# Research Papers — 2026-06 · bundle page 229 of 260 > Full-text markdown of papers #11401–11450 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/229 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/228.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/230.md) ### Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization Authors: Jiahua Dong, Wenqi Liang, Hongliu Li, Yang Cong, Duzhen Zhang, Hanbin Zhao, Henghui Ding, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan Published: 2026-06-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.04797v1 Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they exhibit significant catastrophic forgetting and concept neglect of previously learned concepts when incrementally learning a sequence of new ones. To resolve the above challenges, we develop a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization. Specifically, we design an attribute-decoupled LoRA (AD-LoRA) module and a relevance-guided AD-LoRA aggregation strategy to mitigate catastrophic forgetting. They can preserve concept-specific attributes of each task and leverage beneficial inter-task correlations to enhance the continual learning of new customization tasks. Additionally, to address the challenge of concept neglect, we propose a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions. This strategy enhances the overall consistency in multi-concept synthesis by guaranteeing semantic independence between user-defined regions and their smooth boundary transitions. Experiments show our CCDM exhibits significant improvements over baseline methods. --- ### A Pathology Foundation Model for Gastric Cancer with Real-World Validation Authors: Ling Liang, Jiabo Ma, Zhengyu Zhang, Fengtao Zhou, Yingxue Xu, Yihui Wang, Cheng Jin, Zhengrui Guo, On Ki Tang, Zhijian Cen, Zhen Wang, Qi Xie et al. Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04792v1 Gastric cancer remains a major cause of cancer mortality, yet its histological and molecular heterogeneity complicates diagnosis and risk stratification. General-purpose pathology foundation models (PFMs) often plateau on fine-grained endpoints central to gastric cancer care, and few have undergone rigorous prospective validation or clinical reader studies. We present GRACE, a Gastric-specific foundation model for Real-world Assessment and Clinical dEcision support. GRACE was developed from multicenter gastric pathology datasets totaling 48,364 primarily HE-stained whole-slide images from 37,493 patients. When evaluated on 28 clinically relevant tasks, GRACE consistently outperformed representative pancancer PFMs, achieving a macro-AUC of 0.9188, with strong performance for precancerous lesion diagnosis (macro-AUC 0.9322), tumor histopathological assessment (macro-AUC 0.9119), molecular profiling (macro-AUC 0.8682), and prognostic prediction. Beyond benchmarking, GRACE's translational value was substantiated through a rigorous evidence chain. Under safety-gated criteria requiring 100% NPV for rule-out and 100% PPV for rule-in, GRACE streamlined review for up to 69.6% of malignancy-diagnosis cases and triaged 46.8% of MMR-IHC follow-up requests. This translational feasibility was further strengthened by a randomized crossover reader study of pathologist-AI collaboration. With GRACE assistance, diagnostic accuracy improved from 82.0% to 89.9%, yielding nearly twofold higher adjusted odds of a correct diagnosis (OR 1.987) alongside concurrent gains in sensitivity and specificity. AI assistance also reduced diagnostic time by 14.9%, elevated diagnostic confidence by 9.0%, and markedly improved inter-rater agreement. When calibrated to maintain non-inferior performance to senior pathologists, the AI-assisted workflow could triage 60.7% of atrophy and 82.7% of intestinal metaplasia cases. --- ### Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives Authors: Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys, Daniel Barath Published: 2026-06-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.04788v1 Visual localization -- estimating a camera pose within a pre-existing map -- is a fundamental problem in computer vision. Floorplans are an attractive map representation: they are readily available for most buildings, compact, and inherently invariant to visual appearance changes. However, bridging the severe domain gap between camera observations and floorplan geometry remains challenging. Existing methods address this gap through data-driven learning, yet they require large-scale training data and environment-specific retraining, limiting their practical deployment. We propose a zero-shot floorplan localization method that generalizes to novel environments without any retraining. Our key insight is that dominant geometric primitives -- lines and circles -- are ubiquitous in human-made environments and provide appearance-invariant structural constraints. We extract these primitives from a bird's-eye-view (BEV) projection of monocular 3D reconstructions and match them to the floorplan via dedicated minimal solvers within a robust estimation framework. Experiments on both simulated and real-world datasets show that our approach outperforms state-of-the-art learning-based methods on unseen environments, while using a single fixed set of hyperparameters across all experiments. The source code will be made publicly available. --- ### AIP: A Graph Representation for Learning and Governing Agent Skills Authors: Zachary Blumenfeld, Jim Webber Published: 2026-06-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04781v2 Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session. This imposes two compounding costs: reduced reliability on implementation-heavy tasks, and difficulty in skill creation and improvement, since editing prose is a fragile process that both humans and agents struggle with, particularly for domain-specific procedural knowledge underrepresented in model training. The Agent Instruction Protocol (AIP) addresses both by modeling a skill as a directed execution graph: discrete steps as nodes backed by deterministic scripts or natural-language descriptions, connected by explicit typed input/output edges, and governed by a schema-validated YAML specification. A compiler meta-skill translates existing human-written skills into this form. The benefits are twofold. First, compiling human-written skills to AIP raised Claude Sonnet's mean task reward from 0.60 to 0.71 and pass rate from 53% to 67% across 27 real agent tasks from SkillsBench - a statistically significant gain (Wilcoxon signed-rank p = 0.011), winning 12 tasks to 2 with 13 ties - often in less wall-clock time. The graph delivers vetted, runnable units to the agent rather than asking it to re-derive code, commands, and tool calls from natural language. Second, on creation and improvement, because each skill is schema-validated, functionally testable, and addressable node-by-node, failures can be diagnosed and repaired precisely. Two authored-skill failures were traced to the script level. After adjusting the AIP spec and recompiling, both recovered with zero regressions (one task going from 0/5 to 5/5), turning skill improvement into a measurable tuning loop rather than a prose rewrite. That same graph structure supports corpus-level governance and skill introspection, and provides a natural action space for reinforcement learning over skills. --- ### AIP: A Graph Representation for Learning and Governing Agent Skills Authors: Zachary Blumenfeld, Jim Webber Published: 2026-06-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04781v1 Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session. This imposes two compounding costs: reduced reliability on implementation-heavy tasks, and difficulty in skill creation and improvement, since editing prose is a fragile process that both humans and agents struggle with, particularly for domain-specific procedural knowledge underrepresented in model training. The Agent Instruction Protocol (AIP) addresses both by modeling a skill as a directed execution graph: discrete steps as nodes backed by deterministic scripts or natural-language descriptions, connected by explicit typed input/output edges, and governed by a schema-validated YAML specification. A compiler meta-skill translates existing human-written skills into this form. The benefits are twofold. First, compiling human-written skills to AIP raised Claude Sonnet's mean task reward from 0.60 to 0.71 and pass rate from 53% to 67% across 27 real agent tasks from SkillsBench - a statistically significant gain (Wilcoxon signed-rank p = 0.011), winning 12 tasks to 2 with 13 ties - often in less wall-clock time. The graph delivers vetted, runnable units to the agent rather than asking it to re-derive code, commands, and tool calls from natural language. Second, on creation and improvement, because each skill is schema-validated, functionally testable, and addressable node-by-node, failures can be diagnosed and repaired precisely. Two authored-skill failures were traced to the script level. After adjusting the AIP spec and recompiling, both recovered with zero regressions (one task going from 0/5 to 5/5), turning skill improvement into a measurable tuning loop rather than a prose rewrite. That same graph structure supports corpus-level governance and skill introspection, and provides a natural action space for reinforcement learning over skills. --- ### PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents Authors: Yubo Hou, Jingwei Song, Hongbo Zhang, Zhisheng Chen, Bang Xiao, Tao Wan, Zengchang Qin Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04780v1 Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet give limited account of how accumulated interaction evidence is abstracted into person understanding. We view this process as schema formation, where situated evidence is abstracted into reusable patterns and stable person level claims. We introduce PersonaTree, a structured lifecycle memory framework that realizes this view as a three level persona tree with explicit support paths from evidence to claims. PersonaTree maintains the tree through conservative writing, confidence guided consolidation, and query conditioned path retrieval, returning only the evidence depth required by each query. Across six person understanding and persistent memory benchmarks with three answer backbones, PersonaTree ranks first in 12 of 18 compact scores and reaches the top two in 16 settings. Ablations show that hierarchy improves abstract person understanding on KnowMe, while support path retrieval improves RealPref alignment under a comparable context budget. --- ### Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions Authors: Andrea Ferrario Published: 2026-06-03 Categories: cs.AI, math.CO arXiv: https://arxiv.org/abs/2606.04779v2 Complementarity is the case in which a human--AI interaction (HAI) outperforms the best prediction benchmark available among its members. Although this idea is central in HAI research, formal work on complementarity remains limited. Existing frameworks do not model how agents' predictions compose into workflow-sensitive multi-agent protocols. We close this gap by introducing a tree-based formalization of complementarity in multi-agent HAI. An HAI protocol is represented by an ordered agent-role configuration together with a rooted planar binary tree whose leaves are decorated by prediction vectors. A local binary composition rule is evaluated recursively along the tree, yielding a tree-relative complementarity functional relative to a pointwise-min benchmark. We prove four results. First, selector-based HAIs, including reliance, cannot achieve complementarity regardless of task, loss, or prediction quality. Second, in regression under squared loss, complementarity is equivalent to Euclidean distance minimization from the ground-truth vector; for $N=2$, the optimal linear-pooling weight has a closed form and a residual-correction interpretation. Third, under linear local composition, every protocol tree defines a barycentric coordinate chart on the simplex of leaf weights; Tamari-cover reparameterizations of protocol trees preserve complementarity, and for all $N$, any two Tamari paths with the same initial and terminal trees preserve the protocol output and complementarity. Fourth, in binary classification, no internal local composition can achieve complementarity under endpoint-monotone losses, including standard Bregman and many finite Bernoulli $f$-divergence losses; an analogous obstruction holds for multiclass aggregation under cross-entropy. In summary, our framework shows that complementarity is attainable in multi-agent regression, but obstructed in classification. --- ### Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories Authors: Kyungmin Park, Taesup Kim Published: 2026-06-03 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.04778v1 Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent work attributes this to shallow safety, where alignment concentrates in the first few output tokens. We show that shallow safety is a special case of a broader inference-time vulnerability, in which short token injections at any generation step can substantially alter subsequent safety behavior. We also find that a model's alignment with refusal directions in its hidden states does not predict its robustness to such injection, revealing that internal state alone does not determine generation behavior under perturbation. To address this, we align models directly on generation trajectories constructed by simulating mid-sequence perturbation, and show that this improves robustness to mid-sequence injection and generalizes to attacks that exploit early-token generation. Our work argues that robust safety alignment requires training on the generation process itself, not only its outputs. --- ### UniFair: A unified fair clustering approach based on separation and compactness Authors: Antonia Karra, Vasiliki Papanikou, Georgios Vardakas, Evaggelia Pitoura, Aristidis Likas Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04777v2 Clustering is increasingly used to support high-impact decisions, yet standard objectives such as k-means can produce clusterings that treat demographic groups unequally. Existing fair clustering methods typically optimize a single notion of fairness and often overlook how clustering costs interact with the geometry of the induced decision boundaries. We propose UniFair, a unified framework that jointly optimizes separation fairness and social fairness. Separation fairness encourages protected groups to lie farther from the induced decision boundaries, while social fairness reduces disparities in within-cluster distortion by penalizing group-wise clustering costs. We develop gradient-based optimization procedures for separation-fair and unified k-means objectives, and extend them to deep clustering by enforcing the same criteria in the latent space of an autoencoder. Experiments on tabular and image datasets show that UniFair reduces both boundary-related and cost-based group disparities with only a modest increase in clustering loss. --- ### Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control Authors: Jihoon Hong, Alice Chan, Qiyue Dai, Julian Skifstad, Glen Chou Published: 2026-06-03 Categories: cs.LG, cs.AI, cs.CV, eess.SY, math.OC arXiv: https://arxiv.org/abs/2606.04775v1 Text-to-video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs without sacrificing visual quality. Activation steering offers an attractive mechanistic alternative to finetuning and prompt filtering, but existing T2V steering methods remain limited, typically applying coarse, non-anticipative interventions that can lead to oversteering and content degradation. To close this gap, we propose Latent Activation Linear-Quadratic Regulator (LA-LQR), a reduced-order optimal control framework for minimally invasive T2V steering. LA-LQR formulates T2V inference as a dynamical system and computes closed-loop feedback interventions that steer activations toward desired feature setpoints while penalizing unnecessary perturbations. To make optimal control feasible for high-dimensional video activations, we project activations onto a low-dimensional, task-relevant subspace derived from contrastive prompt pairs, estimate local linear dynamics in this latent space, and solve a latent LQR problem to obtain timestep- and layer-specific steering signals. We provide theoretical bounds relating latent setpoint tracking to raw activation-space feature control, and empirically validate the fidelity of the reduced latent dynamics. On concept steering and video safety benchmarks, LA-LQR reduces unsafe generations relative to baselines, while preserving prompt fidelity and visual quality. --- ### NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models Authors: Yong Cao, Chuqiao Li, Xianghui Xie, Gerard Pons-Moll, Andreas Geiger Published: 2026-06-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.04773v1 Reliable evaluation of human motion understanding is fundamental to advancing embodied AI, robotics, and animation. However, existing benchmarks suffer from coarse semantic granularity, undifferentiated difficulty, limited annotation quality, and pervasive answer ambiguity, leaving them unable to diagnose where current models fail. To bridge this gap, we introduce NextMotionQA, a comprehensive benchmark that leverages vision-language models (VLMs) for semi-automated, expert-verified dataset. NextMotionQA features three complementary tasks: multiple-choice question answering, video captioning, and fine-grained error correction. Each task is systematically structured across three core semantic axes and stratified into three task complexity levels. Our extensive evaluation of twelve representative VLMs uncovers critical capability gaps and weakness that remain invisible under conventional, single-task evaluations. In a complementary direction, recent work has begun using VLMs as judges for text-to-motion evaluation; we ask whether they show the same degradation under harder tasks. We find that VLMs align strongly with expert ratings on coarse criteria (Cohen's κ=0.70) but break down on fine-grained, part-level judgment (κ=0.10), validating the paradigm in its strong regime while clarifying its limits. --- ### Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction Authors: Hoang-Son Vo, Van-Hung Bui, Minh-Huy Mai-Duc, Tien-Dung Mai, Soo-Hyung Kim Published: 2026-06-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.04772v1 Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question. In this study, we propose CHASMBrain, a novel hierarchical two-stage framework for image-to-fMRI encoding. Our architecture leverages a dual-stream Mamba design to explicitly separate and process global semantic tokens and local spatial patches, motivated by the functional organization of the visual cortex. A coarse-to-fine strategy is employed: Stage 1 predicts denoised ROI-level activations, while Stage 2 refines these coarse responses into full voxel-level predictions using a Mamba-VAE. Experiments on the Natural Scenes Dataset (NSD) demonstrate that our method achieves a Pearson correlation of 0.429 and an MSE of 0.261, outperforming all evaluated baselines including ridge regression and DINOv2 linear probes. Beyond predictive performance, causal branch-ablation experiments reveal an asymmetric specialization: the patch stream is specifically locked to early visual cortex (retinotopic regions), while the CLS stream contributes broader semantic context to higher-order areas -- a correspondence that holds causally, not merely correlationally. Cross-subject transfer experiments further show that the learned backbone generalizes across individuals with minimal per-subject adaptation, suggesting the model captures a shared, subject-agnostic visual representation. --- ### Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications Authors: Yutao Shi, Xiaohan Zhang, Xiangjing Zhang, Xihua Shen, Hui Ouyang, Huming Qiu, Mi Zhang, Min Yang Published: 2026-06-03 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.04769v1 The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool descriptions faithfully reflect their underlying implementations, while this assumption is not mandatorily verified in practice. As a result, MCP deployments may suffer from a problem named Description-Code Inconsistency (DCI), where a tool's description of its capabilities and security boundaries is not consistent with what the code actually does. In this paper, we present a comprehensive study of DCI in real-world MCP servers. We formally define the problem and propose a comprehensive taxonomy spanning functionality inconsistencies and undeclared side effects. Guided by this taxonomy, we develop DCIChecker, an automated framework that combines structure-aware static analysis with the Direct-Reverse-Arbitration prompting method to cross-validate tool descriptions against actual code implementations. We apply this framework to a large-scale dataset comprising 19,200 description-code pairs extracted from 2,214 real-world MCP servers. Our measurement reveals that DCI is widespread, with 9.93% of these pairs exhibiting inconsistencies. We further demonstrate that DCI creates a critical defense blind spot, facilitating varied risks from operational failures to stealthy malicious behaviors. Finally, we propose mitigation strategies to enforce semantic consistency and enhance the reliability of the emerging agentic ecosystem. --- ### Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms Authors: Chong Zhang, Xiang Li, Jia Wang, Qiufeng Wang, Xiaobo Jin Published: 2026-06-03 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2606.04767v1 The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability. We propose a principled, attack-agnostic robustness metric based on the spectral norm of the Fisher Information Matrix (FIM), which quantifies the worst-case sensitivity of the model's output distribution to input perturbations. Theoretically, we establish that the FIM equals the variance of the input Jacobian and derive closed-form spectral bounds for common architectures, including VGG, ResNet, DenseNet, and Transformer, providing the first theoretical robustness ranking. To enable scalable evaluation, we develop efficient algorithms, including power iteration and Hutchinson-based estimation, that support both white-box and black-box settings. Extensive experiments across multiple datasets, including CIFAR, ImageNet, and medical images, and across multiple architectures show a strong correlation between our metric and adversarial vulnerability. Our framework serves as an interpretable diagnostic tool that complements attack-based evaluations, offering insights into architectural sensitivity and guiding the design of more robust models. Code is available at: https://github.com/franz-chang/SRP/. --- ### Do Foundation Models See Biology? Evaluating Attention Coherence with Spatial Transcriptomics in Glioblastoma Authors: Dilakshan Srikanthan, Amoon Jamzad, Paul Wilson, Nooshin Maghsoodi, Robert Policelli, Gabor Fichtinger, John F. Rudan, Parvin Mousavi Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04764v2 Whether attention maps from pathology foundation models capture genuine biology remains unknown, yet this question is critical for clinical trust and regulatory approval. We propose a spatial transcriptomics-based framework for orthogonal, hypothesis-free evaluation of attention and apply it to five pathology foundation models (CONCH v1.5, UNI v2, Virchow2, GigaPath, H-Optimus-1) and a ResNet50 baseline. Using attention-based multiple instance learning, we train single-task and multi-task models to predict five molecular alterations in glioblastoma on the CPTAC cohort, validate on an independent TCGA cohort, and evaluate biological coherence of attention maps against 87 transcriptional signatures using co-registered Visium spatial transcriptomics data from 18 samples. Internally, no single encoder dominates across all tasks, and external validation inverts internal performance rankings. Attention maps show a five-fold enrichment gradient from pathways (Cohen's d=0.329) to individual genes (d=0.055), indicating that attention captures emergent multi-gene transcriptional programs rather than individual molecular events. Spatially smooth attention maps do not imply biological coherence, and different encoders attend to distinct biological compartments. Our framework provides objective, quantitative assessment of what foundation models learn from histopathology, moving the field beyond qualitative saliency map review. --- ### Near-Optimal Decentralized Stochastic Convex Optimization over Networks Authors: Nitai Kluger, Amit Attia, Tomer Koren Published: 2026-06-03 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2606.04757v1 We study decentralized stochastic smooth convex optimization, where $M$ workers minimize an average objective using local stochastic gradients and neighbor-only communication over a fixed gossip network. A central question in this setting is to determine the largest number of workers that can be used under a total budget of $N$ gradient samples while still preserving the centralized $O(1/\sqrt N)$ statistical rate. We introduce an accelerated decentralized method that preserves this rate for up to $\smash{M\lesssim \sqrtρ\,N^{3/4}}$ workers, where $ρ$ is the spectral gap of the gossip network, improving the best prior maximal scaling of $\smash{M\lesssim ρ\sqrt N}$. The method is based on a one-step-delayed stochastic acceleration scheme that enables workers to interleave minibatching with accelerated gossip while controlling residual disagreement, and its guarantee depends only logarithmically on the optimum-local heterogeneity. We also establish a matching lower bound for linear-span decentralized first-order methods, showing that the method is optimal up to logarithmic factors. --- ### Archi: Agentic Operations at the CMS Experiment Authors: Pietro Lugato, Luca Lavezzo, Jason Mohoney, Hasan Ozturk, Muhammad Hassan Ahmed, Juan Pablo Salas, Viphava Ohm, Krittin Phornsiricharoenphant, Gabriele Benelli, Mariarosaria D'Alfonso, Manasvita Joshi, Warren Nam et al. Published: 2026-06-03 Categories: hep-ex, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.04755v1 We present Archi, an open-source, end-to-end framework for scientific collaborations that combines the systematic ingestion and organization of heterogeneous data sources with the deployment of configurable, private, and extensible agents that retrieve and reason over them. An instance of Archi has been deployed for the Computing Operations team of the CMS experiment at CERN's LHC since February 2026 as a support agent for technical operators, offering retrieval and analysis capabilities by combining documentation, historical data, and live monitoring systems. We evaluate the system on operator feedback and a question set collected from production usage, graded by human and automated panels. The system proves effective at operational tasks, resolving real-world queries posed by CMS operators. We also observe that locally-hosted, open-weight models perform competitively, enabling fully private management of sensitive data. --- ### Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability Authors: Vincent Bürgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04754v2 Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformations that leave the realized function unchanged. Despite growing attention to parameter symmetries, the exact interplay between parameters, data, and representations remains underexplored. To investigate this, we develop a theoretical framework of effective function classes, i.e., the set of functions a neuron can realize on its input support, and the norm cost of realizing them. We then formalize effective symmetry breaking via neuron identifiability across independent training runs. Our analysis shows that neural networks can admit large families of approximately equivalent solutions even in structurally asymmetric models. We further show that neuron identifiability enables representation merging without prior alignment, and characterize when such merging admits a linear low-loss path. These findings highlight the role of effective function classes in affecting the loss landscape. --- ### Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability Authors: Vincent Bürgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04754v1 Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformations that leave the realized function unchanged. Despite growing attention to parameter symmetries, the exact interplay between parameters, data, and representations remains underexplored. To investigate this, we develop a theoretical framework of effective function classes, i.e., the set of functions a neuron can realize on its input support, and the norm cost of realizing them. We then formalize effective symmetry breaking via neuron identifiability across independent training runs. Our analysis shows that neural networks can admit large families of approximately equivalent solutions even in structurally asymmetric models. We further show that neuron identifiability enables representation merging without prior alignment, and characterize when such merging admits a linear low-loss path. These findings highlight the role of effective function classes in affecting the loss landscape. --- ### An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers Authors: Ossi Lehtinen Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04752v3 Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_{\text{model}}$-dimensional vector per time step. We audit eight input encoders -- a shared-scalar baseline, per-channel linear projections, an orthogonality regulariser, a nonlinear MLP, block-partitioned concatenation, channel-independent and channel-as-token architectures, and a projected positional encoding -- on a synthetic benchmark where channel identity is informative and on ETTh1, scored by next-step negative log-likelihood. The headline is practical near-equivalence within a wide "top tier": the standard per-channel linear projection matches every alternative up to small, statistically real but practically modest differences. A direct geometric probe attributes this to a spontaneous orthogonalisation of the per-channel projections: with no explicit regulariser they tighten well beyond the near-orthogonality of random initialisation, letting the standard linear recover channel identity from the summed embedding. Two encoders lose decisively: the shared-scalar baseline collapses for information-theoretic reasons we make explicit, and the channel-independent PatchTST-spirit baseline overfits universally on the synthetic benchmark and underperforms on both. Paired tests resolve two small gaps: projecting the sinusoidal positional encoding through a learned linear layer edges the rest at small $C$ by extending this orthogonality to the positional subspace; a nonlinear MLP stem edges them at the largest $C$, with the gap shrinking under more training data. The practical recommendation: use the standard per-channel linear projection by default; reach for something more elaborate only when the task calls for it. --- ### FALSIFYBENCH: Evaluating Inductive Reasoning in LLMs with Rule Discovery Games Authors: Leonardo Bertolazzi, Katya Tentori, Raffaella Bernardi Published: 2026-06-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.04751v1 Large language models (LLMs) are increasingly deployed as autonomous agents in scientific tasks. Yet whether these systems can effectively engage in forms of inductive reasoning relevant to scientific discovery remains an open question. In this work, we introduce FALSIFYBENCH, an evaluation framework for hypothesis-driven reasoning inspired by the classic Wason 2-4-6 task, in which agents must discover hidden semantic properties by iteratively proposing examples and receiving feedback. This task captures key elements of scientific reasoning: hypothesis generation, evidence gathering, and belief revision in response to both confirming and disconfirming evidence. Our evaluation of 12 LLMs across model families and scales shows that reasoning models are generally stronger scientific reasoners than instruction-tuned models, although no model comes close to optimal performance. The primary driver of success is the capacity for negative testing: models that actively seek to falsify their hypotheses consistently outperform those that primarily seek confirmation. Moreover, a fine-grained turn-level analysis, neglected in previous work, reveals that failure is tied to identifiable patterns in how models navigate the hypothesis space. --- ### Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment Authors: Ajay Vishwanath, Christian Omlin Published: 2026-06-03 Categories: cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2606.04750v1 Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being fully dependent on the reward function design. Thus far, this technique has been demonstrated to be effective in grid worlds and toy-problem environments with minimal state and action spaces. To expand this research to more sophisticated environments, we introduce a two-player multi-agent environment based on the role-playing board game known as Fog of Love. In this environment, two agents compete to fulfill their individual virtues, while also cooperating to satisfy their relationship. Given the multi-agent nature, this is a complex problem where multi-agent deep deterministic policy gradient agents neither compete nor cooperate successfully. We present evidence that localized affinities enhance agent performance in achieving both competitive and cooperative objectives, resulting from superior overall scores in both domains. This not only results in virtuous choices but also clarifies an agent's teleology and makes its behavior human-level interpretable. --- ### COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection Authors: Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan, Julian F. P. Kooij Published: 2026-06-03 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.04749v1 Safe robot control requires maximizing return while satisfying safety constraints. In off-policy safe reinforcement learning, reward and safety Q-values are commonly learned by separate critic ensembles, with uncertainty handled independently for each objective. This objective-wise treatment neglects inter-objective correlation and can lead to overly conservative value estimates, thereby reducing sample efficiency. To address this issue, we propose Cholesky-Ordered Projection Q-learning (COP-Q), a safety-first method that incorporates inter-objective covariance into vector-valued Q-value estimation. COP-Q constructs a generalized confidence bound in the joint Q-value space and uses Cholesky factorization to encode objective priority in a sequential form. This preserves conservatism on safety while adaptively reducing excessive conservatism on the reward objective. The resulting estimate is used in both temporal-difference target computation and actor optimization. COP-Q incurs minimal computational overhead and is readily compatible with most existing deep Q-learning frameworks. Experiments on robot locomotion in Brax and safe navigation in Safety-Gymnasium, covering both hard- and soft-safety settings, demonstrate that COP-Q achieves strong safety performance together with competitive or improved sample efficiency relative to representative baselines. --- ### TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration Authors: Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang Published: 2026-06-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04743v2 Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution. --- ### TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration Authors: Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang Published: 2026-06-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.04743v1 Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution. --- ### Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models Authors: Sabrina Kaniewski, Fabian Schmidt, Tobias Heer Published: 2026-06-03 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.04739v1 Large language models (LLMs) have shown strong potential for automated software vulnerability detection, particularly in retrieval-augmented generation (RAG) settings. However, for approaches relying on proprietary models and APIs, reproducibility and replicability remain largely unexplored, raising the question of whether reported results generalize or depend primarily on specific model choices. In this work, we present a reproducibility study of Vul-RAG, a RAG-based framework for source code vulnerability detection that enhances LLMs with high-level vulnerability knowledge. We first replicate the results in a fully local and open-weights setting using the reported open-weight baseline models. We then extend the evaluation to a diverse set of recent open-weight LLMs, including code-specialized, general-purpose, and reasoning models of varying parameter sizes. The results confirm that the findings of Vul-RAG are reproducible under local deployment, but with minor deviations. Across all evaluated models, we observe a performance plateau at approximately 0.30 pairwise accuracy (code pairs for which both the vulnerable and the patched function are correctly classified). Notably, this plateau persists even for more recent and advanced models, indicating that improvements in model capacity alone do not substantially enhance performance. Finally, we discuss practical implications and trade-offs between detection effectiveness, model capabilities, and model scale. Implementation and evaluation artifacts are publicly available at https://github.com/hs-esslingen-it-security/revisiting-Vul-RAG. --- ### Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment Authors: Cong Wang, Hanxin Zhu, Jiayi Luo, Yonglin Tian, Xiaoqian Cheng, Peiyan Tu, Xin Jin, Long Chen, Zhibo Chen Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04737v1 Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincing. Nevertheless, the dynamics induced by pixel-level fitting do not naturally accommodate the regularities that govern real-world motion and interaction, resulting in persistent shortcomings in physical plausibility. To address this limitation, we propose \textbf{PILA} (Physics-Informed Latent Alignment), a framework that injects physics-structured latent guidance into the frozen flow-matching dynamics of pretrained video models. Specifically, PILA first employs anchored field estimation to map frozen-generator latents into an operational physical attribute bank organized by field-proxy slots, using observable motion as a kinematic anchor for constructing less directly observed proxies. To handle the heterogeneity of real-world dynamics, PILA adopts a mixture-of-experts design over physical categories. Label-prior masked expert routing selects category-specific operator experts, whose refinements are regularized by operational residuals abstracted from physical relations. Finally, the refined proxies are fused into the physical attribute bank and decoded into a correction to the flow-matching vector field, injecting physics-aware guidance while preserving the visual prior of the pretrained backbone. With staged adapter training on Wan 2.1-1.3B and direct transfer of the learned adapter to Wan 2.2-14B, PILA achieves state-of-the-art results on VBench-2.0, VideoPhy-2, and PhyGenBench in both visual quality and benchmark-measured physical plausibility. --- ### Curvature-aware dynamic precision approach for physics-informed neural networks Authors: Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn, Taniya Kapoor Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04736v1 Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, recent studies show that PINN optimisation is sensitive to numerical precision. Existing implementations commonly use either single precision (FP32), which is computationally efficient but prone to failure modes, or double precision (FP64), which is robust but substantially expensive. This creates a trade-off between computational efficiency and numerical accuracy. To reduce the computational cost of double-precision training while retaining prediction accuracy, we propose a curvature-aware precision controller that adapts numerical precision during training rather than treating it as a fixed implementation choice. The proposed method reuses curvature information derived from the limited-memory BFGS (L-BFGS) optimiser to construct a precision controller, retaining FP32 when lower precision is sufficient and promoting computation to FP64 when the training dynamics indicate numerical sensitivity or precision-limited stagnation. We evaluate the proposed approach on four canonical PINN failure-mode benchmarks and an irradiance-driven ordinary differential equation example. We further test the proposed approach across different neural network architectures. The method consistently matches or even slightly exceeds full FP64 solution accuracy while reducing training time relative to full double-precision training on all benchmark equations. The obtained results indicate that precision sensitivity in PINN optimisation is phase-dependent, and that selectively applying higher precision only during numerically critical stages can lower computational cost without sacrificing predictive accuracy. --- ### Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning Authors: Viktor Veselý, Aleksandar Todorov, Erwan Escudie, Matthia Sabatelli Published: 2026-06-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.04735v1 Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood. We identify a systematic failure mode in deep reinforcement learning (RL) termed Trace-Mediated Peak Bias (TMPB). At intermediate eligibility trace depths, agents irrationally prefer trajectories with high-magnitude reward ``peaks'' over alternatives with higher cumulative returns. This provides a mechanistic account of the Peak-End Rule: a human memory bias where experiences are judged by their most intense moments rather than integrated utility. We show that TMPB emerges because traces amplify distal Temporal Difference errors into ``gradient shocks'' that fixed-step-size Stochastic Gradient Descent cannot normalize, leading to global overestimation. Conversely, adaptive optimizers mitigate this pathology via second-moment normalization. Our results suggest that human-like saliency distortions may emerge naturally from the mathematical constraints of credit assignment in distributed systems, and that adaptive optimization is a theoretical necessity for rational value estimation. --- ### Contrastive Learning and Correlation Clustering for Sequences of Network Telescope Data Authors: Jannik Presberger, Alexander Männel, Maynard Koch, Thomas C. Schmidt, Matthias Wählisch, Bjoern Andres Published: 2026-06-03 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2606.04733v1 Understanding activities of Internet scanners is challenging; it often requires identifying relationships between sources, a task for which semantic annotations are scarce. This work investigates whether semantically meaningful pairwise relationships between sequences of network flow records can be estimated by contrastive learning, without pretraining and without annotations. To this end, we propose a transformer model that embeds minimally preprocessed sequences of network flow records and train it using contrastive learning. With the similarities obtained from this model, we state a correlation clustering problem and solve it locally. Experimentally, we show: Learned similarities are higher on average for sequences originating from the same source than for sequences originating from different sources, and this property generalizes to unseen sequences of unseen sources. Moreover, correlation clustering yields clusters consistent with scanner labels. The complete source code of the algorithms and for reproducing the experiments is publicly available. --- ### Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026 Authors: Enes Yavuz Ugan, Maike Züfle, Yuka Ko, Supriti Sinhamahapatra, Fabian Retkowski, Seymanur Akti, Jan Niehues, Alexander Waibel Published: 2026-06-03 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2606.04730v1 With the advent of Large Language Models, single-task and token-based multi-task models have evolved into instruction-based systems that infer task and target language implicitly from natural language prompts. This trend is reflected in IWSLT's Instruction Following Track, which this year introduced new tasks including an unknown surprise task, posing a genuine challenge against overfitting to known tasks. We present KIT's submission to the Long and Short Instruction Following tracks in the unconstrained setting. Our approach combines a general data augmentation pipeline that converts short-form corpora into long-form training data through segment concatenation, LLM-based label generation, and cross-lingual translation, yielding over 1M instances across six tasks and four languages. We further show that likelihood-based re-ranking, while highly effective for ASR, systematically degrades semantic tasks by spuriously selecting candidates generated from segmented audio processing rather than holistic long-form inference, a failure mode resolved by combining likelihood with Minimum Bayes Risk decoding. --- ### StrokeTimer: Robust Representation Learning for Ischemic Stroke Onset-Time Estimation from Non-contrast CT Authors: Weiru Wang, Susanne G. H. Olthuis, Elizaveta Lavrova, Robert J. van Oostenbrugge, Charles B. L. M. Majoie, Wim H. van Zwam, Ruisheng Su Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04722v1 Ischemic stroke is a major global disease. Treatment decisions are highly time-sensitive, as eligibility for reperfusion therapies relies on the interval between stroke onset and intervention. However, the true onset time is often uncertain in clinical practice, necessitating imaging-based assessment of tissue age as a surrogate marker. Early ischemic changes on routinely acquired non-contrast CT (NCCT) are often subtle, and real-world clinical datasets exhibit pronounced onset-time class imbalance and center-scanner-related heterogeneity. In this work, we propose StrokeTimer, a fully automated framework for onset-time estimation in acute ischemic stroke. StrokeTimer integrates self-supervised disentanglement learning with energy-guided contrastive learning to capture subtle ischemic patterns while addressing long-tailed data distributions under acquisition variability. Onset time is categorized into three clinically relevant windows: <4.5 h, 4.5-6 h, and >6 h. Experimental results on a large multi-center NCCT dataset from two national cohorts, MR CLEAN Registry and MR CLEAN LATE, show that StrokeTimer achieves a macro AUC of 0.69 and a macro F1-score of 0.57, improving the strongest baseline by nearly 50% (p < 0.005). In this realistic, challenging setting, representative baseline approaches exhibit near-chance macro performance. Model explanations further highlight subtle gray-white matter blurring and hypodense regions consistent with established radiological biomarkers. These findings demonstrate the potential of StrokeTimer to support treatment decision-making in acute ischemic stroke. Code is available at https://github.com/BrainVas/StrokeTimer. --- ### Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM Authors: SooHwan Eom, Jay Shim, Gwanhyeong Koo, Haebin Na, Mark A. Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04719v1 The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively. This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling by compressing visual tokens based on input through the cross-attention mechanism. This innovative projector also removes the need for manually designing the 2D scan order of original image features when converting them into an input sequence for Mamba LLM. Experimental results across various vision-language understanding benchmarks show that the proposed cross-modal projector enhances Mamba-based multimodal LLMs, boosting both performance and throughput. --- ### CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation Authors: Kailun Huang, Zikang Xie, Yanzhe Xie, Panpan Liao, Fanghai Zhang, Yanheng Mai, Wenhao Xu, Yunheng Wang, Renjing Xu, Haohui Huang, Chenguang Yang Published: 2026-06-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.04718v3 Humans primarily rely on walking and running to traverse complex terrains. Similarly, humanoid robots should be able to smoothly transition between walking and running while maintaining natural and stable locomotion. However, unifying gait transition and multi-terrain adaptation within a single policy remains challenging due to gradient interference between tasks and the distribution shift caused by terrain variations. Although Mixture-of-Experts (MoE) architectures can mitigate multi-skill interference, direct joint training often fails to achieve clear expert specialization. To address these challenges, we propose CoRe-MoE, a two-stage reinforcement learning framework that decouples gait generation from terrain adaptation. In the first stage, a stable locomotion policy is learned to produce natural walking and running behaviors with smooth transitions. In the second stage, a terrain-aware MoE branch is introduced, and the gating network is trained with a contrastive objective to learn structured terrain representations and promote expert specialization. The final action is obtained through weighted fusion of the base gait policy and the terrain-aware branch, enabling the policy to preserve stable locomotion while adapting to complex terrains. Extensive simulation results demonstrate that the proposed method outperforms baseline approaches in terms of success rate, locomotion stability, and multi-terrain adaptability. Furthermore, zero-shot deployment on a Unitree G1 humanoid robot validates the effectiveness of our framework, achieving robust walking and running across stairs, slopes, steps, obstacles, and unstructured outdoor terrains while maintaining accurate foothold control and dynamic stability. --- ### Data Efficient Complex Feature Fusion Network For Hyperspectral Image Classification Authors: Maitreya Shelare, Atharva Satam, Poonam Sonar, Sneha Burnase Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04710v1 This work presents a data-efficient variant of the Attention-Based Dual-Branch Complex Feature Fusion Network (CFFN) for hyperspectral image classification. The proposed model, termed DE-CFFN, retains the original two-stream structure: the Real-Valued Neural Network (RVNN) processes standard hyperspectral patches, while the Complex-Valued Neural Network (CVNN) handles their Fourier-transformed counterparts. The main contribution of this work lies in the feature extraction process and architectural enhancement. Factor Analysis is used for dimensionality reduction, offering improved latent feature representation over Principal Component Analysis. Additionally, both the RVNN and CVNN streams are structurally modified by successively halving the number of filters in the 3D convolutional layers to reduce complexity. The outputs of both branches are concatenated and passed through a Squeeze and Excitation (SE) block to enhance joint feature representation. Evaluated on the Pavia University and Salinas datasets, DE-CFFN achieves classification performance comparable to CFFN, while significantly reducing model size, memory consumption, and inference latency, making it suitable for real-time hyperspectral imaging applications. --- ### VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training Authors: Siyuan Yang, Linzheng Guo, Ouyang Lu, Zhaxizhuoma, Daoran Zhang, Xinmiao Wang, Ting Xiao, Fangzheng Yan, Zhijun Chen, Yan Ding, Chao Yu, Chenjia Bai et al. Published: 2026-06-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.04708v2 Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions. To address the challenges, we present VISTA, a framework that bridges this dual gap through three synergistic components. (i)~UMI-VQA, the first large-scale VQA dataset tailored to wrist-mounted fisheye observations, aligns VLM representations to the distorted visual regime via auxiliary vision-language supervision. (ii)~A systematic physical-validation pipeline performs a data-completeness pre-check and scores each valid trajectory for trajectory continuity, self-collision risk, and execution fidelity before it enters training. (iii)~A two-stage co-training recipe jointly learns vision-language grounding on UMI-VQA and action prediction on validated trajectories. Our experiments empirically show that incorporating UMI-VQA consistently improves downstream policy performance, and that physical-validation scores are strongly predictive of deployment success. On diverse simulation and real-world manipulation tasks, VISTA significantly outperforms strong baselines including $π_{0.5}$, LingBot-VLA, and Wall-X. We release the physical-validation pipeline, UMI-VQA, validated trajectory data, and the pre-trained model for the community. --- ### ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection Authors: Xiaojing Chen, Xinyu Lu, Changtao Miao, Yunfeng Diao Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04706v1 AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models. In this paper, we explore reconstruction error as a discriminative forensic cue for AI-generated video detection. By reconstructing input videos with a pretrained WF-VAE, we observe that real and generated videos exhibit distinguishable frame-wise reconstruction error patterns, suggesting that reconstruction errors can reveal their distributional discrepancies. However, extending reconstruction-based image detection to videos is non-trivial, since video reconstruction errors are temporally organized across frames and require semantic context for effective interpretation. To address these challenges, we propose ReConFuse, a reconstruction-guided semantic fusion framework for video-level AI-generated video detection. ReConFuse extracts reconstruction error cues from WF-VAE reconstructed videos, aligns them with multi-frame semantic features, and uses a Mamba-based module to model temporal evolution for video-level classification. Experiments across multiple generators and evaluation settings demonstrate the effectiveness and strong generalization ability of ReConFuse. --- ### Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation Authors: Amirhossein Movahedisefat, Amirreza Fateh, Mohammad Reza Mohammadi Published: 2026-06-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.04705v2 Semantic segmentation in medical imaging is a critical yet challenging task due to data scarcity and high variability across modalities. While foundation models like the Segment Anything Model (SAM) show promise, they often struggle with medical images without specific adaptation. Moreover, point prompts, despite being the most natural form of user interaction, provide insufficient spatial context for reliable segmentation, particularly when target structures are irregular or poorly contrasted. In this paper, we propose an enhanced segmentation framework that integrates a lightweight Box Predictor module into the MedSAM architecture. The Box Predictor estimates an approximate bounding box from a single user click using localized image embedding features, providing spatial guidance that reduces the ambiguity of point prompts, while introducing only 1.6M additional parameters and negligible inference overhead. We introduce a two-stage training pipeline where the Box Predictor is trained independently before being integrated into MedSAM. To validate the generalization capability of our method, we conduct extensive evaluations on four diverse datasets (FLARE22, BRISC, BUSI, LungSegDB) spanning distinct imaging modalities, including CT, MRI, and Ultrasound. Our method improves segmentation accuracy and robustness across varied anatomical structures and imaging domains, achieving Dice scores of 0.89 (BUSI), 0.93 (FLARE22), 0.88 (BRISC), and 0.98 (LungSegDB). Code is available at https://github.com/Amirhosseinmovahedi/MedSAM-BoxPredictor --- ### Rethinking Continual Experience Internalization for Self-Evolving LLM Agents Authors: Jingwen Chen, Wenkai Yang, Shengda Fan, Wenbo Nie, Chenxing Sun, Shaodong Zheng, Yangen Hu, Lu Pan, Ke Zeng, Yankai Lin Published: 2026-06-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.04703v1 Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement. We systematically examine this failure through three vital dimensions of experience internalization: (1) Experience Granularity: We find that principle-level experience is more durable than instance-level experience, as it effectively abstracts transferable strategies away from trajectory-specific details. (2) Experience Injection Pattern: Our analysis reveals that step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states, a property that is critical for long-horizon tool use. (3) Internalization Regime: We demonstrate that off-policy context-distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-distillation, which is inherently limited by local corrections on student-induced flawed states. Together, these insights yield a simple yet robust recipe for stable and sustainable experience internalization, providing concrete guidance for engineering self-evolving and continually learning LLMs. --- ### Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms Authors: Jiashu Yao, Heyan Huang, Daiqing Wu, Wangke Chen, Huaxi Ai, Haoyu Wen, Zeming Liu, Yuhang Guo Published: 2026-06-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.04701v1 GUI agents today assume a static screen, where the world is frozen between two actions. However, real interfaces such as short-video applications violate this assumption, as their content keeps playing, and a competent user must decide what to watch and for how long. We formalize this task as Living-Screen-Native GUI agents and introduce LivingScreen, the first benchmark instantiating it on short-video platforms, with a faithful browser-based environment, a three-tier task suite, and metrics that jointly score accuracy and information efficiency. Evaluating extensive frontier models, we find that none reaches the human cost-accuracy performance, and that their dominant failure mode is over- and under-observation, pointing to observation control as a missing capability axis for future GUI agents. All data and code will be available at https://github.com/BITHLP/LivingScreen. --- ### A New Angle on Bones: Robust Pose Estimation in X-Ray and Ultrasound Authors: Ron Keuth, Christoph Großbröhmer, Franziska Halm, Miriam Johann, Anne-Nele Schröder, Ludger Tüshaus, Mattias P. Heinrich, Lasse Hansen Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04700v3 Measuring the angle between bone structures is a routine task in medical image analysis and provides a key quantitative parameter for diagnosis and treatment planning. Automated methods can reduce time and cost while improving reproducibility. In this work, we address automatic bone pose estimation using a learning-based point candidate proposal followed by a line model to extract axis parameters. Since conventional line models such as least squares are sensitive to outliers, we incorporate false-positive reduction strategies and robust fitting techniques, such as RANSAC and Hough transforms, to improve robustness. We evaluate our method on three clinically relevant paediatric angle estimation tasks: fracture fragment assessment in radiographs and ultrasound and developmental dysplasia of the hip evaluation in ultrasound using the Graf method. Our approach achieves mean errors of $4.1^\circ$, $5.4^\circ$, and $5.51^\circ$, respectively, not only remaining within the expected clinical observer variability, but also significantly outperforming landmark-based methods. Our code and annotations for fracture angle assessment in radiographs are publicly available on GitHub. --- ### Graph-Guided Universum Learning in Generalized Eigenvalue Proximal SVMs for Alzheimer's Disease Classification Authors: Yogesh Kumar, Vrushank Ahire, Mudasir Ganaie Published: 2026-06-03 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.04699v1 Early and accurate detection of Alzheimer's disease (AD) is important for timely intervention and disease management. Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) and its Universum-based variants have shown promising results for AD classification. However, existing methods treat Universum samples as independent points and do not consider the geometric relationships among them. This paper proposes two graph-guided Universum learning models, namely UG-GEPSVM and IUG-GEPSVM, for AD versus cognitively normal (CN) classification using structural MRI data. In the proposed framework, mild cognitive impairment (MCI) subjects are used as Universum data to provide intermediate information between AD and CN classes. A graph is constructed over the Universum samples using Gaussian similarity, Minimum Spanning Tree connectivity, and multi-hop propagation. From this graph, a Laplacian matrix is derived that captures the geometric structure of the MCI samples. This Laplacian-based regularization is incorporated into the learning process in place of the conventional independent Universum penalty term. UG-GEPSVM integrates this regularization into the generalized eigenvalue formulation, while IUG-GEPSVM extends the numerically stable improved GEPSVM framework using a standard eigenvalue formulation. Experiments on ADNI MRI dataset variants using ICA- and PCA-based features at five different noise levels show that both proposed models consistently outperform existing GEPSVM and Universum-based methods. UG-GEPSVM achieves the highest average AUC of 88.07% and maintains stable performance under increasing noise levels. Statistical tests further confirm the significance of the observed improvements. --- ### From Cone Geometry to Monge Structure: Local Defects and Global Regret in High-Dimensional Optimal Transport Authors: Lei Luo, Jian Yang Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04695v2 Exact optimal transport in high dimensions becomes tractable only when additional structure selects the optimal coupling. Classical Monge transportation solves the discrete problem once a cost array is known to be Monge, but it does not explain when geometry in the original feature space creates that structure. We characterize this regime for cone-induced orders and squared Mahalanobis costs: Macuteness of the cone is equivalent to the Monge property of every cross-cost matrix generated by two cone chains, after which classical northwest-corner optimality gives exact transport. When the inequalities fail, we derive an exact variational representation of northwestcorner regret over a marginal-dependent cumulative-deficit polytope. Its Fréchet box relaxation yields a projection-free, marginal-weighted localdefect bound; we characterize when the relaxation is exact and prove that it is worst-case sharp when only local defect budgets are known. We further show that the worst-case defect patterns can be realized by genuine squared-Euclidean cross-costs. Finally, Mahalanobis distances of observed increments to the cone control the local defects, while a strict geometric margin gives an explicit radius of exact stability. The resulting theory links high-dimensional ground-space geometry to exact Monge transport and quantifies the global loss induced by local departures from ordered structure. --- ### Cone-Compatible Monge Geometry for High-Dimensional Ordered Optimal Transport Authors: Lei Luo, Hongliang Zhang, Jian Yang Published: 2026-06-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.04695v1 High-dimensional optimal transport is seldom available in closed form. The one-dimensional case is exceptional because the order of the real line is compatible with convex transport costs, making monotone rearrangement optimal. This paper studies when an analogous Monge structure can be recovered in higher dimensions from a partial order. We introduce a cone-compatible Monge geometry: a closed convex cone (K) induces the order (x\preceq_K y) whenever (y-x\in K), and is compatible with a cost if ordered pairs satisfy a Monge exchange inequality. For squared Mahalanobis costs (c_M(x,y)=(x-y)^\top M(x-y)), we prove a sharp characterization: compatibility holds exactly when (K) is acute under the (M)-inner product, namely (u^\top Mv\ge0) for all (u,v\in K), equivalently (K\subseteq K_M^*). Under this condition, measures supported on cone chains admit a quantile-type closed-form optimal coupling, yielding exact transport under the original ground cost rather than after projection or metric replacement. We distinguish the resulting cone-chain Wasserstein metric on canonically ordered chain distributions from an extended directed cone transport cost on general measures, and develop feasibility, duality, stability, approximation, Gaussian recovery, statistical, and computational results. The theory is complementary to sliced and tree Wasserstein distances: it is not a universal fast surrogate, but a way to obtain interpretable, direction-valid, original-space monotone transport for ordered high-dimensional data. --- ### DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer Authors: Patomporn Payoungkhamdee, Tinnakit Udsa, Jian Gang Ngui, Sarana Nutanong, Alham Fikri Aji, Peerat Limkonchotiwat Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04694v2 Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade severely at sub-billion scales, especially for Southeast Asian (SEA) languages. We introduce DuDi, a dual-signal multilingual distillation framework that combines an online sequence-level signal with off-policy and on-policy token-level signals. DuDi further uses a cross-lingual verbalizer to refine teacher feedback and improve teacher-student transferability in multilingual settings. Experiments on SEA-HELM across multiple model families, scales, and teacher-student settings show that DuDi consistently outperforms competitive distillation baselines. Ablations and analyses confirm that sequence-level optimization, token-level supervision, and cross-lingual verbalization provide complementary and transferable learning signals for multilingual SLMs. --- ### SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction Authors: Kenfeng Huang, Yi Cai, Xin Wu, Zikun Deng, Li Yuan Published: 2026-06-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.04691v1 Zero-shot information extraction (IE) with large language models (LLMs) has attracted increasing attention due to its flexibility in adapting to new schemas and domains without task-specific training. Existing approaches mainly rely on monolithic prompting, each-type prompting, or multi-agent debate. However, monolithic prompting often suffers from boundary and type errors, while each-type prompting and multi-agent debate introduce cross-type conflicts, redundant agent interactions, and substantial token overhead. To address these challenges, we propose SMADE-IE, a sparse and evidence-driven multi-agent framework for zero-shot IE. SMADE-IE first employs an Adaptive Mode Selector to dynamically route inputs into either a lightweight Global Extraction Mode or a Type-Centric Extraction Mode, reducing unnecessary type selection and reasoning noise. For conflicting predictions, we further introduce an Evidence-Driven Debate mechanism that structures arguments into Toulmin-style components and performs confidence aggregation through external evidence scoring and Bayesian updates. Experimental results on 9 benchmark datasets across NER, RE, and JERE tasks show that SMADE-IE consistently outperforms existing zero-shot IE baselines while also improving token efficiency through sparse agent selection and early-stopping debate. --- ### QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation Authors: Prerana Ramkumar, Nouhaila Innan, Muhammad Shafique Published: 2026-06-03 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2606.04689v1 Scene Graph Generation (SGG) requires relational reasoning over objects and their interactions, but performance is often limited by severe long-tail predicate imbalance. Classical SGG models frequently rely on dataset statistics, leading to biased predictions toward frequent relations rather than fine-grained semantic predicates. Although existing debiasing strategies improve mean recall, predicate classification in current frameworks still often depends on large classical decision modules with high parameter cost. This work introduces a hybrid quantum predicate classifier for SGG by replacing the classical predicate head in Causal Feature Enhancement Network (CFEN) with a Quantum Predicate Head (QP-Head) trained using weighted cross-entropy. To the best of our knowledge, this is among the first studies to evaluate a hybrid quantum architecture for scene graph predicate classification on Visual Genome 150. We study the effect of qubit count, encoding strategy, entangling structure, and circuit depth on relational prediction. The best 4-qubit QP-Head uses Amplitude Embedding and Strongly Entangling Layers to compress 4096-dimensional pair features into a 16-dimensional quantum-compatible representation, corresponding to a 256$\times$ reduction. It achieves an mR@100 of 57.25%, compared with 41.1% for the classical CFEN reference, while using only 96 trainable quantum parameters. Scaling to 8 qubits maintains strong long-tail performance, reaching an mR@100 of 55.38% with 384 quantum parameters, while the depth analysis shows a trade-off between expressibility and runtime overhead. These results suggest that compact hybrid quantum predicate heads can support parameter-efficient long-tail relational classification in complex visual reasoning tasks. --- ### MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation Authors: Jiale Xu, Wang Zhao, Ying Shan Published: 2026-06-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.04688v1 Autoregressive mesh generation has gained attention by tokenizing meshes into sequences and training models in a language-modeling fashion. However, existing approaches suffer from two fundamental limitations: (i) low tokenization efficiency, which yields long token sequences and prevents scaling to high-poly meshes, and (ii) absence of geometry-aware guidance, as generation is conditioned only on global shape embeddings rather than local surface cues. We introduce MeshWeaver, an autoregressive framework that treats mesh generation as a surface weaving process by directly predicting the next vertex instead of independent coordinates. At its core is a multi-level sparse-voxel encoder that injects geometric context into the generative process in three complementary ways: providing voxel features as vertex representations, guiding token prediction via cross-attention to voxel features, and serving as a structural scaffold that constrains generation around the input surface. Our hierarchical design enables coarse-to-fine vertex prediction in a single decoding step, while tightly coupling the generative model with 3D geometry. Extensive experiments demonstrate that MeshWeaver achieves a state-of-the-art compression ratio of 18%, can generate meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches. --- ### Real-Time Automatic License Plate Recognition Using YOLOv8, SORT Tracking, and Temporal Data Interpolation Authors: Mirza Muhammad Mobeen Published: 2026-06-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.04684v1 The real-time hardships of video processing seriously limit the usage of Automatic License Plate Recognition (ALPR) with application in dynamic traffic monitoring settings. High-fidelity recognition of unconstrained variables, e.g. drastic variations in illumination, acute camera scans, high vehicle speeds, and harsh physical concealment, is a problem that often leads to disjointed tracking paths and poor Optical Character Recognition (OCR) rates. In order to mitigate these weaknesses, the study proposes a 5 stage, end-to-end algorithmic pipeline, encompassing a smooth transition between deep learning based object detection, multi-object tracking which is kinematic in nature, and geometry temporal data interpolation. The suggested architecture takes advantage of a very powerful YOLOv8 nano model to localize the vehicle at the first stage and then Simple Online and Realtime Tracking (SORT) algorithm is used to build spatial-temporal links between frames. Another, more specific typology of YOLOv8 object detectors the license plate area, channeling the sliced array to an EasyOCR chain under the limitations of positional syntax verification. More importantly, an offline interpolation mechanism of temporal bounding box is initiated to recast fragmented paths. --- ### Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy Authors: Zhihan Li, Hankun Wang, Yiwei Guo, Bohan Li, Xie Chen, Kai Yu Published: 2026-06-03 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2606.04680v1 Automatic speech recognition systems commonly rely on reference transcriptions for evaluation, while reference-free approaches often depend on internal confidence estimation or auxiliary language models. We propose READ (Reference-free Hypothesis Evaluation with Acoustic Discrepancy), a novel metric that evaluates ASR hypotheses directly from the speech signal. READ emphasizes the acoustic grounding of hypotheses. It uses a pretrained auto-regressive TTS model to compute the conditional likelihood of speech tokens given a text hypothesis, to measure fine-grained acoustic discrepancy between speech and text. Without additional training, READ can be applied for hypothesis refinement. Experiments show that READ correlates with specific recognition errors and improves ASR outputs, achieving up to 20\% relative error rate reduction, with particularly strong gains under noisy conditions. ---