# Research Papers — 2026-05 · bundle page 196 of 326

> Full-text markdown of papers #9751–9800 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/196
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/195.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/197.md)

### Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion

Authors: Shiyu Tan, Zixuan Zhao, Hao Gao, Zhiheng Chen, Xiaolong Yin, Enya Shen
Published: 2026-05-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.13293v1

Boundary Representation (BRep) is the standard format for Computer-Aided Design (CAD), yet reconstructing high-quality BReps from single-view images remains challenging due to the complexity of topological constraints and operation sequences. We present Img2CADSeq, a multi-stage pipeline that overcomes these limitations by encoding CAD sequences into a three-level hierarchical codebook. Guided by an importance prioritization, this strategy values profiles over details, compressing long sequences into a stable discrete latent space. To bridge the modality gap, we leverage a coarse-to-fine point cloud intermediate, aligning 2D visual features with 3D CAD sequences via contrastive learning to condition a VQ-Diffusion model. Supported by newly introduced CAD-220K and PrintCAD datasets, our approach ensures robust industrial domain adaptation. Extensive experiments demonstrate that Img2CADSeq significantly outperforms state-of-the-art methods, producing standard STEP files that can be directly used in commercial CAD software.

---

### IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages

Authors: Shubham Kumar Nigam, Suparnojit Sarkar, Piyush Patel
Published: 2026-05-13
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2605.13292v1

Most existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. We introduce IndicMedDialog, a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Punjabi, Tamil, Telugu, and Urdu. The dataset extends MDDial with LLM-generated synthetic consultations, translated using TranslateGemma, verified by native speakers, and refined through a script-aware post-processing pipeline to correct phonetic, lexical, and character-spacing errors. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation of a quantized small language model, incorporating optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate against zero-shot multilingual baselines, conduct systematic error analysis across ten languages, and validate clinical plausibility through medical expert evaluation.

---

### What properties of reasoning supervision are associated with improved downstream model quality?

Authors: Mikołaj Langner, Dzmitry Pihulski, Jan Eliasz, Michał Rajkowski, Przemysław Kazienko, Maciej Piasecki, Jan Kocoń, Teddy Ferdinan
Published: 2026-05-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.13290v1

Validating training data for reasoning models typically requires expensive trial-and-error fine-tuning cycles. In this work, we investigate whether the utility of a reasoning dataset can be reliably predicted prior to training using intrinsic data metrics. We propose a suite of quantitative measures and evaluate their predictive power by fine-tuning 8B and 11B models on semantically distinct variants of a Polish reasoning dataset. Our analysis reveals that these intrinsic metrics demonstrate strong and significant correlations with downstream model performance. Crucially, we find that the predictors of utility are scale-dependent: smaller models rely on alignment-focused metrics to ensure precision, whereas larger models benefit from high redundancy, utilizing verbose traces to solve complex tasks. These findings establish a scale-aware framework for validating reasoning data, enabling practitioners to select effective training sets without the need for exhaustive empirical testing.

---

### Delightful Exploration

Authors: Ian Osband
Published: 2026-05-13
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2605.13287v1

Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners default to $\varepsilon$-greedy, which bounds disruption but spends its override blindly. We introduce \textit{Delight-gated exploration} (DE), a host--override rule that spends exploratory actions only when their prospective delight (expected improvement times surprisal) exceeds a gate price. This practical heuristic recovers a classical result: Pandora's reservation-value rule for costly search, with surprisal setting the effective inspection cost. Resolved arms exit the gate, fresh arms shut off above a prior-determined threshold, and selected linear-bandit overrides consume finite information budget. Across Bernoulli bandits, linear bandits, and tabular MDPs, the same hyperparameters transfer without retuning, and DE shows much weaker regret growth than Thompson Sampling and $\varepsilon$-greedy in the tested unresolved regimes. Delight improves acting for the same reason it improves learning: it prices scarce resources by the product of upside and surprisal.

---

### Learning Perturbations to Extrapolate Your LLM

Authors: Zetai Cen, Chenfei Gu, Jin Zhu, Ting Li, Yunxiao Chen, Chengchun Shi
Published: 2026-05-13
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.13284v1

Recent advancements in large language models demonstrate that injecting perturbations can substantially enhance extrapolation performance. However, current approaches often rely on discrete perturbations with fixed designs, which limits their flexibility. In this work, we propose a framework where token prefixes are perturbed by a learnable transformation of a continuous latent vector within an embedding space. To overcome the challenge of an intractable marginal likelihood, we derive unbiased estimating equations for model parameters and optimize them via stochastic gradient descent. We establish the statistical properties of the resulting estimator in over-parameterized regimes. Empirical evaluations on both synthetic and real-world datasets demonstrate that our proposal yields significant gains in out-of-domain settings over a range of state-of-the-art baseline methods.

---

### Byzantine-Robust Distributed Sparse Learning Revisited

Authors: Yuxuan Wang, Lixin Zhang, Kangqiang Li
Published: 2026-05-13
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.13283v1

We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression, quantile regression, and sparse SVM. We show that the resulting estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient. Simulations confirm strong robustness in estimation, support recovery and classification accuracy under various Byzantine attacks.

---

### Differentiable Learning of Lifted Action Schemas for Classical Planning

Authors: Jonas Reiter, Jakob Elias Gebler, Hector Geffner
Published: 2026-05-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.13282v2

Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this work, we develop a novel neural network architecture for learning action schemas from traces where states are fully observed but action arguments are unobserved. The problem is a simplification but an important step towards learning planning domains from sequences of images and action labels, and we aim to solve this simplification in a nearly perfect manner. The challenge lies in learning the action schemas while simultaneously identifying the action arguments from observed state changes. Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure. Additionally, we report experiments on robustness to observation noise and on a variation related to slot-based dynamics models.

---

### Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code

Authors: Hengzhi Ye, Fengyuan Ran, Weiwei Xu, Minghui Zhou
Published: 2026-05-13
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.13280v2

Large Language Models (LLMs) are increasingly changing how code is produced, but generated code still requires human review and validation before it can be adapted or integrated into real-world projects. This makes the readability of LLM-generated code a critical concern. Existing studies have mainly focused on functional correctness and task completion of LLM generated code, leaving open questions about whether it is readable, how its readability fails, and to what extent prompt design can improve it. We therefore investigate the readability of LLM-generated code. We first construct a readability assessment model that integrates textual, structural, program, and visual features. Using this model, we compare human-written code with code generated by representative frontier LLMs across 2,735 scenarios derived from World of Code (WoC) and LeetCode. We further characterize readability issue patterns using thematic analysis and examine prompt design associations through controlled prompt-variant experiments. Our results show that current LLMs produce code that is comparable to human-written code in overall readability. However, this aggregate similarity masks distinct issue patterns, including excessive complexity, redundant comments, and unknown API usage. Prompt analysis further shows that function signature, constraints, and style description are most strongly associated with code readability, although the overall role of prompt design remains bounded. These findings reveal latent readability debt in AI-assisted programming, identify prompt design as a lightweight starting point for improving generated-code readability, and motivate automated support for detecting and mitigating readability issues in future development workflows.

---

### Proximal-Based Generative Modeling for Bayesian Inverse Problems

Authors: Boyang Zhang, Zhiguo Wang, Ya-Feng Liu
Published: 2026-05-13
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2605.13278v2

Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the analytical intractability of the time-dependent likelihood score. To bridge this gap, we propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation. Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization. This enables a new sampling mechanism driven by the proposed Moreau score, which admits a closed-form expression via proximal operators. Moreover, we introduce Moreau score matching to learn the proximal operators that rely solely on samples drawn from the prior distribution. Theoretically, PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence. Experiments demonstrate that PGM significantly surpasses state-of-the-art methods in reconstruction quality and sampling time.

---

### Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

Authors: Weiqing Luo, Zongye Hu, Xiao Wang, Zhiyuan Yu, Haofeng Zhang, Ziyi Huang
Published: 2026-05-13
Categories: cs.CL, cs.AI, cs.CV, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2605.13277v1

Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. We reformulate multimodal evidence selection from an information-theoretic perspective by defining evidence utility as the information gain induced on a model's output distribution. To overcome the intractability of answer-space optimization, we introduce a latent notion of evidence helpfulness and theoretically show that, under mild assumptions, ranking evidence by information gain on this latent variable is equivalent to answer-space utility. We further propose a training-free, surrogate-accelerated framework that efficiently estimates evidence utility using lightweight multimodal models. Experiments on MRAG-Bench and Visual-RAG across multiple model families demonstrate that our method consistently outperforms state-of-the-art RAG baselines while achieving substantial reductions in computational cost.

---

### D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models

Authors: Yucheng Guo, Yongjian Guo, Zhong Guan, Wen Huang, Haoran Sun, Haodong Yue, Xiaolong Xiang, Shuai Di, Zhen Sun, Luqiao Wang, Junwu Xiong, Yicheng Gong
Published: 2026-05-13
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.13276v2

The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (RL) to these massive models in large-scale distributed environments faces severe systemic bottlenecks, primarily due to the resource conflict between high-fidelity physical simulation and the intensive VRAM/bandwidth demands of deep learning. This conflict often leaves overall throughput constrained by execution-phase inefficiencies. To address these challenges, we propose D-VLA, a high-concurrency, low-latency distributed RL framework for large-scale embodied foundation models. D-VLA introduces "Plane Decoupling," physically isolating high-frequency training data from low-frequency weight control to eliminate interference between simulation and optimization. We further design a four-thread asynchronous "Swimlane" pipeline, enabling full parallel overlap of sampling, inference, gradient computation, and parameter distribution. Additionally, a dual-pool VRAM management model and topology-aware replication resolve memory fragmentation and optimize communication efficiency. Experiments on benchmarks like LIBERO show that D-VLA significantly outperforms mainstream RL frameworks in throughput and sampling efficiency for billion-parameter VLA models. In trillion-parameter scalability tests, our framework maintains exceptional stability and linear speedup, providing a robust system for high-performance general-purpose embodied agents.

---

### Physics Guided Generative Optimization for Trotter Suzuki Decomposition

Authors: WenBin Yan
Published: 2026-05-13
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.13268v2

Trotter Suzuki product formulas are the standard route to Hamiltonian evolution on noisy intermediate-scale quantum (\NISQ{}) hardware, but their accuracy depends on three coupled choices: term grouping, product-formula order, and time-step allocation. Grouping and order are discrete, which makes direct gradient optimization infeasible and forces existing compilers to rely on static heuristics. We describe P-GONE, a method that combines a conditional diffusion model (D3PM + DDPM), a graph neural network (\GNN{}) encoder, and closed-loop REINFORCE fine-tuning to jointly learn grouping, order, and time-step optimization over a mixed discrete-continuous space. Under fidelity-matched conditions ($F \geq 0.95$), the method achieves circuit depth 86 versus 1673 for Qiskit fourth-order (ungrouped, Suzuki-4), about $19.4\times$ compression, and 141 for Paulihedral (first-order Trotter), about $1.6\times$ compression. At $T=0.90$ the method also beats the Qiskit group-commuting teacher (65 vs 103, $1.6\times$ compression), though at $T=0.95$ the teacher still leads -- a stratified pattern that points toward fidelity-aware fine-tuning. Under a standard depolarizing noise model, the method achieves noisy fidelity roughly $2\times$ the Qiskit fourth-order baseline (0.743 vs 0.380). Ablation shows a clear hierarchy: order learning $>$ time allocation $>$ grouping. Best-of-N sampling ($N=32$ is a practical sweet spot) and CFG guidance give flexible fidelity-depth trade-offs at inference. The method works well on structured Hamiltonians (TFIM, Heisenberg), but random Pauli Hamiltonians fail entirely at $T \geq 0.95$ -- a boundary that defines where the method applies.

---

### LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections

Authors: Mert Cihangiroglu, Alessandro Pegoraro, Phillip Rieger, Antonino Nocera, Ahmad-Reza Sadeghi
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13265v1

Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication overhead while exposing representations vulnerable to reconstruction attacks. Existing approaches typically address efficiency or privacy in isolation, relying on additional mechanisms such as sparsification, quantization, or noise injection. We propose LightSplit, which limits information exposure and reduces communication overhead by applying a lightweight fixed orthogonal random projection at the cut layer. Based on Shannon's information theory, this projection acts as an information bottleneck that restricts instance-specific information and suppresses exploitable per-sample signals. By transmitting low-dimensional projections instead of raw activations, the server operates on lifted representations without requiring architectural modifications, ensuring compatibility with existing SL architectures. By avoiding additional trainable components on the client, the method remains lightweight and suitable for edge devices while preserving end-to-end differentiability via exact gradient propagation. As the projection is non-invertible, part of the original representation is irreversibly discarded at the client, LightSplit reduces the information available for reconstruction and limits information exposure. We extensively evaluate LightSplit on state-of-the-art benchmarks in both IID and non-IID settings across varying projection dimensions and client scales. Our results show that the method retains more than 95% of the baseline accuracy at up to 32x reduction in transmitted dimensionality while maintaining stable training dynamics.

---

### Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction

Authors: Deepak Warrier, Raja Sekhar Pappala
Published: 2026-05-13
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2605.13262v1

Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-million-molecule self-supervised pretraining. We ask: when a domain carries structural priors as rich as chemistry's, does it warrant a domain-native transformer rather than a generic one rescued by scale? We answer affirmatively with \textbf{GM-Net} (Geometric Measure Network), a transformer family in which every module is replaced by a sphere-native counterpart, and instantiate it as \textbf{Chem-GMNet}. Three blocks follow: SH-Embedding (tokens as learnable directions on $S^{k-1}$ lifted through a Gegenbauer feature map); DualSKA (a per-head fusion of a linear-time gated Sphere-Flow recurrence whose persistent state we prove is the truncated multipole expansion of the input distribution, and a softmax Sphere-Kernel branch over the same Schoenberg-valid kernel); and SH-FFN (sphere projection $\to$ Gegenbauer lift $\to$ moment readout). On canonical DeepChem scaffold splits, against same-shape ChemBERTa-2 baselines under the chemberta3-faithful protocol: (i) random-initialised, Chem-GMNet wins on 7 of 10 MoleculeNet endpoints at $\sim\!35\%$ fewer parameters; (ii) pretrained on the same 10M-SMILES ZINC corpus as ChemBERTa-2 MLM-10M, it matches or beats the public release on 6 of 8 shared endpoints (5/7 excluding a known ClinTox release anomaly). A $(k,L)$ ablation shows that increasing the sphere dimension from $k\!=\!8$ to $k\!=\!10$ at fixed $L\!=\!3$ lowers ESOL RMSE to $0.938$ at scratch, beating pretrained ChemBERTa-2 MLM-10M on this endpoint without any pretraining at all.

---

### "It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps

Authors: Wendy Zhou, Pelin Karaturhan, Alexandra Weilenmann, Jichen Zhu
Published: 2026-05-13
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2605.13261v1

In menstrual cycle tracking apps (MCTAs), AI-based predictions and insights have become increasingly popular. These features enable users to receive personalized information about their bodies and mental states. However, there is currently little research on how these predictive AI features and explanations affect users' lived experiences. This paper examines human-AI entanglement in MCTAs through 14 semi-structured user interviews and a group autoethnography. These methods uncover the processes leading to this phenomenon. Our results reveal that: (1) users understand their lived experiences in light of AI predictions, although these predictions can be faulty due to imperfect logging practices, (2) the user interface features and AI explanations do not support awareness or critical engagement with this entanglement and meaning-making, and (3) non-normative MCTA users report a sense of isolation in this entangled interaction. Based on our findings, we propose design implications for predictive AI features and explanations.

---

### Unified generalization analysis for physics informed neural networks

Authors: Yuka Hashimoto, Tomoharu Iwata
Published: 2026-05-13
Categories: cs.LG, math.AP, math.FA, stat.ML
arXiv: https://arxiv.org/abs/2605.13260v1

Physics-Informed Neural Networks (PINNs) and their variational counterparts (VPINNs) are neural networks that incorporate physical laws, making them useful for scientific problems. Existing generalization analyses for PINNs and VPINNs remain limited, often requiring restrictive assumptions such as stability conditions or linear ellipticity. In this paper, we derive generalization bounds for neural networks that involve differentiation with respect to input variables, covering PINNs and VPINNs under a unified framework. We apply Taylor expansion to represent nonlinear differential operators as linear operators on a high-dimensional space, enabling the use of Koopman-based analysis and showing that high-rank networks can generalize well even in settings involving differential operators. We also show that the nonlinearity of the differential operator exponentially enlarges the bound, highlighting its significant impact on generalization.

---

### X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge

Authors: Youwei Pan, Leilei Cao, Yingfang Zhu, Fengjie Zhu
Published: 2026-05-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.13258v2

In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the X-Restormer baseline, which captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention), augmented with the spatially-adaptive input scaling mechanism from Restormer-Plus. We adopt a two-stage training strategy with dual-model ensemble inference. In the first stage, Model B is trained from scratch on a large-scale diverse dataset randomly sampled from the FoundIR training set (approximately 800 GB out of 4.84 TB), covering five degradation types: blur, haze, rain, snow, and composite conditions such as co-occurring rain and haze. In the second stage, Model A is fine-tuned on the WeatherStream dataset (rain and snow splits) using Model B's final checkpoint as pretrained initialization, enabling efficient domain adaptation with a substantially smaller dataset. To better preserve structural details during training, we propose a novel Gradient-Guided Edge-Aware (GGEA) Loss, which applies Sobel operators to the ground-truth image to construct a spatially adaptive weight map that assigns higher supervision to edge and high-frequency regions. This is incorporated alongside L1 and Multi-Scale SSIM losses in a unified training objective. At inference time, predictions from the two models are fused via a weighted average, out = 0.4 x outA + 0.6 x outB, where the higher weight assigned to Model B reflects its stronger generalization ability from large-scale pretraining. With these strategies, our proposed method successfully ranks 1st in the challenge.

---

### Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning

Authors: Junlong Ke, Zichen Wen, Weijia Li, Conghui He, Linfeng Zhang
Published: 2026-05-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.13255v1

On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's token-level signal uniformly across a chain-of-thought sequence, despite substantial variation in the entropy of the teacher's predictive distribution. We propose EGRSD (Entropy-Guided Reinforced Self-Distillation), which unifies token-level updates through three signals: a reward-grounded direction, a teacher-student likelihood-ratio magnitude, and the proposed teacher-entropy confidence gate that down-weights high-entropy token positions while maintaining a nonzero lower bound on every token weight. We further introduce CL-EGRSD, a causal-lookahead variant that distinguishes sustained high-entropy spans from transient high-entropy positions whose following context rapidly becomes low entropy. Experiments with Qwen3-4B and Qwen3-8B in thinking mode show that EGRSD and CL-EGRSD advance the accuracy-length frontier among the compared trainable methods.

---

### The Sample Complexity of Multiple Change Point Identification under Bandit Feedback

Authors: Maximilian Graf, Victor Thuot
Published: 2026-05-13
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.13252v1

We study multiple change point localization under bandit feedback. An unknown piecewise-constant function on a compact interval can be queried sequentially at adaptively chosen inputs, and each query returns a noisy evaluation of the function. The goal is to identify a prescribed number of discontinuities, known as change points, within a target precision $η$ and confidence level $1-δ$, while using as few samples as possible. We propose an adaptive algorithm that first detects intervals likely to contain change points and then refines their locations to precision $η$. We establish non-asymptotic upper bounds on its sample budget, together with corresponding lower bounds. Prior work shows that jump magnitudes alone determine the asymptotic sample complexity as $δ\to 0$. We reveal that this picture is incomplete beyond this regime. We demonstrate, both empirically and theoretically, that for general $δ$ and $η$, the complexity is jointly governed by the jumps and the relative positions of the change points.

---

### Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis

Authors: Bo Cui, Xiaowen Song, Yaowen Zhang, Shunzhe Zhang, B. J. F. van Beijnum, Monique Tabak, Ying Wang
Published: 2026-05-13
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2605.13248v1

The analysis of physiological time series, such as electrocardiograms (ECG) and photoplethysmograms (PPG), is persistently hindered by modality and frequency gaps stemming from heterogeneous recording devices. Existing foundation models typically rely on continuous latent spaces, which frequently suffer from severe modality entanglement, lack high-fidelity cross-frequency generative capacity, and impose high computational costs that prohibit edge-device deployment. In this paper, we propose Compact Latent Manifold Translation (CLMT), a highly parameter-efficient (0.09B) unified framework that bridges these gaps through a novel two-stage discrete translation paradigm. First, we introduce a Universal Tokenizer utilizing Hierarchical Residual Vector Quantization (RVQ) to decouple heterogeneous signals into isolated, well-structured discrete latent manifolds, effectively preventing inter-modality interference. Second, a Context-Prompted Latent Translator maps these discrete tokens across modalities by integrating static physiological priors, reframing complex signal synthesis as a pure latent sequence translation task. Extensive evaluations demonstrate that our 0.09B model significantly outperforms massive baselines. In cross-modal PPG-to-ECG synthesis, it resolves temporal phase drift and dramatically improves the clinical R-peak detection F1-score from 0.37 (baseline) to 0.83. Furthermore, in extreme cross-frequency super-resolution (25Hz to 100Hz), it successfully recovers high-frequency diagnostic landmarks, achieving an unprecedented Pearson correlation of 0.9956. By learning a universal discrete language for biological signals with a fraction of the computational footprint, our approach sets a new trajectory for edge-deployable, multi-modal medical foundation models.

---

### EMO: Frustratingly Easy Progressive Training of Extendable MoE

Authors: Linghao Jin, Chufan Shi, Huijuan Wang, Nuan Wen, Zhengzhong Liu, Eric Xing, Xuezhe Ma
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13247v2

Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE efficiency paradox in practice: adding more experts balloons memory and communication costs, making actual training inefficient. We argue that this bottleneck arises in part because current MoE training allocates too many experts from the beginning, even though early-stage data may not fully utilize such capacity. Motivated by this, we propose EMO, a simple progressive training framework that treats MoE capacity as expandable memory and grows the expert pool over the course of training. EMO explicitly models sparsity in scaling law to derive stage-wise compute-optimal token budgets for progressive expansion. Empirical results show that EMO matches the performance of a fixed-expert setup in large-scale experiments while improving wall-clock efficiency. It offers a surprisingly simple yet effective path to scalable MoE training, preserving the benefits of large expert pools while reducing both training time and GPU cost.

---

### It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows

Authors: Marios Adamidis, Danae Katrisioti, Yannis Tzitzikas, Emmanuel Stratakis
Published: 2026-05-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.13245v1

Language models can produce convincing scientific analyses, but repeated generations on the same data do not guarantee the same result. A researcher may regenerate an identical query and receive a different fit, a different peak position or a different analysis procedure, without an obvious way to decide which output to trust. We propose typed mediation, a pattern in which the model orchestrates deterministic tools rather than generating analytical code. Each tool encodes one researcher's exact procedure for one instrument, ported through structured interviews. The model selects which tool to call and with what parameters. The tool produces the result. Regeneration does not change it. We evaluate this claim by running the same photoluminescence analysis on four platforms, including three commercial foundation models, four times each with the same prompt. The typed tool produces identical results across all runs. The commercial platforms either vary in numerical output and analytical methodology across runs, or fail to produce valid results on the task. We deploy this pattern on two instruments serving users over approximately six months, with very positive user feedback. Both cases are very challenging: they involve proprietary binary formats and per-seat licensed software, which force the tool to remain on local infrastructure alongside the data and the instrument it operates. We argue that deployment topology is not just a preference, but a structural requirement of scientific tool mediation. The result is a practical pattern for deploying language models in scientific workflows where reproducibility is mandatory, reducing analysis time from weeks to minutes while guaranteeing identical outputs across runs.

---

### When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation

Authors: John Lazarsfeld, Anas Barakat, Georgios Piliouras, Antonios Varvitsiotis, Andre Wibisono
Published: 2026-05-13
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2605.13242v1

This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which the last-iterate of OMWU can converge arbitrarily slowly, but understanding when and why this slow convergence occurs has remained open. In this work, we develop a new analysis framework that gives sharp, quantitative explanations for this behavior. Our analysis is based on viewing the algorithm's dual iterates as an optimistic skew-gradient descent with respect to an energy function. We prove over the dual iterates that energy is dissipative, and by establishing tight bounds on the magnitude of dissipation, our analysis quantifies the geometric bottlenecks that arise when the corresponding primal iterates are close to the simplex boundary. This further translates into a new linear last-iterate convergence rate in KL divergence on games with a unique and interior Nash equilibrium. Compared to prior work, this new rate contains a much sharper dependence on game-specific constants, and we prove this dependence is optimal. Moreover, these geometric insights further translate into new separations on uniform convergence rates for OMWU. On the one hand, we prove constant lower bounds on the uniform best-iterate convergence rate in KL divergence and total variation distance from Nash. On the other hand, we establish for the $2\times 2$ setting a new ${\widetilde O}(T^{-1/2})$ best-iterate rate in duality gap, improving substantially over prior work. Together, this shows in general that uniform convergence rate guarantees do not transfer across different measures of distance to Nash.

---

### IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations

Authors: Rabindra Lamsal, Sisi Zlatanova, Haowen Xu, Yafei Sun, Johnson Xuesong Shen
Published: 2026-05-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.13236v2

The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC's complex, deeply nested schema, motivating natural language interfaces. Existing LLM-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated across three IFC models on 30 query scenarios, our implementation achieves first-attempt accuracy between 93.3% and 100%, with all failed queries resolved via a fallback LLM. Built on an open-weight LLM, it supports local deployment in data-sensitive AEC settings.

---

### Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

Authors: Xinyu Liu, Kechen Jiao, Chunyang Xiao, Runsong Zhao, Junhao Ruan, Bei Li, Jiahao Liu, Qifan Wang, Xin Chen, Jingang Wang, Chenglong Wang, Tong Xiao et al.
Published: 2026-05-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.13230v2

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods rely on reverse KL (RKL)-based teacher supervision over trajectories sampled from the student policy. However, we identify a critical limitation: under large teacher--student policy divergence, RL-driven exploration often produces trajectories outside the teacher distribution, resulting in uninformative negative feedback. To address this, we propose Teacher-Guided Policy Optimization (TGPO), an on-policy reasoning distillation method that remains effective under large policy divergence settings. Rather than relying solely on evaluative supervision, TGPO uses teacher to directly guide token level generation conditioning on student-generated contexts; together with RLVR-style trajectory level rewards, TGPO steers exploration toward improved continuations. Experiments on reasoning benchmarks show that TGPO consistently outperforms existing RKL-based OPD methods and remains robust across different teacher models.

---

### Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

Authors: Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu
Published: 2026-05-13
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2605.13229v1

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by unreliable semantic rewards derived from sparse test cases or restrictive reference translations. We argue that a robust semantic reward for code translation must be derived directly from the source code. In this paper, we propose CTO to improve code translation with syntax-guided and semantic-aware preference optimization. Through contrastive learning, we train a cross-lingual semantic model to directly assess functional equivalence between source and translated code. By formulating code translation as a multi-objective optimization problem, this robust semantic signal is seamlessly unified with compiler-based syntactic feedback within the direct preference optimization framework. Extensive experiments on C++, Java, and Python translations demonstrate that CTO significantly outperforms existing baselines and alternative preference optimization strategies.

---

### ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding

Authors: Xiao Liu, Nayu Liu, Junnan Zhu, Ruirui Chen, Guohui Xiang, Changjian Wang, Kaiwen Wei, Rongzhen Li, Jiang Zhong
Published: 2026-05-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.13228v1

Video understanding requires active evidence seeking, motivating tool-augmented video agents for temporal reasoning, cross-modal understanding, and complex question answering. Existing video agents have improved video reasoning with retrieval, memory, frame inspection, and verifier tools, but they still face two limitations: (1) a coarse tool space that lacks fine-grained operations for compositional reasoning; and (2) a flat action space that forces high-level video intents into primitive executable tool calls. In this paper, we address these challenges with two complementary designs. First, we construct a MetaAug-Video Tool Library (MVTL), an extensible tool library with 134 registered tools, including 26 base tools for general multimodal signal processing and 108 meta tools for filtering, aggregation, reranking, formatting, and other intermediate-result operations. MVTL supports dual-level access to both structured video information and raw modal evidence, enabling diverse video reasoning scenarios. Second, we propose ReTool-Video, a recursive tool-using method that grounds high-level video intents into executable tool chains. In ReTool-Video, matched actions are executed directly, while unmatched intents are delegated to a resolver for parameter repair, tool substitution, or decomposition. This allows abstract actions such as temporal merging, cross-modal verification, or repeated-event aggregation to be progressively translated into concrete multimodal operations at runtime. Experiments on MVBench, MLVU, and Video-MME w/o sub. show that ReTool-Video consistently outperforms strong baselines. Further analysis demonstrates that recursive grounding and fine-grained meta tools improve the stability and effectiveness of complex video understanding.

---

### Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

Authors: Paul Jeha, Anastasiia Sedova, Louis Béthune, Skyler Seto, Jes Frellsen, Pierre Ablin, Natalie Schluter
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13225v1

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such as high weight decay, and mixing in data from a high-resource auxiliary language to directly aid the low-resource target. While hyperparameter tuning regularizes the model by shrinking weights to restrict network capacity, auxiliary data mixing uses a tunable mixing ratio to expand the training distribution and diversify the training signal with new knowledge. Both offer a principled way to improve training in a data-constrained domain. We compare these levers systematically across four model scales from 150M to 1.43B parameters, using Arabic as the low-resource target and English as the auxiliary, over approximately 1000 pre-training runs. Three findings emerge. First, mixing yields larger improvements than hyperparameter tuning on both validation loss and downstream task accuracy, and the gap grows with model size. Second, we quantify how much mixing helps: it boosts performance by an amount equivalent to 2--3$\times$ the unique target data on validation loss and 2--13$\times$ on downstream task accuracy, with the gain scaling steeply with model size. Third, this divergence reveals that target-language validation loss systematically underestimates mixing's value. Mixing regularizes by diversifying the training signal and contributes knowledge the repeated target corpus cannot supply; validation loss captures only the first effect. Our practical recommendations are: mix in a high-resource language, prioritize the mixing ratio over hyperparameter tuning, and transfer hyperparameters from a small proxy model via $μ$P.

---

### Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation

Authors: Abdelrahman Eldesokey, Merey Ramazanova, Ahmad Sait, Ansar Khangeldin, Karen Sanchez, Tong Zhang, Bernard Ghanem
Published: 2026-05-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.13223v1

Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or binary question answering (BQA), across heterogeneous evaluation skills, despite fundamental differences in their nature. In this work, we revisit T2I evaluation through the lens of skill-aligned annotation, where annotation strategies reflect the underlying characteristics of each evaluation skill. We systematically compare skill-aligned annotation against uniform baselines and show that it produces more consistent evaluation signals, with higher inter-annotator agreement and improved stability across models. Finally, we present an automated pipeline that instantiates the proposed evaluation protocol, enabling scalable and fine-grained evaluation with spatially grounded feedback. Our work highlights that improving the foundations of image evaluation can increase reliability and efficiency without simply scaling annotation effort. We hope this motivates further research on refining evaluation protocols as a central component of reliable model assessment.

---

### An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing

Authors: Hanwen Zhang, Dusit Niyato, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low
Published: 2026-05-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.13221v2

In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with computational task scheduling. In this paper, UAVs collect finished products from manufacturing stations and transport them back to a central depot. Meanwhile, computational tasks generated by industrial sensor devices at these stations are processed locally, at UAVs, or offloaded via UAVs to the cloud. This coupling makes the problem challenging. A UAV can provide MEC services only during its service window at a station, so routing decisions directly determine when UAV-assisted offloading is available. Routing decisions also affect the UAV energy budget and the availability of onboard computing and communication resources for computational task execution under task deadline constraints. To address this, we propose an agentic-AI-assisted optimization framework with two components. First, we develop an agentic AI that combines large language models, retrieval-augmented generation, and chain-of-thought reasoning to translate user input into an interpretable mathematical formulation for the hybrid scheduling problem. Second, we design a hierarchical deep reinforcement learning approach based on proximal policy optimization (PPO), where the upper layer learns UAV routing and the lower layer optimizes per-slot task execution and resource allocation. Simulation results show that the proposed framework yields more consistent formulations, while the hierarchical PPO achieves full product collection in 99.6% of the last 500 episodes and maintains a 100% deadline satisfaction rate, with more stable performance than the advantage actor-critic approach.

---

### An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing

Authors: Hanwen Zhang, Dusit Niyato, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low
Published: 2026-05-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.13221v1

In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with computational task scheduling. In this paper, UAVs collect finished products from manufacturing stations and transport them back to a central depot. Meanwhile, computational tasks generated by industrial sensor devices at these stations are processed locally, at UAVs, or offloaded via UAVs to the cloud. This coupling makes the problem challenging. A UAV can provide MEC services only during its service window at a station, so routing decisions directly determine when UAV-assisted offloading is available. Routing decisions also affect the UAV energy budget and the availability of onboard computing and communication resources for computational task execution under task deadline constraints. To address this, we propose an agentic-AI-assisted optimization framework with two components. First, we develop an agentic AI that combines large language models, retrieval-augmented generation, and chain-of-thought reasoning to translate user input into an interpretable mathematical formulation for the hybrid scheduling problem. Second, we design a hierarchical deep reinforcement learning approach based on proximal policy optimization (PPO), where the upper layer learns UAV routing and the lower layer optimizes per-slot task execution and resource allocation. Simulation results show that the proposed framework yields more consistent formulations, while the hierarchical PPO achieves full product collection in 99.6% of the last 500 episodes and maintains a 100% deadline satisfaction rate, with more stable performance than the advantage actor-critic approach.

---

### Machine Learning-Driven Multimodal Spectroscopic Liquid Biopsy for Early Multicancer Detection

Authors: Alejandro Leonardo García Navarro, Javier Cachón Ortiz, Javier González Colsa, Samuel García Díaz, Carlos Viadero Valderrama
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13218v1

Cancer is one of the leading causes of death worldwide, making the development of rapid, minimally invasive, label-free and scalable diagnostic strategies a major challenge in modern oncology. In this context, spectroscopic liquid biopsy has emerged as a promising alternative, as it enables the holistic characterization of biochemical alterations in biological fluids. In this work, we propose a multimodal spectroscopic liquid biopsy framework for multicancer detection based on the combination of Fourier Transform Infrared (FTIR) spectroscopy, Raman spectroscopy, and Excitation-Emission Matrix (EEM) fluorescence spectroscopy together with Machine Learning (ML) methodologies. Serum samples from breast cancer patients, colorectal cancer patients, and healthy controls were analyzed through the three spectroscopic modalities. After modality-specific preprocessing, low-level data fusion (LLDF) was employed to integrate the complementary biochemical information encoded within the different spectroscopic measurements, and classification was performed using XGBoost models. Seven experimental configurations were evaluated, including the three unimodal approaches, all pairwise bimodal configurations, and the full multimodal approach of FTIR, Raman, and EEM fluorescence. The results show that although several individual modalities achieved high discrimination performance, the multimodal fusion provided the most balanced overall results, reaching a ROC-AUC of 0.997 for breast cancer and 0.994 for colorectal cancer, together with highly balanced sensitivity and specificity values.

---

### GAGPO: Generalized Advantage Grouped Policy Optimization

Authors: Siyuan Zhu, Chao Yu, Rongxin Yang, Zongkai Liu, Jinjun Hu, Qiwen Chen, Yibo Zhang
Published: 2026-05-13
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.13217v1

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on costly auxiliary value models remains an open problem. We propose Generalized Advantage Grouped Policy Optimization (GAGPO), a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment. GAGPO constructs a non-parametric grouped value proxy from sampled rollouts and uses it to compute TD/GAE-style temporal advantages, recursively propagating outcome supervision backward through time. Combined with group-wise advantage normalization and an action-level importance ratio, GAGPO extracts stable, localized optimization signals directly from multi-turn trajectories. Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines. Further analyses demonstrate faster early-stage learning, improved interaction efficiency, and smoother optimization dynamics, suggesting that GAGPO offers a simple yet effective framework for multi-turn agentic reinforcement learning.

---

### Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks

Authors: Marte Eggen, Eirik Reiestad, Kristian Gjøsteen, Inga Strümke
Published: 2026-05-13
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.13214v3

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end trained networks. We construct such an attack mechanism for state-of-the-art architectures, closely aligned to the cryptographic notion of undetectability, by identifying backdoor channels as learned latent directions, and show that the question of undetectability reduces to a hypothesis test between two unknown distributions over model parameters, which we conjecture to be intractable in practice. The consequence of this reframing is significant: if exploitable channels within a network's latent space are statistically indistinguishable from naturally learned directions, an attacker need not introduce foreign structure but can instead exploit the geometry the network already possesses. Demonstrating the approach on ResNet and Vision Transformer architectures trained on standard image classification datasets, the attack achieves both consistently high success rates with negligible clean accuracy degradation, and resists a comprehensive suite of post-training defences, none of which neutralise the backdoor without rendering the model unusable. Our results establish that cryptographic backdoors need not be artefacts requiring exotic architectures or artificial constructions, but identifiable as latent properties inherent to the geometry of learned representations.

---

### Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

Authors: Marte Eggen, Eirik Reiestad, Kristian Gjøsteen, Inga Strümke
Published: 2026-05-13
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.13214v2

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end trained networks. We construct such an attack mechanism for state-of-the-art architectures, closely aligned to the cryptographic notion of undetectability, by identifying backdoor channels as learned latent directions, and show that the question of undetectability reduces to a hypothesis test between two unknown distributions over model parameters, which we conjecture to be intractable in practice. The consequence of this reframing is significant: if exploitable channels within a network's latent space are statistically indistinguishable from naturally learned directions, an attacker need not introduce foreign structure but can instead exploit the geometry the network already possesses. Demonstrating the approach on ResNet and Vision Transformer architectures trained on standard image classification datasets, the attack achieves both consistently high success rates with negligible clean accuracy degradation, and resists a comprehensive suite of post-training defences, none of which neutralise the backdoor without rendering the model unusable. Our results establish that cryptographic backdoors need not be artefacts requiring exotic architectures or artificial constructions, but identifiable as latent properties inherent to the geometry of learned representations.

---

### Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning

Authors: Hao Zhou, Tiru Wu, Yan Jiang, Wanqi Zhou, Junxing Hu, Ai Han
Published: 2026-05-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.13213v1

Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse modalities. As these systems continue to expand in scale and functionality, investigating their potential vulnerabilities has become increasingly important. However, existing studies on adversarial attacks in multi-agent systems primarily focus on isolated agents or unimodal settings, leaving the vulnerabilities of MM-MAS largely underexplored. To bridge this gap, we introduce HAM$^{3}$, a Hierarchical Attack framework for multi-modal multi-agent systems that decomposes attacks into three interconnected layers. Specifically, at the perception layer, HAM$^{3}$ mounts attacks by perturbing visual inputs, textual inputs, and their fused visual-textual representations. At the communication layer, it performs communication-level attacks that corrupt message content and interaction topology, such as manipulating shared context or communication links to distort collective information flow. At the reasoning layer, it conducts reasoning-level attacks that interfere with each agent's cognitive pipeline, biasing reasoning trajectories and ultimately compromising final decisions. We evaluate HAM$^{3}$ on the GQA benchmark through multi-agent systems built on distinct reasoning paradigms including ReAct, Plan-and-Solve, and Reflexion. Experiments demonstrate that our framework achieves an Attack Success Rate of up to 78.3%, with reasoning-layer attacks being the most effective. More than half of the successful attacks lead multiple agents to produce consistent errors. These findings offer valuable insights for building more robust and interpretable multi-agent intelligence.

---

### Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning

Authors: Stefan Stojanovic, Alexandre Proutiere
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13207v1

Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manually designed subgoals. We show that switching successor measures arise naturally from classical successor measures while preserving their underlying structure. Building on this result, we propose FB $π$-Switch, an algorithm that extracts both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward (FB) representations, allowing hierarchical behavior to emerge from a single learned representation. Experiments on both goal-conditioned and general reward-based tasks show that FB $π$-Switch improves over non-hierarchical baselines and matches state-of-the-art hierarchical methods in goal-conditioned settings. These results demonstrate that structured successor representations provide a flexible foundation for hierarchical zero-shot reinforcement learning beyond goal-reaching tasks. Our project website is available at: https://stestokth.github.io/switching-successors/.

---

### STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition

Authors: Hongli Liu, Yu Wang, Shengjie Zhao
Published: 2026-05-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.13202v1

Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decisive visual cues that appear sparsely across sequences, and from inadequate modeling of multi-scale temporal dynamics, as short-term discriminative cues and long-range dependencies are often either oversmoothed or fragmented. To address these challenges, we propose Semantic Temporal Adaptive Representation Learning (STAR), a unified framework, consisting of a semantic-alignment component and a temporal-aware component, effectively bridging the semantic and temporal gaps and transferring the sequence modeling capability of Mamba into the FSAR. The semantic alignment module introduces a Temporal Semantic Attention (TSA) mechanism, which performs frame-level cross-modal alignment with textual cues, ensuring fine-grained semantic-temporal consistency. The temporal-aware module incorporates a Semantic Temporal Prototype Refiner (STPR) that integrates semantic-guided Mamba blocks with multi-frequency temporal sampling and bidirectional state-space refinement, yielding semantically aligned prototypes with enhanced discriminative fidelity and temporal consistency. Furthermore, temporally dependent class descriptors derived from large language models (LLMs) provide long-range semantic guidance. Extensive experiments on five FSAR benchmarks demonstrate the consistent superiority of STAR over state-of-the-art methods. For instance, STAR achieves up to 8.1% and 6.7% gains on the SSv2-Full and SSv2-Small datasets under the 1-shot setting, and 7.3% on HMDB51, validating its effectiveness under limited supervision. The code is available at https://github.com/HongliLiu1/STAR-main.

---

### A Hybrid Tucker-LSTM Tensor Network Model for SOC Prediction in Electric Vehicles

Authors: Han Wang, Ying Wang, Bing Wang
Published: 2026-05-13
Categories: cs.LG, cs.ET
arXiv: https://arxiv.org/abs/2605.13200v1

Accurate state of charge estimation is critical for the success of electric vehicle battery management strategies, but it is well known that conventional estimators suffer from two fundamental shortcomings: cumulative errors that grow over time and reliance on simplified battery models that do not reflect real world dynamics. Therefore, this paper presents a novel hybrid approach combining Tucker tensor decomposition with LSTM networks, using full - lifecycle EV field data for SOC prediction. The inputs are charge status, mileage, voltage, current, cell differentials, and temporal features. Tucker decomposition is skillfully used to reduce dimensionality while maintaining the temporal structure, hence allowing a direct, fair comparison with standard LSTM. The result is unequivocal: Tucker - LSTM outperforms the baseline on all metrics, with MSE dropping 70.5\% (from 21.07 to 6.22 ), MAE improving 48.7\% (from 3.37\% to 1.73\%), RMSE falling from 4.59\% to 2.49\%, and $R^2$ rising from 0.918 to 0.976. Since the experimental results demonstrably demonstrate that tensor decomposition compresses high-dimensional battery data very well without loss of predictive fidelity, this paper naturally opens up a new direction for tensor-based analytics in electric vehicle battery management.

---

### McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting

Authors: Penghui Wen, Yu Luo, Lintao Wang, Mengwei He, Patrick Filippi, Thomas Francis Bishop, Zhiyong Wang
Published: 2026-05-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.13197v1

Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. However, such an approach accumulates errors over long rollouts, causing forecasts to drift away from physically plausible evolution trajectories. Although various studies have attempted to alleviate this problem by improving step-wise prediction accuracy, they largely neglect the global temporal evolution of meteorological systems and lack mechanisms to actively correct drift during rollouts. To address this issue, we propose McCast, a memory-guided latent drift correction method for precipitation nowcasting. Rather than treating memory as an unordered dictionary of latent states for passive conditioning, McCast leverages temporally organized memory to actively correct autoregressive latent evolution. Specifically, McCast introduces a Drift-Corrective Memory Bank (DCBank) that explicitly estimates the temporally consistent drift corrections to calibrate the divergent trajectory. DCBank performs drift correction in two stages: a Corrective Latent Extractor first predicts an initial correction from the current prediction and a reference latent state, and a Correction-Aware Memory Retrieval module then refines the initial correction using temporally organized historical memory. By explicitly correcting latent evolution, instead of improving step-wise prediction accuracy only, McCast produces more temporally coherent and reliable long-horizon forecasts. Experiments on two widely used benchmarks, SEVIR and MeteoNet, show that McCast achieves state-of-the-art performance, particularly in challenging long-horizon forecasting scenarios.

---

### ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification

Authors: Mahsa Gazeran, Sayvan Soleymanbaigi, Fatemeh Daneshfar, Amjad Seyedi, Fardin Akhlaghian Tab
Published: 2026-05-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.13194v1

Electrocardiogram (ECG) arrhythmia classification remains challenging due to signal variability, noise, limited labeled data, and the difficulty in achieving both accuracy and efficiency in models. While self-supervised learning reduces label dependency, most methods target either global contextual features or local morphological patterns, but rarely implement hierarchical multi-scale feature extraction. ECG signals require architectures that simultaneously capture fine-grained beat-level morphology and broader rhythm-level dependencies with computational efficiency. To overcome this limitation, this paper proposes the Electrocardiogram Neighborhood Attention Transformer (ECG-NAT), a novel self-supervised learning approach tailored for multi-lead ECG classification. Our two-stage approach begins with generative pretraining, using a masked autoencoder to reconstruct partially masked ECG signals across multiple diverse datasets, enabling the model to learn robust, domain-invariant representations from unlabeled data. This is followed by discriminative fine-tuning with a dual-loss function that combines supervised contrastive and cross-entropy losses, aligning representation learning with label prediction. The hierarchical attention mechanism efficiently captures multi-scale temporal features from localized beat morphology to broader rhythm patterns at low computational cost. ECG-NAT achieves robust performance on benchmark datasets, with 88.1\% accuracy using only 1\% labeled data, demonstrating strong efficacy in low-resource settings. The framework combines superior classification performance with computational efficiency, making it practical for real-time ECG diagnosis. The code will be made available upon acceptance at: https://github.com/Mahsagazeran/ECG-NAT.

---

### FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition

Authors: Geng Li, Yuxin Peng
Published: 2026-05-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.13193v2

Fine-grained recognition in everyday life is often not a closed-book classification problem: when encountering unfamiliar objects, humans actively search, compare visual details, and verify evidence before deciding. Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored. We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions. We introduce FIKA-Bench, a leakage-aware and evidence-grounded collection of 311 public-source and real-life instances. To ensure high quality, every example is filtered against frontier closed-book models to remove memorized cases and audited to eliminate image-answer leakage, retaining only samples supported by verified evidence. Our evaluation of latest Large Multimodal Models (LMMs) and agents reveals that the task remains a formidable challenge: the best system reaches only 25.1% accuracy, with no model exceeding 30%. Crucially, we find that merely equipping models with tools is insufficient to bridge this gap; agent failures are predominantly driven by wrong entity retrieval and poor visual judgement. These results show that reliable knowledge acquisition needs better agent designs that focus on fine-grained recognition.

---

### N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation

Authors: Aleksander Lorenc, Frédéric Berdoz, Joël Mathys, Roger Wattenhofer
Published: 2026-05-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.13190v1

Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce N-vium, a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware, increasing effective FLOPs per second rather than minimizing compute per token. N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits, with token-adaptive routing. This formulation strictly generalizes the standard transformer, which is recovered exactly when routing assigns zero mass to all intermediate heads. Sampling from the mixture is exact, and complete KV caches are recovered by deferring the upper-layer computation and batching it with later tokens. We pretrain N-vium at scales up to 1.5B parameters. Our largest model reaches 57.9% wall-clock speedup over a parameter- and data-matched standard transformer at no perplexity cost.

---

### LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information

Authors: Stef van Buuren
Published: 2026-05-13
Categories: stat.ML, cs.CL, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2605.13188v1

Large language models (LLMs) are increasingly deployed in settings where the available context is incomplete or degraded. We argue that an LLM generating answers under incomplete context can be viewed as an implicit imputer, and evaluated against a criterion from the multiple imputation (MI) literature: uncertainty should scale with the amount of missing information. We assess this criterion on SQuAD, using a controlled framework in which context availability is varied across five levels. We evaluate two answer-level uncertainty measures that can be estimated from repeated sampling: sampling-based confidence (empirical mode frequency) and response entropy. Confidence fails to reflect increasing missingness: it remains high even as accuracy collapses. Entropy, by contrast, increases with context removal, consistent with the MI analogy, and explains substantially more variance in accuracy than confidence across all evidence levels (quadratic $R^2$ gap up to 0.057). We further introduce a black-box diagnostic $ρ_R(α)$ that estimates the proportion of baseline uncertainty resolved by context level $α$, requiring only repeated sampling with and without context. These results suggest that entropy is a more responsive black-box uncertainty measure than confidence under incomplete context.

---

### DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution

Authors: Zheng Chen, Ruofan Yang, Jin Han, Dehua Song, Zichen Zou, Chunming He, Yong Guo, Yulun Zhang
Published: 2026-05-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.13182v1

Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-resolution (STVSR) setting remains limited. Existing diffusion-based STVSR approaches suffer from two issues: (1) low inference efficiency and (2) insufficient utilization of spatiotemporal information. These limitations impede deployment. To address these issues, we introduce DiffST, an efficient spatiotemporal-aware video diffusion framework for real-world STVSR. To improve efficiency, we adapt a pre-trained diffusion model for one-step sampling and process the entire video directly rather than operating on individual frames. Furthermore, to enhance spatiotemporal information utilization, we introduce cross-frame context aggregation (CFCA) and video representation guidance (VRG). The CFCA module aggregates information across multiple keyframes to produce intermediate frames. The VRG module extracts video-level global features to guide the diffusion process. Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17$\times$ faster than previous diffusion-based STVSR methods. Code is available at: https://github.com/zhengchen1999/DiffST.

---

### Stable Attention Response for Reliable Precipitation Nowcasting

Authors: Penghui Wen, Zexin Hu, Sen Zhang, Patrick Filippi, Xiaogang Zhu, Allen Benter, Thomas Bishop, Zhiyong Wang, Kun Hu
Published: 2026-05-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.13181v3

Precipitation nowcasting remains challenging due to the highly localized, rapidly evolving, and heterogeneous nature of atmospheric dynamics. Although recent methods increasingly adopt attention-based architectures in both unimodal and multimodal settings, they mainly emphasize stronger representation learning and prediction capacity, while paying less attention to the stability of attention responses across samples. In this work, we show that cross-sample instability of attention-response energy is an important and previously underexplored source of forecasting unreliability. Empirically, inaccurate forecasts are associated with larger attention-response energy variance across heads and layers. Theoretically, we show that cross-sample variability can propagate through self-attention, and enlarge a lower bound on prediction error. Based on this insight, we propose HARECast, a Head-wise Attention Response Energy-regulated framework for precipitation nowcasting. HARECast explicitly models head-wise attention-response energy and stabilizes it through a group-wise regularization objective that reduces cross-sample fluctuations. The proposed formulation is generic and applicable to both unimodal and multimodal nowcasting architectures. We instantiate HARECast in a standard forecasting pipeline with reconstruction branches and a diffusion-based predictor, and evaluate it on commonly used benchmarks--SEVIR and MeteoNet. Experimental results demonstrate that HARECast achieves state-of-the-art performance.

---

### Does Engram Do Memory Retrieval in Autoregressive Image Generation?

Authors: Jinghao Wang, Qiyuan He, Chunbin Gu, Pheng-Ann Heng
Published: 2026-05-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.13179v1

The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretraining, with the appealing interpretation that it provides a content-addressed shortcut to recurring local token patterns. We ask whether this interpretation transfers to autoregressive (AR) image generation, or whether the observed gains, if any, come from a different mechanism. We adapt the Engram module to vision with 2D spatial $n$-gram hashing, gated fusion, and KV-cache-compatible incremental inference, and inject it into a class-conditional AR generator trained on ImageNet 256x256. Across a sweep of backbone-to-memory budget ratios $ρ{\in}(0.17, 0.90)$, every Engram-augmented variant trails the pure AR baseline in FID, indicating that the module saves backbone FLOPs but does not, by itself, improve sample quality. We then probe how the module is used. A gate-clamp sweep shows that disabling the Engram pathway entirely is catastrophic, yet a tiny constant gate (g=0.10) matches or beats the learned gate -- inconsistent with a heavily content-addressed recall mechanism. A donor-probe experiment shows that swapping the hash inputs for matched, adversarial, or random same-class exemplars produces statistically indistinguishable next-token distributions, while collapsing or randomising the table degrades them by two to three orders of magnitude. Finally, training a model from scratch with the entire memory table frozen to $\mathcal{N}(0, 1)$ noise costs only $Δ\text{FID}{=}0.10$ and actually raises Inception Score. Together, these findings indicate that the Engram in AR image generation behaves not as a content-addressed retriever but as a gated architectural side-pathway: a hash-keyed residual stream whose benefit is dominated by the pathway itself, with the learned table contributing only a small distributional refinement.

---

### CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

Authors: Sangin Lee, Yukyung Choi
Published: 2026-05-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.13178v2

In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual tokens for image understanding tasks. However, these methods struggle with pixel grounding tasks, where token importance is highly contingent on the input text. Through an in-depth analysis of CLIP, we observe that visual tokens within referent regions often exhibit low similarity to their textual representation. Motivated by this insight, we introduce LiteLVLM, a training-free, text-guided token pruning strategy for efficient pixel grounding inference. By reversing the ranking of CLIP's visual-text similarity, LiteLVLM effectively retains visual tokens covering the referent regions, while recovering context tokens to enable clear foreground-background separation. Extensive experiments demonstrate that LiteLVLM significantly outperforms existing methods by over 5% across diverse token budgets. Without any training or fine-tuning, LiteLVLM maintains 90% of the original performance with a 22% speedup and a 2.3X memory reduction. Our code is available at https://github.com/sejong-rcv/LiteLVLM.

---

### Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training

Authors: Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello
Published: 2026-05-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.13175v2

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is intuitive: if the data are heavy-tailed, HT noise may appear better matched than light-tailed (LT) Gaussian noise. However, replacing Gaussian noise by HT noise also changes the underlying estimation problem. In this paper, we revisit this paradigm through a combined theoretical and empirical study, establishing sampling-error bounds for two representative diffusion models driven by HT and LT noise. We show that HT noise makes the statistical estimation problem harder, leading to less favorable sampling-error bounds. We support these findings with experiments on synthetic and real-world datasets, empirically recovering the predicted error trade-off. Our results call into question a growing design trend in generative modeling and challenge the use of HT noise to improve rare-region exploration.

---

### Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems

Authors: Dengfei Zeng, Lijian Jiang, Shuyu Sun, Dunhui Xiao
Published: 2026-05-13
Categories: stat.ML, cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2605.13174v1

A likelihood-free transport filtering method is proposed based on the couplings between state and observation variables. By exploiting a block-triangular structure in the transport map, the analysis step of filtering is reformulated as the minimization of the maximum mean discrepancy (MMD) between the true joint measure and its transport-based approximation. To circumvent the non-convexity in the MMD optimization, we introduce a training-free transport filter method via gradient flows, which leads to an analytic computation for the transport map that implies the steepest descent direction of the MMD. The proposed approach accurately approximates non-Gaussian filtering posteriors and avoids particle collapse. We provide a convergence analysis for the expectation of the MMD between the approximated posterior and the truth posterior. Finally, we extend the method to high-dimensional problems through domain localization. Numerical examples demonstrate the superior performance of our approach over conventional filtering methods in nonlinear, non-Gaussian scenarios.

---