# Research Papers — 2026-07 · bundle page 128 of 222 > Full-text markdown of papers #6351–6400 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/128 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/127.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/129.md) ### Text-Aided Multi-Modal Panoptic Symbol Spotting for CAD Floor Plan Drawings Authors: Yan Gong, Bohao Li, Bowen Du, Junchen Ye Published: 2026-07-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.12678v1 Computer-Aided Design (CAD) floor plan drawings contain both graphical primitives and textual annotations, which provide complementary geometric and semantic cues for intelligent design understanding. Among CAD analysis tasks, panoptic symbol spotting has become increasingly important with the growing demand for industrial digitalization and deep learning-based automation. However, most existing methods remain primarily primitive-centric and underexploit textual annotations, despite their critical semantic value. Even the few text-aware approaches often treat annotations only superficially, without properly modeling complex syntax and hierarchical semantics of CAD annotations, which leads to semantic loss and suboptimal spotting performance. To address these limitations, we propose TextCAD, a multimodal framework that jointly models graphical primitives and textual annotations for panoptic symbol spotting. Specifically, we design a Type-Attribute Correlation Encoder (TACE) to explicitly encode the compositional semantics within annotations by jointly modeling their types and attributes. We further introduce a Semantic Hierarchy Alignment framework with Multi-level Semantic Filtering (MSF) and primitive downsampling, which adaptively aligns annotation semantics with graphical primitives at different semantic levels and enables accurate cross-modal semantic injection and fusion. Experiments on real-world building-design datasets show that TextCAD effectively improves symbol spotting performance and achieves state-of-the-art results. --- ### MAGE: Color-Invariant and Spatial Knowledge Distillation for Gastric Neoplasm Classification Authors: Jiho Jun, Jeongwon Woo, Jaemin Song, Thanh Bong Nguyen, Dong-heon Yeon, Donghoon Kang, Jae-Myung Park, Sung-Jea Ko, Kwang-Hyun Uhm Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12663v1 Accurate differentiation between gastric adenoma and carcinoma during endoscopy is critical for clinical decision-making. Yet, this task is highly challenging due to high inter-class similarity and ambiguous boundaries between the two classes. Existing ROI-based classification methods often suffer from detection/segmentation error propagation and loss of surrounding global context. In contrast, full-image classification lacks the necessary spatial focus. Furthermore, we observe that deep neural networks gravitate towards domain-specific texture biases(e.g. bleeding, lighting artifacts), often causing models to predict based on spurious correlations instead of intrinsic morphological features. To address these limitations, we propose a novel framework, Masked Achromatic Guidance Expert (MAGE). During training, we introduce an auxiliary local expert branch trained on masked achromatic views of the neoplasm. By suppressing background context and color, this branch is forced to learn highly discriminative, purely structural features. We then employ a dual-objective distillation strategy, transferring both classification logits and spatial attention maps to provide implicit spatial supervision to the main branch that receives full WLI as input. This dual-objective distillation forces the model to ground its predictions in morphology rather than relying on shortcuts, while still retaining clinically relevant color cues. At inference time, our deployable model operates on images without annotated masks, ensuring real-time deployability . Extensive experiments on a clinical gastric endoscopy dataset show that our method significantly outperforms existing detection-based methodologies (e.g. YOLO) and classification-based methodologies (e.g. Swin-Transformer), providing not only superior classification performance but also interpretable attention maps for clinical reliability. --- ### Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration Authors: Quanyan Zhu Published: 2026-07-14 Categories: cs.AI, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2607.12662v1 The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop orchestration framework. The proposed architecture consists of cloud, edge/fog, and physical IoT layers connected through autonomous AI agents that perceive, reason, coordinate, and actuate across distributed cyber-physical environments. The paper formalizes IoAT as a coupled workflow-control problem with nested strategic and tactical decision making using a hylomorphic dynamic programming framework that links agentic planning with physical execution. Smart-building orchestration is presented as a representative use case, and key research challenges related to safety, security, governance, resilience, and trustworthy deployment are discussed. --- ### Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference Authors: Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li Published: 2026-07-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.12659v5 Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial inference latency and low control frequency. Asynchronous inference can partially mask this latency by parallelizing action execution and subsequent inference, but it introduces two critical issues: perception-execution misalignment and long reaction time. In this paper, we propose Jetson-PI, a method for efficient VLA deployment on onboard devices via Foresight-Aligned Asynchronous Correction. To address misalignment, we train a lightweight future correction module that predicts future environment representation conditioned on committed actions, enabling the action expert to directly predict actions from the future time step. To reduce reaction time, we introduce confidence-based scheduling optimization that adaptively balances VLM and action expert invocations, complemented by system-level accelerations including CUDA graph reuse, GPU-resident intermediate buffering, and flow unrolling. Extensive experiments demonstrate that Jetson-PI achieves 8.66x and 5.41x improvements in control frequency compared with naive PyTorch and vla.cpp on NVIDIA Jetson Orin, while outperforming VLASH by 14.8\% in average success rate on the LIBERO benchmark. The code of our asynchronous algorithm is available on https://github.com/PKU-SEC-Lab/Jetson-PI, and our efficient llama.cpp-based inference engine is available on https://github.com/PKU-SEC-Lab/Jetson-PI-Edge. --- ### Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference Authors: Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li Published: 2026-07-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.12659v4 Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial inference latency and low control frequency. Asynchronous inference can partially mask this latency by parallelizing action execution and subsequent inference, but it introduces two critical issues: perception-execution misalignment and long reaction time. In this paper, we propose Jetson-PI, a method for efficient VLA deployment on onboard devices via Foresight-Aligned Asynchronous Correction. To address misalignment, we train a lightweight future correction module that predicts future environment representation conditioned on committed actions, enabling the action expert to directly predict actions from the future time step. To reduce reaction time, we introduce confidence-based scheduling optimization that adaptively balances VLM and action expert invocations, complemented by system-level accelerations including CUDA graph reuse, GPU-resident intermediate buffering, and flow unrolling. Extensive experiments demonstrate that Jetson-PI achieves 8.66x and 5.41x improvements in control frequency compared with naive PyTorch and vla.cpp on NVIDIA Jetson Orin, while outperforming VLASH by 14.8\% in average success rate on the LIBERO benchmark. The code of our asynchronous algorithm is available on https://github.com/PKU-SEC-Lab/Jetson-PI, and our efficient llama.cpp-based inference engine is available on https://github.com/PKU-SEC-Lab/Jetson-PI-Edge. --- ### Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs Authors: Junyu Ren Published: 2026-07-14 Categories: cs.LG, cs.AI, cs.CY, cs.SE arXiv: https://arxiv.org/abs/2607.12650v1 Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny. We present EG-VAR (Evidence-Grounded Verified Agentic Reasoning), a Lean 4-based tool-calling architecture in which the Lean kernel is the sole minter of Verified claims via tool-attestation axioms and declared source lifts. Every verified output structurally descends from an attested tool call (Thm. 3.1) and a kernel-checked chain of valid inference (Thm. 3.2); residual outputs are honest Abstain with a replayable audit trail. On a subcollection of TableBench numerical reasoning (n=120), EG-VAR attains 120/120 versus a 95% same-tool baseline; on counterfactual stress tests (5 domains x 2 models), EG-VAR stays 100% source-faithful while same-tool drops to 80-90% (no-tool 50-80%). With the LLM as deployment-time formalizer, residual semantic-formalization error is 3.3% on Sonnet and 1.7% on Opus. We position EG-VAR as a technical-governance interface for high-stakes empirical claims: a formal sidecar makes the target proposition, source scope, evidence boundary, proof obligation, and abstention condition auditable, eliminating unsupported Verified outputs today while turning formalization errors, lift and source-authority disputes, ambiguities, and abstentions into explicit audit targets. Over time, typed sidecars in datasets, APIs, public records, and AI-generated documents can amortize this formalization burden into reusable infrastructure. --- ### Extractable Memorization From First Principles Authors: A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Georgios Kaissis, Daniel E. Ho, Mark A. Lemley, Percy Liang Published: 2026-07-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.12649v2 Recent work on extractable memorization in language models suffers from two contrasting validity problems. Some studies overstate extraction, for example, by using sequences too short to distinguish memorization from predictability. Others imply that extraction is unreliable evidence because models can reproduce real-world text they weren't explicitly trained on. Both overlook what makes a valid extraction claim: the model must generate a training sequence with high enough probability to indicate memorization. To determine what's high enough, one has to perform a matched comparison, measuring generation probabilities of training and comparable non-training sequences. Since non-training sequences can't have been memorized, their probabilities are a baseline for predictability; exceeding this baseline is evidence of memorization. We formalize matched comparisons with (1) a conformal test calibrated to a chosen false-positive rate when sequences are sampled from populations, and (2) a single-document census that calibrates against a matched non-training document. Matched comparisons enable rigorous, calibrated memorization claims and clarify where prior setups have validity issues. On Wikipedia, OLMo 2 32B reproduces non-training 10-token suffixes roughly 24% as often as training ones: that share reflects false positives, not memorization. For Llama 3.1 70B on books, calibrated census thresholds reach as low as 10^(-27), supporting memorization claims for sequences no feasible sampling budget would extract. We therefore refine "extractable memorization" to require both a valid memorization claim and near-certain generation within a realistic budget. --- ### Extractable Memorization From First Principles Authors: A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Daniel E. Ho, Mark A. Lemley, Percy Liang Published: 2026-07-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.12649v1 Recent work on extractable memorization in LLMs suffers from two contrasting validity problems. Some studies overstate extraction, e.g., relying on sequences too short to distinguish memorization from predictability. Others imply that extraction is unreliable evidence of memorization, since models can also reproduce real-world text they weren't explicitly trained on. In different ways, both overlook what makes a valid extraction claim: the model must generate a training sequence with high enough probability to indicate memorization. To determine what's high enough, one has to perform a matched comparison: measuring the generation probabilities of both the training sequences of interest and comparable non-training sequences. Because non-training sequences cannot have been memorized, their probabilities provide a baseline for predictability; a training sequence exceeding this baseline provides evidence of memorization. We formalize matched comparisons in two ways: (1) a conformal test that calibrates a threshold to a chosen FPR when training and non-training sequences are sampled from populations, and (2) a census that calibrates against a matched non-training document when the object is a single document (e.g., a book). We show that matched comparisons enable rigorous, calibrated memorization claims, and reveal where prior setups have validity issues. For instance, on Wikipedia OLMo 2 32B reproduces non-training 10-token suffixes roughly 24% as often as training ones: that share of the training generation rate reflects false positives, not memorization. For Llama 3.1 70B on books, the thresholds we calibrate are as low as 1e-27, supporting memorization claims for sequences that no feasible sampling budget would extract. Based on these results, we refine "extractable memorization" to require a valid memorization claim and near-certain generation within a realistic budget. --- ### AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation Authors: Shuai Cui, Chen Wenxuan, Wenjie Du, Jian Lou, Dan Li, Wenjie Feng Published: 2026-07-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12645v1 Generative modeling of longitudinal Electronic Health Records is increasingly important for privacy-preserving research, yet standard autoregressive models tend to underrepresent the co-occurrence structure of tail events (i.e., diseases, symptoms), reducing the fidelity and faithfulness of generated data for rare subpopulations. To this end, we propose AdaPCLA framework, which enables generative models to adaptively fit and generate EHR data through a data distribution-aware training strategy; this is achieved by internalizing data knowledge parameters by simulated annealing training. It also supports training-free adaptation to a diverse clinical population for generation through zero-shot distribution control. Moreover, our theoretical analysis characterizes rare-code logit updates through the label-wise empirical NTK and derives a prior-internalization bound for how annealing speed and NTK conditioning affect retained prior signals. Experiments on real-world data show that AdaPCLA achieves consistent gains in tail plausibility, downstream utility, and zero-shot control; in particular, it improves TailPairSeen over HALO by 114.2% on MIMIC-III and 65.1% on MIMIC-IV, outperforms GPT-style generation by 3.5% F1 for zero-shot cross-population adaptation. --- ### A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism Authors: Chengguang Gan, Zhixi Cai, Yunhao Liang, Hanjun Wei, Shiwen Ni, Qinghao Zhang Published: 2026-07-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.12640v1 Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent. We ask whether it adds skill to a small language and vision-language model web agent at the 4B to 8B scale, or whether it mostly reshapes behavior the supervised model already has. Across a control grid of 18 runs that varies learning rate, KL weight, seed, initialization, and clipping, no configuration credibly improves the success rate of a strong supervised baseline on tasks the agent has largely mastered. On the text track, moderate to high learning rates make it credibly worse. The null holds under paired testing, 25 evaluation seeds, 6 training seeds, changes to the recipe, both text and Set-of-Marks screenshot observations, and scaling the backbone to 8B; the credible harm is a text-track finding and is only nominal under Set-of-Marks. To show that the null reflects the setting and not a broken pipeline, we run the identical harness, reward, and recipe on tasks whose reward is reachable by sampling, and there the success rate rises by 22 points with a paired interval that excludes zero. GRPO therefore helps only when there is headroom to climb, meaning the sampled policy already succeeds more often than the greedy one. We then explain the failure. A middle learning rate degrades the agent and a high one collapses it, and the two regimes form a double dissociation: grafting localizes the degrade regime to the attention and MLP blocks, while the collapse regime cannot be traced to any single group, and the embedding change that dominates the weight movement is causally inert. At 4B, effective rank in the late layers tracks capability in both directions; at 8B the two come apart. This coupling is specific to the smaller model, so we report it as scale-dependent. --- ### Atomic Units of X: The Compression Layer of Intelligence Authors: Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliades Published: 2026-07-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12634v3 This paper proposes a theoretical and empirical framework for understanding intelligence as a process of atomic compression and compositional reuse. It argues that scalable cognitive, biological, computational, and organisational systems reduce complexity by organising information into reusable units that can be recombined into higher-order structures. The central contribution is the Compression Calculus, a formal framework for comparing surface evidence with atomic representations and for describing how abstraction can compound across layers. The framework is evaluated on large, multi-source software corpora under an open-world concept model, showing substantial evidence-to-concept consolidation in two large projects, while a smaller third project remains below the target threshold. The analysis further identifies important boundary conditions: consolidation depends on corpus scale, evidence-unit definition, and concept identity, and the observed reduction is driven primarily by within-corpus recurrence rather than cross-source recurrence. The paper also develops a representational account of the meaning gap in contemporary generative systems, describing latent, context-dependent conceptual approximations as soft atoms that lack the persistent identity and compositional constraints of stable atomic units. This motivates an architectural view in which large language models function as dynamic fusion engines that navigate and compose persistent conceptual structures rather than serving as the sole repository of those structures. --- ### Atomic Units of X: The Compression Layer of Intelligence Authors: Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliades Published: 2026-07-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12634v1 This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse. We argue that cognitive, biological, computational, and organizational systems achieve scalable intelligence by decomposing complex phenomena into reusable atomic units that can be recombined into higher-order structures. Drawing on evidence from cognitive science, information theory, evolutionary biology, software engineering, medicine, legal reasoning, education, music, and artificial intelligence, the paper develops the concept of atomic units as fundamental compression layers that support efficiency, transfer, interpretability, and evolvability. The central contribution is the Compression Calculus, a formal framework for comparing surface-level representations with atomic representations and for describing how compression gains compound across abstraction layers. We introduce the Compounding Cascade thesis, according to which each additional layer of abstraction multiplicatively increases representational efficiency rather than merely adding incremental savings. The paper further argues that contemporary AI systems often operate at suboptimal levels of representation, relying on token-level processing or document-level retrieval rather than stable, concept-level atomic structures. In this view, large language models are best understood not as complete knowledge architectures, but as dynamic fusion engines capable of navigating, sequencing, and recombining atomic units. The framework provides a foundation for designing self-evolving knowledge systems that can discover, refine, and compose new primitives over time. By reframing intelligence as compression through compositional abstraction, the paper offers a unifying perspective on expertise, knowledge representation, explainable AI, and the future architecture of adaptive intelligent systems. --- ### Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making? Authors: Minh Khoi Ho, Zihao Zhu, Runchuan Zhu, Levina Li, Zhiwen Fan, Zhangyang Wang, Junyuan Hong Published: 2026-07-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.12631v1 As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents. --- ### Instance-Enriched Semantic Maps for Visual Language Navigation Authors: Jiho Hong, Eunae Kang, Sanghyun Kim, Young-Sik Shin Published: 2026-07-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.12630v2 Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent approaches build semantic spatial maps and leverage Large Language Models (LLMs) for reasoning and decision making. Despite these advances, existing systems lack instance-level object detail and robustness to diverse user queries, limiting reliable navigation in complex indoor environments. To address these limitations, we propose Instance-Enriched Semantic Maps, a unified framework with three key contributions: (1) Instance-level two-and-a-half-dimensional (2.5D) rich information mapping that constructs maps from color and depth observations via open-vocabulary panoptic segmentation, preserving vertical distinctions and capturing small objects, while storing diverse semantic attributes and natural language captions enriched with room-level context. (2) Robust query processing via LLM-based target selection, which dynamically routes queries across type-specialized experts and integrates their outputs through score-level fusion, enabling consistent goal selection across diverse query formulations. (3) Storage-efficient semantic representation that achieves approximately 96% reduction compared to three-dimensional (3D) scene-graph approaches while preserving sufficient spatial information for navigation. The proposed 2.5D representation outperforms the 3D baseline by over 27% in prediction-normalized Area Under the Curve (AUC). In navigation experiments, our method achieves over 17% improvement in object retrieval and over 23% in navigation success compared to the baseline across diverse query types. The project page is available at https://rcilab.github.io/iesm_vln. --- ### Learning Forced Multibody Dynamics on Lie Groups Authors: Martine Dyring Hansen, Marta Ghirardelli, Elena Celledoni, David Martin de Diego, Brynjulf Owren Published: 2026-07-14 Categories: cs.LG, math.DS, math.SG arXiv: https://arxiv.org/abs/2607.12627v1 We propose an architecture for learning the dynamics of mechanical systems based on discrete forced Euler-Lagrange equations on Lie groups using only position data. By formulating the dynamics directly on manifold-valued configuration spaces, the method naturally respects the geometric structure of the systems and preserves geometric invariants and conservation laws. The reliance on position measurements alone makes the framework applicable in settings where velocity data are unavailable or noisy. The approach extends naturally to multibody systems, accommodates external control inputs, and demonstrates strong performance on both synthetic and real-world datasets. --- ### Gradient-free learning of a closed-loop wall controller for turbulent drag reduction Authors: Giorgio Maria Cavallazzi, Miguel Pérez Cuadrado, Alfredo Pinelli Published: 2026-07-14 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2607.12626v2 Closed-loop wall controllers learnt by multi-agent reinforcement learning are usually trained on periodic boxes far smaller than the flows they are meant to drive, and a large part of their drag reduction is lost when they are carried across. Retraining on the target domain is not an affordable remedy: the centralised critic that assigns credit to each wall patch degrades as patches are added, the zero-net-mass constraint couples the patches it is asked to separate, and the episodes must be collected in sequence at a cost that grows with the domain. We propose instead a short gradient-free refinement stage, applied to the transferred policy on the domain it will drive. An evolution strategy scores whole flow episodes against a regularised objective, so no credit has to be assigned to individual patches, and the candidates in a generation are independent and run in parallel. Applied to a recurrent multi-agent policy trained on a minimal flow unit at $\Retau\simeq180$ and evaluated on a channel sixteen times larger in wall-parallel area, a few generations raise the drag reduction from $19.0\%$ to $25.7\%$, above the $22.5\%$ of opposition control. Because the policies before and after refinement share an architecture and a training history, the difference between the controlled flows follows from the refinement alone. It shows in the friction decomposition, in the Reynolds stresses and in the near-wall spectra, and the actuation moves from a weak coupling to the wall-normal velocity towards a strong coupling to the streamwise fluctuation. --- ### Gradient-free learning of a closed-loop wall controller for turbulent drag reduction Authors: Giorgio Maria Cavallazzi, Miguel Pérez Cuadrado, Alfredo Pinelli Published: 2026-07-14 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2607.12626v1 Closed-loop wall control learnt by multi-agent reinforcement learning can lower skin-friction drag in turbulent channels, but these gradient-based policies are trained on small periodic boxes and exhibit reduced performance when carried over to a larger domain. We recently showed that such policies are also prone to saturated bang-bang actuations that collapse into standing streamwise waves whose scale is set by the computational box rather than by the near-wall cycle, and proposed architectural fixes that avoid these degeneracies. Here, we employ Evolution Strategy (ES) to optimise a recurrent closed-loop controller directly on a large turbulent channel at $\mathit{Re}_τ\simeq180$, evaluating policy performance over full flow episodes using an energy-aware criterion and processing candidate policies in parallel. To our knowledge, this is the first application of an evolution strategy to the control of a turbulent flow. The ES controller reduces the skin friction by about $26\%$, exceeding the gradient-based multi-agent controller of Cavallazzi et al. (2026), GRU-MARL, trained on a minimal box ($17\%$), and marginally exceeding classic opposition control (OC, $22\%$). A wall-normal decomposition of the friction, Reynolds-stress profiles and anisotropy invariants show that the ES and opposition-controlled flows follow separate trajectories through the buffer layer, reaching comparable drag reduction by different reorganisations of the near-wall turbulence. In particular, the ES actuation correlates predominantly with the streamwise velocity fluctuations rather than with the wall-normal velocity that classical OC targets. --- ### KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill Authors: Yunxin Li, Jinchao Li, Shibo Su, Zhenran Xu, Chenrui Zhao, Tongshu Bian, Xiaoman Liang, Meishan Zhang, Baotian Hu, Min Zhang Published: 2026-07-14 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.12625v2 OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience. To resolve these issues, we propose the Know Deeply, Act Perfectly paradigm for personal assistants, which holds that accumulated user interaction and task-running experience directly improve execution accuracy and efficiency, unifying cognitive comprehension and operational execution. Based on this paradigm, we introduce KnowAct-GUIClaw, a novel Know-Route-Act-Reflect framework designed to address OpenClaw's GUI manipulation deficits and break through its cross-platform and recursive self-improvement constraints. First, the host agent leverages accumulated interaction experience and task-relevant knowledge for long-horizon task decomposition and allocation (Know). Second, a pluggable GUI subagent with an experience-attributable memory system (Know) and self-evolving skill library (Act), enabling seamless cross-platform migration and fast-path integration. Especially, this framework continuously stores user profiles and feedback to improve the accuracy of task decomposition and tool calls. Extensive experiments across Android, iOS, HarmonyOS and Windows show that KnowAct-GUIClaw achieves superior efficiency, accuracy and cross-platform adaptability. Especially, the GUIClaw with open-source Kimi-2.6 models achieves the best performance (64.1%) on the long-horizon MobileWorld benchmark, beating all agentical frameworks and closed-source agentical models, e.g., Seed-2.0-Pro and GPT-5.5. Additionally, the knowledgeable memory and execution skills supported by our framework are transferable across diverse base models, improving by 8.5% with Kimi-2.6. --- ### Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval Authors: Ryotaro Shimada, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Osamu Torii, Yusuke Matsui Published: 2026-07-14 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2607.12621v1 Recent work has shown that "Vision-Free'' approaches (representing images as text) can be effective for standard image retrieval tasks. However, it remains unclear whether this paradigm can effectively handle a more complex, multimodal task, Composed Image Retrieval (CIR), due to the inherent information loss in textual descriptions. In this paper, we introduce a Vision-Free CIR framework that addresses this challenge through two key techniques: (1) Attribute-Augmented Hybrid Scoring, which compensates for lost visual details via explicit attribute matching, and (2) LLM-Based Reranking, which verifies semantic consistency of top candidates. Experiments on the open-domain CIRR dataset show that our approach outperforms existing Zero-shot CIR methods (44.04% R@1, +8.79%). On FashionIQ, our results highlight the trade-off between semantic reasoning and fine-grained visual matching. Ablation studies reveal that both attribute-augmented scoring and LLM-Based Reranking consistently improve performance. --- ### Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing Authors: Amin Beheshti, Rong N. Chang, Boualem Benatallah, Fabio Casati, Schahram Dustdar, Geoffrey Fox, Quan Z. Sheng, Yan Wang, Jian Yang, Albert Zomaya Published: 2026-07-14 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2607.12619v1 The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflows, they confront challenges that the Service-Oriented Computing community has studied for more than two decades: composition, interoperability, quality of service, lifecycle management, governance, security, and trust. Yet much of today's agentic AI ecosystem is developing these foundations ad hoc, without the engineering rigour required for dependable enterprise and societal deployment. This paper introduces Agentic Service-Oriented Computing (ASOC) as a new research and practice area concerned with engineering agents as services, orchestrating services through autonomous and semi-autonomous agents, and governing ecosystems of agents and services under constraints of trust, cybersecurity, compliance, performance, and accountability. We articulate six foundational principles of ASOC (harness-ability, composability, lifecycle engineering, trustworthiness by design, goal-driven orchestration, and observability/accountability) and organise a five-dimensional research agenda spanning: (i) agentic services foundations and lifecycle engineering; (ii) composition, orchestration, and interoperability; (iii) governance, observability, and accountability; (iv) security, trust, and risk management; and (v) evaluation, certification, and Agentic QoS. We argue that the Services Computing community is especially well positioned to provide the conceptual and engineering spine for this emerging field, transforming agentic AI from fragmented demonstrations into dependable, service-based systems worthy of human and organisational trust. --- ### The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models Authors: Shuchan Wang Published: 2026-07-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12616v1 Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While theoretical targets favor straight trajectories, empirical networks develop complex path deformations. This paper presents the Finite-Time Spectral Sensitivity (FTSS) g(t), a gradient-free, forward-pass metric that exposes flow geometry by tracking the root-mean-square singular value of the state-transition matrix. Serving as a continuous proxy for stable rank, g(t) reveals a distinct geometric pathology under data scarcity: while generalizing models maintain stable effective dimensions, overfitting causes a spectral collapse. We leverage this structural phenomenon to develop an internal geometric audit based on g(t). Our framework detects generative memorization using purely internal trajectory dynamics, removing the need for external membership queries or baseline data comparison. --- ### Translation as a Computationally Efficient Bridge: Feasibility of English BERT for Low-Resource Languages Authors: Hielke Muizelaar, Giulia Rivetti, Marco Spruit, Marcel Haas Published: 2026-07-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.12612v1 BERT models have revolutionised Natural Language Processing (NLP) through their ability to process unstructured text across diverse domains. However, developing high-quality BERT models for non-English languages remains challenging due to limited annotated data and high computational demands. Translating non-English data into English and fine-tuning existing English BERT models offers a resource-efficient alternative, yet few studies have structurally compared translation-based fine-tuning with native-language BERT performance across tasks and languages. This study provides such a comparison, evaluating the feasibility of translation-based fine-tuning across six NLP tasks: Sentiment Analysis, Hate Speech Detection, Question Answering, Named Entity Recognition, Part-of-Speech Tagging, and Natural Language Inference, using datasets translated from Bulgarian, Chinese, Dutch, Italian, and Russian. Across all settings, the translation-based approach was comparable or superior in 53.3 percent of cases. Gains were most frequent in Question Answering, Part-of-Speech Tagging, and Natural Language Inference, while performance declines were common in Named Entity Recognition and Hate Speech Detection. The results show that translation-based fine-tuning is most effective for tasks relying on syntactic or structural patterns and for languages typologically close to English, such as Dutch, but less effective for token-level or culturally nuanced tasks, particularly in Chinese. Overall, this study demonstrates that translation-based fine-tuning offers a scalable, resource-efficient, and empirically validated path for extending NLP to low-resource languages while advancing linguistic inclusivity and sustainability in artificial intelligence. --- ### Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs Authors: Zhili Huang, Ling Xu, Hongyu Zhang Published: 2026-07-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.12605v1 Large language models (LLMs) have improved automated program repair (APR), but two limitations remain. First, raw execution traces are often too large and repetitive to serve as effective model context. Second, repeated patch sampling may produce different implementations without yielding distinct root-cause hypotheses or repair strategies. We present CT-Repair, an agentic APR framework representing static and dynamic evidence as queryable Code Property Graph (CPG) and Temporal Execution Graph (TEG). CT-Repair applies a three-stage filtering pipeline to construct compact TEGs. Three finite-state-machine-guided agents analyze each bug from static, dynamic, and hybrid perspectives and independently produce evidence-grounded repair strategies. A strategy-guided generation procedure instantiates these strategies as candidate patches and uses validation feedback to refine the most promising strategy. We evaluate CT-Repair on 854 Java bugs from Defects4J v3.0. In the mixed-model configuration, CT-Repair correctly repairs 489 bugs. Under a controlled GPT-5.4-mini configuration, it repairs 388 bugs, 19 and 30 more than ReinFix and RepairAgent, respectively. The union of the three evidence perspectives repairs 99 more bugs than the strongest individual perspective. The filtering pipeline also compacts runtime evidence, with execution filtering narrowing the candidate method scope by 94.85% on average and behavior filtering further reducing retained runtime records by 55.97%. These results show that structured runtime evidence and multi-perspective reasoning can improve repair effectiveness without relying solely on a larger patch-generation budget. --- ### Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT Authors: Kwang-Hyun Uhm, Inhwa Son, Sung-Jea Ko Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12602v2 Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG. --- ### Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT Authors: Kwang-Hyun Uhm, Inhwa Son, Sung-Jea Ko Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12602v1 Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG. --- ### Lightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devices Authors: Raheen Junaid Wani, Smruti R. Sarangi Published: 2026-07-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12599v1 Time-series anomaly detection is increasingly important in IoT systems, sensor networks, and edge monitoring applications, where models must operate under strict constraints on memory, latency, and power consumption. While recent deep-learning approaches have improved detection accuracy, many remain computationally expensive and often fail to capture subtle anomalies due to limited multi-scale sensitivity. Autoencoders are widely used for anomaly detection because they reconstruct normal patterns well, leading to elevated reconstruction errors for anomalous inputs. Their simplicity and efficiency also make them suitable lightweight backbones for handling multi-scale inputs. To address these challenges, we propose a Lightweight MultiScale AutoEncoder (LMSAE) network for univariate time-series anomaly detection, designed to be compact and computationally efficient. LMSAE leverages the Discrete Wavelet Transform (DWT) to extract multi-scale features and employs a multi-scale loss function to improve sensitivity to subtle or hidden anomalies. Experiments on benchmark datasets demonstrate competitive or superior detection performance despite using significantly fewer parameters and a model size of less than 500 KB. LMSAE also achieves low-latency, low-power inference on the NVIDIA Jetson Nano, with 9x reduction in inference latency and 2x reduction in power consumption, making it ideal for edge deployment. --- ### WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction Authors: Li Hu, Guangyuan Wang, Peng Zhang, Bang Zhang Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12592v1 We present WanToFight, a generative game engine that simulates real-time, two-player The King of Fighters '97 (KOF~'97) gameplay from keyboard input. Prior generative game engines target either single-player first-person settings or non-real-time cooperative scenarios; multi-player control, real-time inference, complex physical interaction, and adversarial gameplay have not been jointly addressed. WanToFight closes this gap with three components built on the Wan-1.3B video diffusion transformer: a streaming autoregressive generator with block-causal attention and a rolling KV cache; a visually grounded Player Association module that binds each player's keyboard signal to a character identity; and a gated, locally causal keyboard injection module trained with a single-player-to-full-gameplay curriculum. A four-step DMD-distilled student paired with a pruned VAE decoder sustains 30FPS at 512x384 on a single NVIDIA RTX 5090 over the duration of a complete match. To our knowledge, WanToFight is the first generative game engine to combine multi-player control, real-time inference, complex physical interaction, and adversarial gameplay in one system. --- ### Environment Parameter Gradient Theorem for Co-Design in Reinforcement Learning Authors: Amber Srivastava Published: 2026-07-14 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2607.12590v2 Reinforcement learning (RL) is traditionally concerned with learning a control policy for a fixed environment. In many engineering systems, however, the environment itself is alterable, i.e., physical or operational parameters can be tuned to shape the system's transition dynamics and costs experienced by the RL agent. This motivates jointly optimizing both the policy and the environment design parameters. To this end, we establish an Environment Parameter Gradient Theorem --- a formal expression for the gradient of the RL's objective function with respect to environment parameters. The key theoretical device is a generalized action-value function $Q_{π,ξ}(s,a,ζ)$, which comprises two copies of the environment parameters: $ζ$ governs the cost and transition dynamics at the current state--action pair, while $ξ$ governs the future rollouts. This decoupling yields a tractable closed-form gradient expression and is essential to the theorem's derivation. Building on this result, we develop a model-free algorithm that simultaneously learns the optimal policy and the environment parameters. We demonstrate the efficacy of our framework on a UAV network design problem, where the optimal UAV placement (environment parameters) and communication routes (governed by the policy) are learned jointly to minimize the total communication cost in the network. --- ### Environment Parameter Gradient Theorem for Policy-Environment Co-Design in Reinforcement Learning Authors: Amber Srivastava Published: 2026-07-14 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2607.12590v1 Reinforcement learning (RL) is traditionally concerned with learning a control policy for a fixed environment. In many engineering systems, however, the environment itself is alterable: physical or operational parameters can be tuned to shape the transition dynamics and costs experienced by the agent. This motivates jointly optimizing both the policy and the environment design parameters. To this end, we establish an Environment Parameter Gradient Theorem -- a formal expression for the gradient of the value function with respect to environment parameters. The key theoretical device is a generalized action-value function $Q_{π,ξ}(s,a,ζ)$, which comprises two copies of the environment parameters: $ζ$ governs the cost and transition dynamics at the current state--action pair, while $ξ$ governs the future rollouts. This decoupling yields a tractable closed-form gradient expression and is essential to the theorem's derivation. Building on this result, we develop a model-free algorithm that simultaneously learns the optimal policy and the environment parameters. We demonstrate the efficacy of our framework on a UAV network design problem, where the optimal UAV placement (environment parameters) and communication routes (governed by the policy) are learned jointly to minimize the total communication cost in the network. --- ### Vertical Standardisation for High-Risk AI Systems under the EU AI Act: A Domain-Specific Framework for Algorithmic Hiring Authors: Anna Gatzioura, Vrettos Moulos, Nina Baranowska Published: 2026-07-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12588v1 According to the recent European legislation, high-risk AI systems will have to adapt in order to comply with requirements related to specific areas, like risk management, data quality and governance, logging and traceability, technical documentation, transparency, human oversight, and accuracy, as outlined in the European Artificial Intelligence (AI) Act. As the standardisation process for AI is expected to remain iterative and, so far, there are no European standards on AI fully covering the challenges of algorithmic hiring, we propose specific standardisation-oriented recommendations related to the relevant AI areas specified by the European Commission. For each of these areas, we set the context by describing the requirements that AI systems in high-risk domains, and especially in recruitment, should fulfil, as well as the activities that should be carried out to ensure their appropriate use and desired performance, in line with the requirements deriving from the AI Act. Unlike existing horizontal approaches to AI governance and standardisation, this paper contributes a vertical, domain-specific framework for algorithmic hiring, and especially ranking-based recruitment systems, by mapping the requirements of the AI Act to concrete standardisation recommendations, focusing on lifecycle discrimination risks, fairness-aware data governance, explainability, human oversight, and post-deployment monitoring in recruitment systems. Even though our recommendations were informed by the outcomes of the European project FINDHR, they are not tied to the project's technical artefacts and could be implemented using alternative methods, tools, or governance mechanisms. --- ### Medical Image Segmentation based on Deep Active Contour and Mean Curvature Loss Function Authors: Xiao-qiang Zhai, Zhi-feng Pang, Peng Zheng, Ze-wen Li, Yan-zhe Hou Published: 2026-07-14 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.12586v3 Medical image segmentation is an important task in clinical analysis. Although deep learning techniques are widely used, training at the individual pixel level ignores geometric prior information about the region being segmented. Integrating the Chan-Vese model into the loss function is a well-established remedy that accounts for the regions inside and outside the segmentation and, through its length term, for boundary regularity. However, such losses still lack an effective characterisation of local boundary geometry. We introduce the mean curvature as a natural geometric constraint and propose a Deep Active Contour and Mean Curvature (DACMC) loss function, in which a fixed convolution kernel approximates the mean curvature at negligible computational cost. The loss has a single hyper-parameter, the curvature weight $λ$, fixed at $10^{-3}$ for all experiments. We evaluate DACMC on three public datasets - liver computed tomography (CT), spleen magnetic resonance imaging (MRI) and dermoscopy images from the International Skin Imaging Collaboration (ISIC) - using two encoder-decoder networks as backbones and the Dice similarity coefficient (DSC), the 95th-percentile Hausdorff distance (HD95), the Jaccard similarity (JS) and the average surface distance (ASD) as metrics, against the cross-entropy, Dice, active contour and elastica losses. DACMC attains the best or second-best DSC in five of the six dataset-backbone settings; on spleen MRI it reduces HD95 to 16.28 millimetres and ASD to 1.90 millimetres, and on ISIC it reduces HD95 to 7.08 millimetres. A sensitivity study shows a broad plateau for $λ\leq 10^{-3}$ and degeneration only when the curvature term dominates. --- ### Medical Image Segmentation based on Deep Active Contour and Mean Curvature Loss Function Authors: Xiao-qiang Zhai, Zhi-feng Pang, Peng Zheng, Ze-wen Li, Yan-zhe Hou Published: 2026-07-14 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.12586v1 Medical image segmentation is a crucial task in the field of clinical analysis and applications. Though deep learning techniques recently play a crucial role in several scenarios, the training at the individual pixel level leads to a lack of geometric prior information. Scholars proposed to integrate the Chan-Vese model into the loss function for training which can take into account the region and length of the region inside and outside the segmentation process and then improve the performance in medical image segmentation. However, these methods still lack an effective characterization of the segmented region. To overcome this problem, we introduce the mean curvature as a geometric natural constraint and propose a Deep Active Contour and Mean Curvature (DACMC) loss function where the convolution kernel is used to approximate the mean curvature to save computational cost. We have validated the performance of our method on the liver and spleen dataset. Our proposed method demonstrates new state-of-the-art performance on several segmentation datasets. --- ### Explainable-by-Design Audio Deepfake Detection via Wiener-Hopf Linear Prediction Authors: Mattia Tamiazzo, Simone Milani, Massimo Iuliani, Marco Fontani Published: 2026-07-14 Categories: cs.SD, cs.AI, cs.CR, cs.MM arXiv: https://arxiv.org/abs/2607.12584v1 The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics. While recent approaches achieve high detection accuracy, they typically rely on black-box architectures that offer limited interpretability and high computational complexity. In this paper, we propose an explainable-by-design audio deepfake detection framework based on Wiener-Hopf linear prediction, processed by a lightweight 2D Convolutional Neural Network (CNN). This design enables a direct and transparent connection between classification outcomes and the acoustic properties of the signal. Experimental results on benchmark datasets demonstrate competitive detection performance while maintaining significantly lower computational complexity compared to state-of-the-art solutions. The interpretability analysis using Grad-CAM reveals that the classifier focuses on low-order predictor coefficients and on silence and transitional regions, suggesting that the Wiener-Hopf predictor captures reverberation characteristics and subtle statistical inconsistencies in synthetic speech. Finally, robustness experiments show that fine-tuning effectively recovers detection performance under common post-processing degradations, including additive noise, MP3 compression, and telephone filtering. --- ### Wasserstein gradient flows for Coulomb discrepancies Authors: Antonin Chodron de Courcel, Matthew Rosenzweig Published: 2026-07-14 Categories: math.AP, stat.ML arXiv: https://arxiv.org/abs/2607.12579v2 We study the long-time behavior of the Wasserstein gradient flow of the squared Maximum Mean Discrepancy (MMD) between a probability measure $ρ$ and a target measure $μ$, where the underlying kernel is given by a Coulomb potential. For $L^\infty$ target densities $μ$, we establish the existence of global weak solutions starting from arbitrary Borel probability measures and prove that the density $ρ_t$ belongs to $L^\infty$ for any $t>0$. We also show that the Hölder norm can grow exponentially in time. On the flat torus ${\mathbb{T}}^\mathsf{d}$, we prove a global metric PL inequality for every finite-Coulomb-energy source and nearly uniform target. For general bounded, uniformly positive targets, we prove exponential decay of the squared MMD without requiring a lower bound on the initial data, using a defective PL inequality. We also prove that the usual PL inequality may fail when the target vanishes only at one point and that, when $\mathsf{d}\ge2$, no PL constant can hold uniformly over all targets satisfying a prescribed lower bound. On ${\mathbb{R}}^\mathsf{d}$, for $\mathsf{d}\ge2$, under radial symmetry, source-support inclusion, and target-positivity assumptions, we establish a PL inequality and exponential convergence. On the unrestricted whole-space class, neither a multiplicative squared-MMD decay modulus uniform over the initial datum nor a global PL inequality can hold. Finally, in every dimension and in both spatial settings, we prove that every Lagrangian critical point coincides with the target when $(ρ-μ)^+$ is absolutely continuous. In dimension two, the energy supplies uniform tightness. This implies that if our constructed solutions have finite energy at some positive time, then they converge to the target narrowly and strongly in negative-order Sobolev spaces. --- ### Deep Learning-based Surrogate Modelling of the LOD Method for Multiscale Problems Authors: Marc Haltmayer, Jaemin Seo, Yuseung Lee, Sungyeop Lee, Jaehoon Jeong, Jae Yong Lee Published: 2026-07-14 Categories: math.NA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.12570v1 Multiscale problems are notoriously difficult to tackle using traditional numerical methods, as accurately resolving fine-scale features often requires prohibitively fine discretizations. This challenge is particularly pronounced in applications such as materials science, fluid dynamics, climate systems, chemical processes, and complex networks. Recent neural operator models provide a promising data-driven alternative, but frequently struggle to achieve sufficient accuracy in the presence of strongly heterogeneous or oscillatory coefficients. In this work, we focus on the solution of elliptic PDEs with rough and high-contrast inputs. The Localized Orthogonal Decomposition (LOD) method is a well-established numerical approach for such problems, but it comes, however, at a substantial computational cost. We investigate the performance of popular neural operator architectures on these challenging multiscale problems and identify key limitations in their ability to resolve fine-scale structure. To overcome these challenges, we introduce LOD-MSNO (LOD-Multiscale Neural Operator), a hybrid approach that leverages the LOD method as a strong multiscale prior by building on its representation of the solution as a linear combination of problem-adapted basis functions, while addressing its main computational bottlenecks through data-driven operator learning. We further provide theoretical error estimates for the proposed coefficient-learning framework. Lastly, we demonstrate the potential of our proposed method to outperform current neural operator baselines in terms of accuracy for challenging multiscale inputs, while mainly retaining the computational efficiency of neural operator models. --- ### Traceback Translators Against Forgetting in Continual Fake Speech Detection Authors: Enrico Gottardis, Mattia Tamiazzo, Simone Milani Published: 2026-07-14 Categories: cs.CV, cs.AI, cs.CR, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2607.12569v1 Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual learning techniques are nowadays widely considered feasible strategies for updating models to new datasets, but they also lead to decreased performance on previously seen samples (catastrophic forgetting). In this work, we propose a forgetting-resilient solution based on the adoption of domain translators within a frozen detector, which remaps the new feature spaces into the original ones by means of a traceback translator network. Experimental results show that this strategy enables the achievement of high detection rates with respect to traditional retraining, while minimizing the computational effort and preserving the detection accuracy on previous data. --- ### Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding Authors: Yifan Lu, Ziqi Zhang, Chunfeng Yuan, Jun Gao, Bing Li, Weiming Hu Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12557v1 Large Vision-Language Models (LVLMs) face significant challenges in long video understanding due to the excessive computational cost and information loss associated with uniform sampling. Existing keyframe selection methods often treat video frames as atomic entities and allocate visual budgets equally, thereby overlooking high-level semantic structures and introducing substantial redundancy. To address these limitations, we propose GMM-EVA (Gaussian Mixture Modeling for Event-Aware Visual Allocation), which leverages Gaussian Mixture Models to model event-level structure from discrete frame-wise observations. A differentiated allocation strategy is then applied to preserve one primary high-resolution keyframe per event for high-fidelity detail, while utilizing lower-resolution secondary keyframes to maintain temporal context and optimize token budgets. GMM-EVA is a training-free, plug-and-play framework that generalizes robustly across various relevance measures and downstream LVLMs. Extensive experiments on multiple long video benchmarks demonstrate that our method significantly outperforms uniform sampling. Notably, GMM-EVA achieves comparable performance to baseline selection methods while utilizing only approximately half of the visual token budget, highlighting its superior efficiency and effectiveness. --- ### CGRL: Concept-Guided Pruning and Representation Learning for Whole-Slide Image Classification Authors: Thuc Huynh, Tuan Le, Doanh C. Bui Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12556v1 Weakly supervised whole-slide image (WSI) classification is widely used in computational pathology because slide-level labels are easier to obtain than dense region annotations. Existing multiple instance learning (MIL) methods often aggregate large bags of patch embeddings using mainly visual cues, which can retain many non-informative patches and provide weak alignment between instance features and class-level disease semantics. We propose Concept-Guided Pruning and Representation Learning (CGRL), a simple framework that introduces class-level concept prototypes derived from disease prompts into the MIL pipeline. First, concept-relevance pruning ranks patch instances by their similarity to class concepts and retains the top-K concept-relevant patches for downstream MIL aggregation. Second, concept-guided contrastive representation learning constructs class-wise positive and negative patch sets from the same similarity matrix and optimizes target-class, symmetric auxiliary, and cross-class separation objectives, thereby regularizing the projected concept space. We evaluate CGRL on TCGA-BRCA and TCGA-NSCLC using multiple representative MIL methods. Experimental results show that CGRL improves several model-dataset combinations, with gains depending on the downstream MIL model and dataset. It achieves particularly clear improvements in accuracy and macro-F1 while reducing computational cost through concept-relevance pruning. These findings demonstrate that class-level semantic concepts provide an effective and practical prior for patch selection and representation learning in weakly supervised computational pathology. --- ### A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation Authors: Rahul Krishnan, Volker Schulz Published: 2026-07-14 Categories: cs.LG, cs.CL, math.OC arXiv: https://arxiv.org/abs/2607.12550v4 The key-value (KV) cache is the dominant memory bottleneck in long-context language model inference. Existing compression methods apply low-rank factorization or quantization independently, without jointly allocating rank and precision under a shared storage budget. We introduce JoLT, a training-free compressor that treats grouped prefill caches as fourth-order tensors and applies partial Tucker decomposition along the token and feature modes, the two axes that carry low-rank structure, while leaving the head and layer modes intact. A rotated low-bit quantizer captures the truncation residual, and a single Lagrangian dual allocates per-group Tucker ranks and residual bit-widths under a global byte constraint. FlashJoLT replaces the exact token-mode SVD with a randomized approximation that matches JoLT within the free zone at a fraction of the compression cost, and a fused Triton decode kernel evaluates attention directly over the stored factors without materializing dense KV tensors. Across five models from four architecture families, covering multi-head attention, grouped-query attention, and mixture-of-experts architecture, JoLT achieves 2 - 3x compression with less than 0.2% perplexity degradation, without retraining. On RULER at 64K context with LLaMA-3.1-8B, retrieval accuracy remains near-lossless through 3x and declines by only 0.90 and 2.40pp at 4x and 5x, respectively. JoLT demonstrates that tensor-aware low-rank decomposition and quantized residuals, unified under a single storage budget, achieve near-lossless KV-cache compression across diverse model architectures without retraining. --- ### A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs Authors: Rahul Krishnan, Volker Schulz Published: 2026-07-14 Categories: cs.LG, cs.CL, math.OC arXiv: https://arxiv.org/abs/2607.12550v2 The key-value (KV) cache has become the dominant memory cost of transformer inference: it grows with batch size, context length, and depth, and at long context it, rather than the model weights, sets the throughput ceiling. Existing reductions fall into two families. Low-rank methods factor two-dimensional slices of the cache, either per-head matrices or cross-layer feature blocks, and quantization methods lower the bit-width of every entry. Neither exploits the fact that the cache at a layer is naturally a third-order tensor whose three axes, the heads, the tokens, and the features, carry very different amounts of redundancy. We take this tensor view directly. Our method, JoLT (Joint Lagrangian Tucker), applies a partial Tucker decomposition that compresses only the token and feature axes while leaving the head and layer axes intact, then restores the energy that truncation discards with a rotated low-bit residual: a random orthogonal rotation followed by low-bit quantization. A single Lagrangian dual allocates the Tucker ranks and the residual bit-widths together, per layer group and separately for keys and values, under one byte budget. The result is a near-lossless 2-3x compression. Perplexity stays near-lossless on both a grouped-query-attention model (Mistral-7B-v0.3) and a multi-head-attention model (LLaMA-2-13B), and GSM8K accuracy and needle-in-a-haystack retrieval hold at the uncompressed baseline at 2x on both architectures and through 3x on the GQA model. At 2x, JoLT reconstructs the cache to relative Frobenius error 0.009 (K) and 0.006 (V) on both architectures. A randomized-SVD variant, FlashJoLT, delivers a 5-13x compression-time speedup at 1024-token context and matched quality. --- ### Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel Authors: Niccolò Caselli, Francesco Massafra, Samuele Punzo, Salvatore Lo Sardo, Ippokratis Pantelidis, Sathya Kamesh Bhethanabhotla Published: 2026-07-14 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.12547v2 We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control. We introduce Hi-LeWM, an extension that freezes the pretrained low-level LeWM and adds high-level planning over latent subgoals. We evaluate Hi-LeWM on PushT and Cube across increasing goal offsets. Hierarchy does not automatically improve performance: at short horizons, the best configuration uses a one-step high-level horizon, while longer horizons reveal a mismatch between the learned high-level action space and the inference-time search distribution. Experiments with true future latent subgoals show that the frozen low-level controller can execute well-aligned intermediate targets, indicating that high-level subgoal generation is the main bottleneck. Unconstrained search can select latent macro-actions that appear favorable under the learned model but produce poor control targets. Constraining search around macro-actions encoded from training trajectories, with appropriate subgoal execution timing, recovers useful hierarchical regimes, improving over flat LeWM by +11.3 percentage points at medium-range horizons and +14.7 percentage points at the longest PushT horizon. Overall, temporal abstraction can benefit compact frozen LeWM, but only when high-level search remains compatible with the low-level controller --- ### VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness Authors: Niklas Bunzel Published: 2026-07-14 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2607.12545v1 Adversarial robustness research has produced hundreds of defended models over the past decade, yet the literature almost universally reports robustness results in isolation: standard (clean) accuracy and adversarial accuracy of the robust model are shown, but the gap to the corresponding vanilla model is rarely quantified. We introduce VanillaBench, a systematic benchmark that makes this gap explicit. For every adversarially-trained model catalogued by RobustBench across four threat models, we compute the accuracy difference against multiple vanilla references from Papers with Code, computed over both all entries and no-extra-data entries, the best vanilla model as of the robust model's publication year, and an architecture-matched baseline. Across all 186 robust models, the mean delta clean relative to the best vanilla model ranges from -7.7 to -29.5 percentage points, and even the single most robust model per track still trails its temporal vanilla counterpart by 4.0-21.0 points. The architecture-matched comparison, which isolates the effect of adversarial training from architectural differences, reveals a mean gap of -3.5 to -17.5 points. Restricting this architecture-matched comparison to models whose vanilla accuracy is known for the exact same architecture, rather than approximated from a related one, narrows the gap to -4.0 to -14.0 points. These results demonstrate that the robustness-accuracy trade-off is substantially larger than what is typically conveyed by individual papers. This information is critical for practitioners and decision-makers. When deploying models in real-world settings, the accuracy cost of robustness directly affects business outcomes, yet current publications do not provide the vanilla baseline needed to assess it. We argue that future robustness evaluations should report vanilla-referenced accuracy gaps as a standard component. --- ### Edge-Aware Thermal Infrared UAV Swarm Tracking Authors: Yu-Hsi Chen Published: 2026-07-14 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.12544v1 Thermal infrared (TIR) imaging is essential for UAV swarm operations in visually degraded environments. However, tracking tiny UAVs remains challenging due to limited appearance cues, frequent occlusions, and rapid maneuvers. Despite significant progress driven by benchmarks such as the Anti-UAV challenge, existing methods primarily prioritize accuracy while overlooking the computational constraints of real-time edge deployment. The standard Kalman Filter (KF) offers the efficiency required for edge devices, yet its constant-velocity assumption often breaks down under highly dynamic UAV motion and thermal sensor jitter. More sophisticated nonlinear estimators can improve robustness but often introduce additional computational costs. To address this gap, we propose an edge-aware online tracking pipeline centered on the Adaptive Kinematic Kalman Filter (AKKF), which augments the linear KF with state-dependent kinematic modeling while preserving real-time efficiency. Combined with transient false-positive suppression and kinematics-driven predictive coasting, the presented pipeline improves trajectory continuity under challenging TIR conditions. Experiments on the Beyond Strong Baseline (BSB) benchmark provide a starting point for edge-aware UAV tracking by jointly evaluating tracking performance and computational efficiency, offering insights toward future real-time deployment. --- ### DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models Authors: Francesco Taioli, Daniel Coelho, Iaroslav Melekhov, Roberto Alcover-Couso, Jose Miguel Grande Saiz, Virginia Fernandez Arguedas, Artur Bekasov Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12539v1 Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions. First, we introduce ABO-Edit, a dataset specifically designed to study object consistency, comprising over 12,000 triplets of source images, editing prompts, and high-quality target images rendered from artist-designed 3D assets, with multi-view coverage and human-verified quality control. Second, we uncover an overlooked property of image-editing rectified flow models: the conditioning embedding space, not directly supervised during training, encodes a prediction of the final generated image even at high noise levels. Third, exploiting this finding, we propose FlowMirror, a parameter-free auxiliary loss that supervises this conditioning embedding space. Without architectural changes, our method improves generation quality across several metrics over baselines. --- ### Evidence-Grounded AI for Musculoskeletal Care Authors: Wenjie Li, Yujie Zhang, Fanrui Zhang, Haoran Sun, Renhao Yang, Junjun He, Weiran Huang, Yuanfeng Ji, Chenrun Wang, Kailing Wang, Hongcheng Gao, Kaipeng Zhang et al. Published: 2026-07-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12527v3 Musculoskeletal diseases are among the leading causes of disability and drive the greatest global need for rehabilitation. Because recovery, remodelling and degeneration of bones, joints and related tissues unfold over months to years, care requires longitudinal management rather than isolated decisions. Clinicians must repeatedly integrate evolving patient evidence, medical knowledge and stage-specific functional goals, yet evidence is often fragmented across visits, departments and hospital systems, disrupting continuous, individualised management. Here we report OrthoPilot, a clinical artificial intelligence (AI) system powered by a large language model (LLM) that integrates hospital data streams with authoritative external knowledge for continuous musculoskeletal care. It autonomously retrieves real-time imaging, laboratory, pathology and order data and translates evolving patient states into evidence-based decisions from admission diagnosis through rehabilitation planning. We established a specialist-validated benchmark from real-world electronic health records (EHRs) spanning 1,000 disease codes. In a full-pathway reader study against 81 orthopaedic physicians, OrthoPilot outperformed experts with 25 years of experience in diagnostic reasoning, clinical decision-making and management planning. This advantage generalised across 60 external clinical centres, where OrthoPilot surpassed all evaluated intelligent systems. In a prospective physician decision-making study of 1,870 complex cases, OrthoPilot improved full-chain management success by 10.6%. In a randomised deployment involving 8,240 inpatients, integration into routine care increased cumulative cases per bed by 9.7% and improved patient-reported access to health information. These results move clinical AI from predicting isolated events toward executing longitudinal management across complete musculoskeletal care pathways. --- ### From Preimage Search To Source-Grounded Feature Inversion Authors: Kaixiang Shu Published: 2026-07-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.12526v2 Interpreting a neural network requires understanding what its internal features extract from a particular input. Feature inversion seeks to express a selected feature in the input domain, but canonical iterative methods search for an input whose re-encoded representation matches the target. Because many inputs can satisfy this constraint, target matching alone does not specify the inverse associated with the sample that generated the feature. We formulate source-grounded feature inversion by conditioning the inverse on the source-local network geometry at the target-generating input. At each boundary of the computational DAG, backpropagation provides the correct reverse dependencies but transports an adjoint signal rather than an upstream-state estimate. We locally repair this signal with a closed-form matrix Wiener map from a mean-seed VJP to the upstream state, followed by a second Wiener map for the JVP forward-consistency residual, and compose the repaired states through the same DAG in one finite reverse pass. One calibrated zero-intercept map family supports new inputs, depths, channels, and channel groups across diverse CNN and Transformer architectures, tensor components, and visual distributions without query-specific optimisation. Matched target and source controls verify that each inverse depends on the selected feature and the local operators of the sample being explained, rather than a target-independent image template. Prediction-conditioned feature atlases align these visualisations with independent interventions on the corresponding internal features. Together, source-grounded feature inversion opens the model's hidden feature hierarchy to inspection at the level of individual layers and channels, linking what the network extracts from an input to the internal evidence that shapes its decision. --- ### OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning Authors: Emil Mittag, Richard Dazeley, Peter Vamplew Published: 2026-07-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.12523v1 Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of out-of-distribution conditions is pivotal to determining when an agent's observations, transitions, or trajectory dynamics deviate from the assumptions underpinning its policy training. Current out-of-distribution (OOD) detection benchmarks typically evaluate image classifiers or static low-dimensional datasets, failing to account for the complex, action-dependent temporal structure inherent in RL trajectories. To address this gap, we present OOD-RL-Bench, a comprehensive and extensible framework designed to evaluate OOD detectors against categories of anomalies injected into RL trajectories. Detectors and anomaly injectors are integrated through shared interfaces and configuration, which allows new scoring methods and perturbation families to be evaluated without modification of the core benchmark loop. We evaluate the utility of the framework using a Deep Q-Network policy within the LunarLander-v3 environment. We assess the performance of each detector across a suite of anomaly types using matched-time AUROC, matched-time AUPRC, matched-time false-positive rate, detection delay, and segmented-onset metrics. Our analysis reveals significant performance variance across anomaly types: observation perturbations and regime switches are identified with high accuracy by several methods, while observation delay and action-conditioned dynamics remain difficult even when post-onset anomaly scores are compared against clean scores from the same timesteps. We make the framework, trained policy checkpoint, and complete results publicly available as a reproducible artefact. --- ### The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank Authors: Bojie Li, Noah Shi Published: 2026-07-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.12520v1 What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem. Citations explain about a third of whether a model recognizes a researcher; we target the residual and build NameRank, a (0,1) recognition score: each of 4,685 entities in 54 cohorts is probed with one open-ended question across 36 models, and an independent judge returns a binary verdict against a curated gold -- did the model state a specific, non-guessable fact about this exact entity? -- so hallucination, context echo, and guesses earn nothing. Synthetic-null entities hold the floor near zero, and verdicts track the entity, not the model. One thesis organizes the findings: recognition is paid to named, indexable artifacts, not to credentials or titles. Every Olympic-style credential sits below a working-researcher baseline, because no named artifact ships with the medal, yet the ranking inverts at the marquee tier, where Nobel, Turing, and Fields laureates saturate the panel. For independent creators the tool out-ranks its maker, and the credential that does propagate is a named method or awarded paper. Being one of many named contributors to a celebrated artifact, by contrast, earns almost nothing -- the authors listed on a flagship model report or system card sit near the recognition floor -- because recognition attaches to the artifact's own distinctive name, not to the roster behind it. No bibliometric predicts recognition well; top-density institutions out-recognize peers at matched citations; and on 258 news events recognition loads on peak salience, not persistence. A self-report probe shows introspection reads a corpus prior, not its own knowledge. --- ### DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMs Authors: Rongxin Gao, Yuzhi Huang, Dongxuan Liu, Chu Li, Zhenye Wang, Jie Wu, Shuzhao Xie, Jingyan Jiang, Xinghao Ding, Xiaotong Tu, Yue Huang Published: 2026-07-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.12503v2 4D spatio-temporal reasoning, jointly modeling 3D spatial structure and temporal evolution, is essential for understanding dynamic worlds and enabling embodied interaction. While current Multimodal Large Language Models (MLLMs) show strong capabilities in static scene understanding and coarse-grained 4D tasks, they still have notable limitations in continuous dynamic scene perception, especially in tracking dynamic object evidence for coherent 4D spatio-temporal reasoning. This shortcoming stems mainly from relying on sparse frame-level observations, fragmenting continuous dynamic cues and leaving models unable to disentangle genuine object dynamics from camera-induced apparent motion. Inspired by humans tracking dynamic cues while compensating for viewpoint changes, we propose DynTrace, a training-free framework for 4D spatio-temporal reasoning with two complementary components. Dynamic Trajectory Visualization (DTV) reprojects world-coordinate trajectories onto the image plane, providing geometry-informed visual priors that disentangle genuine object dynamics from camera-induced apparent motion. Meanwhile, the Dynamic Trace Token (DT-Token), organized into a Dynamic Trace Graph (DTG), tracks object-level dynamic cues, trace evolution, and key moments, maintaining continuous dynamic object evidence for coherent 4D reasoning. Together, these two components equip MLLMs with continuously tracked dynamic object evidence, grounded in geometry-informed visual priors and structured spatio-temporal traces. DynTrace consistently improves open-source MLLMs, achieving state-of-the-art results on Dyn-Bench, VLM4D, and DSI-Bench, validating the importance of tracking dynamic object evidence for robust 4D spatio-temporal reasoning. --- ### Gauge-Fixing the Forward-Forward Objective: A Whitened Goodness Derived from a Likelihood-Ratio Account Authors: Paolo Giannitrapani Published: 2026-07-14 Categories: cs.LG, eess.IV, stat.ML arXiv: https://arxiv.org/abs/2607.12501v3 The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones. Under an explicit generative model this goodness is the sufficient statistic of a likelihood-ratio test, and the pairwise form of the objective admits a gauge: a layer can lower its loss by inflating the scale of its weights rather than by separating the two populations. The analysis prescribes the repair - a whitened, scale-invariant goodness trained online within each layer - which we evaluate as a training procedure. Across three corpora, three depths and a fourfold range of layer width (13 seeds per cell), it raises linear-probe accuracy over the standard pairwise objective in every measured cell - by 4 to 7 points on eight of nine corpus-depth combinations - and closes 16-61% of the gap to end-to-end backpropagation. A control isolates the mechanism: Hinton's fixed-threshold loss also bounds the runaway, to a factor of 1.4 against 133, yet tracks the unmodified baseline - invariance to the gauge, not a bound on it, is what pays. Against the strongest published alternative - a sparse, top-k goodness - the derived objective is statistically indistinguishable on two corpora of three, yet only it removes the runaway: sparsity and gauge-invariance are independent axes, and the published variant recovers accuracy while leaving the pathology in place. We state the boundaries we measured, and every prediction was recorded before its experiment with the refutations reported. ---