# Research Papers — 2026-07 · bundle page 196 of 222 > Full-text markdown of papers #9751–9800 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/196 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/195.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/197.md) ### Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance Authors: Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris, Roberto Galeazzi, Ioannis Kyriakides Published: 2026-07-03 Categories: cs.AI, cs.IT, cs.LG, cs.RO, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2607.22667v2 This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks. The proposed approach is motivated by information-theoretic sensor management: instead of activating all sensors or repeatedly performing computationally expensive online expected-information-gain evaluation, a learned policy selects one tracking-relevant sensor at each decision epoch. A Bayesian sequential Monte Carlo tracker estimates the vessel state from noisy measurements and provides a belief representation for scheduling under nonlinear and non-Gaussian conditions. A Proximal Policy Optimization agent selects one of five sensors in a georeferenced simulation of the CMMI Smart Marina testbed at Ayia Napa Marina, Cyprus. The policy is trained on the testbed's actual five-sensor configuration. The agent observes belief-state, detection-history, coverage, sensor-geometry, and realized-information-gain features. The reward is defined as a realized-information-gain term gated by an observability mask. Final-test simulations compare the proposed framework with random single-sensor selection, always-on sensing using all sensors simultaneously, and the expected-information-gain sensor-selection baseline proposed in our previous work. Results show that the learned policy achieves tracking performance close to always-on sensing while activating only one sensor per decision time step and avoiding the computationally expensive online entropy search required by expected-information-gain selection. Additional zero-shot evaluation without retraining on ten moderately perturbed versions of actual layout configuration showed broadly stable tracking, with any increase in positional tracking error remaining below 1 meter across all perturbations. --- ### Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance Authors: Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris, Roberto Galeazzi, Ioannis Kyriakides Published: 2026-07-03 Categories: cs.AI, cs.IT, cs.LG, cs.RO, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2607.22667v1 This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks. The proposed approach is motivated by information-theoretic sensor management: instead of activating all sensors or repeatedly performing computationally expensive online expected-information-gain evaluation, a learned policy selects one tracking-relevant sensor at each decision epoch. A Bayesian sequential Monte Carlo tracker estimates the vessel state from noisy measurements and provides a belief representation for scheduling under nonlinear and non-Gaussian conditions. A Proximal Policy Optimization agent selects one of five sensors deployed in a georeferenced simulation of the CMMI Smart Marina testbed at Ayia Napa Marina, Cyprus. The agent observes belief-state, detection-history, coverage, sensor-geometry, and realized-information-gain features. The reward is defined as a realized-information-gain term gated by an observability mask. Final-test simulations compare the proposed framework with random single-sensor selection, always-on sensing using all sensors simultaneously, and the expected-information-gain sensor-selection baseline proposed in our previous work. Results show that the learned policy achieves tracking performance close to always-on sensing while activating only one sensor per decision time step and avoiding the computationally expensive online entropy search required by expected-information-gain selection. --- ### Local Synaptic Rules Can Implement a SIGReg Gradient Without Backpropagation Authors: Martin Andrews Published: 2026-07-03 Categories: cs.NE, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.21622v1 We prove that two canonical local synaptic learning rules, the potentiation arm of spike-timing-dependent plasticity (STDP$^+$) and homeostatic plasticity (instantiated here via flashlight granule-cell-like neurons), together can implement the exact gradient of a SIGReg-like self-supervised learning objective. The equivalence requires no gradient calculations, no global error signals, no weight transport, and no label information: the only inputs are pre- and post-synaptic firing rates, local firing statistics, and the temporal contiguity of natural sensory streams. On a synthetic clustering task designed to probe whether class structure can be recovered from temporal ordering of inputs alone, ordered presentation raised cluster separation (CSR) to 2.49 while random ordering left it near baseline (0.83), a roughly threefold ($\approx 3.5σ$) separation attributable solely to input ordering. On temporally ordered MNIST, a two-layer network trained entirely with these rules achieved 87.3% linear-probe accuracy, showing that the mechanism functions end-to-end. --- ### CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models Authors: Jingquan Chen, Jie Feng, Jinghua Piao, Shaogang Hu, Yong Li Published: 2026-07-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.20507v2 Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these settings often incur substantial inference cost. Many such requests share similar computational structures while differing in variables, constraints, or contexts, creating opportunities for program-level caching. Since program caches need to reapply reusable computation logic to new requests, their key steps often involve lightweight and structured operations such as variable extraction, program binding, and generation acceleration, which are well suited for small models. We propose CacheSpec, an inference optimization framework centered on reusable program caches. The framework converts Program-of-Thoughts (PoT)-style programs from one-time reasoning artifacts into reusable cache objects, and reuses the same small model for two roles: semantic variable extraction on the cache-hit path and speculative drafting during target-LLM generation. Experiments on shopping-style request datasets, WebShop, Formula, and CodeTAT-QA show that CacheSpec reduces inference latency and improves effective cache reuse while preserving comparable or better task quality than existing caching and generation baselines, achieving up to about 3.1$\times$ latency speedup; in parallel serving experiments, it improves throughput by about 2.8$\times$ over PoT-style methods. These results suggest that the sweet spot for small models in large-model inference systems lies not in solving complex tasks independently, but in performing lightweight, structured, and verifiable auxiliary operations. --- ### MiniCache: Reusable Program Caching with Small Model Interfaces for Efficient LLM Inference Authors: Jingquan Chen, Jinghua Piao, Jie Feng, Shaogang Hu, Yong Li Published: 2026-07-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.20507v1 Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these applications often incur high inference cost. We present MiniCache, a reusable program caching framework that transforms Program-of-Thought (PoT) programs into parameterized cache objects, enabling reusable computation across structurally similar requests. MiniCache reuses the same small model for semantic variable extraction on cache-hit requests and speculative drafting during target-LLM generation, reducing expensive target-LLM invocations while preserving task quality. Experiments on shopping-style request datasets, WebShop, Formula, and CodeTAT-QA demonstrate that MiniCache improves the trade-off between inference latency, cache reuse, and accuracy, achieving up to 3.1x lower latency and 2.8x higher throughput under parallel serving. These results show that small models are most effective not as replacements for large models, but as lightweight interface models that enable reliable and efficient reusable program caching. --- ### CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Authors: Pukaphol Thienpreecha, Karthik Subramanian Published: 2026-07-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19396v2 Document-based LLM systems often flatten a PDF before guardrails inspect it. That step can discard evidence that an instruction was never visible to the user. We introduce CrackedPDFs, a controlled benchmark for hidden prompt injection in PDFs. The benchmark contains 29,322 generated PDFs from 4,983 base documents. It includes 9,774 injected files and 19,548 benign or matched-confounder files. We evaluate PromptGuard and a rule baseline. We also evaluate structural-only learned models and a sanitized hybrid detector. The evaluation uses held-out provenance splits and paired benign-confounder controls. It also uses label-shuffle checks and shortcut audits. On a 2,919-document held-out test set, the hybrid detector reaches 0.960 F1. ROC-AUC is 0.998 and PR-AUC is 0.997. On a balanced subset containing 973 injected PDFs and 973 matched benign confounders, the hybrid detector achieves 95.9% classification accuracy. Using score ordering, it ranks the injected member above its matched confounder in 100% of 973 pairs. PromptGuard has low recall when given extracted text only. Structural-only learned models are weak under paired controls. A text-only TF-IDF model reaches perfect held-out scores but fails shortcut audits. These results show that document-aware hybrid detection is useful under controlled paired evaluation. They do not show broad real-world robustness or reliable cross-family generalization. --- ### From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation Authors: Yihan Wang, Zhong Guan, Haoran Sun, Jiale Huang, Likang Wu, Hongke Zhao Published: 2026-07-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.19395v1 Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets. This is inefficient in long-horizon environments, where early decisions shape later states and rewards. We propose Prefix-GRPO, a reinforcement learning framework that decomposes teacher trajectories into replay-aligned prefix queries and online continuations. Each prefix is replayed in the environment to recover a valid intermediate state, after which the student continues online interaction and receives task reward. Unlike response-only GRPO, Prefix-GRPO also applies clipped policy updates to historical assistant tokens inside the replayed prefix, using a policy-distilled SFT checkpoint to estimate their old log-probabilities. This unifies prefix learning and continuation learning within the same policy-optimization form. Experiments on TextCraft, BabyAI, and ALFWorld show that Prefix-GRPO improves small-model agents over distillation and standard RL baselines, while ablations show that replay alone is insufficient without explicit prefix-token optimization. The implementation and reproduction scripts are available at https://github.com/HappynessI/Prefix_GRPO. --- ### Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning Authors: Ji-Hoon Heo, Aleksandra Joanna Wisniewska, Seo-Hyun Lee, Seong-Whan Lee Published: 2026-07-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.19394v1 Generalizing across subjects remains challenging in invasive neural recordings because electrode configurations, anatomical structures, and neural signal patterns vary substantially across individuals. To investigate such inter-subject variability, we propose a cross-subject semantic decoding framework that aligns neural responses to speech perception from multiple subjects into a shared latent space and learns a mapping from the aligned neural representations to contextual embeddings. More specifically, using electrocorticography data collected during natural language comprehension, we estimate the shared space using the shared response model and train a decoder to predict contextual semantic embeddings from projected neural responses. For a held-out subject, we estimate a subject-specific projection into the predefined shared space, and directly apply the pretrained decoder without any retraining. Experimental results demonstrate that the proposed framework consistently outperforms baseline methods across evaluation settings and exhibits a reduced performance drop from source subject to held-out subject testing, indicating improved cross-subject generalization. These results suggest that aligning neural activity into a shared latent space, while decoding in a semantic embedding space, provides an effective strategy for improving cross-subject generalization by reducing subject-specific differences in neural responses while effectively capturing shared stimulus-related representations. --- ### Composable Verification Pipelines for Multi-Agent Systems Authors: Julian Alfredo Mendez, Andreas Brännström Published: 2026-07-03 Categories: cs.LO, cs.AI, cs.LG, cs.MA, cs.PL arXiv: https://arxiv.org/abs/2607.16266v1 Existing approaches for reasoning about action and change provide expressive semantics for modeling dynamic systems, in most cases built on top of logic programming systems. We introduce a modular framework for transition and trajectory verification based on Tiles and implemented in Soda, which is an efficient functional programming language. The framework operationalizes action language semantics through executable verification pipelines that process states, actions, transitions, and rules as compositional functional components. Verification procedures are represented as typed functional pipelines, enabling modular specifications, reusable reasoning components, and transparent execution workflows with guaranteed pipeline termination. The framework includes an executable specification layer that allows users to define domain descriptions in YAML, which are operationalized into the underlying verification model and executable pipeline structure. We provide an open-source implementation and illustrate the framework through examples that involve misinformation and emotional reasoning. --- ### Autonomous UAV Route Planning for Coverage Maximization in Environmental Monitoring: A Systematic Literature Review Authors: Sebastian Jouannet-Contreras, Carola Figueroa-Flores Published: 2026-07-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.13054v1 Environmental monitoring with unmanned aerial vehicles (UAVs) requires route planning methods that maximize covered area while handling energy limits, operational constraints, and geometric complexity. This paper reports the protocol and preliminary results of an ongoing systematic literature review (SLR) on autonomous UAV route planning for coverage-oriented environmental monitoring. The review follows the PRISMA 2020 framework and searches Scopus and Web of Science for studies published between 2015 and 2026. The protocol focuses on path planning, coverage path planning, and informative path planning, with emphasis on algorithmic families, coverage and energy metrics, obstacle handling, geometric environment representations, and environmental constraints. At the current stage, 562 records have been identified, 161 duplicates have been removed, and 401 unique records have been screened by title, abstract, and keywords. From these, 247 studies were retained for full-text eligibility assessment (235 eligible and 12 borderline records to be resolved during full-text review). A preliminary analysis of the retained studies suggests strong concentration on coverage-oriented formulations, multi-UAV coordination, and energy-aware optimization, while fewer studies explicitly address weather, uncertainty, or obstacle-rich environments. Most retained studies rely on simulation-based validation, highlighting a potential simulation-to-reality gap, and recent publications show increasing interest in reinforcement learning, hybrid optimization, and geometry-aware planning. These early findings indicate an active but fragmented research landscape and support the need for a structured synthesis to identify mature techniques and unresolved gaps for realistic environmental monitoring missions. --- ### SeqGPT: A Constrained Transformer Agent for the Inverse Design of Multi-Panel Composite Structures Authors: Driss Chraibi, Alejandro García Pis, Stéphane Grihon, Sixin Zhang Published: 2026-07-03 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2607.11910v1 Optimizing composite stacking sequences to match continuous targets (e.g., Lamination or Buckling Parameters) with discrete manufacturing constraints represents a challenging combinatorial inverse problem that regularly occurs in composite design especially when numerical optimization approaches are used (bi-step, bi-level configurations). In multipanel configurations, this complexity is further intensified by blending, a global compatibility/continuity requirement between the different panel stackings. This study presents SeqGPT, a conditional Transformer agent developed to replace computationally expensive iterative methods. To ensure both global continuity and manufacturing feasibility by construction, we implemented a hybrid neurosymbolic decoding strategy. SeqGPT predicts a conditional distribution that guides a Constrained Beam Search, where any branch violating blending rules is strictly pruned. Numerical experiments on the 18-panel horseshoe benchmark demonstrate that SeqGPT generates solutions near-instantaneously with buckling performance comparable to evolutionary methods, offering a significant speed-up compared to the state of the art. --- ### MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms Authors: Saiyang Feng, Yuanyun Zhang, Shi Li Published: 2026-07-03 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.09749v1 Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology. Electrocardiograms (ECGs) and pulse oximetry (SpO2) waveforms encode rich cardiovascular and hemodynamic information through their morphological structure. In this work, we introduce MorphologyFM, a multimodal foundation model pretrained on paired ECG and SpO2 waveforms from the MIMIC critical care database using a morphology aware self supervised learning objective. MorphologyFM combines morphology guided masking, cross modal representation learning, and contrastive latent alignment to learn representations that capture clinically relevant physiological structure without requiring manual annotations. We evaluate MorphologyFM across multiple downstream prediction tasks, including arrhythmia classification, hypoxemia prediction, mortality prediction, and length of stay estimation, demonstrating consistent improvements over representative self supervised learning methods, including Masked Autoencoders (MAE), contrastive learning, Barlow Twins, and Joint Embedding Predictive Architectures (JEPA). Furthermore, we show that jointly modeling ECG and SpO2 waveforms produces more transferable representations than single modality pretraining. Our results establish waveform morphology as a powerful inductive bias for self supervised physiological representation learning and introduce MorphologyFM as a general purpose foundation model for continuous physiological monitoring. --- ### Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems Authors: Jun He, Deying Yu Published: 2026-07-03 Categories: cs.AI, cs.DC, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2607.09748v1 In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. However, the rise of agentic distributed systems -- where autonomous, stochastic, and model-driven agents orchestrate infrastructure -- presents scenarios where deterministic, bitwise replication is insufficient. Replicas operating with generative models may exhibit divergent reasoning paths, summaries, and token boundaries, yet reach semantically equivalent and correct operational decisions. Forcing bitwise agreement across these stochastic participants degrades execution flexibility, induces context amnesia, and limits performance. We argue that in such settings replicas should agree on belief, not bits. We propose Epistemic State Replication (ESR), a belief-replication layer for agentic distributed systems that shifts the replication boundary from data visibility to knowledge visibility. We formalize the epistemic node state as a pair K = (L, B) separating the deterministic, immutable evidence log (L) from the stochastic, evolving belief lineage (B). To govern execution safety, we define Semantic Linearizability, which requires operations to reflect the latest committed operational meaning within a verifier-bounded semantic compatibility metric, and Bounded Eventual Coherence, which bounds expected semantic divergence under fair delivery, monotonic evidence, bounded verifier disturbance, and a contractive graft operator. We outline protocols for propagating derived insights using structured epistemic deltas, and formalize Verifiable Semantic Rollbacks to prune faulty premises from belief lineages without inducing context amnesia. We prototype ESR and report preliminary simulation results that show feasibility under the stated assumptions and illustrate reductions in secondary cognitive faults. --- ### Life as Plasmas: Autonomy and Interactivism in-materio Authors: Nicolás Hinrichs, Mahault Albarracin, Felipe Engelberger, Leonardo Christov-Moore, Daniel Polani Published: 2026-07-03 Categories: cs.NE, q-bio.PE arXiv: https://arxiv.org/abs/2607.09747v2 When is a material system a candidate for life at all? We argue that this question is prior to behavior, functional architecture, or computational capacity, and that at root it is one of physical admissibility. We develop a framework in which minimal autonomy, taken in the interactivist sense of normativity grounded in self-maintaining far-from-equilibrium organization, corresponds to a distinct non-equilibrium phase of matter, and we take complex plasmas, a physical and non-biological system, as its in-materio exemplar. We formalize a diagnostic phase-space whose criteria (sustained free-energy throughput, organizational closure, active information maintenance, and regulated noise sensitivity) constitute necessary conditions for life-attribution. We instantiate the diagnostics across contrasting systems and fix the boundaries of the phase space via Bénard convection as a driven baseline lacking closure, and a digital self-replicating soup that carries measured informational heredity while its physical closure remains a structural zero. We demonstrate that plasmas satisfy every admissibility condition for minimal physical autonomy while carrying none of the informational heredity that open-ended evolution requires, sharpening the distinction between physical admissibility and biological sufficiency, and bounding downstream questions of machine sentience. --- ### SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks Authors: Tushar Lone, Neha Karanjkar Published: 2026-07-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.09745v1 This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures. It supports multiple replenishment policies, perishable inventory, node disruptions, and stochastic demand and lead times. All components are extensible via inheritance. Users describe a supply chain as a graph with node and link attributes, while the library handles simulation, providing logs and extensive node and network level performance reports. This paper presents the motivation, design, key features, and architecture of SupplyNetPy, along with detailed validation results (against analytical benchmarks, a commercial tool, and a published case study). A key motivation behind SupplyNetPy's development is programmatic generation and simulation of complex models, enabling design-space exploration, what-if analysis, training data generation, and supply chain digital twins. --- ### A Theory of Least Autonomy in AI Authors: Christophe Parisel Published: 2026-07-03 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.09744v1 Least privilege, the principle that an identity should hold only the permissions strictly required for its task, has been a foundational primitive of access control for decades. We argue that this principle is insufficient for agentic AI systems, which do not merely hold permissions but can combine, approve, and amplify them across workflows and system boundaries. We propose least autonomy as an appropriate generalization and develop a formal theory. First, we define a compositional blast radius d(a,b) that measures structural separation between actions in an enterprise hierarchy, combining an ultrametric tree with lattice-valued confidentiality, integrity, and control-context labels. Second, we define a directed agent influence graph G(theta). An arc from U to V requires a directed shared-resource write-to-read meeting or a conservative undirected agent-to-agent (A2A) communication meeting, and a meeting-conditioned influence potential at or above an externally selected policy threshold theta. A catalogue-radius profile supports calibration and audit of theta. Finally, we define a collusion predicate over graph reachability that detects authorization composition, decision manipulation, and cross-domain capability composition. --- ### Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets Authors: Pratyush Singh Published: 2026-07-03 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2607.09743v1 We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models, and whether their effects depend on model architecture. Using Hotelling's linear city model as a diagnostic vehicle, we evaluate GPT-4.1-mini (a standard instruction-following model) and GPT-5-mini (a reasoning-optimized model) under five conditions - an unscaffolded baseline and four reasoning interventions - across eight questions spanning deductive and abductive reasoning, three prompt framings, and three repetitions per condition, yielding 720 individually judged responses. We find a statistically significant crossover interaction between scaffolding type and model architecture ($t(7) = 4.79$, $p = 0.002$, $d = 1.69$): commitment scaffolding improves the standard model ($+0.21$) while degrading the reasoning model ($-0.63$), and principled separation shows the opposite pattern ($-0.40$ vs. $+0.31$). Both crossovers are individually significant (commitment: $p = 0.040$; separation: $p = 0.002$) and hold across all eight questions with 7/8 directional consistency. Adversarial stress-testing harms both models, with $2.6\times$ greater degradation for the reasoning model ($-1.47$ vs. $-0.57$; $p = 0.038$), and the damage correlates negatively with baseline difficulty ($R^2 = 0.36$, $p = 0.014$). We further document a persistent declarative-procedural gap in which both models identify correct strategies at rates far exceeding their ability to execute them; separation fully closes this gap for the reasoning model while no intervention helps the standard model. --- ### SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving Authors: Chengyue Wang, Bin Rao, Haicheng Liao, Bonan Wang, Chengzhong Xu, Zhenning Li Published: 2026-07-03 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.09741v1 Accurate trajectory prediction in autonomous driving hinges on modeling dynamic and context-dependent interactions among traffic agents. However, most existing approaches are purely data-driven and lack structural priors, which limits their generalization under distribution shifts. In this work, interaction modeling is revisited through the structure and dynamics of traffic networks, and SWIFT (Small-World Interaction Framework for Trajectory prediction) is proposed as a unified framework that integrates small-world networks with traffic flow theory. SWIFT introduces structural inductive biases via a Small-World Interaction Network that captures both local and global dependencies, and a Flow Regime Encoder that adapts the interaction structure to scene-level traffic states. Interaction reasoning is further enhanced through a multi-relational graph module that explicitly encodes direct and higher-order agent relationships. Extensive experiments on three real-world datasets, nuScenes, MoCAD, and NGSIM, show that SWIFT consistently outperforms strong baselines in prediction accuracy across diverse traffic regimes. Beyond accuracy, SWIFT exhibits improved generalization to unseen locations and regimes, robustness under noisy observations, and strong performance with limited training data, supporting the effectiveness of its structure-aware design. --- ### Recovering Candidate Circadian Regulators of Arrhythmic Pituitary Hormone Genes Using Reliability-Weighted Magnetic Laplacian with rwMagLap Authors: Shabnam Sodagari, Nick Jasperson Published: 2026-07-03 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2607.06579v1 We study how to recover candidate circadian-clock regulators of pituitary hormone genes that are important for women's health but do not show a clear 24-hour rhythm in bulk tissue, aiming to nominate clock-linked regulatory targets that could inform future chronopharmacologic and chronotherapeutic strategies. We propose \textbf{rwMagLap}, which builds a graph on rhythmic backbone genes. For each edge, we combine 24-hour fit quality with peak-time phase, represented as a complex unit-circle value, yielding a Hermitian adjacency matrix and a magnetic Laplacian. We insert arrhythmic hormone genes, treated as anchors, by a reliability-weighted nearest-neighbor projection. The projected anchor-neighbor weights are pooled into a soft teleport distribution, and complex personalized PageRank then ranks rhythmic backbone genes by the magnitude of their PageRank scores. In pituitary data, we find that all 11 women's-health anchors are arrhythmic. Even so, we find that the top-50 list is $7.95\times$ enriched for the 13-gene KEGG circadian set (7 of the 8 set genes in the 454-gene backbone; corrected Benjamini-Hochberg (BH) $p_{\mathrm{BH}}=4\times10^{-6}$) and $4.54\times$ enriched for the 111-gene Reactome set (8 of 16 genes; $p_{\mathrm{BH}}=1.6\times10^{-4}$), while a phase-blind real-valued baseline recovers none. We recover candidates through reliability weighting and phase-aware seeding rather than through magnetic propagation. The magnetic phase adds a different capability: it represents temporal order. On pituitary backbone, the magnetic embedding recovers measured peak-time order of connected pituitary genes with accuracy $0.971$, while $q{=}0$, i.e., no magnetic charge, is at chance. --- ### Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark Authors: Nishan Pantha, Pranath Reddy Kumbam, Sajil Awale, Pushwitha Krishnappa, Muthukumaran Ramasubramanian, Nidhi Jha, Emily Foshee, Ankur Kumar, Rachel Slank, Ashkbiz Danehkar, Rahul Ramachandran Published: 2026-07-03 Categories: cs.IR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.05443v1 Scientists increasingly rely on open-source tools to support their research workflows, yet discovering relevant software among over 600 million GitHub repositories remains challenging. Existing code search benchmarks focus on general software engineering tasks and fail to capture the domain-specific vocabulary and needs of scientific computing. We present a curated corpus of 5,264 high-quality, domain-classified scientific repositories spanning five NASA Science Mission Directorate divisions -- Earth Science, Astrophysics, Planetary Science, Heliophysics, and Biological & Physical Sciences -- enriched with cleaned READMEs, extracted topics, and additional context from crawled links. Building on this corpus, we introduce two novel information retrieval benchmarks: (1) a repository search benchmark with 219 expert-curated queries designed by domain scientists, and (2) a large-scale code snippet retrieval benchmark containing 117,950 code snippets and 119,720 queries across seven programming languages. Baseline evaluations on repository search reveal significant performance variation across scientific domains. Code snippet retrieval proves equally challenging, with substantial variation driven by differing documentation practices, coding standards, and programming language conventions across scientific communities. All datasets and benchmarks are publicly released on HuggingFace to support research on scientific tool discovery. --- ### PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models Authors: Lorenzo Molfetta, Giacomo Frisoni, Nicolò Monaldini, Gianluca Moro Published: 2026-07-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.05441v1 Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still struggle to effectively manage large tool collections, researchers have begun exploring retrieval-based methods to pre-select the most relevant options, addressing input length and latency constraints. However, existing retrievers are often misaligned with tool-calling LLMs due to their separate training processes. This paper presents PORTS, a novel odds ratio preference optimization method for training retrievers aimed at tool selection. Using a perplexity-inspired preference signal from a frozen LLM, our approach fine-tunes a retriever to find helpful tools by optimizing the correlation between the selection probabilities and the downstream performances while jointly enforcing a contrastive semantic loss between documentation strings. The versatility of PORTS and its ability to significantly improve tool selection accuracy are demonstrated through extensive experiments on six datasets, two encoder models, and three LLMs with diverse prior knowledge. With low computational demands, our alignment process facilitates generalization to new queries and tools, proving valuable for practical applications with evolving toolsets. --- ### Design-CP: Context Parallelism for Design of Protein Nanoparticles Authors: Lorenzo Tarricone, Helen E. Eisenach, Aiko Muraishi, Charlotte M. Deane Published: 2026-07-03 Categories: cs.LG, cs.DC, q-bio.QM arXiv: https://arxiv.org/abs/2607.05439v1 Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- and atom-pair representations quickly exceed single-GPU memory as the number of chains and residues modelled grows. We introduce Design-CP, two context-parallel (CP) inference strategies for RFdiffusion 3 (1D row-sharding and 2D grid sharding with ring attention) that distribute the quadratic activations across a multi-GPU mesh while preserving pretrained weights. We characterise their scaling when sampling icosahedral assemblies, showing that the maximum feasible asymmetric subunit (ASU) size grows with the expected square-root trend in GPU count and that 2D sharding achieves better wall-clock scaling. Moreover, we show how strong point-group symmetry constraints make CP usable out of the box for end-to-end, all-atom design of icosahedral nanoparticles, yielding favourable in silico structural and interface metrics. Finally, we demonstrate octahedral nanoparticle design on a small cluster of workstation-grade 16GB GPUs, illustrating how Design-CP can be a practical path towards democratising large-assembly protein design. --- ### Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG Authors: Xue Li, Yiming Gai Published: 2026-07-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.05438v1 Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images. The dominant deployment choice is binary and made before the model has tried to answer: either run a cheap text(+table) pipeline, or pay for an expensive vision-language model (VLM) over every image. Recent adaptive systems improve on this by selecting the modality or fidelity pre-retrieval, from a question-conditioned predictor of which modality will be needed. We show that this is the wrong decision point. Through an oracle headroom analysis on MultiModalQA, we find that the relevance of a modality to a question is a weak predictor of whether that modality is actually needed to answer correctly: a large fraction of questions whose gold support includes an image are nonetheless answerable from text and tables alone, and a pre-retrieval router that escalates on apparent visual relevance over-escalates substantially relative to an oracle. We propose \textbf{post-hoc selective modality escalation}: answer cheaply from text and tables, run a verifier on the (query, draft answer, evidence) tuple that localizes which modality is missing, and pay for VLM evidence only there. A calibrated value-of-escalation router then decides whether the expected accuracy gain justifies the visual cost. On MultiModalQA, our router recovers the accuracy of an always-on VLM pipeline while issuing far fewer visual calls, and closes most of the gap to the oracle escalation rate. The result extends a routing-signal hierarchy established for retrieval depth and reasoning hops to a third axis -- modality -- under a single cost-aware selective-escalation view. --- ### Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence Authors: Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05436v1 The rapid scaling of over-parameterized machine learning architectures, particularly LLMs, raises a profound crisis: do these systems exhibit genuine intelligence, or are they merely sophisticated statistical pattern matchers? Classical flat Euclidean statistics cannot differentiate continuous interpolation from the autonomous discovery of novel causal laws. To resolve this, we introduce Statistically Meaningful Geometry (SMG), a framework modeling over-parameterized learning systems as infinite-dimensional non-parametric Orlicz fiber bundles. We prove that under persistent out-of-distribution (OOD) stimuli governed by unmodeled causal mechanisms, continuous optimization fails. Unmodeled variance is rejected by the visible horizontal base manifold, leaking into the unobservable vertical fiber space and generating an accumulation of Active Acausal Tension. Driven by the statistical manifold's non-linear curvature, this tension inevitably strikes a conjugate focal boundary ($T_{\text{crit}} = π^2 / K_{\text{max}}$), triggering localized volumetric collapse and a catastrophic matrix singularity ($(G_f)^{-1} \to \infty$). We demonstrate this geometric breakdown acts as the strict non-equilibrium trigger for a Gauge Symmetry Break (GSB). The system purges hidden tension from unobservable gauge redundancies, spontaneously crystallizing a new, mathematically independent horizontal coordinate axis. This non-parametric phase transition registers as a discrete $+1.0$ integer step-jump in observable Structural G-Entropy. By decoupling parameter charts and subjecting emergent axes to a Minimal Energy Path Criterion and a Causal Invariance Filter, we distinguish genuine discovery from malignant hallucinations. Ultimately, SMG provides a parameter-free, falsifiable dashboard to mathematically certify true intelligence, transforming AI for Science into an engine of autonomous paradigm shifts. --- ### Abductive Corroboration of Probabilistic AI Models for Forensic Synthetic Media Detection Authors: Junade Ali Published: 2026-07-03 Categories: cs.CR, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2607.05434v1 Artificial Intelligence (AI) models, at their core, apply general learnings from broad datasets to individual circumstances using probabilistic behaviour. This inductive approach stands in contrast to deductive reasoning approaches which seek to prove conclusions from their premises. However, research has shown that deductive reasoning with AI models is a challenging problem and in the real-world it may not always be feasible. An alternative way forward is to leverage abductive reasoning, seeking to corroborate the output of multiple approaches to identify the most likely conclusion from the factual matrix. We apply this to synthetic media detection in forensic settings, and find we are able to disproportionately lower the risk of false positives to true positive recall. We also provide the first empirical evaluation of OpenAI's rollout of SynthID on synthetic images and evaluate how complementary different synthetic media detection approaches are. --- ### Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing Authors: Ayush Prasad, Swarnalee Mazumder Published: 2026-07-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.03644v1 Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragmented across archives, and no benchmark exists for evaluating machine learning on lunar data. We introduce Moonstone, the first multi-modal foundation model benchmark for lunar remote sensing. Our contributions are: (1) a 28-channel, 128 pixels-per-degree (~237 m) global lunar pretraining dataset from seven instrument families across five missions, (2) MG-MAE, a modality-grouped masked autoencoder with per-group convolutional tokenizers, a shared Vision Transformer encoder, attention masking for missing modalities, coverage-adaptive masking for heterogeneous spatial coverage, and spectral continuity regularization for physically plausible reconstructions, and (3) a benchmark of six downstream tasks covering classification, regression, and segmentation. MG-MAE pretrained features outperform scratch baselines on all tasks and surpass both ImageNet-pretrained and vanilla MAE baselines by large margins. Data and code are available at https://huggingface.co/datasets/ayushprd/Moonstone and https://github.com/ayushprd/Moonstone . --- ### Model Confidence-Guided Multi-Image Fusion of Fundus Images for Diabetic Retinopathy Diagnosis Authors: Ananya Raghu, Anisha Raghu, Alice S. Tang, Yannis M. Paulus, Tyson N. Kim, Tomiko T. Oskotsky Published: 2026-07-03 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.03643v1 Purpose: Early screening for eye diseases is critical in low- and middle-income countries where access to care is limited. We investigate whether a confidence-guided, multi-image diabetic retinopathy diagnosis framework can integrate image filtering with confidence-aware predictions for reliable screening at capture. Methods: We develop a multi-image fusion method that aggregates retinal views to improve confidence and balanced accuracy. Our method uses confidence to identify unreliable predictions, prompting retakes when needed. We compare: (1) a cascaded image-quality and disease diagnosis pipeline using a single image per patient, (2) confidence-based prediction, and (3) our confidence-based multi-image fusion pipeline. All methods are evaluated using a RETFoundGreen backbone on the mBRSET (n = 1,234) and BRSET (n = 7,599) datasets. Results: At 70% coverage, our method achieves 91% balanced accuracy on mBRSET and 97% on BRSET, improvements of ~12% and ~6%, respectively, over cascade filtering. The image-quality cascade reaches sensitivities of 61% on mBRSET and 86% on BRSET, whereas our framework reaches 94% and 96%, respectively, at 50% coverage. Conclusions: Human-annotated quality labels are weakly associated with diagnostic performance, and confidence-based filtering consistently outperforms image quality-based cascaded pipelines. Translational Relevance: Using confidence-based multi-image fusion, patients receive more reliable predictions, reducing incorrect diagnoses during screening. The lightweight backbone and single inference pass per image make the framework compatible with low-latency mobile screening systems in resource-limited settings. --- ### Missing Data Imputation under Manifold Hypothesis Authors: Zelong Bi, Amuchechukwu Ibenegbu, Sarat Moka Published: 2026-07-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.03641v3 The manifold hypothesis posits that high-dimensional data are concentrated near a low-dimensional embedded manifold. Recent advances in mixture variational autoencoders (VAEs) provide a powerful tool for extracting such underlying structure in a faithful manner. The resulting geometric structure naturally introduces local and global relationships among variables, thereby providing a systematic way of imputing missing data. We propose a model-based imputation method that enables sampling from \( p(\bm{x}_{\mathrm{mis}} \mid \bm{x}_{\mathrm{obs}}) \) via a sampling-importance-resampling (SIR) procedure, which can be further augmented with a joint diffusion model in the latent space. Our method imputes missing data while respecting the underlying geometry, achieves competitive performance compared to state-of-the-art procedures, quantifies uncertainty in the imputations, and is model-based, thereby enabling on-the-fly imputation without rerunning the entire procedure. --- ### Missing Data Imputation under Manifold Hypothesis Authors: Zelong Bi, Amuchechukwu Ibenegbu Published: 2026-07-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.03641v2 The manifold hypothesis posits that high-dimensional data are concentrated near a low-dimensional embedded manifold. Recent advances in mixture variational autoencoders (VAEs) provide a powerful tool for extracting such underlying structure in a faithful manner. The resulting geometric structure naturally introduces local and global relationships among variables, thereby providing a systematic way of imputing missing data. We propose a model-based imputation method that enables sampling from \( p(\bm{x}_{\mathrm{mis}} \mid \bm{x}_{\mathrm{obs}}) \) via a sampling-importance-resampling (SIR) procedure, which can be further augmented with a joint diffusion model in the latent space. Our method imputes missing data while respecting the underlying geometry, achieves competitive performance compared to state-of-the-art procedures, quantifies uncertainty in the imputations, and is model-based, thereby enabling on-the-fly imputation without rerunning the entire procedure. --- ### Revealing Hidden Model Behaviors with Task-Specific Self-Reports Authors: Taras Kutsyk, Bartosz Zieliński Published: 2026-07-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.03640v2 Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic. We introduce the Stabilized Adapter for self-Report (SAR), a lightweight LoRA adapter that makes a fine-tuned model describe its own hidden behavior in plain language, using only the model and the dataset it was trained on. Across seven implanted behaviors, SAR detects the hidden behavior in every one--even when the model has generalized into broad misalignment that the training data alone does not predict. Introspection Adapters (IA), the closest existing baseline, detects some behaviors from our suite but misses others entirely--and where it misses, it hallucinates, consistently reporting wrong behaviors. SAR retains positive signal on every setting where IA fails and roughly halves the rate of hallucinations. This gives practitioners a more reliable tool to audit a fine-tuned model and answer ``what did it actually learn?'' type of questions. --- ### An AI-Assisted Solution to the Signed BAR Conjecture: Uniqueness in the Harrison--Reiman Class and a Completely-$\mathcal{S}$ Class Obstruction Authors: Yiping Lu, Youheng Zhu Published: 2026-07-03 Categories: math.PR, cs.AI, cs.NI, math.ST arXiv: https://arxiv.org/abs/2607.03639v1 For a multidimensional reflected diffusion, determining whether the associated basic adjoint relationship (BAR) uniquely characterizes the stationary distribution is a basic uniqueness problem in the BAR approach. The problem has remained unresolved for more than 35 years since the introduction of the BAR approach. In this paper, we resolve the finite-signed uniqueness problem for stable Harrison--Reiman data with a nonsingular $M$-matrix reflection matrix. The proof uses pathwise differentiability of the reflected diffusion implies feasible directional differentiability of the probabilistic resolvent to show that, at boundary points, its one-sided initial-state derivative factors through the tangent projection and vanishes along active reflection directions. An interior one-sided convolution then yields smooth test functions whose oblique derivatives are uniformly bounded and converge pointwise to zero on each closed face. The interior signed measure is consequently invariant for the reflected semigroup. The proof was discovered with the assistance of ChatGPT 5.5 Pro and subsequently verified by the authors. We also show that the nonsingular $M$-matrix assumption is structural. In the larger completely-$\mathcal{S}$ class, a nonsingular reflection matrix with a singular proper principal block admits boundary gauges supported on lower-dimensional strata. Under standard exponential ergodicity and a mild one-step regulator bound, these gauges produce nonzero zero-mass signed BAR tuples; indeed the zero-mass interior BAR coordinates contain an infinite-dimensional subspace. A four-parameter three-dimensional family, including an explicit rational example, verifies the obstruction. Thus the finite signed version of the Dai--Dieker question has a positive answer in the Harrison--Reiman $M$-matrix class and a negative answer in a natural completely-$\mathcal{S}$ extension. --- ### Probing Identity-Specific Motion Signatures: A Controlled Diagnostic Study Authors: Yingtie Lei, Fangxun Liu, Baicheng Wu, Colin Lee, Ziheng Zhang, Junke Yang, Zhiyuan Tao, Xuyan Huang, Shuheng Wang, William Koran, Kyle Park, Elijah H Buckwalter et al. Published: 2026-07-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.03633v1 Identity recognition (e.g., person, animal re-identification) has traditionally relied heavily on static appearance cues. Yet motion--consistent, individual-specific dynamics--can provide a complementary and potentially more robust signature, especially when appearance is weak or variable. This raises a fundamental question: when identity-specific motion cues are clearly present, to what extent do modern video models use them for recognition? To investigate this question, we conduct a systematic diagnostic study and introduce BALLER120, a controlled benchmark of 120 professional basketball players performing free-throws. By focusing on the same multi-phase action across individuals, BALLER120 reduces action-level variation and identity-correlated acquisition biases, enabling fine-grained analysis of identity-specific kinematic patterns. We find that modern video models can predict identity accurately from RGB videos, but often rely on static appearance cues such as faces and jersey regions, even when informative motion cues are available. Strikingly, when appearance is suppressed through silhouette-only or skeleton-only inputs, the same model architectures shift toward motion micro-patterns (e.g., foot placement and elbow bending). Despite containing less visual information, appearance-suppressed representations achieve competitive accuracy and stronger robustness to appearance shifts. Our qualitative analyses further show that appearance-suppressed models attend to distinctive motion patterns across individuals. Overall, our study demonstrates that identity-specific motion signatures are present, informative, and learnable, but modern video models may overlook them in favor of easier static shortcuts unless appearance cues are explicitly suppressed. --- ### Reflected Schrödinger Bridge Matching Authors: Marcus Häggbom, Viktor Nilsson, Pierre Nyquist, Joakim andén Published: 2026-07-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.03626v1 Recent advances in generative modeling have enabled the efficient computation of Schrödinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free training methods inspired by flow matching. However, these have not covered SBs with reflecting dynamics, a useful model choice with built-in guarantees that generated samples stay in the data domain. Existing alternatives for reflected SBs instead rely on more complex training based on forward--backward SDE theory, requiring expensive higher-order derivatives and sampling entire paths during training. In this article, we introduce a partially simulation-free framework that allows reflected SBs to be trained similarly to flow matching, using a new sampling method and regression target. We demonstrate our results by coupling pairs of well-known high-dimensional image datasets. Using reflected dynamics incurs negligible additional wall-clock time during both training and inference while maintaining or slightly improving generative performance. --- ### RADIO1D: Elastic Representations for Condensed Vision Modeling Authors: Greg Heinrich, Mike Ranzinger, Collin McCarthy, Natan Bagrov, Eugene Khvedchenya, Bryan Catanzaro, Jan Kautz, Andrew Tao, Pavlo Molchanov Published: 2026-07-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.03624v1 This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features. Analyzing fine-tuned vision encoders, we find that representations become increasingly abstract and less spatially coherent during VLM training. Notably, models trained with image-text alignment (such as SigLIP2) develop a small number of specialized tokens that effectively summarize global image content. Building on this, we introduce RADIO1D, which compresses images into a compact, variable-length 1D token sequence using multi-teacher knowledge distillation and an autoencoder design. The resulting representations exhibit strong hierarchical summarization, enabling accurate scene understanding - even with a single token - and support improved composition-aware image retrieval. In VLMs, RADIO1D provides flexible accuracy-efficiency tradeoffs through adjustable token counts, delivering competitive performance on diverse multimodal benchmarks with lower computational overhead and better accuracy. --- ### A Vision Based System for Guided and Collaborative Reconstruction of Fragmented Documents Authors: Oliver Krumpek, Diana Leo Published: 2026-07-03 Categories: cs.CV, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2607.03621v1 This paper presents the development and evaluation of a collaborative system for real-time reconstruction of fragmented paper documents in the context of cultural heritage preservation. The developed system includes a collaborative robot, or cobot, that can fully manage the positioning of paper fragments using a specially designed vacuum-based suction attachment. This attachment enables gentle and precise positioning, ensuring the preservation of fragile materials. With this device, we are able to achieve a positioning repeatability of 0.57mm for fragments of 8cm^2. The system offers users the flexibility to choose between manual positioning, with visual guidance, or fully automated positioning performed by the cobot. To further improve the reconstruction process, AI methods for image interpretation, specifically for segmentation and positioning tasks, were applied and evaluated for their applicability to template-based reconstruction of damaged paper fragments. Our investigation provides critical insights into the performance of different local feature matching methods under different document types, taking into account rotation, scale robustness, and the degree of damage to the fragments. With a focus on the reconstruction of damaged and optically altered archival material, SE2-LoFTR, a detector-free local feature matching method, was chosen as the preferred method for the system due to its robust performance in our experiments. --- ### IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning Authors: Yuening Cai, Junwei Zhou, Youran Qu, Yu-Wing Tai Published: 2026-07-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.03614v1 Spatial question answering is the dominant paradigm for evaluating spatial intelligence in Vision-Language Models (VLMs), but it leaves a complementary axis of spatial competence under-evaluated: holistic 3D layout inference, which predicts every visible object's pose and extent from a single image in a structured form. To this end, we introduce IDEAL-Bench, an evaluation suite that requires VLMs to predict structured 3D layouts on photorealistic indoor scenes across 10 room types, scored along five numerical dimensions and a perceptual render-and-compare protocol. By operating on semantically realistic scenes with full asset substitution under controlled lighting and viewpoint, IDEAL-Bench moves beyond CLEVR-style simple geometric primitives so that any image-space discrepancy reflects spatial reasoning alone. The benchmark is built on IDEAL-Scenes, a procedurally generated dataset of 1,000 re-renderable Blender environments with ground-truth layouts. Evaluating 15 prominent VLMs reveals three findings: the task remains substantially unsolved, with the strongest model reaching only 62.1/100 overall; all models exhibit a sharp asymmetry between object recognition and geometric regression, indicating that current VLMs are trained to describe scenes rather than to measure them; model rankings partially diverge from those on QA-based and primitive-reconstruction benchmarks: top-tier consensus holds, but mid-tier rankings shift substantially. Collectively, these findings establish IDEAL-Bench as a diagnostic suite, targeting the geometric and structural competencies that QA-based evaluation cannot surface, and paving the way towards more rigorous evaluation of spatial intelligence in next-generation VLMs. Together, these findings position IDEAL-Bench as a principled diagnostic for whether future VLMs achieve genuine spatial understanding rather than linguistic approximations of it. --- ### Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse Authors: Shuang Liang, Tom Jacobs, Guido Montúfar Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.03613v1 We study the implicit bias of noisy stochastic gradient descent in training wide two-layer ReLU networks for multivariate regression. In a mean-field regime, the training dynamics are approximated by a Wasserstein gradient flow that converges to a unique stationary measure. We characterize the structure of this stationary measure and the predictor it represents. We show that, despite the network being infinitely overparameterized, the learned predictor admits an effectively finite representation: the input weights and biases align along finitely many directions, leading to an effective width collapse. In particular, the solution function is continuous piecewise affine, with affine regions determined by the cells of a finite hyperplane arrangement. The number of learned directions, and hence hyperplanes, is bounded above by $2\mathcal{P}-1$, where $\mathcal{P}$ denotes the number of linear dichotomies realizable on the training inputs. We further establish a non-redundancy property of the learned representation by proving that each learned direction induces a unique ternary activation pattern on the training data. Consequently, the complexity of the learned predictor is governed by the combinatorial geometry of the training data. --- ### SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers Authors: Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu Published: 2026-07-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.03612v2 Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attempt to improve efficiency through compressed or sparse attention, they fail to fully exploit the inherent sparsity and dynamic behavior of global attention. In this work, we present a comprehensive analysis of global attention across multiple F3R transformers and reveal that attention patterns are highly heterogeneous, dynamic, and extremely sparse across layers and attention heads. Motivated by these findings, we propose SAF3R, a training-free dynamic sparse attention framework tailored to F3R transformers. SAF3R integrates tailored sparse attention mechanisms with offline head profiling and an efficient online adaptation strategy to match input-dependent attention behaviors. Extensive experiments demonstrate that SAF3R achieves high sparsity ratios while preserving camera pose estimation and 3D reconstruction quality, translating into substantial end-to-end speedup on F3R transformers compared to existing methods. Code is available at https://github.com/jndeng/SAF3R --- ### SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers Authors: Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu Published: 2026-07-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.03612v1 Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attempt to improve efficiency through compressed or sparse attention, they fail to fully exploit the inherent sparsity and dynamic behavior of global attention. In this work, we present a comprehensive analysis of global attention across multiple F3R transformers and reveal that attention patterns are highly heterogeneous, dynamic, and extremely sparse across layers and attention heads. Motivated by these findings, we propose SAF3R, a training-free dynamic sparse attention framework tailored to F3R transformers. SAF3R integrates tailored sparse attention mechanisms with offline head profiling and an efficient online adaptation strategy to match input-dependent attention behaviors. Extensive experiments demonstrate that SAF3R achieves high sparsity ratios while preserving camera pose estimation and 3D reconstruction quality, translating into substantial end-to-end speedup on F3R transformers compared to existing methods. Code is available at https://github.com/jndeng/SAF3R --- ### A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning Authors: Sushant Dagaji Desale, Rahul Mishra, Ashutosh Kumar Sinha Published: 2026-07-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.03600v1 Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains. Existing approaches often fail to achieve an optimal trade-off between robustness and accuracy, as pseudo-labels generated by domain-adapted models tend to introduce classification errors under adversarial attacks. In this work, we propose \textbf{SFT+RL}, a two-stage robust UDA framework that integrates Supervised Fine Tuning (SFT) and Reinforcement Learning (RL) on top of CLIP's pre-trained visual encoder. In the SFT stage, we adversarially fine-tune a linear classifier using PGD-based perturbations over the labelled source domain while partially unfreezing CLIP's projection layer. It allows adaptation to adversarial noise while preserving CLIP's rich semantic priors. We introduce a confidence-guided pseudo-labeling strategy in the RL stage to annotate unlabeled target samples progressively. Pseudo labels are filtered using a decaying confidence threshold to balance quality and coverage, and the model is trained on a composite dataset formed by combining clean source samples with high-confidence target samples. Adversarial training is applied to mixed batches of clean and adversarial examples to enhance cross-domain robustness. Comprehensive evaluations on three benchmark datasets OfficeHome~\cite{tomm-ude}, PACS~\cite{pacs}, and VisDA~\cite{visda} demonstrate the effectiveness of our approach. Notably, \textbf{SFT+RL} achieves average improvements of \textbf{10.2\%} in clean accuracy and \textbf{15.8\%} in adversarial robustness across all three datasets, outperforming existing state-of-the-art methods. --- ### They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It Authors: Alex Kwon Published: 2026-07-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.03598v1 When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check. We treat the sender's communicative intent, the Gricean what-was-meant, as a first-class interpretability object, and show the failure is one of readout on top of a robust representation. A linear probe decodes the sender's intent, whether they want a thing recognized or evaluated, from a model's default-pass hidden states, cleanly and surface-independently, across six models and four families and in the base checkpoints. The representation generalizes further, to intent that is only pragmatically inferred, and to a second, lexically clean intent (support versus help). The behavioral half of the story, and every causal test, is established on the recognize/evaluate contrast, where what varies is whether the default output acts on the intent. The readout lags the representation in depth within a model (the intent is decodable several layers before it drives the output); across models, which ones act on it by default is model-specific, an observed stratification (three of six show the failure) that we do not read as a scaling law. Where the gap is open, a direction closely tied to the representation, the discriminative direction at a searched-for layer, is a causal handle: steering it recovers the intended behavior, as well as an explicit instruction does and with no prompt at all. This direction is near-orthogonal to the feedback-offering axis, so it routes a represented intent rather than a generic feedback knob, though at the recovery dose the routed intent can override an explicit request. We support each link with controls against obvious deflations and report the nulls as plainly as the confirmations. --- ### Empirical Bayes for correlated Gaussian sequence model Authors: Qiyang Han, Cun-Hui Zhang Published: 2026-07-03 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.03596v1 Empirical Bayes methods are among the most widely used statistical methods for large-scale inference. A central paradigm is the NPMLE, whose theoretical guarantees are by now well understood for the independent Gaussian sequence model. In this paper, we study empirical Bayes estimation from dependent observations in the Gaussian sequence model. We show that the maximum Composite Marginal Likelihood (CML) estimator, which ignores all correlations in the likelihood, converges in weighted Hellinger distance at the rate $n_*^{-1/2}$, where $n_*=n/κ_0$ is the `effective sample size' determined solely by the number of observations $n$ and the spectral radius $κ_0$ of the correlation matrix of the Gaussian observations. A complementary minimax lower bound shows that $n_*$ indeed serves as the right complexity measure, and that the CML estimator is nearly rate optimal under general dependence. We consider two concrete applications. In the first, we consider Bayesian linear regression, where the signal prior is estimated via CML applied to the least squares estimator. In the second, we consider the more challenging Bayesian nonlinear single-index model, where prior is estimated by CML applied to a one-step debiased gradient descent. In both applications, although the full likelihood landscape can be arbitrarily complicated and intractable, our CML method is facilitated by exploiting the high-dimensional distribution of the auxiliary statistics through a correlated Gaussian sequence model. The key ingredient in the proof of our results is a sharp local maximal inequality for the log composite marginal likelihood process under dependent Gaussian observations. In contrast to standard empirical process methods, we prove this inequality by leveraging a recent geometric Brascamp-Lieb inequality for Gaussian measures. --- ### Token-Based Affordance Grounding with Large Vision-Language Models Authors: Seung Il Lee, Qinqian Lei, Daguang Xu, Dong Yang, Robby T. Tan, Yixin Chen, Bo Wang Published: 2026-07-03 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2607.03595v1 Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception. Previous studies have primarily relied on weakly supervised learning with action labels from exocentric images. However, these methods often struggle with visually ambiguous exocentric images containing co-occurring actions; moreover, they fail to distinguish semantically similar actions because existing methods typically rely on brief action phrases that lack rich semantic details for action-specific localization. Although large vision-language models (LVLMs) encode rich action semantics and their action-conditioned textual outputs implicitly contain spatial cues, they do not directly provide action-specific spatial localization. To address these problems, we propose TokAG, a zero-shot affordance grounding framework that exploits the token-level semantic-spatial signals in LVLMs to localize action-relevant regions without external supervision. We observe that attention maps associated with different LVLM output tokens vary significantly, with many attending to irrelevant regions such as the background. Thus, we introduce a spatial-aware token-selection mechanism to systematically evaluate each output token and select the one whose attention maps exhibit dominant activation over the target object, instead of relying on arbitrary attention maps. By extracting these object-focused attention maps, we transform the LVLM's implicit semantic signals into zero-shot affordance heatmaps. Our zero-shot framework consistently outperforms prior weakly supervised approaches across multiple benchmarks, improving NSS by 10.7% on the unseen split of AGD20K and by 29.7% on HICO-IIF. The code and models will be made publicly available. --- ### An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Radiomic Signatures in Tumor Classification Authors: Chengkun Sun, Jinqian Pan, Renjie Liang, Zhengkang Fan, Xin Miao, Yi Guo, Mei Liu, Muxuan Liang, Russell Terry, Jie Xu Published: 2026-07-03 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.03593v1 Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, characterization, prognosis, and treatment planning. Although deep learning has shown great potential for imaging signature discovery, its limited interpretability remains a major barrier to clinical adoption. Existing approaches often achieve high predictive performance but provide little biological insight into the identified signatures. We propose a unified framework for interpretable imaging signature discovery by integrating deep learning based segmentation, explainable classification, and radiomic analysis. A robust segmentation model is first used to accurately delineate tumors, followed by a Grad-CAM guided pipeline that identifies diagnostically important regions as candidate imaging signatures. A mutual information based adaptive thresholding strategy enables patient-specific signature extraction. The resulting signatures are validated using a downstream deep learning classification model, while radiomic features extracted from the signature regions are evaluated with traditional machine learning models and interpreted using SHAP to identify the most discriminative biomarkers. The proposed framework is evaluated on the public BUSI breast ultrasound, KiTS renal CT, and BraTS brain tumor datasets, as well as a private UF Health renal CT cohort. Compared with conventional whole-tumor radiomics, the proposed signature-based approach achieves improved discriminative performance while providing greater biological interpretability. By converting deep learning attention into reproducible quantitative imaging biomarkers, this framework offers an interpretable and reproducible solution for non-invasive tumor characterization and imaging biomarker discovery. --- ### Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models Authors: Ryosei Tamura, Andrew Shin Published: 2026-07-03 Categories: cs.CV, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.03591v1 Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured crash records. However, such data sources are costly to deploy and maintain at large scale, and they cannot objectively capture what the driver was actually able to observe before the accident. In contrast, ego-view accident videos directly represent the driver's visual perspective, making them suitable for reasoning about avoidability and driver responsibility. In this paper, we introduce responsibility distribution estimation for ego-view traffic accident videos, a new task in which a model predicts the percentage of responsibility assigned to each involved agent. We construct an LLM-assisted responsibility annotation pipeline and fine-tune multimodal large language models under multiple input settings, including raw frames, segmentation-enhanced input, and textual descriptions. Experimental results establish a strong initial benchmark, demonstrating that multimodal LLMs can effectively perform this nuanced, constraint-based reasoning task. Our findings suggest that ego-centric accident videos provide a promising foundation for socially and legally meaningful multimodal reasoning beyond conventional accident classification and explanation tasks. --- ### Tightening Control in Neyman--Pearson Linear Classification Authors: Yijian Huang Published: 2026-07-03 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.03590v1 Neyman--Pearson classification prioritizes one class by constraining its accuracy above a prespecified level, and then takes the accuracy of the other class as the utility objective. This paradigm is well suited for disease screening and diagnosis, among other applications. Statistical learning under this framework is complicated since classifier performance determines its acceptability. Furthermore, no learned classifier that is consistent for the oracle classifier can guarantee satisfaction of the control constraint in finite samples. Classical learning theory targets a control-relaxed empirical utility maximization (EUM) classifier. However, even the EUM classifier fails to achieve the desired control level on average. We conjecture that this under-control phenomenon is a manifestation of the over-optimism bias well known in standard statistical learning, and develop asymptotic theory to confirm it. Motivated by this insight, we propose refined learning procedures under two accuracy control strategies for the prioritized class: one controlling accuracy in expectation and the other with high probability. We further develop training-data-based methods to predict and infer class-specific accuracies of the resulting classifiers. Simulation studies demonstrate favorable finite-sample performance, and we illustrate the proposed methods with an application to cancer detection. --- ### Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics Authors: Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan, Rajgopal Kannan, Viktor Prasanna Published: 2026-07-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.03589v2 State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal sequence modeling. While effective for sequential data, directional scanning introduces spatial bias and orientation-sensitive representations. We present Vision Non-Causal Trapezoidal Mamba (VNCT), a second-order non-causal vision SSM that enables all image tokens to interact in a single pass, eliminating direSctional scanning and achieving low single-image inference latency. VNCT exhibits more orientation-robust representations, showing reduced performance degradation under image rotations and flips, while improving Boundary IoU by up to 3.7 points, leading to more accurate boundary preservation and object localization. Across ImageNet-1K classification, COCO object detection and instance segmentation, and ADE20K semantic segmentation, VNCT consistently outperforms both directional-scanning vision SSMs and first-order non-causal SSMs. These results show that directional scanning is unnecessary for high-performance vision SSMs and that second-order non-causal state-space modeling offers a simple, efficient, and robust alternative for visual recognition. --- ### Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection Authors: Abdullah Shaik, Anwar Said Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.03587v1 We propose NetinfoGC, a framework for graph classification that extends the Network Usable Information (NUI) paradigm to graph-level learning. Unlike conventional graph neural network approaches that rely on end-to-end training of black-box embeddings, NetinfoGC constructs a family of permutation-invariant graph representations derived from propagation-based mechanisms and classical structural descriptors, including graph centrality measures. To evaluate representation quality, we introduce a training-free NUI estimation procedure based on clustering consistency with ground-truth labels, providing a proxy for task-relevant information without supervised learning. We further exploit the same representations using sparse-group LASSO regularization, enabling automatic selection of informative structural descriptors while suppressing redundant ones. Experiments on benchmark datasets show that classical centrality measures are highly competitive with learned propagation-based representations, and in several cases yield superior performance. Moreover, we observe a strong correlation between estimated NUI and downstream classification accuracy, validating NUI as an effective measure of representation utility. Overall, NetinfoGC provides a unified and interpretable framework for evaluating and exploiting graph representations without requiring end-to-end neural training. --- ### Modular Foundation Models for Time-Series Perception in Digital Twins Authors: Quang Hung Pham, Ryad Zemouri, Martin Gagnon, Luc Vouligny Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.03585v1 Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from heterogeneous and non-stationary time-series data. However, most existing approaches remain task-specific, data-hungry, and difficult to integrate into scalable monitoring and decision-making pipelines. Moreover, purely data-driven models often lack robustness and transferability across varying operating conditions. To address these challenges, this paper proposes a modular foundation model for time-series perception based on a collection of pretrained representation encoders. The framework leverages self-supervised learning on heterogeneous datasets to learn transferable and task-agnostic representations, which can be reused across multiple PHM tasks. A gating mechanism is introduced to dynamically select relevant encoders for a given target dataset, enabling conditional computation and adaptive model composition. The selected representations are projected into a shared latent space and aggregated using a Transformer-based self-attention module that explicitly models cross-encoder interactions. The resulting architecture supports multiple downstream tasks, including imputation, long-term forecasting, and few-shot learning, through lightweight task-specific heads, while keeping pretrained encoders frozen during adaptation. Extensive ablation studies demonstrate the complementary roles of self-supervised pretraining, encoder selection, representation alignment, and adaptive aggregation. Experimental results on the ETT benchmark show competitive performance across tasks, while a real-world industrial case study on virtual sensing for hydro-generator rotor temperature highlights the practical relevance of the approach. --- ### PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition Authors: Dana A Abdullah Published: 2026-07-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.03581v2 The widespread adoption of facial masks, accelerated by COVID-19 and mandated in security-sensitive settings, has exposed limitations of conventional face recognition systems. Existing approaches relying on fixed cosine thresholds, non-adaptive CNNs, and purely data-driven features fail to generalize when facial regions are occluded, creating a gap between lab performance and real-world deployability. This paper proposes PLGSA-Transformer, a cross-modal face matching framework with three contributions. First, Periocular Landmark-Guided Spatial Attention (PLGSA) uses MediaPipe landmarks to compute Gaussian heatmaps over the eye, brow, and forehead regions, fusing them with EfficientNetB3 features via a learnable residual gate to direct attention toward discriminative visible regions. Second, a Hybrid CNN-Transformer Branch reshapes feature maps into tokens processed by a two-layer Multi-Head Self-Attention encoder, enabling cross-regional dependency modelling. Third, the Occlusion-Adaptive Cosine Threshold (OACT) is a jointly trained head that raises the matching threshold in proportion to predicted occlusion severity. The model is evaluated on 858 images from Zenodo MDMFR (60%), Kaggle CelebA-HQ masked collection (25%), and author-collected images (15%), spanning both genders, ages 21-75, with varied mask types, trained via a unified loss combining contrastive verification, identity classification, and occlusion cross-entropy. PLGSA-Transformer achieves 97.22% pair verification accuracy with ROC AUC 1.0000, surpassing VGG-16-based MUFM (Abdullah et al., 2025; 95.0%), HOG classifiers (Adnan et al., 2020; 85.0%), and Feature-based Structural Measure (Shnain et al., 2017; 86.61%). These results confirm that encoding periocular geometry into attention, with Transformer modelling and occlusion-adaptive thresholds, yields a robust, scalable solution for cross-modal masked face recognition. ---