# Research Papers — 2026-06 · bundle page 233 of 260 > Full-text markdown of papers #11601–11650 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/233 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/232.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/234.md) ### Frames2LoRA: Parametric Video Internalization for Vision-Language Models Authors: Manan Suri, Sarvesh Baskar, Dinesh Manocha Published: 2026-06-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.04351v2 Processing video in vision-language models is expensive: each frame occupies hundreds of tokens, and inference cost scales with every frame and every repeated query. We introduce Frames2LoRA, a method for parametric video internalization. A perceiver hypernetwork reads the intermediate representations produced layer-by-layer as a frozen VLM encodes a video, and generates a Low-Rank Adaptation (LoRA) adapter in a single forward pass. Unlike standard LoRA fine-tuning, which requires iterative gradient updates, Frames2LoRA predicts these weights directly from the video. Trained for SmolVLM2 500M and 2.2B on video summarization and captioning, Frames2LoRA enables the same frozen VLM to answer queries from the adapter alone, with zero visual tokens in its context at query time. Frames2LoRA is statistically non-inferior and equivalent to direct video-in-context inference across all five captioning benchmarks at both model scales, and across seven of eight video question answering benchmark-scale pairings. Although trained only on 12 frames at 384px, it remains stable up to 1,024 frames and 1024px, where direct video-in-context inference often degenerates. Across this sweep, it reduces answer-time visual-token load by up to 1,500x and query TTFT by 6-80x, while preserving video-faithful outputs. We also find that independently generated adapters for non-overlapping video segments can compose in rank space, suggesting a path toward chunked long-video internalization. --- ### MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models Authors: Yue Wu, Changyuan Wang, Zixuan Wang, Shilin Ma, Yansong Tang Published: 2026-06-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.04349v2 Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities. To address this, we propose MorphoQuant, a modality-aware PTQ framework engineered to preserve cross-modal morphology and mitigate outlier loss. Specifically, we introduce Distribution-Aware Bias Compensation (DABC), which selectively absorbs long-tailed outliers into channel-wise biases. This mechanism safeguards outlier magnitudes while maintaining high-precision discretization for dense inliers, thereby preserving accurate discretization across diverse modal distribution. Complementing this, we propose Morphology-Directed Quantization Function Optimization (MDQFO) to co-optimize the quantization grid with the bias mask, ensuring fine-grained alignment across modalities. Extensive evaluations on Qwen2.5-Omni across benchmarks like MMMU and Video-MME demonstrate our approach's superiority. Notably, our W4A4 model achieves 76.63% on ScienceQA, significantly outperforming SOTA W4A4 methods and surprisingly surpassing the W4A16 baseline, which fully demonstrates the exceptional accuracy-efficiency trade-off of our framework. --- ### HYolo: An Intelligent IoT-Based Object Detection System Using Hypergraph Learning Authors: Isha Abid, Fawad Khan, Muhammad Khuram Shahzad Published: 2026-06-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04345v1 This paper presents HYolo, an intelligent IoT-based object detection framework that integrates hypergraph learning into the YOLO architecture. Traditional YOLO-based object detection models primarily capture pairwise feature interactions and may fail to model complex high-order relationships among objects and contextual features. To address this limitation, HYolo incorporates hypergraph learning to capture richer contextual dependencies and improve object representation. Experimental evaluation on the COCO dataset demonstrates significant performance improvements over baseline YOLO models. The proposed approach achieves approximately 12% improvement in mAP@50 while enhancing overall detection accuracy and robustness. By modeling high-order feature relationships, HYolo provides improved contextual understanding and more reliable object detection performance in IoT-based environments. The results indicate that integrating hypergraph learning into object detection pipelines offers a promising direction for intelligent and context-aware IoT vision systems. --- ### Robust Multi-view Clustering against Imperfect Information Authors: Zhichao Huang, Haochen Zhou, Hao Wang, Mouxing Yang, Xi Peng Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04343v1 Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV) and cross-view correspondences are mismatched (i.e., Noisy Correspondences, NC) for certain instances. As a remedy, numerous IV- and NC-oriented multi-view clustering (MvC) methods have been proposed, which however require either reliable correspondences or sufficiently complete instances, thus stopping short of addressing the imperfect information problem. In contrast, we observe that both IV and NC challenges originate from the same issue of imperfect cross-view counterpart information, where the counterpart of an anchor instance in another view might be either unavailable or unreliable. Based on the observation, we propose a novel robust MvC framework, termed Posterior-guided Latent Counterpart Inference (PLCI), which could handle both IV and NC in a unified manner. Specifically, PLCI formulates the desired cross-view counterpart of each anchor instance as a latent variable, and integrates both instance-level reliability and prototype-level semantic transport to infer the posterior distribution of the latent counterpart. Extensive experiments on six widely-used multi-view datasets against 10 state-of-the-art MvC methods demonstrate the effectiveness of PLCI for tackling the imperfect information problem. The code will be released upon acceptance. --- ### Expectations vs. Realities: The Cost of MSE-Optimal Forecasting Under Conditional Uncertainty Authors: Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04342v1 Multi-step time series forecasting (MSF) is commonly evaluated using point-wise error metrics such as mean squared error (MSE), implicitly treating the conditional mean as a sufficient target. We show that this can be misleading under conditional uncertainty, where the conditional expectation becomes unrepresentative of typical realized values at longer horizons. We formalize this effect through a conditional uncertainty gap and prove that whenever this gap is nonzero, no deterministic predictor can simultaneously minimize MSE and match the marginal distribution of realized futures. This establishes a fundamental, model-agnostic trade-off between point accuracy and marginal realism in MSF evaluation. Using controlled stochastic dynamical systems and nine real-world forecasting benchmarks, we empirically characterize the resulting accuracy--realism frontier and \textbf{quantify the practical cost of MSE-only model selection}. As conditional uncertainty increases with forecast horizon, the attainable set expands into a pronounced Pareto front, separating MSE-optimal but under-dispersed predictors from methods that trade accuracy for realistic marginal variability. \textbf{Across benchmarks, we find that small relaxations in MSE ($\boldsymbol{\le 5\%}$) frequently unlock disproportionate gains in marginal realism, with median improvements of $\mathbf{17.3\%}$ and gains exceeding $\mathbf{30\%}$ in some datasets.} We further show that common forecasting strategies systematically occupy different regions of this frontier: direct multi-output predictors concentrate near the accuracy-optimal extreme, while recursive strategies and sample-based inference favors marginal realism. Together, these results expose a structural failure mode of MSE-based evaluation in long-horizon forecasting and recast strategy and inference selection as navigation of an unavoidable accuracy--realism trade-off. --- ### Noisy memory encoding explains negative polarity illusions Authors: Yuhan Zhang, Edward Gibson Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04340v1 A sentence like "The authors that no critics recommended have ever received acknowledgment for a best-selling novel" is sometimes rated as acceptable even though, strictly speaking, it is ungrammatical because the negative polarity word "ever" is not licensed where it is. This behavioral effect is sometimes called a "negative polarity illusion". Here we propose that the lossy context surprisal theory of Hahn et al. (2022) -- whereby people have an imperfect encoding of complex sentences -- might explain this effect. We hypothesize that people have poor memory representation of the determiners in the main-clause and embedded-clause subjects and could entertain a determiner exchange that licenses ever. We propose that more similar determiners in those positions would trigger stronger illusion effects. Acceptability judgment tasks with six novel determiner pairs (e.g., "few" and "many", "few" and "most") support our proposal, showing, specifically, that a novel sentence, "Many authors that few critics recommended have ever received acknowledgment for a best-selling novel", triggered a much stronger illusion than the canonical one even without time pressure. These results offer further support for the suggestion that human language processing is imperfect and resource-rational: in face of working memory limitations, humans rationally reconstruct what is most likely from noisy linguistic input to facilitate downstream processing. --- ### Literature-Guided Minimax Optimization of Virtual Epilepsy Neurostimulation Authors: Cathy Liu Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04339v1 Computational models of epilepsy promise patient-specific treatment design, but most optimization workflows still search for parameters that perform well on average. In neuromodulation, this is a weak target: a protocol that improves the mean response can still fail in the patient whose network is least tolerant to stimulation. We present a literature-guided minimax pipeline that couples PubMed-scale hypothesis extraction, The Virtual Brain (TVB) Epileptor simulations, and large-language-model-guided black-box optimization. The optimizer proposes either intrinsic model-control parameters or clinically interpretable external-stimulation protocols; TVB evaluates each proposal across sampled virtual patients; and the objective maximizes worst-case reward, defined as the negative variance of simulated seizure activity. In the intrinsic model-control experiment, the best archived parameter set improved worst-case reward from -0.5285 to -0.3182, a 39.8% gain over baseline. The clinical-style external-stimulation search produced a much smaller worst-case improvement (1.7%), and a 20-patient virtual cohort showed no aggregate benefit (p=0.9019), despite a 55% responder rate and a positive temporal-lobe subgroup signal. The study should be read as an in silico proof of concept for robust, literature-aware neurostimulation design, not as clinical evidence. --- ### Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving Authors: Xixi Tian, Di Wu, Xiang Liu, Yiziting Zhu, Yujie Li, Xin Shu, Bin Yi Published: 2026-06-03 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2606.04338v1 Privacy-sensitive and distributed characteristics of multi-center medical data bring severe obstacles to centralized modeling for accurate early prediction of sepsis. Federated learning (FL) has attracted growing attention as a promising framework for collaborative model development, as it allows multiple institutions to jointly train predictive models without directly sharing or centralizing raw data. Nevertheless, its practical performance, robustness, and privacy-preserving benefits remain insufficiently evaluated using real-world clinical datasets. To bridge this gap, this study systematically examines the application of federated learning to multi-center sepsis prediction. The experimental dataset consists of 648 clinically screened samples collected from three tertiary hospitals in China, with rigorous inclusion and exclusion criteria. We establish a centralized training paradigm as the performance baseline, and then implement a horizontal federated learning framework for distributed collaborative modeling. Extensive experimental results demonstrate that the federated learning-based model achieves highly comparable prediction accuracy to the centralized counterpart, while fundamentally avoiding privacy leakage. Further privacy security analysis verifies that malicious attackers cannot reconstruct the original patient data from the transmitted model parameters, indicating strong resistance against data reconstruction attacks. This work not only validates the practicality and security of federated learning in clinical sepsis prediction, but also provides a reliable and feasible solution for privacy-preserving multi-center medical collaboration. --- ### Policy Gradient for Continuous-Time Robust Markov Decision Processes Authors: Tanya Veeravalli, David M. Bossens, Atsushi Nitanda Published: 2026-06-03 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2606.04335v2 The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimisers to obtain linear convergence in the oracle-based setting and an $\tilde{\mathcal{O}}(\frac{1}{ε^2})$ sample complexity in the sample-based setting in an analysis which also derives novel tools for the framework of undiscounted total cost MDPs. Additionally, we propose mean-field optimisers as distributional optimisers with an $\tilde{\mathcal{O}}(\frac{1}{K})$ oracle-based convergence rate and an $\tilde{\mathcal{O}}(\frac{N^2}ε)$ sample complexity under $N$-particle approximation. The effectiveness of continuous-time policy gradient algorithms is confirmed for both optimisers on continuous-time RMDPs with neural ordinary differential equation dynamics. --- ### From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents Authors: Pritam Dash, Tongyu Ge, Aditi Jain, Tanmay Shah, Zhiwei Shang Published: 2026-06-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.04329v2 Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory poisoning, where a single adversarial memory write can exert long-term influence over agent behavior. We present a systematic study of memory poisoning in LLM-based agents. We identify four memory write channels and nine structural vulnerabilities in model capabilities, system prompt design, and agent system architecture that make these channels exploitable. Based on these vulnerabilities, we develop a taxonomy of six classes of memory poisoning attacks. Furthermore, we design MPBench -- a benchmark for evaluating memory poisoning attacks, and show that agents designed to write and retrieve memory more aggressively are more exploitable. We also show that existing prompt injection defenses fail to cover memory poisoning attacks. Our findings provide a foundation for understanding and mitigating memory poisoning attacks against AI agents. --- ### Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers Authors: Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci Published: 2026-06-03 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2606.04328v1 Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conventional rule-based and optimization-driven radio resource management (RRM) toward artificial intelligence (AI)-driven RRM. AI-driven approaches can learn complex nonlinear relationships, generalize across diverse network conditions and enable real-time, scalable and autonomous decision-making. Among RRM techniques, coordinated multipoint (CoMP) transmission is pivotal for mitigating inter-cell interference and enhancing cell-edge performance, thereby improving quality of experience (QoE) in dense deployments. However, optimal multi-cell selection remains a complex combinatorial challenge as it requires jointly optimizing over many possible serving-cell combinations under dynamic traffic and channel conditions. Despite their success, conventional deep reinforcement learning (DRL) methods such as proximal policy optimization (PPO) suffer from poor sample efficiency, limited generalization, and costly retraining when state and action spaces change. To address these bottlenecks, we propose a Prompt Decision Transformer (PromptDT) based multi-task learning framework capable of learning across diverse network configurations and reformulating multi-cell selection as a sequence modeling problem. By leveraging offline trajectories and task-specific prompts, PromptDT enables scalable learning across diverse network configurations, including varying base stations and user equipment counts, and scheduler policies. Experimental results demonstrate that PromptDT improves QoE by up to 49% in multi-task settings compared to baselines, with performance scaling positively alongside model capacity. Moreover, PromptDT generalizes effectively to unseen tasks, achieving robust few-shot adaptation to new network configurations without retraining or fine-tuning. --- ### A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks Authors: Tian Ding, Dawei Li, Ruoyu Sun Published: 2026-06-03 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2606.04327v1 We investigate the geometric structure of stationary plateaus that arise in the loss landscape of two-layer neural networks with smooth activation functions. We focus on the phenomenon of "neuron splitting" where duplicating a hidden neuron yields an affine set of stationary points in a wider network. We provide a comprehensive classification of all stationary points on these plateaus, determining under what conditions they constitute local minima or saddle points. Our characterization hinges on a per-neuron curvature object we term the "inner Hessian" matrix. Our analysis reveals that the definiteness of the inner Hessian and the choice of splitting coefficients jointly dictate the local geometry of the plateau. We show that "splitting" a local minimum can yield either a mixture of local minima and saddles or an all-saddle plateau, with a concrete sure-saddle region identified under mild assumptions. In contrast, splitting a saddle point always produces a plateau of saddle points. Our results unify and extend prior landscape analyses, elucidating when and how model expansion preserves or alters the nature of stationary points. These findings offer new geometric insights into the effects of width expansion and reparameterization in neural networks. --- ### Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models Authors: Julian Skirzynski, Harry Cheon, Shreyas Kadekodi, Meredith Stewart, Berk Ustun Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04326v1 Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels. This limits researchers' ability to determine which problems are suitable for these models, isolate the factors that drive their performance or lead to failures, or uncover which algorithms perform well. In this paper, we develop synthetic benchmarks for concept-bottleneck models, focusing on their two main use cases: decision support, in which models assist humans in making better decisions, and automation, in which models handle routine tasks without supervision. Our benchmarks can generate labeled datasets while controlling for properties that affect performance, including data modality, concept choice, annotation quality, and completeness. We demonstrate how the benchmarks can be used to evaluate representative classes of concept bottleneck models. Our demonstrations show how the benchmarks can diagnose failure modes and guide follow-up testing. --- ### Parameter-Efficient Fine-Tuning with Learnable Rank Authors: Arpit Garg, Simon Lucey, Hemanth Saratchandran Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04325v1 Low-Rank Adaptation (LoRA) is a popular parameter-efficient fine-tuning (PEFT) method that restricts weight updates to low-rank adapters, introducing a fixed low-rank inductive bias by optimizing in a low-dimensional subspace. In this work, we question whether a fixed-rank constraint is the most effective inductive bias for parameter-efficient fine-tuning. We introduce *Learnable Rank LoRA (LR-LoRA)*, a PEFT method in which the adapter rank is learned during the training process. Instead of prescribing a uniform rank for all adapter layers, LR-LoRA allows the optimizer to determine the appropriate rank for each layer. Using this approach, we find substantial layer-wise variation in the learned ranks, with the attention and MLP layers in the transformer models exhibiting systematically different rank preferences. Across a range of language understanding and commonsense reasoning benchmarks, LR-LoRA achieves state-of-the-art performance in most settings and consistently outperforms strong PEFT baselines, demonstrating that a learnable rank provides a more flexible and effective inductive bias than fixed-rank adaptations. --- ### Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries Authors: Riccardo Saporiti, Fabio Nobile Published: 2026-06-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.04324v1 One of the primary challenges in Bayesian inference on the parameters of a diffusion model from discrete observations is the unavailability of an analytical expression for the transition density function between consecutive observation times, which is needed to derive the likelihood function. Extending previous studies that solve Fokker-Planck (FP) type partial differential equations with Normalizing Flows, we propose a new Normalizing Flow architecture to learn the transition density function of the diffusion process between two observation times. We do so by solving in a Neural Galerkin framework the associated FP equation with a Dirac mass as initial condition, over a specified training distribution of the initial datum and the coefficients of the diffusion. We specifically focus on processes whose diffusion matrix vanishes in certain inaccessible boundary regions, such as Stochastic Volatility models that satisfy a Feller condition. The product of the obtained transition densities evaluated along the observed trajectory approximates the likelihood function, thereby enabling cheap posterior sampling via Markov chain Monte Carlo (MCMC). After the offline training phase, inference becomes significantly more efficient, as it avoids the need to solve the FP equation in real time for each parameter proposed by the MCMC sampler or to rely on other likelihood-free methods for Bayesian inference that involve repeated simulation of diffusion bridges. --- ### Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge Authors: Tomoya Miyazawa, Hiroyasu Okuno Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04323v1 In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, where models must infer relations that are not always explicitly visible. We propose Answer Self-Consistency with Margin-Triggered Question Re-Arbitration (ASC-MQRA), a training-free test-time reasoning framework built on a multimodal reasoning model. The core ASC component performs multiple stochastic video question-answering runs and aggregates their answer choices through answer-level self-consistency. This substantially improves over single-pass inference and forms our final test submission. We further study MQRA, a conditional re-arbitration module for low-margin examples where the first-stage vote distribution indicates uncertainty. Our vote-margin analysis shows that low-margin examples often retain the ground-truth answer among the top candidates, motivating MQRA to narrow the candidate set and re-watch the video only over the retained candidates. On validation, MQRA further improves over ASC, indicating that low-margin vote distributions can provide a useful uncertainty signal. On test, however, MQRA slightly degrades performance relative to ASC, suggesting that re-arbitration is sensitive to the size and category distribution of the triggered subset. Our final test submission therefore uses ASC without re-arbitration, achieving 72.73 average accuracy and 78.34 category-wise macro average accuracy on validation, and 81.16 average accuracy and 80.91 category-wise macro average accuracy on test. This report details our prompting strategy, implementation setup, ablation studies, and diagnostic analyses. The code is available at https://github.com/data-analytics-labo/ASC-MQRA --- ### The Digital Apprentice: A Framework for Human-Directed Agentic AI Development Authors: Travis Weber, Rohit Taneja Published: 2026-06-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.04321v1 Agentic AI deployments face a recurring design tension: heavy human oversight limits scale, while broad autonomy outruns accountability. Neither posture provides the governance infrastructure required for responsible delegation. We present the Digital Apprentice, a framework for scalable, safe AI agency in which autonomy is earned, not assumed. The Digital Apprentice is a developmental learner that internalizes the tacit methodology of a directing human, graduating through per-skill autonomy tiers only when empirical evidence justifies it. The result is an agent that becomes genuinely useful over time while remaining aligned to a specific human's standards. Three architectural components make this possible. (1) Methodology capture, distilling a directing professional's tacit approach into structured assets. (2) Authorization, with autonomy escalation gated by explicit human approval. (3) Continuous alignment, correcting drift at runtime and converting each correction into owned preference data. We instantiate this framework as an inference-time control plane. We mathematically model the quality framework and discuss policies and techniques designed to raise quality. We apply the framework to an open professional corpus, and we show how catching data drift and applying a different technique at runtime recovers degraded quality dimensions under traffic shift. The implication extends beyond any single application. We believe these three pillars, stitched together as a system, form a safer and more viable path to agentic systems that can scale without sacrificing trust. --- ### OpenRFM: Dissecting Relational In-Context Learning Authors: Zhikai Chen, Junyu Yin, Jialiang Gu, Siheng Xiong, Xiaoze Liu, Ruowang Zhang, Keren Zhou, Kai Guo Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04320v1 Relational Foundation Models (RFMs) promise a single pre-trained predictor that, given any relational database, returns predictions in one forward pass via relational in-context learning (ICL). Yet a substantial gap separates open RFMs from their commercial counterparts, and the origin of this gap has not been systematically understood. We dissect a representative framework, the Relational Transformer (RT), from two perspectives. Model side: we show that RT performs relation-level ICL, and a kernel regression view shows it fails when sparse label-cell coverage yields an underdetermined regression. Data side: we ablate RT's pre-training source and find that existing synthetic-only pre-training and in-distribution pre-training drive the same architecture into different regimes, lazy vs. feature-learning. Probing this gap reveals that the missing ingredient is a support-identifiable relational latent in the label-generation process. These two diagnoses translate into (1) a dual-stage ICL architecture that combines the relational backbone with a batch-level ICL layer lifted from a pre-trained tabular foundation model to overcome relation-level label scarcity, and (2) a homophily-aware synthetic plus continual real-data pre-training mixture, augmented with a prototype-based regularization. These choices define OpenRFM, a simple yet effective RFM that improves average task performance by approximately 30% over the RT backbone and surpasses the commercial model KumoRFMv1 on a large set of evaluation tasks. --- ### PureLight: Learning Complex Luminaires with Light Tracing Authors: Pedro Figueiredo, Zixuan Li, Beibei Wang, Miloš Hašan, Nima Khademi Kalantari Published: 2026-06-03 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.04319v3 We propose a neural formulation for estimating the appearance of complex luminaires. We focus on challenging luminaires with complex light transport (e.g., small emitters enclosed by multiple specular layers) that are difficult for (bidirectional) path tracing. To this end, we use light tracing to construct paths from emitters to the exit surfaces and formulate appearance estimation as a distribution learning problem. Specifically, we model the probability density function (pdf) of outgoing radiance on the exit surfaces using a large normalizing flow network, and recover the outgoing radiance as the product of the estimated pdf and flux. To enable efficient inference, we distill the learned appearance into a lightweight MLP that directly estimates radiance on the exit surfaces. We additionally train a sampling network for effective direct illumination computation from the luminaire, and a blending network to composite the luminaire into the scene. Our formulation makes it feasible to render challenging luminaires using low sample counts in arbitrary scenes. Code is available at https://github.com/pedrovfigueiredo/purelight. --- ### PureLight: Learning Complex Luminaires with Light Tracing Authors: Pedro Figueiredo, Zixuan Li, Beibei Wang, Miloš Hašan, Nima Khademi Kalantari Published: 2026-06-03 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.04319v2 We propose a neural formulation for estimating the appearance of complex luminaires. We focus on challenging luminaires with complex light transport (e.g., small emitters enclosed by multiple specular layers) that are difficult for (bidirectional) path tracing. To this end, we use light tracing to construct paths from emitters to the exit surfaces and formulate appearance estimation as a distribution learning problem. Specifically, we model the probability density function (pdf) of outgoing radiance on the exit surfaces using a large normalizing flow network, and recover the outgoing radiance as the product of the estimated pdf and flux. To enable efficient inference, we distill the learned appearance into a lightweight MLP that directly estimates radiance on the exit surfaces. We additionally train a sampling network for effective direct illumination computation from the luminaire, and a blending network to composite the luminaire into the scene. Our formulation makes it feasible to render challenging luminaires using low sample counts in arbitrary scenes. --- ### Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks Authors: Bin Duan, Zeyu Bai, Guowei Yang Published: 2026-06-03 Categories: cs.CR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2606.04317v1 Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution platforms. This broad deployment landscape exposes model parameters to various integrity risks. Unlike input-space adversarial attacks, parameter attacks directly tamper with the model's internal parameters and persist across all subsequent inferences. Existing defenses either require retraining, incur significant accuracy degradation, or are limited to specific attack classes. However, in real-world deployment scenarios, the forms of parameter attacks are often unpredictable. To address this challenge, we present ParDef, a generalized defense for deep neural networks against diverse types of parameter attacks. ParDef integrates keyed channel reparameterization, which obscures sensitive parameter directions, QC-LDPC quantization, which embeds redundancy and supports error correction, and adaptive robust inference, which stabilizes predictions under uncertainty. Our evaluation on CIFAR-10, CIFAR-100, and Tiny-ImageNet using ResNet and VGG models demonstrates that ParDef consistently reduces attack success rates across different parameter attacks while maintaining high model performance and incurring only moderate deployment overhead. These results highlight that ParDef is a practical and generalized defense for DNN deployments. --- ### Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline Authors: Zhikai Chen, Jialiang Gu, Junyu Yin, Xianxuan Long, Shenglai Zeng, Xiaoze Liu, Kai Guo, Keren Zhou, Jiliang Tang Published: 2026-06-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.04315v1 LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (multi-session chat or a single trajectory format), and there is little evidence that they generalize across the heterogeneous trajectories agents encounter in deployment. We revisit eight memory systems plus an agentic harness for search problems, on five scenarios: single-turn QA, multi-session chat, agentic-trajectory QA, memory stress tests, and long-horizon agentic tasks. The harness, which self-manages flat text-file storage via tool calls, achieves the best cross-task ranking, suggesting that memory performance hinges on giving the agent active control over storage and retrieval rather than on a passive store behind a fixed pipeline. We instantiate this insight in AutoMEM, an agentic memory harness with a self-managed tool interface that achieves the best cross-scenario generality among the systems we evaluate. --- ### Testing Neural Networks via Bayesian-Guided Exploration of Decision Landscapes Authors: Bin Duan, Meiru Che, Guowei Yang Published: 2026-06-03 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2606.04314v1 As neural networks are increasingly deployed in safety-critical domains, testing is essential to evaluate and improve their reliability. Existing testing methods, whether black-box or white-box, primarily use global mutation or coverage-guided strategies, both of which struggle to efficiently uncover diverse model failures while remaining proximate to the original data distribution and semantics. We propose BayesWarp, a testing framework that addresses this limitation by mutating decision-critical input regions identified via interpretable saliency techniques and adaptively guiding the testing process using an uncertainty-aware Bayesian Optimization strategy, enabling the discovery of diverse failures while preserving distributional and semantic proximity to the original data. Evaluation on MNIST, CIFAR-10, and ImageNet across six neural network models shows that BayesWarp improves failure discovery, failure diversity, test case quality, and critical neuron coverage under a fixed mutation budget. These results demonstrate that BayesWarp improves testing effectiveness. Moreover, fine-tuning with the generated failure cases leads to improvements in model performance. --- ### Latent Anchor-Driven Test Generation for Deep Neural Networks Authors: Bin Duan, Matthew B. Dwyer, Guowei Yang Published: 2026-06-03 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2606.04310v1 Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds. --- ### Folded Transport MCMC: Eliminating Label Switching by Sampling on a Fundamental Domain Authors: Jun Hu Published: 2026-06-03 Categories: cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2606.04307v2 In Bayesian mixture models and other exchangeable-component models, the posterior is invariant under permutation of component labels, creating m! equivalent modes-the label-switching problem. Standard MCMC methods either mix poorly across these modes or rely on post-hoc relabelling that cannot guarantee the sampler has converged. We propose Folded Transport MCMC (FolT-MCMC), which eliminates label switching before sampling by restricting the Markov chain to a fundamental domain-a sorted or reflected subspace containing exactly one representative from each symmetric mode. The proposal is a learned normalising flow whose density is symmetrised over the group orbits, ensuring correct targeting on the reduced space. We show that this construction preserves a computable convergence diagnostic based on the oscillation of the log-density ratio, and that the diagnostic becomes sharper on the fundamental domain whenever the original-space flow under-covers one or more symmetric modes. Experiments on Gaussian mixtures (d=2-20), label-switching targets (up to 24 equivalent modes), a standard Bayesian three-component mixture posterior, and real accelerometer data from a supertall building show improvement ratios of 2x to 145x, with the folded diagnostic stable across dimensions while the unfolded diagnostic collapses. --- ### Offline-to-Online Learning in Linear Bandits Authors: Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan Published: 2026-06-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.04305v1 We study online learning with an additional offline dataset in the stochastic linear bandit setting. Although this problem arises frequently in practice, the offline-to-online tradeoff remains poorly understood in structured environments. We propose a linear bandit algorithm that balances this tradeoff: it relies on offline data during early rounds, and increasingly favors exploration as the horizon grows. We establish regret bounds showing that our method is simultaneously competitive with both purely online and purely offline solutions. In particular, it achieves sublinear regret relative to the optimal action in the number of online interactions, while its regret relative to an offline reference decreases as the number of offline samples grows. Empirical results further demonstrate its effectiveness across various problem parameters. --- ### LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding Authors: Haocheng Xia, Mihir Pamnani, Hanxi Fang, Supawit Chockchowwat, Yongjoo Park Published: 2026-06-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.04302v1 Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens. Its importance becomes even greater in long-context applications such as retrieval-augmented generation (RAG) and in-context learning (ICL). However, conventional KV caching embeds positional information directly into the cache, limiting its reusability. Existing solutions either restrict reuse to prefixes or require expensive memory materialization for positional re-encoding. We introduce LazyAttention, a novel attention mechanism that kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV reuse. By adjusting positional encoding within attention kernels on-the-fly, LazyAttention resolves the materialization bottleneck, allowing a single physical KV copy to serve multiple logical requests at arbitrary positions. Leveraging attention kernels tailored for prefilling and decoding, our system achieves significant efficiency improvements: under skewed document distributions, it reduces time-to-first-token (TTFT) by 1.37$\times$ and increases inference throughput by 1.40$\times$ compared to the state-of-the-art Block-Attention, while maintaining comparable output quality. --- ### XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation Authors: Byunghyun Ko, Aleksei Anisimov, Kobe Ke, Suhas Bharthepude, Jeongkyu Lee Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04301v1 Acquiring labeled medical image data is resource-intensive and a challenge further exacerbated in cross-domain scenarios where source and target datasets differ in imaging equipment, population, or clinical site. This study introduces XSSR (Cross-Domain Self-Supervised Representative Selection), a framework designed to minimize annotation effort in the target domain while maintaining robust segmentation performance. XSSR comprises three stages: first, a Masked Autoencoder (MAE) is trained on unlabeled source data to establish a shared embedding space without requiring target labels; second, a greedy selection algorithm scores unlabeled target samples based on a composite density, novelty, and diversity criterion; and third, a U-Net segmentation model is trained exclusively on the selected subset. The novelty-diversity trade-off parameter, alpha, is automatically calibrated by minimizing embedding-space coverage, eliminating manual tuning. We evaluate XSSR on three public benchmarks: Chest X-ray, RIGA+ retinal fundus imaging, and multi-site Prostate MRI, each under a fixed 5% annotation budget. XSSR achieves 99.3% of full-data performance on Chest X-ray using only 22 labeled samples, surpasses random selection by up to 2.5 Dice points on Prostate MRI, and consistently outperforms the CoreSet baseline by 0.4 to 1.2 Dice points across all datasets. Ablation studies indicate that diversity is the most influential scoring component, and per-site analysis shows that performance correlates with scanner similarity to the source domain. --- ### Efficient and Training-Free Single-Image Diffusion Models Authors: Haojun Qiu, Kiriakos N. Kutulakos, David B. Lindell Published: 2026-06-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.04299v1 We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, training is computationally expensive and requires hours of optimization. Instead, we model the image using a dataset of its patches at different scales. As this dataset is finite and the dimensionality of its patches is small, the score function for a noisy patch can be computed tractably using an optimal, closed-form denoiser, eliminating the need for neural network training. We integrate this patch-based denoiser into an efficient, training-free image diffusion model, and we describe how our method connects to classical patch-based image restoration techniques. Our approach achieves state-of-the-art generation quality and diversity compared to trained single-image diffusion models, and we demonstrate applications, including unconditional image generation, text-guided stylization, image symmetrization, and retargeting. Further, we show that our approach is compatible with latent space diffusion, and we show multiple additional acceleration techniques to achieve megapixel single-image generation in one second, and gigapixel generation in minutes. --- ### WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling Authors: Zhongzheng Li, Qingsong Ran, Shikun Feng, Nian Ran, Wenhao Li, Xiaoyuan Zhang, Yue Wang, Xiaoguang Zhao Published: 2026-06-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.01608v1 Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error refinement. A natural way to improve search efficiency is to use world modeling, which can help identify promising optimization directions before costly evaluation. Large language models can predict the outcomes of these candidates with nontrivial accuracy because of their implicit knowledge. Motivated by this observation, we propose WMLLM, a self-evolving optimization-agent framework based on predict-then-act world modeling. The agent first predicts promising directions and then acts to generate candidates. Combined with agentic multi-turn refinement, population-based search, and reinforcement learning, WMLLM refines both its implicit world model and its optimization strategy during search. Experiments on black-box optimization tasks, especially multi-objective molecular optimization, show that WMLLM improves sample efficiency and final optimization performance. On the multi-objective molecular optimization benchmark, WMLLM achieves state-of-the-art results under a limited evaluation budget. --- ### Transformer Models for Text Summarization: A Comparative Study of BART, BERT, and RoBERTa Authors: Daisy Aptovska, Vinayak Elangovan Published: 2026-06-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.19200v1 Text summarization refers to the task of condensing a document into a shorter version while preserving its key information. Automatic text summarization (ATS), driven by advancements in natural language processing (NLP), has developed rapidly in recent years. ATS methods are commonly categorized by input type (such as single-document or multi-document summarization) and by output type (extractive, abstractive, and hybrid). This article presents a focused review of modern summarization techniques with an emphasis on transformer based models and large language models (LLMs), specifically BERT, RoBERTa and BART. It examines their architectures, pretraining strategies, and their suitability for extractive and abstractive summarization tasks. --- ### Position: Certified Correctness in Neural Constraint Reasoning Requires Symbolic Integration Authors: Shufeng Kong, Xiaochuan Zhang, Caihua Liu Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14569v1 Neural solvers for constraint satisfaction problems have achieved remarkable in-distribution accuracy, yet they suffer from a fundamental limitation persistent constraint violations occur under distribution shifts even when the model reports high confidence. This position paper argues that when hard constraints exist and the cost of verification is relatively low, neural constraint reasoning must prioritize symbolic integration over pure learning. We justify our focus on Sudoku as a representative NP-complete testbed because it exhibits a sharp asymmetry between easy verification and hard solving: checking a candidate solution requires only polynomial time $O(n^{2})$, while finding a solution may require exponential search. Through a comprehensive survey of solving methods spanning deterministic algorithms, metaheuristic optimization, learning-based approaches, and language-conditioned reasoning, we demonstrate that neural-only methods without instance-level certification fail to achieve the provable correctness that symbolic and neuro-symbolic approaches provide. We advocate for a bidirectional integration in which neural methods enhance symbolic solvers by learning heuristics and converting percepts into symbols, while symbolic methods verify neural outputs to ensure their reliability. To operationalize this position, we propose a multi-agent certified reasoning framework that demonstrates how this integration can achieve both computational efficiency and provable correctness. --- ### Steering the Language Axis: From Linear Decodability to Causal Control Authors: Arnav Srivastav Published: 2026-06-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.12334v1 Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood. In this work, we ask whether language identity is merely linearly decodable from hidden states, or if it can be causally controlled by a compact activation direction. We conduct an exhaustive causal intervention analysis across multiple model families, including Qwen 3.5-2B and Llama-3.2-1B-Instruct, isolating PCA-derived "language axes" to perform steering and ablation experiments across 1.26 million generations on the FLORES-200 dataset. Steering along these geometric directions reliably forces language switching in both cross-script (English to Chinese) and same-script (English to Spanish) settings, whereas equal-magnitude random perturbations yield virtually no effect. Our layerwise analysis reveals that language commitment is highly localized and explicitly language-pair-dependent. While English to Chinese switching resists early intervention and steers easily in the later layers, the English-Spanish transition shifts earlier, displaying a distinct, bimodal sensitivity. Furthermore, targeted ablation uncovers a fundamental reversion to English: once the language signal is removed, the model falls back to English regardless of the input prompt. Ultimately, these findings demonstrate that language decision boundaries function during inference as causally active features that are direction-dependent and layer-specific. --- ### Vision-Language Models are Fragile Multilingual Associators Authors: Ritabrata Chakraborty, Rajatsubhra Chakraborty, Shivakumara Palaiahnakote, Angelo Cangelosi, Umapada Pal Published: 2026-06-02 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.12333v1 Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the input changes is unexplored. We introduce M$^2$BIND, a benchmark varying the language of the context and query across multiple languages. We evaluate binding both extrinsically through task performance metrics and intrinsically through causal interventions. We find that binding is not language-invariant: cross-family and cross-script settings trigger significant binding collapse, with the model's internal binding computation shifting to later layers and losing causal strength. Closely related languages preserve associations comparatively better. In a broader sense, our findings indicate how VLMs deployed globally in multilingual settings cannot be assumed to maintain the same association quality observed in monolingual evaluation. --- ### Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation? Authors: Hyowon Wi, Noseong Park Published: 2026-06-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.12332v1 In recent years, low-rank adaptation (LoRA) has emerged as a significant paradigm that freezes pre-trained weights and introduces small, learnable adapters instead of fine-tuning the full set of parameters. In this work, we uncover several key insights regarding the singular components of network parameters based on Singular Value Decomposition (SVD). Firstly, the principal singular components with large singular values in pre-trained network parameters can be effectively reused during fine-tuning, whereas the minor components with smaller singular values are more task-specific and require substantial adaptation. Secondly, we first establish the theoretical connection that the uncontrolled growth of singular values in LoRA adapters leads to the forgetting of pre-trained knowledge -- a well-known issue referred to as catastrophic forgetting. Building on these observations, we propose SCLoRA, which injects parameterized singular components with spectral clipping into the pre-trained model in a way that is aware of the spectral distribution of the pre-trained model. SCLoRA effectively adapts to new tasks by focusing updates on components that require adaptation, while simultaneously alleviating catastrophic forgetting. We conduct extensive experiments and demonstrate that SCLoRA not only improves downstream performance but also effectively retains pre-trained knowledge. --- ### HyperShape: Hyperelasticity Across Diverse Shapes Authors: Leo Widmer, Sidaty El Hadramy, Stéphane Cotin, Philippe Claude Cattin Published: 2026-06-02 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2608.09938v1 Hyperelastic deformations are highly sensitive to domain geometry and boundary conditions, making generalization across both a critical capability for neural operators applied to these problems. However, existing benchmarks for neural operators on hyperelasticity rely on simple or few geometries, which makes it difficult to assess this capability rigorously. To address this gap, we introduce HyperShape, an extensible framework designed to generate synthetic shapes and their corresponding hyperelastic simulation data, producing a suite of 2D and 3D datasets with adjustable complexity and controllable shape variations. This design enables systematic assessment of generalization across in-distribution, out-of-distribution, and synthetic-to-real transfer settings. Using this framework, we evaluated the performance of several state-of-the-art neural operators over diverse shape distributions. Our findings reveal that neural operators perform well on simple shapes but struggle as shape complexity, geometric diversity, and boundary condition variability increase, requiring large amounts of training data in such regimes. Performance degrades consistently and predictably with geometric complexity highlighting the need for further model development. As an open and extensible benchmark, HyperShape is designed to grow alongside the field: new geometries, material models, loading conditions, and evaluation settings can be easily incorporated to validate hyperelastic surrogate models. --- ### Unanticipated Effects of Generative AI on Expertise Pathways and Performance Perception in System Administration Authors: Rana Abou Khamis, Hala Assal, Ashraf Matrawy Published: 2026-06-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28650v2 While industry discourse often emphasizes immediate productivity gains and frames GenAI primarily as a tool for automation, the integration of GenAI into system administration may involve deeper shifts in professional practice that are not yet fully understood. Drawing on 14 semi-structured interviews with IT professionals, this paper explores the lived reality of embedding GenAI into daily routines of troubleshooting, scripting, and system verification. Through inductive thematic analysis, we uncover two unanticipated socio-technical findings. First, we describe a "compression of traditional expertise pathways" where GenAI appears to function as both a mentor-like tutor and a "ladder-shortening" tool. While the tool can support faster task performance in unfamiliar domains, our findings suggest it may also reduce a practitioner's exposure to the foundational, hands-on cycles of building, failing, and debugging that historically served as the training ground for technical expertise. Second, we describe a "performance perception shift," where the speed of AI-assisted work begins to reset organizational and self-expectations for productivity. This shift may create a "two-speed culture" within teams and introduce "productivity guilt," as necessary manual work, even when required for safety or validation, is increasingly perceived as slow or a failure of efficiency. Our results raise broader questions about how GenAI may influence expertise development, how professional value is assessed in high-stakes technical environments, and the role of human judgment in complex technical environments. --- ### Unanticipated Effects of Generative AI on Expertise Pathways and Performance Perception in System Administration Authors: Rana Abou Khamis, Hala Assal, Ashraf Matrawy Published: 2026-06-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28650v1 While industry discourse often emphasizes immediate productivity gains and frames GenAI primarily as a tool for automation, the integration of GenAI into system administration may involve deeper shifts in professional practice that are not yet fully understood. Drawing on 14 semi-structured interviews with IT professionals, this paper explores the lived reality of embedding GenAI into daily routines of troubleshooting, scripting, and system verification. Through inductive thematic analysis, we uncover two unanticipated socio-technical findings. First, we describe a "compression of traditional expertise pathways" where GenAI appears to function as both a mentor-like tutor and a "ladder-shortening" tool. While the tool can support faster task performance in unfamiliar domains, our findings suggest it may also reduce a practitioner's exposure to the foundational, hands-on cycles of building, failing, and debugging that historically served as the training ground for technical expertise. Second, we describe a "performance perception shift," where the speed of AI-assisted work begins to reset organizational and self-expectations for productivity. This shift may create a "two-speed culture" within teams and introduce "productivity guilt," as necessary manual work, even when required for safety or validation, is increasingly perceived as slow or a failure of efficiency. Our results raise broader questions about how GenAI may influence expertise development, how professional value is assessed in high-stakes technical environments, and the role of human judgment in complex technical environments. --- ### COSI-Lab: Conference Living Lab for Modeling Multi-Perspective Multimodal Social Intention Authors: Zonghuan Li, Litian Li, Arthur Mercier, Gara Dorta, Balint Dioszegi, Jose Morales-Vargas, Chenxu Hao, Ivan Kondyurin, Vanessa Begemann, Nale Lehmann-Willenbrock, Bernd Dudzik, Saunaq Chakrabarty et al. Published: 2026-06-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28649v1 COSI-Lab presents a multimodal, multi-sensor dataset of an interdisciplinary scientific workshop containing 32 academics at an international conference. It captures ecologically valid social interactions in a weakly scripted setting consisting of two 30-minute mingling sessions with real professional and social consequences for the participants involved. We argue that future intelligent systems could be better equipped to handle subjective perceptions by modeling their multiplicity not as label noise but as a explainable perspective-driven reasoning process. We focus on the Apparent Intent Inference (AII) problem as determined by ex-situ observers and conceptualize intentions to be independent of manifest future outcomes. We contribute 1. a novel annotation process for AII that accounts for a perceiver's own interpretative tendencies, 2. quantitative and qualitative analyses of intent narratives with respect to diversity, grounding, and plausibility; 3. benchmark tasks for AII and surrounding relevant contextual factors such as social involvement; 4. speech quality audio for all participants as well as privacy preserving multi-modal data, enabling lexical and nonverbal behavior analysis; and 5. coupling of self-reported goals of each participant (30 minute to 3 hour) with annotated AII (seconds). --- ### Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations Authors: Hainiu Xu, Zhaoyue Sun, Hanqi Yan, Jinhua Du, Caroline Catmur, Yulan He Published: 2026-06-02 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28648v2 Large Language Models (LLMs) are increasingly used for emotional support tasks, such as negative thought reframing. This task relies on modifying cognitive appraisals, the subjective interpretation of events that elicit negative emotions, which is typically conceptualized along multiple discrete dimensions. Current LLM-based frameworks model cognitive appraisal by exhaustively evaluating all possible dimensions, but they fail to account for the varying saliency of these dimensions across different contexts. In this work, we investigate a vital yet overlooked question: "Can LLMs infer the salient appraisal dimensions from emotional support conversations?" To address this question, we introduce the AppraiSal benchmark, containing 996 emotional support conversations with human-annotated mental states, including salient cognitive appraisal dimensions. Furthermore, we propose PRISM, a multi-agent probabilistic framework grounded in Bayesian Inverse Planning, designed to improve LLMs' ability to identify context-specific appraisal dimensions. Experimental results show that PRISM brings improvements to LLMs across various sizes, particularly in identifying the most salient appraisal dimensions. --- ### Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations Authors: Hainiu Xu, Zhaoyue Sun, Hanqi Yan, Jinhua Du, Caroline Catmur, Yulan He Published: 2026-06-02 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28648v1 Large Language Models (LLMs) are increasingly used for emotional support tasks, such as negative thought reframing. This task relies on modifying cognitive appraisals, the subjective interpretation of events that elicit negative emotions, which is typically conceptualized along multiple discrete dimensions. Current LLM-based frameworks model cognitive appraisal by exhaustively evaluating all possible dimensions, but they fail to account for the varying saliency of these dimensions across different contexts. In this work, we investigate a vital yet overlooked question: "Can LLMs infer the salient appraisal dimensions from emotional support conversations?" To address this question, we introduce the AppraiSal benchmark, containing 996 emotional support conversations with human-annotated mental states, including salient cognitive appraisal dimensions. Furthermore, we propose PRISM, a multi-agent probabilistic framework grounded in Bayesian Inverse Planning, designed to improve LLMs' ability to identify context-specific appraisal dimensions. Experimental results show that PRISM brings improvements to LLMs across various sizes, particularly in identifying the most salient appraisal dimensions. --- ### ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning Authors: Thang Doan Viet, Anh Nguyen Hoang, Tinh Luong Son, Anh Hoang Thi Ngoc, Huyen Giang Thi Thu, Tai Le Quy Published: 2026-06-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28647v1 This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement. Built on VietEduQwen, a Vietnamese educational large language model trained via supervised fine-tuning and direct preference optimization, the system ensures academically accurate, pedagogically appropriate, and student-safe interactions. ConnectED operationalizes the ADDIE framework through structured prompt templates aligned with Official Dispatch No. 5512/BGDDT-GDTrH, where each phase serves as both a generation step and a teacher validation gate. The Evaluation phase further closes the loop by connecting student performance data with iterative lesson improvement. Beyond lesson generation, the system integrates a student-facing interactive environment, enabling continuous collection of learning signals to support teacher decision-making. Evaluation on 3,119 questions from the 2025 Vietnamese National High School Examination shows that VietEduQwen achieves 87.02% accuracy, outperforming Qwen3-8B by 6.10 percentage points. Surveys of teachers (n=18) and students (n=214) demonstrate strong satisfaction with curriculum alignment, lesson clarity, and usability. In practice, lesson preparation time is reduced from 3--4 hours to approximately 30--45 minutes with teacher-in-the-loop review. Ablation studies confirm that both DPO training and ADDIE-based orchestration contribute independently to system performance, highlighting the importance of structured teacher oversight for practical deployment. --- ### Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels Authors: Joshua Brodsky, Dhravid Kumar, Savini Kashmira, Jayanaka Danatanarayana, Jason Mars, Krisztian Flautner, Lingjia Tang Published: 2026-06-02 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2607.24762v1 Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization. Optimizing these kernels is one of the most direct ways to reduce latency and cost, but it has traditionally required expert engineers to hand-write low-level GPU code. Agentic systems built on large language models (LLMs) can now generate and optimize kernels with far less human effort, yet existing tools are largely evaluated on randomly generated tensors and isolated kernels, emit standalone CUDA code that developers must manually reintegrate, mostly target only LLM PyTorch models, and offer limited support for inspecting and debugging results. We present Kernel Forge, an open-source, end-to-end agentic harness that accepts any unmodified PyTorch model in place. Kernel Forge supports vision, diffusion, and LLM workloads, uses Monte Carlo Tree Search (MCTS) to explore multiple optimization paths rather than a single linear refinement chain, and ships with a graphical user interface for monitoring progress, inspecting candidate kernels, and debugging failures. We evaluate Kernel Forge on four PyTorch models spanning vision, diffusion, and LLM workloads on an NVIDIA DGX Spark with GB10 GPU. With only 50 optimization iterations per kernel, it optimizes 14 kernels to outperform PyTorch eager mode, reaching $1.52\times$ on adaptive\_avgpool2d in ResNet-50, $1.70\times$ on group\_norm in Stable Diffusion 3.5 Medium, $2.83\times$ on softmax in Gemma 4 E2B, and $1.54\times$ on softmax in Qwen 3.5 35B-A3B. --- ### SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs Authors: Prateek Chaturvedi, Yuqicheng Zhu, Hongkuan Zhou, Dongzhuoran Zhou, Yunjie He, Steffen Staab, Fei Du, Jie Tang, Evgeny Kharlamov Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22571v1 Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perform well on public benchmarks often fail to generalize to real-world enterprise Knowledge Graphs (KGs), which are dense, schema-driven, and operationally constrained. To address these limitations, we propose SCAIR (Schema-Conditioned Agentic Iterative Reasoning), a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schema-aware traversal during multi-hop reasoning. Experiments on an enterprise-oriented benchmark constructed from a real-world Configuration Management DataBase (CMDB) demonstrate that SCAIR substantially improves performance over existing KG-RAG methods. Crucially, our study highlights that reliable enterprise graph reasoning cannot rely on generic agentic designs; instead, it must explicitly incorporate the target domain's structural and operational constraints into the reasoning process. We demonstrate that by aligning agent design with business logic, substantial performance gains can be achieved without the need for costly model retraining. --- ### Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering Authors: Chendi Wang, Liam Cunningham, Tom Yishay, Jieying Chen Published: 2026-06-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20487v2 Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings where factual errors and ideological distortions are high-stakes. We present a reproducible measurement framework that treats hallucinations, unsupported statements in document-grounded QA, as diagnostic signals of ideological drift. Using 21,727 expert-labeled U.S. political news articles from QBias spanning left, center, and right sources, we (i) generate an article-specific question, (ii) elicit document-grounded answers from three open-weight LLMs and one proprietary model, (iii) detect sentence-level hallucinations via reference-based comparison, (iv) classify the ideological valence of hallucinated sentences with a fine-tuned stance classifier, and (v) probe output logits to relate token-level uncertainty to hallucination and drift. Hallucination rates vary substantially across models and concentrate in contentious topics, while source-ideology differences in hallucination frequency are modest. In contrast, hallucination content exhibits robust leftward drift: a majority of hallucinated sentences are classified as left-leaning, including among hallucinations generated from right-leaning sources. Logit-level analysis shows hallucinations arise in high-entropy generation contexts, and in some models uncertainty also predicts leftward drift, consistent with an "uncertainty to guessing" mechanism. We discuss implications for auditing AI-mediated political information and for designing safeguards in election-relevant deployments. --- ### OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining Authors: Zhongzheng Li, Tiancan Feng, Wenhao Li, Qingsong Ran, Shikun Feng, Xiaoyuan Zhang, Yue Wang, Xiaoguang Zhao Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20486v1 Designing optimizers for modern deep learning remains a challenging scientific problem, requiring the joint consideration of optimization geometry, state dynamics, numerical stability, implementation constraints, and empirical generalization. Existing automated optimizer discovery methods typically search either over unconstrained code spaces or within narrowly parameterized optimizer families. The former is flexible but often produces invalid or uninterpretable programs, while the latter is stable but limits novelty. We introduce OPTScientist, a theory-guided multi-agent framework for optimizer discovery in a typed domain-specific language (DSL). OPTScientist formulates optimizer design as a constrained scientific search process, where candidate updates are expressed through direction, scaling, preconditioning, regularization, state, and grouping modules. Four role agents, Theorist, Designer, Engineer, and Reviewer, collaborate within a single orchestration loop to propose hypotheses, synthesize DSL candidates, compile and evaluate optimizers, and critique results. To overcome the limitations of a fixed search space, OPTScientist combines evolutionary search over optimizer programs with a second-stage mechanism that proposes small DSL extensions when repeated failures reveal representational bottlenecks. Using this framework, we discover RS-MR, a reduced-state matrix optimizer that improves transformer pretraining over strong baselines under our native evaluation protocol. Our results suggest a path toward automated optimizer science grounded in theory, typed programs, compiler validation, and closed-loop experimentation. --- ### Expectation Alignment of Language Models for Real-World User Expectations Authors: Miaomiao Li, Yang Wang, Bin Liang, Shudong Liu, Zhiwei Zhang, Kam-Fai Wong Published: 2026-06-02 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.20485v1 Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity and subtlety of real human expectations, causing models to appear competent while misaligning with what users actually seek. We present the first systematic study of user expectations in real-world LLM interactions, proposing a principled procedure to extract semantically rich expectations and introducing ExpectBench, a benchmark grounded in real user expectations. Analyses reveal that current LLMs struggle to satisfy and anticipate what users hope to obtain, highlighting a fundamental source of misalignment. Building on these observations, we propose LENS, a lightweight latent expectation-aware response generation framework. LENS enables models to internalize user expectations and generate better-aligned responses, consistently improving expectation satisfaction and underscoring the importance of explicitly modeling user expectations for realistic human-AI alignment. --- ### The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path Authors: Yiheng Tao, Kaiwen Cheng, Yao Lu, Chang Liu, Jie Chen Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20484v1 Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance. We identify that existing approaches risk drifting into one of two pathological extremes: homogenization collapse (e.g., attention sinks causing rank deficiency) and isolation collapse (e.g., local attention causing context disconnection). Through spectral analysis of attention dynamics, we derive an intrinsic trade-off between mixing efficiency (spectral gap) and information capacity (effective rank) that standard mechanisms struggle to balance. To resolve this dilemma, we propose the Topologically Regularized Side-Path (TRSP), a non-invasive architectural intervention that achieves spectral balance. TRSP employs a parameter-free Triangular Box mechanism, scaled by a lightweight, length-aware gate, to regularize the token interaction topology. By integrating proximal coupling to preserve effective rank and distal propagation to support non-degenerate mixing, TRSP promotes a geometrically healthier transition operator without altering core attention. Experiments show significant improvements across general capabilities and long-context benchmarks. Notably, on NoLiMa at $8\times$ the training length, TRSP retains $83\%$ accuracy and surpasses the Differential Transformer and Gated Attention by approximately 30 and 50 percentage points, respectively. Code available at: https://github.com/Eziotao-tyd/TRSP. --- ### Lifted State Hypothesis in Large Language Models Authors: Bumjin Park, Jaesik Choi Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19360v2 Large language models (LLMs) adapt rapidly through fine-tuning and in-context learning, yet it remains unclear which inputs they treat as the same case and why their predictions change together. We introduce the Lifted State Hypothesis. Under fixed model parameters, context scope, and target computation, samples indistinguishable in their observed computation-relevant behavior form a computation-relative type. We hypothesize that compatible episodes activate a reusable latent component---a lifted state---that supports the target computation. State reuse enables type-level generalization but creates a non-monotonic revision problem. When later evidence distinguishes a subtype, revising a state still shared with its parent may affect members whose predictions should remain unchanged. The model must separate the subtype through rerouting, a new state, or input-specific compensation. We formalize this relation between generalization and revision. We introduce the NMR-Type Dataset to evaluate LLMs. The dataset first supports a broad modulo rule. It then provides conflicting supervision for a withheld subtype while replaying earlier examples. Across full fine-tuning, LoRA, and in-context learning, models often generalize the broad rule to the subtype but fail to localize its later revision. These results provide behavioral evidence consistent with the hypothesis and motivate further study of lifted-state formation and revision. --- ### Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation Authors: Kyunghoon Jeon, Youmin Ko, Woohwan Jung, Hyunjoon Kim Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18270v1 While Electronic Health Records (EHRs) offer a wealth of clinical data, effectively augmenting a patient's records with heterogeneous external knowledge to predict the patient's clinical risk remains a significant challenge. Existing methods fail to capture disease severity, treatment responses, and nuanced clinical progression, due to data sparsity and the underutilization of unstructured clinical notes. To address these challenges, we propose TRACER (a trajectory-aware and clinically grounded prediction framework) that (1) constructs a medical knowledge graph enriched with severity information from medical literature, (2) retrieves clinically relevant, severity-weighted paths of a patient's progression from the knowledge graph, (3) extracts clinically relevant events from unstructured clinical notes, and (4) augments patient context with similar peer cases. Experiments on the MIMIC-III and MIMIC-IV datasets demonstrate large gains over state-of-the-art baselines, with up to 28.5% increase in Macro F1 score for the mortality prediction task, and 19.7% increase for the readmission prediction task. ---