free diffusion-based policies for imitation learning using the closed-form score derived from the demonstration dataset. We deploy CFDP with real-time inference with a mobile CPU in hardware experiments, showing it can successfully perform imitation directly from the dataset in milliseconds and with faster inference than neural diffusion policies. In experiments on imitation learning benchmarks, we show that CFDP is competitive against neural baselines that require hours of training, providing a favorable tradeoff between training time and performance. Finally, we show how closed-form diffusion policies act as a composable primitive that enables data-driven inference-time editing of pre-trained neural diffusion policies, including policy guidance and novel demonstration augmentation.

---

### Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline Diagnosis Using Multimodal Connectomes

Authors: Xiongri Shen, Jiaqi Wang, Zhenxi Song, Yi Zhong, Leilei Zhao, Xin He, Baiying Lei, Zhiguo Zhang
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01237v1

Mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are closely associated with the early Alzheimer's disease continuum, where accurate and explainable diagnosis is important for early risk assessment and intervention. Existing connectome-based deep learning models can improve classification performance but often provide limited insight into disease-related functional and structural connectivity changes. This paper proposes an atlas-knowledge-guided Generative Counterfactual Attention-guided Network (GCAN) for explainable cognitive decline diagnosis using multimodal brain connectomes. GCAN formulates diagnosis as a source-to-target counterfactual generation problem, where target-label connectomes are generated from source-label inputs and their differences are used to construct counterfactual attention maps. To preserve connectome topology, an Atlas-aware Bidirectional Transformer (AABT) performs network-level token encoding and decoding under brain-atlas constraints. The framework is further extended from functional connectivity (FC) to joint functional and structural connectivity (SC) modeling, enabling counterfactual analysis of complementary functional reorganization and structural topology changes. Experiments on hospital-collected and ADNI datasets show that GCAN achieves competitive performance across HC vs. SCD, HC vs. MCI, and SCD vs. MCI classification tasks. Visualization, circular connectome analysis, CAM-based comparison, ablation studies, and confidence interval analysis further support the interpretability and reliability of the proposed framework. Modality-specific FC and SC pre-trained classifiers are used to provide target-state priors for counterfactual generation while being separated from the downstream diagnostic classifier to prevent data leakage.

---

### Differing Roles of Leisure and Productivity in GDP - A Machine Learning based comparative analysis of Germany and USA

Authors: Achintya Ranjan, Uma Ranjan
Published: 2026-05-31
Categories: econ.GN, cs.CE, cs.CV, cs.GT, cs.LG, physics.soc-ph
arXiv: https://arxiv.org/abs/2606.01234v1

The GDP of a country is modelled as the relative interaction between two agents - working hours, reflecting the social choice of a population, and Total Factor Productivity, reflecting the collective investment in productivity enhancers. It is shown that a Random Forest model can accu- rately predict the GDP from these two factors. The differences in the choices made by Germany and USA are analysed though Gini importance, SHAP plots and partial dependency. It is shown that the differences in the social structure of the countries are reflected in the relative contribution of working hours and productivity to the GDP.

---

### HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation

Authors: Yi Gu, Huacan Wang, Shuo Zhang, Yuqing Hou, Lei Xue, Weipeng Ming, Chen Liu, Fangzhou Yu, Kuan Li, Ronghao Chen, Sen Hu, Xiaofeng Mou et al.
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01230v1

Large language model agents are moving beyond text-only interaction toward physical-world control, with smart homes as a representative domain. Real domestic interaction requires understanding ambiguous intents, operating in dynamic environments, and performing multi-turn reasoning. However, existing methods struggle to generate high-quality training data for smart home agents. We propose HomeFlow, a verifiable data flywheel for this domain. HomeFlow uses HomeEnv as a unified simulation environment and HomeMaker to procedurally generate diverse home settings. Subsequently, Blueprint compiles open-ended user intents into executable state-based success conditions, while MCTS-Flow synthesizes diverse, verifiable multi-turn trajectories through environment-guided tree search. We then optimize the agents via supervised fine-tuning and step-wise RLVE, which facilitates iterative improvement through authentic physical feedback. We further construct SmartHome-Bench to evaluate the agent across various smart home tasks. On this benchmark, HomeFlow-RL-4B and HomeFlow-RL-8B achieve task success rates of 84.60% and 87.03%. It is worth noting that HomeFlow-RL-8B even surpasses the leading GPT-5.5 by 1.23 percentage points.

---

### Application of Algorithms in Energy-Efficient Design Platforms for Green Building

Authors: Na Yu, Fu Wenli, Guo Fei
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01229v1

During green building design, computer-aided energy assessment is widely used to improve efficiency and achieve overall optimization. This paper presents a platform that combines Building Information Modeling (BIM), sensor operational data, and advanced simulation workflows using robust algorithms. The platform uses a multi-layer service architecture with dynamic energy simulation and evolutionary multi-objective optimization, connected via a high-performance C++ core and adaptive agent models. A mid-rise office building was selected as the case study. Five representative areas were chosen to collect data on building envelope characteristics and occupancy patterns. After preprocessing, missing sensor data accounted for 3.2% of annual records, and all variables were standardized using 15-minute interpolation. After 40 optimization rounds, annual energy consumption per square meter dropped by 29.3% from 315 kWh/m2 to 223 kWh/m2. The lifecycle cost increase for occupants was limited to 3.7%, and discomfort hours were reduced to under 70 hours per year. Analysis of Pareto optimal solutions shows that the envelope U-value ranges from 1.05 to 1.57 W/m2K, and nighttime ventilation rate ranges from 2.1 to 3.6 h-1, both closely linked to energy performance. The results confirm that the integrated algorithm framework offers good scalability, strong performance, and technical feasibility for green building design. This platform provides a reliable decision-support tool for design engineers and sustainability practitioners, enabling accurate, data-driven delivery of energy-efficient buildings.

---

### DAGGER: Gradient-Free Construction of Transiently Amplifying Networks under Hard Connectivity Constraints

Authors: James C. Ferguson
Published: 2026-05-31
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2606.01227v1

Many networks not only support but also rely on transient non-normal amplification, an orders-of-magnitude increase in the activity of an otherwise stable system. Constructing such networks under hard sign/sparsity/diagonal constraints -- the regime relevant for biological connectomes and structured RNN initializations -- has so far required either gradient-based local search with thousands of inner-loop eigendecompositions or Schur-form direct construction in an abstract basis that breaks the constraints under projection. Here we introduce DAGGER (Directed Acyclic Graph Guided Edge Reweighting), a gradient-free single-pass algorithm. Given a stable signed sparse matrix, DAGGER produces an output with the same sign, sparsity, and diagonal. A single scalar $β$ controls a Wasserstein-2 budget that smoothly trades exact multiset preservation ($β= 0$) for amplification; peak amplification grows essentially without bound with $β$, empirically reaching $10^{10}$ before numerical overflow. DAGGER matches or exceeds gradient-based methods at multiset preservation in a single forward pass -- 30-100$\times$ fewer eigendecompositions than a typical gradient inner loop -- and at moderate $β$ beats them by orders of magnitude with connectivity exactly preserved. We develop the algorithm, compare it to the existing methods and on a downstream signal-detection task, and examine the diagnostics that show why DAGGER is structurally different from other amplifying networks.

---

### Advanced Mathematics Learning Behavior Prediction and Academic Early Warning Model Based on Multimodal Data Analysis

Authors: Liu Qiong, Li Zhengbo
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01224v1

Early detection of at-risk students and timely academic intervention pose major challenges in advanced mathematics education, where complex conceptual hierarchies and nonlinear learning trajectories often hold back students' academic performance. This study adopts multimodal data analytics to build a dynamic framework for learning behavior prediction and academic early warning. It constructs a hierarchical knowledge graph ontology, realizes adaptive edge weighting according to problem difficulty and student performance, and combines heterogeneous graph attention with temporal sequence modeling to capture students' evolving knowledge states. Empirical tests on semester-long multimodal datasets prove that this method can accurately identify high-risk students and effectively track error propagation. Targeted interventions greatly improve students' knowledge mastery and reduce academic risks. The results verify that integrating knowledge graph analytics with multimodal temporal modeling can deliver more efficient and personalized learning support for advanced mathematics education.

---

### Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue

Authors: Jingjie Lin, Bingbing Wang, Zihan Wang, Zhengda Jin, Weiming Qiao, Jing Li, Ruifeng Xu
Published: 2026-05-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.01223v1

Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations. To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue. RefMem-Bench contains 26K annotated QA instances with eight reflective-memory dimensions and three task formats, requiring models to move beyond surface-level retrieval and infer latent meanings from evidence distributed across interaction histories. To enhance reflective memory capability, we propose REflective Memory INDuction (REMIND), a hierarchical framework that treats reflective memory as progressive meaning construction. REMIND couples question-conditioned evidence retrieval, salience-aware grounding, and abstraction-level supervision, and uses Progressive Reflective Alignment to distill high-level reflective reasoning into the factual inference pathway. Experiments show RefMem-Bench poses a substantial challenge to current models, while REMIND consistently improves both answer accuracy and memory recall through progressive evidence perception, grounding, and abstraction.

---

### Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancing

Authors: Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi
Published: 2026-05-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.01221v1

Imbalanced learning is a critical challenge in machine learning, where underrepresented target values can bias models and degrade prediction performance on rare but important cases. Although extensively studied in classification, imbalanced regression remains relatively underexplored. Existing methods mainly focus on either data-level balancing, which may introduce noise and overfitting, or algorithm-level balancing, which often struggles with highly complex target distributions. To address these limitations, we propose a unified hybrid framework that integrates both data- and algorithm-level balancing strategies into a regressor-agnostic pipeline. The proposed framework consists of five stages: (1) adaptive bin partitioning to dynamically segment the target space based on local linear coherence; (2) target-conditioned representation learning using a Conditional Variational Autoencoder; (3) multistage data-level balancing through feature-space clustering and oversampling of minority clusters; (4) algorithm-level balancing using a novel Latent-Density Weighted Loss (LDWL) to emphasize rare samples in latent and target spaces; and (5) attention-based gated fusion for final regression. Experimental results on benchmark datasets demonstrate that the proposed framework consistently improves predictive performance compared to standalone regressors and existing imbalanced regression approaches.

---

### Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling

Authors: Guang Lin, Shikui Tu, Lei Xu
Published: 2026-05-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.01220v1

Generating molecules that simultaneously satisfy drug-like properties and conform to the 3D structure of a target protein is a core challenge in structure-based drug design (SBDD). Existing generative approaches, however, often rely on costly post-hoc processing during Sampling or require carefully curated datasets during training, yet still achieve modest gains. These limitations are especially pronounced in multi-objective settings, where balancing conflicting criteria remains a core challenge. To address these challenges, We propose FTDiff, a reinforcement learning fine-tuning framework tailored for diffusion-based molecular generation under structural constraints. To ensure stable and sample-efficient optimization, FTDiff adopts a group relative policy optimization (GRPO) style strategy. Furthermore, FTDiff builds upon a time-free pretrained diffusion model and incorporates a fast sampling mechanism that reduces the number of denoising steps, significantly accelerating both training and inference while maintaining generation quality. By optimizing a fixed threshold-aware reward, FTDiff effectively guides the model to produce valid, diverse, and high- quality molecules that balance multiple drug design objectives. Extensive experiments on benchmark datasets demonstrate that FTDiff consistently outperforms prior methods, without requiring expensive post-hoc optimization or intricate data engineering.

---

### Analysis of Ethnic Disparities in Autism Spectrum Disorder among Toddlers

Authors: Aadithya Prabha Ramaharsha, Deevna Reddy, Uma Ranjan
Published: 2026-05-31
Categories: cs.CV, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2606.01217v1

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by challenges in communication and behavior. This study examines the relationship between ethnicity and ASD traits, along with behavioural scores, sex and neonatal jaundice across three ethnic groups: White Europeans, Asians, and Middle Eastern individuals. We perform a logistic regression and show that ethnicity has a significant effect on incidence of ASD. White Europeans are 81% increased risk of ASD and Middle Easterners are at 79\% reduced risk of ASD compared to Asians. We also confirm earlier studied which show that neonatal jaundice is a significant predictor of ASD, while male children are at much higher risk of ASD compared to female children. These results suggest the need for diagnostic frameworks and interventions that account for ethnic in the presentation and assessment of ASD traits

---

### Riemannian Optimization for Hadamard Products of Low-Rank Matrices

Authors: Pratik Jawanpuria, Ankish Chandresh, Bamdev Mishra
Published: 2026-05-31
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2606.01216v2

The elementwise Hadamard product of two low-rank matrices provides a parameter-efficient model for data with multiplicative structure, but its modeling is challenging due to the presence of additional symmetries under coupled row/column scalings between the two factors. In order to leverage the geometry of the space, we formulate the learning of such matrices as optimization on a Riemannian quotient manifold. We propose a novel block-diagonal Riemannian metric derived from the pullback of the Frobenius inner product. The metric is shown to be invariant under these symmetries. We develop a Riemannian gradient descent algorithm that uses a tuning-free Gauss--Newton step size and scales linearly in the number of observed entries per iteration. The versatile framework of Riemannian quotient optimization enables both first-order and second-order Riemannian methods, the latter through a closed-form connection and the Riemannian Hessian. Experiments on real and synthetic datasets illustrate the efficacy of our proposed Riemannian approach.

---

### Riemannian Optimization for Hadamard Products of Low-Rank Matrices

Authors: Pratik Jawanpuria, Ankish Chandresh, Bamdev Mishra
Published: 2026-05-31
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2606.01216v1

The elementwise Hadamard product of two low-rank matrices provides a parameter-efficient model for data with multiplicative structure, but its modeling is challenging due to the presence of additional symmetries under coupled row/column scalings between the two factors. In order to leverage the geometry of the space, we formulate the learning of such matrices as optimization on a Riemannian quotient manifold. We propose a novel block-diagonal Riemannian metric derived from the pullback of the Frobenius inner product. The metric is shown to be invariant under the full symmetry group. We develop a Riemannian gradient descent algorithm that uses a tuning-free Gauss--Newton step size and scales linearly in the number of observed entries per iteration. Experiments on real and synthetic datasets illustrate the efficacy of our proposed Riemannian approach.

---

### Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs

Authors: Wentao Mo, Yang Liu
Published: 2026-05-31
Categories: cs.CV, cs.AI, cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2606.01215v2

Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification. We introduce APEIRIA, a neuro-symbolic 3D MLLM to bridge two paradigms by distilling symbolic reasoning patterns into MLLMs with natural language chain-of-thought. Our three-stage curriculum progressively builds reasoning capabilities: a) 3D perception alignment grounds object visual-geometric features to the LLM, b) CoT-SFT teaches query decomposition and stepwise verification from symbolic program traces, and c) CoT-RL extends reasoning patterns to open-set concepts and deeply nested instructions. By transferring reasoning patterns rather than concept-specific knowledge, APEIRIA preserves key NS3D virtues: transparent reasoning and modular interchangeability of planning and perception components. Evaluations on grounding, question answering, and captioning show that APEIRIA surpasses prior NS3D methods and matches state-of-the-art 3D MLLMs on 3D spatial reasoning datasets, unifying symbolic methods' systematic reasoning with MLLMs' flexibility. Code is available at https://github.com/oceanflowlab/APEIRIA.

---

### TECCI: Tricky Edits of Collected and Curated Images

Authors: Aishwarya Agrawal, Roy Hirsch, Yasumasa Onoe, Sherry Ben, Jason Baldridge
Published: 2026-05-31
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.01213v1

Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction following, minimally editing the source image, and ensuring high visual quality. These problems are especially apparent when the requested edit is challenging, such as those that involve position, motion, viewpoint, scale and creative edits. To systematically test generative image editors, we propose a novel image editing benchmark -- TECCI: Tricky Edits of Collected and Curated Images. TECCI consists of a completely new set of images we are releasing. The images in TECCI span 7 image categories. The images and these categories were curated intentionally to target weaknesses of existing methods. The edit instructions in TECCI are automatically generated by Gemini, covering 5 edit types per source image. We also curated a set of 530 images for which we created challenging manually written edit instructions. Overall, TECCI contains 7550 pairs of images and edit instructions. We conduct human evaluations of five leading image editing models on TECCI. Humans judge outputs along three dimensions: 1) instruction following, 2) minimality of the edits, and 3) visual quality. To scale-up the evaluation, we also build an auto-rater using Gemini that achieves 74.7% accuracy in matching human evaluations. Our evaluations reveal that: 1) none of the models exceed a 22% overall success rate, demonstrating the challenging nature of TECCI, 2) Nano Banana Pro is the best performing model overall, 3) models perform significantly better at instruction following compared to minimal edits and visual quality, 4) models struggle with editing architecture and nature images which require strong understanding of spatial layout and intricate visual details. 5) reasoning and creative edits are the most difficult, whereas color and appearance edits are the easiest.

---

### DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation

Authors: Yuyang Gong, Miaokun Chen, Jiawei Liu, Zhuo Chen, Guoxiu He, Wei Lu, XiaoFeng Wang, Xiaozhong Liu
Published: 2026-05-31
Categories: cs.CL, cs.AI, cs.CR, cs.IR
arXiv: https://arxiv.org/abs/2606.01212v2

Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retrieval content. Existing RAG attacks are largely focusing on individual queries or narrow topic-local query sets, which limits their practical reach and offers limited camouflage in real-world settings. In this paper, we introduce discourse-level opinion manipulation, a new threat model in which coordinated influence across a semantic query network induces opinion shifts over a holistic, multi-topic query space. We formalize this threat in a black-box setting and propose DiscourseFlip, an agentic, graph-guided attack that dynamically allocates a limited poisoning budget to maximize discourse-level opinion deviation. Extensive experiments demonstrate that DiscourseFlip consistently induces targeted opinion shifts across the contextualized query network and significantly outperforms existing baselines in terms of coverage and effectiveness. User studies further confirm that DiscourseFlip is effective while remaining well camouflaged from user detection. Moreover, systematic analyses show that existing mitigation strategies are ineffective against discourse-level manipulation, underscoring the urgent need for more robust and adaptive defenses to address discourse-level vulnerabilities.

---

### Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning

Authors: Zhiqiang Zhou, Xuezhen Xie
Published: 2026-05-31
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.01207v1

The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding. In this paper, we demonstrate that feature alignment quality, not data scale alone, is the primary determinant of which fusion strategy excels. Through controlled experiments on Flickr8k using two feature extraction backbones (ResNet18 and CLIP ViT-B/32), we show that concatenation outperforms cross-attention by 4.1-5.1 percentage points across all tested scales (2048-16384 samples) when features are pre-aligned by a vision-language pretraining objective. We provide a theoretical explanation grounded in sample complexity analysis: concatenation requires O(d_v + d_t) samples to learn its fusion projection, while cross-attention requires O(d_v * d_t) samples to learn bilinear attention weights, over 256 times as many for 512-dimensional CLIP features. When features are already aligned, the approximation error gap between the two methods vanishes, and concatenation's sample efficiency dominates at all practical dataset sizes. An alignment degradation study confirms a monotonic trend: as feature alignment degrades, concatenation's advantage grows from 1.3% to 2.8%. These findings provide a principled decision framework for fusion method selection in multimodal systems, with direct implications for the design of Multimodal Large Language Models.

---

### Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations

Authors: Qi Han Wong
Published: 2026-05-31
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2606.01204v1

We investigate whether large language models produce different medical triage recommendations for identical symptoms based solely on the language of the patient prompt. Using Gemini 3.5 Flash, we evaluate a neurological symptom profile (persistent headache, blurred vision, nausea) across six languages (English, Spanish, Chinese, Hindi, Japanese, Arabic) with 30 runs per condition (n=450 total API calls). We find that the model recommends emergency room visits at rates ranging from 0% (Japanese, Hindi) to 30% (English, Arabic), despite assigning nearly identical severity scores (7.7-8.0/10) across all languages. Adding a single sentence specifying the patient's US location increases ER recommendations by up to 76.7 percentage points for non-English prompts, while the reverse anchor (English prompt with a Tokyo location) reduces the ER rate from 30% to 6.7%. A back-translation control (Japanese to English) produces ER rates comparable to the English baseline, confirming that the disparity is not caused by translation quality but by implicit geographic inference from the input language. We release the complete dataset, experiment code, and results.

---

### The Shape of Wisdom: Decision Trajectories in Language Models

Authors: Shailesh Rana
Published: 2026-05-31
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.01202v1

Language models do not simply choose an answer at the output layer. In a 9,000-trajectory MMLU study across Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, and Mistral-7B-Instruct-v0.3, the score of the answer moves across depth in structured ways. We describe each trajectory with three quantities: the current answer margin, the next-layer change in that margin, and the distance from a decision flip. The main empirical picture is that correctness and stability are different: the largest group is unstable-correct, not stable-correct. A traced subset then asks what moves the margin. In stable-correct cases, the average attention scalar points in the correct direction, while the average MLP scalar does not; span deletion shows that removing answer-supporting text hurts the margin and removing distractor-like text helps it. The result is not a full circuit explanation. It is a reproducible way to see which answers are settled, which remain fragile, and which measured sources move them.

---

### Can LLM Agents Sustain Long-Horizon Organizational Dynamics?

Authors: Xuancheng Zhu, Yang Yue, Shuaibing Wan, Zihan Dou, Xiaohan Zhang, Yongrui Liu, Guoshun Nan
Published: 2026-05-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.01199v1

Large language agents are increasingly used for social simulation, yet it remains unclear whether they can sustain coherent behavior in structured organizations, where goals must propagate through hierarchy, tasks depend on prior execution, and artifacts accumulate over long horizons. We formulate long-horizon organizational simulation as a memory-centered coordination problem and introduce TaskWeave, a hierarchical agentic framework that maintains planning states through a Formulate-Partition-Diagnose-Align cycle and grounds execution through dependency-aware trace memory. We evaluate TaskWeave in a year-long IT company simulation and compare it with other multi-agent frameworks on organizational coherence, execution grounding, and downstream enterprise NLP utility. Experiments show that TaskWeave supports coherent and long-horizon organizational dynamics while producing grounded artifacts and adapting to external environments. These findings suggest that structured simulation memory is a key mechanism for building reliable LLM-based organizational simulators.

---

### Linear Strategic Classification with Endogenous Improvements

Authors: Siddharth Shrivastava, Mahvith Akshintala, B Vamsha Vardhan Reddy, Naresh Manwani, Sujit Gujar, Ganesh Ghalme
Published: 2026-05-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.01198v2

Strategic classification studies settings in which agents respond to a deployed classifier by modifying observable features at a cost. Classical models typically treat such responses as cosmetic: features may change, but true labels remain fixed. We study an improvement-aware variant in which strategic responses can induce genuine changes in outcome-relevant features. Agents choose post-deployment feature vectors strategically, and labels are then generated according to a stable conditional outcome law that preserves the relationship between features and outcomes. We formalize this problem for linear classifiers under a single-index qualification model and linear-decomposable costs. We show that the strategic-optimal classifier is obtained by a parallel shift of the Bayes-optimal decision boundary, and that it provides a better surrogate for the improvement-aware objective than the Bayes classifier. Since improvement-aware learning requires post-deployment labels, which are typically unavailable before deployment, we provide PAC-style guar- antees under an oracle model, propose a practical plug-in algorithm, establish its generalization bound, and evaluate it on synthetic and real-world datasets.

---

### Low-Resource Safety Failures Are Action Failures, Not Representation Failures

Authors: Rashad Aziz, Ikhlasul Akmal Hanif, Fajri Koto
Published: 2026-05-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.01196v1

Safety alignment learned in high-resource languages transfers poorly to low-resource languages. Models refuse harmful prompts in English but fail to refuse when the same prompts are translated into Swahili or Burmese. Adaptive steering methods like AdaSteer and CAST inherit this failure cross-lingually. We diagnose where transfer breaks down. Across Qwen2.5-7B, Gemma-2-9B, and Llama-3.1-8B on 23 languages, the harmfulness direction extracted from high-resource activations linearly separates harmful from harmless low-resource prompts nearly as well as high-resource ones. The relevant representation is present. Yet harmful refusal drops from 87.9% to 43.9%. The model fails to convert the representation into refusal. What fails to transfer is calibration of the safety decision, not the underlying representation. We exploit this by recalibrating, rather than retraining, a high-resource gate: a low-rank logistic readout with its decision threshold reset using as few as 1 to 4 target-language examples per class. The gate routes between refusal steering and harmfulness-direction ablation, substantially raising mean refusal selectivity ($Δ$ = harmful $-$ harmless refusal) from 33.6 for the strongest adapted baseline to 54.5 while preserving MMLU utility. These results suggest that some low-resource safety failures can be repaired by recalibrating existing representations rather than learning new ones. Our code is released: https://github.com/rashadaziz/low-resource-safety.

---