# Research Papers — 2026-07 · bundle page 192 of 222 > Full-text markdown of papers #9551–9600 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/192 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/191.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/193.md) ### Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees Authors: Lei Yang Published: 2026-07-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.21623v1 We present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices: conformal prediction with finite-sample-corrected Adaptive Prediction Sets, calibration assessment, drift detection via RFF-approximated Maximum Mean Discrepancy, fairness monitoring with bootstrap confidence intervals, a DAG-based pipeline orchestrator, and a result storage API. We validate four key methodological concerns. First, empirical coverage is consistent with the marginal conformal guarantee across K=50 random calibration/test splits, with mean coverage within 1.4 percentage points of the nominal target. Second, all four MMLU answer tokens appear in the top-20 logprobs with 0% imputation needed, and simulated imputation at 10% produces less than 1.5% coverage impact. Third, RFF-MMD achieves 100% detection power for mild and severe drift at the median heuristic bandwidth, with Type I error between 5-8.5%. Fourth, fairness monitoring on the UCI Adult Income dataset reveals significant demographic parity disparities by race (DP gap=0.33) with stable alerts across sequential batches. Conformal prediction and calibration services achieve sub-2ms p99 latency at batch size 100; RFF-MMD requires ~500ms suited for periodic batch monitoring. A comparison with four open-source tools suggests that, to the best of our knowledge, no current platform combines conformal-prediction-as-a-service, microservice decomposition, and DAG-based orchestration. --- ### Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain Authors: Dmitrii Khizbullin, Zaid Alyafeai, Abdelrahman Eldesokey, Nourah AlSultan, Raghad Alshalan, Bernard Ghanem, David R. Pugh Published: 2026-07-04 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20510v2 We introduce Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator. Telco-GAIA comprises 100 human-verified question-answering tasks, in English and Arabic, that each demand multi-hop reasoning (4.2 hops on average) over three heterogeneous sources: a static website snapshot (HTML, images, and linked PDFs), a synthetic relational SQL database, and external web archives, spanning text, image, and tabular modalities. The benchmark is delivered as a sandboxed Docker environment and scored by normalized exact string matching, making evaluation objective, deterministic, and reproducible over time without any LLM-as-a-Judge. Evaluating a purpose-built reference agent across twelve commercial and open LLMs, we find Telco-GAIA challenging: even the strongest model solves only 71% of tasks; under a moderate cost budget, this falls to about 40%, and the visually grounded categories remain the weakest, where the average backend scores below 30%, leaving substantial headroom in document and image understanding. Telco-GAIA offers a rigorous, reproducible testbed for enterprise agents and a template for constructing closed-domain benchmarks. --- ### Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain Authors: Dmitrii Khizbullin, Zaid Alyafeai, Abdelrahman Eldesokey, Nourah AlSultan, Raghad Alshalan, David R. Pugh, Bernard Ghanem Published: 2026-07-04 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20510v1 We introduce Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator. Telco-GAIA comprises 100 human-verified question-answering tasks, in English and Arabic, that each demand multi-hop reasoning (4.2 hops on average) over three heterogeneous sources: a static website snapshot (HTML, images, and linked PDFs), a synthetic relational SQL database, and external web archives, spanning text, image, and tabular modalities. The benchmark is delivered as a sandboxed Docker environment and scored by normalized exact string matching, making evaluation objective, deterministic, and reproducible over time without any LLM-as-a-Judge. Evaluating a purpose-built reference agent across twelve commercial and open LLMs, we find Telco-GAIA challenging: even the strongest model solves only 71% of tasks; under a moderate cost budget, this falls to about 40%, and the visually grounded categories remain the weakest, where the average backend scores below 30%, leaving substantial headroom in document and image understanding. Telco-GAIA offers a rigorous, reproducible testbed for enterprise agents and a template for constructing closed-domain benchmarks. --- ### HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questions Authors: Junyi Wang Published: 2026-07-04 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.19398v1 Multi-entity compositional questions pose significant challenges to existing retrieval-augmented language models. Conventional methods fall into a dilemma: standard RAG lacks dynamic reasoning, traditional Graph-RAG is limited by structural sparsity, and LLM-constructed Graph-RAG incurs prohibitive costs. We propose \textbf{\fwa}, a unified framework that embeds unstructured text into structured knowledge graphs, creating a heterogeneous network for flexible evidence retrieval. Reasoning is formulated as adaptive structure induction, learned via a robust two-stage process: (1) imitation learning distills heuristic expert signals, and (2) reinforcement learning refines the policy using LLM-driven preference rewards. Experiments demonstrate that {\fwa} effectively merges textual richness with structural knowledge, outperforming SOTA baselines in answer accuracy and reasoning fidelity while maintaining extremely low token costs and near real-time inference((code available at https://github.com/wjywjy123/HyGRL) . --- ### Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning Authors: Adrian Ly, Richard Dazeley, Peter Vamplew, Sunil Aryal, Francisco Cruz Published: 2026-07-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19397v1 Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improves short term stability, yet each hard update abruptly replaces the target parameters with the newest online network and discards recent parameter history. This can produce sudden changes in the bootstrap target and may remove value function structure that remains useful later in training. This paper introduces Memory Merge DQN, a target network update mechanism that maintains a short memory of recent historical online network copies and constructs the target network by merging network parameters based on the Q-value sensitivity rather than copying only the newest online network. Memory Merge gives greater influence to parameters that remain locally important for current Q-value behaviour, while using a recency prior to keep the merged target close to the latest online parameters. The method is inspired by Fisher Weight Model Merging, but uses Q-value sensitivity rather than Fisher information as the weighting signal. This paper evaluates Memory Merge DQN on Atari environments against DQN, Averaged DQN, DQN with layer normalisation, and PQN (with gradient clipping). The results show that Memory Merge DQN is highly competitive and it achieves the largest number of first place final performance results among the evaluated methods, beats DQN, Averaged DQN, and PQN (with gradient clipping), and produces substantial gains in several games where preserving useful value-function parameters appears beneficial. These findings suggest that selectively merging recent parameter weights and history can improve the stability and final performance of DQN agents, and that target network design is an important mechanism for preserving useful value function structure during long horizon value learning. --- ### Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programming Authors: Ali Kohan, Mohamad Roshanzamir, Roohallah Alizadehsani, Seyedali Mirjalili Published: 2026-07-04 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2607.11913v1 Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-linear reasoning workflows. A prominent example is Genetic Network Programming (GNP), a self-evolving algorithm that utilizes directed graphs to evolve interpretable decision structures for agents. As in most evolutionary algorithms, effectively balancing exploration and exploitation is a key aspect of GNP. However, this trade-off has received limited attention in the GNP literature. To address this gap, we draw inspiration from human developmental patterns, where children prioritize broad experimentation and action over deliberation, with this tendency reversing with age. By mapping transitions between GNP's judgment nodes to deliberation and processing nodes to action, we propose Human-Inspired GNP (HGNP), a novel adaptive framework that dynamically regulates the exploration-exploitation balance throughout the evolutionary process. The method consists of novel adaptive crossover and mutation operators, and a cycle elimination mechanism. HGNP not only improves the evolutionary process but also provides a framework for adjusting the exploration-exploitation balance based on the characteristics of the target environment and its search space. This approach is more effective than tuning via crossover and mutation probabilities in standard GNP. The modifications are general and can be applied to almost all GNP variants. When integrated with standard GNP and two recently introduced GNP variants and evaluated on the Tileworld benchmark, HGNP demonstrated significant performance improvement in agents' strategy. The combination of HGNP with Situation-based GNP (HGNP-SBGNP) achieved the best overall results. --- ### Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis Authors: Haksoo Lim, Myeongjin Lee, Wonjoon Chang, Jaesik Choi Published: 2026-07-04 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.09753v1 Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function. In this paper, we present a systematic, phase-aware analysis of diffusion components and show that abrupt, early-stage fluctuations in deep latents are strongly associated with artifacts. Guided by these findings, we introduce DUNE (Diffusion Unified Network refiNEr), a training-free refinement framework that detects abrupt deviations in deep low-noise internal latents using a shared EMA-based criterion, and applies backbone-specific suppression to the detector-selected entries. Although derived from U-Net, the same detect-suppress principle extends naturally to Transformer-based diffusion models by acting on the latents of deep self-attention blocks. Extensive experiments across multiple backbones indicate that DUNE improves fidelity while reducing hallucinations, offering new insight into where and when diffusion backbones should be controlled. --- ### Data-Driven Forward and Inverse Modeling of V-Beam Thermal Sensors Authors: Tudor Bartha, Radu Chiorean, Adrian Groza Published: 2026-07-04 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2607.09752v1 This paper presents a machine learning framework for data-driven inverse design of V-beam thermal sensors. The goal is to determine the optimal sensor geometry: beam inclination angle, beam length and beam width that achieves a target displacement under a given temperature. The design should also provide the geometry with minimum structure volume and minimum mechanical stress the sensor must support. This problem is ill-posed as for a given displacement there are multiple possible geometric configurations, causing direct regression methods to fail. We document a series of five exploratory trials that progressively revealed the nature of the problem culminating in a two-phase solution: a neural network forward model trained to map geometry and material constants to sensor responses, a gradient-descent inverse optimization over the frozen forward model, minimizing stress and volume simultaneously. The proposed pipeline utilizes a 3000-sample dataset and achieves a MAPE of 4.76% for predicting the displacement, more than 70% of predictions having MAPE of under 5%. --- ### Task-Conditioned Synthetic Data Generation for Improving Machine Learning Performance in Agricultural Prediction Tasks Authors: Hamid Ebrahimy, Moritz Lucas, Martin Atzmueller Published: 2026-07-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.09751v1 Machine Learning (ML) algorithms have been widely used to estimate agricultural variables across diverse contexts. However, because the quantity and quality of training data strongly influence performance of ML algorithms, their use can be constrained by limited or incomplete reference data. Synthetic Data Generation (SDG) offers a practical approach to address this issue by producing artificial but realistic samples that preserve key characteristics of the original data. Building on teacher-student knowledge transfer and in-context learning for tabular data, this study proposes a Task-Conditioned SDG (TCSDG) algorithm that pairs a Bayesian Network generator with a transformer-based tabular foundation model (TabICL). The proposed algorithm was evaluated on two agricultural prediction tasks: crop yield prediction and crop type classification. Six benchmark SDG algorithms were also utilized to compare their performance with that of TCSDG. Across twelve study sites, two training-data fractions, four multiplication ratios, and three predictive ML algorithms, augmenting the original data with TCSDG-generated synthetic data improved ML performance in 89% of the crop type classification experiments and 74% of the crop yield prediction experiments. TCSDG also substantially outperformed benchmark SDG algorithms and was the only method to consistently improve ML performance across both tasks at the aggregate level. The study demonstrates that carefully designed and processed synthetic data can improve ML performance in precision-agriculture applications. TCSDG offers a practical and extensible framework for generating synthetic data that supports downstream ML agricultural prediction. The full implementation of TCSDG is publicly available as open source at https://github.com/HamidEbrahimy/TCSDG. --- ### SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data Authors: Muhammet Sami Yavuz, Ayhan Can Erdur, Sabri Mustafa Kahya, Benedikt Wiestler, Jana Lipkova Published: 2026-07-04 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2607.07725v1 Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment. Existing approaches to this challenge typically restrict analysis to genes shared across cohorts, exclude patients with incomplete profiles, or rely on test-time imputation, all of which can reduce robustness and limit the use of multi-center data. We propose Survival prediction Handling Incomplete Features using Transformer (SHIFT), a missingness-aware survival model that directly predicts from incomplete genomic inputs without test-time imputation. SHIFT represents each genomic feature separately and uses masked self-attention, along with a feature-availability mask, so that predictions are based only on observed inputs. Further, we introduce variable-rate feature masking during training to improve robustness to heterogeneous missingness patterns. We evaluate the approach on glioblastoma and lung squamous cell carcinoma with external validation across multiple cohorts, including a challenging setting with severe cross-cohort panel mismatch. Across these settings, SHIFT shows strong generalization and compares favorably with standard survival baselines and imputation-based approaches, while using a single model across differing feature sets. We also find that incorporating patients from incomplete cohorts during development can improve performance on external data, suggesting that partially observed cohorts need not be excluded from model building. These results support missingness-aware modeling as a practical strategy for multi-center survival prediction in precision oncology. --- ### Uncertainty-gated selection for block-sparse attention Authors: Thomas Rossi Published: 2026-07-04 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.07724v1 Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks. This cutoff is myopic: when the k-th and (k+1)-th blocks are nearly tied in score, the selector commits without spending extra budget, and a dropped block carrying answer evidence is unrecoverable downstream. We propose a value-of-information router that measures, for each query, how decisively the top-k cut was made, and doubles the kept set for the queries where that gap is smallest; the rule is backbone-agnostic and stacks with existing block-scoring methods such as Quest. On LongBench-v2 medium at n=215 (the entire dataset subset), router-on-Quest reaches paired recall 0.75 vs. top-k 0.47 -- +28 pp over the SSA-style baseline (McNemar p<0.01) -- and lands within 2 pp of dense on RULER NIAH multikey at the same context. The lift reproduces on four models from three architectures (Qwen2.5, Mistral-Nemo, Qwen3.6). At 128K, the router preserves 0.81 and 0.89 of dense accuracy on Qwen2.5-7B-1M and Qwen3.6 (vs. SSA-style top-k at 0.09 on the former) while the fused selection-plus-kernel pipeline runs at 0.62x and 0.80x dense wall time. --- ### Context Graphs for Proactive Enterprise Agents Authors: Avinash Kumar Published: 2026-07-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.07721v1 Retrieval-Augmented Generation (RAG) and agentic frameworks have advanced enterprise AI considerably, yet agents remain fundamentally reactive: they wait for a human query before acting. This paper argues that genuine enterprise productivity gains require proactive agents: systems that surface relevant, actionable information to workers before they ask. We propose the Context Graph, a live relational data structure that models enterprise entities, their relationships, and state transitions over time. Built on this graph, we define a Delta Detection Engine that continuously monitors state changes, a Proactivity Scorer that ranks candidate insights by urgency, relevance, and persona-fit, and a Surfacing Layer powered by an LLM that delivers ranked notifications with grounded explanations. We formalize each component, derive a unified Proactivity Score function, and provide a complete end-to-end Python implementation using NetworkX and the Anthropic Claude API. Evaluation across three generic enterprise case studies (contract lifecycle management, engineering incident response, and sales pipeline hygiene) demonstrates that context-graph-driven proactivity achieves Precision@5 of 0.83, a false positive rate of 0.11, and reduces mean time to surface from 47 minutes (reactive baseline) to under 30 second. --- ### Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS-ANS Dynamics Authors: Zhoujie Hou, Song Wang, Kexin Lou, Mo Wang, Chen Wei, Quanying Liu Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.07720v2 Sleep physiology arises from the coordinated dynamics of the central nervous system (CNS) and autonomic nervous system (ANS), as reflected by multimodal polysomnography signals including EEG, EOG, EMG, ECG, and respiration. However, existing sleep foundation models often fuse heterogeneous biosignals in a topology-agnostic manner, overlooking their physiological organization. We introduce Omni-Sleep, a sleep foundation model that uses the CNS/ANS partition as a physiological prior for topology-constrained representation learning. Omni-Sleep learns structured representations through three objectives: intra-system consistency, which captures shared subsystem-level factors within neural and cardio-respiratory signals; inter-system synchronization, which aligns subsystem trajectories to model brain--body dynamics; and latent-space masked temporal modeling, which captures long-horizon sleep dynamics. Pre-trained on over 100,000 hours of multi-center multimodal PSG data, Omni-Sleep is evaluated on sleep staging and multi-disease classification. Across datasets and modality-ablation settings, Omni-Sleep outperforms strong foundation-model baselines, showing improved label efficiency, cross-dataset generalization, and robustness to missing modalities. These results highlight the value of physiological hierarchy for generalizable sleep representation learning. Code is available at https://github.com/AutoBrain-sleep/OmniSleep. --- ### ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning Authors: Wentao Lu Published: 2026-07-04 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.07719v1 Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task sequence LoRA-style methods keep stacking low-rank updates on the same frozen weight, so each new task tends to overwrite the previous ones. We present ReCoLoRA (Recursive Consolidation of Low-Rank Adapters), a spectrum-aware framework for continual fine-tuning: adapters are initialized from a randomized SVD of the pretrained weight, per-layer effective ranks are selected by an elbow criterion, and the principal subspace is adapted before residual capacity is opened. Before each new task, ReCoLoRA re-decomposes the current effective weight, rather than the original one, into a frozen residual, a slowly updated principal component, and a fresh adapter (recursive consolidation), so every task starts from the model that has already absorbed its predecessors. On a six-task continual GLUE sequence over four 7-8B backbones, ReCoLoRA attains the best final average score on three of the four backbones against rank-swept LoRA, PiSSA, AdaLoRA, and DoRA baselines while training fewer parameters; an oracle-routed task-bank variant serves as an upper bound under full task isolation. Code: https://github.com/bhqy666/ReCoLoRA. --- ### LLT: Local Linear Transformer for PDE Operator Learning Authors: Oded Ovadia, Eli Turkel Published: 2026-07-04 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2607.07718v1 Neural operators have become a common approach for learning PDE solution maps and accelerating numerical simulations. Transformer-based neural operators are of particular interest, since attention can learn long-range dependencies in the computational domain. However, standard attention has two major limitations when applied to PDEs: it scales quadratically with the number of computational nodes, and it lacks an explicit bias toward local interactions. To address these issues, we introduce Local Linear Transformer (LLT) for PDE operator learning. The architecture combines linear global attention with local spatial mixing, and incorporates coordinate and geometry information. We evaluate LLT on several PDE problems, including elasticity, plasticity, airfoil flow, pipe flow, and Darcy flow. The reference data for these problems span finite-element, finite-volume, and finite-difference discretizations on structured and unstructured meshes. Compared with other neural-operator and transformer baselines from prior studies, LLT achieves competitive or lower relative $L_2$ error across these problems. On matched structured discretizations, wall-clock time per training iteration is reduced by factors of 1.8 to 2.5 relative to Transolver. We also scale the approach and apply it to a three-dimensional car aerodynamics dataset with 32,186 unstructured mesh points per sample. Together, these results indicate that LLT provides an accurate and computationally efficient operator for PDE problems across discretizations, mesh types, and problem settings. --- ### Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification Authors: Ha-Hieu Pham, Hai-Dang Nguyen, Dang P. M. Cao, Thanh-Huy Nguyen, Min Xu, Trung-Nghia Le, Ulas Bagci, Huy-Hieu Pham Published: 2026-07-04 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.07717v1 In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-label CXR model is converted from scores into decisions, who is missed? Across VinDr-CXR and MIMIC-CXR/CXR-LT, we use a diagnostic ladder to separate class-level long-tail losses, subgroup-aware weighting, group robustness, and threshold selection. On VinDr-CXR, group-tail weighting followed by tail-aware thresholding reduces tail FNR from 0.665 to 0.269, sex worst-group FNR from 0.705 to 0.157, and age worst-group FNR from 0.822 to 0.133, while macro-mAP increases from 0.611 to 0.635. On MIMIC-CXR/CXR-LT, the same score-to-threshold comparison reduces tail FNR from 0.866 to 0.741 and lowers worst-group FNR across sex, age, race, and insurance; residual missed-positive rates nevertheless remain high. Paired bootstrap contrasts on VinDr support the thresholded FNR reductions, and GroupDRO reference runs indicate that aggregate group robustness alone does not remove rare subgroup misses in this setting. The study supports a narrow audit claim: rare-label fairness in CXR depends jointly on the finding, subgroup, and operating threshold, not on label frequency or ranking metrics alone. --- ### Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution Authors: Yazheng Liu, Xi Zhang, Sihong Xie, Hui Xiong Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.07716v1 Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding which historical events drive model predictions can enhance trustworthiness of TGNs. Existing explanation methods overlook the memory module, the core component that records and updates node histories, leaving the influence of past events unexplored. To address this, we attribute TGNs predictions through the topology attribution tree and memory backtracking tree. The topology attribution tree captures the influence of neighbors and their memory vectors, then the memory backtracking tree quantifies how historical events shape node memory vectors. We apply the LRP in TGNs, ensuring that the total contribution of events equals the logits of model. Finally, top-k selection may be unfaithful due to the nonlinear mapping from logits to probabilities, we design optimization objectives to identify the important events. Experiments on nine temporal graph datasets, spanning node property prediction, link prediction tasks and graph classification tasks, show that our method provides faithful explanations and outperforms state-of-the-art baselines. The code is available at https://github.com/yazhengliu/MemExplainer --- ### Trajectory Inference of Human Aging from Cross-Sectional DNA Methylation Data Authors: Chandan Gupta, Syed Haider, Pietro Liò Published: 2026-07-04 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2607.06583v1 DNA methylation (DNAm) serves as one of the most robust molecular biomarkers of biological aging. While conventional epigenetic clocks accurately predict chronological age from high-dimensional CpG profiles, they treat aging as a static regression task, meaning they can only output a single score rather than simulating how an entire profile continuously changes over time. To reconstruct these continuous dynamics, we frame lifelong human epigenetic aging as a trajectory inference problem across discrete age snapshots derived from widely available cross-sectional data. We introduce a two-stage computational pipeline: first, an age-regularized Variational Autoencoder (VAE) maps high-dimensional CpG profiles onto a chronologically ordered latent manifold while preserving a generative decoder bridge back to the original methylation space. Second, we model the continuous movement across this latent space via Regularized Unbalanced Optimal Transport (RUOT) that unifies deterministic drift, random diffusion, and non-conservative mass changes. By resolving this RUOT formulation using the DeepRUOT framework, our model fluidly accommodates population-level density shifts like survivorship bias and cellular attrition without requiring rigid biological priors. Evaluated on a large-scale, 80-year pan-tissue dataset, our model demonstrates robust distribution interpolation and uncovers a prominent late-life surge in the learned growth field that mathematically captures the variance expansion driven by stochastic epigenetic drift. Finally, by decoding continuous latent paths back to individual CpG sites, we reconstruct and empirically verify distinct biological aging archetypes, offering a rigorous, generative paradigm for simulating human molecular aging. --- ### BitFair: A 12-nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision Authors: Ang Li, Chang Gao Published: 2026-07-04 Categories: cs.AR, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.05445v2 Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few milliseconds for neural-network inference. Bit-serial computing is attractive for such energy-efficient neural network acceleration, but many existing architectures still process all bits even when ReLU sets the final output to zero. This paper presents BitFair, a software-hardware co-designed bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering, working under the ultra-low-power and strict latency requirements of XR applications. BitFair exploits dynamic bit-level sparsity by learning per-layer thresholds that trigger early termination when partial sums reliably predict that the final ReLU output will be zero. Furthermore, it searches for layer-wise bit orders that prioritize informative bits, maximizing early termination without sacrificing accuracy. A GlobalFoundries 12-nm FinFET implementation with a core area of 0.34 mm^2, 104 KB on-chip memory, and voltage scaling from 0.55 to 0.70 V achieves sub-millisecond latency, up to 117.0 BTOPS/W, and 0.07 pJ/SOP. On IBM DVS128 Gesture and N-MNIST, BitFair achieves 96.5% and 97.7% accuracy, respectively, while improving effective energy efficiency by 4.0-22.1x and accuracy by up to 9.2% over prior fabricated XR vision accelerators. --- ### BitFair: A 12nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision Authors: Ang Li, Chang Gao Published: 2026-07-04 Categories: cs.AR, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.05445v1 Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few milliseconds for neural-network inference. Bit-serial computing is attractive for such energy-efficient neural network acceleration, but many existing architectures still process all bits even when ReLU sets the final output to zero. This paper presents BitFair, a software-hardware co-designed bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering, working under the ultra-low-power and strict latency requirements of XR applications. BitFair exploits dynamic bit-level sparsity by learning per-layer thresholds that trigger early termination when partial sums reliably predict that the final ReLU output will be zero. Furthermore, it searches for layer-wise bit orders that prioritize informative bits, maximizing early termination without sacrificing accuracy. A GlobalFoundries 12nm FinFET implementation with a core area of 0.34 mm^2, 104 KB on-chip memory, and voltage scaling from 0.55 to 0.70 V achieves sub-millisecond latency, up to 117.0 BTOPS/W, and 0.07 pJ/SOP. On IBM DVS128 Gesture and N-MNIST, BitFair achieves 96.5% and 97.7% accuracy, respectively, while improving effective energy efficiency by 4.0-22.1x and accuracy by up to 9.2% over prior fabricated XR vision accelerators. --- ### PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes Authors: Amanda Adkins, Tarunvidyut Ravisankar, Joydeep Biswas Published: 2026-07-04 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.04057v1 Robots deployed over long periods must reason about environments that change over time. Existing long-term perception systems often address object change reactively, updating their maps only after revisiting a scene and observing that an object has moved. Instead, robots should reason proactively about how long objects are likely to persist using the context in which they appear. For example, a car at a traffic light and a car in a parking spot share the same semantic class, but their contexts imply different persistence durations. We propose PreSIST (Predictive Scene-conditioned Instance Survival over Time), a method for predicting whether an observed object will remain in its last seen pose at arbitrary future times. PreSIST estimates instance-level persistence priors from object properties and scene context, then integrates these priors with a probabilistic persistence filter as observations become available. Its key insight is that the reasoning capabilities of vision-language models (VLMs) can relate scene context to likely object use and human activity, enabling persistence prediction before long-term observations are available. We develop two interchangeable variants: PreSIST-Lang, which estimates persistence priors using a VLM, and PreSIST-Vis, a novel vision-only model trained using PreSIST-Lang pseudo-labels for efficient deployment. Experiments on a new dataset of in-the-wild object persistence annotations show that PreSIST-Lang and PreSIST-Vis outperform baselines on open-world persistence prediction. --- ### A Policy Decomposition Framework for Dynamic Order Fulfillment Operations Authors: Gal Neria, Michal Tzur, Marlin W. Ulmer Published: 2026-07-04 Categories: math.DS, cs.LG, math.CO, math.OC arXiv: https://arxiv.org/abs/2607.04056v1 Modern supply chains span diverse operational environments, ranging from e-commerce distribution networks to customized production-to-order manufacturing lines. Across these settings, operational efficiency depends on coordinating two highly interdependent stages: order preparation and downstream delivery. Although these stages are traditionally managed in isolation, real-world fulfillment systems must satisfy stringent delivery expectations under dynamic stochastic order arrivals. To bridge this gap, we introduce the Dynamic Order Fulfillment Problem (DOFP), a new problem class unifying logistical challenges previously studied separately. We model DOFP as a Markov decision process whose state and decision spaces are partitioned into preparation and delivery sub-spaces, linked by synchronization constraints. While recent approaches attempt to optimize both fulfillment stages simultaneously over myopic rolling horizons, our framework isolates and optimizes the downstream delivery policy, treating preparation strictly as a state-level constraint filter. To solve this, we develop the Decomposition-Driven Framework with Value Function Approximation (DDF-VFA), which utilizes a novel policy-level decomposition. This design partitions the search into a delivery-stage master problem and a preparation-stage compatibility subproblem, iteratively refined via feedback loops. DDF-VFA executes this strategy by combining a large-neighborhood search over partial delivery decisions with a neural-network value function approximation for the cost-to-go. Numerical illustrations on two example variants using real-world datasets show that DDF-VFA consistently outperforms benchmarks that optimize the two stages independently or jointly without decomposition. Finally, the framework naturally scales to accommodate additional real-world complexities such as batched or multi-stage preparation. --- ### What is Left for Us? Second Scholarship Against the Degradation of Research by AI Authors: Claudio Novelli, Luciano Floridi Published: 2026-07-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.04049v2 We argue that generative AI can degrade research by eroding the very practices through which scholarly judgement is formed. As constitutive conditions for the production and validation of knowledge, these practices cannot be reduced to the outputs of research, which is what AI tools so effectively simulate. When scholars delegate central tasks of inquiry to Large Language Models (LLMs), they may stop engaging in these practices and lose the formation they provide: the output may improve while the researcher fails to develop. Against this risk, merely keeping humans "in the loop" as prompters or quality checkers of AI outputs is insufficient to preserve research as a site of intellectual formation. What is needed instead is a renewed commitment to research as a lived practice in which judgement is formed gradually, often through friction, and participation in a scholarly community. We defend it because it rests on four sources and warrants of research that cannot be automated: tacit knowledge, personal commitment, socialisation, and deep reading. These enact what we call second scholarship, i.e., the reappropriation of scholarly craft, chosen out of a critical experience of what AI tools can and cannot do. Researchers who practise it may delegate tasks to these tools, provided that their own judgement in the delegated competence is already formed, that they can answer for the output, and that they keep exercising the competence themselves. What cannot and should not be delegated becomes what research communities must value and answer for. This is what is left for us. --- ### What is Left for Us? Second Scholarship Against the Degradation of Research by AI Authors: Claudio Novelli, Luciano Floridi Published: 2026-07-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.04049v1 We argue that generative AI can degrade research by eroding the very practices through which scholarly judgement is formed and academic trust is built. As constitutive conditions for the production and validation of knowledge, these practices cannot be reduced to the final outputs of research, which is what AI so effectively simulate. Accordingly, when researchers delegate central tasks of inquiry to systems like Large Language Models, they may stop enacting these practices and, with them, lose access to the formation they provide. An individual research output generated by AI may even appear improved but the researcher behind it fails to develop. Against this risk, merely keeping humans in the loop as prompters or quality checkers of AI outputs is insufficient to preserve research as a site of intellectual formation. What is needed instead is a renewed commitment to research as a lived practice in which judgement is formed gradually, often through frictions, and participation in a scholarly community. We defend it because it rests on four sources and warrants of research that cannot be automated: tacit knowledge, personal commitment, socialisation, and deep reading. This practice enacts what we call second scholarship, by which we understand the reappropriation of scholarly craft, chosen out of a critical experience of what generative AI can and cannot do. What cannot and should not be delegated becomes what research communities must value and answer for. This is what is left for us. --- ### SiamJEPA: On the Role of Siamese Student Encoders in JEPA Authors: Makoto Yamada Published: 2026-07-04 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2607.04044v3 Joint Embedding Predictive Architectures (JEPAs) have emerged as a promising framework for self-supervised representation learning by predicting latent embeddings of masked regions rather than reconstructing pixels. Existing JEPA methods typically employ a single student encoder, leaving the role of Siamese student encoders largely unexplored. In this paper, we propose Siamese JEPA (SiamJEPA), a JEPA framework with masked Siamese student encoders and an exponential moving average (EMA) teacher, which can also be viewed as a JEPA formulation of the brain-inspired representation learning model PhiNet. We further introduce Random Shuffle Teacher (RST), which removes spatial correspondence in teacher targets to encourage semantic patch representations, and develop an RST-based semantic-to-spatial curriculum. Experiments on ImageNet show that Siamese student encoders effectively regularize the JEPA objective, improving representation separability and accelerating early-stage learning. Moreover, under RST, stronger Siamese regularization substantially increases class-discriminative information in individual patch tokens, suggesting that the semantic bias arises from the interaction between RST and the Siamese objective rather than from shuffling alone. SiamJEPA consistently outperforms comparable single-encoder JEPA variants under limited training budgets. With RST-based curriculum learning and a ViT-Base backbone, SiamJEPA achieves 74.2\% linear-probing accuracy after 450 epochs using a substantially simpler masking strategy, compared with I-JEPA (72.9\%) and DSeq-JEPA (73.5\%) after 600 epochs. These results demonstrate that Siamese student encoders provide an effective inductive bias for predictive representation learning and can be further enhanced through semantic-to-spatial curriculum learning. The source code is publicly available at https://github.com/oist/SiamJEPA. --- ### SiamJEPA: On the Role of Siamese Student Encoders in JEPA Authors: Makoto Yamada Published: 2026-07-04 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2607.04044v2 Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning. Unlike masked autoencoders that reconstruct pixels, JEPA models learn representations by predicting latent embeddings of masked regions. Existing JEPA-based methods, such as I-JEPA and V-JEPA, typically employ a single encoder in the student network. In contrast, using Siamese encoders for student network is more naturally aligned with brain-inspired representation learning frameworks, yet their role in JEPA models remains largely unexplored. In this paper, we investigate the effect of Siamese student encoders in JEPA-based representation learning. To this end, we propose SiamJEPA, masked Siamese student encoders equipped with an exponential moving average (EMA) teacher network. SiamJEPA can also be viewed as a JEPA formulation of the brain-inspired representation learning model PhiNet. Through extensive experiments on ImageNet linear probing, we demonstrate that Siamese encoders act as an effective regularizer for the JEPA objective, improving representation separability and accelerating learning during the early stages of training. Furthermore, SiamJEPA consistently outperforms comparable single-encoder JEPA variants under limited training budgets and achieves higher linear probing accuracy than Masked Autoencoders (MAE) which requires longer training. Our findings reveal that Siamese student encoders are not merely an architectural choice but constitute an important inductive bias for predictive representation learning. These results provide new insights into the design of JEPA-based models and suggest that incorporating Siamese student architectures offers a simple yet effective approach for improving self-supervised representation learning. --- ### Reward-Gated On-Policy Distillation Authors: Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi, Chanakya Ekbote, Sujay Sanghavi, Aleksandar Bojchevski Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04037v1 On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the teacher provides dense token-level supervision on the states the student actually visits. However, this supervision is not always reliable: a teacher can assign high likelihood to plausible but incorrect solutions, or low likelihood to correct student solutions that follow different reasoning paths. Unconditionally distilling the teacher can therefore reinforce bad modes or erase useful student behavior. To address these limitations, we introduce RG-OPD: Reward-Gated On-Policy Distillation that uses verifier feedback to decide when teacher logits should be trusted. RG-OPD bridges sparse verifier rewards and dense teacher logits, preserving token-level supervision while filtering misleading teacher signals. Across reasoning and coding benchmarks, RG-OPD produces stronger distilled students, outperforming both vanilla reverse-KL distillation and the recent TSD-KD baseline. At 1K generation length, RG-OPD improves over reverse-KL by 2.9 points and over TSD-KD by 4.9 points; in the long-generation setting, it improves over the untuned student by 8.2 points. Our code is available at https://github.com/UoC-tail/RG-OPD. --- ### The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling Authors: Stefan Broecker, Mason del Rosario, Boris Selitser, Thomas Strohmer Published: 2026-07-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.04034v1 The language models that underpin agents have seen a rapid rise in performance on function calling benchmarks. However, the metrics used in the training and evaluation of these models often encourage models to make positive claims even when the answer is uncertain, leading to hallucinations. Such hallucinations can be disastrous when language models are trusted to use function calls to make decisions in high stakes applications. To that end, we propose an agent evaluation metric that takes into account the negative outcomes associated with incorrect function calls. Further, to catch hallucinations before they can cause harm, we propose a lightweight trainable filter that can quantify a language model's uncertainty and remove potentially harmful function calls. By training that filter to detect and suppress uncertain function calls without modifying the underlying model, we demonstrate a practical path toward agents that know when to say "I don't know," a property we argue is essential to production reliability. --- ### OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers Authors: Siyuan Li, Jiabao Pan, Yumou Liu, Zhuoli Ouyang, Xin Jin, Xinglong Xu, Jingxuan Wei, Shengye Pang, Jintao Che, Xuanhe Zhou, Conghui He, Cheng Tan Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04033v1 Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the landscape of over one hundred methods remains fragmented. We therefore present OmniOpt, a unified survey and benchmark cookbook of optimizers for the research community. OmniOpt rests on four coupled components. First, we treat every optimizer update as a structured transformation through a five-stage meta-pipeline, and show that most methods engage only one or two of these stages. Second, we use norm-constrained linear minimization oracles (LMOs) to unify different optimizers. Third, these two views ground a dual-dimension taxonomy, one dimension assigning each method to a mechanism family and the other recording the measurable training objectives it aims to improve. Fourth, and at the core of this paper, we instantiate the full taxonomy in a unified cross-domain benchmark spanning representative optimizers, model scales, and training regimes from language model pretraining to image classification, systematically analyzing each method family across multiple effect objectives and laying out their trade-offs. OmniOpt thus supplies the research community with an operational coordinate system for selecting optimizers under explicit mechanism and objective assumptions, and charts a direction for the future development of the optimizer community. --- ### Efficient Discovery of Conditional Dependencies with Desbordante Authors: Ivan Kozhukov, Dmitry Fedoseev, Maksim Emelyanov, Artem Smola, Pyotr Senichenkov, Pavel Anosov, George Chernishev Published: 2026-07-04 Categories: cs.DB, cs.AI, cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2607.04030v1 Conditional functional dependencies (CFDs) are functional dependencies with a restricted scope: they specify the context in which a dependency holds and are useful for data-quality tasks, specifying complex integrity constraints, and extracting valuable insights from data. We study the CFD discovery problem, which is computationally demanding. We build on the state-of-the-art CFDFinder algorithm and introduce a set of algorithmic and engineering improvements, including a parallelization strategy, to produce ParCFDFinder. Our implementation is integrated into Desbordante - a high-performance open-source data profiler written in C++ that exposes a Python interface, enabling CFD discovery to be invoked from any Python program. Experimental results show that our enhancements speed up the algorithm by up to $318\times$ ($118\times$ on average) and reduce memory usage by up to $23\times$ ($14\times$ on average) compared with the existing Java-based implementation of Metanome. Integrating ParCFDFinder into Desbordante makes it possible, for the first time, to conveniently discover CFDs on datasets with hundreds of thousands of rows on a commodity machine within a reasonable time. --- ### CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals? Authors: Aisha Alansari, Malak Alkhorasani, Hamzah Luqman Published: 2026-07-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.04029v2 Recent hallucination detection techniques in large language models (LLMs) focus on directly extracting features from a model's internal representations and training a classifier on these features to detect hallucinations, demonstrating promising results. Notwithstanding this advancement, most internal-state hallucination detection techniques have been explored predominantly in English, raising the question of whether such internal signals generalize across different languages and domains. To address this gap, we present CrossHallu, the first study to evaluate the cross-lingual and cross-domain generalization of hallucination detection using internal representations from six LLMs on the generative question-answering task. We conduct a systematic Arabic <-> English evaluation using TruthfulQA, an Arabic translated version of TruthfulQA, and HalluScore. This evaluation encompasses monolingual training and testing, cross-lingual transfer, cross-domain transfer, and combined cross-lingual and cross-domain transfer. The results reveal that internal-state hallucination signals in LLMs transfer across languages and domains for most models, with cross-lingual performance highly dependent on both class separability and language alignment in the feature space, whereas cross-domain transfer within Arabic varies depending on the training and testing datasets used for the hallucination detector. The code is publicly available at https://github.com/aishaalansari57/CrossHal. --- ### A Unified Algebraic Framework for Classification Performance Evaluation Authors: Ronaldo C. Prati Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04028v2 We propose a unified algebraic framework for classification performance evaluation covering binary, multiclass, multilabel, ordinal, hierarchical, cost-sensitive, and soft-label settings. Actual and predicted labels are represented as binary indicator matrices, where three aggregation operators (global, column-wise, row-wise) correspond directly to micro, macro/weighted, and exemplar averaging. Any binary measure expressed in terms of the four confusion-matrix counts extends to all these settings by substituting an operator, with no measure-specific derivation. We show that structural properties governing an extension are derivable from the binary formula. Micro-averaging equals denominator-weighted macro-averaging precisely for aggregation-decomposable (linear-fractional) measures, a strict class characterised algebraically. For soft ground truth, we prove from t-norm axioms alone that the product t-norm is the unique choice whose confusion counts preserve marginal memberships. In multiclass settings, micro-precision, micro-recall, and micro-F1 collapse identically onto accuracy. Furthermore, binary skew-invariance transfers unconditionally to multilabel aggregation, but only partially to multiclass problems. For measures with a linear numerator and prediction-independent denominator, the optimal decision threshold is the share of the numerator weight favouring a negative prediction, revealing when standard training targets the measure. Under one-hot multiclass encoding, a measure fails to attain its theoretical minimum whenever its zero-true-positive value still depends on true negatives, establishing non-trivial performance floors even for completely incorrect classifiers (e.g., zero correct predictions on 10 classes yields a label accuracy of 0.8). --- ### A Unified Algebraic Framework for Classification Performance Evaluation Authors: Ronaldo C. Prati Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04028v1 We propose a unified algebraic framework for classification performance evaluation that encompasses binary, multiclass, multilabel, ordinal, hierarchical, cost-sensitive, and soft-label settings within a single formalism. The foundation is a representation of actual and predicted labels as binary indicator matrices, combined with three aggregation operators -- global, column-wise, and row-wise -- that correspond exactly to micro, macro/weighted, and exemplar averaging. Any binary performance measure expressed in terms of true/positive/negative counts extends automatically to all settings by substituting these operators, generating multiclass and multilabel versions without measure-specific derivations. The framework further accommodates soft classifier outputs via argmax or thresholding, soft ground truth via triangular norms, ordinal classification via membership functions or cumulative encodings, and cost-sensitive evaluation via a cost matrix that subsumes MAE and MSE as special cases. We establish several theoretical results: micro-averaging equals denominator-weighted macro-averaging; the product $t$-norm is the unique one preserving the confusion-matrix partition; skew-invariant measures are characterised as functions of recall and specificity; and micro-precision, micro-recall, and micro-$F_1$ are all equal to accuracy in multiclass settings. Empirical illustrations on synthetic and real data confirm the theoretical findings. --- ### Paired Uterine Whole-Slide Images and Pathology Reports for Multimodal Computational Pathology Authors: Han Li, Jingsong Liu, Ayako Ura, Junlin Hou, Zhengyang Xu, Azar Kazemi, Oskar Thaeter, Christian Grashei, Fabian Gülhan, Reza Nasirigerdeh, Xun Ma, Rui Yan et al. Published: 2026-07-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04020v2 Uterine diseases represent an important category of gynecologic pathology and require accurate histopathological assessment for diagnosis and treatment planning. Whole-slide images (WSI) have enabled the digital transformation of pathology workflows and provided new opportunities for artificial intelligence (AI) in computational pathology. In particular, multimodal models that jointly analyze histopathology images and pathology reports have shown promising potential for automated pathology report generation and AI-assisted diagnosis. However, the development of such systems remains limited by the scarcity of datasets that pair whole-slide images with clinically meaningful pathology reports. Instead, existing pathology datasets focus on patch- or slide-level annotations of a single endpoint (e.g., disease class), which do not fully capture the rich information in full clinical diagnostic workflow reports. Here, we introduce TUM-Uteria, a uterine pathology dataset comprising WSIs paired with diagnostic pathology reports at both the case and slide levels, collected from a tertiary medical center. The dataset contains 216 clinical cases, comprising 455 slide-level WSI-report pairs. The dataset underwent a structured multi-stage validation procedure involving board-certified pathologists to ensure reliable annotations. TUM-Uteria supports research in computational pathology, including whole-slide image analysis, multimodal learning, and automated pathology report generation. --- ### Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making Authors: Hyung-Jin Yoon, Hunmin Kim Published: 2026-07-04 Categories: eess.SY, cs.AI, cs.RO, math.OC arXiv: https://arxiv.org/abs/2607.04019v1 Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use. We introduce Finite Reliability Representations (FRR), a framework for covering belief spaces by reliability cells: regions within which the optimal action-value function Q*(b,u) varies by at most a tolerance epsilon, uniformly over actions. The framework is formulated on beliefs rather than states and uses a cover rather than an equivalence quotient, because approximate decision-closeness is not transitive in general. A central technical point is that noisy Bayesian updates should not be treated as globally contractive on arbitrary beliefs. We therefore separate three objects: the fixed-observation filter map, the predictive observation law, and the controlled belief-transition kernel. For nonlinear continuous-state systems, FRR is obtained under a reachable-set Lipschitz modulus for the belief-transition kernel. For finite-state POMDPs, the same construction becomes exact on the belief simplex: prediction is linear, Bayesian correction is a normalized positive linear map, sensor noise enters through observation-distribution distinguishability, and actuation uncertainty enters through an action-execution channel. Under the corresponding action-value Lipschitz condition, an FRR cover supports a cell-constant policy whose suboptimality is bounded by 2 epsilon/(1 - gamma). We also introduce reliability entropy, the logarithm of the minimal number of reliability cells, as a measure of certified decision-relevant belief complexity. The framework distinguishes representation sufficiency from fundamental performance floors imposed by sensing, process, and actuation noise. It applies to finite POMDPs, linear-Gaussian filters, locally linearized nonlinear filters, and particle-filter implementations through analytic or empirical certification of reliability cells. --- ### SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding Authors: Chenyi Kuang, Nakul Agarwal Published: 2026-07-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04017v1 Human object interaction (HOI), gaze pattern, and their anticipation are intricately linked, providing valuable insights into cognitive processes, intentions, and behavior. However, most existing models handle gaze and actions separately, missing both their interdependence and the advantages of a unified solution. This paper presents a novel unified framework, SAGE (Synchronized Action-GazE), which integrates simultaneous recognition and anticipation of both HOI and human gaze into a single unified end-to-end trainable model. Our approach leverages a transformer-based architecture and incorporates gaze data into spatiotemporal attention mechanisms to simultaneously predict current and future human actions and gaze behavior. We explore this bidirectional relationship between gaze and actions under different scenarios, whether requiring a close-up, detailed view (egocentric) or a wider, more contextual view (exocentric), making our framework versatile for various applications. Additionally, due to lack of datasets for comprehensive analysis of both HOI and gaze in exocentric videos, we establish a new benchmark Exo-Cook to facilitate further research in this domain. Experiments on three benchmark datasets: VidHOI, EGTEA Gaze+, and Exo-Cook show that jointly modeling gaze and actions across current and future frames achieves consistently strong results, often surpassing specialized state-of-the-art models tailored to individual tasks. By unifying actions and attention in a comprehensive way, our work lays the groundwork for more intuitive human-machine interaction. --- ### When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah Authors: AlJawharh S. AlOtaibi, Mohamed Eltahir, Jude AlSubaie Published: 2026-07-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04013v1 Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling is costly, such as crowd monitoring during Hajj and Umrah. Tabular foundation models, which predict from only a handful of examples without task-specific training, were recently introduced to address this very-few-label regime. In this study we test them on crowd-state classification to assess how much they help when labels are scarce, and we compare them against standard machine learning methods to characterize the accuracy and efficiency trade-offs between the two approaches. Using three real datasets we evaluate different machine learning models, in untuned and tuned forms, against three foundation models. Results show that no single family is best everywhere. The right choice depends on the label budget. When labels are very few, foundation models lead. As labels grow, tuned conventional models catch up and significantly surpass the foundation models on the more structural geometry target. Efficiency separates them further where tuned machine learning models incur a large tuning cost that foundation models avoid, although foundation models reprocess their context at every prediction. We summarize these results as a practical map of which approach to prefer under a given label budget and computational budget. --- ### Separating Representation from Reconstruction Enables Scalable Text Encoders Authors: Megi Dervishi, Mathurin Videau, Yann LeCun Published: 2026-07-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.04011v1 While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the representations of BERT encoders become increasingly $\textit{unexploitable}$ by frozen probes, despite improved perplexity. The misalignment originates in BERT's flat design, which couples representation learning to the token reconstruction loss. We propose $\textbf{CrossBERT}$, a two-part architecture that separates the learning of high-quality encoded representations from the rigid grounding of token reconstruction. This design further enables high masking ratios ($\ge 50\%$) and gradient collection over all tokens via a $\textit{Complementary Masking Strategy}$, respectively increasing throughput by $1.5$ to $2\times$ and sample efficiency by $2\times$. Overall, CrossBERT demonstrates monotonic scaling and superior performance on MTEB(eng, v2) and frozen GLUE benchmarks. --- ### Explainable AI for Screening Abuse-Related Trauma in Bangladeshi Children: A Training-Free Multimodal Framework Evaluated on Noise-Aware Synthetic Data Authors: Salma Hoque Talukdar Koli, Fahima Haque Talukder Jely Published: 2026-07-04 Categories: cs.AI, cs.CL, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2607.04010v1 Bangladesh has an estimated 1.17 mental-health professionals per 100,000 population and only six child psychiatrists nationwide. No Bengali-language, culturally adapted tool exists for early screening of abuse-related psychological trauma in children. We present ShishuRaksha AI, a decision-support (not diagnostic) framework that fuses four screening modalities: validated questionnaires (SDQ, CPSS), Bengali narrative text, House-Tree-Person (HTP) drawing features, and facial affect. The fusion is training-free and clinically weighted, uses cross-modal attention, and includes a single-modality override rule. Every risk score is explained through clinically weighted, perturbation-based additive attribution and rendered as a bilingual (Bangla/English) report with referral routing to national child-protection services (OCC, DSS, NMHH) under the Children Act 2013. No clinical dataset of abused children can be collected ethically at this stage, so we introduce a noise-aware synthetic benchmark (500 cases, 116 positive (23.2%), four deliberate noise layers, literature-grounded HTP priors) and evaluate tree-ensemble surrogates of the fusion design (facial channel excluded) under 5-fold stratified cross-validation. The fused model reaches an AUC of 0.874 (0.834-0.908), against 0.756 (0.705-0.803) for an SDQ-only baseline, with ablation, operating-point, subgroup, and calibration analyses. We state all limitations openly, including synthetic-only data, no held-out set, text-feature circularity, and an urban-rural subgroup gap. This work is a feasibility study and a design contribution toward ethically deployable child-protection screening in low-resource settings. --- ### Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis Authors: Yingdong Yang, Haijian Wu Published: 2026-07-04 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.04008v1 We present a candidate-constrained retrieval-augmented generation system for LongEval-RAG, where each query is associated with an organizer-provided candidate set and all retrieved evidence and final citations must remain within that set. The system combines deterministic provenance tracking with passage-based retrieval, deterministic query expansion, pseudo-relevance feedback (PRF), reciprocal rank fusion (RRF), lightweight evidence reranking, citation-aware evidence aggregation, and optional MiniLM sentence reranking. We evaluate ten pipeline variants using a primary organizer evaluation and a supplementary self-generated diagnostic protocol. The primary evaluation shows that the strongest balanced variant is rule-minilm: a rule-based chunking pipeline with query expansion, PRF, RRF, reranking, citation prior, and late MiniLM sentence selection. This variant obtains the highest BERTScore, retrieval precision, nugget coverage, and average grade among our submissions. The result suggests that the main gain does not come from more complex semantic or topic-shift chunking, but from pairing stable rule-based evidence units with sentence-level neural selection before generation. The supplementary LLM-judge evaluation remains useful for early diagnosis and additional analysis, but it emphasizes different systems than the primary gold-answer and nugget-based evaluation, highlighting the need for multi-metric RAG evaluation. --- ### Significance-First Splitting: Aligning Treatment Heterogeneity Detection with Honest Estimation Authors: Pantelis Z. Hadjipantelis, Weng Man Chiang, Karthik Nagesh Published: 2026-07-04 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.03999v2 Estimating heterogeneous treatment effects (CATE) requires simultaneously detecting effect modification and quantifying estimation uncertainty. Existing tree-based methods make an uneasy trade-off: significance-based approaches (Radcliffe and Surry 2011) identify subgroup interactions directly but lack valid inference; honest causal trees (Athey and Imbens 2016) deliver nominal confidence interval coverage but use outcome-agnostic splitting criteria that sacrifice interaction sensitivity. We introduce a hybrid algorithm that fuses significance-based splitting with honest sample-splitting and cross-validation. Our splitting criterion uses the squared $t$-statistic for the treatment $\times$ side interaction ($t^2$), which is shown to be directly aligned with the honest $\text{EMSE}_τ$ criterion when the interaction is strong. Post-hoc honest cross-validation selects the cost-complexity penalty, giving a single principled estimator with nominal CI coverage at the leaf level. For forests, we retain bootstrap count vectors to enable an infinitesimal jackknife (IJ) variance estimate of Monte-Carlo convergence rather than formal pointwise inference. On the three synthetic designs from (Athey and Imbens 2016) the single tree achieves approximately 90% leaf-average CI coverage at the 90% nominal level across all three designs (200 replications each); on the Criteo, Hillstrom and Starbucks uplift datasets we match Qini coefficient performance of S-, T-learner and GRF baselines. An open-source Python package with reproducible seeds, sklearn-compatible API, and full test coverage accompanies this work (https://codeberg.org/hadjipantelis/rattus). --- ### Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam Authors: Ashmitha R, Jörg Frochte Published: 2026-07-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.03998v4 The local sharpness of the loss, the top Hessian eigenvalue $λ_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector products. A single Armijo backtracking line search already carries this information at the cost of a few forward passes: the accepted step $α$ brackets the directional curvature along the probed direction within the multiplicative band set by the backtracking factor: exactly the curvature averaged over the tested step, and empirically $q = g^\top H g/\|g\|^2$ to within that band. Across CIFAR-10, Fashion-MNIST and Imagenette, $\logα$ tracks $\logλ_1$ at Pearson $-0.91$ to $-0.95$, and the relation survives a per-run detrending check at $-0.60$ to $-0.70$, a low-cost online Edge-of-Stability reading of the slow sharpness component. Used as a safeguard rather than a faster optimiser, the reading caps a too-large initial learning rate. A single fixed protocol, probing along Adam's own update direction at initialisation and over the first fifty optimiser steps and capping the rate at twice the smallest reading, removes every divergence across learning-rate grids spanning $10^{-3}$ to $3.0$ and at GPT-2 pretraining scale, and all but one marginal case across the further architectures we test, at about $1\%$ overhead, and it leaves training bit-identical whenever the cap does not bind. No constant in the protocol is tuned per architecture; this is the sense in which the safeguard is calibration-free. The guarantee is divergence, not accuracy: where the productive range is narrow the capped run survives at strongly reduced accuracy (chance level on AG News at aggressive rates), and our measurements show why any cap frozen at initialisation must fail at pretraining scale: the loss surface sharpens within the first five optimiser steps, the gap warmup has always filled by convention. --- ### Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam Authors: Ashmitha R, Jörg Frochte Published: 2026-07-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.03998v3 The local sharpness of the loss, the top Hessian eigenvalue $λ_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector iterations. We observe that a single Armijo backtracking line search already carries this information at the cost of a few forward passes: the accepted step $α$ brackets the \emph{directional} curvature $q = g^\top H g/\|g\|^2$ within the multiplicative band set by the backtracking factor. Across CIFAR-10, Fashion-MNIST and Imagenette, $\logα$ tracks $\logλ_1$ at Pearson $-0.91$ to $-0.95$, giving a low-cost online Edge-of-Stability reading. Used once at initialisation, this measurement yields a learning-rate cap (a safeguard, not a faster optimiser) that makes Adam robust to a too-large initial learning rate across more than three orders of magnitude ($10^{-3}$ to $3.0$), at about one percent overhead, and it is a no-op when the chosen rate is already safe. One probe is enough: periodic in-training probing adds no robust benefit. The raw-gradient probe exposes the mechanism but needs a safety factor calibrated to the architecture by a one-minute divergence sweep. Probing along Adam's own update direction removes this calibration: a single fixed safety factor $κ= 2$ avoids divergence on all nine architectures we test and across the full learning-rate grids of all four benchmarks, and the recipe transfers to AdamW unchanged. --- ### One Image, No Tokens: A Controlled Study of Glyph-Based Chinese Language Modeling Authors: Shuyang Xiang, Hao Guan Published: 2026-07-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.03994v2 Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned. We challenge this representation, especially for Chinese, by replacing index-based token embeddings entirely with a single rasterized image of the character sequence, processed by a vision encoder composed of a shared ResNet and a shallow Vision Transformer. To isolate the role of input representation, we construct a dual-branch controlled framework in which both a Vision-based model and an index-based baseline share an identical decoder backbone, training objective, optimizer, and data curriculum. Any performance difference is therefore attributable to the input modality only. Across all tested decoder backbones, the Vision-based model consistently outperforms the baseline, reaching a peak accuracy of 0.429 versus 0.355 for the index-based baseline---a 21\% relative improvement---while converging in about half the number of training epochs. The advantage emerges especially within the first five epochs (under 21\% of total data) and persists under moderate character corruption: the corrupted Vision model matches the \emph{clean} index-based baseline. Ablation studies reveal that the advantage requires both spatially coherent input and a ViT encoder with 2D positional encodings. A cross-script comparison on English shows the advantage does not transfer directly to alphabetic writing systems, suggesting that the uniform visual density and radical structure of Chinese characters are enabling conditions. These findings suggest that transformers are more modality-agnostic than commonly assumed, and that discrete tokenization is not a fundamental requirement for Chinese language modeling. --- ### Full Glyph Images Beat Token Embeddings: A Controlled Study for Transformers Authors: Shuyang Xiang, Hao Guan Published: 2026-07-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.03994v1 Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned. We challenge this representation, especially for Chinese, by replacing index-based token embeddings entirely with a single rasterized image of the character sequence, processed by a vision encoder composed of a shared ResNet and a shallow Vision Transformer. To isolate the role of input representation, we construct a dual-branch controlled framework in which both a Vision-based model and an index-based baseline share an identical decoder backbone, training objective, optimizer, and data curriculum. Any performance difference is therefore attributable to the input modality only. Across all tested decoder backbones, the Vision-based model consistently outperforms the baseline, reaching a peak accuracy of 0.429 versus 0.355 for the index-based baseline,that is, a 21% relative improvement, while converging in about half the number of training epochs. The advantage emerges especially within the first five epochs (under 21% of total data) and persists under moderate character corruption: the corrupted Vision model matches the clean index-based baseline. Ablation studies reveal that the advantage requires both spatially coherent input and a ViT encoder with 2D positional encodings. A cross-script comparison on English shows the advantage does not transfer directly to alphabetic writing systems, suggesting that the uniform visual density and radical structure of Chinese characters are enabling conditions. These findings suggest that transformers are more modality-agnostic than commonly assumed, and that discrete tokenization is not a fundamental requirement for Chinese language modeling. --- ### Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL Authors: Yaron Anavi, Mor Aisenberg, Nadav Nesher, Elena Khabibullina, Isabella Cattinelli Published: 2026-07-04 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.03991v1 Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open question is when to stop, when the consistency has converged. We formulate this as a convergence-prediction problem and train a family of lightweight 1-D models that observe the running consistency trajectory and decide, at each step, whether further runs are unlikely to shift it materially, and we benchmark them against a principled Beta-Bernoulli stopping rule and a learned run-count baseline. On the BIRD benchmark and two production customer datasets, our method adapts its stopping point to each user question, halting sooner when consistency converges early and continuing longer when it converges late. We further show that the weak serial correlation between runs lets us permute their order as a training augmentation, controlled by a tunable shuffling weight. Performance stays consistent across the three datasets, and to mimic an imperfect production judge we inject noise into the correct/incorrect verdicts obtained by comparing the generated and ground-truth SQL results, showing that the method still predicts convergence reliably. --- ### InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image Authors: Gwanhyeong Koo, Hyunsu Kim, Youngji Kim, Taejae Lee, Siwoo Lim, Sunjae Yoon, Suyong Yeon, Chang D. Yoo Published: 2026-07-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.03990v1 Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation remains challenging. Existing methods focus on asset-level generation while neglecting the structural layout, which is essential for downstream applications and serves as the spatial anchor for grounding assets. However, a single image with a limited field of view lacks the spatial coverage to recover a coherent global layout. To this end, we use a 360° image represented in equirectangular projection (ERP) and propose InSpace, a structure-aware framework for 3D indoor scene generation. InSpace comprises three stages: (1) estimating partial scene geometry as spatial priors, (2) generating coarse scene structure with view-selective cross-attention, and (3) producing detailed layout and asset geometry with textures through a global-local hybrid attention, using flow matching. We also propose ERP-FRONT, a paired ERP-Image-to-3D indoor scene dataset based on 3D-FRONT. Experiments show that InSpace generates complete 3D indoor scenes with structural layout, along with separate textured assets from a single ERP image, achieving strong performance across 3D and 2D metrics. Project Page: https://kookie12.github.io/InSpace-Project-Page/ --- ### NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization Authors: Meiying Melissa Chen, Anastasia Kuznetsova, Zhenyu Wang, Zhiyao Duan Published: 2026-07-04 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2607.03985v1 Advanced neural technologies in speech synthesis and voice conversion (VC) have introduced severe risks to personal privacy, necessitating robust Speaker Anonymization Systems (SAS). Existing SAS approaches modify voice characteristics in the hand-crafted feature space or speaker embedding space, often struggling to provide sufficient identity variance across generated voices. In this paper, we propose NouveauVoice, a novel pseudo-speaker generation framework based on a Hierarchical Deep Variational Autoencoder (NVAE). Integrated as a standalone plug-in module on top of state-of-the-art architectures (FACodec and CosyVoice2), our approach leverages tractable sampling and the Evidence Lower Bound (ELBO) objective to synthesize highly expressive pseudo-speaker embeddings with significantly enhanced speaker diversity. Evaluating our framework under a protocol similar to the VoicePrivacy Challenge alongside Maximum Mean Discrepancy (MMD) analysis, we demonstrate that NouveauVoice achieves strong identity concealment, yielding an Equal Error Rate (EER) exceeding 38% against an automatic speaker verification attacker model. Our system shows a reasonable trade-off between strict anonymity, rich pseudo-speaker diversity, and downstream speech utility, such as intelligibility and emotional expressiveness. --- ### BanglaMemeEvidence: A Multimodal Benchmark Dataset for Explanatory Evidence Detection in Bengali Memes Authors: Fatema Tuj Johora Faria, Mukaffi Bin Moin, Md. Mahfuzur Rahman, Pronay Debnath, Asif Iftekher Fahim, Faisal Muhammad Shah Published: 2026-07-04 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.03981v1 Memes have become influential communication tools on social media, combining viral visuals with concise messaging to convey impactful ideas. While substantial research has examined the affective dimensions of memes, key challenges such as detecting harmful content, identifying cyberbullying, and performing accurate sentiment analysis remain critical, largely due to the need for deeper contextual understanding. In this paper, we introduce MemeEvidenceDetect, a hybrid task aimed at analyzing a meme and its contextual information to identify specific sentences that explain or elucidate its meaning and humor. To support this task, we present BanglaMemeEvidence, a curated dataset of 2,917 Bengali memes, emphasizing its significance as a resource for the Bangla language. Each meme is annotated with natural language explanations, including Meme OCR, Meme Context, and Evidence Sentences, alongside relevance scores that reflect the relationship between a meme and its corresponding annotations. To address the gap in dynamically inferring a meme's context, we propose BengaliMemeEvidenceNet, a hybrid multimodal framework that integrates textual and visual features for comprehensive meme representation. Our experiments demonstrate the effectiveness of BengaliMemeEvidenceNet, achieving an F1 score of 0.74. To the best of our knowledge, this is the first study to focus on evidence detection in Bengali memes, marking a notable step forward in the analysis of memes in low-resource languages. --- ### Scalable Semantic Steering of Embedding Projections Authors: Wei Liu, Eric Krokos, Kirsten Whitley, Rebecca Faust, Chris North Published: 2026-07-04 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.03978v1 Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relationships. Recent LLM-augmented semantic steering methods address this gap by externalizing analyst intent from user-defined groups of seed examples, but they propagate intent through per-item LLM reasoning, causing LLM calls and cost to grow linearly with collection size. We propose a scalable semantic steering method that shifts semantic computation from individual items to user-defined groups. A single LLM call generates structured profiles for all groups, which are embedded and combined with seed centroids to form hybrid semantic prototypes. The method then propagates intent without retraining, using embedding-space soft assignment, abstention, and alignment-scaled updates before reprojection. On a 5K-document LitCovid corpus, our method achieves global alignment comparable to per-item LLM steering while reducing LLM calls by over three orders of magnitude. An image case study shows that the same prototype-based mechanism extends to multimodal embeddings. These results suggest that group-level representations can make semantic steering more practical for larger embedding collections. ---