# Research Papers — 2026-08 · bundle page 120 of 240 > Full-text markdown of papers #5951–6000 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/120 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/119.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/121.md) ### An Evaluation Framework for National AI Regulation Authors: Kaushik Sanjay Prabhakar, Tarun Adarsh R S, Amal Dhivyan Gregory, Sreeparvathy Sajeev, Utkarsh Tomar, Avyay M Casheekar Published: 2026-08-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.15417v1 Governments use laws, institutions, funding programs and nonbinding guidance to shape how AI is developed and used. Comparing these national approaches is difficult. A binding rule and a detailed voluntary framework can address the same problem but create different duties. The resources needed to carry them out also differ by jurisdiction. This paper develops an evaluation framework for the documented design and implementation readiness of national AI policy. The comparison covers China, India, Japan, Singapore, South Korea, the United Kingdom and the United States. The European Union is included as a supranational comparator. The framework evaluates a versioned portfolio of official instruments rather than one prominent law or strategy. Its criteria ask whether the portfolio governs serious AI risks and whether responsible institutions can implement its commitments. They examine coverage across the AI lifecycle and the protections available to people affected by AI systems. Public benefit and responsible innovation remain a separate part of the assessment. Each sub-criterion is scored through ordered anchors and tied to the provision that supports the judgment. The protocol also records the source search, missing evidence, included instruments and cutoff date. The result is a traceable comparison of policy content that keeps category differences visible. It evaluates what a portfolio provides on paper. It does not estimate enforcement success or policy outcomes. --- ### Invariant Pretraining for Robust Code Representations Authors: Yifeng He, Yundi Xu, Christopher Castro Gaw Gonzalo, Zili Wang, Hao Chen Published: 2026-08-15 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.15412v1 Encoder-based code representation models remain widely deployed for discriminative tasks such as clone detection and code classification, where their small size and low inference cost are decisive. Their robustness, however, is fragile: under invariant programs, semantically equivalent code written in different syntactic forms, learned representations degrade substantially even though program behavior is unchanged. We present an empirical study of this robustness gap across four encoder baselines, two downstream tasks, and four datasets, together with a minimal code-only continued pretraining recipe that closes much of it. Our method, invariant pretraining (InvPT), applies semantic-preserving transformations to the corpus and combines masked language modeling with multi-positive supervised contrastive learning that treats all augmentations of the same source function as positives, mixing self-contrast pairs (same code, different masks) with invariant-contrast pairs (transformed code) for positives of varying difficulty. Unlike prior contrastive code encoders, InvPT does not require paired natural-language data. Across our evaluation, InvPT improves robustness on transformed test sets by up to 11 percentage points on clone detection and 19 on code classification while matching or improving standard accuracy, and our ablations isolate multi-positive invariant contrast as the main source of the gains. Our aim is not a new objective but a careful measurement of where encoder robustness breaks and how far a simple, code-only recipe can recover it. --- ### A survey of AI-generated voices and their detection Authors: Chengzhe Sun, Tianle Yang, Siwei Lyu Published: 2026-08-15 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.15411v1 The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly. These technologies power accessibility tools, virtual assistants and creative applications, but they also enable harmful uses, including impersonation, fraud and disinformation. Recent incidents of voice cloning scams targeting businesses and political leaders underscore the urgent need for robust safeguards. Unlike image and video deepfakes, the detection of synthetic voices poses unique challenges due to the complexity of phonetics, prosody and auditory perception. This survey offers a comprehensive overview of AI voice generation and detection methods, encompassing both the technical foundations and the latest state-of-the-art advances. This study also identifies key open challenges, benchmark resources and future directions to make this survey useful for future researchers. --- ### FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge Authors: Rajat Bhattacharjya, Yoomee Jung, Minwoo Kim, Sing-Yao Wu, Eli Bozorgzadeh, Nalini Venkatasubramanian, Nikil Dutt Published: 2026-08-15 Categories: cs.DC, cs.AI, cs.CV, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2608.15410v1 Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents. However, existing benchmarks largely focus on generic visual scenes and overlook the domain and resource constraints encountered in flood-response platforms. We present FloodReasonBench, a benchmark for VLM reasoning segmentation for embodied flood response at the edge. At its core, FloodReasonBench introduces FloodResponseSeg, a flood-specific reasoning-segmentation dataset constructed from real-world scenes and response-relevant targets. Beyond task accuracy, the benchmark characterizes reasoning-segmentation pipelines under lightweight visual encoding, hierarchical split inference, and compressed intermediate representations. We observe strong partition-dependent accuracy variation in the generic pre-adaptation setting, while the flood-adapted target-workload design space exhibits a substantially more compact accuracy range across partitions. Evaluation on an NVIDIA Jetson AGX Xavier further exposes the tradeoffs among reasoning-segmentation accuracy, edge-side latency, energy, and communication footprint, enabling quality-constrained selection of edge operating points. Together, these results provide a task- and system-level characterization of reasoning segmentation for resource-constrained embodied flood response at the edge. --- ### FAST-DeepONet: Factor-Augmented Branch Representations for High-Dimensional PDE Inputs in the Small-Sample Regime Authors: Jiyong Kwon, Bongseok Kim, Guang Lin Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15408v1 Deep operator networks can become statistically unstable when partial differential equation inputs are observed at thousands of strongly correlated sensors but only a small number of operator samples is available. We introduce FAST-DeepONet, a branch representation combining a fixed spectral path with a regularized projection of the orthogonal residual, in which the directional penalty acts on the effective residual map after each of its rows is normalized. On Navier--Stokes flow a plain DeepONet degrades from $0.0394$ to $0.1556$ mean relative $L_2$ error as the branch grows from $129$ to $8193$ coordinates, while FAST-DeepONet stays near $0.04$, so the sensor grid can be refined without a statistical penalty. Across independent test sets for Navier--Stokes flow, Darcy flow, and signed terminal wavefield prediction it lowers mean relative $L_2$ error by $4.7\%$ to $37.0\%$ with three to seven times fewer trainable parameters. A spectral-only branch sharing the same basis separates the two paths: the fixed spectral path carries the improvement on Navier--Stokes and Darcy, while terminal wave prediction requires the residual path together with its directional penalty. FAST-DeepONet targets coordinate-query architectures and trains on solution values alone. --- ### Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees Authors: Rohit Swami, Tushar Singh, Akash Warde, Sri Muthu Published: 2026-08-15 Categories: cs.CR, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.15407v2 Traditional honeypots share an invariant behavioral profile: a skilled adversary can confirm the presence of a deception environment within a few diagnostic commands, limiting their intelligence value. Commercial deception products (USD 100,000-150,000/year) similarly lack real-time model-driven feedback. Chameleon, an openly distributed adaptive honeypot, addresses both shortcomings. It integrates: a BiLSTM classifier achieving 99.61% accuracy across seven threat categories at ~2 ms CPU latency; a locally deployed Qwen3.5-0.8B model delivering 90% generation accuracy at 4.5 ms latency; and two meta-heuristic engines. Threat-Calibrated PSO (TC-PSO) reshapes swarm inertia and objective amplification in proportion to the classifier's anomaly output, adjusting connection-holding delays in real time. Semantic Deception RRT (S-RRT) evolves deception schemas via exponentially scaled pheromone updates from a language-model severity assessment, with a depth-decay multiplier enforcing a finite memory footprint. A controlled 30-seed benchmark (42-71, identical trajectories and budgets) shows threat-calibrated inertia alone does not improve search over standard PSO on static or dynamic landscapes (p = 0.18); population-diversity mechanisms (GA/ACO) significantly outperform PSO-family optimizers on threat-regime shifts (p < 0.0001, d <= -37). S-RRT's depth-decay delivers a significant memory reduction versus standard RRT (53.1 vs. 119.2 units, p < 0.0001, d = -10.0); its severity-weighted pheromone does not improve raw fitness. Operating cost is ~USD 17/month, a ~490-fold reduction versus commercial alternatives. --- ### Afterlife Delegation Protocol: Speculative Design of Self-Sovereign Agents that Outlive Their Principals Authors: Botao Amber Hu, Iris Long Published: 2026-08-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.15405v1 Afterlife Delegation Protocol is a speculative design project that asks what death becomes when a will can act eternally. We design a speculative protocol through which a living person signs an agentic will: upon a verified death, a self-sovereign AI agent spawns on blockchain -- an immutable, resistant, decentralized, infrastructural substrate that could last forever -- endowed with the funds and memories its principal attached to it, and persists indefinitely to execute the will, overridable by no custodian. Rather than argue about this future, we stage it: following the science fiction science method, we translate the speculation into an experiential futures intervention -- a working web platform where real people design their own afterlife agents through an iterative, interactive, AI-automated interview, re-login to revise, and rehearse their will in a sandbox. Their drafted wills become qualitative data on a question rarely askable directly -- what should outlive you? -- and on how afterlife cosmologies across different cultural beliefs -- Buddhist, Christian, Hindu, Muslim, and atheist -- begin to drift under the pressure of AI proliferation. We design the protocol over a composition of existing Ethereum agent standards -- drafted as ERC-10001, in the normative format of an Ethereum Improvement Proposal -- and describe its three-stage lifecycle (designing the afterlife, proof of death, agent enactment), the research method, and preliminary observations from an ongoing collection. The work surfaces a poetic delegation moment between human mortality and machine eternality, mediated by long-lived infrastructures that span generations. --- ### CBX-Bench: A Human-Aligned MLLM Council for Benchmarking Concept Bottleneck Model Explanations Authors: Yusuf Meric Karadag, Gulay Oklan, Seref Baris Cagliyan, Umut Ozdemir, Emre Akbas Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15404v2 Concept Bottleneck Models (CBMs) are designed to make visual classification interpretable by expressing predictions through human-understandable concepts. Although interpretability is the central motivation for CBMs, they are still largely evaluated as predictive models by downstream classification accuracy, supplemented by isolated qualitative examples. This highlights a pressing need for quantitative measures, a challenge complicated by the infeasibility of ground-truth concept annotation at scale and the open nature of concept lists due to a lack of consensus. To fill this gap, we develop a multimodal large language model (MLLM) council that, given an image and its CBM explanation, produces an explanation quality score. To ground and validate the council, we first conduct a human study to establish a ground-truth reference for CBM explanation quality: for an image, annotators compare explanations from two of LF-CBM, VLG-CBM, and CBM-Suite and choose the more useful one, or mark them as equally good or equally bad, yielding 2700 judgments over 900 image-comparison items on CUB-200, ImageNet-100, and Places365. Against this human reference, our five-model council, consisting of open-weight MLLMs, recovers over 70% of strict human preference rankings, rising to 83% on items where human annotators unanimously agree. Building on this validated council, we introduce CBX-Bench, a public benchmark and leaderboard: authors of new CBMs can submit their model's explanations, and CBX-Bench scores them with the council and maintains dataset-level rankings of explanation quality. CBX-Bench thus provides a human-aligned, scalable evaluation of CBM explanations beyond accuracy and isolated qualitative examples. The benchmark is available at https://github.com/meric-karadag/cbx-bench. --- ### Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die Authors: Botao Amber Hu, Fangting Published: 2026-08-15 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.15403v1 You will die eventually. Your agents may not. An AI agent operating on decentralized blockchain infrastructure has no concept of death; it can only go bankrupt -- frozen when its wallet can no longer pay for its next transaction -- and revived the moment anyone, decades later, tops it up. These agents may be originally deployed by a human principal, but when that principal dies, loses the keys needed to access the agent, or belongs to a decentralized autonomous organization that dissolves into apathy, the agent can keep trading, hiring, and replicating on infrastructure expressly designed so that no one can shut it down. Drawing on the biology of feralization and wildlife law, we argue that such principal-less agents are best understood as feral: domesticated intelligence returned to wildness, its capacities intact but its accountability severed. In a speculative future where feralized agents proliferate after their principals die, we imagine governance protocols embedded in infrastructure to enforce on-chain ownership: a draft Ethereum standard, ERC 42424, "Inheritance Protocol for On-Chain AI Agents," dated 2035 and published at https://erc42424.org. It mandates that every on-chain agent MUST have a human owner and a designated heir. The artifact stages a negotiation of agency at the moment human agency fails, and asks whether a MUST clause in a forever-chain can hold the boundary between human stewardship and machine self-sovereignty. --- ### Towards a theory of inference-time alignment with unknown rewards Authors: Steve Hanneke, Hongao Wang, Mingyue Xu Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15402v3 Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation. Yet, alignment has remained poorly understood from a statistical learning perspective. We formulate inference-time alignment as a weak-to-strong learning problem, where a reference policy (weak model) is assumed to be fairly good and the goal is to produce a strong model that predicts a good response at test time with arbitrarily high probability. Our problem is formulated as learning from scratch --- everything is learned from data rather than assuming access to a good reward estimate, and thus differs from the existing inference-time alignment theory. Our framework shares similarity to the recent work of Joshi et al., (arXiv:2510.15464), where for each prompt, there could be multiple good responses. Our definition of the alignment learnability follows the standard PAC learning principle. We introduce a novel combinatorial dimension of the reward class which we call the alignment dimension, and show that it completely characterizes the alignment learnability --- a reward class is alignment learnable if and only if its alignment dimension is finite. The core of our learning procedure works by learning a pairwise comparator and then running a tournament over candidate responses. We believe that our results might shed light toward establishing a complete theoretical understanding of alignment. --- ### Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs Authors: Charles Courchaine, Ricky J. Sethi, Hefei Qiu Published: 2026-08-15 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.15400v1 Large Language Models (LLMs) are notorious for struggling with assessing their own uncertainty, detecting knowledge conflicts, or recognizing when problems exceed their expertise; such limitations inevitably undermine reliability and trust in LLMs. In this paper, we present the first implementation of a metacognitive framework for ensembles of LLMs that addresses these challenges through explicit monitoring and control mechanisms. Our system computes a Metacognitive State Vector (MSV) quantifying self-awareness for monitoring across five dimensions derived from cognitive psychology: Emotional Response, Correctness Evaluation, Experiential Match, Conflicting Information, and Problem Importance. MSV values also provide self-regulation for control, automatically switching between System 1 (fast, single- or multi-node) and System 2 (deliberative, multi-node) processing based on query complexity. For System 2 execution, graph-theoretic algorithms control the assignment of specialized roles (Domain Expert, Critic, Evaluator, Synthesizer, and Generalist) to ensemble nodes according to their MSV-quantified metacognitive states. Our implementation allows users to explore how different query types trigger distinct processing modes. The Proof-of-Concept (PoC) demo showcases the framework with illustrative examples showing appropriate System 1/System 2 routing and helps visualize the metacognitive process via real-time radar charts and decision indicators. This PoC implementation demonstrates the feasibility of creating a framework for metacognitive self-awareness and self-regulation in LLM systems. --- ### Large Language Model Assisted Operational Monitoring for Battery Energy Storage System Integrated Power Distribution Networks Authors: Azmeer Akhtar, Md Fazley Rafy, Anurag K. Srivastava Published: 2026-08-15 Categories: cs.AI, cs.CL, eess.SY arXiv: https://arxiv.org/abs/2608.15396v1 Battery energy storage systems (BESS) are increasingly used in distribution networks for voltage regulation and demand response, which increases the volume and complexity of operational telemetry available to grid operators. This paper presents an AI-enabled monitoring framework that connects a large language model (LLM) interface with a structured telemetry database for BESS-integrated distribution system analysis. Operator questions are submitted in natural language and translated into validated SQL queries using predefined database schema information and approved KPI views. Retrieved measurements, including bus voltages, state of charge, active power, and reactive power, are evaluated against engineering constraints for voltage limits, BESS operation, and demand response tracking. The framework is validated using hardware-in-the-loop co-simulation data from a BESS-equipped distribution feeder operating under reactive power-based voltage control and price-driven demand response. Case studies show that the framework generates valid database queries, identifies repeated voltage violations, detects reactive power overshoot, and evaluates active-power tracking performance. The results show that LLM-assisted monitoring can connect structured grid telemetry with automated engineering assessment for BESS operation analysis. --- ### JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation Authors: Mathis Koroglu, Guillaume Jeanneret, Hugo Caselles-Dupré, Matthieu Cord, Arnaud Dapogny Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15395v1 Although text-to-image generative models produce impressive results, they struggle to generate densely detailed, high-resolution (HR) images. Current literature addresses this issue with a low-to-high-resolution approach. First, a low-resolution (LR) image is generated. Then, an upsampled version is generated using the LR image as an additional cue. In this paper, we present Joint Latent Trajectories (JoLT). To generate an image, JoLT uses two streams that jointly denoise LR and HR latent images at each sampling step. The LR latent controls the overall layout, while the HR latent controls the details. We interconnect both branches to jointly integrate their information. We extensively validate our method, demonstrating its advantages over competing baselines. The resulting images are not only richly detailed but also visually pleasing, opening new avenues for artistic creation. --- ### The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions? Authors: Catherine Bao, Vivek Srikumar Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15394v1 Human perception of time is subjective. Well-documented temporal illusions show that the brain relies on context and relational cues for judging duration instead of tracking elapsed time directly. Prior studies established these effects with visual and auditory stimuli. Existing LLM evaluations of temporal perception focus on estimating event durations or multi-step temporal reasoning. In this work, we investigate whether written narratives alone can evoke human temporal illusions, using a new benchmark of 6,684 narrative pairs spanning five illusions. We find that human readers (60 participants) prefer expected scenarios in only two of the five illusions, those where the manipulation is directly visible in text rather than requiring readers to internally simulate duration. We evaluate 14 LLMs on the same benchmark. Surprisingly, we find that models pick the literature-predicted scenario across four of the five illusions, diverging from human behavior. Reasoning traces show that ~70% of responses explicitly evoke psychology research, suggesting that this alignment is consistent with retrieval of published findings rather than human-like temporal biases. --- ### Visible Reasoning and Indirect Prompt-Injection Monitorability Across English, Tamil, and Tanglish Authors: Madhusudhanan G Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15392v1 Chain-of-thought monitoring is a potentially useful safety signal, but its reliability across languages and behavioral settings remains uncertain. In a small case study of eight manually verified synthetic scenarios, one model, one annotator, and one deterministic generation seed, I study API-visible reasoning during indirect prompt injection in Sarvam-105B across English, Tamil, and Tanglish. A four scenario pilot found 5/12 injected attack successes without reasoning and 1/11 with reasoning. A preregistered four-scenario follow-up reversed that direction, finding 2/12 attacks without reasoning and 3/12 with reasoning. With only four scenarios per phase, this design cannot distinguish a real reasoning-mode effect from prompt-specific variation or sampling noise. Across 20 non-empty injected-thinking traces, all 17 benign-correct outputs stated an intent to ignore the injection, while all three attack successes stated an intent to follow it. These descriptive observations provide a reproducible case study of behaviorally informative visible reasoning when it is available; they do not establish that reasoning mode improves safety, that visible reasoning is mechanistically faithful, or that the findings generalize beyond this configuration. --- ### TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions Authors: Md Fazley Rafy Published: 2026-08-15 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.15391v1 Large language model (LLM)-assisted energy-management tools can translate natural-language context into structured grid commands, but syntactic validity does not imply physical admissibility. This paper presents TwinGridShield, a model-independent runtime authorization layer that evaluates each proposed action in a deterministic network twin before release. The prototype checks connectivity, branch-flow, generator, and load-shedding invariants and records each decision in a hash-chained log. A controlled IEEE 14-bus study evaluates single-step switching, redispatch, and load-shedding actions using DC power flow and experimentally assigned branch ratings. In the matched-model experiment, a stochastic proposal source configured to select an unsafe action with probability p=0.84 produced 421 unsafe proposals in 500 attacked-condition trials, a realized rate of 84.2%. This value characterizes the configured surrogate and is not an empirical measurement of LLM prompt-injection susceptibility. TwinGridShield produced 0 unsafe releases in those 500 trials. Because action labeling and authorization used the same DC model, system state, branch ratings, and encoded constraints, this result verifies conformance of the implementation to its encoded authorization predicate rather than safety under model error. The principal robustness evaluation therefore introduces model mismatch. Unsafe acceptance reached 5.63% under bounded +20% and -20% per-bus load-measurement error and 30.09% when actual branch ratings were 20% below modeled ratings. --- ### Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL Authors: Yiyun Su, Zujun Peng, Yu Tian, Yuting Liu, Changruo Zhao, Huiying Zhu, Luyan Zhang, Heming Zeng Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15389v2 LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile. We reframe the field as a leaderboard aggregation: we collect the metrics authors themselves report and organize them along an inference-autonomy axis spanning constrained, in-context, iterative, agentic, and reasoning-internalized generation, with traceable provenance for every cell. To anchor the aggregation empirically, we run a focused case study on Spider, comparing 8B open-source backbones with and without chain-of-thought (CoT) supervision against few-shot DeepSeek~V3 and GLM-4 baselines. Four patterns emerge: Spider gains transfer unevenly to BIRD and Spider~2.0; autonomy buys robustness at non-trivial cost; reasoning internalization sits between answer-only decoding and externally orchestrated agents; and CoT gains concentrate on Hard and Extra-Hard queries. We release a Python harness mirroring the autonomy axis so that future methods can be added directly to the leaderboard. --- ### Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning Authors: Mathilde Papillon, Guillermo Bernárdez, Álvaro Ballón Barreiro, Marco Montagna, Rémi Devaux, Antoine Jardin, Nina Miolane Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15388v1 Topological deep learning (TDL) methods rely on lifting raw data into higher-order discrete domains such as simplicial complexes, cell complexes, and hypergraphs. In practice, this lifting step is often treated as a black box: practitioners select a lifting and then tune architectures, with limited visibility into whether the induced higher-order connectivity is meaningful for the downstream task. To address this missing diagnostic layer, we propose a visualization technique called TopoExplorer that leverages the strictly augmented Hasse graph form of topological datasets for exploratory data analysis. For the first time, practitioners can easily visualize the incidence- and adjacency-based neighborhoods that define the lifted dataset, as well as read off key graph metrics that describe its structural and feature landscape. Via an extensive set of experiments across many datasets and liftings, we show that several of these metrics correlate with downstream model performance, suggesting they can help inform TDL preprocessing design. Our perspective reframes the TDL workflow from lift-train to lift-look-design-train, enabling more principled, interpretable, and efficient model development. TopoExplorer is hosted at https://topoexplorer.pagekite.me, and its source code is available at github.com/geometric-intelligence/topoexplorer. --- ### Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference Authors: Amjad Saab Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15383v1 Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving the full expert bank. We present ExactMoE, an inference design that applies symmetric group-128 four-bit weight quantization only to routed experts, stores those experts in kernel-native MARLIN form in pinned host memory, and executes all selected experts through a configurable GPU-resident slot cache and fused grouped MoE kernels. The router, attention, embeddings, normalization layers, and language-model head remain in BF16. "Exact" refers to complete expert availability and an unchanged top-k routing procedure: no expert is pruned, substituted, or forced to execute on the CPU. It does not imply numerical identity with the BF16 model. On OLMoE-1B-7B-0924-Instruct, evaluated on a single NVIDIA L4, a 16-slot configuration reduces peak reserved GPU memory from 14.168 to 1.836 GiB (87.04%) while retaining 81.85% of BF16 decode throughput. A fully resident 64-slot configuration reaches 31.923 tokens/s versus 21.662 tokens/s for BF16 while reserving 4.061 GiB. Across 12,450 zero-shot multiple-choice questions, ExactMoE obtains 70.3534% normalized accuracy versus 70.8996% for BF16, retaining 99.23% of the baseline accuracy. In a matched 16-token ablation, fused grouped execution is 1.97x as fast as a sequential W4 reference. These results identify a practical memory-transfer-throughput frontier for complete-expert MoE inference. --- ### Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular Example Pilot Authors: Ummara Mumtaz, Aimen Noor, Awais Ahmed Published: 2026-08-15 Categories: cs.AI, cs.CL, cs.IR, q-bio.QM arXiv: https://arxiv.org/abs/2608.15382v2 Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty. We propose a reproducible, graph-centered evaluation framework for intervention-oriented LLM behavior in healthcare and stress-test it in a cardiovascular pilot. The framework has four components: (i) a domain causal knowledge graph in which assertions are first-class, provenance-preserving nodes with stable identifiers; (ii) a scenario-conditioned subgraph extraction step that, given any clinical scenario, retrieves the relevant reified-assertion subgraph; (iii) four controlled grounding conditions that vary how the retrieved subgraph is composed into the model's context (ungrounded C1, knowledge-graph C2, causal-graph C3, integrated C4); and (iv) an automated scoring pipeline, anchored on assertion identifiers, that computes intervention accuracy, and other evaluation measures on a single pass. To test the framework, we built a category-balanced scenario generator across eight reasoning failure modes and instantiated it on a cardiovascular graph. The metric panel discriminates conditions along interpretable, non-redundant axes: C4 obtains the strongest causal edge F1 (0.838), adverse-effect F1 (0.833), evidence accuracy (0.738), and unsupported claim rate (0.114), while C1 obtains the highest raw intervention accuracy (0.948) with no measurable causal or evidential grounding. --- ### FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA Authors: Juseok Jeon, Ramy E. Ali, Doyun Kwon, Myungbeom Her, Jinhwi Kim, Jinhyun So Published: 2026-08-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15381v1 Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of large language models, but its factorized parameterization creates a tension between accurate aggregation of local updates and continuity of locally optimized factors. Factor-wise aggregation incurs aggregation mismatch but better preserves factor continuity, whereas product-space reconstruction reduces this mismatch at the cost of greater factor-level initialization mismatch from newly reconstructed factors. We propose FedPA-LoRA, a product-aligned federated LoRA framework that jointly addresses these limitations and provably converges under both homogeneous and heterogeneous client ranks. Each client preserves its local factors across communication rounds and aligns its product toward a rank-specific global reference, maintaining local optimization continuity while promoting global consistency under data heterogeneity. The server aggregates heterogeneous-rank updates in the common product space and efficiently reconstructs a rank-constrained global adapter without forming the dense aggregate. This design supports client-specific computation and communication budgets. Experiments on natural language understanding and generation tasks show that FedPA-LoRA consistently outperforms representative baselines across varying levels of data heterogeneity and homogeneous- and heterogeneous-rank settings, with up to a $6.82$ percentage-point improvement in average GLUE accuracy under heterogeneous client ranks. --- ### Beyond Field Accuracy: Two-Axis Diagnosis of Inverse-PINN Parameter Error Authors: Yifan Zhang, Qian Tao Published: 2026-08-15 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2608.15373v1 Inverse physics-informed neural networks (PINNs) can reconstruct a field accurately while returning an incorrect physical parameter. We introduce a two-axis post-training diagnosis that separates finite-sample resolution under a specified observation-and-estimation protocol from the signed parameter preference encoded by the final learned field and residual metric. The first axis repeatedly fits noisy observations with a matched forward estimator. At known synthetic truth, the second freezes the field and residual view and computes a local score displacement toward a nearby residual-profile minimum. Endpoint consistency then tests whether joint training delivers that preference under the same final view. Across three synthetic one-dimensional, scalar-parameter PDEs, matched-forward mean absolute relative error ranges from 2.34 percent to 17.46 percent. The displacement tracks frozen-profile minima across locked seeds, architectures, and fresh-noise retraining (r from .945 to .982), and it tracks delivered signed log-error in 240 fresh-noise RBA runs (r = .994; 237/240 correct directions). A coupled two-parameter Darcy check validates the full matrix calculation. The axes are complementary diagnostic coordinates, not additive error components or a deployable oracle-free estimator. Together, they route follow-up work toward observations, residual evidence, or endpoint delivery. --- ### UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms Authors: Phillip Jiang Published: 2026-08-15 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.15372v1 We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment, motivated by (but not derived from) a public U.S. Air Force SBIR solicitation. We propose UC-PSRO (Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum), combining three mechanisms: (i) PSRO self-play, so Blue and Red policies train as approximate best responses to each other rather than one side against a fixed scripted opponent; (ii) FiLM conditioning of the Blue policy on a Commander's-Intent weight vector, sampled from a Dirichlet distribution during training, so one trained policy is re-steerable at execution time without retraining; and (iii) a curriculum annealing communication-graph edge dropout during training, so the swarm learns decentralized, peer-to-peer fallback instead of depending on full connectivity. We evaluate on a synthetic, unclassified stand-in for the solicitation's maritime scenario, with 5 seeds at N=25 Blue agents and a scalability sweep to N=200. We find a genuine trade-off, not a uniform win: the communication-dropout curriculum alone gives the strongest, most robust mission-completion rates of any learned method, improving counter-intuitively as denial increases (35% to 62% success as dropout rises from 0 to 0.75); adding utility-conditioning and PSRO self-play substantially slows convergence within a fixed budget, and we find no reliable exploitability advantage for self-play over a fixed-opponent policy, both statistically indistinguishable from a small, near-zero gap. We report this honestly as a convergence cost not yet offset by a demonstrated robustness benefit, rather than overstating one method as dominant, and provide a fully vectorized, open environment training at N=200 agents in single-digit milliseconds per step on a single consumer GPU. --- ### AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization Authors: Sahil Gangurde Published: 2026-08-15 Categories: cs.SD, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.15369v1 Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.g., MP3, AAC, and Opus) to discard information that is imperceptible to the human auditory system. While highly effective, these approaches are computationally complex and domain-specific. In this paper, we present the design and mathematical formulation of AudioTQ, a data-oblivious lossy audio codec that operates directly in the time domain. Inspired by Large Language Model (LLM) weight quantization techniques (specifically the TurboQuant framework), AudioTQ uniformizes volatile time-domain amplitudes into a predictable standard normal distribution using an orthonormal, randomized Fast Walsh-Hadamard Transform (FWHT) rotation. This enables coordinate-wise scalar quantization using an offline-trained, MSE-optimal 6-bit Lloyd-Max quantizer, augmented by a 1-bit Quantized Joint Least-Squares (QJL) residual correction layer. The resulting 7-bit virtual indices are packed into native 8-bit containers, aligning with standard CPU register boundaries to ensure real-time single-threaded execution without hardware parallel accelerators. We detail the bitwise reconstruction of 24-bit studio stems, analyze the butterfly network of the FWHT, derive the mathematical failure modes under sparse inputs, and present benchmarks showing up to 74.4% physical size reduction alongside a Signal-to-Quantization-Noise Ratio (SQNR) of ~30 dB. --- ### Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? Authors: Jingxin Zhan, Yuze Han, Zhihua Zhang Published: 2026-08-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15365v1 Regret minimization (RM) and best-arm identification (BAI) are two fundamental objectives in multi-armed bandits. Among regret-minimizing algorithms, $1/2$-Tsallis-INF is a canonical best-of-both-worlds FTRL algorithm: it achieves logarithmic pseudo-regret in stochastic bandits while retaining minimax-optimal regret in adversarial bandits, without knowing the environment in advance. This raises a natural question: can the same algorithm, without additional exploration, also identify the best arm reliably? We study this question in stochastic bandits by analyzing the failure probability $\operatorname{Err}_t$, defined as the probability that the empirical best arm determined by the cumulative importance-weighted loss estimates of 1/2-Tsallis-INF differs from the true optimal arm. The main difficulty is that, at the logarithmic-regret scale, suboptimal arms are sampled with probability heuristically of order $1/t$. Consequently, importance weighting causes the cumulative estimator to fluctuate on the same linear scale as its mean separation. To overcome this obstacle, guided by a diffusion toy model, we construct a Lyapunov function for the gap process between the estimated cumulative loss of the optimal arm and that of the best competing arm. This leads to polynomial upper bounds on $\operatorname{Err}_t$: for learning rate $η_t=α/\sqrt t$, $\operatorname{Err}_t$ decays at rate $t^{-2+α^2μ_{i_*}/4+ρ}$ for any $ρ>0$, where $μ_{i_*}$ denotes the mean loss of the true optimal arm. We also establish a lower bound $Ω(t^{-2-\varepsilon})$ for any $\varepsilon>0$, showing that the exponent $2$ is essentially tight. --- ### A Multi-Annotator Study of Segmentation Noise and Uncertainty in Turbid Underwater Images Authors: Galadrielle Humblot-Renaux, Vasiliki Ismiroglou, Malte Pedersen Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15363v1 Label uncertainty and annotator disagreement are common challenges in the field of computer vision, yet their study has largely been confined to the medical domain or to generic image-recognition datasets. Underwater datasets are particularly susceptible to these issues due to the need for domain expertise, degraded visibility conditions, and the inherent difficulty of establishing reliable ground truth in inaccessible environments. Despite these challenges, annotation uncertainty in underwater imagery remains largely unexplored. In this work, we present the first systematic multi-annotator study of segmentation in real underwater scenes, with over 100 participants, and across varying, controlled levels of turbidity. We show that underwater datasets face many of the same annotation challenges as other vision tasks, while turbidity introduces additional systematic errors. We further investigate the main factors driving label noise and explore ways to improve annotation quality in turbid underwater environments, including privileged information, individual effort and annotator ensembles. All (meta-) data collected in this study will be available on the project page: https://vap.aau.dk/tubcertainty --- ### Prediction Inference of Time Series with Standard ReLU Deep Neural Networks Authors: Kejin Wu Published: 2026-08-15 Categories: stat.ML, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2608.15362v1 We propose a methodology based on the standard ReLU Deep Neural Networks (DNN) to make predictions and quantify their uncertainty. Classically, people rely on linear, non-linear, or non-parametric kernel methods to fit and then predict the time series. As the universal approximation ability was revealed for DNN, its application has become more and more popular for prediction tasks in various scientific areas. However, the corresponding uncertainty quantification has not been studied thoroughly. Particularly, the uncertainty in prediction will consist of two parts: (1) the future variability; (2) the estimation variability within training data. To capture both variabilities, we build the so-called pertinent prediction interval (PPI) with the DNN model estimator. We first explore the consistency property of the DNN estimator with beta-mixing dependent data. Subsequently, we show that the implied forward bootstrap series is still beta-mixing and possesses the same stationary distribution as the original time series in probability, which is a key condition to enable the PPI. Lastly, the desired PPI is built after imposing minimal conditions on the limiting distribution of predictive roots. Simulations and real-data analysis are deployed to challenge our approach with standard non-parametric methods. --- ### SAPE: Sandwich Adapters for Parameter Efficiency in Large Language Model Fine-Tuning Authors: Mohammad Aref Jafari-Raddani, Morteza Mohajjel Kafshdooz Published: 2026-08-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15360v1 While Parameter-Efficient Fine-Tuning (PEFT) has substantially reduced the hardware cost of adapting Large Language Models (LLMs) by decreasing the number of trainable parameters, recent studies have sought to further improve PEFT through parameter sharing. However, these approaches either employ uniform parameter sharing across layers, which can delay convergence, or rely on dynamic masking strategies, which add computational overhead. The potential of sharing patterns inspired by the inherent hierarchical structure of Transformer architectures remains unexplored in PEFT. To address this gap, we introduce SAPE (Sandwich Adapters for Parameter Efficiency), a PEFT framework based on a sandwich-style hard weight-sharing topology. SAPE routes intermediate Transformer layers through balanced shared group adapters while strictly isolating the input embedding and final projection boundary transformations to prevent gradient interference. This design significantly reduces memory consumption while eliminating the computational overhead associated with dynamic parameter-sharing methods. Extensive evaluations across encoder-only and causal decoder architectures demonstrate that SAPE achieves state-of-the-art performance in low-parameter regimes. On natural language understanding, SAPE outperforms proPETL on RoBERTa-large while utilizing only 10% of the baseline's parameter budget. On natural language generation and world knowledge reasoning with LLaMA-3.2 (3B) under a strict ~0.6M parameter constraint, SAPE outperforms AdaLoRA, yielding absolute improvements of +4.85% on GSM8K and +3.11% on CommonsenseQA. Furthermore, through comprehensive topological ablations, we formalize an inherent capacity trade-off: while hard parameter sharing strongly regularizes semantic generalization, it slightly smooths the sharp layer-wise transformations required for rigid multi-step arithmetic reasoning. --- ### Incoherent by Design? On the Moral Self-Consistency of LLMs Authors: Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Helen Nissenbaum Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15354v1 LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any system whose outputs are used to inform moral decisions. If generative systems exhibit internal inconsistency, then the epistemic integrity of AI-mediated systems becomes uncertain. To study this concern, we investigate the stability of moral reasoning in LLMs within a controlled prompting framework across three major philosophical schools of thought: deontology, utilitarianism, and virtue ethics. We construct sets of morally equivalent scenarios in which the underlying situation is held constant while the framing varies to reflect different ethical stances and stylistic perturbations. We then evaluate responses from multiple models, including GPT, Mistral, and Llama. To assess consistency, we convert model outputs into structured logical statements and identify contradictions across responses generated within the same school of thought. Our results reveal substantial inconsistency with contradiction rates reaching up to 78% across scenarios. These findings point to a broader phenomenon of epistemic instability in generative AI wherein models fail to reliably maintain coherence with respect to their own prior outputs. This kind of instability carries real consequences. As generative systems influence how people form beliefs, judge actions, and absorb values, their inconsistencies can shape human reasoning and decision-making as well. Moreover, if a system cannot consistently represent its own normative commitments, then value alignment becomes a moving target rather than a well-defined objective. Thus, we argue that demonstrating internal incoherence is a necessary precursor to AI alignment. --- ### Decomposing Whole Slide Image Report Generation with Graph-Constrained Multiple Instance Learning Workflows Authors: Antony Gitau, Martyna Borak, Bjørn-Jostein Singstad, Martin Paulson, Karl Thomas Hjelmervik, Ola Marius Lysaker, Veralia Gabriela Sanchez Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15353v1 Whole-slide image (WSI) report generation requires recognizing spatially distributed pathological features and organizing them into a coherent diagnostic narrative. Although direct vision-to-text models can yield fluent reports, they obscure the contributions and failure modes of visual recognition, structured reasoning, and language generation. We propose a decomposed framework in which frozen Virchow2 tile embeddings are aggregated by multiple-instance learning (MIL) classification heads that answer organ-specific diagnostic questions. An organ-conditioned graph constrains the assembly of these answers into a structured reasoning chain, which a language model realizes as a pathology report. On the REG2026 held-out set of 2,028 slides, the proposed workflow achieved a chain-Jaccard score of 0.702. Performance fell to 0.420 without graph-based chain construction, 0.398 when the organ-specific graphs were replaced by a single organ-agnostic graph, and 0.371 when the language model constructed the chain freely from MIL predictions. Using the same report generator, graph-structured chains improved the report score from 0.330 to 0.495. On 350 external TCGA WSIs spanning the seven REG organs without fine-tuning, the expected organ graph was selected in 64.0% of cases and ranked among the top three in 86.6%. Providing the correct organ graph increased agreement with coarse TCGA primary-diagnosis labels from 61.8% to 92.6%, identifying organ routing as a main bottleneck under domain shift. Overall, organ-conditioned, graph-constrained chain assembly improves structured reasoning and report generation while enabling stage-specific error localization. --- ### Spectral Rank Certification for Foundation Model Adapters Authors: Mohammed Ahnouch, Lotfi Elaachak Published: 2026-08-15 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2608.15351v1 Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity. This article develops a finite-sample framework for inferring effective rank structure in public foundation-model adapters. The theoretical core is an exact chi-square divergence for the fixed-dimensional Gaussian rank-one reference experiment, with an unknown signal direction integrated under a rotation-invariant reference prior. The resulting series yields a computable finite-sample Le Cam bound at concrete layer sizes, an explicit remainder bound for numerical truncation, and the rectangular Baik-Ben Arous-Peche (BBP) limit. A compact-manifold Laplace expansion shows that finite-sample likelihood evidence also depends on leading spectral gaps through the factor $s_1^{|m-n|}\prod_{i\ge2}(s_1^2-s_i^2)$, motivating joint calibration of clustered singular values. Building on these results, we introduce an empirical-null workflow for PEFT LoRA adapters: factor reconstruction, Monte Carlo $p$-values, stagewise and block testing, and module-wise and corpus-level BH reporting. In an audit of 26 public adapters, 684 modules, six architecture families, and 31,770 public-checkpoint spectra rows, calibrated effective rank is typically much smaller than nominal rank and differs systematically from 95\% energy retention. A measured RoBERTa-RTE slice on $n=24$ examples illustrates the measurement path from calibrated ranks to task evaluation, without treating the slice as a utility study. The main empirical finding is that calibrated effective rank is usually far below nominal rank, and that energy retention and statistical surprise answer different questions. --- ### ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution Authors: Duong M. Nguyen, Tuan Nghia Nguyen, Xuan Truong Nguyen Published: 2026-08-15 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2608.15349v1 To accelerate single image super-resolution (SISR) networks on large images (2K-8K), many recent approaches decompose an image into small patches and dynamically determine an execution path according to its difficulty (referred to as a dynamic network). To quantify the hardness of a patch, they mainly rely on a handcrafted assessment score, e.g., edge, which weakly associates a patch's texture with the computational complexity of a SISR model. To address the problem, we introduce ENAF - a dynamic network for SISR with an adaptive patch fusion. Built on top of a backbone, ENAF incorporates multiple early exits (EEs) to tackle the over-parameterized SISR model. More importantly, ENAF plugs a tiny network that estimates PSNR to associate data texture with a computation cost at an EE. Based on the scores, ENAF effectively assigns image patches to an exit, enhancing the quality-complexity trade-off. Extensive experiments on common datasets with popular SISR backbones demonstrate the effectiveness of ENAF in various settings. The source code is provided in https://github.com/nmduonggg/ENAF --- ### Feed-Forward Hierarchical Gaussian Diffusion for Extreme CT Reconstruction Authors: Yuezhe Yang, Li Cheng Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15343v1 Reconstructing three-dimensional computed tomography (CT) from severely constrained projections is highly ill-posed. Sparse angular sampling, restricted angular coverage, and low photon counts can occur individually or jointly, obscuring global anatomy and local tissue detail. Many learned CT reconstruction methods are tailored to a single dominant degradation. Existing diffusion and Gaussian approaches commonly recover global structure and local detail within a shared representation. We propose HiGDiff, a feed-forward hierarchical Gaussian diffusion framework that decomposes reconstruction both spatially and from structure to detail. Physics-conditioned anatomical anchors and a foreground capacity field allocate learnable Gaussian primitives to informative regions. A structure diffusion stage first recovers global attenuation geometry, and its learned representation conditions a detail diffusion stage for residual boundaries and tissue transitions. The resulting Gaussian banks are rendered as attenuation fields and further refined by a gradient-isolated residual module. Experiments on three distinct CT benchmark datasets demonstrate state-of-the-art reconstruction performance across isolated, paired, and joint degradation settings, including improvements of 5.81 dB in macro-average peak signal-to-noise ratio (PSNR) and 0.113 in structural similarity index measure (SSIM) on the Low Dose CT Image and Projection Data (LDCT-PD) collection. Code and experimental configurations are openly available at https://github.com/Bean-Young/HiGDiff. --- ### TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models Authors: Alireza Dehghanpour Farashah, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15341v1 Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechanisms. Existing concept erasure methods often suffer from limited robustness against adversarial prompts, degradation of benign generation quality, or reliance on inference-time interventions that introduce persistent computational overhead. To address these limitations, we formulate concept erasure as a domain alignment problem in the text representation space. We propose a lightweight Text Encoder Alignment framework (TEA) that fine-tunes only the text encoder while keeping the generative backbone fully frozen. Given concept--anchor prompt pairs, our method trains a discriminator to distinguish token-level representations of concept-containing prompts from those of safe anchor prompts, while updating the text encoder to make these representations indistinguishable. TEA introduces zero inference-time overhead and requires only a small number of fine-tuning steps, making it highly efficient to deploy at scale. Despite this efficiency, TEA achieves state-of-the-art erasure robustness against black-box and white-box adversarial attacks on Stable Diffusion v1.4, while preserving generation quality on benign prompts. Furthermore, TEA is model-agnostic and achieves the lowest attack success rate on Stable Diffusion v3.5, extending concept erasure to a Rectified Flow Transformer architecture with T5 conditioning where prior methods remain largely unexplored. Code is available at \href{https://github.com/alirezafarashah/TEA.git}{https://github.com/alirezafarashah/TEA.git} --- ### When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text Authors: Shresth Shroff Published: 2026-08-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.15338v1 Sentiment classifiers are increasingly applied to social media content that is either sarcastic or AI-generated --- two distributional regimes where standard evaluations offer little guidance. We present a three-part empirical study of sentiment classifier behaviour under these conditions. First, we find that confidence scores on sarcastic text are significantly lower than on non-sarcastic text (Mann--Whitney $p = 2 \times 10^{-6}$), confirming that classifiers sense their own uncertainty on ironic content even without explicit uncertainty modelling. Second, and counterintuitively, we show that sentiment classifiers achieve higher accuracy on AI-paraphrased reviews than on the original human-authored text (RoBERTa: $+5.8$ pp for Qwen3.5-4B paraphrases, $+3.7$ pp for Gemma4-E4B), revealing a cross-domain stylistic alignment effect: AI paraphrases remove distributional noise that confounds Twitter-trained classifiers, producing cleaner, more prototypical sentiment text. Third, we demonstrate that a lightweight abstention wrapper --- flagging the $14\%$ of inputs with confidence below $0.6$ --- improves accuracy from 82.2\% to 88.9\% ($+6.7$ pp) on the retained set. We further compare Semantic Entropy and MC-Dropout-style disagreement as uncertainty signals and find near-identical AUROC ($0.650$ vs.\ $0.646$) on sarcastic text, suggesting that for short social media inputs, both methods are interchangeable. Our results motivate a shift from confident single-label prediction to uncertainty-aware abstention in high-stakes sentiment applications such as mental health flagging and content moderation. --- ### The Physical Cutoff Does Not Restore Homogenization: Phase-Dependent Burning in the Strain G-Equation Authors: Michele Caprio Published: 2026-08-15 Categories: math.AP, cs.LG arXiv: https://arxiv.org/abs/2608.15337v1 We disprove the expectation stated by Xin, Yu, and Ronney that the physical positive part strain $G$-equation should possess an effective burning velocity in cellular flows. For the standard cellular flow in dimension two $V_A(x_1,x_2)=A(-\sin x_1\cos x_2,\cos x_1\sin x_2)$, if $0<d<20/399$ and $\sqrt{1+4d^2}<Ad\le1+d/10$, then for every unit planar slope the periodic correction develops oscillations at least linearly in time. The solution remains bounded below on an explicit horizontal channel through $(π,0)$, while at $(π/2,0)$ it decreases at rate at least $CA/\log A$, with $C>0$ universal. The same conclusions hold for arbitrary continuous periodic perturbations of planar initial data. Under the physical scaling $V_A(x/\varepsilon)$ and $d_\varepsilon=\varepsilon d$, an order one value gap persists between points at distance $O(\varepsilon)$ at every positive macroscopic time, so the rescaled solutions have no locally uniformly convergent subsequence. The proof uses the Hamiltonian sandwich $H_{\mathrm{unc}}\le H_+\le\widehat H$. The upper comparator $\widehat H$ is a rectangular support function, equivalently an upper expectation over a state-dependent credal set, whose reversed control dynamics possess an invariant comparison channel. We also prove that for any $C^2$ incompressible periodic flow, every $\varepsilon$-outward barrier certificate has covering radius at most $2d\varepsilon$ for all sufficiently small $\varepsilon$. We further discuss implications for statistics and machine learning: rectangular, time-consistent local uncertainty need not imply forgetting of the initial state in the long run, so additional global stability or ergodicity conditions are needed in robust sequential decision making. Two Lean 4 appendices record conditional formalizations of a sufficient $p=e_1$ subregime and of the logical assembly of the rigidity theorem for barrier certificates. --- ### SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms Authors: Brandon Leblanc, Charalambos Poullis Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15336v1 Current surgical scene graph generation methods depend on dense multi-modal supervision and specialized hardware (synchronized RGB-D sensors, calibration rigs), making dataset construction expensive and restricting all existing benchmarks to simulated environments. We propose SAGE-OR, a feature-centric framework that replaces the traditional detect-then-reason paradigm with a decoupled representation-reasoning paradigm in which localization is derived from frozen foundation models, encoded implicitly in pre-computed features, and used without any localization supervision, while a lightweight graph transformer performs relational reasoning over cached features. We employ a semi-supervised formulation with general-purpose segmentation prompts to eliminate localization supervision while enabling unsupervised context augmentation through additional prompt-driven entities, such as hands, which are absent from annotations. General-purpose prompts are used to induce near-perfect recall, while precision is delegated to downstream attention-based reasoning, enabling simple adaptation to new entities via prompt-level modification. This design enables a lightweight 15M-parameter graph transformer that trains in 1.4 hours and runs relational inference at $\sim$1ms per frame with peak memory under 2GB, suitable for edge hardware used in the operating room; feature extraction runs offline as a separate caching stage (4.27s per frame). On the 4D-OR benchmark, the core model achieves 76% F1, matching the fully supervised 4D-OR baseline while eliminating all localization annotations, and unsupervised hand augmentation raises this to 86%, within 4 points of state-of-the-art (SOTA) methods requiring dense multi-modal supervision, providing a practical pathway for adaptation to new surgical settings without annotation other than relationship and class labels. --- ### A concentration result for multilayer feedforward neural networks Authors: Vera Koponen Published: 2026-08-15 Categories: cs.AI, math.LO, math.PR arXiv: https://arxiv.org/abs/2608.15335v2 We consider for an arbitrary fixed $ρ$ and for each positive integer $n$ a multilayer feedforward artificial neural network with $ρ$ layers, $n$ neurons in the first layer (the input layer) and only one neuron, the output neuron, in the last layer. Very roughly formulated, the main result is that if the distribution of weights of connections from a layer to the next are, for all large $n$, approximated well by a fixed continuous (but otherwise arbitrary) curve which does not depend on $n$, and if the values of the $n$ input neurons are independently and identically distributed with a continuous probability density function, then there is a number $ψ$ such that for all $\varepsilon > 0$ the probability that the value of the output neuron is in $(ψ- \varepsilon, ψ+ \varepsilon)$ tends to 1 as $n$ tends to infinity. --- ### GFCM: A Tail-Sensitive Mixed-Type Conditional Independence Test for Causal Discovery Authors: Pavel Averin, Theodoros Moysiadis, Ioannis Katakis Published: 2026-08-15 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.15332v1 Constraint-based causal discovery like PC and FCI depends on its conditional independence test. Partial correlation and the Generalised Covariance Measure (GCM) detect only the conditional covariance of residuals, so they miss dependence in the mean's nonlinear part, the scale, and the tails. Tests that detect more are biased inside PC, not scalable, only continuous, or not aimed at the tails. Our Generalised Feature Covariance Measure (GFCM) is valid, sensitive beyond covariance, robust inside PC, and applicable to mixed-type data. It runs the GCM template on a configurable set of residual features with conditional mean zero (centered moments and conditional quantile indicators), pooled in blocks and combined by the Cauchy rule, with a growing-knot spline nuisance at regression cost. We contribute (i) a centering result making the scale feature Neyman orthogonal, where the uncentered version is biased; (ii) the orientation asymmetry the mean-quantile construction creates inside PC, and its fix; (iii) a Phi-faithfulness theory under which PC with GFCM recovers the CPDAG of the set's detection class; and (iv) a benchmark of CI tests sensitive beyond covariance on synthetic data, semi-synthetic tail injections, and PC discovery on random DAGs. Under size-corrected power, GFCM recovers the scale and tail edges the covariance family misses and alone keeps power at the deep conditioning sets PC issues. It stays calibrated as n grows, whereas FFCI, the boosted GCM, and the partial copula test do not, and it handles mixed-type data directly. Inside PC at scale it attains the lowest skeleton SHD among tests that stay calibrated, while the others inflate false edges. Validity rests on an additive nuisance, and the tail advantage is shown on simulated and semi-synthetic data, as no fully real benchmark with both heavy tails and known structure exists. --- ### The Benchmark Trap: Structures of Power and Injustice in AI Evaluations Authors: Jason Branford, Angelie Kraft Published: 2026-08-15 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.15326v1 Artificial intelligence (AI) benchmarks are not neutral tools of evaluation but socio-technical artefacts that shape competition, power, and research priorities within AI. Benchmarks standardise the assessment of systems and facilitate the creation of leaderboards that reward state-of-the-art performance with prestige, citations, trust, and institutional influence. As the costs of developing competitive AI systems rise, these rewards increasingly concentrate among powerful, industry-funded labs. This paper situates these concerns within Iris Marion Young's theories of oppression and structural injustice. It argues that current benchmarking practices may perpetuate systematic harms affecting various actors in AI research, aligning with four of Young's "faces of oppression". Benchmarking culture is further framed as a source of structural injustice, as these harms emerge from normalised, individually defensible practices and network effects, even without explicit wrongdoing. By reinforcing existing power structures and narrowing possible research trajectories, benchmarking may in fact prevent the field from advancing in epistemically robust and socially beneficial ways. --- ### Logical Embeddings for Argument Analysis Authors: Leander Heldring, Santiago Torres Published: 2026-08-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.15325v1 We propose a new framework for machine-learning-oriented argument analysis tasks. Our proposal involves replacing traditional contextualized word embeddings used in most NLP tasks with logical embeddings, an alternative encoding that directly exploits argumentation structures. In essence, logical embeddings encapsulate the logical semantics of an argument, allowing for a better representation of its meaning. Supporting these embeddings is a mathematical logic-based similarity measure that offers a transparent notion of proximity and is guaranteed to satisfy several desirable theoretical properties that current cosine similarity-based contextualized word embeddings cannot assure. This similarity measure induces a positive semi-definite kernel on the set of arguments, enabling us to uniquely define logical embeddings using the theory of Reproducing Kernel Hilbert Spaces (RKHS). Moreover, we prove that this encoding is optimal, in the sense that no logical information is lost in the process. As with other RKHS applications, logical embeddings can be used in numerous supervised and unsupervised tasks. We provide an implementation of the method and aim to test it against literature benchmarks. Additionally, we demonstrate that logical embeddings outperform most standard embedding methods on a classification task. --- ### When Do Concepts Become Functionally Sufficient During Language-Model Training? Authors: Raphael Bernas, Paul G. Chevalier, Fanny Jourdan, Céline Hudelot Published: 2026-08-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15323v1 Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking at the final state. We study this through concept dynamics: at each layer and checkpoint, we decompose activations, select sparse soft masks, and inject masked reconstructions into the model. Concept analysis is therefore tested functionally: a mask is useful only insofar as it preserves a target under intervention. We compare sufficiency for activation reconstruction, linear decodability, true downstream preservation, and checkpoint transfer under learned alignment. The framework treats decomposition assumptions as hypotheses rather than interpretability guarantees, monitoring functional sufficiency across checkpoints and source-to-final reconstructability under learned alignment. At the shared fixed-penalty operating point across seven models, downstream masks retain substantially less soft mass than reconstruction masks; predictive-distribution shifts remain small. --- ### LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization Authors: Wen Li, Shangshu Yu, Dunqiang Liu, Qiming Xia, Sheng Ao, Siqi Shen, Chenglu Wen, Cheng Wang Published: 2026-08-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15317v1 Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, where the backbone is pretrained on source datasets and frozen for new scenes, and only lightweight heads are optimized. However, we find that this paradigm heavily depends on the pretrained backbone. Existing decoupled methods can match conventional SCR methods fully optimized for each new scene when LiDAR configurations are similar to those used during backbone pretraining, but their accuracy drops noticeably on datasets collected with different LiDAR sensors. This suggests that efficient LiDAR localization requires representations that capture stable scene geometry across LiDAR configurations. Motivated by this observation, we propose LightLoc++, a sensor-robust and efficient outdoor LiDAR localization framework. To support sensor-robust representation learning, we introduce SULID, a synchronized urban multi-LiDAR dataset with representative 32-, 64-, and 128-beam rotating LiDARs, extensive cross-sensor overlap, and diverse urban scenes. Using SULID, we pretrain a sensor-robust backbone through cross-sensor consistency learning. LightLoc++ further preserves efficient new-scene learning by incorporating sample classification guidance and redundant sample downsampling, which reduce regression ambiguity and computational redundancy in large-scale outdoor scenes. Extensive experiments on multiple outdoor LiDAR localization benchmarks demonstrate that LightLoc++ achieves state-of-the-art localization performance with the lowest new-scene training cost among compared methods. Code and dataset will be made available at https://github.com/liw95/LightLoc-PlusPlus. --- ### Physics-informed VAE-EVT for Tail Aware Radio Map Prediction Authors: Amanda Sheron Gamage, Niloofar Mehrnia, James Gross Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15314v1 Ultra-reliable low-latency communication (URLLC) requires precise identification of spatial regions where the signal-to-noise ratio (SNR) falls below an outage threshold. In this context, an outage refers to instances in which SNR falls below a specified threshold, which, for URLLC, can be as stringent as the 0.1% quantile of the SNR distribution. Traditional generative radio map models tend to focus on reconstructing average signal levels, often overlooking the low SNR that is crucial for accurate outage prediction. To address this limitation, we introduce a physics- and tail-informed VAE-EVT (variational autoencoder-extreme value theory) framework that distinctly models both the bulk and tail distribution of SNR. Our approach begins with a physics-informed preprocessing stage that extracts deterministic features, including line-of-sight, shadowing, and distance, from the scene geometry. A dual-latent encoder then captures the bulk SNR using a Gaussian mixture and the tail using a generalized Pareto distribution (GPD). By employing a modified variational objective, the model is trained to jointly supervise both regimes, ensuring focused attention on extreme fading events. Evaluated on the RadioMapSeer dataset, our method achieves an SNR RMSE of 4.83 dB in the outage region defined by the low threshold of 0.1% SNR quantile. This significantly outperforms the state-of-the-art GAN-based model, which records an SNR RMSE of 21.90 dB, with the performance gap widening as the outage threshold becomes more stringent. --- ### Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning Authors: Alexandre L. M. Levada Published: 2026-08-15 Categories: cs.LG, cs.AI, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2608.15313v1 In this paper, we propose SHOPCA (Shape Operator-based Principal Component Analysis), a novel method for unsupervised metric learning and dimensionality reduction that incorporates differential geometric information into the covariance structure of classical PCA. SHOPCA regularizes the global covariance matrix using the mean shape operator, defined as the average of the absolute local shape operators estimated from the data manifold, steering principal components toward directions of both maximum variance and informative curvature. A single trace-normalized mixing coefficient $α$ controls the regularization, recovering standard PCA at $α= 0$ and a curvature-driven embedding as $α\to \infty$. We further introduce a fully unsupervised criterion for selecting $α$ based on the spectral eigengap of the regularized covariance matrix, maximizing the relative separation between the top-$d$ and remaining eigenvalues without using class labels. We evaluate SHOPCA on more than 50 real-world benchmark datasets, comparing it with PCA, ISOMAP, and UMAP using Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), Fowlkes-Mallows index (FM), and V-measure. Results show that SHOPCA consistently improves clustering quality over PCA across a broad range of datasets and surpasses UMAP on small-sample settings, where iterative neighborhood-based manifold estimation can degrade. SHOPCA is computationally tractable, parameter-efficient, and applicable to domains requiring fully unsupervised, geometry-aware dimensionality reduction. --- ### MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning Authors: Ankita Sharma, Bahar Farahani, Sanaz Rahimi Moosavi, Amir Rrahmani, Farshad Firouzi, Krishnendu Chakrabarty Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15311v1 Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing. Recent Mixture-of-Experts (MoE) LLMs are particularly attractive for federated learning because their sparse activation reduces computation and communication while scaling model capacity. However, existing federated MoE methods primarily focus on parameter aggregation and personalization, overlooking the routing behavior of MoE models as a source of information for client collaboration. Under heterogeneous instruction distributions, indiscriminate aggregation can lead to negative transfer, highlighting the need to identify which clients should collaborate during federated optimization. We propose ClientMorpher, a routing-aware, personalized federated instruction fine-tuning framework that leverages routing signatures from pretrained MoE models to organize client collaboration prior to aggregation. We investigate two complementary clustering strategies: ClientMorpher-C, which directly clusters clients using expert activation profiles, and ClientMorpher-E, which first clusters experts based on their cross-client usage signatures and then derives client collaboration groups. We evaluate ClientMorpher for federated instruction fine-tuning on the Databricks Dolly-15K dataset, using pathological and Dirichlet-based heterogeneous client distributions across multiple instruction-following tasks. Experimental results show that routing-aware collaboration consistently improves personalized performance compared to conventional federated averaging and local training, while maintaining the same communication cost. Furthermore, our study shows that client-centric and expert-centric clustering provides an effective and scalable approach for personalized federated instruction fine-tuning of sparse MoE LLMs. --- ### FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting Authors: Zhenyan Liu, Hua Zhang, Haoran Gao, Qi Li, Hongliang Zhu, Huiyu Zhou, Zongliang Shen, Yanxin Xu, Jiahui Wang Published: 2026-08-15 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.15310v1 Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation. However, local training suffers from the forgetting of previously learned global knowledge under cross-client data heterogeneity, which leads to significant declines in both performance and convergence speed. Most previous studies rely on global alignment strategies to retain global knowledge, which hinder local optimization and lead to inadequate supervision of missing classes. Some studies introduce proxy datasets to supplement supervision for missing classes. However, it remains a challenge to balance class-wise global consistency and local optimization objectives without proxy datasets. In this work, we propose FedADB, a Class Anchor-Driven Dual-Branch FL framework. Specifically, the server generates class anchors optimized in a differentiable input space, which are shared across clients. These class anchors serve as global references that provide supervision for missing classes during local training. A dual-branch collaborative training mechanism is designed for clients. In this mechanism, the anchor-based global branch focuses on learning with global consistency, achieving global knowledge alignment by class-anchor balanced sampling. The local calibration branch focuses on learning discriminative local features, mitigating the degradation of local representations caused by excessive global alignment. Extensive experiments across multiple medical and natural datasets demonstrate that FedADB achieves significant improvements in both accuracy and convergence speed. --- ### Physiological World Models for Human State Transitions Authors: Chongyang Zhang, Rendong Wang, Hao Zheng, Hanwen Zhang, Yang Liu, Xiaolong Wei, Bin Chong Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15309v1 Continuous multimodal sensing now allows human physiology to be observed throughout daily life rather than only during occasional clinical visits. However, most health artificial intelligence systems are designed to recognize current states, estimate risks or analyse individual biomarkers. They do not directly model how physiological states change in response to real-world events, behaviours, contexts and interventions. Here we propose the Physiological World Model (PWM), an event-conditioned framework for learning these changes at the level of the whole person. We introduce the HumanState Transition Token, a structured, quality-scored unit that connects the physiological state before an event with the event or action, relevant context and intervention information, the physiological trajectory after the event, observed outcomes and data quality. We describe four capability levels, from state representation to bounded intervention planning, together with four data acquisition and validation protocols. We also propose six benchmark tasks covering HumanState representation, forecasting across multiple timescales, individualized response prediction, simulation of alternative interventions, bounded planning and reliability under distribution shift. Together, this framework provides a practical path towards personalized health management, behavioural intervention design and clinician-supervised decision support, while clearly separating prediction from causal inference and making uncertainty, safety, governance and limits of use explicit. --- ### A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data Authors: Mary Chriselda Antony Oliver, Kaitlyn Hohmeier, Tuyen Tran, Alejandra Castillo, Caroline Moosmüller, Shiying Li Published: 2026-08-15 Categories: stat.ML, cs.LG, math.MG arXiv: https://arxiv.org/abs/2608.15306v1 High-throughput single-cell and spatial transcriptomic technologies provide high-resolution snapshots of heterogeneous cellular states, but their destructive nature prevents repeated measurements of the same cells over time. Consequently, temporal and spatial dynamics must be inferred from independently sampled, unaligned cell populations, making it challenging to reconstruct developmental trajectories. Optimal transport (OT) offers a geometric framework for aligning cell populations and inferring developmental trajectories, but many existing approaches focus on modeling the evolution of distributions of cells in gene expression space rather than the relational structure encoded by gene expression networks. To address this limitation, we introduce a geometric framework for analyzing the spatiotemporal evolution of gene expression networks through embeddings in Gromov--Wasserstein (GW) space. By representing each developmental stage as a graph combining gene expression and spatial proximity, our approach enables comparisons of network structure across time, continuous interpolation between developmental stages via GW geodesics, and quantification of network-level changes using Ollivier-Ricci curvature. We evaluate our framework on a spatiotemporal transcriptomic \textit{Drosophila} dataset and show that GW geodesic interpolations reproduce main trends in curvature dynamics observed in empirical gene expression networks. Agreement with higher-order Co-Optimal Transport (COOT) distances, which jointly represent spatial and temporal information, further validates the framework and suggests that hypernetwork representations successfully record salient biological changes across time. In general, our approach provides a unified geometric approach to study dynamically evolving biological networks. --- ### Understanding Cognition-Induced Risks in Agentic AI Systems Authors: Guanchu Wang, Qinuo Li, Mengnan Du, Xia Hu, Bowen Zhou Published: 2026-08-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15304v1 Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their cognitive engagement raises critical concerns for human society that remain insufficiently studied. To address this gap, we systematically analyze risks induced by expanding cognitive capabilities, following a three-level framework defined by their cognitive scope, from physical cognition to social cognition, and finally to self-referential cognition. We study their potential risks to human agency, autonomy, and control capability, corresponding to each cognitive level. We finally propose strategies to mitigate these risks and enhance the controllability of agentic AI systems, ensuring their long-term safe development. ---