# Research Papers — 2026-07 · bundle page 132 of 222 > Full-text markdown of papers #6551–6600 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/132 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/131.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/133.md) ### Good Benchmarks Authors: Ivan Bercovich Published: 2026-07-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12217v1 Good tasks are correct, solvable, verifiable, well-specified, and hard for interesting reasons. The best tasks describe a real problem an experienced practitioner would recognize, in language a practitioner would use, with tests that verify the outcome rather than the approach. --- ### RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls Authors: Brenda Lelis, Rodrigo Cabral-Carvalho Published: 2026-07-13 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.12216v1 Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation problem: every token spent on coordination is unavailable to task instructions or evidence when a call is assembled under a fixed context budget. We introduce the Roundtable Context Window Test (RCWT), a controlled protocol for measuring this task-budget displacement effect. RCWT varies coordination content while controlling total budget, position order, task family, and scoring. In the main context-dependent recall task at $W=4096$, three commercial models remain near baseline through moderate overhead and then degrade sharply once residual reference evidence falls to a few hundred tokens. Window-scaling summaries are consistent with a task-specific residual-budget interpretation rather than a fixed percentage threshold, but we treat this as descriptive evidence rather than a universal law. To test whether the fixed-budget cliff persists when task evidence remains intact, we add an intact-task ablation: the full task/reference block is kept present while coordination tokens increase by expanding total prompt length. In that setting, all tested calls return every scored field correctly across GPT-4.1-mini, Claude Haiku 4.5, and Gemini 2.5 Flash up to a 95\% coordination ratio. This ablation narrows the claim: the main RCWT cliff is best read as task-budget displacement, not as proof that coordination volume alone causes semantic interference in the original open-ended task. RCWT is therefore a measurement primitive for context-allocation budgeting, not a complete theory of multi-agent benefit or session-level coordination. --- ### Fine-Tuned Multi-Agent Framework for Detecting OCEAN in Life Narratives Authors: Rasiq Hussain, Darshil Italiya, Joshua Oltmanns, Mehak Gupta Published: 2026-07-13 Categories: cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.12215v1 Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, but pretraining of these models can induce latent "personality-like" biases, making single-model inferences inconsistent. We propose a fine-tuned multi-agent framework for detecting OCEAN personality traits, in which sub-agents are conditioned to adopt high, low, or neutral perspectives for each trait through masked language modeling (MLM) and psychometric supervision. A judge LLM aggregates and compares sub-agent outputs to generate final trait predictions, capturing multiple complementary perspectives while mitigating individual model biases. We evaluate the framework on life narrative dataset through quantitative and qualitative experiments, including baselines, ablations, and inference quality analyses. Our approach offers a scalable and interpretable method for text-based personality inference, highlighting the benefits of multi-agent reasoning grounded in psychometric supervision. --- ### The Benjamini--Hochberg Procedure Can Fail to Control the FDR for Correlated Two-Sided Gaussian Tests Authors: Edgar Dobriban Published: 2026-07-13 Categories: math.ST, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2607.12208v1 We show that the Benjamini--Hochberg procedure can fail to control the false discovery rate (FDR) at its nominal level for correlated two-sided Gaussian $p$-values. We construct a factor model for which, at level $α=0.01$, a rigorous interval-arithmetic certificate proves $FDR>0.0104$ for all sufficiently large numbers of hypotheses. This disproves a conjecture widely believed to be true for twenty years. Monte Carlo experiments are consistent with the theoretical result. The proof was obtained by GPT-5.6 Pro and carefully checked by the author. --- ### RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration Authors: Jiahao Luo, Hao Zhang, Jianqi Chen, Yijie He, Jiaxu Zou, Michael Vasilkovsky, Sergei Korolev, Sergey Tulyakov, Chaoyang Wang, Peter Wonka, James Davis, Jian Wang Published: 2026-07-13 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2607.12206v1 We present RegHead, a framework for constructing semantic blendshape sets for animatable non-humanoid head avatars. With a fixed expression vocabulary, semantic blendshapes provide a low-dimensional and interpretable animation interface and support cross-identity retargeting. Building such blendshape sets remains expensive because (i) expression-consistent supervision is scarce, (ii) generated 4D assets typically lack correspondence, and (iii) facial motion is highly localized. We propose (1) a large-scale dataset of non-humanoid identities paired with a shared expression vocabulary, obtained by expanding a small artist-rigged library via fine-tuned image editing; (2) a dense stochastic anchor motion representation tailored to localized facial deformations; and (3) a fast feed-forward registration model that converts unregistered expression meshes into a corresponded blendshape basis by predicting anchor-based deformations from the neutral shape. Experiments show that our approach produces higher-fidelity expression meshes than baselines, while running orders of magnitude faster than optimization. We further demonstrate real-time retargeting from human face tracking signals to non-humanoid characters, capturing both head pose and localized facial motions. Our project page is available at https://snap-research.github.io/RegHead/. --- ### What a Deletion Certificate Covers, and Where It Expires: Auditable Removal from a Support-Vector Memory Authors: Vishwajith Ramesh Published: 2026-07-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12204v4 We study deletion in a context memory that fits a support-vector boundary around stored keys and uses the resulting nonnegative coefficients to weight their values. An exactly zero coefficient lets us remove a key without changing the current normalized readout. In a three-key construction, however, a later admission makes the discarded key active in a solve over the full history. For a positive-weight key, a decremental update targets a refit on the remaining keys at the original coefficient cap, under its stated assumptions. Earlier standalone comparisons show close typical gate-score agreement, while similar keys with different values can yield larger readout differences. The journal extension tests chained deletions and admissions, checking coefficient feasibility and optimality conditions in both returned states and fresh references. The initial audit completes 66 of 80 trajectories and exposes numerical failures. A separately checked wrapper completes all 5,120 scheduled operations at unchanged acceptance thresholds, with eight initialization rescues and 84 update rescues. Its largest readout difference is 0.5273% of retained-value range. These finite results support explicit acceptance and rescue rules for the evaluated memory edits. They do not extend the current-state removal guarantee to arbitrary future admissions. --- ### Forgetful Attention: An Auditable Support-Vector Memory for Selective Retention and Verified Deletion Authors: Vishwajith Ramesh Published: 2026-07-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12204v2 Auditable memory requires a precise contract: which output is preserved, relative to which reference solve, and across which updates. We introduce Support Vector Attention (SV-Attention), a one-class support vector data description (SVDD) gate whose coefficients enter the readout. Zero-coefficient keys are reserve; positive-coefficient keys are active. Removing a reserve token without re-solving preserves the current readout. Maintained deletion, which updates the existing solver state, targets a fresh retained-key fit under the same coefficient cap C. Across 1,200 fp64 deletion/refit trials on Gaussian, redundant, MIMIC-IV, and learned keys, 1,199 complete. Median maximum gate-score discrepancy over declared probes ranges from 4.5e-13 to 5.7e-7, and fresh refitting is 24-223 times slower than maintained deletion on the reference CPU. A deterministic example shows that current reserve status does not guarantee equivalence after future admissions. At matched token counts, rare-group recall is 0.861 versus 0.319 for an oracle attention-mass proxy (H2O-style). In a held-out-channel ICU control, SpO2 below 90 percent defines events but SpO2 is excluded from every selector; event-hour retention is 0.464 versus 0.225 for an RBF-density baseline. A separate batched approximation supports end-to-end training; at 3.22M parameters, seven paired seeds yield mean best-validation bits per character of 2.178 versus 2.383 (p=0.001). The contracts are point-in-time and fixed-C; future-safe streaming and general-purpose performance remain open, and larger fixed-step runs suggest slower optimization. --- ### A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models Authors: Rahul Gupta, Abhinav Mohanty, Payal Motwani, Venkatesh Saligrama, Satyapriya Krishna, Connor Harris, Gary Anthony Ackerman, Brandon Behlendorf, Tom Hobson, Theodore Wilson, Spyros Matsoukas Published: 2026-07-13 Categories: cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2607.12200v1 As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert actor's ability to plan high-consequence Chemical, Biological, Radiological, or Nuclear (CBRN) misuse relative to public tools alone. Existing CBRN evaluations differ in non-expert definitions, threat scope, baselines, scoring rubrics, and decision rules, making results difficult to compare across studies. We introduce a Threshold Exceedance Criteria (TEC) framework that decomposes an uplift study into independently executable components: determining non-expert participant eligibility, defining the CBRN threat scope for the study, and statistically estimating material uplift. We then operationalize the TEC framework in a large-scale empirical study using a design that determines two forms of uplift: generative (where a model assists plan creation from scratch) and revisionist (where a model assists refinement of an existing plan). The study produced attack plans across the CBRN domains, which we evaluated through subject-matter-expert review to estimate generative and revisionist uplift. Applying the framework, our empirical study revealed domain heterogeneity: under this controlled pre-release evaluation, model-assisted plans sometimes received expert-equivalent instructional ratings, but confirmed material uplift was limited to the radiological domain. These findings informed mitigation and deployment-governance decisions rather than characterizing deployed model behavior. We conclude with methodological lessons for future CBRN uplift evaluations, emphasizing prespecified criteria, explicit baselines, separation of generative and revisionist estimates, and careful distinction between preliminary screening signals and confirmed risk determinations. --- ### Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing Authors: Gabriel Paris-Colombo, Rodrigo M. Cabral-Carvalho, Felipe D. Toro-Hernández Published: 2026-07-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.12195v1 Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three large language models (GPT-4o, Gemini-2.5-Pro, Claude-Sonnet-4.5) using verbal fluency data. By applying trajectory-based NLP metrics to the items generated by 82 human participants and LLM output across eight temperature settings, we quantified three complementary dimensions: entropy (step size predictability), distance to next (successive semantic steps), and distance to centroid (global dispersion). Humans exhibited higher entropy, larger semantic steps and broader dispersion than all LLMs, indicating more variable and exploratory search. Temperature tuning produced only partial alignments, as individual metrics matched between humans and LLMs at specific settings, but no configuration reproduced the complete human profile (in all dimensions). These findings suggest that human semantic search implements a distinctive balance between local exploitation and global exploration that current model architectures fail to reproduce. --- ### Compos3D: Interactive Part-Based Composition for Creative Control in Generative 3D Models Authors: Faraz Faruqi, Sean J. Liu, George Fitzmaurice, Justin Matejka Published: 2026-07-13 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2607.12193v1 While generative AI has unlocked new opportunities for 3D content creation, current workflows often rely on multiple regenerations, which provides limited control and unpredictable outcomes. We present Compos3D, a system that introduces a compositional workflow for generative 3D modeling through remixing. Instead of repeatedly regenerating models, users generate multiple candidates from text or image prompts, select parts of interest via 2D image regions or 3D mesh segments, and assemble them into a coherent design. The system synthesizes these compositions into a refined 3D model, preserving high-level intent while resolving low-level geometry. To evaluate this approach, we conducted a controlled user study comparing remixing and regeneration workflows across both 2D and 3D modalities. Results show that the remixing workflow provides participants with greater creative control, stronger alignment with their intent, and higher satisfaction. We conclude with design recommendations for future AI-assisted 3D modeling workflows. --- ### Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems Authors: Navnit Shukla Published: 2026-07-13 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2607.12188v1 Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants. We present Cost-Governed RAG, an architecture that integrates a codebook-oblivious vector index (TurboVec) with a multi-tenant LLM governance gateway, creating a unified observability stack where embedding, retrieval, and generation costs are jointly attributable per tenant. The architecture exploits TurboVec's deterministic, closed-form memory formula to enable near-exact per-tenant retrieval cost calculation - a property unavailable in graph-based indexes with non-linear memory overhead. Deployed on Snowpark Container Services within a cloud data platform's governance boundary, the system achieves 99.96% end-to-end cost attribution accuracy across 100 simulated tenants (10M vectors, log-normal size distribution) with telemetry overhead below 0.04% of query latency. The architecture reduces retrieval infrastructure cost by 3.1-9.0x compared to managed vector database services under the pricing assumptions detailed in Section IV. We formalize a three-layer cost model and demonstrate that codebook-oblivious quantization enables deterministic per-tenant cost attribution while also removing the shared-codebook leakage surface present in trained quantizers - the latter observation being exploratory and subject to the limitations described in Section VII. --- ### Overview of Cross-Component In-loop Filters in Video Coding Standards Authors: Zhaoyu Li, Xuewei Meng, Jiaqi Zhang, Cheng Huang, Chuanmin Jia, Siwei Ma, Yun Jiang Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12186v2 In-loop filters have been comprehensively explored during the development of video coding standards due to their remarkable noise-reduction capability. In the early stage of video coding, in-loop filters, such as Deblocking Filter, Sample Adaptive Offset, and Adaptive Loop Filter, were performed separately for each component. Recently, cross-component filters were studied to improve the chroma fidelity by exploiting correlations between the luma and chroma channels. This paper summarizes the cross-component filters used in the state-of-the-art video coding standard. Specifically, it includes the Cross-Component Adaptive Loop Filter and Cross-Component Sample Adaptive Offset. Cross-component filters aim to reduce compression artifacts based on the correlation between different components and provide more accurate pixel reconstruction values. In this paper, we introduce the origin, development, and status of cross-component filters in the current video coding standards. Finally, we had some discussions on the further evolutions of cross-component filters. --- ### Overview of Cross-Component In-loop Filters in Video Coding Standards Authors: Zhaoyu Li, Xuewei Meng, Jiaqi Zhang, Cheng Huang, Chuanmin Jia, Siwei Ma, Yun Jiang Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12186v1 In-loop filters have been comprehensively explored during the development of video coding standards due to their remarkable noise-reduction capability. In the early stage of video coding, in-loop filters, such as Deblocking Filter, Sample Adaptive Offset, and Adaptive Loop Filter, were performed separately for each component. Recently, cross-component filters were studied to improve the chroma fidelity by exploiting correlations between the luma and chroma channels. This paper summarizes the cross-component filters used in the state-of-the-art video coding standard. Specifically, it includes the Cross-Component Adaptive Loop Filter and Cross-Component Sample Adaptive Offset. Cross-component filters aim to reduce compression artifacts based on the correlation between different components and provide more accurate pixel reconstruction values. In this paper, we introduce the origin, development, and status of cross-component filters in the current video coding standards. Finally, we had some discussions on the further evolutions of cross-component filters. --- ### Entropy in Semantic Memory Navigation in Blind and Sighted Individuals: The Effect of Visual Experience Authors: Felipe D. Toro-Hernández, Rodrigo Lagos, Sergio E. Chaigneau Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12185v1 Embodied accounts of semantic memory highlight the role of sensorimotor systems in acquiring and storing knowledge. Congenitally blind populations offer a critical test bed for these assumptions, providing an opportunity to assess whether conceptual grounding requires visual experience. In this study, we assessed semantic memory navigation differences between blind and sighted individuals using a property listing task with concrete and abstract concepts. We computed semantic entropy, an embedding-based natural language processing metric that captures the predictability of retrieval. Generalized linear mixed models revealed distinct navigation patterns across groups: while sighted individuals showed higher entropy for abstract than concrete concepts, blind participants did not. Instead, blind individuals exhibited higher entropy for visually salient concrete concepts (e.g., penguin). These results underscore the role of visual experience in the organization and dynamic navigation of semantic memory. --- ### TRAIL: A Platform for Configurable Human--AI Teaming Experiments Authors: Mohammad Amin Samadi, Pedro Martins De Bastos, Jaeyoon Choi, Spencer JaQuay, Seehee Park, Nia Nixon Published: 2026-07-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.12180v1 An AI teammate's design properties (personality, communication style, when it speaks) can shape a team's trust, coordination, and decisions. Studying this rigorously demands infrastructure no existing tool provides: reproducible configuration of an AI teammate embedded in instrumented, real-time collaboration sustained over time. We present the Team Research and AI Integration Lab (TRAIL), a web platform that makes the AI teammate a configurable, reproducible design object, pairing a Big Five persona with a selective-participation message pipeline, dual memory, chained longitudinal experiments, and export-ready analytics. In a real six-session classroom deployment (about 51 students), TRAIL sustained longitudinal chaining, held the AI to a stable minority of the conversation, and enabled export-driven AI-human text-similarity analysis. A single blind persona change produced a design-consistent double dissociation: a cognitive-scaffolding agent drew stronger contribution ratings and closer linguistic alignment; a socially-supportive agent, a warmer team climate and lower over-reliance. --- ### The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning Authors: Shelley Cazares Published: 2026-07-13 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.12177v1 The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models. This paper describes the concept of Geospatial Foundation Models (GeoFMs), which are artificial intelligence/machine learning (AI/ML) models pre-trained on massive geospatial datasets through varied methodologies. We first articulate the core paradigm shift that GeoFMs enable: a separation of duties, where large-scale model providers perform the computationally intensive pretraining, allowing domain experts to rapidly fine-tune or prompt these models for specific, mission-critical tasks. This approach democratizes access to state-of-the-art AI/ML while maintaining the security and confidentiality of the downstream task. We then explore the novel capabilities unlocked by different types of GeoFMs, distinguishing between the finetunable vision models produced by self-supervised techniques like masked auto-encoding, and the vision-language models produced by contrastive learning which enable zero-shot tasks like open-vocabulary image analysis. Next, we discuss the practical considerations for operationalizing GeoFMs, from performance-cost analysis to the broader MLOps ecosystem. To that end, we introduce a taxonomy of model adaptation strategies and propose a framework for domain experts to select the most cost-effective adaptation approach for their particular mission set. Finally, we present a forward-looking vision of Agentic Geospatial Reasoning, where Large Language Models act as intelligent orchestrators, leveraging GeoFMs as tools to answer high-level user queries in natural language and automate complex analytical workflows, moving the field from perception to cognition. --- ### HEDGE: A Calibrated Ensemble for A/H Recognition Authors: Josep Cabacas-Maso, Ismael Benito-Altamirano, Carles Ventura Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12176v2 Ambivalence and hesitancy (A/H) undermine digital behaviour-change interventions, and recognizing them automatically from video is the goal of the ABAW A/H challenge on the BAH dataset. We describe HEDGE (Hesitancy/Ambivalence Estimation via Distribution-aware, Generalized Ensembling), our system for the 11th edition of the challenge: a calibrated, equal-weight ensemble of three fusion models over frozen face, audio, text, and pose embeddings, which reaches 0.7358 macro-F1 on the public test set. We also submitted four variants of this system to this year's private test (30 new participants): a fixed-threshold version, a single individual model, and an ensemble with cache-personalization test-time adaptation (TTA). The plain calibrated ensemble scored 0.7361 macro-F1 on the private test, closely matching our public-test estimate, and the TTA variant scored highest of all five at 0.7367 macro-F1, our official challenge result (team AIWELL, rank 5 of 12), even though TTA showed no benefit on the public test. The single individual model dropped to 0.6759, far more than any ensemble variant. We explain both results: TTA only has distribution shift to correct on the private test, which the public test lacks, and a text-only linear probe reaches 0.716 macro-F1 (within noise of the full system, correlated at 0.91 in its errors), so the ensemble's robustness to new participants comes from the same modality redundancy that makes single, less-diversified models comparatively brittle. We additionally report a systematic study of more than 60 further controlled experiments (modality, backbone, loss, and adaptation ablations) that did not improve on this system, and an explainability analysis showing the transcript's delivery style dominates the signal while the extractable non-verbal ceiling saturates near 0.60 macro-F1. --- ### A Calibrated Multimodal Ensemble for Ambivalence/Hesitancy Recognition: System Description and Private-Test Submission Strategy Authors: Josep Cabacas-Maso, Ismael Benito-Altamirano, Carles Ventura Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12176v1 Ambivalence and hesitancy (A/H) undermine digital behaviour-change interventions, and recognizing them automatically from video is the goal of the ABAW A/H challenge on the BAH dataset. We describe our system for the 11th edition of the challenge: a calibrated, equal-weight ensemble of three fusion models over frozen face, audio, text, and pose embeddings, which reaches 0.7358 macro-F1 on the public test set. This year's private test, released on a disjoint set of 30 new participants, is scored on five allowed submissions; we report the configuration and rationale of each of our five submissions, and, where already available, the private-test score obtained. Our first submission, an exact replica of the calibrated ensemble tuned only on public validation, scored 0.7361 macro-F1 on the private test, matching our public-test estimate almost exactly and confirming the pipeline generalizes to unseen participants without leakage. --- ### From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data Authors: Pradyumna Elavarthi, Arun J. Bhattacharjee, Harrison Lisabeth, Anca Ralescu, Petrus H. Zwart, Dilworth Parkinson, Elizabeth G. Clark Published: 2026-07-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.12175v3 X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction. However, rapid interpretation remains limited by image segmentation, which often requires manual thresholding, user prompting, or material-specific model training. We present a zero-setup framework for multi-phase segmentation of synchrotron X-ray tomography data that generates interpretable masks for previously unseen datasets without user input or retraining during deployment. The framework combines a material-agnostic mask preparation strategy with a pretrained semantic segmentation network. It represents commonly occurring structural regions as background, sample, bright, dark-gray, light-gray, and porosity masks. Unlike conventional deep learning pipelines that require dataset-specific annotations and retraining, the proposed framework can be applied directly to new scans and produce diagnostic-level segmentations within minutes of reconstruction. This enables rapid assessment of scan quality, sample morphology, porosity, and attenuation variations during ongoing beamline experiments. The generated masks can later be manually refined or used to fine-tune application-specific models when greater accuracy or material-specific labeling is required. Evaluation on held-out synchrotron micro-CT images and qualitative testing on additional datasets demonstrate consistent and physically meaningful segmentations across varying samples and imaging conditions. The framework also substantially outperforms conventional intensity-based thresholding. By connecting high-speed reconstruction with immediate interpretation, the approach supports near-real-time beamline feedback and scalable AI-assisted scientific imaging workflows. --- ### Decentralized Gradient Descent: Bottleneck Regimes and Budget Complexity Authors: Nicolò Michelusi Published: 2026-07-13 Categories: cs.DC, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2607.12172v1 Decentralized gradient descent (DGD) is widely used for solving distributed optimization problems over networks of agents. While its convergence properties are well understood, less is known about the communication and computation resources required to attain a prescribed accuracy. In this paper, we study DGD from a resource-aware perspective and characterize the communication-computation budget required to attain a target error level. We develop a bottleneck-centric framework in which different factors dominate the optimization dynamics at different error scales. Specifically, we identify operating regimes governed by initialization, objective heterogeneity and network connectivity, gradient noise, and communication noise. To capture these effects, we introduce two fundamental quantities: the gradient-Diversity-to-Network-connectivity Ratio (DNR) and the Gradient-to-Communication-noise Ratio (GCR). We show that these quantities determine the sequence of bottlenecks encountered during optimization and the corresponding budget-optimal operating strategy. Using a multi-stage analysis, we derive optimal stepsize selections and explicit budget-complexity bounds that quantify the budget resources required to attain a prescribed accuracy. The resulting expressions reveal how the overall budget decomposes into contributions associated with successive bottlenecks and provide insight into the fundamental tradeoffs among objective heterogeneity, network connectivity, gradient noise, and communication noise. --- ### Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models Authors: Xu Han, Jiajing Hu, Li-Ping Liu Published: 2026-07-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.12171v1 In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear. In this work, we analyze how learning errors from different parameterizations affect the generation performance. We show that predicting the data endpoint has a clear training signal that stabilizes training, whereas predicting the velocity maintains stable sampling dynamics near the data manifold. Motivated by these insights, we propose Self-Consistent Flow (SC-Flow), a new method that unifies the benefits of both parameterizations. By employing a lightweight consistency loss, SC-Flow jointly trains a single network to predict both the local velocity and the data endpoint, and the consistency between the two predictions improves the model's performance. The method requires no major architectural changes and adds minimal computational overhead. Extensive experiments on image generation tasks demonstrate that SC-Flow substantially stabilizes optimization and improves the straightness of generation paths, leading to significant gains in generation quality over standard rectified-flow baselines. --- ### We Hebben Een Serieus Translatie: Modeling Intercomprehension as Probabilistic Inference Authors: Thomas Hikaru Clark, Edward Gibson, Roger Levy Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12169v1 Intercomprehension refers to partial intelligibility of an unfamiliar language (L2) by a speaker of a related language (L1). How is this zero-shot cross-language comprehension possible? In this work, we extend past work on algorithmic models of noisy-channel inference to model intercomprehension in a Bayesian framework. The model uses an LM in L1 only for scoring latent hypotheses about the translations of observed L2 utterances, and a general-purpose noise model to infer a mapping between L2 and L1 words based on either form-based similarity or symbolic rules. We then conduct a human behavioral experiment, eliciting inferences for utterances in Dutch, Italian, and Ukrainian from speakers of English, Spanish, and Russian, respectively. Our full model shows a closer alignment to the distribution of human intercomprehension performance than ablations, and also compares favorably to zero-shot prompting of much larger models. These results provide a cognitively plausible computational model of intercomprehension, and highlight the flexible inferences made by comprehenders under wide uncertainty in real-world cross-language scenarios. We share our code publicly. --- ### From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness Authors: Mohamed Abdessalem Bal Published: 2026-07-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12166v1 Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and decoder atoms. We show this conflates two distinct claims: decoder-geometry alignment and encoder-activation behavior. We reproduce the superposition phase diagram of Elhage et al. (2022), identifying a convergence artifact at high sparsity and an under-described diffuse sharing regime at extreme overcompleteness. We reproduce the TopK-versus-L1 comparison of Gao et al. (2024), with direct evidence of L1 shrinkage. Our central result is causal: subjecting every recovered feature to ablation and steering, we find up to 77% of features passing a recovery bar (cosine >= 0.90) in a degraded SAE -- and 9% in a well-trained one -- are causally inert: the matched atom never fires when the feature is present, including matches at cosine ~1.000. We package the method as sae-causal-audit, a model-agnostic instrument with a deterministic pipeline. Re-auditing refines the finding: inertness decomposes by cause into structural inertness (antipodal-pair geometry, present in good SAEs) and competitive inertness (a TopK pathology of degraded SAEs), and by direction into read- and write-inertness, which five antipodal pairs dissociate completely -- unmonitorable yet steerable through the same atom, with steering specificities of 143-310 attached to zero ablation effects. We document why byte-exact reproducibility is unavailable by construction, and propose reporting it as a stack of claims with explicit scopes. Applying the instrument to a production SAE reproduces the pattern at small scale (14% inert) and surfaces an atom-collision signal: a handful of atoms recur as the nearest match for dozens of unrelated concepts, replicated across three batches. --- ### Data Safety: Synthetic Data Quality Analysis Using CIFAKE Dataset Authors: Kuniko Paxton, Amila Akagić, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12165v1 Recently, the societal implementation of high-performance image classification models has expanded rapidly. While these models require vast amounts of training data to improve performance, securing sufficient real images is often impractical. As a means to compensate for this shortage, the use of synthetic data is becoming widespread. However, synthetic images are not necessarily equivalent to real images for training purposes. This study systematically analyzes the differences between two types of synthetic images created by different generation methods and real images from three perspectives: high-dimensional feature space, low-level statistics in color space, and the model training process. Furthermore, it experimentally verifies how synthetic data should be utilized by considering realistic data mixing scenarios. This enables the proposal of an evaluation and application strategy for performing preliminary assessments on synthetic images of unknown quality and safely incorporating them into training. This research aims to contribute to enhancing the reliability and safety of image classification models utilizing synthetic images. --- ### Token Reduction Is Not Cost Reduction Authors: Sarel Weinberger, Amir Hozez Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12161v5 Token-reduction tools for coding agents are often evaluated by the number of tokens they remove, but token count alone does not determine end-to-end inference cost. We evaluate three token-reduction approaches against an unmodified Claude Code baseline across controlled coding tasks, measuring provider-billed cost, task success, cache traffic, and agent behavior. The largest compression setup reduced delivered tool-output tokens by 38.4% but increased billed cost by 6.8%, while lighter compression produced only small and statistically uncertain savings. Across tasks, token reduction was weakly correlated with cost reduction (Pearson r = 0.15). Cost decomposition shows that prompt-cache creation and reads dominate the measured input-side cost, leaving only a limited fraction of total spend directly addressable by tool-output compression. We also find that compression can alter agent trajectories through additional retrieval, diagnosis, testing, and turns, offsetting local token savings. On a SWE-bench Go subset, aggressive compression also reduced successful patch application. These results show that token reduction is not a reliable proxy for cost reduction in tool-heavy coding agents. Effective optimization should therefore be evaluated at the level of cost per successful task, including cache behavior, trajectory changes, and correctness rather than token counts alone. --- ### Token Reduction Is Not Cost Reduction Authors: Sarel Weinberger, Amir Hozez Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12161v3 Context-reduction layers for API-based coding agents, including command-output compressors, retrieval rankers, and API-boundary proxies, are commonly evaluated by how much context or tool output they remove. We ask a different question: which interventions actually reduce end-to-end billed cost while preserving task success? Our primary evidence is a pre-specified, hash-frozen, paired campaign of 2,908 provider-billed Claude Code runs, of which 2,848 were analyzed, covering 103 tasks, seven repositories, and three models. The campaign compared a baseline with two generations of hook-based compression and an API-boundary proxy within a broader measured program of roughly 5,500 billed executions. Three findings emerge. First, prompt-cache traffic dominated cost composition, accounting for about 87% of reconstructed four-component cost (about 80% of the actual bill), with an 8.7% dollar-weighted residual not attributable from retained telemetry. Second, local payload reduction was not a reliable predictor of end-to-end billed cost. An arm that removed 38% of estimated raw tool-output tokens incurred 6.8% higher paired cost (95% CI: +2.8% to +11.3%), while per-task reduction showed only a weak association with cost change (Pearson r = 0.15). Third, aggressive compression can remove action-critical evidence: on SWE-bench-derived Go tasks, compression reduced successful patch application from 27/40 to 15/40 by corrupting verbatim edit anchors. We propose evaluating context-reduction systems by success-adjusted billed cost rather than token reduction alone. --- ### Falsifying Causal Graphs With Outlier Events Authors: William Roy Orchard, Philipp M. Faller, Dominik Janzing Published: 2026-07-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.12145v1 True causal relationships are rarely known, and inferring causal graphs from data is hard. A fundamental challenge is how to assess whether a given causal graph is good in the absence of a ground truth. We propose falsifying candidate causal graphs based on whether they can explain the propagation of an outlier event. Our approach leverages a key principle: weak outliers rarely cause strong ones. While this principle has previously been used in root cause analysis to identify root causes without prior knowledge of the graph, we turn it on its head and use it to falsify candidate causal graphs whose implied outlier propagation is inconsistent with the data. To this end, we present the first statistical tests for the hypothesis that a candidate graph is the true causal graph, and show they have false positive control, power guarantees against incorrect causal graphs, and can operate with a single outlier sample. --- ### Generating Physically Plausible Parachute Dynamics with Deep Generative Modeling Authors: Yulong Yang, Clara O'Farrell, Christine Allen-Blanchette Published: 2026-07-13 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2607.12143v1 Accurately modeling the dynamics of planetary parachute and entry vehicle systems is critical for Entry, Descent, and Landing events such as vehicle separation and sensor activation. These dynamics are difficult to capture with traditional system-identification methods as parachute motion is highly nonlinear, the governing equations are not fully known, and relevant test data are scarce and expensive to acquire. In this work, we sidestep these challenges by leveraging a physics-aware generative modeling approach that learns parachute dynamics directly from data. The proposed method, Symplectic Parachute Generative Adversarial Network (SPar-GAN), adapts a Hamiltonian generative architecture to the parachute setting by conditioning on canopy design and freestream velocity, while enforcing conservation of energy through symplectic integration. We apply SPar-GAN to subscale parachute tests conducted at the National Full-Scale Aerodynamics Complex and show that it reproduces qualitatively accurate pitch-yaw dynamics of different parachute configurations while recovering a compact two-degree-of-freedom phase-space consistent with canopy axisymmetry. These results suggest that physics-constrained generative models can characterize parachute dynamics across operating conditions and may help reduce the volume of physical testing required to assess performance. --- ### Causal Graphs, Markov Properties and Do-calculus for Stochastic Differential Equations Authors: Philip Boeken, Joris M. Mooij Published: 2026-07-13 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2607.12140v2 Stochastic differential equations (SDEs) are widely used to model continuous-time dynamical systems, but graphical causal models for them are not yet well-understood. We consider systems of causal SDEs that are equipped with an explicit causal semantics. We pose solvability conditions for systems of causal SDEs such that they have well-defined observational and interventional distributions - even after marginalisation - and provide a general class of Lipschitz semimartingale SDEs that satisfies these conditions. As core results we establish the $σ$-separation Markov property and the do-calculus in terms of the system's causal graph for probabilistic independence and interventions on the level of sample paths. For a class of additive-noise SDEs we prove a stronger $d$-separation Markov property, even if the system is cyclic. As a corollary of the do-calculus, we obtain an explicit causal interpretation of the graph: that the absence of a directed path implies the absence of a causal effect. We further introduce time-split systems, which consider the causal relations between the processes when evaluated on disjoint intervals or time-points, and use them to reason about subsampled time-series, continuous-time Granger non-causality and local independence. Finally, we discuss how constraint-based causal discovery algorithms (PC, FCI, CCD, CCI) apply directly to SDEs within our framework when conditional independence between sample paths can be consistently tested. --- ### Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems Authors: Ke Sun, Xinyuan Zhang, Xinwu Qian Published: 2026-07-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12127v1 Learning-based methods for the traveling salesman problem (TSP) are often evaluated through the tours produced after decoding or search, but the learned object itself frequently lives in a surrogate space such as heatmaps, assignments, construction policies, or search-guidance scores. This hides the fundamental question: what Hamiltonian structure has actually been learned before decoding? In this study, we directly answer this question by learning TSP through a structurally meaningful latent object, rather than leaving most of the Hamiltonian structure to the final decoding stage. Based on a connected-by-construction rooted $1$-tree Gibbs family, we propose an end-to-end unsupervised learning pipeline called \emph{C2TSP}. The pipeline learns residual edge perturbations from unbiased TSP cost through implicit differentiation. For structural correction, a smoothed Held--Karp layer restores expected degree balance, while certificate-guided sharpening further pushes the connected distribution toward more tour-like structures. Experiments show that C2TSP yields strong decoding performance while preserving interpretable structural information. Ablations further verify that edge perturbation and certificate-guided sharpening jointly improve both tour cost and tour-like structure. --- ### An Agentic AI Scientific Community for Automated Neural Operator Discovery Authors: Luis Loo, Ulisses Braga-Neto Published: 2026-07-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12122v1 We present an agentic approach to autonomous neural operator discovery based on an AI scientific community, which consists of a swarm of virtual laboratories that interact under a citation-based economy of influence. Highly-cited labs found new labs that follow their research direction and replace non-performing labs. Each virtual lab contains three agents: an LLM planner that proposes an architecture, a numerical worker that trains and measures it, and an LLM reviewer that participates in cross-lab peer review. All labs share a common vocabulary consisting of DeepONet (branch-trunk), Fourier, Transformer (attention), wavelet, and residual convolutional neural operator building blocks. We evaluate the neural operator AI scientific community on five problems, namely piecewise regression, the linear advection and Burgers 1D PDEs, and the Navier-Stokes and Darcy flow 2D PDEs, while repeating the simulation three times for each problem. The results show that the neural operator AI scientific community is capable of discovering high-accuracy, low-parameter-count neural operator architectures. All 9,623 LLM calls are logged and audited, which reveals that the virtual lab LLM planners choose to hybridize in 99.8% of their logged decisions, consistently returning multi-family hybrids. Moreover, we conducted an ablation study by replacing the LLM agents in each lab by rule-based alternatives, which caused the scientific community to collapse to non-hybridized single-family stacks in several cases, showing that LLM agency is needed to preserve diversity. The results suggest a no-free-lunch theorem for neural operators: there is no universal winner. The code, configurations, and the complete LLM transcripts are released at https://github.com/luislootx/AI-SC. --- ### FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving Authors: Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, Fan Lai Published: 2026-07-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2607.12121v2 Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoising steps. This all-region execution pattern makes generation latency high and limits serving throughput. Existing multi-GPU parallelization methods can reduce per-step computation, but often introduce substantial activation exchange overhead, causing communication to offset or even outweigh the benefits of parallel execution. This paper presents FlashDiff, a diffusion serving system that improves inference efficiency through adaptive regional execution and scheduling. FlashDiff is based on the observation that diffusion refinement is not uniform across latent regions or denoising steps: different regions often stabilize at different rates, while neighboring steps exhibit strong temporal correlation. FlashDiff leverages these properties to selectively execute only regions that require further refinement and to reallocate the resulting compute slack across concurrent serving requests. FlashDiff consists of three mechanisms. First, it decomposes the latent representation into coherent execution regions using early-stage attention signals, preserving semantic structure while exposing fine-grained parallelism. Second, it uses a lightweight runtime controller to estimate region activity and bypass low-impact updates when further refinement is unlikely to affect output quality. Third, it applies an affinity-aware online scheduler that co-locates dependent regions, balances residual load across GPUs, and reuses reclaimed compute capacity to improve serving efficiency. Across real-world image, video, and audio workloads, FlashDiff reduces end-to-end serving latency by 30-97% and improves throughput by 1.2-2.2x. --- ### GaitSpan: Growing Humanoid Locomotion from Walking to Running Authors: Kwan-Yee Lin, Zilin Wang, Janelle J. Liu, Stella X. Yu Published: 2026-07-13 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.12114v1 A humanoid that can walk should not relearn locomotion from scratch to jog or run. Yet current approaches often obtain gait diversity by prescribing gait schedules, imitating motion clips, training experts to switch between or distilling skills into one policy. These strategies can produce impressive behaviors, but offer limited flexibility across continuous speed commands, terrains, and morphologies. We study skill growth with GaitSpan, a framework that expands a pretrained, basic walking policy into faster locomotion. It treats walking as a seed skill: reusable motor structure for balance, support, body coordination, and contact transition that can be regenerated at new rhythms, extended into longer/higher strides, and corrected by residual adaptation. This expansion has three aspects: 1) rhythm generation, which modulates the frozen walking policy with multiple internal clocks and learns command-conditioned combinations of the resulting canonical actions; 2) stride shaping, which rewards dynamic locomotion patterns appropriate for higher commanded speeds using a physically grounded objective inspired by spring-loaded inverted pendulum dynamics; and 3) residual adaptation, which captures motion details not accounted for by rhythm generation or stride shaping. GaitSpan is the first to deliver a single command-conditioned humanoid policy that spans walking, jogging, and running-like regimes covering a continuous speed range, transfers across morphologies, and deploys zero-shot on unseen sim-to-sim, and real-world terrains. Compared with baselines either trained with multi-experts or imitation from humans, it learns faster and achieves stronger gait performance. --- ### Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap Authors: Rafael Ferreira da Silva, Milad Abolhasani, Peter Beaucage, Laura Biven, Michael Bussmann, Kyle Chard, Ryan Coffee, Stephen DeWitt, Sagar Dolas, Carrie Eckert, David Elbert, Ian Foster et al. Published: 2026-07-13 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.12113v1 One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than anticipated. Multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field. Producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. We update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18), and scope the path forward to a two-year horizon. The first year concentrates on interfaces, protocol adoption, and the scaffolding of verification, and the second targets federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo. --- ### Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning Authors: Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang, Chengfang Li, Yan Wang, Zhenchao Ma, Bo Hu Published: 2026-07-13 Categories: cs.LG, cs.AI, cs.CV, cs.DC arXiv: https://arxiv.org/abs/2607.12112v1 Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynamic environments: catastrophic forgetting, wherein sequential task updates erase previously acquired knowledge across visual, linguistic, and cross-modal representations. Addressing this challenge is especially critical for autonomous networked AI operating in safety-sensitive domains, such as content moderation, where reliable retention of prior knowledge underpins system integrity. To overcome this, we propose Federated Continual Multimodal Learning (FedCMM), a framework that embeds continual-learning safeguards into the federated optimization loop at three complementary levels. At the parameter level, modality-aware elastic weight consolidation computes separate Fisher information matrices for the vision encoder, language backbone, and cross-modal projector, providing granular, asymmetry-aware protection against modality-specific forgetting. At the data level, each client trains a lightweight local generative replay module to synthesize raw-data-free embedding-level multimodal replay tuples without any raw data sharing. At the aggregation level, Task-similarity-aware gradient aggregation autonomously filters and reweights client updates by gradient cosine similarity, suppressing conflicting directions and stabilizing the global learning trajectory. Extensive experiments on two benchmarks demonstrate that FedCMM consistently outperforms recent baselines on accuracy and backward transfer, confirming that holistic, modality-aware optimization enables robust evolutive adaptation across heterogeneous networked AI deployments. --- ### PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs Authors: Jing Liu, Kun Yang, Yan Wang, Dingkang Yang, Xiaoshuai Hao, Wei Zhang, Yang Liu, Wei Zhou Published: 2026-07-13 Categories: cs.LG, cs.AI, cs.DC, cs.MA, cs.NI arXiv: https://arxiv.org/abs/2607.12111v1 Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within distributed network environments, Multimodal Large Language Models (MLLMs) serve as cognitive engines for edge devices, yet federated fine-tuning faces substantial challenges in balancing global knowledge aggregation with local adaptation under heterogeneous network conditions. Conventional federated protocols typically rely on uniform parameter aggregation, which conflates domain-invariant features with client-specific nuances, thereby resulting in suboptimal personalization and excessive communication overhead. To address these challenges, we propose PFAdapter, a communication-efficient framework introducing hierarchical LoRA decomposition to explicitly separate adapter parameters into global-shared and local-private components. Query and key projections are assigned to global synchronization for capturing universal multimodal semantics across the network, while value and output projections remain localized for edge-specific adaptation. Additionally, orthogonality regularization based on the Frobenius norm enforces strict separation between these components, preventing redundant feature learning. Selective aggregation protocols synchronize only global-shared components across the federated network, preserving local expertise and reducing communication costs by nearly 50%. Extensive experiments on VQA-RAD, SLAKE, Hateful Memes, and CrisisMMD datasets demonstrate that PFAdapter consistently outperforms state-of-the-art baselines, achieving accuracy improvements ranging from 2.4% to 4.8% across diverse edge intelligence tasks. Consequently, our framework establishes an efficient solution for agentic AI deployment in resource-constrained communication networks. --- ### ACZ-GSeg: Adaptive Concentric Zone-based Two-stage Ground Segmentation for LiDAR Point Clouds Authors: Ge Zhang Chunyang Wang Bin Liu Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12110v1 Ground segmentation is a fundamental prerequisite for autonomous navigation, environmental perception, and object detection in ground mobile platforms. To address the under-segmentation of ground points caused by sparse long-range point clouds, ground undulations, and interference from non-ground structures in complex road scenarios, this paper proposes a two-stage ground segmentation method based on the Adaptive Concentric Zone Model. First, an Adaptive Concentric Zone Model is constructed to dynamically determine the number of sectors in each ring, thereby forming local zones with more balanced point distributions. Based on this model, a two-stage ground segmentation method is developed. In the coarse segmentation stage, a lowest-height seed constraint and height-decay weighting are introduced to establish a weighted principal component analysis plane fitting model, from which ground candidate points are extracted. In the fine segmentation stage, a reflectance intensity consistency constraint is employed to distinguish high-confidence ground points from uncertain points, and the uncertain points are further refined based on the local height stability of high-confidence neighborhoods. Experimental results show that the proposed method achieves Precision, Recall, and F1-score values of 99.12%, 96.24%, and 97.66% on the SemanticKITTI dataset, and 98.72%, 100.00%, and 99.36%, respectively, on a self-collected point cloud acquired using a RUBY-PLUS. The results demonstrate that the proposed method can effectively adapt to the range-dependent distribution characteristics of LiDAR point clouds, which are dense at near ranges and sparse at far ranges. It reduces the misclassification of non-ground points while maintaining ground point recall, thereby effectively improving the stability of ground segmentation. --- ### Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design Authors: Yifei Chen, Shihan Lu, Ed Colgate, Kevin Lynch Published: 2026-07-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2607.12105v1 In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by gravity. While reinforcement learning has shown promise in learning complex finger gaiting, existing approaches do not prioritize maintaining well-conditioned grasps for sustained manipulation. We introduce two complementary physics priors for robust in-hand rolling: a global grasp-quality prior derived from classical grasp analysis and a local contact-geometry prior based on fingertip curvature. The grasp-quality prior is used as a dense reward-shaping term that encourages well-distributed contacts with improved worst-case wrench resistance. The contact-geometry prior is expressed in the fingertip geometry that mechanically shapes the contact interface toward task-aligned rolling while reducing off-axis drift. We evaluate the effect of these priors on learning in-hand rolling manipulation for a multifingered robotic hand manipulating three different objects at four palm orientations. Results show significant improvement in rotation efficiency, grasp stability, and disturbance rejection, suggesting that physics priors embedded in both learning and fingertip morphology improve task robustness and sim-to-real transfer. An overview video can be found at https://youtu.be/pdd1wHxQnJM?si=dM-U5kiiPTYsk3Pk. --- ### TraceSynth: Generating Production-Quality Kernel Traces with Constraint-Guided Diffusion Models Authors: Yuvraj Sehgal, Sneh Patel, Mahsa Panahandeh, Naser Ezzati-Jivan, Francois Tetreault Published: 2026-07-13 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2607.12104v1 Machine learning models for system diagnostics rely on kernel execution traces to capture fine-grained system behavior, but collecting production traces in industrial systems is costly due to runtime overhead, storage demands, and privacy constraints. We present TraceSynth, a diffusion-based framework for generating synthetic kernel traces that augment limited real data for downstream ML tasks. TraceSynth models traces as multi-channel sequences (event types, timestamps, CPU affinity, thread identifiers, and process metadata) using a Transformer-based denoising diffusion process with constraint-guided repair to enforce system invariants. Across six benchmarks, results show strong workload dependence. For deterministic, compute-heavy workloads (scimark2), synthetic augmentation achieves 87.2% F1-Macro at context length L=4096, only 2.6 percentage points below real-only baselines. Context length is the dominant quality factor, with L=4096 yielding a +104% relative improvement over L=256, while constraint-guided repair improves synthetic data quality by up to 4.3%. Ablation studies show that lightweight 2-channel models retain 97-99% of the performance of full 6-channel models at roughly half the computational cost. TraceSynth supports cost-effective augmentation of kernel execution traces in production observability pipelines and helps identify when synthetic data can substitute for limited real traces. --- ### Representing and Generating Levels Over Time through Playtrace Reconstructive Partitioning Authors: Emily Halina, Matthew Guzdial Published: 2026-07-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12097v1 Video games are a dynamic medium experienced over time. While there are many Procedural Content Generation (PCG) approaches for generating video game levels, they often use representations that abstract away this dynamic nature. In this paper, we introduce a novel, domain-independent ``cake'' representation for game levels over time which implicitly encodes dynamic information. We present a novel level generation approach Playtrace Reconstructive Partitioning (PRP) specifically developed for this cake representation. We compare against six state-of-the-art PCG approaches in the game domain of \textit{Sokoban}, and find that our approach can generate valid levels without sacrificing solution diversity. We believe our cake representation more neatly encodes the implicit dynamic nature of games compared to existing representations, which allows for our domain-agnostic level generation algorithm PRP. --- ### Dynamic Online Processor-Native Inference for State Estimation Authors: Orestis Kaparounakis Published: 2026-07-13 Categories: eess.SP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.12095v1 Sensor-rich data-driven applications increasingly use Bayesian approaches to infer latent states of dynamic systems from noisy sensor measurements and physical models. Yet the computation of the likelihood remains an essential bottleneck for accurate posteriors and performant inference. This paper presents a Bayesian filtering technique that uses processor-native uncertainty tracking for both uncertainty propagation and inference. The technique implements deterministic hierarchical importance restructuring through a native operation, giving deterministic latency and bounded memory use for arbitrary models written as program code. Benchmarks across three nonlinear state-space systems compare the approach against particle filters and Monte-Carlo-based likelihood estimators. The technique enables deterministic approximate filtering with as high as 805$\times$ average speedup against direct Monte Carlo work at matched result quality for model evaluation, and Pareto-dominant accuracy-latency trade-offs for posterior inference while remaining competitive in RMSE with baseline particle filters. --- ### Sparse Autoencoders for Interpretable Out-of-Distribution Detection Authors: Ayush Karmacharya, Luke Luschwitz, Lucia Romero, Yanan Niu, Joseph Campbell Published: 2026-07-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.12094v1 Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce overconfident predictions for inputs that deviate from their training data, leading to significant degradation in performance. While many OOD detection methods focus on the final output layer, they neglect the rich hierarchical information present in intermediate network layers. This paper introduces a novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from these intermediate activations. We find that in-distribution (ID) and OOD data activate distinct sets of these sparse features. We propose a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes. Our post-hoc detection method not only achieves state-of-the-art performance on standard OOD detection benchmarks, but yields interpretable insights into how distribution shift affects learned representations. --- ### Causal Supervision of Attention for Affective Behaviour Analysis Authors: Nemanja Rašajski, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12091v3 The \textit{11th Affective Behaviour Analysis in-the-wild Competition} includes the Multi-Task Learning Challenge, where participants develop a unified framework for Valence-Arousal Estimation, Expression Recognition, and Action Unit Detection. The challenge lies in learning emotion-related representations that generalize across subjects while remaining robust to spurious factors such as identity, illumination, pose, and demographic variation. To aggregate features extracted by a pre-trained backbone into a compact representation for prediction, attention mechanisms selectively weight the most informative facial regions. However, these attention weights can still capture dataset-specific correlations rather than genuine affective cues. To address this limitation, we propose an attention pooling framework that combines causal supervision with cross-covariance regularization of attention components, encouraging subject-invariant attention and non-redundant representations that improve generalization. Our method achieves $CCC_{VA}=0.5123$ for VA estimation on the official validation set, together with $F_{EX}=0.3116$ and $F_{AU}=0.3974$ for expression recognition and action unit detection, respectively, resulting in an overall $P$ score (the sum of the individual task metrics) of $1.2214$. --- ### CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform Authors: Gustavo H. Santos, Aline Viana, Thiago H Silva Published: 2026-07-13 Categories: cs.CL, cs.CY, cs.MA, cs.SI arXiv: https://arxiv.org/abs/2607.12086v1 Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an interactive LLM-assisted urban simulation platform that scales to city-size populations, exposes agent behavior for inspection, supports empirical validation, and generates mobility patterns that better match real-world spatial, temporal, and semantic distributions. Instead of invoking large language models for every agent action, CityBehavEx combines established human mobility models with fine-tuned cross-encoders that estimate semantic alignment between agent profiles, schedules, and activity transitions. This design enables large-scale simulations, as demonstrated in a case study of 100,000 agents over 75 days in under one hour on a single consumer GPU. The platform allows users to define simulation regions, launch experiments, inspect trajectories and activity traces, debug unrealistic behaviors, and validate generated routines against real-world mobility, time-use, and semantic metrics. --- ### Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking Authors: Niranjan Kumar M, Balaji Nagarajan, Karthik Nair, Faysal Satter, Nithin Surendran Published: 2026-07-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12085v1 Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality. Although LLM-as-a-judge methods provide scalable alternatives to human evaluation, production deployment introduces challenges in governance, reproducibility, cost, schema consistency, traceability, and reliability. We present GenAI Evaluation, a governed, configuration-driven pipeline for large-scale evaluation of retail conversational systems. It processes production chatbot logs through normalization, sharding, asynchronous execution, and schema-constrained LLM scoring. The framework evaluates helpfulness, truthfulness, clarity, tone alignment, and translation-specific dimensions. Selective re-evaluation processes only incomplete, malformed, or schema-invalid records, while schema locking, versioned configurations, validation logs, and record-level provenance support auditability. The framework processes approximately 50,000 records daily and has evaluated more than two million interactions. Validation used 12,980 stratified-random human-labeled records from four trained annotators. Classification covered 14 intents, 156 sub-intents, 18 major domains, and 129 sub-domains. The pipeline achieved a macro F1 score of 0.93 and 89% human-acceptability accuracy for translation. --- ### The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline Authors: Milos Suvakovic, Dom Marhoefer, Glenn Grant-Richards, Aidan Pinero Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12079v1 Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expanded voxel selection (10K->15K), substitution of GPT-2 medium for GPT-1 as the beam-search proposal model, and GPU-accelerated bootstrap training, achieving mean METEOR = 0.149 and BLEU-1 = 0.200 across three held-out narratives for subject UTS03 -- an 11% relative METEOR gain over our replication baseline. Second, we introduce fMRIFlamingo, which maps BOLD activity to a frozen Llama-3.2-1B with trainable gated cross-attention layers via a learned brain tokenizer and a Perceiver Resampler. Despite achieving 42.86% Top-1 accuracy on a 1-in-100 ranking task, well above chance, a blind control ablation with zeroed fMRI inputs yields near-identical scores, revealing that apparent decoding success is driven primarily by the frozen language prior rather than by neural input. These results demonstrate that high-capacity language models do not inherently improve fMRI decoding and can actively obscure failures without rigorous blind-control evaluation. --- ### Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations Authors: Samer Saab, Chaouki Abdallah Published: 2026-07-13 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.12077v2 Multi-agent language-model (LM) systems often determine which agents communicate, yet routing is usually treated as an implementation detail. We ask whether routing itself determines whether a population converges on a shared convention or fragments into persistent cliques. We study open-weight agents spanning 1.1B-32B parameters in a controlled naming game, tracking both emitted labels and full first-token preference distributions over the allowed labels. Similarity-based routing can isolate emerging conventions and sustain fragmentation even when every agent interacts in every round. Matched controls show that this effect is not explained solely by uneven participation or model-family-specific score preferences: random rematching and policies that connect disagreeing groups improve coordination when partner-label history is retained, but not when it is absent. Exposure alone is nevertheless insufficient, as some mixed-model populations remain divided despite frequent cross-family interaction, although the same models coordinate homogeneously. Trajectory and controlled-history analyses further distinguish reaching consensus from maintaining it. Finally, ARC-Challenge and MMLU experiments show that routing changes how correct and incorrect answers propagate without reliably improving accuracy. These results establish the runtime interaction graph as a causal design variable whose effects depend jointly on memory, model response, and population composition. --- ### NEEDL-Bench: Dataset for Swiss Needle Cast and Stomata Detection in Microscopy Images Authors: Benjamin Blake, Declan McIntosh, Jürgen Ehlting, Nicolas Feau, Joey B. Tanney, Alexandra Branzan Albu Published: 2026-07-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12076v1 We present NEEDL-Bench, a microscopy detection benchmark for Swiss Needle Cast (SNC), a fungal disease of Douglas-fir trees. Douglas-fir is a keystone species of major ecological and economic importance as a softwood timber resource, and SNC affects productivity by forming sexual reproductive structures (pseudothecia) that emerge through the gas exchange pores (stomata) of the needles, thereby blocking gas exchange and compromising needle function. To date, there is no dataset for automatic computer vision detection of these structures, despite computer vision being well poised to standardize and viably scale severity measurements. To address this, we present NEEDL-Bench, a dataset of 3250 annotated images from 1082 Douglas-fir needles, annotated for both keypoints and bounding-box detectors. This dataset exhibits a challenging collection of features, including blur, poor object contrast, small objects of interest, and occlusions. To better capture both the nominal distribution of the data and the full breadth of rare structures, we present two distinct evaluation splits: either random sampling from the collected images or sequential sampling to maximize structural diversity. We evaluate multiple popular keypoint and bounding box methods for detection on this dataset as a baseline and observe a maximum F1 score of 0.8479, suggesting significant potential for gains from future development on this problem. Further, we find that larger models generally do not show commensurate gains in performance on this dataset, indicating that improvements on this problem will not come from scaling laws but rather from domain-specific inductive biases. --- ### Calibrated Selective Prediction Using Deep Ensembles for ROI-Based Thyroid Nodule Ultrasound Classification Under Dataset Shift: A Retrospective Evaluation Authors: Md. Sadibul Hasan Sadib, Md. Mohayminul Mukit, Rahmatul Kabir Rasel Sarker, Tahmid Alam Tamim, Md. Monir Hossain Shimul Published: 2026-07-13 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.12075v1 Background: Deep learning models can classify thyroid nodules on ultrasound, but reliable clinical decision support also requires calibrated probabilities, uncertainty estimation, and selective referral, particularly under dataset shift. Methods: We developed a calibrated deterministic five-member deep ensemble for ROI-based thyroid nodule classification and selective image-based triage. TN5000 was used for model development, five-fold cross-validation, member-wise vector-scaling calibration, and fold-specific threshold selection. TN3K served as an independent external dataset-shift evaluation. The framework used ConvNeXt-Tiny with squeeze-and-excitation attention, ensemble-mean malignancy probability, and mutual information (MI) as an ensemble-disagreement score. A three-tier policy assigned images to No-FNA suggestion, FNA recommendation, or radiologist review. Results: On pooled out-of-fold TN5000 predictions, the ensemble achieved AUC-ROC 0.9395, AP 0.9715, ECE 0.0088, and Brier score 0.0813. At 50% nominal MI retention, 7.2% of cases received a No-FNA suggestion, 39.9% an FNA recommendation, and 52.9% radiologist review, with 98.3% No-FNA NPV and 99.83% malignancy capture. On TN3K, AUC-ROC decreased to 0.7870, AP to 0.7254, ECE increased to 0.1899, and Brier score to 0.2281. The frozen TN5000 policy assigned 83.7% to review, 1.0% to No-FNA, and 15.3% to FNA recommendation. No malignant image entered the No-FNA pathway, but FNA-recommendation PPV fell to 76.6%. Conclusion: The framework showed strong internal discrimination and calibration, but limited external threshold transportability. Selective prediction may help identify images unsuitable for automated triage, but local recalibration, threshold validation, and prospective clinical evaluation are required before deployment. --- ### Beyond Parallel Tracking: Interactive Multi-Feature Fusion Drives Semantic Reconstruction from Non-invasive Brain Recordings Authors: Boda Xiao, Xiran Xu, Songyi Li, Yujie Yan, Xihong Wu, Heping Cheng, Jing Chen Published: 2026-07-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12071v2 Continuous semantic reconstruction from non-invasive neural recordings remains limited by the representational mismatch between semantic feature spaces and neural coding patterns, which severely impedes cross-modal alignment between high-noise neural signals and target semantic features. Prior semantic decoders have predominantly relied on static lexical representations or dynamic contextualized representations in isolation. This single-dimension approach inevitably leads to severe information loss, as it fails to account for the human brain's capacity to integrate stable word attributes and dynamic contexts simultaneously. To bridge this gap, this study introduces a multi-feature fusion framework for non-invasive semantic reconstruction, systematically benchmarking two integration approaches: linear Naive Concatenation and non-linear Multi-Head Cross-Attention. Within this framework, our approach complements static lexical representations (W2V) with dynamic contextual representations (GPT) via an interactive gating mechanism to facilitate cooperative processing during language comprehension. Evaluated through extensive semantic reconstruction and text generation experiments, our framework reveals a robust performance hierarchy: Cross-Att > Concat > GPT > W2V. Crucially, the non-linear cross-attention fusion method achieves state-of-the-art performance, demonstrating that neural language decoding benefits from simulating the collaborative modulation between contextual information and core lexical attributes rather than depending on isolated individual features, while also offering a viable non-invasive brain-to-text decoding method. ---