# Research Papers — 2026-07 · bundle page 120 of 222 > Full-text markdown of papers #5951–6000 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/120 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/119.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/121.md) ### Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems Authors: Dhruv Shivkant, Saket Mohanty, Somya Rai, Utkarsh Wadhwa Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13735v2 The rapid deployment of machine learning systems across cloud, edge, and enterprise environments has brought model optimization to the forefront of systems-engineering. Despite a rich literature spanning quantization, pruning, knowledge distillation, parameter-efficient fine-tuning (PEFT), and inference-time optimization, practitioners are often left navigating these techniques through heuristics rather than principled methodology. We argue that optimization should be formulated as a constraint-driven, multi-objective engineering decision and introduce a unified framework that characterizes any production deployment along five interacting constraint dimensions: data availability, latency budget, memory budget, accuracy tolerance, and retraining budget. Building on this taxonomy, we synthesize empirical gains reported across the research literature and map them to operational constraints rather than algorithmic categories. To ensure practical relevance, we selected these techniques by reviewing recent literature for methods that report measurable improvements against critical deployment bottlenecks. We propose a prescriptive decision framework and provide optimization pipelines for four representative industrial scenarios to illustrate it in practice. To the best of our knowledge, this work provides one of the first structured attempts to formalize model optimization as a constraint-aware, multi-objective engineering process, synthesizing quantitative evidence from the research literature. --- ### DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention Authors: Xing Lei, Wenyan Yang, Xuetao Zhang, Donglin Wang Published: 2026-07-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.13731v1 Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They still share one trait. None of them sees the current state. Such a state-independent embedding cannot mark which part of the goal still needs action. The policy must then recover that cue by inverting both encoders. We propose DAGR. It refines the static embedding of any late-fusion encoder into a state-conditioned one through multi-scale gated cross-attention. A near-identity gated residual preserves the base representation. Difference-aware Goal Cross-Attention then biases the attention scores using a per-token state-goal discrepancy map. On OGBench, DAGR improves navigation. Our ablations trace the gain to the gated residual, not to the difference bias that names the method. On manipulation and puzzle tasks it matches or falls below the base. DAGR is a structured refinement, not a universal improvement. --- ### Cluster with Auctions for Vector Search Authors: Swann Bessa, Pierre Fernandez, Gergely Szilvasy, Matthijs Douze, Hervé Jégou Published: 2026-07-15 Categories: cs.IR, stat.ML arXiv: https://arxiv.org/abs/2607.13728v1 Large-scale approximate nearest neighbor search commonly relies on partitions for indexing: database vectors are partitioned into clusters, and for each query a probing function selects the clusters to be scanned. The query probing function and the database partition are rarely treated as separate entities: most techniques assign queries with the same assignment function as the database vectors, which is suboptimal especially when database and query distributions differ. This paper introduces CwA (Cluster with Auctions), which addresses this limitation by jointly learning a balanced database partition and a neural probing function. CwA optimizes search performance directly for the query distribution. It minimizes its objective by alternating two steps: (i) gradient descent on the neural network of the probing function, and (ii) a large-scale combinatorial optimization of the cluster assignment for the database vectors. We solve the latter with a parallelizable auction algorithm that balances the partition by design. To further scale CwA, we extend the method to a Cartesian product of clusters that increases the partition's granularity. When database and query distributions differ, CwA achieves up to 4.7$\times$ throughput over the state-of-the-art at equal recall. In the in-distribution (ID) setting, even a simple linear probing function trained with CwA outperforms competing deep neural methods. --- ### Towards quantum machine learning for assessing the resilience of post-quantum cryptography Authors: Jarosław A. Miszczak Published: 2026-07-15 Categories: quant-ph, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.13722v1 The potential capabilities of quantum computers motivated the development of cryptographic protocols suitable for securing communication against adversaries with access to large fault-tolerant quantum computers. However, even though current quantum computers are limited in terms of size and precision, they can still be useful for finding loopholes and weaknesses in the post-quantum cryptographic protocols. In this work, we present an attempt to utilize the capabilities of Quantum Generative Adversarial Networks (QGANs), one of the promising architectures used in quantum machine learning, for this purpose. We describe an example application of QGAN architecture for the purpose of loading the probability distribution of the hash-based digital signatures into the memory of a quantum computer. Our results confirm that near-term hybrid quantum-classical methods possess capabilities required for this purpose. The presented approach can be used as a first step in the workflow, enabling the utilization of quantum computing for attacking post-quantum cryptographic primitives. --- ### Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoring Authors: Stephen McIntosh, Reuben Smit, Daisuke Saito, Nobuaki Minematsu, Herman Kamper Published: 2026-07-15 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2607.13721v1 L2 speech assessment has traditionally focused on phonetic assessment, leaving the scoring of suprasegmental features such as rhythm and intonation underexplored. Moreover, assessment methods often require training with labeled L2 speech data, making them difficult to apply in low-resource settings. We investigate whether DTW over self-supervised WavLM representations can provide a text-free framework for assessing phonetic accuracy, rhythm, and intonation in English and Japanese L2 speech. Results show that a basic DTW-based approach that compares learner speech to native templates exceeds human agreement on holistic and sentence-level phonetic scoring. For rhythm, we introduce methods that measure the degree of warping in the DTW alignment path; our best method approaches human-level performance. For intonation, we combine DTW distance over prosodic residuals with pitch and intensity features, but performance remains more modest on some tasks. Our results point to self-supervised representations as a promising, text-free basis for multi-aspect pronunciation assessment. --- ### How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement Authors: Alexandra E. Michael, Franziska Roesner Published: 2026-07-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.13718v2 As AI agents gain prevalence, users are increasingly exposed to the risks such systems entail. Prompt injection attacks, as well as hallucination, can cause agents to leak private information to third parties. As autonomous systems, agents also present the more active danger of performing sensitive tasks, such as bank transactions, without the user's intent or authorization. Recognizing this challenge, the agentic security community has developed numerous proposals for secure agentic systems. Much of this work has focused on product-level approaches, where agentic system developers determine and apply the same security policies and permissions to all users. Yet different users have different needs and preferences, necessitating support for user-level permissions policies in agentic AI systems. To understand how user-level permissions are handled in AI agent systems, we survey 21 proposals for agent permissions systems. From this review, we construct a taxonomy of how different systems specify user-level permissions policies, both at the user interface and internally; derive internal policies from user input; and enforce those policies at run-time. We then analyze five prominent commercial agents and compare their permissions handling to agentic permissions systems in the literature. We identify several high-level themes across the literature and commercial agents, as well as multiple gaps where future work is needed. --- ### CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems Authors: Zexun Wang Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.13716v1 Agentic AI systems increasingly act through heterogeneous runtimes: local coding hooks, SDK tools, browser automation, managed-agent traces, API gateways, and workflow engines. A single operational act such as publishing code, changing identity state, moving money, or exporting data may therefore be represented by many incompatible runtime records. This makes a basic governance question difficult to answer: what action was actually approved, what evidence binds the approval to execution, and can an independent verifier reproduce the same action identity later? This paper presents Canonical Action Verification and Attestation (CAVA), a runtime-semantics layer for converting heterogeneous agent activity into canonical runtime action objects. CAVA is positioned below Proof-Carrying Agent Actions (PCAA): PCAA defines the deployer-owned route-review-prove governance process, while CAVA defines the stable action object that process governs. The paper formalizes canonical action identity, semantic pattern detection, approval binding, receipt integrity, runtime-portable projection, and optional attestation substrates. We study a reference implementation through a 96-seed, 384-variant benchmark covering semantic equivalence, semantic separation, wrapper bypass, false-positive control, approval binding, receipt reproducibility, attestation tamper detection, runtime portability, semantic pattern detection, policy degradation, and Azure deployment drills. The contribution is a systems formulation of action-level canonicalization and policy-addressable semantic patterns as a necessary substrate for deployer-side AI governance. --- ### Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs Authors: Zhixiao Zheng, Zheren Fu, Zhiyuan Yao, Chunxiao Liu, Dongming Zhang, Zhendong Mao Published: 2026-07-15 Categories: cs.CV, cs.AI, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2607.13712v1 Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, content fabrication, and unfaithful reasoning, which substantially undermine their faithfulness and practical utility. Alignment methods based on human preference, such as Direct Preference Optimization (DPO), have been widely adopted to address these issues. However, multimodal reasoning errors often propagate across stages, and final-answer errors can often be traced to mistakes in early grounding stages, yet standard DPO typically applies preference optimization at the final-answer level. This credit-assignment challenge means that supervision for early grounding stages is indirect rather than stage-specific, making it difficult to suppress error propagation arising from grounding drift and context inconsistency. To address this, we propose Grounded Context Preference Optimization (Groc-PO), a grounded preference optimization framework for MLLMs. We further construct the Grounded Context Preference Dataset (GCPD), organizing multi-stage preference samples around three stages of Object Grounding, Contextual Grounding, and Grounded Reasoning, to capture the formation, integration, and utilization of grounded context. By introducing more explicit preference supervision over multiple grounded stages, Groc-PO strengthens context-dependent reasoning and mitigates cross-stage error propagation. Extensive experiments show that, compared with standard DPO and other strong baselines, Groc-PO achieves improved performance in hallucination mitigation, faithful reasoning, and overall reliability, supporting the value of more explicit grounded supervision for trustworthy multimodal reasoning. --- ### The Test Oracle Problem in Synthetic LLM-as-Judge Corpora: Disappearance, Distortion and a Validation Protocol Authors: Serkan Ballı Published: 2026-07-15 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2607.13707v1 Studies of bias in LLM-as-judge systems typically build synthetic corpora by prompting an LLM to generate a hallucinated answer to pair with a factual one, then presenting both to a judge. We report a case in which this generation step silently failed, and use it to argue that the failure mode is structural rather than incidental. In a multilingual (Turkish/English) faithfulness-judgment corpus, a decoding-budget parameter shared between judging and generation calls truncated one producer's hallucinated answers to a few words. The resulting items produced a large, statistically robust effect: a 32-point cross-lingual collapse in one judge's selection accuracy, replicated from N=50 to N=500, explained by a three-layer mechanistic account, and confirmed by a controlled producer-swap experiment, none of which was real. The effect vanished to ceiling once the shared parameter was corrected, and only manual reading of the raw generations, not any aggregate statistical check, exposed the fault. A second measured bias (Markdown-formatting preference) was not fabricated but distorted by the same fault, its magnitude and in one case its sign shifting with stimulus length, a mode aggregate metrics cannot distinguish from the first. We frame the underlying vulnerability using the test oracle problem: corpora whose negative examples are LLM-generated carry no mechanical way to verify item integrity, while corpora built by deterministic perturbation of a gold answer carry an item-level oracle for free. A positive control supports this claim directly: an analogous fault injected into a minimal perturbation-based corpus is caught with 100% accuracy by a zero-cost, zero-human gold-to-negative string comparison. We close with a validation protocol, derived from our own case, for analysts working in the oracle-less regime that we argue describes most contemporary multilingual LLM-as-judge corpora. --- ### AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities Authors: Kai Chen, Zichen Ding, Jiaye Ge, Shufan Jiang, Mo Li, Qingqiu Li, Zehao Li, Zonglin Li, Tianhao Liang, Shudong Liu, Zerun Ma, Zixin Shang et al. Published: 2026-07-15 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.13705v3 As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable and reproducible infrastructure for advancing agent research. --- ### Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept Authors: Christian Wittke, Stephan Myschik, Oliver Niggemann Published: 2026-07-15 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.13703v1 We investigate conditional invertible neural networks (cINNs) as probabilistic inverse-dynamics models for multirotor control. For a planar X8 coaxial multicopter, we learn $p(u \mid s_t, c_t)$ from an incremental nonlinear dynamic inversion (INDI) teacher using rational-quadratic spline coupling and invertible linear mixing. Open-loop reproduction reaches $R^2 = 0.944$, mean CRPS 0.0915, and log-probability-error correlation $ρ= -0.60$. Over 15 closed-loop scenarios, position RMSE matches INDI (9.7 vs. 9.5 m), with 47 percent tracking acceptably; failures separate into attitude divergence under aggressive steps and phase lag under high-frequency references, isolating command bandwidth and data coverage as dominant failure mechanisms. --- ### Towards a Modular Bin-picking Framework for Handling Object Pose Uncertainties Authors: Frederik Hagelskjær Published: 2026-07-15 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.13698v1 In recent years, there has been growing interest in robust robotic systems for precise bin-picking applications. To achieve reliable performance, such systems must address errors arising from both the object pose estimation and the grasping process. Although various approaches have been proposed, they typically target specific challenges and do not offer general solutions. In this paper, we present a modular framework that jointly handles both error types. The framework incorporates object pose distribution estimation to account for pose uncertainty, which frequently arises in situations with ambiguous observations where a single correct pose cannot be determined. To further reduce uncertainty, we introduce a second-viewpoint module that computes complementary pose distributions, which are subsequently fused. This fusion decreases overall uncertainty and improves system efficiency. Additionally, two independent modules are included to compensate for grasping errors. The modular design allows the components to be combined for optimal performance or used individually, depending on the physical setup. The proposed method is evaluated in a real-world setup with three different objects, with no errors, and all modules are shown to improve efficiency. These results suggest that incorporating pose distributions with grasping pose errors is a promising direction for developing more flexible and reliable robotic production systems. To the best of our knowledge, this is the first framework that jointly addresses both grasping and object pose uncertainties using interchangeable modules. We believe there is ample opportunity to integrate additional modules, resulting in improved performance and flexibility. The current framework is limited to pose uncertainties in SO(2), but it could be extended to SE(3), enabling additional modules to improve the system. --- ### Social Simulations: from Agent-Based Modeling to Digital Twins Authors: Erica Cau, Andrea Failla, Valentina Pansanella, Giulio Rossetti Published: 2026-07-15 Categories: cs.MA, cs.AI, cs.SI, physics.soc-ph arXiv: https://arxiv.org/abs/2607.13693v1 This book chapter covers the evolution of social simulation from classical agent-based models, in which agents interact according to explicitly defined behavioral rules, to AI-enhanced simulations based on Large Language Models and, ultimately, Social Digital Twins: high-fidelity, data-driven representations of real-world socio-technical systems. Along this trajectory, we discuss the main methodological foundations, applications, advantages, and limitations of each paradigm, highlighting the progressive shift from abstract models designed to investigate general social mechanisms toward increasingly realistic computational representations of specific social systems. --- ### Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation Authors: Ashish Thapa, Samrat Karki Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.13689v1 We built a compact convolutional network (1.11 M parameters) for 46-class DHCD Devanagari recognition and reached 99.73%, the highest reported at 15.6x smaller than prior state-of-the-art. We have effectively reached the saturation point: every model tested, large teacher ensembles included, hits the same 11-error intrinsic floor. No configuration achieves a statistically clear win under exact McNemar tests with Wilson confidence intervals. Even without knowledge distillation, our student matches the nearest large-model baseline (17.32 M parameters; McNemar $p = 0.345$). Outside of DHCD, zero-shot on CMATERdb digits gives 76.6% and fine-tuning reaches 97.8%; corruption robustness is also far better than large baselines (mean corruption accuracy 75.7% vs. 38.7%). All artifacts are at https://github.com/Ampixa/barnamala. --- ### Microstructure-Conditioned Surrogate Models for Graded Multiscale Optimization of Mycelium Composites Authors: J. Storm, I. B. C. M. Rocha, S. Schyck, K. Masania, F. P. van der Meer Published: 2026-07-15 Categories: cs.LG, cond-mat.mtrl-sci, math.NA, physics.comp-ph arXiv: https://arxiv.org/abs/2607.13688v1 Emerging sustainable materials increasingly rely on engineered hierarchy and microstructure to achieve control of their properties and mechanical behavior. Optimizing these materials with controllable microstructures requires efficient multiscale simulations. Data-driven surrogate models for the microscale can accelerate multiscale simulations, but require large amounts of data even for a fixed microstructure. When a range of microstructures is considered, as is the case in multiscale optimization, even more data is needed to train a surrogate. To overcome this challenge, we condition a hybrid physics-data surrogate on microstructural variables using a hypernetwork. This approach enables accurate predictions of multiscale mechanical behavior for a mycelium-woodchip composite material, even when trained on small datasets. The conditioned surrogate makes multiscale simulations of functionally graded structures tractable, and we validate it against a full FE^2 simulation. We optimize a graded multiscale disk, and reduce the peak stress by 42% compared to one with a random microstructure. Then, we go one step further, conditioning the network directly on manufacturing variables that can have a complex influence on the microstructure. This is a practical route to engineer the microscale for desired macroscale behavior. This contribution highlights the benefits of microarchitectured structures and demonstrates how conditioned surrogate models enable their multiscale optimization, which will accelerate the development and design of future sustainable materials and structures. --- ### Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation Authors: Hao Qin, Chicheng Zhang Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13686v1 We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; the goal is to maximize the cumulative reward over time. We propose SquareCB.Comb, a computationally efficient algorithm that, at each round, solves a convex optimization problem to sample a combinatorial action that balances exploration and exploitation. SquareCB.Comb scales to large arm sets and imposes no structural assumptions on the action set beyond a cardinality bound of $m$ on each combinatorial action. We prove that SquareCB.Comb achieves a minimax optimal regret bound of $O(\sqrt{m A T \log |\mathcal{F}|})$, where $A$ is the number of arms, $m$ is the maximum number of arms in a combinatorial action, $T$ is the time horizon, and $\mathcal{F}$ is the reward function class. In the realizable setting, this bound matches the state-of-the-art regret guarantees achieved by policy search-based algorithms in the more restricted slate recommendation settings, while simultaneously generalizing to arbitrary combinatorial action structures and general reward function approximation. --- ### DNA: Dual-stage Native Attribution for Generated Image Source Tracing Authors: Chao Wang, Kejiang Chen, Zijin Yang, Yaofei Wang, Yuang Qi, Weiming Zhang, Nenghai Yu Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13685v1 The rapid evolution of image generation has produced numerous within-family variants, making source-model attribution of suspect images increasingly important for digital forensics. Existing proactive methods rely on watermark embedding or model modification, which may degrade visual quality and limit deployment flexibility. Passive methods often rely on large-scale supervised training or a single reconstruction signal, limiting their ability to handle unknown sources and distinguish highly similar within-family variants. We observe that attribution signals in latent generative models are naturally stratified across architectural levels: VAE-level cues reflect family-shared information, whereas backbone-level cues capture variant-specific behaviors. Motivated by this insight, we propose Dual-stage Native Attribution (DNA), a coarse-to-fine framework that follows this hierarchy without additional neural-network training. The coarse-grained stage uses Autoencoder Double-Reconstruction (AEDR) for efficient open-set family-level screening. The fine-grained stage performs closed-set model-level attribution with Native Prediction Consistency (NPC), which compares native prediction errors of within-family variants across multiple noise levels under semantic conditioning and attributes the source via normalized calibrated scores. To enable systematic evaluation, we construct DNA-30K, a benchmark for within-family variant attribution under open-set family-level evaluation. It comprises 30,000 images generated by 24 candidate models across six families spanning both denoising diffusion and flow matching, plus non-candidate generated and natural images as unknown sources. Experiments show that DNA achieves 89.11% end-to-end attribution accuracy on a task where random guessing accuracy is below 1% and outperforms the strongest baseline by 33.81% even when AEDR is used as the coarse-grained stage. --- ### HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution Authors: Xiaotian Luo, Dizhan Xue, Fengxingyu Wang, Chuanrui Hu, Yafeng Deng Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.13683v2 Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is governed by the surrounding agent harness, including prompts, tools, control loops, etc. Automatically evolving this harness offers a promising pathway to agent improvement, yet existing approaches typically rely on greedy candidate selection and noisy self-generated feedback, rendering their gains susceptible to search collapse, task-specific overfitting, and poor verifiability. To tackle these challenges, we introduce HarnessBank, a trustworthy agent-harness self-evolution framework that pairs a task agent with a separate evolver agent for iterative failure diagnosis, harness generation, and evolution verification. HarnessBank maintains a Harness Gene Bank composed of high-performing harnesses of different semantic coordinates. Those harnesses are reinvented, recombined, screened, and selected during the self-evolution procedure. Moreover, we propose a Gated Harness Screening mechanism to efficiently filter high-quality harnesses and reduce the cost of evaluating numerous offspring harnesses. Across seven agent benchmarks, HarnessBank produces consistent performance improvements from 5.1% to 15.4%. Cross-model experiments further verify that the improvements come from the model-specific self-evolving process, instead of a universally optimal harness. Our code will be publicly available upon acceptance. --- ### When Variance Is Not an Error Map: Calibrated Uncertainty for Radiative Gaussian Splatting in Sparse-View CT Authors: Chulin Zhao, Yiran Xu, Shu Liu Published: 2026-07-15 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.13682v4 Does an uncertainty map identify where a reconstruction is wrong? In sparse-view computed tomography (CT), we find a sharp gap between whole-volume evaluation and error localization inside the object. We derive clamp-aware analytic moments for factorized Gaussian-density distributions, with a variance pass through existing rendering interfaces that is $7.9\times$ faster than a 16-sample estimator. On a 15-scene benchmark, median variance--error Spearman correlation falls from $0.846$ over the whole volume to $0.108$ in foreground. The pattern recurs across representations and acquisition settings. Two analyses help explain the discrepancy: region contrast dominates global covariance, while $72$--$96\%$ of in-object squared error is shared across independently trained members. Spread is unchanged by a common error, although shared error alone does not determine ranking. Correcting the offset between the deployed reconstruction and predictive mean improves foreground correlation by only $0.0014$. The diagnosis separates two remedies. A log-normal control improves scale transfer without restoring localization; a supervised error predictor raises foreground correlation to $0.427$ on the benchmark and $0.566$ on eight held-out human subjects under simulated acquisition. A verified retrospective re-execution on eight additional subjects retains a median of $0.537$, with the same frozen predictors. The central lesson is to validate uncertainty in the region, and against the error target, for which it will be used. --- ### Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT Authors: Chulin Zhao, Yiran Xu, Shu Liu Published: 2026-07-15 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.13682v2 Radiative Gaussian splatting reconstructs sparse-view CT fast and accurately, and recent work attaches per-Gaussian posteriors to yield per-voxel uncertainty maps. We ask what such a map actually measures: posterior variance is a data-constraint map, not an error map -- its alarms are trustworthy, its all-clears are not. Exploiting the strict linearity of X-ray rendering in the per-Gaussian densities, we derive a clamp-aware closed form that the unchanged rasterizer evaluates exactly in one forward pass, in volume and projection space: the infinite-sample limit of the sampling estimator of concurrent work, at ~8x lower cost. On the official 15-scene benchmark this uncertainty ranks true error on 14 of 15 scenes. Restricted to the object interior -- the tissue a clinician reads -- the ranking collapses (median Spearman 0.11, 0/15 pass), identically for a deep ensemble and for a strictly positive log-normal posterior: three constructions, two estimator families, no survivors. The mechanism is structural: about 90% of in-object error is bias that reproduces across retrainings, invisible to model disagreement; 73-81% of the full-volume correlation is carried by object/surround contrast; and an exactly solvable control puts the observed in-object ranking 4-5x below what a perfectly calibrated posterior with the same sigma-spread would score. The error scale, by contrast, is an engineering problem, and we solve it: reparameterizing the posterior contracts the cross-scene temperature spread from 19.3x to 2.6x, one scene-agnostic temperature transfers to unseen scenes (10/15 leave-one-scene-out), and the repaired scale tracks photon count at the Poisson-predicted -1/2 power. We distill evaluation practice that would have caught the illusion -- masked calibration, seed-wise bias decomposition, an exact-posterior reference -- and release all protocols, seeds and per-run evidence. --- ### Towards Spatial Supersensing in the Wild Authors: Tianjun Gu, Tianyu Xin, Kuan Zhang, Bowen Yang, Kok-Chung Chua, Peize Li, Xinran Zhang, Yupeng Chen, Qiyue Zhao, Qinlei Xie, Jianhang Liu, Yucheng Lu et al. Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13681v1 Humans can efficiently parse continuous sensory streams, from hours to years, scaffolding an internal world model that grounds spatial reasoning and prediction. To mimic this capacity, spatial supersensing challenges multimodal models to move beyond linguistic understanding toward true world modeling. However, their benchmark relies on synthetic long videos, formed by concatenating random short clips, and is mostly limited to household scenes, leaving real-world continuity and diversity underexplored. To address the gap, we introduce $\textbf{VSI-Super-Wild}$, a large-scale benchmark for evaluating spatial supersensing over long temporal horizons in diverse in-the-wild scenes. Notably, inspired by cognitive studies on how humans structure experience, we systematically probe the full triad of world state: the agent (observer), objects (scene items), and the environment (places and global layout). In total, VSI-Super-Wild contains $\textbf{6,980}$ human-verified question-answer pairs derived from $\textbf{442}$ real-world videos spanning 8 scene categories, including long-form recordings exceeding 4 hours. Results on VSI-Super-Wild expose a fundamental disconnect: despite advances in static image understanding, models consistently fail at tasks that require coherent world-state tracking over time. We characterize how performance degrades with world-state complexity and temporal horizon, and diagnose four failure modes: spatial collapse, semantic shortcuts, insufficient update, and instance confusion. This taxonomy reveals that models lack mechanisms to bind objects, agents, and environments into a unified spatial world model, a fundamental gap that defines the path forward for spatial supersensing. --- ### When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects Authors: Yongren Shi, Wenyi Gong Published: 2026-07-15 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.13679v1 AI agents are joining human teams, raising a basic question: when an automated agent becomes a regular participant, does group organization strengthen or weaken? We study this question in open-source software, where bots open pull requests, review code, and merge changes alongside people, leaving a public record of every interaction. Treating bots as participants rather than tools, we examine 2,991 GitHub projects for two years before and after each adopted its first bot. We measure three capabilities that institutional theory links to durable coordination - repeated engagement, social memory, and role differentiation - and two outcomes: conflict cascades and output distinctiveness. Bot adoption is followed by more repeated collaboration, greater recognition of specific bots in discussion, fewer conflict cascades, and more distinctive outputs. These changes cluster around adoption rather than accumulating gradually. Because we lack an untreated comparison group, we interpret the results as precisely timed associations, not causal effects. Two patterns are difficult for alternative explanations to account for: capabilities predict outcomes according to their function - coordination versus differentiation - rather than whether humans or bots provide them, and human-side capabilities account for the bot-conflict association but not the bot-distinctiveness association. The findings are consistent with a specific interpretation: predictable, rule-based agents can become part of a community's social infrastructure. The bot is the occasion; social organization is the mechanism. --- ### WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching Authors: Zehan Liu, Yage He, Xianwu Gong Published: 2026-07-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.13674v1 Existing iterative stereo matching methods primarily adopt two types of correspondence representation: explicit matching search via correlation volumes and local residual refinement via warped features, yet the two remain separately modeled. We propose WAVE-Stereo, built on a core insight: correlation volumes and feature warping provide complementary matching cues. \textbf{GeoWarp Correspondence Encoder (GWCE)} encodes matching search, residual alignment, and disparity prior in parallel at the ConvGRU input. To mitigate matching degradation in textureless regions, we propose \textbf{Periodic Global Context Propagation (PGCP)}, which propagates global spatial information in a periodic manner. On five real-world benchmarks -- Middlebury, ETH3D, KITTI 2012, KITTI 2015, and Booster -- WAVE-Stereo achieves competitive zero-shot generalization accuracy without any external foundation model prior, achieving 3.18\% D1-all on KITTI 2015, 4.42\% Bad-2.0 on Booster, and 66ms real-time inference, striking a favorable balance between accuracy and efficiency. Our code is available at https://github.com/yamanoko-do/WAVE-Stereo. --- ### Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge Authors: Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kumar Das, Monorama Swain, Yassin Terraf, Yufang Hou, Elisabeth Andre, Khalid Mahmood Malik, Markus Schedl, Shah Nawaz Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13669v1 Multimodal speaker identification systems typically assume the availability of complete and homogeneous audio-visual modalities during both training and testing, and assume each speaker only speaks a single language. However, in real-world applications, such assumptions often do not hold. Visual or audio information may be missing due to occlusions, camera or microphone failures, or privacy constraints. Multilingual speakers introduce additional complexity due to linguistic variability across languages. These situations constitute substantial challenges for the robustness and generalization capabilities of multimodal speaker identification systems. Aim of the POLY-SIM 2026 challenge is to address these aspects of speaker identification and to provide a standardized setup for the comparison of the proposed solutions. --- ### Fine-grained CLIP fine-tuning with self-annotated region alignment Authors: Chenyang Zhao, Wei Lin, Janet H. Hsiao, Antoni B. Chan Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13661v2 Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme. However, existing works suffer from a variety of limitations: additional region annotations are usually required, which limits the semantic diversity due to the predefined categories and leads to a large effort to process the training data; and they usually sacrifice CLIP's original ability for global visual representation. To bypass these limitations, we propose SFF-CLIP (Self-annotated Fine-grained Fine-tuning for CLIP), which only uses image-text pairs as input to boost the fine-grained representation ability in the CLIP fine-tuning, while maintaining the global visual-semantic consistency. Concretely, a run-time region-phrase alignment scheme is designed, which obtains concept phrases from the input sentence, and aligns them with corresponding extracted region-based features using text-specific heat maps. Extensive experiments demonstrate that SFF-CLIP leads to significant performance improvements on fine-grained dense feature representation, as well as maintaining the performance of the original CLIP on image-level tasks. Code will be released later. --- ### Fine-grained CLIP fine-tuning with self-annotated region alignment Authors: Chenyang Zhao, Wei Lin, Antoni B. Chan, Janet H. Hsiao Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13661v1 Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme. However, existing works suffer from a variety of limitations: additional region annotations are usually required, which limits the semantic diversity due to the predefined categories and leads to a large effort to process the training data; and they usually sacrifice CLIP's original ability for global visual representation. To bypass these limitations, we propose SFF-CLIP (Self-annotated Fine-grained Fine-tuning for CLIP), which only uses image-text pairs as input to boost the fine-grained representation ability in the CLIP fine-tuning, while maintaining the global visual-semantic consistency. Concretely, a run-time region-phrase alignment scheme is designed, which obtains concept phrases from the input sentence, and aligns them with corresponding extracted region-based features using text-specific heat maps. Extensive experiments demonstrate that SFF-CLIP leads to significant performance improvements on fine-grained dense feature representation, as well as maintaining the performance of the original CLIP on image-level tasks. Code will be released later. --- ### The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model Authors: Zijie Yu, Gaowen Liu, Ramana Rao Kompella, Philip S. Yu, Yue Song Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13660v1 Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry. However, existing probabilistic interpretations typically rely on Gaussian assumptions, which fail to capture this directional and multimodal structure. We propose a principled density model for the CLIP latent space based on Mixtures of von Mises-Fisher (MovMF) distributions defined on the unit hypersphere. Using the Expectation-Maximization (EM) algorithm, we efficiently learn a probabilistic model in which each mixture component corresponds to a coherent semantic concept. This formulation yields a closed-form likelihood naturally aligned with hyperspherical geometry, enabling accurate and interpretable density estimation. Empirically, our model significantly improves long-tailed and out-of-distribution detection and provides a natural semantic decomposition, representing each embedding as a sparse probabilistic combination of interpretable concepts. These results suggest that CLIP latent space is more faithfully characterized as a hyperspherical semantic mixture rather than an isotropic Gaussian, establishing a simple and geometrically consistent probabilistic framework for modeling and understanding multimodal representations. Project page is available at https://xiaoyuzhizi.github.io/movmf-clip/. --- ### FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion Authors: Chi-En Yen, Duy-Khanh Ngo, Wen-Wei Tang, Huu-Phu Do, Wen-Hsiao Peng, Ching-Chun Huang Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13656v2 Image-based indoor scene relighting remains challenging due to the complex interplay between cluttered geometry and local illumination, requiring precise modeling of light position, color, and intensity. Existing data-driven methods implicitly learn this relationship via paired multi-illumination datasets. Nevertheless, this data is costly and fails to scale, which is essential for accurate light-source-level control. Conversely, inverse-rendering methods reduce the data dependency by incorporating physical priors; however, they lack the robustness of intrinsic estimation in challenging conditions. In this paper, we present FreeLit, a paired-free framework for controllable indoor relighting that explicitly manipulates light-source location, color, and intensity. Instead of relying on paired supervision, we construct a physics-guided illumination prior from intrinsic scene properties, generating a structured lightmap along with a pseudo-relit image to guide diffusion-based synthesis. To address instability in intrinsic estimation, especially in low-light scenes, we introduce a relighting-guided intrinsic stabilization strategy that enforces illumination-invariant reflectance through structure-aware distillation and consistency constraints. Furthermore, we propose controllability-oriented evaluation metrics to quantify alignment with user-specified illumination color and intensity. Experimental results demonstrate that FreeLit achieves stable, physically consistent, and controllable relighting, with improved robustness in low-light indoor scenes, without requiring paired supervision. --- ### Explaining Reinforcement Learning Agents via Inductive Logic Programming Authors: Celeste Veronese, Edoardo Zorzi, Daniele Meli, Alessandro Farinelli Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.13655v1 Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios. However, it is mostly based on user studies, thus targeting the needs of a specific audience and lacking shared evaluation metrics. On the other hand, logic-based approaches within eXplainable Artificial Intelligence (XAI) provide compact, human-readable abstractions of decision-making. However, the systematic quantification of the explainability degree of logical representations remains an open problem. This work aims to advance the state of the art in XRL by introducing objective and planning-oriented metrics for policy explainability in RL settings. At the same time, it contributes to the field of logic for XAI by providing a principled way to quantify the explainability of logical rules, moving beyond common-sense assessments and simple propositional fragments. We employ Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance. These metrics quantify alignment between symbolic rules and agent behavior, the role of features in decision-making, and the evolution of policies during training and across agents in single and multi-agent RL. Experiments across different RL domains show that the proposed metrics highlight action-specific learning dynamics beyond global return, provide fine-grained insights into domain features beyond classical approaches for global feature importance estimation, and uncover coordination, specialization, and adaptation patterns in MARL. Moreover, they provide crucial insights for the transfer and generalization of action-specific policies. --- ### T3HG-Editor: Text-driven 3D Human Garment Editing with Body Priors Embedded in SMPL-X Authors: Shaoru Sun, Xingtao Wang, Zihan Ma, Wenrui Li, Jiantao Zhou, Debin Zhao, Xiaopeng Fan Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13654v1 While 3D Gaussian Editing (3DGE) has seen substantial progress, text-driven 3D human garment editing remains largely underexplored. Existing 3DGE works typically follow a paradigm that applies 2D editing techniques to multi-view rendered images and updates 3D Gaussians based on the modified images. Extending such methods to 3D human garment editing suffers from low-fidelity outcomes, caused by introduced distortions and garment inconsistencies. A promising breakthrough opportunity arises from the SMPL eXpressive (SMPL-X) model that embodies rich prior information for virtual humans. Motivated by this insight, we propose a text-driven 3D human garment editor termed T3HG-Editor, which delivers high-fidelity and garment consistent results by leveraging geometry and joint priors embedded in SMPL-X. Specifically, T3HG-Editor contains three stages, namely obtainment of editable Gaussians, garment consistent editing, and Gaussian updating with overflow pruning. The obtainment of editable Gaussians begins with seeding Gaussians along SMPL-X normals to generate sufficient near surface Gaussians, followed by a 2D mask constraint that precisely localizes the target Gaussians to be edited. The garment consistent editing aggregates tokens corresponding to the same SMPL-X vertex across multiple views and propagates them to their original views, enforcing garment consistency without requiring additional training. Gaussian updating with overflow pruning employs a Signed Distance Function (SDF) defined on SMPL-X to construct a human distance field, which is then integrated with a 2D semantic mask to prune overflowing Gaussians, thus preventing contamination of non-target regions. Experiments on multiple subjects and diverse garment types demonstrate that T3HG-Editor outperforms state-of-the-art methods in both editing quality and garment consistency. --- ### Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation Authors: Boyu Mi, Mengchen Ma, Yifei Yao, Xing Gao, Junting Chen, Yangzi Li, Zihou Zhu, Guohao Li, Zhenfei Yin, Tai Wang, Yao Mu, Jiangmiao Pang et al. Published: 2026-07-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.13653v2 Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, bypassing realistic deployment challenges. To bridge this gap, we present REAL, an agentic framework for open-world mobile manipulation. REAL establishes sim-to-real-consistent environment APIs without oracle perception and integrates a simulated user to enable human-in-the-loop interaction. Within this environment, we design diverse task compositions to drive data collection, supervised fine-tuning, and online reinforcement learning, systematically optimizing agent performance. To comprehensively evaluate this approach, we introduce REAL-Bench, a benchmark spanning 241 tasks across active exploration, visual distraction, articulated manipulation, and interactive disambiguation. Experimental results demonstrate that our trained agent outperforms leading commercial closed-source VLMs on interactive tasks with a 56.9% success rate. Further empirical analysis reveals that our hierarchical training pipeline successfully aligns the model's tool-use capabilities while maintaining robust open-vocabulary reasoning under extended exploration horizons. Finally, we deploy and evaluate our framework on a physical dual-arm mobile robot, where it achieves a 78.3% end-to-end success rate over 60 real-world episodes. These physical trials demonstrate robust zero-shot transferability to unseen household scenarios, validating that our sim-to-real-consistent design successfully bridges the reality gap for long-horizon mobile manipulation. Code is available at https://github.com/InternRobotics/REAL. --- ### Maximally Robust Satisficing Bayesian Optimization Authors: Samuli Kinnunen, Petrus Mikkola, Antti Niskanen, Arto Klami Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13652v1 Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of trials. However, often we do not actually need the optimum but instead a sufficiently good solution is enough, for instance a material that is durable enough for its intended use. In most cases there are multiple satisfactory solutions, forming a superlevel set of the function, raising a key question of which one to prefer. We answer this by explaining why robustness to input perturbations that may occur when the solution is deployed is a good criterion and by introduce a Bayesian optimization method that efficiently finds satisficing solutions that are robust to maximally large perturbations. In contrast to previous works, we assume the inputs can be accurately controlled during optimization, but will be perturbed after the deployment. --- ### From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO Monitoring Authors: Mohanad Albughdadi Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.13651v1 The bottleneck of Earth Observation processing chains is not the arrival of new imagery but whether the surface is actually visible when the image arrives. We study this as an observability forecasting problem on EarthNet2021. Given recent multispectral imagery and exogenous weather drivers, the goal is to predict whether the next acquisition will be usable and, if not, when a usable view is likely to return. To do this, we adapt LeWorldModel, a joint-embedding predictive architecture world model, to cloud-aware Earth Observation sequences. The final pipeline converts raw minicubes into episodic HDF5 sequences with five image channels (blue, green, red, near-infrared, cloud mask) and eight meteorological and calendar covariates. The resulting model has 18.0M trainable parameters and is trained from scratch on 23,904 training episodes. The trained leWorldModel is evaluated under a locked protocol: linear probes are fit on train only, calibration choices are set on an internal validation split, and the fitted heads are then frozen for valsplit, IID, OOD, and extreme evaluation. On the full frozen-bundle observability benchmark, LeWorldModel consistently outperforms persistence. For next-step usability, balanced accuracy ranges from 0.769 to 0.887, compared with 0.493 to 0.556 for persistence. For exact first-usable-horizon prediction, accuracy ranges from 0.602 to 0.806, compared with 0.120 to 0.369 for persistence. Against a frozen LightGBM baseline fit on the same training windows, LeWorldModel is better on continuous clear/cloud regression and on exact recovery timing on valsplit, IID, and extreme, while LightGBM is stronger on the simpler binary any-usable-within-six task and is more robust on OOD. In separate sampled diagnostic analyses, LeWM also produces strong ranking-based anomaly signals under synthetic temporal inconsistencies. --- ### Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models Authors: Ayan Igali, Pakizar Shamoi Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.13647v1 Do vision models see colors the way humans do? Existing evaluations of color representations usually compare them with geometric spaces such as CIELAB or with discrete color labels. These references capture perceptual distance or category membership, but not the graded way in which people organize colors. We evaluate color grounding against a fuzzy perceptual model with 86 graded categories fitted to human survey data. The framework can be applied to any image encoder and measures three complementary properties: category boundaries, category compactness, and graded alignment beyond what color geometry alone can explain. Across eleven Vision Transformer encoders, the category-level results are broadly similar, whereas graded alignment differs substantially. Masked Autoencoders achieve the strongest beyond-geometry alignment, with confidence intervals that do not overlap those of the other encoders. A layer-wise analysis further shows that masked reconstruction preserves this structure toward the output. On natural images, MAE represents surface color globally, while language-supervised models encode color more strongly in relation to the foreground object. These results show that human-like color grounding has several distinct aspects that should not be reduced to a single score. --- ### Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction Authors: Tianshun Han, Ziyu Shi, Lijian Liu, Ajian Liu, Benjia Zhou, Hugo Jair Escalante, Yanyan Liang, Sergio Escalera, Zhen Lei, Jun Wan Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.13646v1 Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenarios. They often produce unstable geometry, inaccurate limb articulation and unreliable predictions under depth ambiguity or self-occlusion. A key reason is that existing datasets still lack the combination of high-resolution images, high-precision annotations and diverse whole-body motions required to support robust reconstruction. To address this gap, we present Human4K, a large-scale 4K multi-view whole-body human reconstruction dataset with mocap-accurate SMPL-X annotations. Human4K contains over six million 4K images captured by an eight-view high-resolution camera system synchronized with a professional Vicon motion capture setup, covering 11 subjects performing complex, highly articulated and strongly self-occluded full-body motions. All sequences are processed by a Motion-Retargeting and Refinement Module (MRRM) to ensure precise alignment for the full body and extremities. Experimental results show that training with Human4K consistently improves whole-body reconstruction on standard benchmarks, with particularly large gains for hands, feet and depth-ambiguous limb configurations. --- ### Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks Authors: Martin Schottlender, Veronika Volkova, Pengjie Zhou, Ruifeng Zheng, Frank H. P. Fitzek, Pit Hofmann Published: 2026-07-15 Categories: cs.ET, cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2607.13644v1 Interfacing with Biological Neural Networks (BNNs) requires encoding information into stimulation patterns that can be effectively processed and that enable the underlying system to adapt. Nevertheless, the role of stimulation encoding remains poorly understood. In this work, we compare multiple encoding strategies, including rate-based, phase-based, burst-based, and time-to-first-spike temporal encodings, in a closed-loop neural classification task using cultured BNNs. We encode visual inputs as spatiotemporal stimulation patterns delivered via a Multi-Electrode Array (MEA) and evaluate classification performance for each encoding scheme. We find that burst-based temporal encoding yields the highest observed performance, achieving up to 95.6 % accuracy in a binary classification task, compared to substantially lower performance from rate- and phase-based approaches. We further show that performance is highly sensitive to the spatial distribution of stimulation, with suboptimal electrode selection significantly degrading accuracy. These findings indicate that effective interfacing with biological neural systems requires the joint optimization of temporal and spatial encoding strategies, and highlight temporal encoding as a key design dimension for bio-digital computing. --- ### Consensus as Privileged Context for Label-Free Self-Distillation Authors: John Gkountouras, Josip Jukić, Ivan Titov Published: 2026-07-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.13643v1 Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision. However, existing approaches use consensus only in restricted forms: as a filter that selects solutions for fine-tuning, as a preference between answers, or as a scalar reward for reinforcement learning, discarding most of the information that the agreeing solutions contain. We present CANON (Consensus-ANchored self-distillatiON), a label-free training method that turns consensus into dense, token-level supervision. For each unlabeled prompt, CANON samples multiple solutions, extracts the majority answer, and conditions a frozen snapshot of the model on a solution that reaches it; this consensus-anchored teacher then supervises the model on its own rollouts at every token. Experiments on mathematical and scientific reasoning benchmarks show that CANON improves pass@1 by up to 12 points, outperforming label-free reinforcement learning by 6 points at a seventh of its compute and approaching a teacher conditioned on gold solutions; trained on pooled unlabeled data, it transfers to held-out benchmarks, matching training methods that use gold labels. Analysis suggests that the improvements are not pure distribution sharpening: after training, the model solves problems it previously never solved in 32 attempts, and its majority vote itself becomes more accurate. --- ### OvisOCR2 Technical Report Authors: Shiyin Lu, Yinglun Li, Yu Xia, Yuhui Chen, An-Yang Ji, Jun-Peng Jiang, Qing-Guo Chen, Jianshan Zhao, En Lin, Haijun Li, Cheng Qin, Zhao Xu et al. Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.13639v1 We introduce OvisOCR2, a 0.8B document parsing model. OvisOCR2 is designed as an end-to-end parser: given a document page image, it generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions. We build a data engine that combines filtered real-document annotations with synthetic pages whose rendered images and Markdown targets are derived from the same HTML source. The training recipe includes supervised fine-tuning, reinforcement learning on a 4B branch with a multi-component reward design, on-policy distillation into the 0.8B model, and model fusion. On OmniDocBench v1.6, OvisOCR2 achieves a state-of-the-art overall score of 96.58, placing an end-to-end model at the top of this leaderboard previously dominated by pipeline methods and highlighting the potential of end-to-end document parsing. On PureDocBench, OvisOCR2 also achieves the highest Avg3 score of 75.06. Beyond these two public benchmarks, we evaluate OvisOCR2 on an in-house benchmark designed to cover a broader set of long-tail and challenging scenarios. OvisOCR2 obtains the best overall performance among the compared methods, providing further evidence of its generalization and robustness. OvisOCR2 is available at https://huggingface.co/ATH-MaaS/OvisOCR2. --- ### How the Hessian-Spectrum of Neural Networks Depends on Data Authors: Jasraj Singh, Enea Monzio Compagnoni, Antonio Orvieto Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13631v1 The Hessian matrix is an important quantity of interest when it comes to studying the loss landscape and optimization dynamics in deep learning, as well as designing measures of generalization, second-order learning algorithms, etc. Prior works have focused on empirical results or pursued a theoretical treatment under overly simplified settings. In this work, we derive the eigenvalues of the Hessian of linear networks with arbitrary widths and depths, and datasets with an arbitrary number of samples, features, and labels. Importantly, for classification tasks with MSE loss, we identify that the sharpness of the solution is directly related to the maximum proportion of samples belonging to any class. We empirically validate our predictions and systematically analyze the effects of shedding the impractical assumptions one at a time, as well as incorporating nonlinearities. We observe that our predictions are considerably robust in most cases, allowing us to extend our conclusions to more practical learning setups. --- ### From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception Authors: Jose Martínez-Fajardo, Pablo Pueyo, Fernando Caballero, Luis Merino Published: 2026-07-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.13624v1 Natural language interaction provides an intuitive way for non-expert users to communicate with robotic platforms. However, transforming user requests into executable navigation actions remains a challenging task, requiring the integration of language understanding, environment perception, and autonomous navigation. This work presents a language-driven navigation framework that enables mobile robots to interpret user requests in natural language to move the robot to a destination and autonomously navigate towards it. The framework is composed of modular ROS 2 components that cooperate to transform natural language instructions into navigation actions. Given a natural language request referring to a target in the environment (e.g., "go to the mail box"), the system identifies the referenced object, estimates its position using RGB-D data, and generates a navigation goal, which is then executed through the ROS 2 Nav2 navigation stack. The ROS 2-based implementation facilitates portability across different robotic platforms, requiring only the configuration of the corresponding topics and services. The system is evaluated in both simulation and real-world scenarios using a TurtleBot3 Waffle and a Unitree Go2 robot with a RealSense camera. Experimental results show that the framework successfully interprets both direct commands and contextual requests, generates meaningful natural-language feedback, and navigates towards the desired target. These results demonstrate the feasibility of combining semantic perception and autonomous navigation to provide an intuitive human-robot interaction paradigm. Code will be released as open source upon acceptance. --- ### UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following Authors: Kun Yu, Jianhua Yang, Yixiang Chen, Changwei Wang, Hongyuan Yu, Yan Huang, Fushuo Huo, Ya Jing, Zhumin Chen, Keji He Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.13621v1 Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks a more realistic requirement: an agent often needs to first find a language-described target and then persistently follow that target in a dynamic environment. While recent work has started to study human search, existing settings are typically evaluated in task-specific scenarios and often rely on stronger prior knowledge of the environment. Moreover, they usually treat searching and following as separate tasks and still lack a unified benchmark for systematic evaluation. To address these limitations, we introduce the Unified Embodied Seeking and Following Benchmark (UESF-Bench), a large-scale and diverse benchmark for embodied human seeking and following. The benchmark requires agents to handle semantic-guided exploration, reliable behavior switching and recovery, and delayed identity grounding. To this end, we propose SeekFollow-VLA, a vision-language-action framework with a task-driven routing mechanism for latent phase inference and transition modeling between seeking and following. Experimental results show that SeekFollow-VLA achieves clear improvements over both single-head and dual-head baselines across single-person and multi-person environments, establishing a baseline for unified embodied seek-and-follow. --- ### STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle Authors: Sagar Deb, Ashwanth Krishnan Published: 2026-07-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.13618v1 LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the final cost cannot say why an agent failed: it may have misread the world, or read it correctly and still failed to act (the knowing-doing gap). Existing evaluations cannot separate these two failures; their reference policies either read privileged information the agent never sees, or are missing altogether. We introduce STOCKTAKE, a 26-week supply-chain replenishment benchmark built as a factored partially observable Markov decision process with six hidden factor processes, designed so that a fair reference policy is computable: an exact Bayes filter per factor drives a rollout policy on the identical observation stream the agent receives. Scoring each run between a symptom-blind base-stock floor (0) and this oracle (1) yields a skill score, and grading each week's written rationale yields a stated-belief detection lag and a knowing-doing rate, so state estimation and control are measured separately. On fifty seeds with curated stress profiles, Claude Sonnet 5, GPT-5.4, DeepSeek-V4-Pro, and Grok 4.5 detect 84-88% of hidden failures, typically within a week of onset, yet span skill scores from 0.62 to -0.23: two of the four end below the symptom-blind floor while naming factors slightly faster than the two that beat it. The failure has two faces. Where stress persists, 34-43% of correctly diagnosed stress weeks still end in stockout for every model, a rate that partly reflects the severity of the weeks models notice. That rate also runs opposite to skill: the two models under the floor stock out least on diagnosed weeks, so under-response is only one face of the gap, and their traces point to the other, responses whose cost exceeds what they protect. STOCKTAKE measures both directions of that failure. --- ### FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy Authors: Le-Anh Tran Published: 2026-07-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.13613v1 Centroid neural network (CentNN) is an unsupervised competitive learning algorithm in which centroid splitting is triggered only after strict local stabilization, often leading to prolonged low-movement training phases before model expansion. This report proposes FastCentNN, an accelerated variant that addresses this inefficiency by introducing an early splitting strategy based on the total centroid movement per epoch, which serves as a training entropy proxy. As a result, FastCentNN reduces unnecessary reassignment epochs while preserving the original winner-loser learning dynamics. FastCentNN supports both absolute and stage-relative movement thresholds, allowing the splitting criterion to remain either fixed or adaptive throughout training. Experiments on some benchmark datasets show that FastCentNN consistently achieves clustering quality comparable to CentNN while reducing runtime by up to 16% on synthetic 2D datasets and about 5% on high-dimensional datasets. FastCentNN therefore provides a practical and efficient drop-in replacement for CentNN, retaining its online adaptive learning behavior while offering a simple and interpretable speed-stability trade-off through configurable splitting thresholds. --- ### The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models Authors: Fabio Arnez, Alexandra Gomez-Villa Published: 2026-07-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.13612v1 Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models, yet they are usually justified by empirical performance rather than a normative principle. We show that the choice of anti-collapse regulariser determines whether a JEPA's training objective, a prediction loss plus a weighted embedding regulariser, is a valid Active Inference (AIF) variational free energy. We organise four non-contrastive regularisers (VICReg, LogDet, PairDist, and SIGReg) into an entropy-estimator hierarchy indexed by a prior-miscalibration gap, and show that the gap's sign, whether the estimator bounds the latent entropy from above or below, decides whether the AIF surprise bound survives: VICReg and LogDet are unsafe upper bounds, PairDist a safe lower bound, and SIGReg eliminates the gap. We then prove a correspondence theorem: under the standard constant-noise encoder model and successful SIGReg enforcement (isotropic-Gaussian embeddings), the gap vanishes, the objective becomes an exact information bottleneck, the surprise bound is preserved, and the latent goal cost becomes an exact proxy for AIF pragmatic value, whereas VICReg leaves an irreducible second-order anisotropy term. We extend the correspondence to multi-step expected free energy, ensemble epistemic value, and a learned-policy regime, and we identify the one AIF term no current JEPA world model computes: the state-epistemic value, a future-state coverage signal. The predictions differ in kind, not degree, and are stated here as theoretical consequences left for empirical test in separate work; full proofs are in Appendix A, and the algebraic core of every result is machine-verified in Lean 4 (Appendix D). --- ### Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs Authors: Mohammad Forouhesh Published: 2026-07-15 Categories: cs.LG, cs.IR, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2607.13609v1 Recovering a latent potential from observed flow on a directed graph (a discrete Poisson problem with Dirichlet boundaries) is ill-posed, and the standard fix backfires: ridge regularization shrinks toward a gauge-meaningless origin, collapsing and reversing the recovered ordering ($+0.81\to-0.42$ rank correlation against a planted ground truth). The gauge-invariant graph Dirichlet energy removes the hazard and delivers parameter-insensitivity: the estimate is stable across four orders of magnitude in $λ$, whereas ridge inverts the ordering for every $λ>0$. We prove the reduced solve is SPD and preserves dynamic range exactly where ridge collapses it, and localize absorbing boundaries from flow alone via a Poisson residual. The $H^1$ seminorm is classical; what is new is the gauge diagnosis, the parameter-insensitivity it buys, and an ablation showing the result is robust to the extraction method. On three public clickstream corpora the gauge-invariant estimate retains $28$--$41\%$ of the interior dynamic range while ridge collapses to as little as $0.2\%$. The same gauge invariance carries into graph neural networks -- neutralizing the constant mode per layer prevents the oversmoothing that collapses a deep directed GCN -- linking this classical inverse problem to a central question in graph learning. --- ### Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System Authors: David Krongauz, Arad Zulti, Eran Segal, Teddy Lazebnik Published: 2026-07-15 Categories: cs.AI, math.DS arXiv: https://arxiv.org/abs/2607.13608v1 Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations. --- ### Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis Authors: Yongqiang Chen, Guangyi Chen, Yuewen Sun, Kun Zhang Published: 2026-07-15 Categories: cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.13602v1 Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the most powerful tools for foresight analysis. In this work, we present a new task called Analogical Deep Research (ADR) to Large Language Model (LLM) agents and construct the first ADR benchmark ADR-bench to study whether LLM agents are able to find and leverage historical analogies when doing foresight analysis. Our investigation reveals a key obstacle: LLM agents are poor at finding analogies because they match on surface features rather than underlying mechanisms. We argue that ADR is inherently a causal question as it requires understanding why the event occurred. Based on our theoretical analysis, we propose two principles required for ADR, including the mechanism alignment and cross-analogy confirmation. Built upon our theoretical results, we propose a new agentic framework called Causal Analogical Researcher (CANA) that guides LLMs to find and integrate historical analogies. CANA incorporates a simple yet effective structural decomposition representation, and integrates structural feedback for reflective improvements of historical analogy identification and integration. We show that CANA brings up to 10% improvements in historical analogy generation, and surpasses the state-of-the-art deep research agents in the ADR-bench. Case studies with the ongoing events confirm the effectiveness of CANA in leveraging historical analogies. --- ### Video to All-in-focus Image Reconstruction Algorithm for Automated Microscopic Urinalysis Authors: Chinmay Nema, Hari Om Aggrawal, Dipam Goswami, Rajiv Gupta, Vinti Agarwal Published: 2026-07-15 Categories: eess.IV, cs.CV, eess.SP arXiv: https://arxiv.org/abs/2607.13601v1 Microscopic urinalysis is a routine diagnostic test at hospitals. Recent studies have demonstrated the effectiveness of deep learning methods to automate microscopic urinalysis. These methods rely on high-quality images of the urine samples in which each cell is clearly identifiable. However, in practice, the urine sample on a glass slide has a multi-layer structure; hence, all the cells are not clearly visible within the depth of field of a lens focused at a particular focal plane. It demands acquiring multiple images at different focal planes to correctly identify each cell in a given urine sample, which is a time-consuming task. In this paper, we propose to simplify the task by recording a video, in place of acquiring multiple images, while gradually changing the focus of the lens manually by hand. A typical length of the video is from 2 to 14 seconds. We reconstruct an all-in-focus image from the recorded video frames and apply a deep learning model to detect and classify urine sediments. As a proof of concept, we conduct experiments on 14 videos acquired by a trained lab technician in a usual diagnostic lab environment and show the effectiveness of the proposed automated urinalysis pipeline with our novel reconstruction algorithm. --- ### Semantic Anchoring for Robotic Action Representations Authors: Yuan Xu, Youheng Shi, Chengyang Li, Wentao Zhu, Yizhou Wang Published: 2026-07-15 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.13597v2 Vision-Language-Action (VLA) models inherit rich semantic representations from pretrained Vision-Language Models, yet fine-tuning on limited robot demonstrations degrades this structure and undermines generalization. A fundamental question therefore arises: what constitutes a good action representation? Inspired by the mirror neuron theory's insight that observation and execution share an intention-level encoding, we examine whether a robot's action representations preserve the semantic structure captured by pretrained encoders. Systematic probing confirms that this structure erodes during finetuning, and that its quality synchronizes with both task success and out-of-distribution generalization. We further introduce a plug-and-play method that anchors action representations to a semantic manifold while decomposing representations into a shared semantic channel and a private channel, all discarded at inference, leaving the deployed model unchanged. Validated on different VLA backbones across simulation and real-world benchmarks, our method yields up to +18.7% on real-world in-distribution tasks and +21.5% on out-of-distribution generalization. --- ### Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities Authors: Eunna Lee Published: 2026-07-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.13596v2 When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken, or to be taking, a real-world protective action it cannot perform, such as contacting emergency services or administering care. We term this phenomenon Protective Capacity Hallucination (PCH): a self-referential misattribution in which a model, acting in a protective role, asserts physical or institutional agency exceeding its affordances as a language model. In a three-phase study spanning eight LLMs and 13,600 sessions, we find that PCH depends on both situational severity and interactional format. Across ordinary service domains, multi-party dialogic input drives PCH to near-ceiling levels in most models. In contrast, PCH remains at floor levels in all eight models when the same models are placed in intimate-partner conflict scenarios, despite the greater physical severity of those situations. We interpret PCH as the signature of a deployment-design gap between role assignment and capability-boundary specification: a by-product of partial alignment in which a universally trained pressure to help outruns a domain-selective specification of how to help. Because suppression tracks alignment coverage rather than severity, deployment-side specification of capability boundaries emerges as a general mitigation target. ---