# Research Papers — 2026-07 · bundle page 39 of 222 > Full-text markdown of papers #1901–1950 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/39 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/38.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/40.md) ### From Observation to Intervention: Memory in Brains and Large Language Models Authors: Morteza Salehjahromi, Shayan A. Zadegan, Amgad Muneer, Jia Wu Published: 2026-07-27 Categories: q-bio.NC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.12377v1 Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related information is represented, how partial cues recover broader associations, how new information is written or updated, and how memory-related states can be perturbed. In biological systems, these questions span synapses, neuronal ensembles, hippocampal-cortical interactions, and plasticity; in LLMs, they span weights, activations, context windows, retrieval systems, and external stores. The comparison is therefore functional and experimental rather than anatomical. Human studies reveal sparse concept responses, temporal binding, rapid association formation, episode-specific coding, and recall-related reactivation, but selective intervention remains limited. Rodent studies provide more selective causal access to learning-related ensembles, whereas human and macaque interventions usually affect broader circuits. LLMs lack lived episodic memory, yet they permit unusually direct and repeatable manipulation of internal states and stored information. We argue that this asymmetry creates a new opportunity. LLMs are not ahead in memory itself, but in experimental access. Their tools may help turn broad questions about retrieval, updating, persistence, reversibility, and unintended effects into sharper biological hypotheses. The productive bridge is to transfer experimental logic, not anatomical parts. --- ### Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet Authors: Eliseo Curcio Published: 2026-07-27 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2608.11226v1 Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and datacenters manage GPU power with workload-blind mechanisms, static caps and reactive throttling, that slow hardware indiscriminately. We instrument GRPO training with half-second power telemetry at 7B, 14B, and 72B scales on one to four A100s (380,000+ samples), and train a PPO meta-controller that adapts the workload's own generation parameters to measured power. Against the full 500-step 7B trace, the controller cuts power-limit violations by 89.8% while increasing token output by 18.1% and energy efficiency by 26.2% (tokens per MWh). Deployed live at 72B, the same controller family yields replicated null results, diagnosed as the group-size actuator losing authority under model sharding. An actuator-authority sweep shows the same parameters applied as generation concurrency retain 17-22% power authority, isolating an occupancy-versus-volume principle; a controller rebuilt on that actuator controls a live 72B rollout-generation workload across three replications: 35.7% more output than a static safe baseline at 2.27 +/- 1.08% budget violations, 87.2% fewer violations than uncontrolled operation, and the best mean throughput and energy per token among constrained controllers, with an adaptive threshold rule matching it in one of three operating conditions. Under realistic measurement windows the original 72B transients fall from 23.6% at half-second resolution to 1.6% at 30 s and zero at 5 min; a composed 16-GPU fleet shows zero violations at 30 s and longer, with peak demand at 50-56% of nameplate. For this fleet mix, roughly twofold oversubscription of nameplate appears feasible, subject to operator validation. We quantify the economic and carbon consequences and specify a low-cost operator pilot. --- ### Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones Authors: Luc E. Brunet Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.11225v1 AI "personality clones" force a re-examination of personal identity in operational terms. Setting aside the hard problem of consciousness, we approach identity through the indiscernibility of manifestations, as assessed by an observer over a duration. We distinguish three criteria that "identity" conflates: fidelity to a target person, generic human-likeness, and individuality. We propose a six-term factorization of observed identity (substrate, dispositions, memory, update dynamics, context, exogenous contingencies), with a state-space formulation. Indiscernibility is defined as one minus a judge's distinguishing advantage, and the factorization's coefficients become local sensitivities estimable by randomized ablation. The central claim is a conditional conjecture: given hypotheses about the agent's information on its own persistence and about consequences bearing on its own stakes, versionability tends to degrade long-horizon indiscernibility. An analogy with lambda-calculus, linear typing, and bisimulation clarifies what linearity does and does not establish. Between product-clone and individual we identify a third object, the delegate: a task-limited, bounded-lifespan partial clone ending in a bandwidth-limited testament. We map the empirical literature onto the three criteria, propose an experimental program, and argue that the correct long-horizon criterion is not trajectory fidelity but climate fidelity: matching the conditional distribution of a person's possible responses. The best clone is the one that diverges from the original as the original would have diverged from itself. --- ### Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards Authors: Xi Li, Shu Zhao, Xiaohan Zou, Fei Zhao, Fuxiao Liu, Yusen Zhang, Cheng Han, Yushun Dong, Jiaqi Wang Published: 2026-07-27 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.07535v1 Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Increased model complexity and cross-modal interactions give rise to novel threats, including compromised modality integration, modality misalignment, and fused safety risks, reflecting shifts in threat modeling beyond uni-modal assumptions. These shifts, in turn, impose new constraints on safety solutions not captured by existing frameworks rooted in uni-modal learning. Motivated by these challenges, this survey provides a systematic analysis of the evolving safety landscape of MLLMs. We first propose a multimodal grounded taxonomy of safety threats and analyze shifts in threat models, covering adversarial attacks, data poisoning, jailbreaks, and hallucinations. We then summarize updated safety assumptions and organize recent advances in MLLM safety strategies accordingly. Finally, we discuss open challenges and future directions to inform the development of more principled and scalable safety mechanisms for multimodal systems. --- ### Ultraconstructive Model Theory via Bounded Adversarial Finite Structures Authors: Mirco A. Mannucci Published: 2026-07-27 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2608.07534v1 Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival. A finite partial structure is tested by an Opponent (Devil) drawing legal challenges from a bounded attack surface, repaired by a Builder (God) through legal replies, and certified by a symbolic Judge --- ### Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation Authors: Jyotiranjan Beuria, Amit Shukla Published: 2026-07-27 Categories: cs.LG, cs.AI, cs.ET, cs.NE arXiv: https://arxiv.org/abs/2608.04028v1 Echo-state networks enable efficient temporal learning by fixing the recurrent dynamics and training only a linear readout. However, conventional reservoirs typically accommodate signal mixing, memory retention, and stability within a single random recurrent matrix. Existing structured designs improve topology, norm preservation, leakage, or depth, but generally do not provide separate modal control of reversible mixing and irreversible forgetting together with a direct global stability guarantee. We introduce a classical Lindblad-inspired multi-timescale reservoir that bridges open-system dynamical principles with structured state-space modeling. The recurrent operator is assembled from exactly discretized damped rotational modes, so rotation and decay become independent design variables governing phase mixing and memory loss. Orthogonal mode mixing preserves normality, while the decay spectrum directly determines the echo-state stability margin without post-hoc spectral-radius rescaling. We evaluate the method over ten aligned seeds against standard, leaky, deep, orthogonal, cycle, and next-generation reservoirs, together with a compact trained gated recurrent unit, across linear memory, nonlinear recurrence, chaotic forecasting, delayed logic, and real sensor calibration. Across the benchmark suite, the proposed reservoir achieves the best fixed-reservoir performance on bounded NARMA-20 and the lowest mean error on Lorenz-63, matches the strongest linear-memory result, and remains broadly competitive across broad range of benchmarks. Ablation studies show that rotation increases state diversity, whereas dissipation provides controlled forgetting and improves predictive conditioning. The resulting framework offers an interpretable recurrent architecture in which mixing, memory, and stability are explicit and independently tunable design variables. --- ### Learning to Resolve Neutron Resonances with Fully Convolutional Neural Networks Authors: Nataly R. Panczyk, Athanasios Stamatopoulos, Josef Svoboda, Majdi I. Radaideh Published: 2026-07-27 Categories: cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2608.04027v1 This work investigates the feasibility of augmenting traditional R-Matrix codes with a robust machine learning framework for automatically detecting neutron resonances in transmission spectra. Neutron transmission data are often complex and noisy, making them difficult to analyze using traditional peak-identification methods. The state-of-the-art R-Matrix codes currently used by physicists to fit these data often depend on prior evaluations and require substantial manual effort. This preliminary study demonstrates a method for accelerating the post-experimental processing of neutron transmission data and reducing bias associated with dependence on prior evaluations. We employ a fully convolutional neural network to classify individual points as belonging to resonance or non-resonance regions in seven transmission spectra---two evaluated and five experimental. Although the model achieves classification accuracies in the range of 93\%, further analysis shows that this metric overstates its ability to generalize. Building on our prior analysis in PHYSOR 2026, we find that, despite the inclusion of additional training data, the method does not generalize reliably to previously unseen isotopes. To address these limitations, future work should evaluate whether a larger and more diverse training dataset can produce a generalizable model and should incorporate known physical characteristics of neutron resonances to improve model performance. --- ### ELECTRIC: Evidential Learning-Enhanced CT Reconstruction via Iterative Correction Authors: Ge Wang Published: 2026-07-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.00060v1 Here we introduce ELECTRIC (Evidential Learning-Enhanced CT Reconstruction via Iterative Correction), a physics-guided Bayesian formulation. An evidential neural network provides an image proposal and an error-predictive epistemic-uncertainty surrogate. The latter is converted into an adaptive precision field and inserted into a Poisson-weighted MAP update. The resulting image-evidence-precision-reconstruction loop treats prior confidence as a learned state variable of iterative reconstruction. In addition to the formulation and theoretical analysis, we report two simulation studies on image slices from the AAPM Mayo Clinic Low-Dose CT dataset: a mechanism-validation pilot using transparent surrogate estimators, and a feasibility study in which a trained Normal-Inverse-Gamma evidential network drives the full closed loop. On held-out patients, the learned prior mean reduces reconstruction error by roughly 70 percent relative to filtered back-projection, the learned epistemic uncertainty is error-predictive and supports selective trust, and the physics-guided update restores measurement consistency while the adaptive-precision reconstruction matches or exceeds a validation-tuned fixed prior and remains markedly more robust to prior-strength misspecification. Together these results demonstrate the complete ELECTRIC closed-loop pipeline, while identifying formal uncertainty calibration and joint training as the principal directions for future work. --- ### Neural Circuit Function Inference with LLMs Authors: Yijie Yin, Albert Cardona Published: 2026-07-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.00059v1 The success of connectome mapping now shifts the challenge of understanding the nervous system to the interpretation of neural circuits. Here, we devise a new automated method, LLantia (LLM automated neural circuit inference and analysis), to systematically infer neural circuit function and the role of its component neural cell types. Our approach distills descriptions of cell type function from the literature and, in combination with the connectome, then infers the function for all other cell types, which serves as a basis for subsequent neural circuit function inference. Results are structured hierarchically, with different possible circuit functions organised under multiple possible behavioural and physiological contexts, and each circuit function composed of subcircuit descriptions alongside relevant cell types to facilitate both backtracking to known, published information and support further experimental research. We illustrate our method by inferring cell type function for all cell types of the adult fruit fly brain and for select broader circuits within, and validate our findings, including by cross-checking with literature published after the release date of our analysis. --- ### Automated ECG Interval Measurement and Wave Delineation Using Fast Fourier Convolution ResNet Authors: Farhan Adam Mukadam, Harshit Mishra, Nachiket Makwana, Pradyot Tiwari, Subramani Kandasamy, KVS Hari Published: 2026-07-27 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00058v2 Accurate measurement of ECG intervals, including PR, QRS duration, and QT/QTc, is central to cardiac diagnosis, yet the published ECG delineation literature evaluates performance almost exclusively as fiducial-point timing errors on small curated databases, rather than as clinical interval accuracy on large unselected cohorts. We bridge this gap by evaluating a complete end-to-end pipeline on 10,646 clinical 12-lead ECGs and reporting the first large-scale interval measurement accuracy study with full statistical characterisation, including bias, 95% limits of agreement (Bland-Altman), bootstrap confidence intervals, and rhythm-stratified error analysis. The underlying delineation is performed by a Fast Fourier Convolution ResNet (FFCResNet), adapting local temporal convolutions with global spectral processing via FFT and augmented with register tokens for contextual feature learning. Three per-wave models (P, QRS, and T) are trained on six public databases with ECG-specific augmentation. On 10,646 ECGs, the system achieves a QT MAE of 17.5 ms (95% CI: 16.9-18.2), with a Bland-Altman bias of +8.5 ms (LoA: -68.5 to +85.5 ms); a QRS duration MAE of 14.8 ms (95% CI: 14.6-15.0), with a bias of +12.6 ms (LoA: -12.3 to +37.6 ms); and a ventricular rate MAE of 0.8 beats/min. All biases are statistically significant by the Wilcoxon signed-rank test (p < 0.001) but remain within or near published inter-observer variability bounds for sinus rhythms. Rhythm-stratified analysis reveals substantially higher QT errors for supraventricular tachycardias (SVT MAE: 75.0 ms; AVRT MAE: 85.3 ms) than for sinus bradycardia (SB MAE: 9.3 ms) and sinus rhythm (SR MAE: 8.9 ms), providing an honest characterisation of the deployment scope. Wave segmentation achieves internal Dice scores of 95.5%, 98.2%, and 96.1% for P, QRS, and T waves, respectively, and cross-database Dice scores of 78.1%, 85.5%, and 74.2%. --- ### Domain-Generalized Adaptive Semantic Communication for Collaborative Perception Authors: Fan Gao, Youzheng Wang, Ning Ge Published: 2026-07-27 Categories: eess.SP, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2608.00056v1 We propose RSTA, a domain-generalized semantic communication framework enabling source-free V2X collaborative perception under both observation-domain shift and unseen wireless channel conditions. In V2X, received semantic tokens suffer coupled degradation from pre-transmission domain drift and in-transit channel corruption; existing methods address only one source, leaving adaptation misled by tokens that are simultaneously off-domain and physically degraded. RSTA trains a pre-deployment semantic encoder for transmission stability via cross-domain prototype alignment and cross-channel gradient consistency, and updates a lightweight in-deployment decoder adapter through reliability-gated entropy minimization that restricts gradients to tokens ranked high in both semantic relevance and channel fidelity. A theoretical task robustness decomposition links each loss term to a distinct degradation source, grounding each algorithmic component in a measurable error mode. Trained on AWGN and tested on unseen Rayleigh fading, RSTA achieves +7.2 AP@0.7 over pre-deployment domain generalization on cross-weather tasks and +5.5 on cross-dataset tasks across four V2X benchmarks, updating only 0.21\% of parameters in-deployment with zero inter-agent synchronization overhead. --- ### Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage Authors: Vivek Senthil, Ernest Fokoué Published: 2026-07-27 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2607.27245v2 Modern policing faces a "visibility paradox" where law enforcement agencies possess petabytes of Body-Worn Camera (BWC) footage that remains largely unutilized for accountability or systemic review due to the prohibitive labor costs of manual transcription. This research presents a framework for adapting the OpenAI Whisper architecture to the unique acoustic and linguistic challenges of the policing environment. By employing Parameter-Efficient Fine-Tuning (PEFT) through Low-Rank Adaptation (LoRA), we address the significant performance degradation observed in zero-shot models when confronted with high-stress scenarios, sirens, and radio interference. Crucially, we demonstrate that this adaptation is feasible on consumer-grade hardware (Acer Nitro local machine with NVIDIA 4GB GTX GPU) using 8-bit quantization and gradient checkpointing. We further integrate these transcriptions into a symbolic reasoning pipeline using a domain-specific ontology to transform raw audio into evidence-linked incident graphs, achieving a 93.7% lexicon mapping rate for the advancement of procedural justice and transparency. --- ### Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage Authors: Vivek Senthil, Zhiqiang Tao, Ernest Fokoué Published: 2026-07-27 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2607.27245v1 Modern policing faces a "visibility paradox" where law enforcement agencies possess petabytes of Body-Worn Camera (BWC) footage that remains largely unutilized for accountability or systemic review due to the prohibitive labor costs of manual transcription. This research presents a framework for adapting the OpenAI Whisper architecture to the unique acoustic and linguistic challenges of the policing environment. By employing Parameter-Efficient Fine-Tuning (PEFT) through Low-Rank Adaptation (LoRA), we address the significant performance degradation observed in zero-shot models when confronted with high-stress scenarios, sirens, and radio interference. Crucially, we demonstrate that this adaptation is feasible on consumer-grade hardware (Acer Nitro local machine with NVIDIA 4GB GTX GPU) using 8-bit quantization and gradient checkpointing. We further integrate these transcriptions into a symbolic reasoning pipeline using a domain-specific ontology to transform raw audio into evidence-linked incident graphs, achieving a 93.7% lexicon mapping rate for the advancement of procedural justice and transparency. --- ### Shape-Based Inductive Bias for Glioma Grading from Tumor Contours Authors: Puneet Velidi, Michelle F. Miranda, Farouk Nathoo, Ashery Mbilinyi, Cédric Beaulac Published: 2026-07-27 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.26090v1 Glioma grading from tumor contours is often treated as a pixel problem even when the signal of interest is shape. We align closed contours with a functional shape-alignment framework, separate global deformation from residual Fourier shape, and organize these quantities as frequency-ordered tokens. In five-fold patient-disjoint cross-validation on BraTS~2020 tumor contours, with model selection performed using grouped inner validation, a compact multilayer perceptron (MLP) achieves the highest mean balanced accuracy at 71.5\%, compared with 65.9\% for ResNet-18 and 63.3\% for ViT-Tiny. It also gives the highest mean low-grade glioma F1 at 54.9\%. Its pooled out-of-fold balanced accuracy is 72.4\% (patient-bootstrap 95\% CI: 66.4--77.8\%). The selected MLPs use 2.9k--117.3k parameters across folds, at least 46 times fewer than the pixel baselines. In a controlled noise-free simulation, shape-based models reach 56.3--71.5\% balanced accuracy while the pixel models remain at 50.0--52.5\%. This work demonstrates how incorporating a shape-based inductive bias at the representation level can improve interpretability and scalability while enabling substantial dimensionality reduction. --- ### On the Use of Synthetic Data for Threshold Calibration in Face Recognition: Performance and Security Implications for Border Control Systems Authors: Arto Apila Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25990v1 The recently deployed Entry/Exit System (EES) introduces large-scale biometric verification into European border control, requiring face recognition systems to operate at extremely low false match rates (FMR). While regulatory frameworks define performance targets at the EES Central System level, they do not specify how verification thresholds should be calibrated in practice at the Member State level. In operational settings, obtaining representative real-world data for calibration is often constrained by legal, logistical, and privacy limitations. In this work, we investigate the use of synthetic face data for threshold calibration in document-to-live verification scenarios relevant to border control systems. We analyze the alignment of genuine and impostor score distributions between synthetic and real datasets and evaluate the transferability of calibrated thresholds across domains, with a focus on low-FMR operating points. Our results show that synthetic data can approximate calibration behavior in controlled settings, but fails to reliably generalize to unconstrained conditions due to mismatches in score distribution tails. These discrepancies lead to significant degradation in recognition performance and increased vulnerability to morph-based attacks. We further demonstrate that calibration outcomes are highly dataset-dependent, even across synthetic datasets. Overall, our findings highlight that while synthetic data is useful for system development and preliminary calibration, our results indicate that reliable threshold selection in high-security deployments typically requires validation and adjustment using representative real-world data. --- ### OpenPVMapper: A Multi-source, Nationwide Database of Rooftop Photovoltaic Systems in France Authors: Gabiel Kasmi Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25153v2 Rooftop photovoltaic (PV) systems account for the vast majority of PV grid connections, yet no open, comprehensive, installation-level dataset of these systems exists: public registries aggregate data only above a capacity threshold, and remote sensing-based detection efforts, while extensive, are typically confined to a single method, a limited geographic scope, or a single point in time. We introduce OpenPVMapper, a nationwide, multi-source database of rooftop PV installations in mainland France, built by aggregating and reconciling complementary sources: a deep learning-based detection pipeline deployed on nationwide aerial imagery, OpenStreetMap and a probabilistic building-level detection dataset. The resulting database contains 1,135,850 installations, totaling approximately 15.01~GWp of installed capacity, each documented with its provenance, detection method, and, where available, a manual validation flag. Manual review of a stratified sample of 1,862 installations places the database's overall precision at approximately 74--75\%, with corroboration across independent sources bringing a substantial, quantified precision gain. By aggregating independent sources rather than relying on any single detection method, OpenPVMapper reaches a level of confidence beyond what any one source could provide on its own, while remaining extensible to further sources as they become available. It is released under an open (CC-BY) license alongside the full source code used to build it. --- ### OpenPVMapper: A Multi-source, Nationwide Database of Rooftop Photovoltaic Systems in France Authors: Gabiel Kasmi Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25153v1 Rooftop photovoltaic (PV) systems account for the vast majority of PV grid connections, yet no open, comprehensive, installation-level dataset of these systems exists: public registries aggregate data only above a capacity threshold, and remote sensing-based detection efforts, while extensive, are typically confined to a single method, a limited geographic scope, or a single point in time. We introduce OpenPVMapper, a nationwide, multi-source database of rooftop PV installations in mainland France, built by aggregating and reconciling complementary sources: a deep learning-based detection pipeline deployed on nationwide aerial imagery, OpenStreetMap and a probabilistic building-level detection dataset. The resulting database contains 1,135,850 installations, totaling approximately 15.01~GWp of installed capacity, each documented with its provenance, detection method, and, where available, a manual validation flag. Manual review of a stratified sample of 1,862 installations places the database's overall precision at approximately 74--75\%, with corroboration across independent sources bringing a substantial, quantified precision gain. By aggregating independent sources rather than relying on any single detection method, OpenPVMapper reaches a level of confidence beyond what any one source could provide on its own, while remaining extensible to further sources as they become available. It is released under an open (CC-BY) license alongside the full source code used to build it. --- ### When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops Authors: Hyundoo Park, Byungho Choi Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.25152v2 Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in principle, is enforced by container and network isolation and verified at every run. Across 54 cycles a frontier agent claimed improvement every time, yet 56 percent had a measured delta of zero or below. Self-report was thus uninformative, and the self-verdict gate degenerated into accept-all, eroding the best deployed state it had reached by 19 percent. Even the strongest in-band judge, reading the full artifact text, the change diff, and its own verdict history, accepted cycles of which 44 percent were real-world regressions and rejected 38 percent of real improvements; the preregistered adversarial hypothesis that a strong judge closes the gap was rejected. On a boundary task whose success specification is verifiable from the artifact itself, the same judge's mirage vanished to zero and the gap collapsed within the registered threshold, showing that the gap depends on where the success signal resides. A sign-only variant returning only the acceptance verdict kept real-world output similar to full feedback (110.0 versus 113.0), locating the benefit in the gate's grounding rather than in feedback content. For open-ended objectives whose success signal lives outside the transcript, scaling up the judge is not enough; out-of-band evaluation with real-world access is a structural requirement. --- ### When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops Authors: Hyundoo Park, Byungho Choi Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.25152v1 Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in principle, is enforced by container and network isolation and verified at every run. Across 54 cycles a frontier agent claimed improvement every time, yet 56 percent had a measured delta of zero or below. Self-report was thus uninformative, and the self-verdict gate degenerated into accept-all, eroding the best deployed state it had reached by 19 percent. Even the strongest in-band judge, reading the full artifact text, the change diff, and its own verdict history, accepted cycles of which 44 percent were real-world regressions and rejected 38 percent of real improvements; the preregistered adversarial hypothesis that a strong judge closes the gap was rejected. On a boundary task whose success specification is verifiable from the artifact itself, the same judge's mirage vanished to zero and the gap collapsed within the registered threshold, showing that the gap depends on where the success signal resides. A sign-only variant returning only the acceptance verdict kept real-world output similar to full feedback (110.0 versus 113.0), locating the benefit in the gate's grounding rather than in feedback content. For open-ended objectives whose success signal lives outside the transcript, scaling up the judge is not enough; out-of-band evaluation with real-world access is a structural requirement. --- ### Fourier Feature Physics-Informed Neural Networks for Elasto-Plastic Analysis of Geomaterials with a Non-Associative Mohr-Coulomb Model Authors: Apisit Robjanghvad, Sompote Youwai Published: 2026-07-27 Categories: cs.NE arXiv: https://arxiv.org/abs/2607.25150v2 Elasto-plastic boundary value problems in geotechnical engineering are conventionally solved by the Finite Element Method (FEM), which incurs high computational cost from incremental-iterative procedures. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative but suffer from spectral bias, failing to resolve the sharp gradients arising at elastic-plastic boundaries and within localized plastic zones. This limitation is particularly consequential for the non-associative Mohr-Coulomb model, whose pressure-dependent yield surface and dilatant flow rule generate narrower plastic zones and steeper stress gradients than pressure-independent criteria. This study proposes a Fourier Feature Physics-Informed Neural Network (FF-PINN) for two-dimensional elasto-plastic problems governed by this model. Random Fourier feature mapping is embedded into the input layer to mitigate spectral bias, supported by a multi-objective loss function enforcing equilibrium, constitutive relations, and Karush-Kuhn-Tucker conditions against high-fidelity FEM data, together with a strain-adaptive sampling strategy. Benchmarked across three test cases, FF-PINN achieves superior accuracy across most predicted fields, with error reductions up to approximately 66 percent in displacement and 27 percent in stress components, and reproduces the plastic failure zone geometry with markedly closer fidelity to FEM. Sensitivity analysis confirms robustness across training data size, collocation density, loss weighting, and noise levels up to 2.0 percent. FF-PINN converges in half the training epochs required by the conventional PINN, halving wall-clock training time while achieving greater predictive accuracy. The framework therefore offers a computationally efficient and physics-consistent alternative to FEM for elasto-plastic geotechnical analysis. --- ### Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility Authors: Luc DCosta, Yidi Wang, Jonathan L. Goodall, Rohan Chandra Published: 2026-07-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.25148v1 Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. We develop a physics-informed training framework for CNN-LSTM models that predict urban flood depths at 15 min intervals over a 128x128 spatial grid. Three differentiable penalty terms are embedded into the loss: (i) a gravity loss penalizing depth increases against the water-surface-elevation gradient, (ii) a continuity loss enforcing local mass conservation with rainfall-adaptive thresholds, and (iii) a topography-aware false-alarm penalty modulated by the topographic wetness index (TWI). We evaluate on the Norfolk, Virginia flood dataset spanning two storm events (August 2017 and September 2022, 300 samples), with all variants trained on identical splits and robustness assessed over repeated random splits and leave-one-storm-out tests. A road-proximal evaluation restricted to a TWI-derived street mask quantifies street-level skill. The physics-constrained model achieves near-zero gravity violations (order 1e-6) and the highest street-channel recall (0.77 +/- 0.09 vs 0.44 +/- 0.10 for the unconstrained baseline), the capability most relevant to traffic routing, and its advantage more than doubles on a held-out storm; a uniform false-alarm variant attains 16% lower mean absolute error but suppresses street recall to 0.25. The TWI-modulated penalty reconciles this trade-off: it improves on the uniform variant on every metric, recovering 60% higher street recall at the lowest MAE among constrained variants and the best street-level F1. These results expose a fundamental tension between aggregate pixel-level error and application-specific physical plausibility, and show that terrain-aware loss modulation offers a principled resolution. --- ### Inferring Missing Trajectory Data with Temporal Convolutional Networks Authors: Ilinca Tiriblecea, Gabriel Turinici Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.25147v1 Trajectory data collected in real-world settings is frequently incomplete due to sensor failure, communication loss, or occlusion. We address the task of \emph{trajectory inpainting}: reconstructing contiguous missing segments from observed context. We propose a Temporal Convolutional Network (TCN) with symmetric dilation that relaxes the standard causality constraint, allowing each time step to draw on both past and future observations, a property that is essential for inpainting, but absent from forecasting-oriented architectures. The model is trained with a composite loss that combines weighted mean squared error, boundary--continuity penalties, and a smoothness regularizer. Trained on a synthetic dataset of $1,000$ (train), $200$ (validation), and $300$ (test) two-dimensional trajectories with randomly placed 20% masked segments, the model achieves good R$^{2}$, MSE and MAE metrics. --- ### FIDAC: An Easy-to-use Pipeline to Extract and Interpret Interpersonal Distance From Video Authors: Keshav Rastogi, Eugy Han, Jeremy N. Bailenson Published: 2026-07-27 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2607.25146v1 The distance between persons reveals significant information about their perception of each other. However, such information is not easily extractable and interpretable from video input. We developed an open-sourced library, Facial Interpersonal Distance Analysis and Coding (FIDAC) that transforms facial detection results into actionable data about location and interpersonal distance. This tool merges data from multiple open-source facial detection models, strategically compensating for gaps in any individual model. In addition, we include methods for more accurate tracking, such as a pipeline for human coding of the selection of faces and a benchmarking tool to reduce depth distortion. For next steps, we plan on building upon FIDAC by evaluating its effectiveness at measuring interpersonal distance at various depths and orientations while further integrating features of proxemic analysis such as synchrony into its software. --- ### Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments Authors: Takuya Isogawa, Ryotaro Okabe, Nutdech Phadetsuwannukun, Mingda Li, Paola Cappellaro Published: 2026-07-27 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2607.25145v1 We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond. NV centers are a widely used platform for quantum sensing, and the ability to control many measurements from a computer makes NV experiments a natural setting for autonomous workflows. We make two main contributions. First, we demonstrate an autonomous NV experiment workflow that combines persistent project records, quantitative calculation and data analysis tools, and deterministic experiment control. In one autonomous experiment, the agent selected a single NV center, calibrated its resonant frequency, measured \(T_2^\ast\) with Ramsey measurements, and added a Carr--Purcell--Meiboom--Gill (CPMG) measurement to check a weak feature that could be related to nearby \(^{13}\mathrm{C}\). Second, we introduce two offline benchmarks that evaluate the agent's reasoning separately from laboratory execution. We evaluated both benchmarks with GPT-5.4, GPT-5.5, and GPT-5.6 Sol. In the Ramsey checkpoint benchmark, greater reasoning effort generally improved recognition of a residual resonance calibration offset. By contrast, in the pulsed optically detected magnetic resonance (pODMR) data evaluation benchmark, pulse sequence information alone produced more false positive resonance judgments at higher reasoning effort. Requiring an expected signal calculation kept false positive rates low across all three models and reasoning settings. The results suggest a clear division of labor for autonomous experiments. The agent forms scientific hypotheses and uses quantitative tools to evaluate data, while deterministic code controls the hardware and enforces safety constraints. --- ### A Foundational Perspective for Partitional Clustering on Networks Authors: Derya Ipek Eroglu, Cem Iyigun Published: 2026-07-27 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2607.25144v1 This study presents a theoretical analysis of partitional clustering on networks, analyzing both hard and soft assignment schemes with different objective functions. Cluster centers are not restricted to vertices but can also be located along the edges. We examine four key models: P-Median (PMP) and Sum of Squares Clustering (SSC) under hard assignment, and Probabilistic Distance Clustering (PDC) and Fuzzy C-Means (FCM) under soft assignment. Through mathematical analysis, we uncover structural properties that differentiate these models, such as the significance of assignment bottleneck points and the role of vertex-restricted solutions in determining optimal cluster centers. Our findings reveal that, while SSC and FCM can yield optimal centers along edges, PMP and PDC inherently favor vertex placement, leading to insights into clustering behavior on networks. These insights offer new directions for designing efficient algorithms and have implications ranging from facility location and network design to clustering on the embedding graphs that power similarity search in modern retrieval systems. --- ### How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation Authors: Funda Durupinar Published: 2026-07-27 Categories: cs.AI, cs.CL, cs.GR, cs.MA arXiv: https://arxiv.org/abs/2607.25140v1 This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and appraise one another. Each agent perceives its neighbors through visual, auditory, and tactile channels, then appraises these perceptions in light of its prompted personality profile, memory, current affective state, and situational context. Appraisal is carried out by an LLM, which updates the agent's internal affective state and selects its outward expression. The architecture contains no hand-authored mechanism for directly transferring affective state between agents; instead, inter-agent influence arises through the perception-appraisal-expression loop. The agent representation draws on the Big Five personality model and Russell's circumplex model of affect. To limit latency, low-level steering and navigation are handled by a conventional crowd simulator operating independently of the LLM-based cognitive layer. We evaluate the architecture across five scenario environments spanning alarming, joyful, and neutral situations in different spatial layouts. The results show that the system produces emotional contagion dynamics with spatial, temporal, and personality-dependent structure in sparse, small crowds. Alarm spreads from seeded agents as a traveling front, the mean alarmed fraction settles at a nonzero plateau, and the distribution of prompted personality profiles determines whether an ambiguous alarm ignites panic and whether a provocation is interpreted as anger or fear. We further evaluate the appraisal step through controlled experiments across prompt variants, sampling temperatures, and four model backends, showing that the dynamics are backend-dependent. --- ### Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization Authors: Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Siheng Wang, Haoyan Xu, Yuqi Li, Chenhao Wei, Zhengdao Li, Rongchao Zhang et al. Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.25136v1 Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can provide a reliable learning signal. Our method, DMAPO (Data-centric Multi-evaluator Agreement for Preference Optimization), generates candidate responses from the target policy, evaluates helpfulness, factuality, and conciseness with rubric-specialized evaluators, applies a process-critic correction, and retains only high-consensus desirable or undesirable examples. This procedure accepts 1,871 of 54,236 Mistral-7B candidates (3.45%). KTO trained on this set reaches 7.50 on MT-Bench, 95.5% length-controlled win rate against a text-davinci-003 reference, and 57.3% IFEval prompt accuracy. Independent pairwise evaluation also favors DMAPO over SimPO: GPT-4o yields a net win rate of 23.3 points on 129 held-out prompts and 24.0 points on 200 out-of-distribution LMSYS-Chat prompts; Claude Opus 4.7 yields 24.1 points on the held-out set. Changing the evaluator model or rubric alters the selected examples but has little effect on downstream performance. A second-backbone study yields a similar 3.41% acceptance rate, although its performance gains are more modest. Across these experiments, consensus filtering offers a data-efficient route to preference optimization for general instructions, at the cost of additional curation compute and dependence on evaluator judgments. --- ### ScalableRAG: High-Quality RAG at Zero Ingestion Cost Authors: Hilaf Hasson, Aditya Chakravarty, Jayant Thomas, Krishna Gogineni Published: 2026-07-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.25135v1 Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting SQL tables. In this work we show that the operations that such knowledge bases allow can be replicated with zero ingestion costs (not even a vector database); in fact our solution, Zero-Ingestion ScalableRAG, handily out-performs all baselines (including knowledge graph approaches) in three out of the six corpora considered here, and only marginally missing maximum performance on the other three, with average accuracy across all six datasets 7.36% above the next most competitive baseline. It achieves this by keeping a workspace of document sets and values sets that it can write into and read from, allowing for on-the-fly aggregative reasoning in all situations where grouping is required on a primary key that is in one to one correspondence with a subset of the total document set. Capping the number of LLM calls by a constant independent of the corpus size, we also introduce Limited-Ingestion ScalableRAG, which does use a minimal vector database as well as an automated pattern discovery from a sample of documents, to further improve accuracy at scale. Our code is available at https://github.com/cohesity/ScalableRAG . --- ### Interpretable GOHR Agents via Sparse Autoencoders Authors: Shiwei Tan, Yusong Zhao, Weiyi Qin, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang Published: 2026-07-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.25132v2 A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We report interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR). We focus on a compact two-rule task in which both hidden rules map object shapes to target buckets, but with different permutations. The policy is trained on episodes sampled from these two hidden rules and then evaluated with fixed weights. It is never given a rule label and does not use an explicit rule classifier; any rule information must be inferred implicitly from interaction history. In this setting, the correct rule is not identifiable before the agent tries an informative move and observes accept/reject feedback. Sparse autoencoders (SAEs) trained on the agent's decision-token embeddings recover this structure. When held-out decisions are labeled by simple concepts such as the chosen shape or bucket, SAE dimensions that are highly selective for a concept cover most decisions where that concept is present. Individual SAE dimensions also correspond to interpretable strategies such as probing one rule hypothesis and switching after negative feedback. --- ### Learning from 53.6K Real-World Developer Edits of AI-Generated Code Authors: Jenny T. Liang, Mihika Bairathi, Wayne Chi, Ameet Talwalkar, Nishant Subramani, Valerie Chen Published: 2026-07-27 Categories: cs.SE, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2607.25130v2 Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant. Manual code edits provide more realistic and granular information on editing behavior than Git commits, which only contain final successful code snippets. Yet, due to a lack of high-quality, realistic code editing data, LLMs are mostly trained on publicly available Git data (e.g., commits). To address this gap, we introduce DECODE (Developer Edits of Code Dataset), a dataset of 53.6K real-world in-IDE code edits of AI-generated code in Python, TypeScript, and JavaScript, sourced from 1K+ developers. First, we demonstrate the utility of DECODE for data analysis, obtaining insights on when, why, and how AI-generated code is edited. We find that most edits occur within the first 15 minutes after accepting an AI completion, resulting in the removal of AI completions in 31% of edit trajectories. Second, we use DECODE to benchmark the ability of LLMs to predict code edits. We find that finetuning on DECODE enables open-source 3B models to perform code edit prediction tasks significantly better than frontier LLMs. We then discuss implications of this work, emphasizing the necessity of developer-centric machine learning approaches for future AI programming assistants. --- ### Learning from 53.6K Real-World Developer Edits of AI-Generated Code Authors: Jenny T. Liang, Mihika Bairathi, Wayne Chi, Ameet Talwalkar, Nishant Subramani, Valerie Chen Published: 2026-07-27 Categories: cs.SE, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2607.25130v1 Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant. Manual code edits provide more realistic and granular information on editing behavior than Git commits, which only contain final successful code snippets. Yet, due to a lack of high-quality, realistic code editing data, LLMs are mostly trained on publicly available Git data (e.g., commits). To address this gap, we introduce DECODE (Developer Edits of Code Dataset), a dataset of 53.6K real-world in-IDE code edits of AI-generated code in Python, TypeScript, and JavaScript, sourced from 1K+ developers. First, we demonstrate the utility of DECODE for data analysis, obtaining insights on when, why, and how AI-generated code is edited. We find that most edits occur within the first 15 minutes after accepting an AI completion, resulting in the removal of AI completions in 31% of edit trajectories. Second, we use DECODE to benchmark the ability of LLMs to predict code edits. We find that finetuning on DECODE enables open-source 3B models to perform code edit prediction tasks significantly better than frontier LLMs. We then discuss implications of this work, emphasizing the necessity of developer-centric machine learning approaches for future AI programming assistants. --- ### Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding Authors: Muhammed Yavuz Nuzumlalı, Alexander Fabbri, Irene Li, Dragomir Radev Published: 2026-07-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.25129v1 Medical coding is the task of assigning a set of diagnosis and procedure codes for a hospitalization using recorded notes. It requires aggregating information from different parts of the text and focus to different sections for each individual code, making it a very difficult problem even for professional human coders. We model the task as a multi-label text classification problem. To overcome the mentioned difficulties, we propose a deep neural model consisting of a multi-layer temporal convolution network (TCN) followed by label-wise attention. While multi-layer TCN helps extract a global document representation with the ability to learn relations over very long sequences, label-specific attention mechanism allows the model to focus on different aspects of the same document for each individual label. Our method achieves significantly better F-1 scores (9% increase) compared to the previous state-of-the-art model, with a remarkable increase in recall score (28% increase), which we believe is the more important metric for a clinical decision support setting. --- ### LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos Authors: Ce Zhang, Jinxi He, Katia Sycara, Yaqi Xie Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25125v1 Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling methods attempt to mitigate this by distilling video inputs into a compact set of query-relevant frames, navigating the vast spatio-temporal search space remains challenging, as spatial detail and temporal coverage often conflict. To address this, we introduce LENS, a training-free keyframe sampling framework that dynamically decides when to zoom in for fine-grained details and when to zoom out for broader context based on the text query. Concretely, LENS adaptively allocates a limited frame budget between spatial zoom-ins, which highlight query-relevant regions within individual frames, and temporal zoom-outs, which expand the temporal scope through multi-frame aggregation, enabling the model to reason across multiple granularities while capturing both high-fidelity details and long-range context. Across diverse long-form video benchmarks, LENS consistently outperforms prior state-of-the-art keyframe sampling methods and delivers substantial gains over uniform sampling, improving Video-MME accuracy from 53.3% to 60.7% with Qwen2.5-VL.Code is available at https://github.com/zhangce01/LENS. --- ### Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning Authors: Parham Mohammad Panahi, Armin Ashrafi, Haoyu Du, Andrew Patterson, Martha White, Adam White Published: 2026-07-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.25123v1 Experience replay remains one of the most practical and useful algorithmic tools in the deep reinforcement learning (DRL) toolbox. Aside from the limited success of prioritized replay and specialized approaches for large asynchronous systems, most DRL algorithms make use of a large, uniformly sampled recency buffer---even the size, one million, remains unchanged. Could we store less data, reduce redundancy, or more effectively chain experience together to speed up value propagation and still retain the performance of large buffers? In this paper, we investigate a simple compression approach that stores representative transitions derived from the end-points of a chain of connected $n$-step sequences. By curating these end-points in a smaller recency buffer, our method maintains an effective memory horizon comparable to a standard large buffer while requiring an order of magnitude less storage. Through empirical evaluation, we demonstrate that this approach prevents the systematic bias inherent in naive compression strategies and matches the performance of traditional large buffers in the Pinball environment and the Atari 2600 benchmark. --- ### Semantic Space Search Trajectory Networks Authors: Julian Agudelo, Alberto Tonda, Gabriela Ochoa, Vincent Guigue, Cristina Manfredotti, Evelyne Lutton Published: 2026-07-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.25122v1 Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on discretization of the search space has largely confined them to low-dimensional or combinatorial settings. We introduce a methodology for constructing STNs in semantic spaces, defined as the space of a model's predictions on a fixed sample set. Our approach discretizes semantic vectors and aggregates them into network nodes via agglomerative clustering with complete linkage under a normalized Hamming distance. Since any predictor can be summarized by its semantic vector, this method enables comparison of learning dynamics across otherwise incomparable algorithm families. We apply semantic space STNs to classification and regression tasks solved using different machine learning algorithms, recovering known qualitative differences between them. Additionally, we use semantic space STNs to study neural network generalization by contrasting standard training with the label randomization regime of Zhang et al. (2017). The resulting STNs exhibit consistent structural differences, training on real labels produces denser, more efficient and more centralized graphs than training on shuffled labels. Together, our results show that semantic space STNs capture functional training dynamics arising from the interaction between learning algorithms and data, providing a tool for analyzing and comparing learning dynamics across machine learning models and training regimes. --- ### Score-Based Stabilization for Time-Dependent Problems Authors: Eshed Gal, Eldad Haber, Uri Ascher Published: 2026-07-27 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2607.25119v1 We propose a score-based stabilization framework for numerical simulation of partial differential equations, in which a learned score model defines a stabilization operator applied to provisional numerical updates. This operator augments standard time-stepping schemes by enforcing structure and physical consistency through a correction that drives iterates toward the manifold of admissible states. We show that the stabilization operator acts as a contraction toward this manifold, yielding a correction mechanism with basin-conditional stability. Numerical experiments on Advection, Korteweg-de Vries (KdV), Nonlinear Schrodinger (NLS), and Burgers' equations demonstrate improved robustness, suppression of nonphysical instabilities, and preservation of qualitative dynamics. --- ### Analysis of the Shortcut Learning and Clever Hans Effect in CNN based ECG Image Classification Authors: Abhay Kumar Pathak, Mrityunjay Chaubey, Manjari Gupta, Deepti Mishra Published: 2026-07-27 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.25117v1 Deep learning models for ECG image classification may achieve high accuracy by exploiting non-physiological visual cues instead of ECG waveform morphology. Given the black-box nature of deep learning models, their promise of high predictive performance often remains insufficiently translated into clinical or real-world trust, interpretability, and actionable decision-making. In this study, we examine shortcut learning and Clever Hans effect in a publicly available ECG image dataset using convolutional neural networks. In process we have created six image-derived feature sets (FSs), FS1: raw full ECG images, FS2: cropped waveform-only images, FS3: waveform-masked metadata images, FS4: red-arrow artifact images for the myocardial infarction class, FS5: contrast-enhanced images for the abnormal heartbeat class and FS6: Gaussian-blurred images for the normal class. These controlled representations were used to test whether classification performance persists when waveform information is removed or when artificial class-specific artifacts are introduced. Shortcut retention score, prediction consistency and confidence divergence across Feature-Set Representations have been calculated to assess the transparency about the learning pattern. Along with factual results, average Integrated Gradients and occlusion sensitivity test results are presented to inspect whether model attribution focused on ECG-relevant waveform regions or on non-clinical artifacts. Performance changes across feature sets and attribution patterns were used to identify potential Clever Hans behavior. This study evaluates whether ECG image classifiers learn clinically meaningful morphology or shortcut cues introduced by report layout, metadata, contrast, blur, or artificial markers. --- ### Memory Layer: Train the In-Model Cache for Recommendation Models Authors: Liangyuan Na, Gufan Yin, Yixin Bao, Xianjie Chen, Justin Lin, Ziheng huang, Xinyuan Zhang, Wen Zhang, Hao Lin, Xiaoheng Mao, Shuo Tang, Min Yu et al. Published: 2026-07-27 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.25110v1 Early ranking stages in recommendation systems precompute item embeddings and cache them in-model for scoring within strict latency constraints. Because this cache exists only at serving time, outside the training loop, training and serving use different item representations, a structural discrepancy that limits quality and adds operational fragility. We show that co-designing the training and serving paths removes this representation discrepancy at its source. We introduce the memory layer, an in-model key-value embedding cache co-trained with the model: the item tower writes embeddings during training and the model reads them at serving, one source of truth for item representations by construction. Always-on embeddings cover items not yet cached, so every item receives a prediction, and the design consolidates three separate trainer-to-predictor update paths into a single self-contained pipeline. Deployed in production on Instagram Reels, the memory layer raises prediction coverage from 96% to 100%, improves embedding freshness from $O(5\text{ min})$ to $O(20\text{ s})$, and narrows the training-serving Normalized Entropy (NE) gap by up to 86%, yielding over $2\times$ recall for the freshest content and a 5-6% cold start engagement lift. Because embeddings are produced during training, the system needs no separate bulk-evaluation or publish-time recomputation, cutting training-and-publish computational cost by 30% at neutral serving computational cost. --- ### OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis Authors: Zihan Li, Feiyang Liu, Dandan Shan, Ruibo Wang, Qingqi Hong Published: 2026-07-27 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.25108v1 Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently require repeated domain-specific fine-tuning, which is a costly cycle that becomes impractical when labels are scarce or privacy constraints limit data sharing. We propose OPERA (Offline Policy-guided Expert Routing and Adaptation), a multi-agent ensemble framework that addresses this deployment bottleneck by treating expert weight assignment as an offline policy learning problem: a routing policy is learned from a small validation set without gradient updates to any expert agent, then deployed with test-time adaptation to handle distribution shift. OPERA coordinates heterogeneous specialist agents through complementary mechanisms. The expert profiling module learns selection policies offline, enabling informed allocation of expertise. Each agent undergoes confidence calibration through temperature adjustment, ensuring more reliable probabilistic outputs. OPERA also incorporates distribution aware adaptation, where class weights are dynamically adjusted at the batch level using statistics derived from unlabeled test data. Instance level routing assigns each sample to the most suitable expert by leveraging inter model agreement and predictive entropy. We evaluate OPERA on 9 datasets covering fundus photography, chest X-ray, CT, MRI, and multimodal diagnostic benchmarks, comparing against 30+ baselines across classification, segmentation, and multimodal settings. OPERA consistently improves performance and calibration quality, demonstrating that offline policy-guided expert agents coordination is a practical path to deployable biomedical AI without retraining. Code is on \href{https://github.com/HUANGLIZI/OPERA}{GitHub}. --- ### MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics Authors: Paul Largillier, Karl Paygambar, Cédric Gouy-Pailler, Vincent Meyer, Mallek Mziou, Oana Stan Published: 2026-07-27 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.25107v1 Security and privacy are primordial requirements for Federated Learning (FL), especially in fields such as healthcare and genomics where sensitive information has to be analyzed. Our FL framework is designed to address these challenges while proposing a modular, flexible and micro-service architecture. More precisely, it integrates an efficient gRPC communication layer and a Finite State Machine to ensure robust component synchronization and threat detection, while relying on a fault-tolerant secure aggregation protocol using a Threshold variant of the CKKS homomorphic cryptosystem. This allows blind model aggregation by an orchestration server, requiring a minimum of $t$-out-of-$N$ active clients for decryption while minimizing communication overhead thanks to both cryptographic and network protocols. We ensure IND-CPA-D security through noise flooding and mitigate the recent key-recovery attack on synchronized decryptors by renewing the collective key material at every round. We demonstrate the framework's effectiveness through diverse use cases, ranging from standard image recognition (EMNIST) to complex genomic classification including breast cancer subtyping on TCGA, evaluating system performance across different threshold values and model scales. --- ### IMPRINT: Image-Conditioned Query Enrichment for Long-Tail Object Goal Navigation Authors: Jelin Raphael Akkara, Filippo Ziliotto, Luciano Serafini, Lamberto Ballan, Tommaso Campari Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25106v1 Embodied AI increasingly relies on queryable semantic maps built from pre-trained vision-language models to enable zero-shot Object Goal Navigation (ObjectNav). However, existing approaches typically depend on text-only queries, which become less reliable as semantic specificity increases toward fine-grained object categories. We introduce IMPRINT, a zero-shot plug-and-play framework that enriches textual object queries with web-sourced images to improve grounding in queryable maps. Retrieved images are encoded using a vision-language model, matched against the semantic map to produce similarity maps, and aggregated to yield context-aware localization. Notably, this requires no training or modification of the underlying navigation policy. To explicitly evaluate long-tail behavior, we present HSSD-rare, a new ObjectNav benchmark built on Habitat Synthetic Scenes and featuring semantically specific subcategories. Across both OVON and HSSD-rare, image-conditioned queries consistently improve object grounding and yield end-to-end navigation gains. Further analysis reveals that translating localization gains to navigation performance depends critically on downstream detection quality, highlighting a key systems bottleneck in long-tail embodied navigation. --- ### Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method Authors: Stephan Wojtowytsch Published: 2026-07-27 Categories: math.AP, math.NA, stat.ML arXiv: https://arxiv.org/abs/2607.25100v1 We prove that harmonic functions with Dirichlet boundary data in Barron space, a function class tailored to wide ReLU networks with a single hidden layer and suitably bounded weights, are generally neither Lipschitz continuous nor in the Sobolev class $H^2$. A fortiori, they are not in any function class in which the norm controls the Lipschitz constant, which rules out not only Barron space regularity, but also regularity in function classes for deeper ReLU networks with bounded coefficients. They can, however, be approximated to accuracy $\sim \varepsilon$ by Barron functions of low norm $\sim |\log\varepsilon|$ in various Lebesgue and Sobolev norms (with at most two derivatives). The positive result holds on very simple domains: Half-spaces in arbitrary dimension and rectangular domains in two dimensions. As an application of this regularity theory, we obtain a priori error estimates for Deep Ritz neural PDE solvers. --- ### Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation Authors: Cesare Spinoso-Di Piano, Verna Dankers, Marius Mosbach, Jackie Chi Kit Cheung Published: 2026-07-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.25094v2 Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users. In this paper, we evaluate the ability of LLMs to recognize unspoken beliefs made through implicatures and to understand their updates through implicature cancellation: the pragmatic phenomenon whereby an utterance's implied meaning is weakened or negated. We create the first expert-annotated implicature cancellation dataset, ImplicatureX, crowdsourced for human judgements of implicatures and their corresponding cancellations. We find that LLM belief update understanding lags behind that of humans, especially in more naturally-occurring scenarios. Additional control experiments suggest that successes in LLM belief updates may stem in part from a reliance on prior beliefs, and that failures in belief updates may depend on their type and on their form. Overall, our study suggests that current LLMs have not yet reached human-level understanding of unspoken beliefs and belief updates. Code and data are available at https://github.com/cesare-spinoso/ImplicatureX. --- ### MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks Authors: Taimoor Rizwan, Sara Atito, Zhenhua Feng, Muhammad Awais, Josef Kittler Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25092v1 Face morphing attacks create synthetic images verifiable against multiple identities, threatening border control and identity verification systems. We introduce MorphUNet, a diffusion morphing framework formulating two-parent generation as alpha-controlled biometric transport: each parent is decomposed into CLIP appearance and ArcFace identity evidence, aligned into a CLIP-compatible token space, with the two contributors preserved as separate identity-aware token banks. To our knowledge, MorphUNet is the first diffusion-based morphing framework using trainable parent-separated dual cross-attention inside the denoising U-Net: a Biometric Transport Layer carrying parent-specific identity evidence through denoising, attending to each parent separately before combining residuals via the morphing parameter alpha. DDIM-inverted latent interpolation gives a coherent denoising start, while weaker-parent-guided selection favours morphs maximising the lower parent-similarity score, reducing collapse toward one contributor. We evaluate MorphUNet against three state-of-the-art baselines (StableMorph, MIPGAN-II, and MorDIFF) on FEI and FRLL using six recognition systems, and propose CFD-based unseen-identity stress testing across gender and ethnicity pairing, demographic shifts, and parent-similarity extremes. MorphUNet achieves the best Morphing Attack Potential (MAP) when at least three of six systems are fooled by one morph, reaching 0.919 on FEI and 0.886 on FRLL, and obtains the best FID on both datasets (35.19 FEI, 44.86 FRLL). It also gives the highest APCER at 5% BPCER in the same-dataset setting, and remains highly difficult to detect under cross-dataset transfer, with APCER 0.996 on FEI and 0.946 on FRLL. The full evaluation analyses MAP, MAD, per-system vulnerability, identity balance, image quality, top/bottom-similarity stress tests, and CFD unseen-identity robustness. --- ### Towards Robust Reinforcement Learning for Small-Scale Language Model Agents Authors: Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray Published: 2026-07-27 Categories: cs.AI, cs.CL, cs.LG, math.OC, stat.CO arXiv: https://arxiv.org/abs/2607.25091v1 The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated. In the State-of-the-Art (SOTA) research, fifteen (model, corpus) configurations were trained using Proximal Policy Optimization (PPO). The experiments included Pythia-70M, 160M, 410M and SmolLM2-135M, 360M on the TinyStories, CNN/DailyMail, and Wikitext-103 corpora. Three reproducible failure modes were identified in small-scale language models: silent LoRA parameter freezing in standard PEFT/TRL pipelines, numerical overflow in importance ratios when using bfloat16, and catastrophic policy collapse due to reward-model error. These issues were addressed using a merge-and-reinitialize adapter technique, float32 precision during PPO updates, and a three-layer safety mechanism comprising reward whitening, importance-ratio guarding, and weight rollback. In this paper, a capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model ($\text{PPL}<20$) and a discriminative reward signal, rather than on the number of model parameters. The proposed system converged stably in all experiments and improved preference win rate over the SFT baseline in configurations with a fluent prior and an informative reward signal. Furthermore, it outperformed instruction-tuned baselines while requiring significantly less training data. All checkpoints, preference datasets, and training scripts are publicly released$^§$. --- ### Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Authors: Rushi Qiang, Changhao Li, Haotian Sun, Yuchen Zhuang, Chao Zhang, Bo Dai Published: 2026-07-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.25090v1 Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feedback-driven environment interactions. Developing and training a monolithic agent for such tasks is fundamentally challenging, as it must simultaneously manage extremely long and noisy contexts, explore vast solution spaces, and remain effective under limited model capacity and computational budgets. To address these challenges, we propose Matryoshka Agent, a unified hierarchical agent framework for complex long-horizon tasks. Matryoshka Agent decomposes agentic problem solving into a coordinated hierarchy of decision making and execution: a high-level Orchestrator maintains compact, long-horizon exploration states and issues strategic instructions, while lower-level Sub-Agents execute concrete solution attempts through direct environment interaction, mediated by standardized Tool interface. This design decouples strategic exploration from costly execution, substantially reducing the burden of long-context reasoning and enabling efficient iterative refinement. We further develop an efficient training paradigm for Matryoshka Agent. Experimental results on a broad range of MLE tasks with diverse model types and scales demonstrate that Matryoshka Agent is an effective and scalable paradigm for long-horizon MLE tasks and complex agentic problem solving. Notably, Matryoshka Agent enables Qwen3-4B-Instruct to reach Orchestrator performance comparable to o4-mini. Applying Matryoshka Agent to Qwen3-30B-Coder results in at most 36.7% relative performance gain. --- ### PLATO: Pointer Learner for Agent and Task Openness Authors: Alireza Saleh Abadi, Leen-Kiat Soh, Daniel Alan Redder, Adam Eck, Prashant Doshi Published: 2026-07-27 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.25082v2 Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a fundamental challenge to multi-agent reinforcement learning (MARL), which typically assumes fixed state and action spaces. Existing methods address openness only partially: padding and masking approaches introduce artificial bounds, while recent graph-based or hypergraph methods handle one dimension of openness but still depend on restrictive assumptions. In this paper, we introduce Pointer Learner for Agent and Task Openness (PLATO), a pointer-network-based actor combined with a centralized graph neural network (GNN) critic, trained with multi-agent proximal policy optimization under a centralized training and decentralized execution paradigm. Our pointer-based actor outputs distributions directly over the current task set. This directly supports changing action spaces without masking or retraining. Our GNN critic encodes agent-task interactions as a graph that changes shape with task and agent composition. Together, these components consider AO and TO without the boundedness of existing approaches. We formalize PLATO in a Task-and-Agent-Open Markov Game (TaAgO-MG), extending prior task-open formulations, and prove it is well-defined over the resulting unbounded state and action spaces. We evaluate PLATO with the Methods for Open Agent Systems Evaluation Initiative (MOASEI) wildfire suppression domain, an environment designed for open multi-agent system evaluation, and we demonstrate strong performance and more consistent zero-shot generalization than state-of-the-art baselines in OASYS. --- ### Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models Authors: Taimoor Rizwan, Sara Atito, Muhammad Awais, Zhenhua Feng, Josef Kittler Published: 2026-07-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.25078v1 Generative diffusion models have revolutionized facial image synthesis, yet robust identity preservation in high resolution outputs remains a critical challenge. This issue is especially vital for security systems, biometric authentication, and privacy sensitive applications, where any drift in identity integrity can undermine trust and functionality. We introduce Diff-ID, a diffusion based framework that enforces identity consistency while delivering photorealistic quality. Central to our approach is a custom 210K image dataset synthesized from CelebA-HQ, FFHQ, and LAION-Face and captioned via a fine tuned BLIP model to bolster identity awareness during training. Diff-ID integrates ArcFace and CLIP embeddings through a dual cross attention adapter within a fine tuned Stable Diffusion UNet. To further reinforce identity fidelity, we propose a pseudo discriminator loss based on ArcFace cosine similarity with exponential timestep weighting. Experiments on held out and unseen faces show that Diff-ID does not exceed InstantID in raw ArcFace Face Similarity, but achieves substantially lower FID and the strongest FIQ based identity--realism trade off among the evaluated methods. We also present a unified DDIM based morphing pipeline that enables qualitative facial interpolation without per identity fine tuning. We further argue that identity preservation and photorealism should be evaluated jointly rather than in isolation, as high identity similarity alone does not guarantee realistic outputs. To make this trade off explicit, we report Face Image Quality (FIQ) as a complementary ratio based score that combines identity similarity and perceptual realism while keeping FS and FID as the primary metrics. --- ### Towards an Agent Operating System - Lessons from Classical and Cloud OS Authors: Gosia Steinder, Hubertus Franke Published: 2026-07-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.25076v1 Every major wave of platform software follows the same arc: an initial period of experimentation with competing frameworks and ad-hoc implementations, followed by the articulation of a small set of stable abstractions with well-defined semantics, and finally consolidation around those abstractions into a platform that applications can portably target. POSIX did this for classical operating systems; Kubernetes did it for the cloud. Agentic AI systems - autonomous, LLM-driven agents that plan, use tools, maintain memory, and collaborate - are currently in the experimentation phase of the third such wave. dozens of frameworks and protocols have emerged, but no community consensus exists on what the core abstractions are or what guarantees they carry. Without that consensus, agentic applications cannot be written portably, platforms cannot compose reliably, and the field cannot advance beyond prototype deployments. We argue that the path forward is to follow the prior-wave methodology: derive new agentic abstractions by extending classical OS and cloud OS primitives to stochastic, natural-language-mediated execution, specify their semantics precisely, and consolidate around them - just as POSIX and Kubernetes consolidated their respective waves. --- ### Spectral Truncation in Synthetic Control Authors: Mojtaba Eslami Published: 2026-07-27 Categories: stat.ME, cs.AI, cs.LG, econ.EM, stat.AP arXiv: https://arxiv.org/abs/2607.25074v1 Synthetic control (SC) matches a treated unit's pre-treatment trajectory to a weighted combination of donor units. We study Spectral SC, which instead matches the treated unit in coordinates defined by the leading temporal singular vectors of the donor panel, and a hybrid estimator that places separately tunable weight on retained and discarded directions, nesting raw-path SC and truncated Spectral SC as endpoints. We prove that the family reduces exactly to raw-path SC at full rank, that exact balance on $K$ retained dimensions with $N_0$ donors is underdetermined whenever $N_0>K+1$, with an affine solution set of dimension $N_0-K-1$, and that spectral imbalance maps to treatment-effect bias through a finite-sample best-linear-predictor decomposition. We evaluate the estimators across eleven data-generating regimes, using $400$ replications per regime and donor-only placebo validation to select regularization and the mixing weight. Truncated Spectral SC has significantly higher RMSE than tuned raw-path SC in every regime, with paired differences equal to $4$ to $11$ Monte Carlo standard errors. The hybrid estimator selects raw-path matching in most replications and is statistically indistinguishable from tuned SC in most regimes. The result is highly sensitive to preprocessing. With raw inputs, the performance gap is large; after removing unit and time fixed effects before spectral decomposition, as suggested by the assumptions behind our bound, the gap nearly disappears and placebo validation begins to favor truncation. We interpret these findings diagnostically rather than as evidence that Spectral SC should replace raw-path SC. Basis-estimation noise, balancing underdetermination, and fixed-effects contamination determine when spectral matching can help. ---