# Research Papers — 2026-05 · bundle page 92 of 326

> Full-text markdown of papers #4551–4600 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/92
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/91.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/93.md)

### Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions

Authors: Ghassen Marrakchi, Basarab Matei
Published: 2026-05-23
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.24621v1

Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in global averaging. We propose Phase-Aware Scattering Encoder-Decoder, which restores this information by explicitly preserving phase in skip connections. On image denoising (BSD68), breaking translation invariance improves PSNR by $+2.17$~dB; phase preservation adds $+1.03$~dB. A novel spatial shuffling ablation ($-1.26$~dB penalty) demonstrates phase encodes location-dependent structure. We conduct a preliminary extensibility study on a second dense prediction task (ISIC skin lesion segmentation), with full cross-validation as ongoing work. This work advances principled wavelet-deep learning integration, showing how phase information complements scattering's stability-expressiveness trade-off in pixel-level prediction.

---

### Measuring the Depth of LLM Unlearning via Activation Patching

Authors: Jaeung Lee, Dohyun Kim, Jaemin Jo
Published: 2026-05-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.24614v2

Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is truly erased remains challenging. Existing output-level metrics fail to detect when this knowledge remains recoverable from internal representations. Recent white-box studies reveal such residual knowledge but often rely on auxiliary training or dataset-specific adaptations, leaving no generalizable metric. We close this gap with the Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching. UDS first identifies layers that encode the target knowledge using a retain model baseline, then measures how much of it is erased in the unlearned model on a 0-1 scale. In a meta-evaluation across 20 metrics on 150 unlearned models spanning 8 methods, UDS achieves the highest faithfulness and robustness, confirming our causal approach as the most reliable for unlearning evaluation. Case studies further show that UDS uncovers residual knowledge obscured from observational metrics by representational shifts, with erasure depth varying across prompt types. We provide guidelines for integrating UDS into existing benchmarking frameworks and streamlining the evaluation pipeline. Code and data are available at https://github.com/gnueaj/unlearning-depth-score.

---

### Measuring the Depth of LLM Unlearning via Activation Patching

Authors: Jaeung Lee, Dohyun Kim, Jaemin Jo
Published: 2026-05-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.24614v1

Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is truly erased remains challenging. Existing output-level metrics fail to detect when this knowledge remains recoverable from internal representations. Recent white-box studies reveal such residual knowledge but often rely on auxiliary training or dataset-specific adaptations, leaving no generalizable metric. To address these limitations, we propose the Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching. UDS first identifies layers that encode the target knowledge using a retain model baseline, then measures how much of it is erased in the unlearned model on a 0-1 scale. In a meta-evaluation across 20 metrics on 150 unlearned models spanning 8 methods, UDS achieves the highest faithfulness and robustness, confirming our causal approach as the most reliable for unlearning evaluation. Case studies further reveal that white-box metrics can disagree at the layer level and that erasure depth varies across examples. We provide guidelines for integrating UDS into existing benchmarking frameworks and streamlining the evaluation pipeline. Code and data are available at https://github.com/gnueaj/unlearning-depth-score

---

### Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning

Authors: Haizhou Xia
Published: 2026-05-23
Categories: cs.CL, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2605.24613v1

Post-hoc repair of LLM mathematical reasoning introduces an asymmetric risk: fixing an incorrect reasoning trace is useful, but replacing a trace that was already correct can be harmful. We study this problem under a selective replacement setting, where a system must decide whether a repaired candidate is safer than preserving the original cached trace. We present GuardedRepair, a guarded best-of-N repair framework that diagnoses cached reasoning traces, selectively triggers repair, and accepts answer-changing candidates only when deterministic verification guards support replacement. The framework combines lightweight symbolic checks, surface semantic-risk diagnostics, bounded candidate generation, and conservative acceptance policies. On the full GSM8K test set, where the initial reasoner already achieves 95.60% accuracy, GuardedRepair improves final accuracy to 96.89%, fixing 17 of 58 remaining errors without measured broken-correct cases in the main run. On a weak-reasoner ASDiv setting, accuracy improves from 78.40% to 87.60%. Direct regeneration baselines show that this gain is not explained by stronger-model re-solving alone: re-solving all GSM8K examples lowers accuracy to 93.03% and breaks 47 initially correct answers. Additional analyses show that guarded repair substantially improves the fixed/broken tradeoff, while also revealing that replacement risk is reduced rather than eliminated. These results support viewing post-hoc repair as harm-aware selective replacement rather than unconstrained re-solving.

---

### Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks

Authors: Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn, Emanuele Natale
Published: 2026-05-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.24611v1

Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving high-capacity storage of long sequences in classical synchronous asymmetric networks, however, has remained a challenge. We present a simple and robust construction within the classical asymmetric Hopfield model with binary neurons and synchronous updates, that allows $n$ neurons to support $\exp\!\big(Ω(n/(\log n)^2)\big)$ distinct limit-cycle attractors, each with period $\exp\!\big(Ω(\sqrt n/\log n)\big)$ and robust to random noise with flip probability up to $\frac12-o(1)$, yielding superpolynomial capacity in both the number and length of stored sequences. This is the first demonstration of such capacity for asymmetric Hopfield networks, which we obtain by combining results from combinatorics, number theory and the analysis of opinion dynamics. Our findings show that synchronous asymmetric Hopfield networks possess a sequence-memory capacity which is larger and more robust than previously recognized, demonstrating that, in both biological and artificial neural systems, robust sequence representation can be achieved through coarse architectural motifs rather than complex nonlinearities.

---

### Catching magnetic resonance imaging outliers in artificial intelligence-supported radiotherapy workflows: unsupervised detection and localization of image anomalies using deep learning

Authors: Mustafa Kadhim, Viktor Rogowski, Emilia Persson, Camila Gonzalez, André Haraldsson, Sofie Ceberg, Mikael Nilsson, Malin Kügele, Sven Bäck, Christian Jamtheim Gustafsson
Published: 2026-05-23
Categories: physics.med-ph, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.24609v2

Artificial intelligence is increasingly integrated into radiotherapy workflows, yet such pipelines remain vulnerable to out-of-distribution image data that may introduce unexpected behavior in clinical tasks. Deep learning-based anomaly detection for pelvic magnetic resonance imaging (MRI) remains largely unexplored, and transparent evaluation of its feasibility for full automation is limited. We developed and evaluated a fully automated, unsupervised anomaly-detection framework for pelvic and brain MRI. A two-stage framework was trained on reference images from public datasets: LUND-PROBE for pelvic MRI, and IXI, fastMRI, and fastMRI+ for brain MRI. In the first stage, MRI slices were compressed into discrete tokens; in the second, the distribution of normal tokens was modeled. Anomaly evidence was estimated by combining perceptual image differences with token-surprisal scores based on negative log-likelihood. Automated detection was evaluated on pelvic MRI with synthetic global and real clinical anomalies, and on brain MRI with clinically annotated fastMRI+ abnormalities. Sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and false-positive behavior in held-out normal cases were assessed. The framework achieved robust detection across hidden evaluation cohorts, with AUCs of 0.97 (95% CI, 0.95-0.98) and 0.81 (95% CI, 0.74-0.87) for pelvic and brain MRI, respectively. Heatmap analysis showed strong spatial agreement between detected anomalies and ground-truth locations, supporting localization accuracy and interpretability. These results support the potential of unsupervised anomaly detection as an automated MRI quality-control layer for radiotherapy workflows, with transparent visualization of image regions likely to compromise downstream AI-based tasks.

---

### Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology

Authors: Gustavo, Angulo
Published: 2026-05-23
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.24608v1

We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematical morphology. The central tool is the Matheron--Maragos--Banon--Barrera (MMBB) universal representation theory for translation-invariant operators, which we apply systematically to every layer of a standard deep network. The principal finding is that the standard CNN pipeline (linear convolution~$+$ ReLU~$+$ flat max-pooling) is a cross-lattice operator: the convolution is an erosion in the Fourier inf-semilattice while ReLU is a lattice-join closing and max-pooling is a dilation in the pointwise max-plus lattice, and their composition is a morphological opening in neither. A second finding is that the upper adjoint of ReLU in the pointwise lattice is a global (non-local) operator, the identity on globally non-negative functions and $-\infty$ otherwise, so no local morphological erosion can form an adjunction pair with ReLU. These two results together provide the precise algebraic reason why depth in standard CNNs introduces genuine representational power: the composed layer is not idempotent. Three layer designs that are genuine idempotent openings are identified and fully characterised: the pure max-plus morphological layer (pointwise lattice), the spectral Wiener layer (Fourier lattice), and the self-dual morphological layer. We establish a complete fixed-point and convergence theory. The framework also unifies max-pooling, strided convolution, and the Laplacian pyramid under the Goutsias--Heijmans adjoint pyramid theory, and gives the Activation--Pooling Dilation (APD) factorisation with its correct adjoint.

---

### LC-Flow: Learning Local Continuous Optical Flow and Confidence from events

Authors: Gunwoo Jeon, Chaesong Park, Jongwoo Lim
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24604v1

Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer from domain overfitting, while model-based local methods operate statelessly, discarding temporal history between predictions and yielding inaccurate flows. We propose \textbf{LC-Flow}, the first temporally continuous, learning-based optical flow estimator that operates purely from local events. At its core, a Continuous Local Recurrent Network maintains persistent hidden states per spatial grid, incrementally accumulating temporal context as events arrive. Unlike frame-based methods constrained to fixed accumulation windows, and unlike stateless model-based methods that recompute motion from scratch at each step, LC-Flow produces sparse local flow estimates at arbitrary timestamps with full motion history. To address the inherent ambiguity of local observations, we jointly learn a confidence score that quantifies the reliability of each prediction, explicitly handling event sparsity and the aperture problem. This confidence serves a dual role: filtering unreliable estimates for downstream tasks such as visual odometry, and providing principled weights for a multi-scale confidence-guided aggregation that reconstructs globally consistent flow from the sparse local outputs. LC-Flow achieves state-of-the-art performance among local methods on both MVSEC and DSEC, while the confidence-guided aggregation establishes a new overall state-of-the-art on the MVSEC benchmark, surpassing heavy frame-based networks that rely on global spatial priors.

---

### CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer

Authors: Piotr Wilam
Published: 2026-05-23
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.24603v1

A sparse 8-layer code transformer develops dedicated neural circuitry for every Python construct tested, and that circuitry is organised by a clean computational principle rather than by semantic category. We extract neural circuits for 106 concepts (43 AST node types, 63 builtin objects) by marginalising across 63,800 controlled prompts, and decompose each circuit into concept-specific and token-driven components using contrastive checker prompts that present a keyword token without its associated syntactic structure. Three findings emerge. First, all 106 concepts produce non-empty universal circuits at every one of nine parameter settings, and the ranking of concept-specificity across constructs is stable across the sweep - survival is not an artifact of a permissive threshold. Second, AST circuits contain a genuine concept component distinct from token activation: concept-only neurons constitute up to 62.5% of the loudest-firing neurons at mid-to-late layers, while builtin circuits are almost entirely token-driven. Third, six computationally atomic constructs - Import, ImportFrom, Break, Continue, Pass, Assert - cluster together despite being semantically unrelated, sharing only the property of being single-statement constructs requiring no nested body; this atomicity super-cluster, together with a four-tier hierarchy organised by token ambiguity and structural distinctiveness, shows that the model's internal organisation tracks computational structure rather than meaning. The methodology, full decomposition data, and analysis code are released.

---

### Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory

Authors: Quanjiang Li, Zhiming Liu, Wei Luo, Tingjin Luo, Chenping Hou
Published: 2026-05-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.24602v5

Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly associated with a human-like attention distraction phenomenon, where humans under divided focus experience degraded visual clarity and produce inaccurate descriptions, while in models the same mechanism manifests as spatial inconsistency in multi-head attention and temporal fading of attention to image tokens during decoding. We further provide theoretical insights that attention dispersion increases model complexity and degrades classification generalization. Motivated by these findings, we propose an Attention-Focused Approach for Improved Image Perception (AFIP), which corrects attention distraction via cross-head attention enrichment and reinforces visual grounding through dynamic historical attention enhancement. Extensive experiments on multiple benchmarks and models validate the effectiveness of AFIP without additional training. Code is available at: https://github.com/MIKUZ12/AFIP.

---

### Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

Authors: Zhimin Lin, Kun Cheng, Zhiyao Shu, Junhua Fang, Juntao Li, Fan Bai, Jie Gao
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24600v3

Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analysis. We argue this gap reflects a missing credibility practice from human QDA: peer debriefing, in which an analyst seeks feedback from a disinterested peer and uses it to refine their coding. To bring this practice into LLM-assisted QDA, we propose Agent-as-Peer-Debriefer, a multi-agent QDA framework that builds peer debriefing into key coding steps. In our framework, a Hierarchical Coding Agent follows the standard QDA process to generate codes, sub-themes, and themes, along with self-explanations and reflection memos. It then shares these outputs with three Peer-Debriefing Agents, each applying a distinct analytical perspective (Theory-Driven, Data-Driven, or Applied) and refining the codes by keeping, renaming, reassigning, merging, or splitting them. These perspectives are drawn from established human QDA practices that generalize across domains and datasets. To evaluate the framework, we test it on three datasets across two domains with three LLMs, measuring semantic similarity to human-annotated codes. Across all settings, perspective-based, peer-debriefing refinement aligns more closely with human codes than a single-LLM baseline, and an ablation further shows the gain is not merely from additional refinement. The three perspectives also produce distinct trade-offs, showing that the choice of perspective is a meaningful and controllable design decision. More broadly, these findings suggest that simulating peer debriefing with explicit perspectives is a promising route to more credible LLM-assisted QDA.

---

### Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

Authors: Zhimin Lin, Kun Cheng, Zhiyao Shu, Junhua Fang, Juntao Li, Fan Bai, Jie Gao
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24600v2

Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analysis. We argue this gap reflects a missing credibility practice from human QDA: peer debriefing, in which an analyst seeks feedback from a disinterested peer and uses it to refine their coding. To bring this practice into LLM-assisted QDA, we propose Agent-as-Peer-Debriefer, a multi-agent QDA framework that builds peer debriefing into key coding steps. In our framework, a Hierarchical Coding Agent follows the standard QDA process to generate codes, sub-themes, and themes, along with self-explanations and reflection memos. It then shares these outputs with three Peer-Debriefing Agents, each applying a distinct analytical perspective (Theory-Driven, Data-Driven, or Applied) and refining the codes by keeping, renaming, reassigning, merging, or splitting them. These perspectives are drawn from established human QDA practices that generalize across domains and datasets. To evaluate the framework, we test it on three datasets across two domains with three LLMs, measuring semantic similarity to human-annotated codes. Across all settings, perspective-based, peer-debriefing refinement aligns more closely with human codes than a single-LLM baseline, and an ablation further shows the gain is not merely from additional refinement. The three perspectives also produce distinct trade-offs, showing that the choice of perspective is a meaningful and controllable design decision. More broadly, these findings suggest that simulating peer debriefing with explicit perspectives is a promising route to more credible LLM-assisted QDA.

---

### Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Authors: Yuxin Zhang, Mengxue Hu, Zheng Lin, Xiaoyi Fan, Fan Xie, Zihan Fang, Jing Yang, Wenjun Zhu, Zhiwen Chen, Chengfei Lv, Zhe Chen
Published: 2026-05-23
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2605.24598v1

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

---

### Learning to Reason Efficiently with A* Post-Training

Authors: Andreas Opedal, Francesco Ignazio Re, Abulhair Saparov, Mrinmaya Sachan, Bernhard Schölkopf, Ryan Cotterell
Published: 2026-05-23
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.24597v1

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid proof itself, requiring a reasoning procedure in which intermediate inferences are correct. Specifically, we investigate whether LLMs can learn to generate correct and efficient proofs with guidance from A* search -- an algorithm that guarantees an optimally efficient path to a goal. We explore two training techniques: supervised fine-tuning on execution traces from A* and reinforcement learning with A*-informed process reward models. Empirically, we find that Llama-3.2 models in the 1B--3B range benefit substantially from A* post training, going from near-zero accuracy to outperforming DeepSeek-V3.2 -- a much larger model. Our analysis uncovers a trade-off: while simple correctness rewards maximize accuracy, A*-informed signals strike a balance between accuracy and efficiency. Furthermore, we find that on larger search spaces, models trained with imperfect heuristics exhibit superior accuracy. Our results demonstrate a promising direction towards reasoning guided by principles derived from classical search algorithms.

---

### Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration

Authors: XiaoWan Hu, Jing Yang, HeNan Liu, HuaQiu Li, Mai Xu
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24593v1

Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while overlooking physically consistent priors. The insufficient degradation prompts impose the heavy training burden and high sampling costs during zero-shot diffusion. Moreover, the fixed inference trajectory often collapses to suboptimal solutions under complex corruptions. We observe that heterogeneous degradations can be reparameterized into a minimal set of physically coherent parameters for compact representation. Based on this insight, we first propose a unified physical zero-shot image restoration (UP-ZeroIR) framework that explicitly models heterogeneous degradations into a homogeneous all-in-one distribution. The distribution can be optimized directly in the latent space, enabling principled solution exploration and effective prompt adaptation. Besides, we introduce a dynamic quality-refinement strategy that adaptively adjusts the diffusion trajectory for robust globally optimal convergence. Extensive experiments demonstrate that our method achieves state-of-the-art performance across both single and mixed degradations. Our code is available at https://github.com/yangjinglyy/UP-ZeroIR

---

### Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions

Authors: Ziyan Huang, Lang Wu, Hongji Wang, Yifei Liu, Dongliang Tang, Hongqiao Wang
Published: 2026-05-23
Categories: cs.CV, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.24590v2

Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Existing methods typically rely on simplified noise assumptions, which limits their effectiveness under realistic imaging conditions. In this work, we propose Physen-Noise2Noise, a self-supervised deblurring framework guided by the physical model of defocus imaging, which leverages noisy multi-frame observations without requiring clean reference images. Unlike conventional Noise2Noise-based approaches that assume zero-mean noise, we derive a frequency-domain constraint inherent to the defocus imaging process and incorporate it into the learning framework via a learnable noise bias parameter. In addition, a multi-frame noisy initialization strategy is introduced to suppress complex biased noise prior to deblurring, providing a more stable starting point for reconstruction. This formulation explicitly models biased noise and enables joint bias correction and high-frequency detail recovery during training. Furthermore, we develop a pretrain-finetune variant to enhance robustness and generalization under challenging noise conditions. Extensive experiments on both simulation and real-world datasets demonstrate that the proposed method consistently outperforms state-of-the-art self-supervised approaches for defocus deblurring in the presence of complex biased noise.

---

### HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection

Authors: Shubham Gupta, Nikhil Panwar, Partha Pratim Roy
Published: 2026-05-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.24588v1

While Deep Learning (DL) enhances automated electrocardiogram (ECG) analysis, clinical deployment is hindered by class imbalance and the generalization gap. This paper presents HeartBeatAI, a deep learning framework combining domain generalization, multi-scale feature aggregation, and clinical explainability for robust 12-lead ECG classification. Moving beyond image-based paradigms, HeartBeatAI integrates a Squeeze-and-Excitation (SE) ResNet to isolate diagnostic leads alongside a Multi-Layer Concentration Pipeline to capture macro-rhythm and micro-morphological anomalies. To mitigate domain shift, the framework employs MixStyle regularization and Label Smoothing. Rigorous benchmarking across four large-scale datasets using intra-source and Leave-One-Domain-Out (LODO) protocols demonstrates high performance (98% Macro F1-score) under intra-source conditions. However, LODO evaluations reveal significant degradation in detecting rare anomalies, highlighting a persistent challenge in cross-institutional deployment.

---

### Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language

Authors: Mathis Immertreu, Achim Schilling, Thomas Kinfe, Patrick Krauss
Published: 2026-05-23
Categories: cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2605.24585v1

Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Representations (SRs), which model the expected discounted distribution of future states rather than the immediate next state. We transfer this framework to natural language and train neural networks to predict future word distributions across multiple temporal horizons, thereby learning representations of long-range transition structure. We train a deep residual neural network on WikiText-103 (103 million tokens; 20,000-word vocabulary) and optimize successor representations as probability distributions using KL divergence. Without explicit linguistic supervision, structured language representations emerge spontaneously. After training, the learned space develops a clear geometric organization with respect to part-of-speech (POS) categories: nouns, verbs, and adjectives become separable and recoverable through unsupervised clustering. This organization depends systematically on predictive horizon, with short horizons producing the strongest syntactic structure and longer horizons increasingly integrating broader contextual and semantic information. At finer resolutions, additional interpretable lexical substructure emerges, revealing coherent subclasses within major word categories. These findings suggest that syntactic categories need not be explicitly encoded but may arise as a consequence of predictive sequence learning. To our knowledge, this work provides the first systematic application of successor representations to natural language and establishes a conceptual bridge between reinforcement learning, linguistics, and cognitive neuroscience.

---

### LAPLEX: The FFT of Learnable Laplace Kernels

Authors: Łukasz Struski, Hanna Blazhko, Piotr Kubaty, Jacek Tabor
Published: 2026-05-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.24584v1

Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators. A LAPLEX layer is a typically full-rank dense matrix, implicitly defined by learnable coordinate anchors, with FFT-like scaling. Consequently, it supports trainable matrix--vector operations at vector dimensions up to $10^9$ on modern GPUs. As a neural layer, it yields compact projections and classification heads interpretable as soft, trainable routing models. The same primitive also serves as an efficient Gram operator, enabling high-dimensional covariance models on flattened images of dimension $3 \cdot 10^6$ that preserve visible spatial structure without imposing convolutional bias. These applications reflect a single principle: dense geometry can be learned without storing a dense matrix, which enables data-adaptive global interactions in regimes where ordinary dense layers are out of reach. In this sense, LAPLEX separates expressivity from storage cost: it behaves like a dense trainable matrix, but is represented and applied through a small structured set of parameters.

---

### Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol

Authors: Yuki Nakamura
Published: 2026-05-23
Categories: cs.LG, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2605.24583v3

Comparing a model's internal activations before and after alignment is a natural way to ask what safety training changes: one forms the matrix of paired aligned-minus-base activations on safety-relevant inputs and reads off its effective rank or top direction. We show the obvious way to form this matrix is confounded. The aligned model is evaluated under a chat template the base model never saw, so the naive difference conflates the alignment shift with chat formatting. We introduce a four-variant decomposition of the modification matrix (naive, template-controlled, within-aligned, and difference-in-differences, DiD) that separates the two effects. Template control alone removes a 2.0-3.9x inflation of the measured effective rank across Llama-3.1-8B, Gemma-2-9B, and Qwen-2.5-7B; the DiD contrast is what recovers the refusal direction of Arditi et al. (2024), lifting its cosine alignment from 0.18-0.39 to 0.50-0.86. Projection-ablation across the three families confirms the recovered subspace is behaviorally active and that singular-value order is not causal order. We validate the protocol on a controlled testbed and distill it into measurement recommendations for activation-difference studies of alignment.

---

### WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems

Authors: Jiangnan Yu, Kisson Songqi Lin, Jilong Wu
Published: 2026-05-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.24579v1

Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression or preserved but never retrieved. We introduce a four-condition diagnostic protocol that evaluates a fixed reader under truncated full context (TFC), oracle evidence (OE), complete stored memory (CSM), and retrieved memory (RM). Under this fixed-budget LongMemEval setup, write-side gaps exceed retrieval-side gaps for most tested baselines, with four of six baselines robustly write-dominant under our default diagnosis margin. Motivated by this diagnosis, we propose Expected Predictive Compression (EPC), which moves the key decision--what information to retain--to write time by using an LLM to anticipate likely future questions and preserve the minimal supporting evidence under the token budget, while leaving retrieval unchanged at question time. Across all 500 LongMemEval questions with three readers (GPT-5.2, Claude Sonnet 4, Gemini 2.5 Pro), EPC achieves the highest CSM scores among all systems (0.49 vs. 0.44 for Summary (LLM), the strongest baseline), reducing Delta_write to 0.04 while leaving Delta_retr comparable to other LLM-based systems. These results suggest that, on this benchmark and evaluation setup, improving what the write stage preserves is a key avenue for performance gains in the tested systems.

---

### World Models as Group Actions

Authors: Zijie Wang, Wei Zhang, Weiming Zhang, Fanqi Zhang, Xiao Tan, Yipeng Qin, Guanbin Li
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24578v1

Video world models have achieved strong visual realism, but this does not ensure that their dynamics are truly governed by actions. In this work, we argue that action faithfulness should be understood through the compositional structure of actions, which in many embodied settings follows a group structure (e.g., SE(2) for navigation). Based on this insight, we formalize action-conditioned world modeling as realizing a group action on the state space, providing a principled criterion for evaluating dynamics beyond visual quality. To operationalize this framework, we propose a unified approach that enforces identity, inverse, and composition consistency via latent-space regularization with synthesized supervision, avoiding additional data collection. We further introduce two metrics: Group-Action Consistency (GAC) and Group-Action Robustness (GAR), to evaluate structural correctness and rollout stability. Extensive experimental results show that our method consistently improves both GAC and GAR in state-of-the-art video world models without degrading perceptual quality.

---

### Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m

Authors: Jordan F. McCann
Published: 2026-05-23
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.24577v1

Independently trained transformers compute the same function in residual-stream bases that differ by a uniform random rotation on $\mathrm{SO}(d_{\mathrm{model}})$. We call this phenomenon polymorphism: same function, mutually unintelligible interior coordinates. One matrix multiplication per model pair removes it: an orthogonal Procrustes fit on a single batch of activations transfers sparse-autoencoder feature dictionaries and steering vectors between independently trained models, with no retraining. The phenomenon is invisible to the standard SAE universality metric. Decoder-column cosine similarity matches across seeds at 98%, the SAE-universality headline number, while an SAE trained on one seed reconstructs another seed's activations at negative explained variance, worse than predicting the constant mean. The decoder columns align; the encoder reads from a rotated frame. A single Procrustes rotation $R$ restores reconstruction to within 0.025 EV of the within-seed ceiling at every internal site. $R$ is Haar-distributed: $\|R - I\|_F$ matches the random-orthogonal prediction $\sqrt{2 d_{\mathrm{model}}}$ to 0.1% at $d_{\mathrm{model}} = 512$, and a Kolmogorov-Smirnov test of $R$'s eigenvalue spectrum against Haar $\mathrm{SO}(d_{\mathrm{model}})$ returns $p \approx 1.000$ pooled and per-pair. Diff-of-means steering vectors transfer in three regimes by alignment with $R$'s invariant subspace: clean when pinned by shared output weights, partial when overlapping the rotated subspace, inverted otherwise. With no shared I/O (Pythia), all three collapse to universally inverted. The same rotation account holds across training checkpoints within a single run. Validated on a 104k-parameter Dyck-3 transformer and nine independently-trained Pythia-70m seeds on The Pile, via a pre-registered four-bar operational framework. Frontier-scale (10B+) replication remains open.

---

### Associations between echocardiographic traits and AI-ECG predictions of heart failure

Authors: Elias Stenhede, Eivind Bjørkan Orstad, Torbjørn Omland, Henrik Schirmer, Arian Ranjbar
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24576v1

Artificial intelligence-enabled electrocardiography (AI-ECG) can detect heart failure (HF), including disease not captured by left ventricular ejection fraction (LVEF), but the cardiac phenotypes underlying model predictions remain unclear. We therefore investigated whether AI-ECG-predicted HF risk aligns with established echocardiographic measures of myocardial dysfunction, remodelling, and filling pressures. We retrospectively analysed ECG and echocardiography data from 8147 patients who underwent both examinations within three days at Akershus University Hospital between 1 January 2023 and 1 June 2025. A previously validated AI-ECG model for HF detection was applied to all ECGs. Spearman's rank correlation $ρ$ quantified associations between echocardiographic parameters and AI-ECG risk. Subgroup analyses were performed by sex and left ventricular ejection fraction (LVEF). External validation included 36,286 ECG-echocardiography pairs from Columbia University Irving Medical Center. Global longitudinal strain (GLS) showed the strongest correlation ($ρ$=0.57), followed by mitral annular plane systolic excursion (MAPSE) ($ρ$=-0.49) and LVEF ($ρ$=-0.45). In patients with LVEF>50%, correlations remained substantial for GLS, MAPSE, and diastolic-related parameters. Volumetric left ventricular indices correlated less strongly in women, whereas diastolic indices showed stronger correlations in women than in men. Physiological validation showed that AI-ECG HF risk predictions align primarily with measures of systolic function, particularly global longitudinal strain, while also capturing diastolic-related abnormalities in patients with preserved LVEF. This approach may improve clinical interpretability and identify opportunities for model refinement.

---

### AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models

Authors: Hao Liu, Siyuan Yang, Qinglei Hu, Dongyu Li
Published: 2026-05-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.24573v1

Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth orbits grow crowded and contested. Current analysis pipelines are built for detection: they are good at picking up that something happened, less good at reasoning about what it means. AstroMind is a physics-grounded benchmark designed to close that gap. It draws on high-fidelity astrodynamics simulations and real observational constraints, converting them into verifiable reasoning problems across three task types: intent inference, maneuver parameter estimation, and threat assessment. Each scenario includes realistic sensing noise and multi-source textual intelligence at varying reliability levels. Evaluation metrics capture both semantic correctness and quantitative consistency under physical constraints. Benchmarking a suite of open-weight models shows no single model dominates every axis: Qwen3 (32B) leads on intent inference accuracy; QwQ (32B) leads on threat assessment and achieves the lowest median relative error on parsed items; GPT-OSS (20B) produces the strongest judged reasoning quality and extracts the most scalar values for parameter estimation (136 of 241 parsed items). Training data composition and reasoning style matter as much as model size. Structured reasoning prompts help consistently across tested 8B models, with larger gains for those that can already track physical constraints. AstroMind gives the field a shared test for a problem where getting the physics right and reading the tactical situation correctly are both required -- neither is sufficient on its own.

---

### PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training

Authors: Sattam Altuuaim, Lama Ayash, Muhammad Mubashar, Naeemullah Khan
Published: 2026-05-23
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.24570v1

Despite the central role of optimization in deep learning, most optimizers rely on update structures whose functional form is fixed before training begins. This static design can limit their ability to respond to changing gradient behavior across the loss landscape, where training may shift between stable, noisy, and inconsistent regimes. This study proposes PILOT (Policy-Informed Learned OpTimizer), an online optimizer that adapts its update behavior during training. Rather than using a fixed balance between momentum, normalization, and sign-based updates, PILOT uses gradient-direction agreement as a signal of local training stability. Conditioning the update rule on this agreement signal allows the optimizer to adjust its behavior when gradients become stable, noisy, or inconsistent. Experiments on FashionMNIST and CIFAR-10 show that PILOT consistently achieves the highest accuracy among the evaluated optimizers across convolutional settings. On the CNN architecture, PILOT reaches 94.13% on FashionMNIST and 81.94% on CIFAR-10. On ResNet-18, it further improves performance, reaching 95.71% on FashionMNIST and 93.42% on CIFAR-10. These results suggest that learning how to adapt the update structure during training can improve performance across both compact and deeper convolutional models while preserving a simple first-order optimization framework. The implementation of PILOT is publicly available at https://github.com/SattamAltwaim/PILOT.git

---

### EMA: Effort Metric Attention for Anatomical Effort-Guided Human Motion Diffusion

Authors: Joshua Siy, Huakun Liu, Yutaro Hirao, Monica Perusquia-Hernandez, Hideaki Uchiyama, Kiyoshi Kiyokawa
Published: 2026-05-23
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2605.24566v1

Human motion diffusion models can synthesize action sequences from text, but controlling motion intensity remains challenging. Existing approaches rely on effort-related adverbs, which are ambiguous and fail to capture quantitative aspects such as pacing, often resulting in flat and monotonous dynamics. We propose an intensity-control framework based on Effort Metric Attention (EMA), a cross-attention module that conditions diffusion on numerical effort signals. Inspired by Laban Movement Analysis (LMA), the framework focuses on the Time and Weight effort factors. We approximate these factors using two kinematic metrics: peak joint positional change for pacing and collective joint positional change for motion amount. EMA enables fine-grained, region-wise control without costly post-hoc optimization. We introduce two evaluation tasks, metric-to-motion consistency and body-part-level effort modulation, to assess numerical fidelity and localized control. Experiments and a user study show near-monotonic alignment between specified effort levels, generated motion dynamics, and established LMA descriptors. These results indicate effective and interpretable control of effort dynamics in practice.

---

### Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models

Authors: Weixian Waylon Li, Mengyu Wang, Tiejun Ma
Published: 2026-05-23
Categories: cs.AI, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2605.24564v2

Backtesting large language models (LLMs) on historical financial data is unreliable when their pre-training data include the evaluated events. An LLM trained in 2024 may already encode how stocks moved during 2018-2020. We name this failure parametric look-ahead bias and propose FinCAD, an inference-time adaptation of Context-Aware Decoding that attenuates contributions from memorised historical outcomes without retraining. FinCAD pairs an adversarial bias-discovery pipeline that learns a model-specific memory-activating prior prompt with an entity- and date-adaptive rule that scales the CAD strength using a per-(entity, date) confidence signal. Across five 7-14B LLMs and five mega-cap equities, the largest model-level mean in-sample return correction is -67.1%. For the three larger models, 2025 out-of-sample returns remain within $8K and mean Sharpe within $\pm$0.10 of baseline; mean general-benchmark accuracy remains positive or within -1.7 points for four of five models. On an eleven-model leaderboard, FinCAD raises the subset-averaged in-sample/out-of-sample Spearman correlation from +0.779 to +0.846, yielding rankings that are more closely aligned with post-cutoff performance.

---

### Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models

Authors: Weixian Waylon Li, Mengyu Wang, Tiejun Ma
Published: 2026-05-23
Categories: cs.AI, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2605.24564v1

Backtesting large language models (LLMs) on historical financial data is unreliable because pre-training cuts off after the events happened. An LLM trained in 2024 already "knows" which way 2018-2020 stocks moved. We name this failure parametric look-ahead bias and propose FinCAD, an inference-time adaptation of Context-Aware Decoding that suppresses an LLM's memory of historical outcomes without retraining. FinCAD pairs an adversarial bias-discovery pipeline that learns a model-specific memory-activating prior prompt with an entity- and date-adaptive rule that scales the CAD strength to per-(entity, date) memorisation, so the penalty fires on memorised in-sample dates and decays to zero out-of-sample. Across five 7-14B LLMs and five mega-cap equities, FinCAD cuts in-sample backtest returns by up to -67.1% on memorised dates while leaving 2025 out-of-sample returns within $8K and Sharpe within 0.10 of baseline, and preserves general-purpose reasoning within 1.7 pts. On an eleven-model leaderboard, it raises the in-sample / out-of-sample Spearman correlation from +0.779 to +0.846, recovering rankings that genuinely predict out-of-sample performance.

---

### PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Prediction

Authors: Naman Mishra, Shankar Gangisetty, C. V. Jawahar
Published: 2026-05-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.24562v1

Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation decisions in complex traffic environments. Recent advances in large vision-language models offer a powerful new paradigm for these tasks by combining high-capacity visual understanding with flexible natural language reasoning. In this work, we introduce PedestrianQA, a large-scale video-based dataset that formulates pedestrian intention and trajectory prediction as question-answering tasks augmented with structured rationales. PedestrianQA expresses richly annotated pedestrian sequences, in natural language, enabling VLMs to learn from visual dynamics, contextual cues, and interactions among traffic agents while generating concise explanations of their predictions without needing specialized architectures tailored for each task. Empirical evaluations across PIE, JAAD, TITAN, and IDD-PeD show that finetuning state-of-the-art VLMs on PedestrianQA significantly improves intention classification, trajectory forecasting accuracy, and the quality of explanatory rationales, demonstrating the strong potential of VLMs as a unified and explainable framework for safety-critical pedestrian behavior modeling.

---

### Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference Components

Authors: Ling Zhan, Xiaoyao Yu, Tao Jia
Published: 2026-05-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.24558v1

AI for Science (AI4Science) workflows often treat the released dataset as a fixed interface to the underlying system. However, in domains relying on \emph{indirect observation}, the learner observes a derivative representation produced by multi-stage measurement, reconstruction, and preprocessing pipelines. \textbf{We argue that these measurement-to-dataset pipelines are inference components: treating their outputs as ``given data'' freezes an observation model and obscures uncertainty over feasible pipeline choices.} We identify three failure modes arising from this ``frozen lens'': \textbf{(C1) hidden hypothesis space}, where the released dataset does not specify the pipeline configuration or its validity conditions; \textbf{(C2) uncertified transportability}, where a pipeline may be documented but its regime of validity is untested, so failures under distribution shift cannot be adjudicated; \textbf{(C3) ungoverned multiplicity}, where many defensible pipelines exist and dispersion is real but not propagated into uncertainty-aware evidence. We stress-test these claims with a large-scale neuroscience empirical audit, finding a survival rate of $\approx 0.0004\%$ under a cross-dataset stability criterion. We call on the AI4Science community to make pipelines \emph{computable} inference objects via domain-specific Computable Observation Frameworks. This shift enables quantifying pipeline adequacy and stability, converting implicit implementation choices into auditable, reproducible, and cumulative scientific evidence.

---

### The Multilingual Curse at the Retrieval Layer: Evidence from Amharic

Authors: Yosef Worku Alemneh, Kidist Amde Mekonnen, Maarten de Rijke
Published: 2026-05-23
Categories: cs.IR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.24556v1

Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across many languages. We argue that this assumption breaks down for underrepresented, morphologically rich languages, and use Amharic as a diagnostic case. Under a shared passage retrieval protocol covering dense, late-interaction, learned sparse, and cross-encoder paradigms, we compare zero-shot multilingual retrievers, Amharic-fine-tuned multilingual retrievers, and monolingual Amharic retrievers. The strongest zero-shot multilingual retriever underperforms the strongest monolingual Amharic first-stage retriever by 23% relative MRR@10. Fine-tuning two recent multilingual embedding models on the same Amharic supervision yields 32-60% relative MRR@10 gains over zero-shot, but the best Amharic-fine-tuned multilingual model remains below the strongest monolingual Amharic retriever. These findings indicate that zero-shot multilingual retrieval is not a sufficient proxy for equitable information access in the LLM era: for underrepresented languages, retrieval must be evaluated and adapted in-language rather than inferred from aggregate multilingual benchmarks. To foster future research, we publicly release the dataset, codebase, and trained models at https://github.com/rasyosef/amharic-neural-ir.

---

### IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring

Authors: Xinge Peng, Yiting Lu, Xin Li, Zhibo Chen
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24553v1

We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods typically support only partial perception dimensions, such as quality description and question answering~(\textit{i.e.}, reasoning) or pixel-level grounding. This limitation largely stems from the absence of (i) a unified task and data formulation and (ii) effective optimization paradigms for multi-granularity learning. To address these limitations, we formulate a rigorous four-task paradigm covering global and local quality description, pixel-level grounding, and region-level referring. Based on this formulation, we construct a corresponding IQA dataset with a scalable and automatic annotation pipeline, thereby providing a solid foundation for unified multi-granularity learning. To further enable unified perception, we adopt a conflict-free two-stage design that progressively extends text-level multi-granularity understanding to pixel-level grounding: (i) the first stage equips the model with fine-grained text-level reasoning across multiple IQA tasks, and (ii) the second stage introduces a training-free text-to-point grounding paradigm, which bridges textual semantics and pixel-level perception by mapping token logits to spatial coordinates. Based on these efforts, we achieve IQA-Spider with unified multi-granularity explainable image quality assessment. Extensive experiments across multiple benchmarks demonstrate strong performance, validating the effectiveness and versatility of the proposed formulation and framework.

---

### Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models

Authors: Seokil Ham, Jaehyuk Jang, Wonjun Lee, Changick Kim
Published: 2026-05-23
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.24550v1

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning can prevent models from learning undesired behaviors, but its mechanism remains unclear. In this paper, we revisit temporary jailbreaking as a defense against harmful fine-tuning and provide a gradient-level analysis showing that it saturates safety-degrading gradients while preserving benign task-relevant gradients. Based on this insight, we propose a Buffer-and-Reinforce fine-tuning framework that buffers harmful updates during user fine-tuning and reinforces safety after adaptation. Specifically, BufferLoRA induces temporary jailbreaking as a removable adapter to reduce harmful updates during user fine-tuning. After adaptation, ReinforceLoRA, trained to recover refusal behavior under the temporarily jailbroken state, is integrated with UserLoRA via QR decomposition-based merging to reinforce safety while preserving user-task performance. Extensive experiments show that our framework achieves superior safety and utility with no additional safety data during user fine-tuning and minimal computational cost.

---

### PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models

Authors: Mustafa Hayri Bilgin, Mariam Barry, Albert Bifet, Azzedine Idir Ait Said, Soumya Banerjee
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24549v1

Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously acquired reasoning abilities. This tension reflects a plasticity-stability dilemma: models must incorporate new knowledge while preserving skill-critical representations. In this work, we study this trade-off through the spectral structure of multilayer perceptron weight matrices. We show, both theoretically and empirically, that information essential for reasoning is not localized only in dominant singular directions, but is instead distributed across the singular spectrum. Motivated by this observation, we introduce PALoRA, a two-stage framework for knowledge injection with reduced interference. PALoRA first trains a Singular Value Fine-Tuning (SVF) expert on a reasoning dataset and uses its learned singular scaling vector as a frozen geometric probe to identify components that are critical for the target skill. It then performs factual knowledge injection with Low-Rank Adaptation (LoRA) under a structural orthogonality constraint, ensuring that updates avoid the identified skill-relevant subspace. Across Llama 3.1 8B and Mistral 7B, and across mathematical, coding, and scientific reasoning benchmarks, PALoRA preserves on average 95% of the SVF expert's reasoning performance while maintaining competitive factual recall. It consistently improves skill retention over prior spectral Parameter-Efficient Fine-Tuning (PEFT) methods while adding less than 0.006% parameter overhead.

---

### Deep ZakaiJ: Structured Filtering for Jump-Diffusion Time Series Forecasting

Authors: Yan Leng, Thibaut Mastrolia, Hao Wang
Published: 2026-05-23
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2605.24548v1

Time series driven by unobserved latent states frequently exhibit abrupt jump discontinuities whose timing and magnitude cannot be predicted from observed history alone. Classical jump-diffusion models offer a principled mathematical framework but assume rigid parametric forms, while recent neural jump models operate on fully observed trajectories without inferring the hidden states that govern the dynamics. We propose \textit{Deep ZakaiJ}, a latent-state model for partially observed jump-diffusion systems that embeds the Zakai nonlinear filtering equation into a neural encoder--decoder architecture. The encoder recursively updates a belief over the latent state via Strang splitting into three interpretable substeps: prior propagation, diffusion innovation, and jump innovation, yielding a differentiable, first-order-accurate approximation of the exact filtering evolution. The decoder is a structured jump-diffusion model explicitly conditioned on the filtered belief, preserving the separation between continuous dynamics and discontinuous shocks. On synthetic, financial, and oceanographic datasets, \textit{Deep ZakaiJ} improves distributional forecasts while remaining competitive in point accuracy, achieving calibrated predictive intervals and recovering interpretable latent structure in synthetic and qualitative case studies.

---

### RL with Learnable Textual Feedback: A Bilevel Approach

Authors: Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty, Amrit Singh Bedi
Published: 2026-05-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.24547v1

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, where a critic model generates natural language feedback to guide a reasoning model (the actor), augmenting scalar rewards with richer learning signals. However, existing methods typically treat feedback as fixed or auxiliary, which misses a key property: feedback should not merely be correct, but should improve the policy (actor model) when provided in context. This motivates a paradigm of learnable textual feedback for RL. Yet the learnability and usefulness of feedback depend on the policy's ability to learn from it, making RL with learnable feedback an inherently bilevel problem. We formalize this coupling as a Stackelberg bilevel program and derive Bilevel Natural Language Actor-Critic (Bi-NAC), which jointly trains a critic to generate reward-improving feedback and an actor to exploit it. Across MATH-500, MBPP, and GPQA, Bi-NAC improves sample and parameter efficiency over RL and fixed-critic baselines: our 2B model outperforms the 3B GRPO baseline, achieving 46.6% versus 41.4% on MATH-500, while our 6B model surpasses the 7B GRPO baseline, achieving 49.3% versus 43.6% on GPQA.

---

### Beyond Control-Flow: Integrating the Resource Perspective into Multi-Collaborative Process Modeling from Text

Authors: Anton Antonov, Humam Kourani, Alessandro Berti, Gyunam Park
Published: 2026-05-23
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2605.24546v1

Process modeling is a sub-domain of Business Process Management (BPM) focused on the translation of process artifacts into formal models. This task traditionally requires extensive human input and domain expertise in both BPM notations and the specific business context. While Large Language Models (LLMs) can now automate much of this manual work, current text-to-model approaches focus predominantly on the control-flow perspective-ordering activities without considering the collaborative aspect of the processes. In this paper, we introduce a resource-aware generation pipeline that produces formal BPMN 2.0 collaboration diagrams from natural-language descriptions. Rather than solely prompting an LLM for raw XML, we describe a compact, executable intermediate language with mandatory resource details defining both the organization (pool) and the role (lane). Cross-organization dependencies are materialized using the standard formal notation for such interactions-message events-while an orthogonal layout routine automatically handles the spatial arrangement of elements within pools and lanes. Experiments on ten business processes with nine LLMs show strong resource discovery while preserving control-flow quality and adding only marginal runtime overhead. This approach moves generative modeling toward a more comprehensive, multi-collaborative representation of business operations.

---

### Rethinking Federated Unlearning via the Lens of Memorization

Authors: Jiaheng Wei, Yanjun Zhang, He Zhang, Leo Yu Zhang, Chao Chen, Kok-Leong Ong, Jun Zhang, Yang Xiang
Published: 2026-05-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.24545v1

Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and remaining data, leading to ineffective unlearning and unfairness between clients. In this work, we revisit federated unlearning through the lens of memorization. We argue that unlearning should mainly remove the unique memorized information attributable to the data to be forgotten, while preserving overlapping patterns that are also supported by the remaining data. Specifically, we propose Grouped Memorization Evaluation, an example-level metric that separates memorized knowledge from overlapping knowledge. Building on this metric, we introduce Federated Memorization Pruning (FedMemPrune), a pruning-based unlearning approach that resets redundant parameters responsible for memorization. Extensive experiments show that FedMemPrune closely matches retraining-based unlearning baselines while more effectively eliminating memorization than existing federated unlearning algorithms, yielding strong unlearning performance without sacrificing the utility of retained knowledge.

---

### Emission-Aware Reinforcement Learning for Sustainable Electric Vehicle Charging and Carbon Dioxide Reduction Under Varying Renewable Penetration

Authors: Ninglin Ou, Mohammad A. Razzaque, Iftekher Islam Shovon, Shafkat Khan Siam, Shafiuzzaman K Khadem, Krishnendu Guha, Mayeen U Khandaker, Md. Noor-A-Rahim
Published: 2026-05-23
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2605.24543v1

The rapid growth of Electric Vehicle (EV) adoption challenges power distribution networks through peak load spikes, voltage instability, and transformer overloads from uncoordinated charging. While Model Predictive Control (MPC) and standard Reinforcement Learning (RL) methods have addressed these issues, existing approaches rarely treat real-time carbon intensity or fluctuating renewable energy (RE) availability as primary scheduling objectives, leaving substantial decarbonisation potential unrealised. This paper proposes an emission-aware RL strategy based on the Soft Actor Critic (SAC) algorithm, with a multi-objective reward that penalises carbon emissions, curtailed on-site renewables, and unmet user demand. The agent is trained within a unified benchmarking framework on the EV2Gym platform, incorporating behind-the-meter solar and wind profiles, time-varying EirGrid carbon intensity data, and realistic workplace EV behaviour across 25 Electric Vehicle Supply Equipment (EVSE) units. Nine control strategies, including heuristics, emission-aware MPC variants, and the proposed RL agent, are compared under five renewable penetration scenarios (0%-50%) over ten independent runs each. The RL agent achieves a carbon intensity as low as 23.96 grams of carbon dioxide per kilowatt-hour under 50% wind penetration, representing up to 87% emission reduction versus the uncontrolled baseline, and outperforms the external graph-based Power Distribution Network (PDN) benchmark. Transformer overload remains below 7 kWh across scenarios, against up to 1093 kWh for the As Fast As Possible (AFAP) heuristic, and renewable self-consumption reaches 52% under combined wind and solar supply. Embedding carbon intensity forecasts into the RL state and reward aligns charging with low-emission periods while preserving grid compliance and user satisfaction.

---

### AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Systems

Authors: Petar Radanliev
Published: 2026-05-23
Categories: cs.CR, cs.AI, cs.LG, cs.MA, cs.SE
arXiv: https://arxiv.org/abs/2605.24542v1

This paper examines the erosion of Public Key Cryptography (PKC) security under adaptive adversarial optimisation driven by artificial intelligence. The problem addressed is the growing mismatch between algorithm-centric cryptographic security models and operational attack realities, where adversaries exploit implementation-level observability rather than breaking cryptographic primitives.

---

### SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors

Authors: Natalia Trukhina, Vadim Vashkelis
Published: 2026-05-23
Categories: cs.LG, cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2605.24541v1

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered. This paper is a pilot framework, not a benchmark claim. We formalize LLM-mediated decompression, define a protected/lossy packet architecture, and evaluate six representation regimes over five author-constructed diagnostic cases: structured prose, JSON, CCL-Core, CCL-Min, SemanticZip ASCII, and SemanticZip emoji. An independent decoder LLM reconstructs typed semantic atoms from each compressed representation, and we score Critical Atom Recall, Weighted Atom Recall, precision, and tokenizer gain. In this pilot, structured prose has the highest recoverability, with WAR = 0.956 and 19.1% o200k_base token gain. CCL-Min is the strongest balanced point, with 39.4% token gain and WAR = 0.874. SemanticZip ASCII provides the largest useful compression, with 46.5% token gain and WAR = 0.802, while emoji-heavy SemanticZip performs worse on both compression and recovery. The main contribution is not the claim that these numbers establish a universal frontier. Rather, we introduce a reproducible experimental interface for studying lossy, LLM-decompressible text codes and a design principle: safety-critical and exact commitments should remain protected, while predictable low-risk context may be semantically zipped.

---

### DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback

Authors: Lirong Che, Yuzhe yang, Peiwen lin, Xu Cao, Chuang wang, Xueqian wang, Jian su
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24539v2

Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each rollout is costly, and a limited interaction budget may yield few examples of effective behavior. Sparse, delayed feedback also makes it difficult for a coding agent to diagnose failures and determine which modifications will improve performance. We present DemoEvolve, which uses human demonstrations to guide harness evolution under limited interaction budgets. The coding agent examines demonstrations alongside its own rollout history, extracts strategies and the conditions under which they apply, and turns them into reusable harness components. We compare demonstration guidance with self-rollout evolution and augmentation with retrieved textual knowledge under the same evolution procedure and agent interaction budget. On held-out seeds, DemoEvolve improves mean capped final-round progress from 16.83 to 20.00 in Balatro and mean floor reached from 18.17 to 28.83 in Slay the Spire 2, compared with the respective base harnesses. These results suggest that demonstrations can help harness evolution make better use of limited interaction experience by providing concrete guidance for diagnosis and modification.

---

### DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations

Authors: Lirong Che, Yuzhe yang, Peiwen lin, Chuang wang, Xueqian wang, Jian su
Published: 2026-05-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.24539v1

Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire task-specific competence by changing its external harness, while leaving the base model's general capabilities intact. Prior work shows that self-generated rollouts can support harness search, suggesting that agents may acquire new task competence through practice. Yet in long-horizon stochastic environments, self-practice becomes fragile: rewards are sparse, outcomes are high-variance, and failures are hard to attribute to concrete harness mechanisms. We introduce DemoEvolve, a demonstration-bootstrapped approach to harness evolution. When reward-only search is too broad and noisy, competent human trajectories serve as expert reference experience for the coding proposer, guiding harness-level diagnosis and editing. Experiments on Liar's Dice show that self-rollout evolution can work when episodes are short and failures are attributable. In contrast, Balatro exposes a harder long-horizon stochastic regime, where self-rollout evolution is misled by sparse feedback and candidate-selection noise, while tutorial-like textual knowledge alone does not yield stable improvement. Under the same limited budget, DemoEvolve produces more effective and auditable harness edits and achieves better performance. Overall, demonstrations make sparse-feedback harness evolution more diagnosable, localizable, and stable.

---

### Is Decentralized AI Governable? From Regulative Policy to Constitutive Protocol

Authors: Botao Amber Hu, Helena Rong
Published: 2026-05-23
Categories: cs.CY, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2605.24538v1

Every major framework for governing artificial intelligence presupposes an identifiable entity -- a developer, deployer, or operator -- who can be held responsible and compelled to comply. Decentralized AI (DeAI) dissolves this presupposition. We analyze DeAI as a six-layer decentralizing stack -- model, training, compute, harness, identity, and ownership -- and show how partial decentralization across layers compounds into what we call the \emph{governance vacuum}: a condition in which AI systems are consequential enough to require governance but lack the properties that existing frameworks presuppose in their targets. This vacuum takes two analytically distinct forms: an \emph{accountability gap}, where no addressable principal can be identified, and an \emph{incapacitation gap}, where even an identified principal cannot alter the running system. We demonstrate that these failures are not merely jurisdictional but defeat every presupposition of governance through normative address -- the communication of rules to a comprehending, responsive agent. Drawing on Lessig's modalities of regulation and Searle's distinction between regulative and constitutive rules, we argue for a shift in the locus of governance from policy to protocol, from normative address to architectural constraint. Protocol-based constitutive governance does not address the agents operating within a system but shapes the substrate that determines what kinds of actions are possible within it. We identify four ethical conditions -- legitimacy, contestability, transparency, and non-domination -- that such governance must satisfy to avoid degenerating into unaccountable technocratic power, and we argue that the central political challenge of governing AI in a decentralized world is reconstructing forms of democratic authorization for architectural choices that persist after the ordinary chain of policy has broken down.

---

### Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

Authors: Luoyu Chen, Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Feng Wu, Jianhuan Huang, Ahmed Asiri, Shui Yu
Published: 2026-05-23
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.24535v2

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility. However, existing steering methods are fundamentally supervised and tied to a static, limited training set, whereas real jailbreaks evolve and are often out-of-distributed from the training set, leading to failures on unseen attacks. In this paper, we tackle the failure on unseen jailbreaks problem, base on unsupervised latent direction discovery. We propose a bi-level adversarial training framework for zero-shot jailbreak defense. In the inner step, we simulate diverse jail-broken activations by extrapolating from refusal-state harmful-request activations via unsupervised latent direction discovery, which expands the coverage of real jailbreak activation subspaces. In the outer step, we train a potential-induced steering field to push these adversarial jailbroken states into refusal regions while keeping benign unchanged. Across three LLMs and six classical jailbreak families, our method achieves strong defense with attack success rates mostly below 5%, and rising subspace coverage throughout training helps explain the improved generalization.

---

### Generating Legal Commentaries from Case Databases via Retrieval, Clustering, and Generation

Authors: Max Prior, Niklas Wais, Matthias Grabmair
Published: 2026-05-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.24534v2

We present a fully automated pipeline that transforms large collections of court decisions into legal commentaries for statutes - without providing any handcrafted doctrinal framework. Using 4.555 decisions of the German Federal Court of Justice that cite sections 242, 280, 812 and 823 of the German Civil Code (BGB), we extract paragraph-level chunks, summarize their reasoning, and derive keywords, which are embedded and clustered. For each cluster, an LLM generates headings and synthesizes citation-rich sections, which are then merged into coherent commentaries by four state-of-the-art LLMs. We evaluate along five dimensions - topical relevance, heading-match, citation faithfulness, cluster distinction and logical ordering - using both a human expert and an LLM-judge. Our results show that commentary-like argument mining from court decisions to generate reports that can be refreshed within minutes at minimal cost is feasible, yet they highlight limitations arising from restricted sources and the normativity of legal reasoning.

---

### Generating Legal Commentaries from Case Databases via Retrieval, Clustering, and Generation

Authors: Max Prior, Niklas Wais, Matthias Grabmair
Published: 2026-05-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.24534v1

We present a fully automated pipeline that transforms large collections of court decisions into legal commentaries for statutes - without providing any handcrafted doctrinal framework. Using 4.555 decisions of the German Federal Court of Justice that cite sections 242, 280, 812 and 823 of the German Civil Code (BGB), we extract paragraph-level chunks, summarize their reasoning, and derive keywords, which are embedded and clustered. For each cluster, an LLM generates headings and synthesizes citation-rich sections, which are then merged into coherent commentaries by four state-of-the-art LLMs. We evaluate along five dimensions - topical relevance, heading-match, citation faithfulness, cluster distinction and logical ordering - using both a human expert and an LLM-judge. Our results show that commentary-like argument mining from court decisions to generate reports that can be refreshed within minutes at minimal cost is feasible, yet they highlight limitations arising from restricted sources and the normativity of legal reasoning.

---

### Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation

Authors: Fufan Zhang, Jingxiang Wang, Xiangjie Ye
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24533v1

Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations and must be inferred with the aid of shape priors. Existing methods acquire shape priors through fixed-capacity encoding spaces or expensive generative models, and inject them uniformly across all spatial positions without adapting to the varying prior demand between visible and occluded regions. In this paper, we propose a gated reliability-adaptive shape prior framework, which introduces a shape prior memory module that combines learnable prototypes via cross-attention to produce instance-adaptive shape priors through weighted prototype combination rather than generation. A spatial adaptive reliability gate then employs the signed distance field of the visible mask to modulate injection intensity at each position according to its occlusion depth, preserving reliable features in visible regions while directing shape compensation toward occluded areas. Experiments on two mainstream amodal instance segmentation benchmarks demonstrate that the proposed method outperforms existing approaches under multiple evaluation settings, improving the mean intersection-over-union over occluded regions by over 11 percentage points on one of the two benchmarks under the standard setting, while using approximately one-third of the total parameters. Linear probing analysis further reveals that the visible-mask cross-attention module implicitly encodes occlusion geometry into visual token representations, explaining the effectiveness of the proposed module decomposition.

---

### Image-Conditioned Instance Prompt Network for Referring Remote Sensing Image Segmentation

Authors: Biaoyu Ren, Qingsheng Wang, Cun Xu, Dingkang Yang, Wenxuan Wang
Published: 2026-05-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.24532v1

Referring Remote Sensing Image Segmentation (RRSIS) is a situated, task-driven cross-modal task related to the embodied perception paradigm, requiring models to align visual-spatial features with linguistic intentions for precise target perception. Recent research has focused on refining the granularity of textual features and optimizing image-text feature fusion to better guide target feature representations. However, insufficient descriptive granularity and sensitivity to semantic shifts can cause bottlenecks in cross-modal feature fusion. To address these issues, we propose the Image-Conditioned Instance Prompt Network (ICIPNet) with Bilateral Information Fusion, which is designed to alleviate bottlenecks in cross-modal feature fusion. ICIPNet introduces an Image-Conditioned Instance Prompt (ICIP) module to generate self-adaptive visual and semantic representations without external knowledge. The Bilateral Information Fusion (BIF) module enhances feature fusion along the token and channel dimensions. Experiments demonstrate that the proposed ICIPNet outperforms existing RRSIS models.

---