# Research Papers — 2026-08 · bundle page 94 of 240 > Full-text markdown of papers #4651–4700 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/94 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/95.md) ### Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery Authors: Alizer Wong, Heng Cui, Yi Tan, Xiongchao Zhan, Liang Lin, Yuxiang Guo, Zhaorong Dai, Zixin Zeng, Wenyuan Li Published: 2026-08-19 Categories: cs.AI, math.NT arXiv: https://arxiv.org/abs/2608.19047v1 We present Eureka, a task-conditioned Meta-Agent architecture that compiles long-horizon tasks into dynamic obligation graphs with explicit acceptance semantics. During execution, Eureka forms Macro-Agents with specialized state, memory, operators, tools, verifiers, and local topology via receding-horizon planning, architecture promotion, and minimal-sufficient compilation. When bottlenecks recur, cost-benefit-gated evolution updates the local architecture under constraints. Theoretically, we establish results on regret, planning invalidation, amortization, subtree interfaces, serializability, and verification. Experimentally, Eureka completes 170/170 recursive tasks and generates 3,948 certificates with no false acceptances. Active context compresses median input from 9,490 to 4,005 tokens; incremental processing avoids 65.38% recomputation across 12,000 tasks; 16,000 concurrent executions serialize consistently. The same Meta-Agent instantiates a Theory-Discovery Agent and a Math/Conjecture Agent. The former yields structural results in quantum-process and spacetime theory. The latter identifies bottlenecks in Riemann Hypothesis research and advances a positivity certificate for Suzuki's localized Weil quadratic form to 0 < a <= 69/200 = 0.345, reaching ~99.55% of (log 2)/2. These results suggest that scientific-agent capability depends not only on the base model but on whether an architecture can be formed to match the task's cognitive structure. --- ### Bernstein-Vazirani Networks: Quantum Machine Learning by Interference Authors: Natacha Kuete Meli, Tolga Birdal, Prayag Tiwari, Vladislav Golyanik, Michael Moeller Published: 2026-08-19 Categories: quant-ph, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.19043v1 We introduce Bernstein-Vazirani Networks (BVNs), a non-variational quantum machine learning framework that leverages quantum interference for supervised learning, demonstrated on vision and representation learning tasks. In their standard form, BVNs follow the principle of quantum Fourier sampling: labelled data are placed in superposition and interfered in the Fourier basis to extract globally informative features. We then define generalised BVNs that enable interference in problem-adapted bases, yielding more expressive models under the same measurement budget as in the standard setting. BVNs achieve universal function approximation through (over)complete interference bases, while training of BVNs is gradient-free. Experiments on synthetic and real-world classification tasks, as well as implicit image representation, show strong generalisation capabilities and competitive performance with classical and quantum baselines. --- ### USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes Authors: Li-Heng Chen, Haokai Pang, Chengye Su, Jiarun Liu, Qifeng Chen, Ziqian Ni, Jianxin Huang, Shi-Sheng Huang, Hongbo Fu, Sheng Yang Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.19036v1 Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-oriented 3D primitives (\eg, 3D Gaussians) serve as two distinct yet highly complementary levels for scene understanding. Existing methods typically treat dynamic reconstruction and instance-level perception as separate tasks, despite their shared goal of estimating the underlying 3D world state. As a result, dynamic reconstruction is under-constrained while 3D detection lacks geometric grounding. To address this gap, we propose USR-Drive, a unified conditional generative framework that, given only posed multi-view driving videos, jointly recovers dense dynamic geometry and instance-level object layouts within a shared scene representation. Specifically, USR-Drive represents dense Gaussian primitives and sparse 3D bounding boxes as two aligned latent token streams and jointly denoises them with a unified multi-modal diffusion Transformer. Unlike prior paradigms that use boxes as external conditions or predict them with detached modules, USR-Drive treats them as mutually constrained state variables with a Unified Positional Encoding (UPE) that aligns heterogeneous tokens within a shared metric spatiotemporal coordinate. Via such unified representation and generative framework, the two modalities reinforce each other: geometry supplies dense metric evidence for box prediction, while boxes provide instance-level structural priors that help preserve spatial consistency and reduce ambiguity in sequential 3D geometric representation. Our approach successfully delivers state-of-the-art results for both dynamic reconstruction and 3D detection on the nuScenes and VKitti datasets. --- ### Counterfactual Contrastive Analysis Authors: Yunlong He, Pietro Gori Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.19032v2 Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the classifier's prediction. Existing VCE methods are inherently classifier-dependent and therefore susceptible to classifier biases and failure modes, such as sensitivity to shortcut features and calibration errors. In this paper, we propose a classifier-free approach for visual counterfactual generation based on Contrastive Analysis (CA). Given two datasets corresponding to different classes (e.g., healthy and patients), we disentangle the generative factors that are common across the two datasets from those that are salient to each dataset, and generate counterfactual images by swapping only the salient factors. By operating directly on data distributions rather than decision boundaries, our method provides model-agnostic VCEs that are less sensitive to classifier biases. Our approach leverages the high-quality synthesis and well-structured latent space of StyleGAN2. We use the feature space F, instead than the usual W-space, to improve detail preservation. Unlike conventional CA approaches, which typically assume salient factors in only one dataset, we introduce an adapted framework and loss functions for VCE that allow multiple salient factors in each dataset. We evaluate our method on three medical imaging datasets and demonstrate superior counterfactual generation quality compared to existing approaches. --- ### Counterfactual Contrastive Analysis Authors: Yunlong He, Pietro Gori Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.19032v1 Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the classifier's prediction. Existing VCE methods are inherently classifier-dependent and therefore susceptible to classifier biases and failure modes, such as sensitivity to shortcut features and calibration errors. In this paper, we propose a classifier-free approach for visual counterfactual generation based on Contrastive Analysis (CA). Given two datasets corresponding to different classes (e.g., healthy and patients), we disentangle the generative factors that are common across the two datasets from those that are salient to each dataset, and generate counterfactual images by swapping only the salient factors. By operating directly on data distributions rather than decision boundaries, our method provides model-agnostic VCEs that are less sensitive to classifier biases. Our approach leverages the high-quality synthesis and well-structured latent space of StyleGAN2. We use the feature space F, instead than the usual W-space, to improve detail preservation. Unlike conventional CA approaches, which typically assume salient factors in only one dataset, we introduce an adapted framework and loss functions for VCE that allow multiple salient factors in each dataset. We evaluate our method on three medical imaging datasets and demonstrate superior counterfactual generation quality compared to existing approaches. --- ### Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering Authors: Pradeep Murugesan, Luoxiao Yang, Xueli Chen, Xinqi Fan Published: 2026-08-19 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2608.19029v1 Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases require factual knowledge and nuanced reasoning. Existing medical QA systems, typically based on single-agent architectures and static retrieval, often lack adaptability, persistent memory, and structured decision-making. This work introduces an adaptive memory and reflection (AMR) agentic system, a multi-agent framework in which specialized agents use dedicated memory and reflection-based feedback to retrieve relevant prior cases and improve subsequent reasoning. Complexity assessment routes questions through solo, collaborative, or escalated workflows, while consensus and ethical overseer modules support reasoning consolidation and output review. Evaluation on MedQA and MedMCQA demonstrates strong performance compared with several baselines. Ablation studies show that combining agent-specific memory, reflection, and external retrieval yields the strongest performance. These findings highlight the potential of structured memory and feedback for developing more trustworthy medical agents. The source code is publicly available at https://github.com/mm-air/AMR-Agent. --- ### Institutional Books - Enriched Text: A customizable multilingual open-source pipeline for denoising, deduplicating, and annotating OCR text at scale Authors: David Lowry-Duda, Matteo Cargnelutti, Catherine Brobston, Salwa Ismail, Greg Leppert, Amanda Watson, Jonathan Zittrain Published: 2026-08-19 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2608.19026v1 Released in 2025, Institutional Books: Harvard Library (IB-HL) is a collection of 983,004 volumes (242B o200k_base tokens), originally digitized through Harvard Library's participation in the Google Books Library project. As researchers and developers have begun to use IB-HL, a tension has emerged between standard large-scale preprocessing practices and the goals of careful information stewardship. Many existing pipelines optimize for web text: as a result, they tend to aggressively filter, deduplicate, restrict by language, and sometimes discard meaningful metadata. Meanwhile, researchers seeking to use IB-HL duplicate effort while performing similar processing and analysis. We describe an approach that we call Enriched Text. Instead of producing a single 'complete' stream of tokens, we normalize the text while preserving metadata through annotations. We separate endmatter, detect per-paragraph language, identify clusters of duplicate paragraphs, and compute per-paragraph bits-per-byte scores. We provide this information through HTML-like annotations layered on top of the text. By parsing these annotations, users can tailor the output to their own needs instead of accepting a global editorial decision on content. The pipeline applies to all $\approx$250 languages in the collection. This report describes this project's goals, implementation, and design rationale. The release includes IB-HL-ET (an enriched-text version of IB-HL containing 217B o200k_base tokens across 983,003 volumes, organized into 1.39B annotated subtopic paragraphs) and the pipeline that produced it. These serve to make the collection easier for machines to parse and for humans to study. --- ### Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models Authors: Valentin Romanov, Monique Bax, Steven Niederer Published: 2026-08-19 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2608.19025v1 Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based large language models (LLMs) to extract highly contextualized information. We demonstrate four escalating workflows, 1) given an expert curated prompt and research articles, most frontier LLMs perform well at data extraction, however can struggle with interpreting scientific context and nuance, 2) given simple instructions, LLMs can author their own prompts which were almost as eNective as expert-written prompts, 3) autonomous discovery of research literature was diNicult, agents either missed or hallucinated references, and 4) LLMs can create new datasets from published guidelines that closely match human-expert judges, but still require a human-in-the-loop. Together, these findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases, providing a practical route to scaling scientific data curation without relinquishing expert oversight. --- ### Scalable Amortized Variational Inference for Non-Poisson Buy-'Til-You-Die Models Authors: Sulagna Ghosh, Aaron Schein Published: 2026-08-19 Categories: stat.AP, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.19022v1 Despite the wide variety of existing Buy-`Til-You-Die (BTYD) models, nearly all rely upon the convenient assumption of transactions following a Poisson process. As modern customer bases grow larger and more diverse, a major gap in the marketing literature is BTYD models that can account for heterogeneity in timing patterns across millions of customers. This paper addresses that gap, introducing a family of models that assume transactions follow a Weibull renewal process and developing a highly scalable scheme for parameter estimation based on an amortized variational inference procedure. The proposed model fits to a proprietary dataset of 5 million online retail customers in 8 minutes which would take the current state-of-the-art an estimated 3-4 days. We show both theoretically and empirically that this dramatic improvement in computational performance comes with no appreciable change to either model interpretation or predictive performance. Beyond scalability, gradient-based variational inference also makes it easy to extend the model to covariates, which we illustrate on a public dataset of 4 million political donors during the 2020 US General election cycle. More generally, this paper demonstrates how to blend recent advances in approximate Bayesian inference and the tools of modern machine learning to dramatically improve the efficiency and expressivity of probabilistic models for customer base analysis. --- ### Orthogonal Polynomial Approximation for Matrix Log Normalization in Global Covariance Pooling Authors: Md Rifat Ur Rahman, Md Raihan Khan, Md Sakib Hossain Shovon, Pietro Liò, Mohammad Ali Moni Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.19021v2 Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition. Because covariance matrices live on the Symmetric Positive Definite (SPD) manifold, a normalization step is required before the Euclidean classifier. The faithful choice is the matrix logarithm (MLN-COV), which maps the SPD manifold to its tangent space; in practice it was abandoned in favour of the matrix square root because its eigendecomposition-based gradient is numerically unstable. We show that this instability is an artifact of computing the logarithm spectrally, not of the logarithm itself. Approximating the logarithm with finite polynomials in the covariance matrix removes the eigendecomposition from both passes: every operation becomes a General Matrix Multiplication (GEMM), the gradient stays bounded on the spectral support of the pre-normalized covariance, and the unstable 1/(lambda_i-lambda_j) term never appears. The key ingredient is a mean-eigenvalue pre-normalization that centres the spectrum near 1, away from the singularity of log, with a scalar post-compensation that returns the singular part of log(A) in closed form. Our recommended normalizer is a degree-8 Chebyshev expansion evaluated by a three-term matrix recurrence, with a matching reverse recurrence for the backward pass; Legendre, Laguerre, Taylor and Pade expansions are studied as controls that isolate the roles of the basis and of the target function. On three fine-grained benchmarks and ImageNet-1k the decomposition-free logarithm is both faster and more accurate than the spectral logarithm and than the square-root approximations it replaces, and at matched basis and degree the log target beats the square-root target, confirming that the gain comes from the faithful Riemannian map rather than from a better polynomial family. --- ### Orthogonal Polynomial Approximation for Matrix Log Normalization in Global Covariance Pooling Authors: Md Rifat Ur Rahman, Md Raihan Khan, Md Sakib Hossain Shovon, Pietro Liò, Mohammad Ali Moni Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.19021v1 Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition. Because covariance matrices live on the Symmetric Positive Definite (SPD) manifold, a normalization step is required before the Euclidean classifier. The faithful choice is the matrix logarithm (MLN-COV), which maps the SPD manifold to its tangent space; in practice it was abandoned in favour of the matrix square root because its eigendecomposition-based gradient is numerically unstable. We show that this instability is an artifact of computing the logarithm spectrally, not of the logarithm itself. Approximating the logarithm with finite polynomials in the covariance matrix removes the eigendecomposition from both passes: every operation becomes a General Matrix Multiplication (GEMM), the gradient stays bounded on the spectral support of the pre-normalized covariance, and the unstable 1/(lambda_i-lambda_j) term never appears. The key ingredient is a mean-eigenvalue pre-normalization that centres the spectrum near 1, away from the singularity of log, with a scalar post-compensation that returns the singular part of log(A) in closed form. Our recommended normalizer is a degree-8 Chebyshev expansion evaluated by a three-term matrix recurrence, with a matching reverse recurrence for the backward pass; Legendre, Laguerre, Taylor and Pade expansions are studied as controls that isolate the roles of the basis and of the target function. On three fine-grained benchmarks and ImageNet-1k the decomposition-free logarithm is both faster and more accurate than the spectral logarithm and than the square-root approximations it replaces, and at matched basis and degree the log target beats the square-root target, confirming that the gain comes from the faithful Riemannian map rather than from a better polynomial family. --- ### One-Stage Object Detectors in Autonomous Driving Authors: Jonel Roman, Ryan Sirjue, Peter Nguyen, Daniel Krutky, Juan Jesus, Sudip Dhakal Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.19014v1 Autonomous vehicles depend on fast and reliable perception systems to detect surrounding vehicles, pedestrians, cyclists, traffic signs, and other road objects in real time. This paper presents a comprehensive survey and analysis of one-stage object detectors for autonomous driving rather than an implementation of a new detection system. The survey reviews the evolution of major one-stage detectors, including YOLOv1, SSD, RetinaNet, EfficientDet, anchor-free detectors such as FCOS and CenterNet, and recent real-time models such as YOLOv10. It compares these architectures through their design choices, feature-fusion strategies, loss functions, deployment trade-offs, and reported benchmark performance. The paper also summarizes commonly used autonomous-driving datasets, evaluation metrics, open challenges, and future research directions. Overall, this survey highlights how one-stage detectors balance speed, accuracy, efficiency, and robustness, while also emphasizing the remaining gap between benchmark results and dependable real-world autonomous-driving performance. --- ### Harness Continual Learning: Continual Adaptation Beyond Model Parameters Authors: Borui Kang, Jinrui Gu, Junhan Lv, Wenbin Li, Lei Wang, Yang Gao Published: 2026-08-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.19013v1 Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and routing rules. Because these contents jointly shape later execution, a harness update can disrupt previously reliable behavior even when the model is frozen. This raises a new question: how can an agent continually improve its state outside the model while retaining behavior acquired earlier? We formulate Harness Continual Learning (HCL), a new continual learning paradigm in which the harness evolves around a frozen foundation model, and define the resulting loss of earlier behavior as harness-level forgetting. We instantiate HCL with four execution-facing components: the Task Interface, Experience Memory, Capability Map, and Adaptive Router. We further introduce guarded harness evolution to separate update generation from state commitment. A Continual Optimizer proposes candidate harnesses from post-execution feedback, and a Continual Evaluator commits the resulting candidate harness only after checking current improvement, historical retention, and validity. Experiments on textual reasoning, multimodal perception, and open-world interaction demonstrate capability accumulation and failure recovery, with relative gains exceeding 10% over corresponding baselines in multiple settings. Component ablations assess the contribution of each harness component, while controlled retention sweeps reveal measurable harness-level forgetting and show that the stability--plasticity trade-off can be explicitly adjusted. --- ### From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation Authors: Sepehr Ghaffarzadegan, Boubakr Nour, Makan Pourzandi, Mourad Debbabi, Chadi Assi Published: 2026-08-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.19011v1 Mechanisms for dynamically converting cyber threat intelligence (CTI) into actionable detection capabilities are necessary due to the rapid evolution of Advanced Persistent Threats (APTs). Sigma rules are an essential part of contemporary threat detection workflows because they offer a platform-independent framework for expressing detection logic that can be converted into particular queries across SIEM systems. Conventional techniques for manually crafting Sigma rules are prone to mistakes, and necessitate extensive knowledge, which restricts their scalability. Although there are open-source and industry-maintained Sigma rule repositories, they often fail to keep pace with emerging threats and require frequent customization to fit diverse operational environments. This emphasizes the necessity of dynamic rule generation that is adapted to evolving attack techniques as well as particular use cases. In this work, we design AUTOSIGMA, an automated solution for transforming unstructured CTI reports into relevant Sigma rules. Rather than relying solely on language models, AUTOSIGMA leverages a structured knowledge base to enrich partial inputs, matches the enriched content against a repository of existing Sigma rules, and then employs an LLM-as-a-Judge mechanism to iteratively validate the rules. By combining knowledge-driven enrichment, template-based rule grounding, and a multi-stage solution, AUTOSIGMA enables accurate, context-aware, and relevant rule generation. Evaluations across multiple real-world APT reports and multiple security blogs demonstrate that AUTOSIGMA outperforms alternative solutions and LLM models in rule validity, rule relevancy, MITRE ATT&CK technique coverage, and robustness to input quality. AUTOSIGMA's Demo: https://youtu.be/iSr6IurQ6BM --- ### Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning Authors: Yajie Yin Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.19009v2 Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verification literature uses the word "level" to mean at least five different things: verification granularity, concept abstraction, risk tier, system-stack layer, and the epistemic source of the ground truth. We propose Verification Autonomy Levels (VAL), a meta-standard that classifies any verification scheme along a single axis: where does the verification spec come from, and what does the verdict guarantee? VAL ranges from L0 (LLM self-declaration; no deterministic anchor) through L2 (objective ground truth; correctness only) to L3/L4 (decidable systems with single-property or domain-level completeness), with L5 impossible in the unrestricted case. Central to VAL is the completeness blind spot: substitution- and sampling-based verifiers can confirm that proposed candidates hold, but cannot prove that no candidate was missed. We further identify a dichotomy the literature has not stated: completeness is reachable only for formally specifiable properties, whereas empirical open-world verification (fact-checking, diagnosis) caps at anchored correctness (L2). We document this gap empirically across four domains (symbolic mathematics, behavior monitoring, medical diagnosis, and code generation, the last a reverse validation with predictions stated before evidence) and in the strongest formal-verification baseline in our survey, whose authors note the verifier focuses on the correctness of each step. We show the levels of granularity, concept hierarchy, risk, and system stack are orthogonal to VAL, resolving a systematic conflation across 17 surveyed papers. Code and full assessment are released as supplementary material. --- ### Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning Authors: Yajie Yin Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.19009v1 Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verification literature uses the word "level" to mean at least five different things: verification granularity, concept abstraction, risk tier, system-stack layer, and the epistemic source of the ground truth. We propose Verification Autonomy Levels (VAL), a meta-standard classifying verification schemes along a single axis: where does the verification spec come from, and what does the verdict guarantee? VAL ranges from L0 (LLM self-declaration, no deterministic anchor) through L2 (objective ground truth, correctness only) to L3/L4 (decidable systems with single-property or domain-level completeness), with L5 impossible in the unrestricted case. Central to VAL is the completeness blind spot: substitution- and sampling-based verifiers can confirm that proposed candidates hold, but cannot prove that no candidate was missed. We further identify a dichotomy the literature has not stated: completeness is reachable only for formally specifiable properties, while empirical open-world verification (fact-checking, diagnosis) caps at anchored correctness (L2). We document this across four domains (symbolic mathematics, behavior monitoring, medical diagnosis, and code generation) and in the strongest existing formal-verification baseline, whose authors note the verifier "focuses on the correctness of each step." We show the levels of granularity, concept hierarchy, risk, and system stack are orthogonal to VAL, resolving a systematic conflation across 17 surveyed papers. Code and full assessment are released as supplementary material. --- ### Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy Authors: Stephen Meisenbacher, Vlad Garbuz, Chirill Donos, Maxim Dnestreanschii, Gabriel Creanga, Andreea-Elena Bodea, Thomas Lampert, Jana Diesner Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.19006v1 Hate speech is a real and timely threat that affects a large portion of online users, especially youth and minority groups. While building reliable and robust automatic hate speech detection (HSD) systems is paramount, we argue that this must also be balanced with the individual right to privacy. Exploring the intersection of HSD and privacy, we demonstrate that HSD systems might unintentionally achieve performance at the cost of encoding authorship, posing a threat to privacy. Building on these findings, we establish the notion of a privacy-HSD trade-off, which demands a careful balance. We benchmark a series of text privatization methods, as well as our newly proposed domain-specific AgnoSpeech technique, showing that balancing privacy and HSD is difficult but feasible. The findings make a strong case for more research on the trade-offs between privacy and HSD, both of which have tangible implications for the safeguarding of online participation. --- ### Autonomous Agricultural Tractor: Integrated Weed Detection and LiDAR Navigation for Precision Paddy Farming Authors: Benjamin Merryman-Smith, Tony Nguyen, Bilal Dogutas, Krish Shah, Anthony Raphael, Sudip Dhakal Published: 2026-08-19 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.19004v1 Site-specific weed management in paddy farming offers substantial reductions in herbicide use over conventional broadcast spraying, but field deployment has been limited by three persistent challenges: robust crop-row navigation under canopy where GNSS degrades, real-time visual discrimination between rice and morphologically diverse weeds, and the asymmetric cost of misclassifying rice as weed, which is irreversible. This paper presents AgriNav, an integrated autonomous tractor system built around four ROS-coupled modules: a custom PyTorch reimplementation of WeedDet for rice detection, a parallel lightweight 1.68M-parameter CNN-FPN variant with asymmetric class weighting, an inverted-logic discrimination module that protects the rice class through a hardcoded confidence-gate veto, and a 6-state constant-velocity-turn-rate Extended Kalman Filter fusing GNSS, IMU, and wheel odometry with three-level outage bridging. Our primary system-level contribution is a four-mechanism LiDAR-camera fusion bridge that uses the navigation LiDAR for region-of-interest constraint, world-coordinate projection, ground-plane filtering, and bidirectional confidence fusion at zero additional hardware cost. Simulation experiments demonstrate continuous position tracking through a 20-second GNSS outage, crop row detection confidence above 0.9 throughout operation, and rice-detection confidences from 0.32 to 0.95 across paddy, aerial, and post-flood imagery. The LiDAR ROI constraint reduces detection inference region by an estimated 30 to 50 percent. --- ### Structure, Association, and Decision Value: Representation-Based Difficulty Estimation for Adaptive Inference in African-Language NLI Authors: Toheeb Ogunade Published: 2026-08-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.19003v1 We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP, and find that they cannot in this setting. Studying natural language inference across 15 African languages with frozen off-the-shelf checkpoints, we report four results. First, AfriXNLI's English configuration shares 1,047 of its 1,050 examples verbatim with XNLI evaluation data, and one widely used NLI checkpoint scores 1.000 on that test split, consistent with XNLI test exposure. Because AfriXNLI is derived from XNLI, its English, French and Swahili configurations cannot serve as clean evaluations for XNLI-trained models. Second, parameter count does not reliably order capability across African languages: our larger checkpoint is better in seven languages and worse in eight, with no significant aggregate difference. Third, across three multilingual representation spaces, angular dispersion is consistently more language-determined than effective rank, so pooled correlations can inflate one and mask the other. Fourth, the association that survives language control depends on the target: effective rank predicts probability gain from escalation but not whether escalation changes the prediction, while cheap-model confidence shows the opposite pattern; the two targets correlate at only 0.655. Under the tested models, signals, and compute budgets, no evaluated signal makes adaptive routing preferable to always-expensive inference, although an oracle exceeds it by 11 accuracy points at 60% of the compute. Our central methodological finding is that a representation statistic can be statistically significant for one notion of computational benefit while being irrelevant to another, and therefore be a poor decision variable. --- ### A Theory of Post-hoc Debate Judgement Authors: Xiang Yin, Adam Dejl, Antonio Rago, Lihu Chen, Francesca Toni Published: 2026-08-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.19002v1 Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and user engagement. For example, LLM-empowered agents may debate internally (with themselves) and/or externally (with other agents). In many settings where debates are used, debates' outcomes and resulting outputs are determined post-hoc by external judges, often LLMs. In this paper we develop and test a novel theory of debate judgement applicable to all settings where agents engage in debates by providing pros and cons for their opinions therein. Specifically, we identify a number of formal properties that debate judgement may be required to satisfy in general, as concerns reproducibility, robustness, groundedness and explainability. Then, we explore their satisfaction formally and/or experimentally, for claim verification settings, for two specific alternative debate judgement methods: variants of the LLMs as a judge idea and formal semantics drawn from computational argumentation. We show that the two methods give similar accuracy performances but the former may lack formal guarantees that the latter brings. Overall, our study indicates argumentation semantics as an ideal candidate for principled judges in debate-driven AI. --- ### Mise-en-Scène: Implicit Layout Emergence in Diffusion Transformers for Human-AI Design Co-Creation Authors: Zipeng Xu, Ryan Murdock, Umberto Michieli Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.19000v1 Automating graphic design synthesis from user-provided elements requires both a coherent overall composition and the exact preservation of each asset. Existing methods predict a layout as explicit bounding-box coordinates with a language model and then paste the assets into it, which separates spatial planning from visual synthesis and tends to produce rigid, mis-scaled compositions. We instead ask whether the layout can emerge implicitly inside a pretrained image-editing diffusion transformer. We present Mise-en-Scène, a two-stage framework. In the first stage, a diffusion transformer adapted with a small, knockout-selected LoRA drafts a complete design in which the arrangement of the elements emerges jointly with the rendered canvas. In the second stage, a deterministic match-and-place step moves the original high-resolution assets to the drafted positions, which guarantees exact asset fidelity and yields an editable, layered design that a designer can keep refining rather than a flat image. Notably, a minimal adaptation of the pretrained transformer already suffices, without the specialized conditioning machinery commonly introduced for multi-element generation. On the large-scale PrismLayersPlus benchmark, the designs produced by Mise-en-Scène are the closest to the ground truth in perceived quality among all compared methods, by a wide margin over both an LLM layout planner and a specialized layout transformer, while our match-and-place stage bridges the remaining fidelity gap to the ground-truth composites. --- ### GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery Authors: Chaowei Wang, Yan Di, Jingjun Sun, Baozhe Liu, Jiaxu Tian, Yuheng Li, Guangqian Guo, Shan Gao Published: 2026-08-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.18996v1 Visual grounding in Unmanned Aerial Vehicle (UAV) imagery aims to localize a target object in complex bird's-eye-view scenes according to a natural language description. However, the abundance of small, densely distributed, and visually similar objects creates high visual redundancy, while repetitive local configurations give rise to strong topological ambiguity. Existing approaches mainly focus on visual--language feature alignment or dense contextual interaction, yet they struggle to distinguish subtle inter-instance differences and effectively exploit spatial topological structures, leading to inaccurate grounding in highly crowded scenarios. To address these challenges, we propose $\textbf{GrabVG}$, a novel visual grounding framework inspired by human visual search. GrabVG explicitly decomposes grounding into two sequential stages: $\textit{preattentive hypothesis search}$ and $\textit{graph-attentive feature binding}$. Specifically, we first generate a compact set of reliable object hypotheses through distillation-guided proposal induction and text-aware hypothesis filtering, substantially reducing background distractions and semantic mismatches. These hypotheses are then organized into a sparse graph, where language-guided intra-instance visual cues and inter-instance topological relationships are jointly bound and propagated via graph attention, enabling efficient spatial reasoning and accurate target localization. Extensive experiments on AerialVG and AerialSense show that GrabVG achieves a favorable accuracy--speed trade-off, reaching 67.31$\%$ and 80.34$\%$ Acc@0.5 and outperforming the corresponding baselines by 10.55 and 8.76 percentage points, respectively. --- ### ForeSightGuide: An Anticipatory Framework toward Accurate and Low-Redundancy Guidance for the Visually Impaired Authors: Zhiyuan Wang, Xu Li, Shikang Guo, Wei Meng, Quan Liu, Jie Zuo Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18993v1 Electronic travel aids are pivotal for the independent mobility of the visually impaired. While Vision-Language Models (VLMs) offer rich environmental understanding, they often suffer from excessive false positives in dynamic scenarios, leading to cognitive overload. To address this, we present ForeSightGuide, an anticipatory assistive guidance framework that couples semantic scene understanding with predictive hazard assessment. Unlike reactive systems, ForeSightGuide leverages the reasoning capabilities of VLMs to anticipate obstacle motion, effectively filtering out non-threatening objects to provide concise, actionable guidance. To validate our approach, we introduce a novel dataset captured in complex, dynamic real-world traffic scenes, designed to benchmark predictive capabilities. Extensive experiments on both public benchmarks and our proposed dataset demonstrate that ForeSightGuide achieves state-of-the-art performance. Notably, it significantly mitigates information overload by reducing redundant alerts to 0.299 per guidance output while maintaining a low missed-hazard rate of 0.112, proving its efficacy for safe walking assistance. --- ### DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering Authors: Xujia Wang, Yizhe Zhang, Bin Xu, Lei Hou, Juanzi Li Published: 2026-08-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18988v2 Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose DeepWeaver, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce LoQA, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA. Our code is available at https://github.com/KlozeWang/DeepWeaver. --- ### DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering Authors: Xujia Wang, Yizhe Zhang, Bin Xu, Lei Hou, Juanzi Li Published: 2026-08-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18988v1 Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose DeepWeaver, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce LoQA, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA. Our code is available at https://github.com/KlozeWang/DeepWeaver. --- ### X-LMC: Cross-View Spatiotemporal Collateral Circulation Scoring from DSA Authors: Maedeh Hafezi Moghadas, Hakim Baazaoui, Lukas Bastian Otto, Susanne Wegener, Björn Menze, Ezequiel De la Rosa Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18986v1 Digital subtraction angiography (DSA) is the reference standard for leptomeningeal collateral (LMC) assessment, providing critical prognostic insights to guide secondary treatment strategies, neurorehabilitation planning, and retrospective stroke research. However, clinical LMC grading via the ASITN/SIR scale relies on manual, highly variable visual inspection. We introduce X-LMC, a spatiotemporal framework for automated collateral scoring from time-resolved biplane DSA. The proposed architecture encodes spatial frame representations through a DINOv2 backbone, fuses orthogonal projections via a token-level cross-view attention module, and models representations of contrast bolus dynamics using a recurrent network architecture. We evaluate our framework on a multicenter dataset of 134 patients with M1-segment occlusions. In a 5-fold cross-validation setting, X-LMC yields higher point estimates than static architectures and spatiotemporal baselines adapted from related angiographic tasks, achieving a Quadratic Weighted Kappa (QWK) of 0.398 (vs. 0.322) and a dichotomized macro-F1 score of 0.711 (vs. 0.663) against the best-performing baseline. X-LMC performance also aligns with the observed clinical inter-rater agreement (QWK: 0.314). As the first DSA study attempting to automate LMC scoring, we demonstrate that multi-view temporal deep learning can capture collateral-specific contrast kinetics. Ultimately, these benchmarks delineate the clinical ambiguities and achievable performance boundaries of automated ASITN/SIR grading, establishing a reproducible foundation for objective hemodynamic phenotyping in stroke cohorts. Code is available at https://github.com/maedehafezi/X-LMC. --- ### Uncertainty-Aware Art-Historical Dating with Vision-Language Models Authors: Stefanie Schneider, Peter Bell Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18984v1 Museum and archival datasets do not mirror historical artistic production, but materialize the contingent histories of collecting, preservation, cataloging, and digitization. This has direct consequences for interpreting pretrained image representations: they may appear to encode historical time while actually encoding the institutional conditions under which objects become visible as data. We describe this phenomenon as temporal entanglement and investigate it by formulating artwork dating as an uncertainty-aware regression task over frozen image embeddings. We evaluate several pretrained vision models on a temporally controlled Wikidata corpus of artworks. Our results show that these models contain usable temporal information, with Vision-Language Models (VLMs) outperforming purely visual self-supervised baselines. However, a qualitative analysis indicates that this temporal knowledge is shaped by various biases. --- ### Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference Authors: Blazej Banaszewski, Andrew W. Fitzgibbon Published: 2026-08-19 Categories: cs.LG, q-bio.BM, q-bio.QM arXiv: https://arxiv.org/abs/2608.18982v1 Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular representations that generalize well in data-constrained scenarios. This paper presents Monroe, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction. Our evaluations use a principled pairwise comparison framework that measures statistically significant performance differences. Across established Polaris benchmarks, Monroe matches or exceeds existing MFMs, while on activity cliff benchmarks, designed to assess utility for molecular discovery, it achieves significant improvements over prior methods. Finally, ablation and transfer experiments show that PFN-based downstream predictors also substantially improve two leading existing models, MiniMol and CheMeleon, yielding new state-of-the-art variants we call MiniMol_PFN and CheMeleon_PFN, suggesting that our downstream adaptation strategy generalizes beyond Monroe. Source code is at github.com/blazejba/monroe. --- ### When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation Authors: Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu, Radu Timofte Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18979v1 Semantic segmentation demands a careful balance between accuracy, efficiency, and scalability, which remains difficult to achieve for high-resolution imagery. Convolutional networks effectively model local patterns but struggle with long-range dependencies, whereas Vision Transformers capture global context at a high computational cost. While recent work largely focuses on encoder design, the bottleneck stage, central to contextual aggregation and information flow, has been relatively overlooked. We propose SiConMo, a lightweight yet effective framework, implemented in two variants: an RGB-only model (SiConMo) and a GME-enhanced variant (SiConMo$_\dagger$). We show that simplicity arises from a key design principle: at very low computational budgets, the bottleneck is the most efficient stage to integrate local and global context. SiConMo integrates three complementary components: a Token Pyramid Extraction Module for hierarchical multi-scale representation, a Transformer-Branched Depthwise Convolution block for bottleneck-aware context modeling, and a Feature Merging Module that preserves spatial structure while enhancing semantic consistency. Extensive experiments on ADE20K, PASCAL Context, Cityscapes, and COCO-Stuff demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off among lightweight semantic segmentation models, highlighting simplicity as a powerful design principle. --- ### Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers Authors: Matteo Cargnelutti, Catherine Brobston, Eben English, Jake Sadow, Kacie Bailey, Greg Leppert, Amanda Watson, Jessica Chapel, Jonathan Zittrain Published: 2026-08-19 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2608.18972v1 Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts make computational access to these materials both challenging and limited. We present the Institutional Newspapers Pipeline, a modular system we jointly designed with Boston Public Library to extract high-quality, structured datasets from historical newspaper scans. It was architected so that each step remains interpretable and customizable, and so that the pipeline as a whole remains computationally frugal enough to run on workstation-level hardware. The pipeline runs each scan through a multi-step process: it segments scans into individual type-agnostic crops and performs OCR on each resulting segment before then performing text analysis, type classification, reading order detection, named entities recognition, subject classification, language detection, and pre-computed embeddings generation on every crop. We ran this pipeline against a portion of Boston Public Library's holdings and released the results as an open dataset. The optical character recognition (OCR) output represents 16.3 billion o200k_base tokens across 83.1 million individual crops, extracted from 1,473,635 public domain newspaper scans published between 1795 and 1930. This report describes our methods for each processing step, the small models we trained, as well as the evaluation results and dataset-scale measurements we collected in the process. It accompanies the release of the pipeline, models, and dataset. We position this work as a substantial step towards unlocking high-quality data from tens of millions of newspaper scans. --- ### Fuzzy Accuracy Compensates for Label Subjectivity in Classification of Skin Tone Using Wearable Photoplethysmography Signals Authors: Padmini Krishnadas, Urs Hackstein, Alen Bosnjakovic, Philip J. Aston Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18969v1 We consider the problem of classification of skin tone using photoplethysmography (PPG) signals with labels of the ordinal six-class Fitzpatrick skin tones. A typical accuracy for this task is a poor 40-55 %. However, the labels are subjectively determined by comparing the skin with a colour chart, and hence contain widespread small-scale inaccuracies. By working with a "fuzzy accuracy", which deems a prediction of skin tone class to be correct if its difference from the labelled class is not greater than one, much higher accuracy is obtained which provides more convincing evidence that skin tone can be accurately predicted from PPG signals. Three machine learning approaches were used, namely deep learning or tree-based approaches on raw PPG signals, deep learning on image representations of the signals generated by the Symmetric Projection Attractor Reconstruction (SPAR) method, and machine learning on features extracted from the signals. The first method also employed a fuzzy version of the cross entropy loss function, which gave the best results. Tree-based models on raw signals give accuracies up to 55 % and higher fuzzy accuracies up to 96 %, while deep learning models on the SPAR images obtained lower results of 44 % accuracy and 85 % fuzzy accuracy. The machine learning on PPG features gave similar results to the SPAR method with accuracy of 42 % and fuzzy accuracy of 87 %. We have shown that classification of skin tone using PPG signals is possible with high fuzzy accuracy which implies that our modelling approach enables accurate prediction of skin tone class within at most one class of the observer's choice of class, from which we conclude that PPG signals are affected by skin tone in a discernible way. --- ### Frozen DINO Localizes Image Edits Without a Localizer Authors: Zane Kumar, Vishal Jain, Bernhard Kainz Published: 2026-08-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.18968v1 Localized image edits can change a photograph's meaning while leaving most of it authentic, so forensic analysis must identify where an edit occurred. We show that patch-level perturbation responses from frozen DINO encoders are themselves localization maps. Training-free Localization of AI-image Edits from patch-token Drift (TRAIL) applies one global Haar perturbation and maps cosine drift between corresponding patch tokens. On 80 source-disjoint CocoGlide test images, TRAIL reaches .903 patch AUROC versus .912 for the mask-supervised Detective SAM; fixed-threshold Dice is .619 versus .709, while an oracle threshold raises TRAIL to .790. Transferred unchanged to Poisson image interpolation, TRAIL reaches .855 AUROC versus .864, showing that the cue persists without a generator. Across sixteen DINO encoders, the best block lies at normalized depth .80-.94. Global context matters: AUROC falls from .903 globally to .857 for local-in-canvas perturbations and .735 for independently encoded crops. Frozen DINO patch tokens therefore contain a strong late-layer localization signal whose visibility depends on the perturbation and preserved context. Code: https://github.com/VishalJ99/trail-image-edit-localization. --- ### Institutional Books - Visual Elements: An open-source pipeline for extracting, classifying, deduplicating, and captioning visual elements from digital book collections Authors: Jimmy Mendez, Matteo Cargnelutti, David Lowry-Duda, Catherine Brobston, Salwa Ismail, Greg Leppert, Amanda Watson, Jonathan Zittrain Published: 2026-08-19 Categories: cs.CV, cs.DL arXiv: https://arxiv.org/abs/2608.18957v1 Historical book collections contain rich visual elements - such as illustrations, photographs, engravings, and decorative art - that are frequently under-explored in large-scale digitization projects. While Optical Character Recognition (OCR) has standardized the extraction of textual content, these visual components offer a layer of nuance and context that remains largely untapped by automated text extraction workflows. This technical report introduces Institutional Books - Visual Elements, an open-source end-to-end pipeline for detecting, classifying, deduplicating, and captioning visual elements from historical book collections. Alongside this pipeline, we release an initial dataset of 22.6 million visual elements extracted from the 983,004 scanned volumes that comprise the Institutional Books: Harvard Library dataset. This work contributes to ongoing, community-wide efforts to enable new use cases for digitized library collections through computational access, from artificial intelligence model training to digital humanities research. --- ### rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation Authors: Minh Hoang Nguyen, Tung Le, Huy Tien Nguyen Published: 2026-08-19 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.18952v1 Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or explaining why one item fits better than another - rather than mapping history directly to a ranked list. This reasoning, however, is expensive to repeat on every ranking request and, once produced, is typically consumed once and discarded, leaving it neither reusable across future requests nor easy to inspect or correct as user tastes drift. Our insight is that reasoning does not need to be regenerated at every call if it can instead be compressed once into a compact, structured memory that a lightweight model retrieves from. We propose rEDMRec, which distills a teacher LLM's reasoning into four typed, editable experience channels - long-term preference, short-term context, item-perception, and counterfactual hard-negative comparisons - maintained by an LLM memory controller that performs Add/Delete/Modify/Keep operations and refines entries via K-agent debate. A lightweight student LLM then ranks candidates purely by retrieving from this memory, without invoking the teacher again, decoupling online inference cost from reasoning depth. Across ML-1M, Amazon Beauty, and Steam and ten student backbones, rEDMRec improves HR@1 over zero-shot, few-shot, and RAG on every backbone, and over GraphRAG on most backbones, with Impv up to 13.3% vs. the second-best baseline on ML-1M. Channel ablations show that short-term context is the only channel that helps consistently across capacity tiers, whereas long-term, item-perception, and counterfactual contributions are capacity-dependent (and can reverse on the strongest students); debate-based memory optimization lowers bank duplication by 7.4 percentage points while raising downstream HR@1 by up to +0.029 over six optimization epochs. --- ### AlphaClifford: Efficient Clifford Synthesis and Transpilation with Model-based RL Authors: Daniele Lizzio Bosco, Jacopo Cossio, Carla Piazza, Giuseppe Serra Published: 2026-08-19 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2608.18946v2 Clifford circuits play a foundational role in quantum computing, particularly due to their importance in quantum error correction and fault-tolerant logical synthesis. While these circuits can be efficiently simulated and represented as symplectic matrices, standard synthesis methods-such as the Aaronson-Gottesman algorithm-often yield sub-optimal circuits with excessively high gate counts. In this work, we introduce AlphaClifford, a model-based Reinforcement Learning framework powered by Monte Carlo Tree Search, designed to efficiently synthesize Clifford circuits from the fundamental gate set composed of H, S, and CNOT. By modeling the state space through the algebraic properties of the symplectic group, AlphaClifford effectively explores this combinatorial space to minimize overall circuit cost. For unconstrained Clifford optimization, our approach achieves a consistent reduction in both total and two-qubit (CNOT) gate counts compared to state-of-the-art synthesis heuristics, despite operating with a strictly less expressive gate set. Furthermore, we demonstrate the broad applicability of our framework on two additional tasks: hardware-constrained Clifford transpilation, where we outperform existing RL-based compilers, and as a post-synthesis optimization component within a full Clifford+T logical synthesis pipeline. Our results underscore that model-based RL is highly effective at addressing the combinatorial complexities of quantum compilation, offering a scalable pathway to mitigate hardware constraints in both near-term and future fault-tolerant quantum devices. --- ### AlphaClifford: Efficient Clifford Synthesis and Transpilation with Model-based RL Authors: Daniele Lizzio Bosco, Jacopo Cossio, Carla Piazza, Giuseppe Serra Published: 2026-08-19 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2608.18946v1 Clifford circuits play a foundational role in quantum computing, particularly due to their importance in quantum error correction and fault-tolerant logical synthesis. While these circuits can be efficiently simulated and represented as symplectic matrices, standard synthesis methods-such as the Aaronson-Gottesman algorithm-often yield sub-optimal circuits with excessively high gate counts. In this work, we introduce AlphaClifford, a model-based Reinforcement Learning framework powered by Monte Carlo Tree Search, designed to efficiently synthesize Clifford circuits from the fundamental gate set composed of H, S, and CNOT. By modeling the state space through the algebraic properties of the symplectic group, AlphaClifford effectively explores this combinatorial space to minimize overall circuit cost. For unconstrained Clifford optimization, our approach achieves a consistent reduction in both total and two-qubit (CNOT) gate counts compared to state-of-the-art synthesis heuristics, despite operating with a strictly less expressive gate set. Furthermore, we demonstrate the broad applicability of our framework on two additional tasks: hardware-constrained Clifford transpilation, where we outperform existing RL-based compilers, and as a post-synthesis optimization component within a full Clifford+T logical synthesis pipeline. Our results underscore that model-based RL is highly effective at addressing the combinatorial complexities of quantum compilation, offering a scalable pathway to mitigate hardware constraints in both near-term and future fault-tolerant quantum devices. --- ### Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis Authors: Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Maksim Kuznetsov, Mathieu Reymond, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov Published: 2026-08-19 Categories: cs.LG, cs.AI, cs.CE, cs.CL arXiv: https://arxiv.org/abs/2608.18940v1 Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning. --- ### Breaking the weakest link to evade vision language models Authors: Ilan Zini, Boussad Addad, Katarzyna Kapusta Published: 2026-08-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18938v1 Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in real-world and safety-critical applications. Despite their growing deployment, the robustness of VLMs against adversarial threats remains insufficiently explored, particularly in the context of evasion attacks targeting multimodal alignment. In this work, we investigate the vulnerability of VLMs to adversarial perturbations applied to visual inputs and study two attack settings: untargeted attacks, where the goal is to disrupt the model's interpretation of the original image, and targeted attacks, where the adversary aims to force the model to generate a specific semantic description unrelated to the original image. To efficiently generate adversarial examples, we propose a gradient-based attack method that performs optimization exclusively on the vision encoder of the VLM rather than on the entire multimodal architecture. This design significantly reduces the computational cost and resource requirements of the attack while maintaining strong effectiveness. We evaluate our approach on several open-source VLMs, including Qwen2.5-VL, Granite-Vision, FastVLM, and Phi-3.5-Vision, and show that small, human-imperceptible perturbations can substantially alter the textual interpretation produced by the models. Our findings highlight the vulnerability of modern VLMs to adversarial manipulation and emphasize the need for improved robustness and security mechanisms in multimodal AI systems. --- ### MedUAG: Unified Understanding and Generation for Medical Multimodal Models Authors: Zijie Meng, Yuncheng Zhang, Hualiang Wang, Yitian Tang, Xiaotang Gai, Chen Shen, Songtao Jiang, Shaosheng Cao, Jian Wu, Xian Wu, Zuozhu Liu Published: 2026-08-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18937v1 Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms to the medical domain is hindered by: the absence of comprehensive training and evaluation benchmarks, and the lack of broadly validated unified medical model. To address these gaps, we present a comprehensive foundation for medical UAG. First, we construct MedUAGCorpus, the largest unified medical understanding and generation dataset to date, comprising over 6 million instances across 14 imaging modalities. Second, we introduce MedUAGBench, a systematic benchmark that expands medical generation evaluation to 12 diverse tasks under standardized protocols. Finally, leveraging these resources, we develop MedUAG, an end-to-end trained unified medical model. Extensive experiments demonstrate that MedUAG achieves strong performance across a wide array of understanding and generation tasks, establishing a competitive baseline and paving the way for next-generation medical multimodal systems. --- ### Graphical Design of Interpretable Architectures Authors: Pietro Barbiero Published: 2026-08-19 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.18936v2 Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an architecture at a glance. Probabilistic graphical models and flowcharts do not describe actual tensor manipulations, thus hiding key insights and limiting reproducibility. To close this gap, we introduce a graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation. This graphical notation gives a global view of an architecture and maps one to one onto PyTorch einsum code. We first use this notation to describe architectures that are interpretable by construction, including concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models. We then diagram the key architectural components of Steerling-8B, a frontier interpretable language model. The diagram yields global insights into the architecture (e.g., showing that Steerling is a residual model), a geometric interpretation of each individual operation, and a direct translation into 33 lines of PyTorch code. --- ### Graphical Design of Interpretable Architectures Authors: Pietro Barbiero Published: 2026-08-19 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.18936v1 Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an architecture at a glance. Probabilistic graphical models and flowcharts do not describe actual tensor manipulations, thus hiding key insights and limiting reproducibility. To close this gap, we introduce a graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation. This graphical notation gives a global view of an architecture and maps one to one onto PyTorch einsum code. We first use this notation to describe architectures that are interpretable by construction, including concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models. We then diagram the key architectural components of Steerling-8B, a frontier interpretable language model. The diagram yields global insights into the architecture (e.g., showing that Steerling is a residual model), a geometric interpretation of each individual operation, and a direct translation into 33 lines of PyTorch code. --- ### SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution Authors: Silin Chen, Han Li, Xiaodong Gu, Yuling Shi, Haibing Guan Published: 2026-08-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.18933v1 Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a specific repository because they lack project-specific knowledge. Existing self-evolving approaches acquire such knowledge from repository history or online repair trajectories, but they either depend on available historical issue-resolution signals or incur substantial per-issue test-time exploration cost. In this paper, we propose SkillForge, a self-distillation framework that proactively acquires project-specific knowledge from the repository itself. Instead of waiting for real issues to expose project-specific knowledge gaps, SkillForge synthesizes project-specific issues by re-implementing test-covered core functionalities of the repository. By resolving these synthetic issues, SkillForge distills reusable project-specific knowledge into entity-grounded skills and associates them with relevant repository entities for future issue resolution. Extensive experiments using both open-source and closed-source models show that SkillForge consistently improves issue resolution performance over strong baselines. These results demonstrate that proactively acquiring project-specific knowledge before solving real issues substantially improves downstream software issue resolution. --- ### Transportable Causal Effect Estimation across Networks under Interference Authors: Xiaojing Du, Jiuyong Li, Lin Liu, Debo Cheng, Jixue Liu, Thuc Duy Le Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18932v1 Estimating causal effects under network interference typically assumes that the network used for training and the network used for deployment coincide. In practice, an intervention is run on one population while the question of interest concerns a different population, and the two generally differ in topology, node-covariate composition, and spillover pathways. Transporting a causal effect across networks is therefore a data-fusion problem that no existing algorithm solves. We employ a selection diagram, extended to the network setting so that covariate shift and structural network shift enter as separate selectors, and derive from it a transport formula for the direct, spillover, and total effects in the deployment population. Each formula makes explicit which interventional mechanism is assumed invariant and which observational distribution must be reweighted. We then turn the formulas into TranCE (Transported Causal Effects), a doubly-robust algorithm combining an interventional outcome model, a domain density-ratio correction, and cross-fitted inference. Extensive experiments on two semi-synthetic benchmarks derived from real-world social networks and on a fully real weather-insurance field experiment, where the transported effects are checked against held-out randomized estimates, confirm the effectiveness of our approach. Our findings have the potential to improve intervention strategies in networked systems, particularly in social networks and public health. --- ### Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck Authors: Davide Romano, Kanak Raj, Jerrod Parker, Daniele Giofrè Published: 2026-08-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18931v1 Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively refining drafts. These techniques yield large gains on mathematics and code, but have been developed and stress-tested almost exclusively on tasks where verification is straightforward. We conduct the first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation. The answer depends on which side of that decomposition you examine. Scaling exploration works: the best candidate in the pool improves steadily with compute across all settings. What breaks is exploitation - the step that converts a rich candidate pool into a final output. With state-of-the-art generators, reward models correlate at only $ρ_v \approx 0.12$ with true quality, rendering selection near-random regardless of budget. Tree search amplifies this failure through diversity collapse. Refinement helps on one of five benchmarks; its apparent gains elsewhere are confounded. Only synthesis across candidates (Fusion) consistently improves over single-sample baselines, yet still recovers only ~40% of available quality. The candidate pool is not the bottleneck - choosing from it is. --- ### SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance Authors: Jian Yang, Zhenqi Feng, Zhaoyang Yu, Zhaoxin Fan, Kejian Wu, Xiaofeng Wang, Zheng Zhu, Jianjun Huang, Wei You, Bin Liang Published: 2026-08-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18921v1 Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either repeated queries to the target model or training a dedicated attack model. These expensive operations severely weaken attack leverage. In this paper, we propose \emph{search amplification}, a novel, model-feedback-free LRM-DoS paradigm. It employs the conflict count derived from an Satisfiability Modulo Theories (SMT) solver as a low-cost external signal to guide the synthesis of inference-heavy Constraint Satisfaction Problem (CSP) instances. Our key observation is that LRMs depend on trial-and-backtracking search when solving CSPs, where higher SMT conflict counts on a given CSP instance positively correlate with more extensive LRM backtracking search and substantially longer output trajectories. Building on this finding, we propose \textsc{SMTrap}, a lightweight, CPU-only framework. Guided by SMT conflict counts, \textsc{SMTrap} generates inference-heavy CSP queries without model queries, attack-model training, or GPU computation. Evaluations across seven frontier models demonstrate the state-of-the-art LRM-DoS capability of \textsc{SMTrap}, producing DoS effects multiple times stronger than existing baselines. To mitigate the threat of \textsc{SMTrap}, we demonstrate a tool-based mitigation that significantly cuts token usage. --- ### Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths Authors: Andrej Tschalzev, Stefan Lüdtke, Heiner Stuckenschmidt, Christian Bartelt Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18919v1 Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are useful for selecting robust default models, but they can obscure a different question: which models are necessary to attain peak performance on particular datasets? We argue that benchmark evaluation should also consider the data-centric peak performance frontier, defined by the best statistically supported performance achieved on each dataset. From this perspective, a model may be irreplaceable, sufficient, redundant, or fallible depending on where it lies on the frontier relative to other models. Applying this framework to the TabArena benchmark, we find that common aggregation metrics are highly correlated and largely measure consistency and avoiding failures, while being much less aligned with dataset-level irreplaceability. Consequently, models performing decently across datasets without ever being the best choice are rewarded while models with unique dataset-specific strengths appear mediocre under aggregation. Hence, benchmark progress should be measured not only by improvements on aggregation metrics but also by whether new models expand the set of attainable peak performances across datasets. --- ### Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems Authors: Mark Kozdoba, Shie Mannor Published: 2026-08-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.18918v1 Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on systems assembled from several weakly interacting components --- a structure common in physical and biological settings --- this may either require an exponential number of modes, or drop an entire component: the component is absent from the model rather than modeled coarsely, and no function of it can be predicted at any accuracy. We call this linear masking. The cause is that a rank-based model pays one coordinate per mode. We propose to score instead the $σ$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators rather than by all its interactions. The criterion is a $χ^2$-divergence between the embedded present and future, and it carries a budget guarantee: twice the intrinsic dimension of the dynamics is enough coordinates for an embedding whose algebra carries the operator's entire spectrum, with its full infinite rank. In variational form the criterion admits off-the-shelf estimators, and restricting its critic to the bilinear class returns the VAMP score on the span, so rank-based methods are one end of the same family. We demonstrate the proposed objective on a composite of published benchmark systems. We exhibit examples where the rank-based methods completely miss the masked components at all ranks $k<100$, while ten algebra coordinates recover all of them. In addition, the resulting algebra representation supports predicting the masked components from few labels, while direct regression from the high-dimensional observation or from the VAMP features fail. --- ### Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching Authors: Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai, Marco Lents, Christian Ledig Published: 2026-08-19 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2608.18915v2 Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classifiers. Existing remedies fall short: standard color jittering provides insufficient diversity, while deep generative style transfer algorithms hallucinate features, destroy clinically relevant structures, and waste massive compute resources. To address this, we revisit classical statistical color matching and repurpose it as Colorist, a highly efficient data augmentation strategy that applies global mean-standard deviation matching directly in the RGB color space. We demonstrate that this training-free, fully interpretable approach safely generates structurally intact domain variations, outperforming deep generative models in structural fidelity and color alignment. Across out-of-distribution histopathology, peripheral blood, dermatology, and retinal datasets, it improves balanced accuracy by up to +9% over state-of-the-art domain generalization regularizers and by +13% over an unaugmented baseline. Moreover, by avoiding neural networks in the augmentation loop, Colorist preserves anatomical structure, minimizes carbon footprint, and integrates seamlessly into standard dataloaders. Together, these findings establish statistical matching as a safe, interpretable, yet overlooked alternative to deep architectures for clinical robustness. Source code is available at https://github.com/sdoerrich97/colorist. --- ### Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching Authors: Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai, Marco Lents, Christian Ledig Published: 2026-08-19 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2608.18915v1 Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classifiers. Existing remedies fall short: standard color jittering provides insufficient diversity, while deep generative style transfer algorithms hallucinate features, destroy clinically relevant structures, and waste massive compute resources. To address this, we revisit classical statistical color matching and repurpose it as Colorist, a highly efficient data augmentation strategy that applies global mean-standard deviation matching directly in the RGB color space. We demonstrate that this training-free, fully interpretable approach safely generates structurally intact domain variations, outperforming deep generative models in structural fidelity and color alignment. Across out-of-distribution histopathology, peripheral blood, dermatology, and retinal datasets, it improves balanced accuracy by up to +9% over state-of-the-art domain generalization regularizers and by +13% over an unaugmented baseline. Moreover, by avoiding neural networks in the augmentation loop, Colorist preserves anatomical structure, minimizes carbon footprint, and integrates seamlessly into standard dataloaders. Together, these findings establish statistical matching as a safe, interpretable, yet overlooked alternative to deep architectures for clinical robustness. Source code is available at https://github.com/sdoerrich97/colorist. --- ### Converting Expert Deliberation into Financial Signals Through A Context-Aware NLP Pipeline Authors: Vivek Batra, Kristin Chen, Sanjiv Das, Samuel Judge, Harshad Khadilkar, Sukrit Mittal, Amir Nasrollahzadeh, Daniel Ostrov, Jacob Sisk Published: 2026-08-19 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2608.18911v1 We introduce the CDSP (context-conditional deliberation signal pipeline), converting an investment committee's meeting transcripts into structured predictive features. CDSP segments the meeting transcripts into topical chunks, assigns asset-class context labels using a large language model (LLM), maps financial keywords to a pre-determined taxonomy of labels, and constructs complementary features: sentiment polarity and mention frequency. This feature engineering framework is applied to a dataset spanning 48 monthly committee meetings to predict if global equities will perform better or worse than global bonds in the following month. In experiments with engineered features, raw transcript text, sentence embeddings, and combined representations, the prediction accuracy ranges from 62% to 73%, compared to always choosing stocks, which outperforms bonds 60.4% of the time. The best (73% accurate) model combines sentence embeddings with engineered CDSP features, achieving a 0.73 F1 score (although this is not statistically significant compared to always choosing stocks). Sentiment carries a stronger signal than mention frequency for several taxonomy categories. These findings suggest that experts' deliberations may contain forward-looking information that context-aware NLP can extract. ---