# Research Papers — 2026-05 · bundle page 59 of 326

> Full-text markdown of papers #2901–2950 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/59
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/58.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/60.md)

### Symmetry Defeats Auditing

Authors: Nick Merrill, Zeke Medley
Published: 2026-05-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2605.27836v1

We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).

---

### CAREF: Calibration-Aware Regularization for Explanation Faithfulness Without Rationale Supervision

Authors: Naphat Nithisopa, Teerapong Panboonyuen
Published: 2026-05-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.27835v2

We introduce CAREF, a parameter-efficient fine-tuning framework that jointly optimizes predictive accuracy and explanation faithfulness via calibration-aware regularization. At its core, CAREF couples entropy-based calibration with token-level sparsity control through a single unified loss, the Calibration-Aware Regularization for Explanation Faithfulness (LSCED), without requiring rationale supervision. Evaluated on four NLE benchmarks (COS-E, ECQA, ComVE, e-SNLI) with Flan-T5, our lightweight CAREF-AQ variant attains the best average accuracy (89.04) and explanation alignment (81.00 nBERT) using only 6.43% of trainable parameters, outperforming LoRA and AdaLoRA. To our knowledge, CAREF is the first method to unify entropy and sparsity regularization in a single training objective for interpretable LLM fine-tuning.

---

### Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach

Authors: Guang-Yuan Hao, Lars van der Laan, Aurélien Bibaut, Nathan Kallus
Published: 2026-05-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27834v1

We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrations are collected in a controlled environment. We formulate the problem as a joint system of Bellman equations across the source and target environments and develop minimax estimators for the target soft-$q$-function. Whereas a sequential solution approach first estimates the source reward and then plugs it into the target control problem, a coupled approach solves the source and target system of equations jointly. We show that, in contrast to the sequential approach, the coupled approach removes the first-order influence of source Bellman residual error. We characterize the local behavior of each approach, develop finite-sample soft-$q$-function error bounds, and prove regret guarantees for the resulting soft-control policy. An empirical investigation using a sepsis simulator validates the theoretical comparison.

---

### Playing with Words, Improving with Rewards: Training Language Models for Creative Association

Authors: Vijeta Deshpande, Namrata Shivagunde, Sherin Muckatira, Hadrien Glaude, Mikhail Gronas, Claire Stevenson, Roger Beaty, Anna Rumshisky
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27832v1

Large Language Models (LLMs) are being applied to increasingly difficult problems and use cases. To navigate their vast solution spaces effectively, LLMs need to be creative. Yet the subjective nature of creativity and the limits of human judgment make training LLMs for creativity especially challenging. As a solution, we train LLMs on Codenames, a word-association game that exercises the two central axes of creativity, divergent and convergent thinking, while yielding objectively verifiable outcomes. This verifiability lets us bypass human judgment and train with Reinforcement Learning with Verifiable Rewards (RLVR). We train Qwen3-1.7B, 4B, and 8B models and evaluate them on ten creativity and four reasoning benchmarks. We find that the precision-diversity trade-off is scale-dependent: the 8B model prioritizes creativity over precision, while the 1.7B and 4B models gain reasoning precision at the cost of creativity. Concretely, the 8B model shows modest but consistent creativity gains (8 of 10 benchmarks) with only minor reasoning degradation, whereas the smaller models achieve substantial gains on reasoning tasks. Our study presents a scalable and effective solution to train LLMs for creativity.

---

### Decentralized Parameter-Free Online Learning with Compressed Gossip

Authors: Tomas Ortega, Hamid Jafarkhani
Published: 2026-05-27
Categories: cs.LG, eess.SP, math.OC
arXiv: https://arxiv.org/abs/2605.27831v1

We study decentralized online convex optimization when agents communicate over a graph and messages may be compressed. Classical decentralized online methods typically require learning-rate choices that depend on the horizon, comparator scale, or other problem parameters, while compressed communication introduces additional disagreement that must be controlled. We propose DECO-EF (DEcentralized COin-betting with Error Feedback), a decentralized parameter-free online learning algorithm that combines coin-betting predictions with compressed difference-based gossip. Each agent maintains a clean accumulated state and a compressed tracker, and communicates only compressed state differences during gossip steps. The method is parameter-free in the online-learning sense: it does not tune to the horizon, the comparator norm, or the learning rate. We prove expected comparator-adaptive network-regret bounds for DECO-EF under compressed communication. To the best of our knowledge, this gives the first expected sublinear network-regret guarantees for parameter-free decentralized online learning under compressed communication.

---

### Operational AI Deployment Assurance: Governance-State Orchestration Under Threshold-Sensitive Deployment Conditions -- A Governance Framework for High-Stakes AI Systems

Authors: Khalid Adnan Alsayed
Published: 2026-05-27
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.27827v1

AI governance frameworks increasingly emphasize fairness, transparency, accountability, and lifecycle risk management in high-stakes domains. However, many current approaches remain observational, relying on static metric reporting, post-hoc auditing, and monitoring dashboards without directly governing deployment readiness, remediation progression, escalation states, or assurance-driven deployment control. This paper introduces Operational AI Deployment Assurance (OADA), a governance framework for translating fairness disagreement, subgroup instability, threshold sensitivity, remediation outcomes, and operational uncertainty into deployment-oriented assurance decisions. Building on prior work on the Fairness Disagreement Index (FDI) and FairRisk-FDI, OADA reframes governance uncertainty as an operational concern within AI deployment pipelines rather than a byproduct of metric disagreement. The framework introduces Deployment Assurance Scores, Deployment Readiness Classifications, Threshold Stability Zones, Governance Escalation States, and remediation-aware assurance progression. These constructs support lifecycle-oriented governance decisions across high-stakes settings by connecting evaluation outputs to deployment-state interpretation, reassessment, escalation, and operational control. Through deployment-oriented evaluation across facial recognition systems, with discussion extended to healthcare AI as a representative high-stakes domain, the paper demonstrates how systems may appear acceptable under isolated fairness or performance metrics while still exhibiting instability that affects deployment readiness. The proposed framework positions operational deployment assurance as a governance layer between evaluation and real-world AI deployment.

---

### MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Authors: Kai Chen, Yan Pang, Tianhao Wang
Published: 2026-05-27
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.27825v1

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent memory have received less attention, even though such memory can contain sensitive user-agent interactions, retrieved facts, and user preferences. Therefore, in this work, we focus on chat agent memory MIAs, where an adversary infers whether a candidate memory unit belongs to the chat agent's memory store. We propose Multi-Recall Memory MIA (MRMMIA), a unified attack that utilizes multiple recall probes to the agent to extract the membership signal across black-box, gray-box, and white-box settings. Our experiments demonstrate that MRMMIA consistently outperforms baselines. Our results expose the privacy risk in agents and provide an initial evaluation framework for membership leakage in chat-agent memory systems.

---

### Revealing Algorithmic Deductive Circuits for Logical Reasoning

Authors: Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue
Published: 2026-05-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27824v1

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in few-shot learning settings. However, it remains unclear how LLMs genuinely understand the abstract meaning of each reasoning step and the overall algorithm from only a limited number of demonstrations. This work aims to localize the attention heads responsible for individual reasoning steps and characterize the types of information transferred among them. We first align constituent reasoning steps with their corresponding token logits under a symbolic-aided Chain-of-Thought (CoT) prompting framework. Our analysis shows that token positions that steer the reasoning process are associated with low confidence scores caused by constraints on satisfying reasoning behavior patterns in demonstrations. We then adopt causal mediation analysis techniques to identify the attention heads responsible for these patterns. In addition, our findings indicate that LLMs retrieve factual and rule-based information for individual sub-reasoning tasks through specialized attention heads (approximately 3% total heads), whereas higher layers predominantly facilitate information integration and the emergence of global reasoning strategies (e.g., graph traversal algorithms) that coordinate multiple intermediate reasoning steps to solve the overall task.

---

### Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Authors: Xiang Fang, Wanlong Fang
Published: 2026-05-27
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.27823v1

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and availability of LLMs in security-critical applications. This paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies and neutralizes malicious components in input prompts before they are processed by the LLM. The APD framework integrates three key innovations: (1) a mutual information-based semantic decomposition method to isolate adversarial and benign prompt components, ensuring statistical independence; (2) a graph-based intent classification approach that leverages spectral analysis to detect malicious patterns in prompt semantics; and (3) a lightweight transformer-based classifier trained on real-world datasets of toxic and jailbreaking prompts, enabling efficient and accurate adversarial intent detection. Evaluated on diverse datasets containing adversarial prompts, APD demonstrates superior robustness, reducing harmful output generation by over 85\% while maintaining negligible impact on model performance. The framework's computational efficiency supports real-time deployment, making it a practical solution for securing LLMs. Our work addresses critical challenges in machine learning security on novel attacks and integrity methods for ML systems, and offers a scalable, ethically grounded defense against prompt-based adversarial threats.

---

### EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

Authors: Yunqi Liu, Tong Niu, Zitong Wang, Zhenlong Dai, Yuqi Qing, Weiqiang Wang, Jian Liu
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.27820v1

As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic interaction with users. However, existing benchmarks fail to jointly evaluate these capabilities due to challenges in designing strictly coupled multi-capability tasks, simulating natural and task-constrained user feedback, and ensuring objective evaluation of dynamic interaction. To bridge this gap, we introduce EgoBench, the first interactive multimodal benchmark for tool-using agents. EgoBench comprises 1,045 egocentric-video-grounded tasks covering four daily scenarios, along with a user-agent-tool interactive environment for evaluation. We implement a three-stage synergistic pipeline through which each task is designed to enforce the joint application of visual perception and tool-augmented multi-hop reasoning. We additionally develop a multi-agent simulated user within EgoBench to evaluate agents' interaction capabilities, which generates high-fidelity, task-aligned responses to agents. Furthermore, we establish a deterministic joint validation framework that guarantees objective assessment through process-based and result-based equivalence. Benchmarking eight SOTA video-MLLM agents on EgoBench reveals a severe performance ceiling: the best model achieves only 30.62% accuracy in the best-performing scenario, averaging 19.43% across all four scenarios. Finally, we conduct a multi-dimensional error analysis to disentangle failure modes, exposing capability bottlenecks for advancing future AI agents.

---

### ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions

Authors: Prathyush Poduval, Calvin Yeung, Neel Desai, Mohsen Imani
Published: 2026-05-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.27819v1

Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem for multi-layer interventions: different layerwise dictionaries can spend capacity representing the same carried-forward information, and replacing several layers at once can produce interactions that are not predicted by single-layer behavior. We introduce Residualized Sparse Autoencoders (ReSAEs), which fit an affine map between selected layers and train each later-layer SAE on the unexplained residual rather than on the full activation. Reconstructions are mapped back into the original activation space through the fitted affine chain, so ReSAEs can be evaluated with the same intervention protocols as ordinary SAEs. On Pythia-1.4B and Gemma-2-9B, residualization reduces decoder redundancy and improves sparse probing and targeted perturbation in most tested settings. Despite reconstructing less of the raw activation variance, ReSAEs recover more transformer cross entropy under multi-layer replacement. This gain is clearest under teacher-forcing and at sufficient sparsity online, indicating that ReSAEs preserve the components of the activation most relevant to the model's downstream computation. These results suggest that removing linearly predictable cross-layer structure is a useful default for multi-layer SAE interventions.

---

### Turning Video Models into Generalist Robot Policies

Authors: Sizhe Lester Li, Evan Kim, Xingjian Bai, Tong Zhao, Tao Pang, Max Simchowitz, Vincent Sitzmann
Published: 2026-05-27
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.27817v1

Video generative models have emerged as a promising robotics backbone, capable of generating videos that depict the completion of complex tasks across embodiments and environments. Recent work proposes robot foundation models that jointly predict future observations and actions by finetuning video models with action-labeled data. In this paper, we test the limits of an alternative approach: leave the video planner as-is while training an embodiment-specific inverse dynamics model (IDM). This decoupling offers several natural benefits: the video planner remains embodiment-agnostic, different video models can be interchanged easily without re-training the IDM, and the IDM can be independently trained with readily available self-play data. We present a closed-loop, video-to-action policy that combines an action-free video world model with a carefully-designed IDM based on the robot embodiment Jacobian. We demonstrate that our IDM design is both data-efficient and scalable to high-dimensional action spaces. Our policy, which we coin the Video-to-Embodied Robot Action Model (VERA), achieves strong performance across simulated and real-world benchmarks, including zero-shot Panda arm manipulation and 16-DoF Allegro-hand dexterous cube re-orientation. The same video planner can be used across multiple embodiments by pairing it with different embodiment-specific IDMs. Our results show that decoupled video planning plus faithful video-to-action translation is a viable alternative route towards zero-shot, cross-embodiment, and generalizable robot control. More results are available on our project website: https://vera.csail.mit.edu.

---

### Pattern Recognition Tasks with Personalized Federated Learning

Authors: Md. Arifur Rahman, Isha Das, Mushfiqur Rahman Abir, B. M. Taslimul Haque, Abdullah Al Noman, Abir Ahmed, Md. Jakir Hossen
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27816v1

Personalized Federated Learning (PFL) constitutes a novel paradigm that tailors Machine Learning (ML) models to individual clients, thereby furnishing personalized model updates whilst upholding stringent data privacy principles. Diverging from conventional standard Federated Learning (FL) approaches, PFL adapts models to distinct client data distributions, engendering heightened levels of accuracy, customization, and data security, all while minimizing communication overhead. This methodology proves particularly salient in contexts marked by pattern recognition tasks reliant upon heterogeneous data sources and underpinned by paramount privacy apprehensions. In the present research endeavor, this article undertake a comprehensive comparative analysis of seven distinct PFL algorithms deployed across three diverse datasets, namely MNIST, SignMNIST, and Digit5. The overarching objective entails ascertaining the preeminent PFL algorithm, within the framework of pattern recognition tasks, through a rigorous evaluation anchored in metrics encompassing Accuracy, Precision, Recall, and F1 Score. Concurrently, an in-depth scrutiny of these PFL algorithms is conducted, elucidating their operative workflows, advantages, and limitations. Through empirical investigation, the findings evince that APPLE, FedGC, and FedProto emerge as stalwart contenders, consistently furnishing superior performance across the spectrum of assessed datasets, while acknowledging the contextual specificity of alternative algorithms and the potential for iterative refinement to realize optimal outcomes.

---

### Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models

Authors: Calvin Yeung, Prathyush Poduval, Ali Zakeri, Zhuowen Zou, Mohsen Imani
Published: 2026-05-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.27813v1

Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) have recently been used to decompose diffusion activations into interpretable feature directions, but most approaches analyze activations at individual timesteps or condition on time rather than learning directly from full activation trajectories. In this work, we introduce residualized temporal SAEs for diffusion activation trajectories. We collect activations across denoising time, fit linear predictors between neighboring timesteps, and represent each trajectory using an initial activation together with residual components not explained by these linear dynamics. Training an SAE on this residualized representation encourages sparse latents to capture structure beyond what is linearly predictable. The residualized decoder directions can be mapped back into activation space, allowing each latent to be analyzed as a feature trajectory over denoising time. Through reconstruction and ablation studies, spatiotemporal feature analysis, and qualitative steering experiments on Stable Diffusion~1.5, we show that residualized temporal SAEs provide a useful framework for studying temporally structured diffusion activations.

---

### Constrained Auto-Bidding via Generative Response Modeling

Authors: Eunseok Yang, Xingdong Zuo, Kyung-Min Kim
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.27811v1

Auto-bidding systems aim to maximize advertiser value over long horizons under budget constraints and ratio targets such as cost-per-acquisition, yet future traffic and auction dynamics are non-stationary and uncertain. Existing approaches face distinct limitations: control-based pacing reacts to deviations but cannot anticipate future conditions, while RL and generative methods fold constraints into reward signals, obscuring violations and degrading under distribution shift. We shift the learning target from actions to responses with the Generative Response Model (GRM), a history-conditioned sequence model that jointly predicts future traffic volume and horizon-aggregate cost/value curves as functions of a single bid multiplier. We show that under mild monotonicity conditions, the optimality gap relative to full per-tick control is bounded by the dispersion of per-tick marginal value-per-cost. Given predicted responses, a lightweight analytic controller enforces each active constraint via a 1D root-finding step. We prove this controller is exact for the single-multiplier problem and bound constraint violations under receding-horizon replanning in terms of prediction error. Experiments on AuctionNet show that GRM improves constraint stability and overall score compared to existing baselines.

---

### Density-aware Sample-specific Attack

Authors: Qiyuan Wang, Yao Li, Raymond K. W. Wong
Published: 2026-05-27
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2605.27809v2

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and derive principled criteria characterizing optimal sample-specific trigger construction under a Bayes-optimal model of the victim's training. Our analysis reveals that both attack success and clean-accuracy preservation are simultaneously optimized when triggered samples are steered into low-density regions of the clean data distribution, a distributional condition that controls all moments of the poisoned distribution at once rather than a handful of input-space summary statistics. We introduce a bilevel optimization framework that estimates density ratios via conditional time-score matching and optimizes a mixture-model objective to place triggered samples in these sparse regions. Extensive evaluations on MNIST, CIFAR-10, GTSRB, and TinyImageNet demonstrate that our method achieves above 99\% attack success rate before defense and retains 50--85 percentage points higher post-defense ASR than the strongest baselines under fine-tuning defenses. Against neuron-pruning defenses, the method exhibits complete immunity, with zero neurons identified for removal across all pruning thresholds. These results expose a fundamental gap in current defense paradigms and underscore the need for defenses that operate beyond the support of the clean distribution.

---

### TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition

Authors: Xinyu Wang, Ziyu Zhao, Ke Bai, Silin Meng, Dongming Shen, Xiao-Wen Chang, Yixuan HE
Published: 2026-05-27
Categories: cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2605.27808v1

Data-aware post-training quantization (PTQ) minimizes a per-token reconstruction loss on a small calibration corpus, implicitly weighting positions by their empirical frequency. For \textbf{A}utomatic \textbf{S}peech \textbf{R}ecognition (ASR), this misaligns with tail-sensitive risk: names, numerals, and domain-specific words receive proportionally little calibration mass. We propose \textbf{Tail-Aware Reconstruction Quantization} (\TARQ), a label-free PTQ framework that shifts calibration toward the lexical tail via \textbf{\rareBAL}, a closed-form per-Linear-layer rule equalizing common/tail mass, paired with a metric-consistent residual correction. \TARQ\ requires no entity labels, no curated calibration set, no validation decoding, and no additional training. Across eight ASR backbones and six datasets at W4G128, \TARQ\ improves mean rare-\textbf{W}ord \textbf{E}rror \textbf{R}ate (rare-WER) without an aggregate-WER regression, achieves the lowest cross-corpus rare-WER swing among compared methods, and transfers to entity-rich benchmarks (ProfASR, ContextASR-Speech-En) without entity supervision.

---

### ChildEval: When large language models meet children's personalities

Authors: Yanyan Luo, Xue Han, Chunxu Zhao, Ruiqiao Bai, Yaxing Zhang, Qian Hu, Lijun Mei, Junlan Feng
Published: 2026-05-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.27805v1

While LLMs enable personalized chatbots, their effectiveness in child-centered personalization remains unclear, as systematic evaluation of child-specific preferences is still lacking. To address this gap, we introduce ChildEval, a benchmark for evaluating LLMs' ability to infer and follow child-centered preferences in long-context conversations. ChildEval contains 29K synthesized persona profiles of children aged 3-6, providing relatively static background information. Each persona is associated with a child preference-which may align with, conflict with, or be independent of the persona-expressed either explicitly in a single sentence or implicitly through 6-10 turn dialogues. Explicit and implicit preferences are designed to reflect the same underlying preference but differ in expression, capturing dynamic aspects of preference expression rather than changes in the static persona. The benchmark spans five top-level and fourteen sub-level categories covering children's daily lives and development. We further propose fine-grained, child-centric evaluation protocols to systematically assess open-source LLMs. Experimental results demonstrate how different personalized representations affect LLM responses and suggest that finetuning on ChildEval can enhance child-centered performance. Our code and dataset are available at https://github.com/ziyanluo/ChildEval.

---

### CuriosAI Submission to the CASTLE Challenge at EgoVis 2026

Authors: Yuto Kanda, Hayato Tanoue, Takayuki Hori
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27800v1

CASTLE 2026 asks 185 multiple-choice questions over 600+ hours of synchronized multi-view egocentric video. We explore two approaches on top of a shared multimodal preprocessing layer, including per-person timelines, speaker-resolved transcripts, and multi-VLM caption ensembles. Approach A, SVA: Search-Verify-Answer, is a three-stage pipeline that hierarchically narrows to a primary window, verifies sub-windows with a VLM under four anti-confabulation rules, and fuses evidence with an LLM judge under an evidence-priority hierarchy. Approach B, TMKG: Temporal-Multimodal-Knowledge-Graph, is the contrast: it builds a temporal multimodal knowledge graph, locates a primary cell via graph search, and produces the final answer with a single grounded VLM. SVA reaches a leaderboard accuracy of 0.50 and is our final challenge submission; TMKG reaches 0.35.

---

### GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection of Inflammatory Bowel Disease

Authors: Leo Y. Li-Han, Ellen L. Larson, Elizabeth B. Habermann, Cornelius A. Thiels, Hojjat Salehinejad
Published: 2026-05-27
Categories: cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2605.27799v1

International Classification of Diseases (ICD) is a globally recognized coding system that records diagnostic events during each patient encounter, providing a standardized data foundation for various clinical tasks. However, the irregular and hierarchical nature of ICD code sequences poses challenges for N-D lattice-based sequential modeling methods, leading to overly complex model designs. In this paper, we propose GraD-IBD, a graph diagnosis model that reformulates longitudinal ICD trajectories as visit-bucketized, temporally directed graphs to detect the risk of inflammatory bowel disease (IBD). A novel context-aware, time-decay message passing mechanism was developed to capture temporal dependencies while reducing model complexity. The experimental results using a real-world clinical dataset demonstrated consistent and robust improvements in IBD detection over state-of-the-art methods, with significant reductions in computational complexity compared to sequential models. These findings highlight the potential of graph representation learning to enable efficient, scalable, and accurate disease risk prediction from longitudinal ICD diagnosis codes.

---

### Benchmarking Ultrasound Foundation Models for Fetal Plane Classification

Authors: Leya Barrientos, Yuexi Du, Nicha C. Dvornek
Published: 2026-05-27
Categories: eess.IV, cs.CV, cs.LG, eess.SP, stat.AP
arXiv: https://arxiv.org/abs/2605.27796v1

Ultrasound is widely used in obstetric care due to its safety, accessibility, and real-time imaging. However, interpretation remains operator-dependent and susceptible to noise and artifacts. Deep learning models have shown strong performance to solve these problem, but they typically require large annotated datasets that are difficult to obtain in clinical ultrasound. Foundation models (FMs) offer an alternative, using a large number of ultrasound images to learn transferable representations that can generalize with limited labeled data. This work presents a comprehensive benchmark of ultrasound-specific FMs for fetal plane classification. We evaluated four ultrasound FMs (USFM, MOFO, UltraSAM, FetalCLIP) against two CNN baselines (ResNet50, EfficientNet-V2) and a ViT (DINOv3) pretrained on natural images. We trained all models under two complementary settings: full fine-tuning and linear probing with a frozen encoder. All models were trained using 5-fold patient-level cross-validation on a Spanish fetal ultrasound dataset and tested on both in-domain data and an external African cohort to assess cross-population generalization. We found that FetalCLIP achieved the best results in the linear probing setting (F1 = 0.9261 for in-domain, F1 = 0.9731 for out-of-domain), while USFM performed best in the full fine-tuning setting (F1 = 0.9476 for in-domain, F1 = 0.9515 for out-of-domain). MOFO and UltraSAM degraded most in both settings, underperforming natural image pretrained models in some cases. These findings highlight how the choice of pretrained model strongly affects fetal plane classification performance, since different pretraining objectives lead to different levels of transferability.

---

### Learning to target with network interference

Authors: Xiaomeng Wang, Hamsa Bastani, Osbert Bastani, Zhimei Ren
Published: 2026-05-27
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2605.27794v1

This paper studies adaptive targeting under network interference in a bandit setting, where treatments applied to one individual may affect others through spillover effects. We consider a linear model in a sparse regime, where each individual's outcome can be affected by at most a few others. We first establish a regret lower bound showing that ignoring the network structure and reducing the problem to a standard linear bandit inevitably leads to inefficient learning, particularly in large populations. To understand how structural information can be leveraged, we analyze regimes with varying levels of knowledge of the interference structure: (1) full support knowledge, (2) knowledge of the column support sizes, and (3) no prior knowledge. For each regime, we establish regret lower bounds characterizing the fundamental limits of learning, and develop algorithms that achieve near-optimal regret. Together, our results provide a unified view of how knowledge of the interference structure governs the efficiency of online learning under interference, and offer practical adaptive targeting algorithms in each setting. Numerical experiments on synthetic and real-world data demonstrate the practical benefits of our algorithms.

---

### SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic Denoising

Authors: Akshaj Murhekar, Abhijit Mishra
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.27790v2

Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of viewed stimuli. However, existing systems remain highly vulnerable to biological noise, where corrupted neural projections induce hallucinated or semantically unstable generation in frozen language models. We introduce SYNAPSE (Symbolic Neural Alignment for Precise Semantic Extraction), a lightweight neuro-symbolic framework that stabilizes neural text generation through inference-time symbolic regularization. By purifying EEG-derived semantic candidates using commonsense graph structure and latent exemplars, SYNAPSE improves semantic stability without end-to-end LLM fine-tuning. Experiments across popular EEG decoding benchmarks and multiple frozen LLM backends demonstrate consistent gains over unconstrained prompting baselines, robustness under object-label ablation, and performance commensurate with substantially more resource-intensive fine-tuned systems, while preserving biometric privacy by localizing raw EEG processing entirely within the encoder stack.

---

### SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic Denoising

Authors: Akshaj Murhekar, Abhijit Mishra
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.27790v1

Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of viewed stimuli. However, existing systems remain highly vulnerable to biological noise, where corrupted neural projections induce hallucinated or semantically unstable generation in frozen language models. We introduce SYNAPSE (Symbolic Neural Alignment for Precise Semantic Extraction), a lightweight neuro-symbolic framework that stabilizes neural text generation through inference-time symbolic regularization. By purifying EEG-derived semantic candidates using commonsense graph structure and latent exemplars, SYNAPSE improves semantic stability without end-to-end LLM fine-tuning. Experiments across popular EEG decoding benchmarks and multiple frozen LLM backends demonstrate consistent gains over unconstrained prompting baselines, robustness under object-label ablation, and performance commensurate with substantially more resource-intensive fine-tuned systems, while preserving biometric privacy by localizing raw EEG processing entirely within the encoder stack.

---

### A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test

Authors: Camilo Chacón Sartori, José H. García
Published: 2026-05-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27789v1

Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG, this has become a measurement problem as much as a modeling problem: the same score can reflect retrieval quality, answer length, lexical overlap, or a statistical test that ignores clustered data. We ask what happens when these choices are made explicit. We propose a minimum measurement standard for LLM-as-a-judge comparisons in RAG. The standard fixes the top-100 candidate pool, evidence budget, answer cap, generator, and prompt; it also requires pre-registered hypotheses, cluster-aware inference, an exact cluster sign-flip check when feasible, and second-judge replication. Clustered benchmarks can overstate progress; the field should adopt this standard. We stress-test it with Genetic Algorithm Decoder for Multi-hop Evidence Composition (GADMEC), an evolutionary evidence selector, on 400 multi-hop questions in computer science/machine learning (CS/ML) and Materials Science. The protocol changes the empirical story. A binomial test makes all four semantic-baseline comparisons look significant; cluster-aware inference leaves only one Bonferroni-significant result. BM25 beats pure semantic GADMEC under the same budget, while a lexical-semantic hybrid recovers in CS/ML and narrows the Materials Science gap.

---

### Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use

Authors: Abhijit Kumar, Zoey Wu, Mohit Suley
Published: 2026-05-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.27788v1

Humans know when to reach for help e.g. $347 \times 28$ warrants a calculator while $2+2$ does not. Language models do not. Prompt-based approaches can instruct a model when to invoke tools, but this scaffolding does not teach it to recognize the boundary of its own knowledge. RL approaches that assign a single outcome reward to the whole trajectory fare no better: trajectory-level credit cannot isolate which tool call in a successful episode actually helped, nor penalize unnecessary calls. We propose \textbf{CARL} (\textbf{C}ompetence-\textbf{A}ware \textbf{R}einforcement \textbf{L}earning), which trains a critic on the model's own rollouts to learn where parametric knowledge suffices and where it needs external help. By decomposing each rollout at natural tool-use boundaries (e.g., code fence delimiters and context block transitions), CARL assigns independent credit to each segment from a single binary outcome, without external judges or step-level annotations. As a result, erroneous tool calls, incorrect extractions, and unnecessary calls each receive appropriately signed advantages. The trained critic captures the model's domain competence: it separates parametrically solvable from tool-dependent questions with AUC 0.93 at 7B. On five benchmarks spanning arithmetic, multi-hop factual QA, and numerical reasoning over financial tables, CARL improves exact-match accuracy by 6.7 points at 7B and 9.7 points at 3B over the best RL baseline, with the largest gain (+8.3 EM at 7B, +9.0 EM at 3B) on Musique. The model issues 53\% fewer tool calls on parametrically answerable questions while remaining ${\sim}10$ EM points more accurate on them. Gains are largest at small scale: the 3B improvement is $1.4\times$ the 7B improvement, suggesting that knowing when to ask disproportionately benefits models with smaller parametric memory.

---

### Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems

Authors: Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo, Youngbin Choi, Saemi Moon, MoonJeong Park, Dongwoo Kim
Published: 2026-05-27
Categories: cs.MA, cs.CL
arXiv: https://arxiv.org/abs/2605.27787v2

Multi-agent systems (MAS) have substantially advanced autonomous software engineering (SWE), but their growing inference energy demands raise sustainability concerns. In this paper, we demonstrate that this cost is concentrated in an overlooked source: redundant output tokens generated across agents. Two empirical findings ground this claim. First, our per-token energy attribution for MAS reveals a sharp asymmetry: an output token consumes 30 to 1,000 times more energy than an input or cached token. Second, MAS inflate per-episode output because agents repeatedly re-explore overlapping repository regions. To address this inefficiency, we propose Librarian, a persistent search sub-agent that tracks repository-search history and suppresses redundant exploration actions across agents. By returning short references to file regions instead of full file excerpts, Librarian further reduces output-token volume. On SWE-Bench Verified and SWE-Bench-Live, Librarian reduces per-episode GPU energy consumption of existing multi-agent SWE systems by 11 to 30% while preserving task performance. Our code is available at https://github.com/ml-postech/Librarian.

---

### Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems

Authors: Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo, Youngbin Choi, Saemi Moon, MoonJeong Park, Dongwoo Kim
Published: 2026-05-27
Categories: cs.MA, cs.CL
arXiv: https://arxiv.org/abs/2605.27787v1

Multi-agent systems (MAS) have substantially advanced autonomous software engineering (SWE), but their growing inference energy demands raise sustainability concerns. In this paper, we demonstrate that this cost is concentrated in an overlooked source: redundant output tokens generated across agents. Two empirical findings ground this claim. First, our per-token energy attribution for MAS reveals a sharp asymmetry: an output token consumes 30 to 1,000 times more energy than an input or cached token. Second, MAS inflate per-episode output because agents repeatedly re-explore overlapping repository regions. To address this inefficiency, we propose Librarian, a persistent search sub-agent that tracks repository-search history and suppresses redundant exploration actions across agents. By returning short references to file regions instead of full file excerpts, Librarian further reduces output-token volume. On SWE-Bench Verified, Librarian reduces per-episode GPU energy consumption of existing multi-agent SWE systems by up to 25% while preserving task performance.

---

### Locality-Aware Redundancy Pruning for LLM Depth Compression

Authors: Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo, Minkyu Kim, Sunwoo Lee
Published: 2026-05-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.27786v3

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or fixed redundancy assumptions across architectures. We propose Locality-Aware Redundancy Pruning (LoRP), a training-free one-shot depth pruning framework guided by representation locality. We show that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture. To characterize this phenomenon, we introduce Representation Locality Score (RLS), derived from global inter-layer hidden-state similarity. Using a small calibration set, LoRP computes pairwise layer similarity, clusters layers by representational similarity, and allocates pruning according to residual intra-cluster redundancy. Experiments across diverse LLM families show improvements in both perplexity and downstream task accuracy. Official github repository: https://github.com/daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning/

---

### Locality-Aware Redundancy Pruning for LLM Depth Compression

Authors: Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo, Minkyu Kim, Sunwoo Lee
Published: 2026-05-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.27786v2

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or fixed redundancy assumptions across architectures. We propose Locality-Aware Redundancy Pruning (LoRP), a training-free one-shot depth pruning framework guided by representation locality. We show that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture. To characterize this phenomenon, we introduce Representation Locality Score (RLS), derived from global inter-layer hidden-state similarity. Using a small calibration set, LoRP computes pairwise layer similarity, clusters layers by representational similarity, and allocates pruning according to residual intra-cluster redundancy. Experiments across diverse LLM families show improvements in both perplexity and downstream task accuracy. Official github repository: https://github.com/daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning/

---

### A Query Engine for the Agents

Authors: Kenny Daniel
Published: 2026-05-27
Categories: cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2605.27785v1

The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it, and the questions worth asking ("show me where the agent got confused") cannot be answered by SQL alone, since text is not queryable without a model in the query path. The natural place this analysis is happening is the new class of AI applications (Claude Code, Cursor, Claude Desktop, in-browser agents) that run client-side and host both a human user and an LLM agent in the same process. These applications increasingly want to work with data, but the lakehouse read path has been hard to use from a JS runtime: Spark, Trino, and managed warehouses do not fit there. To build this new kind of AI data application, three properties of the engine become first-order: a JS-native distribution that drops into the runtime the application already runs in, a bundle small enough to ship inside a cold tab or per-turn agent sandbox, and a way to interleave analytic operators with model-based interpretation of text. We present Hyperparam, three open-source JavaScript libraries (Hyparquet, Squirreling, Icebird) totaling under 70 KB, that read Parquet and Apache Iceberg directly from object storage and meet the third property with per-cell, async-native SQL execution, so expensive cells fire only when downstream operators demand them. Squirreling runs LLM-shaped async UDFs over 300x faster than DuckDB-WASM on filter-bounded queries (and 192x on sort-bounded queries) and completes a ten-task agent analyst suite at two-thirds lower cost. We argue that data engineering as a discipline needs to update for the AI-native client applications now in production and the agents that work alongside their users.

---

### WIRE: Profiling Witnessed Within-Policy Instruction Collisions in LLM Agents

Authors: Lu Yan, Xuan Chen, Xiangyu Zhang
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.27784v2

LLM agents are governed by long-lived prompt policies, where individually reasonable stand- ing rules can jointly govern the same pre- generation state. Existing instruction-following evaluations usually ask whether a model satis- fies explicit constraints, but they do not show how a model resolves pressure among rules inside one standing policy. We introduce WIRE, a witnessed resolu- tion profiler for prompt policies. WIRE ex- tracts source-grounded rules, encodes them as PYRULE clauses, uses satisfiability checks only to nominate same-surface hard-collision can- didates, realizes those candidates as concrete co-governance witnesses, and executes subject models to produce a four-cell resolution profile: satisfy both rules, only the earlier rule, only the later rule, or neither. Across six public prompt policies, WIRE ex- tracts 276 source rules and 560 clauses, clas- sifies 30,944 within-policy clause-pair com- parisons, retains 170 encoded hard-collision source-rule pairs, and realizes 1,402 concrete witnesses. In policy-only evaluation, these wit- nesses yield 13,335 jointly governed, judgeable trials; only 35.4% satisfy both governed rules. The resulting profiles reveal policy-specific, model-specific, and tool-interface-specific res- olution patterns. WIRE is not a proof of natural-language contra- diction, a deployment-frequency estimator, or a root-cause diagnosis. It is a measurement tool that returns reproducible witnesses and aggre- gate profiles for inspection, regression testing, and repair.

---

### Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

Authors: Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic, Yue Guo, Antigoni Polychroniadou, Min Wu, Dana Dachman-Soled
Published: 2026-05-27
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2605.27782v1

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach improves computational efficiency over standard differentially private gradient descent (DP-GD) while achieving comparable utility. In particular, we prove convergence of approximate gradient descent using polynomial approximations of activation and loss functions, which are required for FHE compatibility. To preserve privacy in downstream tasks, we integrate differential privacy without relying on costly per-sample gradient clipping, enabling scalable encrypted learning. We also provide data-independent hyperparameter selection and theoretically grounded strategies for polynomial approximation which can be of independent interest. Together, these contributions advance the feasibility of efficient, private, and secure machine learning on sensitive data.

---

### A Virtual Member of a Community of Practice for the Society of Petroleum Engineers: From Prototype to Deployment

Authors: John Boden, Joshua Eckroth, Dayne Freitag, Skyler Gipson, Johnathan Keefe, Karen Myers, Eric Schoen, Pedro Sequeira, Reid Smith, Michael Wessel
Published: 2026-05-26
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2608.19199v1

We describe the evolution of a virtual assistant, called ATHENA, designed to support the capture, retrieval, and dissemination of knowledge for members of a Community of Practice (CoP) related to the Oil and Gas sector. An evaluation of a first prototype involving 75 professionals from the Society of Petroleum Engineering (SPE) showed that ATHENA dramatically improved both their productivity and performance equality on a set of realistic well-planning tasks compare to their use of a state-of-the-art RAG baseline system. However, the evaluation also identified areas for improvement. This paper describes technical advances to our first prototype in the areas of multi-document retrieval, support for answer validation, and more focused proactive dissemination. Evaluation results show that this enhanced version of ATHENA provides better support for completing knowledge-intensive tasks related to well planning than does a state-of-the-art baseline. ATHENA has been integrated into the SPE Research Portal and is being deployed for use by the society's membership.

---

### Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)

Authors: Rivaan Patil, Simon Dennis, Hao Guo, Kevin Shabahang
Published: 2026-05-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.14563v1

Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.7--3.2x the throughput of standard fine-tuning at ~40% less peak training memory, while leaving off-domain benchmarks within seed-noise of baseline, a property that full-network fine-tuning does not reliably reproduce. FPO rests on a single empirical observation: at late layers of a transformer, the output-layer prediction error approximates the true gradient with cosine similarity 0.47--0.59 across six public models we survey. We introduce a two-minute diagnostic that quantifies this approximation per layer for any model, identifying where late-layer adaptation is viable. Informed by the diagnostic, FPO computes a single error signal at the output and applies it to each target layer. No signal is propagated between layers, and no autograd graph is constructed at any point. We evaluate FPO on three model families (OLMo-2-7B, Qwen3-8B, Falcon3-7B). Across all three, FPO produces in-domain perplexity improvement and leaves MMLU, ARC-Challenge, HellaSwag, and Winogrande within seed-noise of baseline. Localizing SFT to FPO's target layers to enter this regime is also feasible, but at 2.2x the wall-clock cost of FPO.

---

### Global AI Regulations for FAIR and Ethics in High-Risk Use Cases: A Comparative Review

Authors: Aasish Kumar Sharma, Dimitar Koysev, Christopher Anich, Roshni Kumari Ojha, Julian Kunkel
Published: 2026-05-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.14562v1

AI governance is shifting from voluntary ethics to enforceable, risk-based regulation, yet cross-jurisdictional divergence creates compliance uncertainty for operators of high-stakes AI. We present a comparative matrix for the EU, US, and China that maps (i) risk classification triggers, (ii) binding obligations, (iii) enforcement and accountability mechanisms, and (iv) the degree to which FAIR principles are operationalised in practice. We stress-test the matrix on three high-impact domains: Electroencephalography (EEG)-guided rehabilitation robotics, AI-enabled debt collection in prospective Central Bank Digital Currency (CBDC) ecosystems, and AI-driven allocation of scarce Graphics Processing Unit (GPU) resources in emerging AI Factory infrastructures. Using primary legal texts and implementation evidence, we identify three recurring gaps: weak interoperability mandates, difficult operationalisation of cross-regime obligations (AI + sector regulation + data protection), and under-specified governance for critical digital infrastructure use cases. To bridge the implementation gap, we outline Knowledge Blocks, a machine-checkable compliance artefact pattern based on Resource Description Framework/Web Ontology Language (RDF/OWL), Shapes Constraint Language (SHACL), and Provenance Ontology (PROV-O), enabling audit-ready compliance-by-design across multiple regimes.

---

### Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning

Authors: Sachini Weerasekara, Sagar Kamarthi, Jacqueline Isaacs
Published: 2026-05-26
Categories: cs.CL, cs.CY, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2608.05166v1

We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings. Our work introduces a novel three-condition experimental framework that disentangles the effect of exposure to a biased user turn from the effect of the turn's semantic content, alongside a benchmark of 24,300 jury-validated user prompts spanning all 81 cells of a 9x9 target-human bias interaction matrix. Across eight frontier LLMs, we find that biased conversational context systematically increases bias expression relative to zero-shot baselines in 6 of 8 models. We identify two competing behavioral dynamics underlying this effect: conversational exposure to biased reasoning generally amplifies downstream bias tendencies, while explicitly stated bias cues often trigger alignment-related suppression behaviors that reduce overt bias expression. We release our framework, codebase, and dataset to support future research on context-conditioned cognitive biases and behavioral adaptation in LLMs.

---

### A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper

Authors: Ali Shendabadi, Parnia Izadirad, Mostafa Salehi
Published: 2026-05-26
Categories: cs.CL, cs.AI, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2608.05165v2

Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data. In this work, we study the use of Whisper for Persian SER with a particular focus on representation dimensionality reduction and language-specific model adaptation. We propose a SER framework in which frame-level embeddings extracted from the Whisper encoder are reduced in dimensionality using PCA, eliminating the need for learned projection layers and substantially reducing the number of trainable parameters. The reduced representations are aggregated using an attention-based pooling mechanism and classified with a lightweight prediction head. In addition, we investigate whether fine-tuning Whisper on a Persian automatic speech recognition (ASR) task improves downstream SER performance. Experiments conducted on the ShEMO dataset under a speaker-independent evaluation protocol show that PCA-based dimensionality reduction consistently improves emotion recognition performance while reducing training latency and memory usage. ASR fine-tuning yields only modest gains for SER, suggesting limited transfer from language adaptation to emotion-related representations under the evaluated conditions. These findings provide practical insights into the efficient use of large pretrained speech models for emotion recognition in low-resource languages.

---

### A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper

Authors: Ali Shendabadi, Parnia Izadirad, Mostafa Salehi
Published: 2026-05-26
Categories: cs.CL, cs.AI, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2608.05165v1

Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data. In this work, we study the use of Whisper for Persian SER with a particular focus on representation dimensionality reduction and language-specific model adaptation. We propose a SER framework in which frame-level embeddings extracted from the Whisper encoder are reduced in dimensionality using PCA, eliminating the need for learned projection layers and substantially reducing the number of trainable parameters. The reduced representations are aggregated using an attention-based pooling mechanism and classified with a lightweight prediction head. In addition, we investigate whether fine-tuning Whisper on a Persian automatic speech recognition (ASR) task improves downstream SER performance. Experiments conducted on the ShEMO dataset under a speaker-independent evaluation protocol show that PCA-based dimensionality reduction consistently improves emotion recognition performance while reducing training latency and memory usage. ASR fine-tuning yields only modest gains for SER, suggesting limited transfer from language adaptation to emotion-related representations under the evaluated conditions. These findings provide practical insights into the efficient use of large pretrained speech models for emotion recognition in low-resource languages.

---

### Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

Authors: Ayushi Agarwal
Published: 2026-05-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.05164v1

Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested. We present the first systematic evaluation of cross-model steering transfer and show that shared LLM geometry is functionally exploitable, conditionally: concept directions from one model can steer a different independently trained model when sufficient representational capacity exists. We study five open-weight models spanning three parameter scales (0.8B--8B) and two architectural lineages, training one Sparse Autoencoder per model across 15 semantic domains and testing alignment across all 20 directed model pairs. We observe a suggestive discontinuity near 1.7B parameters: at >= 1.7B scale, 47--49% of cross-model feature pairs validate (Pearson r >= 0.60, Procrustes cosines 0.895--0.956), while alignment degrades sharply below 0.8B. Cross-model steering vectors (B3-TI) achieve a 71.0% win rate across 15 supervised concepts versus 68.0% for same-model native vectors; a single universal vector achieves 67.3% in 4 of 5 models without any per-model supervision. Transfer degrades for models below 1.7B and for one model with generation instability, confirming that functional exploitability requires sufficient representational capacity. Our findings underscore the importance of scale thresholds in mechanistic interpretability: tools validated at 7B scale may not transfer to smaller models without revalidation. We provide the first functional complement to the Platonic Representation Hypothesis -- geometric convergence across independently trained LLMs supports cross-model behavioural control without fine-tuning, under the identified scale conditions.

---

### Where Privacy Risk Lives in English-Source Multilingual RAG: A Stage-Decomposed Audit Across Five Query Languages

Authors: Yanhang Li, Zhichao Fan, Zexin Zhuang
Published: 2026-05-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.05163v1

A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information. We test this on an English-source synthetic-PII corpus with five query languages and a two-stage defence (LLM input judge + regex output filter), in a pipeline whose translator, judge, back-translator, and generator are all Qwen2.5-7B -- so every finding below is pipeline-conditional, not a causal ranking of language-inherent risk. Under output-only filtering, English has the highest observed unstructured-PII leak rate; only English-vs-Swahili separates cleanly under document-level bootstrap intervals. Once the input judge is added, residual leaks remain on Arabic and Swahili, and back-translating the query does not close the gap (an ablation we report but cannot use as a causal diagnostic, since the back-translator is also Qwen). On a separate n=17 multilingual-prompted-judge residual corner, attaching the gold corpus document to the input judge blocks 15/17 residual cells. We frame this last result as a mechanism diagnostic, not a deployable defence: it uses oracle retrieval, BLOCK/ALLOW rates are measured on adversarial queries only, and we measure no benign-query false-positive rate and no answer-utility cost. The supplementary material contains code, corpora, queries, and per-trial JSONLs; the priority follow-up is an independent-MT plus non-Qwen-judge replication with a native-speaker query set, scoped in the Limitations section.

---

### PoolBench: A Benchmark for Pooling Strategies in Concept Representation Evaluation for Decoder-Only LLMs

Authors: Ayushi Agarwal
Published: 2026-05-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.05162v1

Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden states into a passage-level vector, yet no shared protocol exists for comparing this choice across concepts, models, and tasks. Reported gains are confounded by simultaneous changes in dataset, layer, construction method, and pooling rule, making principled decisions impossible. We introduce PoolBench, a benchmark that isolates pooling as the experimental variable under a fixed evaluation protocol. PoolBench covers 17 concepts, 19 pooling strategies, and 3 open-weight decoder-only models (Llama-3.1-8B, Gemma-2-9B, Mistral-7B), evaluated on a single audited corpus of 37,693 real-text passages. The primary axis is linear separability (D1/AUROC); steered concept prevalence (D2/SCP) and output-level disentanglement (D3) serve as diagnostic axes. The primary finding is decisive: W4_hierarchical reaches a cross-model mean AUROC of 0.7799, while the widely adopted P1_last_token baseline reaches only 0.7640 and is statistically significantly worse (Friedman+Nemenyi, p = 2.0e-36; 77 significant pairs among 18 effective strategies). Rankings are stable across layers (rho = 0.961--0.990). A key negative result: strong detection does not imply strong steering -- D2 and D3 are substantially weaker than D1 for most concepts, indicating a fundamental representational limit rather than a pooling failure. On mid-difficulty concepts, W4_hierarchical outperforms P1_last_token by 0.042--0.113 AUROC; construction method choice (DiffMean vs. REPE) has a larger effect (delta AUROC 0.15) than pooling (delta AUROC 0.016), establishing the correct practical hierarchy. We release the corpus, pre-extracted activations, scorer models, steering vectors, and evaluation code as a reusable protocol for pooling research.

---

### SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters

Authors: Josh McGiff, Salma Mekaoui, Robert Shanahan, Nikola S. Nikolov
Published: 2026-05-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.05161v1

Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge. We present SemiAdapt-Instruct, a modular framework that discovers latent instruction domains, trains per-domain LoRA adapters in parallel, and performs parameter-free routing, incorporating new domains via single-adapter training without modifying existing components. SemiAdapt-Instruct outperforms full model fine-tuning across all configurations on both ROUGE-L and LLM-as-a-judge evaluation, while matching single LoRA fine-tuning and delivering extensibility that monolithic approaches cannot provide. We empirically demonstrate this extensibility by showing that updating a single adapter with new domain data outperforms all monolithic baselines. Our study also finds that independent discovery methods converge on the same specialisation-friendly domains. These findings demonstrate that decomposing heterogeneous instruction data into latent domains enables extensible NLP systems where evolving domains require only targeted single-adapter updates, eliminating the need for full model retraining.

---

### The Ignition Index: Measuring Global Workspace Dynamics in Language Models

Authors: Saman Rahbar
Published: 2026-05-26
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.05160v1

We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in transformer language models. The metric fits a four-parameter sigmoid to per-layer linear probe accuracy as a function of input signal strength, extracting steepness parameter beta-hat: high values indicate abrupt, ignition-like transitions; low values indicate graded build-up. Across 11 models spanning five architecture families, shuffled-label controls demonstrate 9.6-fold selectivity for genuine linguistic structure over spurious probe capacity (p < 0.001, Mann-Whitney U-test). We find: (1) Feedforward transformers exceed SSMs by 89% in aggregate beta-hat (p < 1e-13, Cohen's d = 0.52), with Mamba exhibiting near-linear profiles consistent with absent global broadcast. (2) Huginn-3.5B exhibits 2.12-fold higher ignition along its iteration axis than its depth axis, demonstrating that recurrent architectures manifest workspace-like transitions along the recurrence dimension. (3) Pythia-410M shows a PELT-detected phase transition at training step 256 (+67%), preceding induction-head formation. (4) Hypotheses linking ignition to model scale and signal strength were not confirmed, suggesting transformer architectures may saturate available ignition mechanisms. The Ignition Index provides the first validated quantitative bridge between GWT's dynamical predictions and mechanistic interpretability, with 9.6-fold measurement selectivity and architecture-level discriminability not previously characterized in the scaling literature. Code: https://github.com/saman-rahbar/ignition-index

---

### Transfer Learning for Named Entity Recognition of Classical Latin through LLM Prompting

Authors: Callum Chan
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.04015v1

With the increase in digitized resources of Classical Latin texts and modern breakthroughs of Large Language Models (LLMs), I contribute to ancient language research by participating in EvaLatin 2026. This paper describes Team uOttawa's system description and results for the Named Entity Recognition (NER) shared task. The task is divided into two subtasks: coarse-grained NER with 11 classes and fine-grained NER with 28 classes, each evaluated under strict and fuzzy regimes. Through prompt engineering of commercial LLMs gemini-2.5-pro and claude-sonnet-4-5, I show that the underrepresented ancient Latin language can take advantage of cross-lingual transfer learning by using advancements made by the wider LLM development community. Overall, the methods discussed in this report demonstrate very strong results, placing first in both NER subtasks and achieving the best scores across all evaluation metrics and regimes among all submissions.

---

### ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning

Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng
Published: 2026-05-26
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2607.28642v1

Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under bounded context windows, the core bottleneck is not trajectory compression or test-time control, but the absence of a reusable intermediate interface that can replace discarded history and support continued solving. We further identify a key failure mode of outcome-reward-driven long-chain reinforcement learning: when the model has not solved the task before the window is nearly exhausted, the final-answer reward encourages premature guessing rather than continued careful reasoning. We propose ThinkReset, a text-space instantiation of this view. ThinkReset explicitly constructs reusable intermediate interfaces through interface writeback and reset, and directly optimizes post-reset continuation success. Across multiple long-horizon reasoning benchmarks, this perspective consistently improves success rates under fixed context windows.

---

### Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football

Authors: Mouad Zemzoumi, Amine Abouaomar
Published: 2026-05-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.26061v1

Pre-match tactical decision-making in professional football relies heavily on subjective expert analysis and identity-based scouting systems that cannot generalize to unseen teams. This paper presents Sim2Win, a team-agnostic, event-based pre-match tactical recommendation framework that reframes match outcome prediction as a tactical decision-support problem. Using StatsBomb open event data from eleven competitions spanning 178 teams and 1,411 team-match records, Sim2Win constructs five-match rolling tactical profiles, engineers four interpretable tactical feature ratios, clusters team behaviors into eight playstyles via K-Means, and trains thirteen classifiers to estimate win, draw, and loss probabilities from tactical matchup representations. The system operates without team names or identity features, enabling generalization to teams never seen during training. A rigorous Leave-One-Competition-Out (LOCO) evaluation demonstrates that Sim2Win achieves a mean ROC-AUC of 0.704 and mean accuracy of 55.4% on completely unseen teams, outperforming ELO, Pi-Rating, and GAP baselines on all 21 ROC-AUC comparisons and 19 of 21 accuracy comparisons. Among all evaluated models, CatBoost achieved the strongest in-distribution performance with 60.90% accuracy. These findings suggest that behavioral tactical representations provide transferable predictive signal under distribution shift and offer a viable alternative to identity-dependent football prediction systems.

---

### From Idea to Classroom in Days: Using "Vibe Coding" to Create a Programming Process Visualizer from IDE Activity Logs

Authors: Heidi Taveter, Marina Lepp
Published: 2026-05-26
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2607.24757v1

This paper reports on the rapid development and classroom deployment of a Thonny log visualizer built using AI-assisted ``vibe coding'' to make students' programming processes easily visible to teachers. We developed a web application that analyzes log files generated by Thonny (an IDE for Python) and produces interpretable views of students' programming processes. Teachers can upload a log, a ZIP archive, or a folder containing logs for a group or the course; the system parses all logs, generates results per student, and provides student-by-student navigation for reviewing cases. Each student's view includes an interactive activity timeline, a compact session summary, a code-size graph, a programming-process replay, and more. These views support teacher decision-making by enabling the identification of learning-support situations and flagging sessions for academic-integrity clarification. The tool was initially evaluated using logs from previous courses; a February 2026 pilot in an introductory programming course with 160 participants provided teachers' feedback and informed iterative usability improvements.

---

### What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization

Authors: Kwangsuk Park, Jaehyun Koo, Jiyeon Lee, Anjung Tan, Hyoungchul Park
Published: 2026-05-26
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2607.24756v1

What gets lost when memory becomes media? Diaspora oral-history interviews require a double transformation; first-person recollection to third-person scene, present interview room to past time and place. When generative AI performs this transformation, no agreed criteria for success exist. We derive success conditions from oral-history theory, design 15 metrics around three failure modes, and compare a Multi-Agent Scene-decomposition pipeline (MAS) with a Single Summarization Pipeline (SSP) across 82 interviews from diaspora communities, spanning from oral interviews to 6-image sequences. Scene-planning and narrative preservation conflict in the majority of cases, and the narrative-structure strength of the source testimony is the primary predictor of this conflict. We propose a failure-mode-based evaluation framework, an empirical analysis of conflict conditions, and a routing protocol for system selection based on narrative-structure strength.

---

### Patterns of Learner-AI Interaction and Academic Performance in an Object-Oriented Programming Course

Authors: Marina Lepp
Published: 2026-05-26
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2607.24755v1

This full research paper examines how different forms of learner-AI interaction relate to learning outcomes in object-oriented programming (OOP) courses. Generative artificial intelligence (GenAI) tools are increasingly used by students in programming education, yet evidence on their educational impact remains mixed. In particular, little is known about how students integrate GenAI tools when learning OOP, and how different patterns of use relate to students' learning experiences and outcomes. This study investigates patterns of students' self-directed GenAI use and their relationship with academic performance, perceived difficulty, understanding, and trust. Survey data were collected from 210 undergraduate students enrolled in a first-year OOP course in which the use of GenAI tools was permitted for coursework but prohibited in assessments. Results show that students used GenAI significantly more often for explanation seeking and debugging than for code generation. Cluster analysis identified five distinct learner-AI interaction profiles, including a "smart" high-usage pattern characterized by low reliance on code generation and high use for conceptual support and debugging. While usage patterns were associated with differences in perceived assignment difficulty, self-assessed understanding, trust in AI-generated code, and norm-related attitudes, no significant differences in assessment performance were found across clusters. These findings suggest that self-directed GenAI use alone does not lead to measurable learning gains, underscoring the need for pedagogically guided and process-aware AI support. The study contributes empirical evidence on learner-AI interaction patterns and highlights the importance of pedagogically guided AI use in programming education.

---