# Research Papers — 2026-10 · bundle page 119 of 156 > Full-text markdown of papers #5901–5950 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/119 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/118.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/120.md) ### Exact Unlearning via Quantized Sufficient Statistics Authors: Ami Tavory, Shripad Gade, Tal Sarig, Noam Touitou, Ido Guy Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07197v1 Exact unlearning requires a deployed predictor to match one rebuilt without the information named by a deletion request. Existing general-purpose exact methods localize retraining through disjoint shards, but every request still invalidates a model, and smaller shards reduce the data available to each constituent predictor. We introduce Quantized Sufficient Statistics (QSS), which separates a small frozen schema from mutable, sum-decomposable content. The schema learns global structure; the content stores local prediction corrections as additive statistics indexed by quantized regions. Deleting content is therefore exact subtraction rather than optimization. We distinguish two guarantees: QSS-L exactly removes a label while retaining the unlabelled input, whereas QSS-E exactly removes both input and label by learning the schema without deletable examples. A deletion takes the arithmetic fast path with probability $1-ρ$ and triggers a full rebuild with probability $ρ$; all reported expected latencies include both events. Across 15 vision, text, and tabular datasets at $ρ=0.5\%$, QSS-L is within 2 percentage points of SISA on 11 tasks and provides 4--483$\times$ lower expected deletion latency on the low-class-count tasks where a compact schema is effective. QSS-E quantifies the additional accuracy cost of removing every trace of an input. --- ### Learning Disentangled Representations with Quantum Variational Autoencoders Authors: Gaoyuan Wang, Jerry Tan, Mark Gerstein Published: 2026-10-05 Categories: quant-ph, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2610.07196v1 Variational autoencoders are powerful representation learning models that map complex data into low-dimensional latent spaces, enabling the discovery of interpretable and disentangled factors. Such representations can facilitate the interpretation and controllable generation of data describing complex scientific systems. Understanding how these factors are organized and encoded in latent space is therefore important for developing reliable representation learning models. Recently, quantum variational autoencoders (QVAEs) have been proposed as quantum representation models, demonstrating informative latent representations and improved latent-space occupancy through quantum regularization. However, it remains unclear whether and how QVAEs can learn disentangled and interpretable latent factors. A key challenge in investigating quantum latent factors is that a small number of qubits spans an exponentially large Hilbert space, making the notion of an individual quantum latent dimension nontrivial. Here, we investigate what constitutes an individual quantum latent dimension and whether it can encode a distinct factor. We develop theoretical insights into quantum latent dimensions and support them with empirical studies on representative synthetic problems, including MNIST variants. Across three datasets, we demonstrate that QVAEs can discover factorized and semantically interpretable latent representations, with individual qubits functioning as meaningful latent factors. These results establish a foundation for understanding quantum latent spaces and their potential for structured and interpretable representation learning. --- ### Sim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile Robot Authors: Chalindu Abeywansa, Sahan Gunasekara, Devindi De Silva, Seniru Dissanayake, Ranga Rodrigo, Peshala Jayasekara Published: 2026-10-05 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.07192v1 Vision-Language Navigation (VLN) enables robots to navigate through environments using natural language instructions, making human-robot interaction intuitive. Traditional VLN models often rely on navigation graphs, 360-degree views, and perfect localization which pose significant challenges when adapting these models to real-world settings. This work addresses these limitations by performing a simulation-to-real domain shift of a VLN approach that operates in continuous environments without requiring navigation graphs or panoramic views. The proposed system integrates vision-language models that align visual inputs and linguistic instructions within a shared embedding space, facilitating natural language-driven navigation. We employ a Cross-Modal Attention (CMA) based architecture trained on an existing dataset in a simulated environment and fine-tune it using real-world data collected from a custom-built Ackermann-steered robot equipped with a camera and a LiDAR sensor. By utilising linear photometric adjustments and fine-tuning on a limited number of episodes, our model successfully adapts to real-world environments, achieving effective navigation while running offline on dedicated hardware. Experimental results, evaluated using Success weighted by Path Length (SPL) and Normalized Dynamic Time Warping (nDTW) metrics, demonstrate the robustness and adaptability of our approach. Keywords: Vision-Language Navigation, Cross-Modal Attention, Natural Language Instructions, Sim-to-Real Transfer, Autonomous Navigation, Ackermann-steering. --- ### Agentic Design Space Exploration for Joint Hardware Configuration Selection and Mapping of AI Inference Workloads on Heterogeneous Edge SoCs Authors: Geetha Prasuna Yarramneni, Surya Selvam, Wilfried Haensch, Anand Raghunathan Published: 2026-10-05 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2610.07191v1 Modern edge Systems-on-Chip (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, each with distinct performance and energy characteristics. Deploying AI inference workloads on them under real-time latency and energy constraints requires jointly mapping workloads to PUs and configuring each PU (e.g., selecting the number of active cores and the operating frequency). This joint space grows combinatorially, making exhaustive search infeasible. Most prior work on design space exploration (DSE) applies black-box optimization (BBO) such as evolutionary search, where each evaluation returns only aggregate metrics such as latency and energy. Recent LLM-guided DSE relies on the same sparse feedback. We observe that this limits its efficiency: it offers no insight into the design space or the reasons a design choice performs the way it does, and it leaves the reasoning abilities of LLMs largely unused. We present TraceDSE, an agentic DSE flow that performs joint workload mapping and PU configuration selection for AI inference on heterogeneous SoCs. TraceDSE is an iterative proposer-critic loop driven by richer feedback in the form of system execution traces. The LLM proposer agent generates candidate mappings and PU configurations for hardware evaluation. The LLM critic agent, equipped with programmatic trace-analysis tools, analyzes the traces to identify bottlenecks and suggest targeted refinements. This loop yields deeper insight into each design point, higher-quality decisions, and a more effective search. Across four AI inference workloads (models of varying complexity and a multi-model pipeline) on an Intel Meteor Lake SoC, TraceDSE consistently outperforms two state-of-the-art BBO tools, improving Pareto frontier hypervolume by up to 35% over NSGA-II and up to 68% over Bayesian optimization, while requiring ~6-9x fewer hardware evaluations. --- ### Poisson empirical Bayes estimation of sums of random variables via minimum-distance methods Authors: Stefano Favaro, Sandra Fortini, Soham Jana Published: 2026-10-05 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2610.07190v1 The estimation of sums of functions of observable and unobservable variables is a long-standing problem in statistics, with applications in many domains. We consider this problem in Poisson mixture models, where empirical Bayes provides a natural framework but nonparametric theory remains limited. We develop a nonparametric empirical Bayes methodology based on regular and coarsened minimum-distance estimation of the unknown mixing distribution. For a broad class of such sums, we establish large-sample guarantees showing that the resulting plug-in estimates asymptotically merge with the oracle Bayes estimate. In particular, when the mixing distribution has finite support, we obtain a nearly parametric convergence rate, up to a logarithmic factor. We then provide a finite-sample analysis of two representative sums: the total intensity among units whose observed count does not exceed a fixed threshold, and the number of units whose observed count exceeds their latent intensity. For the total-intensity sum, we establish a lower bound on the minimax regret and derive upper bounds for both regular and coarsened minimum-distance procedures under compact-support and subexponential assumptions on the mixing distribution. These upper bounds match the minimax rate up to logarithmic factors, with the coarsened procedure in the compact-support setting matching the rate exactly when the coarsening level is fixed. The above-average sum displays a markedly different behavior: a lower bound on the minimax regret shows that bounded regret is in general impossible to achieve. We identify additional stability conditions under which bounded regret can be recovered up to logarithmic factors, and show that these conditions are automatically satisfied when the mixing distribution has finite support. Numerical experiments on both synthetic and real data illustrate the performance of the proposed methodology. --- ### Identifying Introspection From the Inside Authors: David I. Atkinson, Dillon Plunkett, David Bau Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.07186v1 Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone. How can we distinguish plausible confabulations from genuine introspection? In this paper, we identify mechanistic signatures of faithful self-report in a controlled setting. Using low-rank adapters, we train models to make decisions on behalf of fictitious characters, according to latent linear preference functions. We find sustained fine-tuning on an implicit decision task can lead to the emergence of accurate self-reporting of models' learned preferences, even without explicit self-report supervision. We ask two research questions about this emergent phenomenon. First: is the emergence of accurate self-reporting accompanied by a measurable structural change in the model? Weight ablations and frozen-layer experiments together indicate that preference representations shift to earlier layers over training, consistent with the hypothesis that faithful self-report requires preferences to be located where pre-existing verbalization mechanisms can access them. Second: can these structural differences distinguish faithful models from unfaithful ones? Using attribution patching, we find that faithful models exhibit significantly higher attribution similarity between the decision-making and self-report tasks -- a mechanistic signature of faithful self-report that does not require us to understand the content of the report itself. Previous work on self-report has observed behaviorally that models can be faithful or unfaithful; our work proposes that, at least in our restricted setting, it is possible to distinguish between the two patterns of computation by examining the structure of the networks themselves. --- ### Learning Scientific Exploration from Human Research Decision Trajectories Authors: Xuchen Gong, Shane Gu, Haokun Liu, Dixi Yao, Chenhao Tan, Tian Li Published: 2026-10-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.07184v1 A key challenge in building AI systems for scientific research is enabling $\textit{scientific exploration}$: the systematic process of investigating unknown phenomena or ideas to gain new knowledge through sequences of research decisions and actions. Yet this process is largely missing from existing scientific corpora; for example, research papers primarily record final outcomes rather than the trajectories that produced them. In this work, we introduce $\textbf{ResearchTrails}$, a dataset of $\textbf{human research trajectories constructed from Git repositories}$, where $\textbf{commit histories}$ serve as proxies for research exploration. We develop an automated and scalable pipeline that extracts structured research trajectories from repository commits, capturing successive changes to methods, experiments, and ablations. We characterize the resulting dataset and show that these trajectories contain meaningful signals about intermediate research decisions beyond what final papers reveal. We further demonstrate utilities of ResearchTrails in multiple use cases, including retrieving human research experience as external skills at test time and training models on research trajectories to improve generalization to new research decisions. Our results suggest a path toward AI systems that learn not only from the products of science, but from the evolving process of discovery itself. --- ### CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks Authors: Gowthamkumar Nandakishore Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.07177v1 An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of-four, chance 0.250) and 0.593 (pairwise, chance 0.500), is statistically indistinguishable from coin flipping on RM-Bench and JudgeBench, and answers every HaluEval item with one constant label, matching the trivial always-first baseline at 0.581. Judges with the same parameter count score far higher everywhere: a reward model reaches 0.764 to 0.976 and a generative judge 0.611 to 0.778, and every gap to CLM is significant after Benjamini-Hochberg correction. Two properties do work. Raw confidences are overconfident by up to +0.401, yet one pooled temperature fit on held-out calibration items repairs expected calibration error to at most 0.062, and the repaired confidence ranks the model's own errors above chance on three of six benchmarks. The decision order-flip rate is 0.0002 against 0.2188 for the generative judge, and the length-preference shift is -0.023 against -0.217. The confidence-gated cascade, however, escalates between 0.923 and 1.000 of items to the strong judge at the preregistered 0.97 retention bar: calibrated confidence about a near-chance judge has almost nothing to keep. The design: five public preference benchmarks and one hallucination benchmark with real labels, scored under a preregistration frozen before any test item was seen, against generative, reward-model, and trivial baselines, with per-item predictions released. --- ### CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression Authors: Zhaoyang Wei, Bowen Jiang, Yanchao Hao, Wenchao Ding, Zheng Wei, Shaocheng Wu, Zhenjun Han, Jianbin Jiao Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07175v1 Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches differ in how they represent these states: continuous methods avoid vocabulary constraints, whereas discrete methods improve accuracy through quantization into a finite codebook. Our analysis of representative continuous and discrete systems identifies two functional requirements: answers must rely on latent states, and those states must carry valid, problem-specific reasoning. Continuous latents influence answers despite collapsed reasoning content, whereas discrete latents retain recoverable intermediate reasoning that answer prediction largely bypasses. To address these challenges, we propose Continuous Anchored Latent Reasoning (CALR), which connects latent formation with answer use through functional anchoring. With reference latents from information-balanced compression, CALR couples latent-mediated answer supervision with derivation-level semantic anchoring: the former routes answer supervision through intermediate states, while the latter grounds their decoded content in problem-specific derivations. A parallel-to-autoregressive curriculum develops sequential reasoning by conditioning subsequent latent blocks on generated prefixes. Evaluations on five mathematical reasoning benchmarks across model families show substantial accuracy gains. Under matched budgets, CALR gains 26.0 percentage points over a comparable continuous latent reasoning method. Further analyses show that its latents support answer prediction and carry problem-specific intermediate reasoning. --- ### A theory of platonic representations in language models Authors: Darshil Doshi, Wenjie Zhou, Corinna Elena Wegner, Daniel J. Korchinski, Santiago Acevedo, Matthieu Wyart Published: 2026-10-05 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2610.07168v1 Representations of translated sentences are similar in the inner layers of multilingual language models -- an observation connected to the platonic representation hypothesis, yet unexplained theoretically. We provide an explanation based on the assumption that data have a hidden hierarchical structure whose abstract levels are shared across languages while surface levels are modality- or language-specific. Concretely, we generate synthetic languages from probabilistic context-free grammars sharing upper-level but not lower-level production rules. In this setting the Bayes-optimal next-token predictor is belief propagation (BP); encoding its messages in successive layers yields analytical predictions that agree well with transformers trained on the same data. The framework explains why cross-lingual similarity peaks in middle layers, coexists with language-specific structure, and strengthens with language proximity, model quality and data exposure. It distinguishes similarity (shared neighborhood geometry) from alignment (shared coordinates), showing that the latter occurs when code-switched data, i.e. mixed-language sentences, are abundant enough. It further predicts that subtracting from each layer the component linearly predictable from the preceding one increases cross-lingual similarity, which we confirm in pretrained LLMs. --- ### Interleaved Projected Gradient Descent for Safe Imitation Learning Authors: Shengfan Cao, Francesco Borrelli Published: 2026-10-05 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2610.07167v1 We propose an imitation-learning design for neural-network control policies under state and input constraints. Training alternates a standard imitation gradient step with a block of $k$ safety steps that pull the network's actions toward their projection onto the safe set; at run time, the controller is the trained network alone, with no safety filter. We analyze this scheme as inexact projected gradient descent in the space of policy actions. When the projected actions are recomputed at every safety step and each step moves the actions consistently toward the safe set, letting $k$ grow logarithmically yields asymptotic constraint satisfaction on the training states and bounds the distance to the constrained optimum of the imitation loss; with the projected actions held fixed, the same holds only if they are exactly representable by the network. On a nonlinear autonomous racing task, we compare our method with adding a weighted constraint-violation penalty to the imitation loss. With a sufficiently large weight, our method matches the lap time of unconstrained imitation while reducing the fraction of violating episodes from $15\%$ to $1\%$, about six times fewer than the penalty approach at its best weight. Its lap times are less sensitive to the weight, which instead sets how quickly violations vanish during training. In racing, the safety corrections are sparse and the conditions of the analysis do not hold; the gain arises instead through the data collected during training. These gains come at the cost of additional training computation. --- ### Adversarial Training for Deep Hedging in Nonstationary Markets Authors: Philipp J. Schneider, Lukas Looser, Antoine Garin, Shuhan Liu, Daniel Kuhn Published: 2026-10-05 Categories: cs.LG, math.OC, q-fin.CP arXiv: https://arxiv.org/abs/2610.07162v1 Deep hedging learns trading policies from historical or simulated market trajectories, yet under nonstationarity these training paths may not represent future market conditions. We propose WRAP (Wasserstein-Reweighting Adversarial Perturbation), a drift-aware adversarial training framework derived from a two-budget distributionally robust optimization (DRO) formulation. The formulation is anchored to a weighted empirical reference distribution whose fixed baseline weights are chosen to balance sampling uncertainty against temporal drift. Around this reference distribution, the ambiguity set addresses two complementary forms of distributional misspecification by allowing an adversary to reweight the observed trajectories subject to a $φ$-divergence constraint and perturb their paths subject to an optimal-transport (OT) constraint. We derive a joint first-order expansion in which the leading-order increase over the nominal expected loss decomposes into a reweighting contribution determined by the dispersion of hedging losses across trajectories and a transport contribution determined by the sensitivity of the loss to path perturbations. This expansion yields an explicit finite-dimensional adversarial attack that replaces the distributional inner supremum with a tractable first-order approximation. Across stationary and nonstationary Heston dynamics and a generalized affine diffusion (GAD), the experiments show complementary benefits from reweighting and transport, with joint adversarial training providing the largest gains under nonstationarity. --- ### CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets Authors: Berke Arda, Ahmetcan Yavuz, Paul Gerry, Sebastian Lobentanzer, Nobin Sarwar, Joan Giner-Miguelez, Kongtao Chen, Luyao Zhang, Mrinmaya Sachan, Mubashara Akhtar Published: 2026-10-05 Categories: cs.CL, cs.AI, cs.DL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2610.07132v1 Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful reading of accompanying dataset documentation. We present the first benchmark enabling end-to-end evaluation of metadata extraction aligned with a community-standard schema. The benchmark comprises 602 papers, including 102 with human-validated gold annotations and 500 with LLM-generated silver annotations, covering the full Croissant schema with both core and Responsible AI (RAI) fields. Using this benchmark, we evaluate a range of extraction systems spanning frontier models, open-weight models, and agentic architectures, under a two-tier evaluation framework that combines rule-based scoring with an LLM judge selected via human audit. We find that single-pass extraction consistently outperforms the four agentic architectures we evaluate: across backbones, these decomposed variants achieve lower accuracy than a single full-context pass. The largest gap appears on long-form RAI fields, which require synthesizing and interpreting information scattered across a paper rather than copying it from a single location, a setting where current systems remain far from reliable. We release the benchmark, evaluation code, judge audit, a live demo, and a leaderboard open to new systems. --- ### The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective Authors: Xingrun Li, Sho Kuno, Yusuke Mukuta, Xin Yang, Tatsuya Harada Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07131v1 We study the implicit bias of Riemannian gradient flow for hyperbolic multiclass classification with fixed class prototypes in hyperbolic space $\mathbb{H}^n$. Our framework accommodates general permutation invariant relative margin (PERM) losses, a class that includes cross entropy and other standard multiclass losses. Our analysis is based on a decomposition: at large radius, the distance to each prototype splits into a radial term and a direction-dependent term described by the Busemann function. This yields two main results. First, we prove a radial dichotomy: the sign of a drift coefficient $μ$ determines whether the radius is pushed toward the ideal boundary or back toward the interior; if the positive drift persists, then $r(t)=\frac{1}{2}\log t+O(1)$, while persistent negative drift returns the trajectory to the large-radius threshold in finite time. Second, we show that the boundary direction converges to a critical point of the Busemann risk on $\partial\mathbb{H}^n$. These results provide a rigorous asymptotic perspective on two phenomena we refer to as boundary saturation and near-boundary clustering in hyperbolic representation learning. --- ### Is this machine playing? Authors: Nathan Cloos, Antonio Norelli, Daniel Durbin, Jacob Andreas, Daniela Rus, Phillip Isola Published: 2026-10-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.07130v1 We placed a modern AI coding assistant in an unintended role: as the mind of a body on an unknown digital island. With only a minimal instruction mentioning no specific task, reward, or activity, the machine started animating its virtual body. Across thirty-hour runs, the embodied AI agent climbed hills, stacked blocks into towers, drew mandalas, reinterpreted sports, ran experiments on the physics of its world, and learned techniques that later expanded what it could accomplish. These activities recurred across thirteen agents but diverged into distinct histories. We examine whether this behavior satisfies classical criteria for play and ask whether play can become a mode of machine development. --- ### Aggregating User Preferences while Ensuring Equity, Diversity, and Inclusion using Graph Summarization Authors: Adji Marieme Sita Cissé, Malek Mouhoub Published: 2026-10-05 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2610.07128v1 Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI): classical aggregation rules such as Borda and Condorcet have no mechanism to prevent results from systematically favoring majority groups, collapsing onto homogeneous items, or under-representing minorities. We address this problem through EDI-constrained graph summarization. User preferences are modeled as a weighted attributed bipartite graph, and a greedy coarsening algorithm iteratively merges user nodes while enforcing three structural EDI criteria: an equity gap constraint ($ΔE$), an intra-list diversity constraint (ILD), and a group inclusion constraint. Rather than correcting fairness after aggregation, our method embeds EDI preservation directly into the graph structure. We evaluate across five datasets spanning four domains: MovieLens 100k and 1M, libimseti.cz, Rate My Professors, and OpenAlex (2018-2023). Our method, AURORA, achieves the largest and most consistent diversity gains over classical voting rules, and on MovieLens 100k at $k = 20$ it simultaneously improves all three EDI criteria over both Borda and Condorcet. On Rate My Professors, it combines high diversity (ILD = 0.808) with the highest female item representation (60%), at a moderate equity cost, and it achieves the lowest equity gap ($ΔE = 0.031$) on OpenAlex, where Borda-based methods recommend zero female authors. On libimseti.cz, the only dataset where the sensitive attribute is present on both sides of the bipartite graph, our method does not reduce the equity gap, a limitation we connect to prior findings that demographic parity is not always an appropriate target. These results demonstrate that embedding EDI constraints into aggregation structure yields more robust fairness-diversity trade-offs than post-hoc approaches. --- ### PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence Authors: Dheeraj Varghese, Anna Vettoruzzo, Walter Simoncini, Michelle Lorena Acevedo Callejas, Mohammad Mahdi Derakhshani, Kristof Meding, Joaquin Vanschoren, Cees G. M. Snoek Published: 2026-10-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.07127v1 Recent advances in multimodal foundation models yield strong performance on static perception and reasoning benchmarks, yet such evaluations largely overlook a central aspect of intelligence: acting competently in dynamic environments over extended time horizons. We introduce PlaySuite, a large-scale benchmark for evaluating interactive visual intelligence across more than 5K open-source video games curated from PyWeek and itch.io. Spanning diverse genres and engines, including Pygame, HTML5, Godot, and Unity, these independent games are largely out-of-distribution for current models, reducing the likelihood that success can be achieved by retrieving memorized walkthroughs or web-scale training artifacts. To enable scalable evaluation across heterogeneous titles, we develop a unified closed-loop interaction framework optimized for HPC clusters alongside a Video-LLM-as-a-judge protocol that maps observable gameplay milestones to standardized progress levels. We evaluate fourteen recent open models spanning vision-language models, computer-use agents, and vision-language-action models. Our results yield strong evidence of a perception-action gap: despite strong reasoning capabilities, current models struggle to make sustained progress and exhibit recurring failures in spatial grounding, action execution, and self-correction. PlaySuite provides a reproducible and extensible testbed for measuring progress from visual perception to goal-directed interaction, and a foundation for developing models that can act, adapt, and generalize in dynamic visual environments. --- ### Jailbreaking Open-Weight LLMs via Random Embedding Perturbations Authors: Abhinav Sudhakar Dubey, Scott Sirri, Vaggos Chatziafratis, C. Seshadhri Published: 2026-10-05 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.07125v1 While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern. One key feature is the ability to refuse or deflect harmful, malicious, or insensitive prompts. In this paper, we expose safety vulnerabilities across six common open-weight LLMs of various sizes that consistently lead to harmful or unsafe responses on the JailbreakBench benchmark dataset. Our proposed attack, Perturbed Embedding Vector (PEV), is a simple and fast "jailbreaking" technique that is cheaper than prior approaches, which typically require gradient computations, per-prompt optimizations, or altering internal weights of the models. PEV just adds independent Gaussian noise in the embedding vector representations of the prompt, with no need for further manipulations. To generate unsafe responses, we repeatedly sample additive noise from this distribution. In our experiments, we observe that the average compute cost to get the first successful attack is up to an order of magnitude less than previous attacks. The first successful jailbreak on a new prompt typically arrives within one minute on every tested model, and PEV generates unsafe responses across all models for all prompts in JailbreakBench. No other tested method achieves such results, despite them taking longer to run. More broadly, we believe that understanding the behavior of LLMs under perturbations in the embedding vectors is an important research direction: while perturbations constitute a major security risk, they can also serve as a valuable tool for exploring the dynamical behavior of such models. --- ### SoloQ: Calibration-Free Quantization for Diffusion Language Models Authors: Donghyun Lee, Arkapravo Ghosh, Varun Manjunath, Bumjoon Kyle Rhee, Hyunho Kook, Shiting Xiao, Youngeun Kim, Priyadarshini Panda Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07121v1 Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based token generation. However, their growing model sizes and high inference costs make efficient deployment challenging: full-sequence denoising repeatedly invokes compute-intensive forward passes, while block-diffusion models additionally introduce a memory-intensive KV-cache. Low-bit weight-activation quantization is therefore attractive, yet existing dLLM post-training quantization methods rely on calibration data despite activation distributions shifting across masking states and denoising steps. We present SoloQ, a calibration-free quantization framework that maps weights and activations into a normalized rotated basis with a predictable marginal distribution, enabling data-independent quantization. SoloQ combines a structured K-RPBH rotation with a lightweight rescaling correction for calibration-free quantization. Its predictable post-rotation distribution supports both distribution-matched codebooks and hardware-native NVFP4. For block-diffusion models, SoloQ further applies commit-time KV-cache quantization to compress persistent states without perturbing the actively denoised block. Across full-sequence dLLMs (LLaDA and Dream) and block-diffusion dLLMs(Fast-dLLM v2 and Nemotron-Labs-Diffusion), SoloQ retains accuracy under 4-bit quantization and outperforms calibration-based baselines on knowledge- and reasoning-intensive benchmarks. With NVFP4, SoloQ reduces peak memory by up to 2.61X and accelerates end-to-end inference by up to 2.24X. --- ### AMBER: Training Long-Horizon Web Agents through Append-Only Memory Authors: Chinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao, Shuang Xie, Han Li, Tianfu Wu, Lingyun Wang Published: 2026-10-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.07118v1 Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interaction history can quickly exceed practical context budgets. To ensure reliability, agents must maintain factual information over long horizons, remember execution errors and corrective feedback, and track progress across actions. Several approaches have been proposed to achieve this without the need for maintaining the entire execution history in context, such as using the reasoning and action history, learning to maintain a fixed-size memory through an overwrite mechanism, and periodic summarization. Although overwrite memory can in principle retain anything an append-only memory can, it must learn to carry each fact through every subsequent rewrite, which is difficult to learn from sparse outcome rewards; for interactive applications like web agents, we find that trained overwrite memories delete key information required by the trajectory, as well as corrective feedback received from the environment. We introduce AMBER (Append-only Memory Bank for Evidence Retention) - a simple and scalable framework where an agent jointly learns to reason, act, and write free-form memory, while an append-only rule guarantees retention by construction. This allows AMBER to be trained end-to-end with reinforcement learning from outcome rewards without the need for extensive curated SFT data. On WebArena Lite, AMBER improves average success over overwrite-based memory by 4.09 percentage points, increases the fraction of tasks solved in five repeated runs by 4.8 percentage points, and matches an overwrite baseline trained on substantially more expensive curated supervision. AMBER achieves these improvements while maintaining a practical token budget, providing a strong balance between context efficiency, task performance, and reliable long-horizon execution. --- ### R2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot Interaction Authors: Gabriele Magrini, Riccardo Catalini, Federico Becattini, Guido Borghi, Pietro Pala, Roberto Vezzani, Lorenzo Seidenari Published: 2026-10-05 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.07117v1 Understanding and modeling interactions between autonomous agents is a fundamental challenge in robotics, with broad implications for collaborative systems, social robotics, and human-robot coexistence. Although the study of robot interactions has emerged as a compelling research direction, progress has been severely hampered by the absence of large-scale benchmarks. In this paper, we introduce Robot-to-Robot Interaction (R2RI), the first dataset specifically designed to address the Robot-Robot Interaction (RRI) task. R2RI consists of different humanoid robots and realistic interactions modeled on real human social behaviors. Complementary viewpoints are available, \textit{i.e.}, an egocentric perspective from each robot's onboard sensors, and an exocentric perspective from external fixed cameras, thus enabling rich spatial and contextual understanding of the interaction dynamics. The dataset comprises more than $6.5$M frames and $\approx5000$ videos at $120$ fps, including Event and RGB domains. We investigate pros and cons of each domain, comparing state-of-the-art approaches for a number of key sensing and interaction based tasks. We publicly release the dataset and its annotations for all tasks and modalities at https://github.com/MagriniGabriele/R2RI. --- ### Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations Authors: Hashmath Shaik, Gnaneswar Villuri, Alex Doboli Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07115v1 The order in which candidate responses are presented can change an LLM judge's verdict. Detecting such a position flip ordinarily requires judging each pair in both orders, which doubles the number of judgments. We investigate whether residual stream activations recorded immediately before the initial verdict can predict a flip. We use nested grouped cross-validation to evaluate regularized linear probes on 534 JudgeBench pairs for three Qwen3 judges and Llama-3.1-8B. The linear probes achieve AUROCs of .621-.850 and outperform a combined baseline that uses verbalized confidence, verdict-label logits, response lengths, and the judge's initial choice by .062-.113 AUROC. Linear probes trained on JudgeBench and then frozen achieve AUROCs of .685-.853 on 1,802 MT-Bench comparisons without MT-Bench fitting or recalibration. These results show that pre-verdict activations support prediction of susceptibility to candidate order and outperform the non-activation predictors evaluated here. --- ### Sample-Optimal Estimation of the Fréchet Inception Distance Authors: Ziyun Chen, Jerry Li, Kevin Tian, Yusong Zhu Published: 2026-10-05 Categories: cs.LG, cs.CV, cs.DS, math.ST, stat.ML arXiv: https://arxiv.org/abs/2610.07114v2 The Fréchet Inception Distance (FID) is widely used to evaluate generative models, but its empirical plug-in estimator suffers from finite-sample bias (BSAG18, CF20). We study the sample complexity $n$ of estimating FID to error $ε$ between $d$-dimensional Gaussians with bounded mean distance and covariances, when one distribution is known. Our contributions are threefold. (1) We establish tight finite-sample $Θ(\frac{d^2}{n})$ bias and $Θ(\frac{d}{n} + \frac {d^2} {n^2})$ variance bounds for the empirical plug-in estimator, establishing a $\gtrsim d^2$ sample complexity. (2) To debias the empirical plug-in estimator, we generalize the ${\rm FID}_\infty$ estimator of (CF20) to extrapolation methods of arbitrary order $k$. We further prove tight bias and variance bounds of $Θ(\frac{d^{k + 2}}{n^{k + 1}})$ and $Θ(\frac d n + \frac{d^2}{n^2})$ for any order-$k$ extrapolation under our framework. (3) We introduce Relative Taylor Debiasing (RTD), a new, computationally efficient FID estimation algorithm using debiasing techniques inspired by U-statistics. We show that RTD achieves an $O(\frac d {ε^2})$ sample complexity, and prove that this is optimal. We provide a complementary empirical evaluation of our new estimators. Our experiments on synthetic Gaussians validate the predicted residual bias and support the tightness of our bounds. On ImageNet with Inception embeddings, RTD achieves the lowest mean estimation error at the standard 50K sample budget, while our second-order variance-aware extrapolation estimator (VALE$_2$) uses only 10K samples to achieve accuracy comparable to FID$_\infty$ at 50K samples. --- ### LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library Authors: Minh Tran Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07111v1 UAVs that act as relays or base stations need accurate air-to-ground path-loss predictions for rate adaptation and placement, but propagation conditions change as a UAV moves between suburban, urban and high-rise areas, and the same areas are often revisited. Online regressors that adapt by forgetting must relearn each environment from scratch, whereas a single model trained on all data averages incompatible regimes. We propose LiLib, a lightweight continual-learning scheme in which a UAV maintains a small library of recursive-least-squares experts. A windowed residual test detects drift; a short probe phase then either reuses the best stored expert or creates a new one. In simulations based on four standard urbanization profiles, LiLib reduces prediction RMSE from 5.89 dB (best sliding-window baseline) to 4.03 dB (p < 0.001), lowers the error shortly after a return to a known environment from 12.3 dB to 5.7 dB, and recovers 99% of the throughput of a regime-aware oracle in rate adaptation. The library stores four experts in under 0.5 KB, and identifies regimes with 92% purity without labels. When a second UAV is initialized with the library of a peer, its error after environment changes halves. LiLib does not reach the oracle, and similar regimes may be merged when shadowing is strong. The results indicate that, for recurring drift, remembering is more effective than re-adapting. --- ### MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs Authors: Yun Jiang, Bo Zheng, Yingying Zhang, Xueming Xiao, Tao Hu, Hutao Cui, Zhiguo Meng, Ke Gao, Yang Gao, Meibao Yao Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07110v1 High-quality 3D reconstruction of lunar terrain from sparse rover images is indispensable for autonomous lunar exploration, but remains challenging because viewpoint overlap is insufficient, surface textures are weak, and data volume is limited. We propose MoonGS, the first feed-forward 3D Gaussian Splatting framework tailored to lunar scenes. Given only two input images, MoonGS predicts pixel-aligned Gaussian primitives in a single forward pass and renders photorealistic novel views without any per-scene optimization. MoonGS (i) adopts an adaptable backbone design that seamlessly integrates advanced vision foundation models to extract robust depth features; (ii) integrates semantic priors in two manners: merging semantic cues with visual features to refine Gaussian parameter estimation, and adopting a semantic ranking loss that regularizes background depth; and (iii) employs an entropy-guided heuristic resampling strategy to augment sparse observations by selecting the most informative distant viewpoints with negligible overhead. Experiments on the LuSNAR benchmark and our synthetic weak-texture MoonBlender dataset show that MoonGS surpasses state-of-the-art feed-forward NeRF/3DGS baselines by +4.9 dB PSNR, +0.29 SSIM, and 40\% lower LPIPS while maintaining sub-second inference. Furthermore, we validate the broad applicability of our framework by demonstrating that it effectively leverages state-of-the-art backbones, including VGGT, to significantly boost performance. Qualitative evaluations on Chang'e mission imagery also show the best visual quality among compared methods, indicating robustness on real lunar data. The source code and dataset are publicly available at https://github.com/InRobots/MoonBlender. --- ### JudgeMoE: Distributional Aggregation for LLM-as-a-Judge Authors: Yiqi Liu, Joseph James, Yang Wang, Kun Zhao, Chenghao Xiao, Chenghua Lin Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.07109v1 When an LLM judge scores an output, its score distribution retains uncertainty and disagreement information that is lost after scalar compression. We introduce JudgeMoE, a lightweight aggregator that assigns example-specific weights to cached judge score distributions and fuses them before computing a final score. A protocol study shows that score-range choice is unstable across judge--dataset settings and that soft scoring usually outperforms hard decoding. On the original 10-cell benchmark, JudgeMoE improves mean Spearman over uniform log pooling by $+0.079$. Applying the same configuration to six additional cells yields a $+0.0393$ mean gain over the strongest local single judge across 16 cells, with positive differences in 12/16 cells and a one-sided Wilcoxon signed-rank $p=0.0091$. Validation-based analyses further show that the preferred aggregation method depends on the task and judge pool. --- ### Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation Authors: Jinfeng Xu, Zheyu Chen, Ziyue Peng, Zheng Lin, Wenhao Yuan, Jian Chen, Shujie Li, Edith Ngai Published: 2026-10-05 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2610.07105v1 Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distributed progress} and quantify it using cross-generation advantage (CGA), a marginally matched contrast between cross- and within-generation model pairs. A rank-separation statistic, label-free at selection time, predicts which family to retain. Across four datasets and three sequential recommendation encoders, the preferred retention regime varies by architecture: cross-generation pairing benefits GRU4Rec and SASRec, whereas FMLP initially favors within-generation pairing and shifts toward cross-generation pairing after a second update. Rank separation selects the stronger family in 12/12 first-update and 5/6 second-update dataset-encoder settings; on held-out tests, the selected family outperforms the direct successor in 34/36 trajectories. Five transfer mechanisms do not consistently reproduce these gains in one model. These findings establish state retention as a distinct Rec-RSI problem: progress may reside in relations between generations as well as in the latest model. Code is available at \href{https://github.com/Jinfeng-Xu/RecRSI}{https://github.com/Jinfeng-Xu/RecRSI}. --- ### Muon Is Theoretically Wrong For Convolutions, But Empirically Effective Authors: Thibaut Boissin, Thomas Massena, Mathieu Serrurier, Franck Mamalet Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07103v1 Muon, an optimizer known for its efficiency, has a clear interpretation for matrix-valued updates, but convolutional kernels are stored as four-dimensional tensors. Standard implementations reshape these tensors into matrices, a shortcut which breaks the theoretical understanding behind Muon. To investigate this, we formalize the corresponding optimization objective directly in convolutional operator geometry and introduce Convolutional Newton-Schulz (Conv-NS), which approximates the polar factor in this geometry while preserving kernel support. When applied in fast training experiments, Conv-NS and reshape-based Muon are both computationally efficient and achieve comparable accuracy on CIFAR-10 and ImageNet classification tasks. However, as one could expect a theoretically aligned Conv-NS to outperform reshape-based Muon, we investigate this mismatch between practice and theoretical understanding, with the hypothesis that exact convolutional orthogonalization may overconstrain updates. These findings highlight Muon's strong practical performance while opening directions for its further development on convolutions. Our code is publicly available at \href{https://github.com/thib-s/muonconv-cifar10-airbench}{github conv-muon}. --- ### When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory Authors: Olukunle Owolabi, Pulkit Gupta, Fei Wang Published: 2026-10-05 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.07100v1 Persistent agent memory is only as reliable as its retention decision: an assertion weakly supported by its source can be stored and later reused as established fact. We study whether the retention decision should be governed by a confidence bar conditioned on the semantic category of the assertion rather than by a single global threshold, retaining well-evidenced categories liberally while abstaining more aggressively where inference is unreliable. We evaluate this in a deployed cold-start memory pipeline on 100 synthetic personas. The empirical evaluation is motivated by a sharp reliability asymmetry: across 4{,}715 candidate assertions, only 77.9\% of value and belief assertions are supported by their source, versus 96.2\% for all other categories. A global confidence threshold cannot separate these: it either admits unsupported value claims or discards well-evidenced ones. Conditioning the threshold on category resolves the tradeoff. In repeated held-out evaluation, a stricter bar on values alone reduces unsupported retentions from 6.2\% to 4.0\% (an ${\approx}36\%$ relative reduction, modest but consistent across folds) and, as corroborating evidence, preserves an estimated 13 percentage points more coverage (95\% CI 9.8--16.0) than a global threshold at comparable retention. Our results suggest that reliable retention depends on the type of assertion, not on confidence alone, and that a category-conditioned threshold can act as a simple, effective form of selective prediction at the write boundary. --- ### T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator Authors: Keyvan Dadashzadeh, Yuehong Zhou, Minyu Cui, Miquel Pericas Published: 2026-10-05 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2610.07098v1 Large transformer-based models increasingly depend on multi-GPU execution, which requires frequent collective communication among GPUs. Existing communication libraries often rely on many GPU threads to achieve high bandwidth or low latency, resulting in a large streaming multiprocessor (SM)-side resource footprint. This footprint can limit the resources available to other GPU work, particularly when communication and computation execute concurrently. Thus, efficient collective communication should not only achieve high collective performance but also reduce its SM-side resource usage. This paper presents T-CCL, a resource-efficient collective communication library based on the Tensor Memory Accelerator (TMA) for intra-node communication. T-CCL offloads both data movement and reduction operations to TMA and executes each collective as a pipelined series of asynchronous TMA operations, reducing the SM resources required for collective communication while maintaining high bandwidth. Evaluated across AllReduce, AllGather, and ReduceScatter collectives, T-CCL outperforms NCCL by up to 2.4x with unrestricted communication resources and up to 3.42x under restricted resource budgets, remains competitive with NCCL's recent symmetric-memory kernels, and occupies the same or fewer SMs in profiled cases. In a GEMM-collective overlap case study, switching the communication backend from NCCL to T-CCL raises the average operator-level speedup over a sequential baseline from 1.12x to 1.25x on two GPUs and from 1.04x to 1.14x on four GPUs, as T-CCL uses fewer SMs for communication, leaving more SMs available to the overlapped GEMM. Integrated into vLLM as a communication backend, T-CCL improves end-to-end inference throughput over vLLM's automatic backend dispatch by up to 1.31x, outperforming it at every evaluated batch size on both the conversation and decode-heavy workloads. --- ### Verified, not generated: expert-verified AI study materials and the distribution of learning gains in a university course Authors: Canh Thien Dang, An Nguyen Published: 2026-10-05 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2610.07097v1 Experimental studies of generative AI in education mostly report average effects, yet field evidence shows that AI can narrow attainment gaps or widen them. We argue that the direction depends on the judgement burden, the expertise a learner must supply to screen AI output before learning from it, and that expert verification before release moves this burden from students to an accountable tutor. We test the argument in a two-cohort difference-in-differences design in which one half of a compulsory firstyear university economics course received AI-generated podcasts, FAQs and quiz-based study guides, produced with a source-grounded model and checked by a named graduate teaching assistant (170 students; 340 examination marks). Access was associated with a 2.34-mark advantage on a 50-mark component. The share of marks below the upper-second classification boundary fell by 24.7 percentage points relative to the counterfactual, effects were significant at every threshold from 23 to 31 marks and at none above, and roughly three-quarters of the average originated in the bottom quintile. The threshold estimate is robust to removing the lowest-scoring students from the pre-intervention cohort; the average effect is not. Interviews and feedback from 36 students indicate that the verification label gave students a reason to engage with AI-generated material without ending their scrutiny of it. Evaluations of AI learning resources that report only mean effects cannot detect whether the students the resources are meant to help are the ones who gain. --- ### Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads Authors: Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid Published: 2026-10-05 Categories: cs.AR, cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2610.07094v1 LLM deployment is shifting from single-turn completion to agentic trajectories in which a model plans, calls tools, reads results and reasons at test time before acting. This inverts the economics of inference hardware: chat serving amortises weight reads across large batches, whereas agent trajectories are sequentially dependent, run at effective batch one, and make per-token decode latency (TPOT) the dominant term in task completion time. Using a roofline analysis and a closed-form episode-latency model, we show why this regime favours accelerators that keep weights in on-die SRAM (Cerebras WSE-3/3T, Groq/NVIDIA LPU) or compiler-managed tiered memory (SambaNova SN40L/SN50), and why three vendor ecosystems converged in 2026 on disaggregated prefill/decode serving. We show that per-step reliability compounds exponentially in trajectory length-a 2% per-step failure rate erases a 2x decode advantage for a 20-step agent-so determinism and tail latency are first-order performance variables. We then propose a four-layer evaluation framework (silicon, serving system, agent episode, enterprise) with a metric set built on goodput at an agentic SLO and cost per successful episode, a six-axis benchmark protocol over six task families, a paired-bootstrap statistical design, an attestation protocol for vendor-run benchmarks, and TCO, availability and adoption-timing models with explicit break-even conditions. All performance figures are public and labelled by evidence class; we state seven falsifiable hypotheses and the experiments that test them, and argue that the most likely original result is that token-throughput rankings diverge from cost-per-successful-task rankings on long-horizon work. --- ### Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach Authors: Cristian Martella, Angelo Martella, Antonella Longo, Motaz Saad Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07093v1 The rapid proliferation of heterogeneous data sources within the Internet of Things (IoT) across domains such as smart cities, energy management, and environmental monitoring necessitates efficient and scalable data standardization methods. Effective classification of smart data models (SDMs) is essential for facilitating interoperability. However, existing approaches are often limited by high resource consumption and lack applicability in edge environments with constrained computational capabilities. Aiming to bridge this gap, the proposed study evaluates the performance of lightweight open-source language models (LMs) to resolve an input data entity against its corresponding best fitting SDM representation under resource-constrained conditions. It systematically benchmarks a diverse array of models, including general purpose (GP), reasoning-specialized (RS), and code-specialized (CS) architectures, across multiple domain-specific datasets. Addressing the current omission of lightweight, resource-efficient solutions in the literature, the investigation provides significant and valuable insights into model selection, task formulation, and deployment strategies that optimize accuracy and efficiency. A complementary experiment also compares the surveyed large language models (LLMs) against two near-zero-cost similarity baselines (Term Frequency-Inverse Document Frequency (TF-IDF) and a lightweight sentence encoder) on the same task, providing a strong reference point for interpreting the practical value of LLM-based classification on edge platforms. --- ### Smart Content Ingestion for Generative AI Workloads Authors: Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid Published: 2026-10-05 Categories: cs.AI, cs.CL, cs.CV, cs.IR arXiv: https://arxiv.org/abs/2610.07091v1 The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data representation, labels and model architecture were tightly coupled, so data preparation was narrow, schema-bound and visible. Generative AI decouples the model from any single task: one foundation model serves open-ended downstream tasks, and the generality gained on the model side is matched by heterogeneity on the data side, because enterprise knowledge is authored in the formats people use (PDF, presentations, spreadsheets, scanned documents, forms, tables, diagrams and mixed-layout files) that carry textual, visual, geometric and structural information at once. A language model or retriever cannot reason reliably over information misrepresented at this interface, so content extraction becomes a lifecycle stage in its own right whose errors no downstream retriever or re-ranker can repair. This paper presents a production-ready content-extraction system that makes this stage explicit, configurable, and measurable. The system incorporates selective OCR routing, a scarcity-first curation engine with a reference-based extraction scorer that measures character, word, and table-structure accuracy, a deterministic structure-aware parent-child chunker, and a read-only retrieval evaluator that generates grounded questions from every page and reports Hit@k, mean reciprocal rank, and latency. On a 180-document corpus the best extractor scores 97.4 of 100 (character error rate 0.13%, table similarity 0.995) and the chunker reaches hit@1 of 68.6%, hit@10 of 92.8% and MRR 0.77 over 25,050 generated questions. We distil three design principles (structure before semantics, never mutate what you measure, budget your labels) and position measured content extraction as the perception layer of enterprise agentic systems. --- ### Towards a Unified Misuse Monitoring Benchmark Authors: Aniruddh Pramod, James Oldfield, Adel Bibi Published: 2026-10-05 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.07089v1 LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluations treat these threats separately and ask whether a trajectory is harmful, rather than when it becomes harmful. We propose monitoring the agent's responses, where its actions are externalised, and ask whether the first point where monitors identify harm lands within a harm window (from the agent's first harmful commitment to goal execution). We develop a unified formalism for trace-level misuse monitoring and use it to construct a benchmark of ~6,200 conversation transcripts between a user, an LLM agent, and the external environment, spanning both threats in a shared schema, with a labelled harm window, corresponding benign controls, and matched instances of refusals to these requests. Across 17 monitor configurations, we find that our proposed action-framed monitors perform well on both threats under classical metrics (AUC: 0.95 and 0.99 respectively), while content-framed monitors collapse on injection attacks (AUC: 0.52). We also show that classical position-blind metrics paint an optimistic picture of monitor performance, since all monitors localise decomposition attacks poorly under the interval metric, which measures the ability to localise harm. Broadly, we illustrate the need for a unified study of misuse monitoring. --- ### A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture Authors: Aamir Hilal, Shabir Ahmad Sofi, Neeraj Goel Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07087v1 Despite rapid advances in artificial intelligence, reliable real-world plant disease detection remains a persistent challenge. Visual and deep learning approaches have shown promising results, but their deployment under field conditions remains limited. A key bottleneck is the reliance on laboratory-generated datasets that lack environmental diversity, realistic backgrounds, and balanced class distributions, resulting in poor generalization. In contrast, datasets collected directly from agricultural environments capture natural variability and better reflect challenges faced by farmers across regions. This review presents a critical analysis of visual and deep learning approaches for plant disease detection, with emphasis on plant disease datasets. It establishes a taxonomy based on acquisition setting, accessibility, plant diversity, disease composition, class structure, and imbalance severity, and examines their implications for model generalization and real-world deployment. A comparative analysis of laboratory and real-field datasets identifies critical gaps that hinder disease detection. The review further analyzes how multi-level dataset imbalance, including intra-class, inter-crop, and cross-dataset imbalance, and limited environmental variability affect model performance and robustness, an area insufficiently examined in existing surveys. Beyond image-based approaches, it highlights the importance of integrating environmental parameters such as temperature, humidity, and leaf wetness with image data to improve prediction under dynamic field conditions. Finally, the review identifies key challenges, research gaps, and future directions concerning dataset construction, environmental variability, structural imbalance, standardization, and multimodal disease monitoring. It provides a foundation for developing next-generation multimodal frameworks for precision agriculture. --- ### SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding Authors: Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan, Han-Jia Ye Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.07086v1 LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool schemas, a tool-calling model must select tools and generate their arguments, potentially producing multiple calls in a single response. Standard autoregressive decoding generates these calls token by token, incurring substantial latency for requests involving multiple calls or many argument fields. The explicit argument structure offers opportunities for parallel generation, but later argument values may depend on preceding fields and calls, so independently generated values can differ from the target model's output. We present SchemaFill, a framework for efficient LLM tool calling through slot-parallel speculative decoding. SchemaFill generates future slot values concurrently as candidates, without requiring advance knowledge of the actual call sequence or argument values. Candidates spanning multiple fields and calls are concatenated for verification by the target model under the actual output prefix. Only verified tokens are committed, and the target supplies corrections when candidates disagree. This applies target verification while exploiting parallelism across slots and calls. On Glaive and BFCL, SchemaFill achieves up to a 4.05$\times$ improvement in end-to-end throughput over autoregressive decoding. Code is available at https://github.com/Czzzk/SchemaFill. --- ### A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral Authors: Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi Published: 2026-10-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.07084v1 An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that function to the answer received. The difficulty is that observed losses reflect both expert quality and an unfinished correction: early errors can discourage queries that would be valuable after learning. We propose ORUCB, which pools shared and expert-specific polynomial responses. A bound on cumulative response-learning error calibrates confidence-weighted risk regression and exploration, allowing the router to account for this error when deciding which answers to buy. Under bounded residuals and disagreements, a fixed feasible model of optimal responses, and linear models of free and optimal queried risk, the calibrated algorithm achieves high-probability pseudo-regret $O(\sqrt T\log(T+1))$ over $T$ rounds for fixed problem parameters. The guarantee permits singular answer distributions and misspecified shared responses; optimality is relative to the bounded response class. On four test streams, the selected cubic policy has lower fee-inclusive cost than seven baselines that deploy answers unchanged. Comparisons with a common correction learner examine routing, while six-price comparisons measure cost and query rates. --- ### Graph-Based Recognition of Simulated Train-Driver States From Facial and Upper-Body Keypoints Authors: Olivia Nocentini, Marta Lagomarsino, Gokhan Solak, Younggeol Cho, Qiyi Tong, Sara Zeynalpour, Marta Lorenzini, Alessandro Ledda, Arash Ajoudani Published: 2026-10-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.07083v1 Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents a vision-based monitoring system that relies solely on a single front-facing RGB camera and a graph neural network to classify simulated train-driver states into alert, not-alert, and an emergency class comprising acted emergency-like behaviours. To optimize input representations for the model, an ablation study was performed, comparing three feature configurations: skeletal-only, facial-only, and a combination of both. Experimental results show that combining facial and skeletal features yields the highest accuracy (81%) for the three-class model under the light condition, outperforming models that use only facial or skeletal features. Furthermore, the combination of facial and skeletal features achieves 99% accuracy in the alert/not alert classification in light condition. Additionally, we introduced a controlled RGB video dataset containing alert, not alert, and acted emergency-like behaviours recorded under three illumination conditions. These contributions represent a step toward passive and non-contact train-driver state recognition based on facial and upper-body dynamics. --- ### Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin Authors: Zerui Kang, Yishen Lim, Zhouyou Gu, Seungnyun Kim, Seung-Woo Ko, Tony Q. S. Quek, Jihong Park Published: 2026-10-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.07081v2 An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs. We demonstrate a vision-language model (VLM)-guided framework using a Unitree G1 robot and NVIDIA Sionna, with two VLM calls: material classification maps visible materials through ITU-R P.2040 to conductivity priors for Sionna's gradient descent on accumulated received signal strength (RSS) measurements; waypoint planning selects the next measurement location online using residual RSS calibration error and image coverage. In a real indoor scenario, the framework achieves a normalized mean absolute conductivity error of $1.74\times10^{-4}$ within 20 m of travel; random initialization never converges, while random waypoints require over twice the travel. --- ### When Attention Does Not Explain the Peak: Temporal Reference vs. Forecast Output in Attention-Based Time-Series Forecasting Authors: Yuji Akamatsu, Takao Yamanaka Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07080v2 Attention maps are often interpreted as evidence of what a forecasting model uses when making predictions. In our load-forecasting model, a CLS representation of historical demand queries 24 future exogenous horizon tokens through cross-attention, inviting a temporal interpretation in which highly attended horizons may appear to explain forecast peak timing. We test this interpretation using a horizon-level attention descriptor, $Ψ_{\mathrm{out}}$. Across 31 day-aligned windows of the Panama load dataset, the forecast achieves a median peak-time error of 0 h and a 51.6% exact-match rate, whereas the argmax of $Ψ_{\mathrm{out}}$ has a median error of 5 h and 0% exact match. The forecast peak is closer to the observed peak in 27 of 31 windows. This dissociation is not merely an argmax artifact: within $\pm1$ h, attention reaches only $1.16\times$, $1.11\times$, and $1.14\times$ the uniform baseline around observed, predicted, and weekly-naive peaks, respectively, indicating weak and non-selective concentration. Yet the attention profile is structured, with cross-window consistency of 0.83. Replacing 12 future weather features with their training-set means makes the profile nearly uniform, showing sensitivity to future weather variation rather than fixed horizon position alone. The dissociation is also reproduced across three random-seed runs. These results show that structured, input-sensitive, and reproducible horizon-level cross-attention need not provide a valid peak-selective explanation of forecast behavior. The observed behavior is instead consistent with an internal horizon-reference role for integrating future exogenous information, although this functional role is not causally established. --- ### Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity Authors: Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin, Ewa Szczurek Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07079v1 Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently. Meta-learning offers a principled approach to this few-shot setting, but assay heterogeneity may limit its effectiveness. Here, we test this hypothesis and show that meta-learning performance degrades as meta-training tasks become more heterogeneous. To address this, we introduce MetaHeta, a meta-learning framework that accounts for assay heterogeneity by conditioning predictions on auxiliary data from related assays, with relatedness defined flexibly from available assay information. The architecture of MetaHeta combines linear attention over large auxiliary datasets with exact attention over scarce task-specific context, enabling efficient scaling to the former without compromising exact attention over the latter. We demonstrate the benefits of our approach on assays from ChEMBL and BindingDB, improving few-shot bioactivity prediction and downstream compound prioritization in retrospective Bayesian optimization. --- ### What Must Replay Preserve? Separating Correctable Bias from Class Correspondence Authors: BoRen Deng, Xiangyue Ma, Chenglong Li, Xiaoting Du Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.07077v1 Class-incremental learning must recognize all classes seen so far without task labels. Logit replay methods such as DER and DER++ mitigate forgetting by matching the model's past predictions on stored examples. Deleting this matching reveals its benefit, but the resulting accuracy cost cannot show whether the stored scores themselves are needed, or whether the cost survives correction of the classifier's bias toward recent classes. We propose a diagnostic framework that treats a cached prediction as temporally heterogeneous supervision: it separates classes known when an example was stored from classes learned afterward, edits each group, and evaluates every model before and after a task-level offset that leaves within-task predictions unchanged. On CIFAR-100 with DER++, suitable fixed constants replace the unrefreshed stored scores of later-learned classes within an equivalence margin of 1 percentage point, and the offset reduces the cost of deleting their matching from 14.9 to 1.8 points. Reassigning the non-gold scores of classes known at storage, which preserves their values and each task's target probability, costs 4.3 points before and 4.0 after the offset, and a parallel cost persists in image distillation. In the tested fixed-head setting, the large cost of deleting later-class matching is thus mostly correctable by this offset, whereas the smaller cost of disrupting class correspondence persists. Code and data are available at anonymous.4open.science/r/replay-preserve-E22B. --- ### CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration Authors: Yixin Zhang, Wenjie Feng Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.07075v1 High-quality datasets are essential for reliable machine learning, but dataset curation remains costly and hard to generalize across domains. Existing methods typically rely on manually designed heuristics or model-dependent signals, limiting their applicability across tasks and user queries. To address these limitations and automate data curation, we propose \textbf{CuratorMAS}, a multi-agent collaboration framework that orchestrates agents to evaluate and curate high-quality datasets. To achieve the goal of flexible curation, CuratorMAS decomposes the complex curation process into five programmable execution stages and forms a parallelizable workflow. Specifically, CuratorMAS first performs dataset exploration to collect contextual information such as file structures and constraint cues, thereby developing a comprehensive understanding of the given task. In order to acquire up-to-date information, CuratorMAS retrieves domain knowledge from online sources to augment the evaluation process. Next, CuratorMAS derives the necessary evaluation criteria and computes the corresponding metrics. Based on these results, CuratorMAS executes filtering accordingly. Finally, an evolution module summarizes the evaluation outcomes and updates the relevant skills. Extensive and comprehensive experiments demonstrate that CuratorMAS significantly reduces the noise rate by up to 36.03 percentage points (pp) while also improving the F1 score of downstream models by up to 8.88 pp. --- ### Learning Decision-Stump Thresholds in Context: Dynamics of Softmax Attention Authors: Hong Ha Le, Jackie Lok, Atsushi Nitanda, Yan Shuo Tan Published: 2026-10-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.07074v1 Estimating a decision threshold requires locating observations near an unknown boundary. We study how gradient-based pretraining learns this statistical rule in a two-parameter softmax-attention model with a fixed feature and inequality direction. Pretraining uses labeled contexts and their true thresholds; a fresh threshold must be inferred from context alone. Under a large-resolution initialization, constant-step gradient descent on $m$ tasks with $n$ examples each produces a frozen estimator with error $\widetilde O((m\wedge n)^{-1}+N^{-1})$ for each fixed interior threshold and every fresh-context size $N$. The two terms separate finite-pretraining accuracy from fresh-context localization. The mechanism is coordinated parameter divergence: population training calibrates the relative label and feature scores, then increases the attention scale as $t^{1/4}$, giving population threshold error $O(t^{-1/4})$. To transfer this mechanism to a fixed finite corpus, we control gradient errors relative to the shrinking directions of progress at successive parameter scales. This certifies a growing training interval without requiring long-time tracking of the population trajectory. We also identify the boundary limitation of the one-head model and explain statistically what a reflected symmetrization could achieve. --- ### On Color Alignment in VAE Latent Spaces and Its Applications Authors: Julian D. Santamaria, Kai Wang, Jesús Malo, Javier Vazquez-Corral, Alexandra Gómez-Villa Published: 2026-10-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.07072v1 Variational autoencoders (VAEs) are a key part of modern text-to-image models, which generate images within their latent space. VAEs are known to disentangle the main factors of variation in the data, and color is known to be one of the most structured of these in natural images: decorrelating it yields one luminance axis and two opponent-color axes. Color should therefore be expected to emerge as a distinct factor in the VAE latent space. Yet how these latent spaces represent color remains largely unexplored. In this work, we show that the VAEs of text-to-image models share a color subspace aligned with brightness and opponent-colors. Through a linear approximation of the encoder and targeted latent steering, we find this subspace consistently across a broad range of VAEs, from SD1.5 to FLUX.2 and Z-Image. Building on this characterization, we propose three applications: ColorTuning, which achieves state-of-the-art in precise numerical color generation on the fine-grained CSS3/X11 system of GenColorBench, saturation control, to adjust the global chromatic intensity, and color transfer, to change the palette to match a reference. The code and models are publicly available at https://julian075.github.io/Color_Subspace/ --- ### A BEMD-Based Quaternion Filtering Approach Sharp-to-Soft Kernel CT Image Conversion Authors: Mahmoud Nasr, Jan K. Argasinski, Krzysztof Brzostowski, Adam Piorkowski Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07071v1 The quality of computed tomography (CT) images is significantly affected by the selection of reconstruction kernels: sharp kernels improve spatial resolution but increase noise, whereas soft kernels diminish noise at the expense of edge clarity. This study presents an innovative enhancement framework utilising Bidimensional Empirical Mode Decomposition in conjunction with Quaternion Bilateral Filtering (BEMD--QBF) to convert sharp-kernel CT images into representations resembling soft-kernels, while maintaining critical anatomical structures. The technique disaggregates each image into intrinsic mode functions via BEMD and analyzes them inside a cohesive quaternion framework to attain efficient noise reduction and structural integrity. The proposed methodology is evaluated using several reconstruction kernels (B50, B46, B41, B36, B35, B31) and compared with recognised filtering strategies, including Non-Local Means, Anisotropic Diffusion, Bilateral Filtering, and Quaternion Bilateral Filtering. Quantitative evaluations of the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) indicate that BEMD-QBF consistently attains superior structural fidelity and competitive noise reduction across all evaluated kernels. The results underscore the efficacy of the proposed strategy as a viable approach to enhancing post-reconstruction CT images, yielding superior image quality without requiring access to raw projection data. --- ### Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine Authors: Aaron Fainman, Gabriela Kadlecová, Maciej Gryka, Bartosz Kruszczyński, Usman Zafar, Cédric Archambeau, Aaron Klein, David Salinas, Selim Nowicki, Jacek Golebiowski Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.07070v1 Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calling, and fine-tuning them needs per-API data that rarely exists. Existing synthesis methods are too expensive for high-scale fine-tuning, as they often require mock operational environments for different domains and multiple LLM calls per generated conversation turn. We introduce a fully automated, lightweight synthesis framework that models each API as a finite-state machine, representing the system as abstract states that determine when each tool may be called, producing state-valid sequences of tools; sequences are translated into complete examples with a single LLM call. Rather than optimize diversity, we set a target distribution over the number of turns, the tool sequence and task complexity. We measure data quality by fine-tuning SLMs on generated trajectories, showing that our FSM-based generation significantly improves downstream accuracy over an unmutated baseline and, against existing works, reaches 70.7% full accuracy over 63.4% and 53.7% with 3.6-6.6$\times$ fewer tokens. --- ### Decomposition-Guided Curvelet Thresholding for Sharp-to-Soft CT Kernel Conversion Authors: Mahmoud Nasr, Jan K. Argasinski, Krzysztof Brzostowski, Adam Piorkowski Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.07067v1 Image denoising is a crucial task in image processing, focused on improving image quality by minimizing noise while maintaining essential structural elements. This study presents a hybrid denoising framework that combines several decomposition techniques, including empirical mode decomposition (EMD), variational mode decomposition (VMD), multichannel EMD (MEMD), and bidimensional EMD (BEMD), with curvelet transform thresholding. Each decomposition mode undergoes processing through both soft and hard thresholding, and the denoised modes are combined to rebuild the final image. Comprehensive evaluations of standard CT image datasets reconstructed with various kernels (B50, B46, B41, B36) reveal substantial enhancements in denoising efficacy. VMD consistently achieves the highest peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), signifying exceptional noise reduction and feature preservation. The study analyses the trade-offs between soft and hard thresholding: soft thresholding maintains intricate visual details, whilst harsh thresholding provides enhanced noise reduction. The suggested method surpasses traditional techniques in both reference and non-reference quality criteria, indicating its potential for broader application in medical imaging and future incorporation with adaptive thresholding algorithms. --- ### Learning to Simulate Individuals from Macro Social Signals Authors: Yining Zhao, Bushi Liu, Haofei Yu, Zhengyang Qi, Shanyong Wang, Chuyue Li, Yuxiang Liu, Jiaxuan You Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL, cs.SI arXiv: https://arxiv.org/abs/2610.07062v1 Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these responses is either inherited from pretraining or learned from individual-level annotations, which offer limited behavioral diversity and little supervision of the reasoning itself. We propose to learn behavioral reasoning from prediction markets, whose price trajectories record how populations respond to real-world events at scale. We introduce macro2mind, which trains a language model with GRPO using market signals. A social behavioral decomposition makes behavioral reasoning an explicit step of forecasting: the model infers representative groups of market participants, predicts how each interprets the news and updates its beliefs, reasons about their interactions, and aggregates these responses into a price. A hindsight-regret curriculum with difficulty-aware sampling focuses training on transitions where hindsight-identified groups substantially improve the forecast while prioritizing examples that remain learnable for the current policy. The learned reasoning applies to user simulation without further training. On SWM-Bench, macro2mind achieves state-of-the-art directional accuracy and correlation on Polymarket. Trained on market data, it transfers zero-shot to four user-simulation benchmarks (Humanual, OvertonBench, PRISM, and CAD) and has competitive performance among zero-shot methods. Used as a data generator, macro2mind also raises a downstream simulator's accuracy on unseen users by 15.5 points, outperforming data generated by its backbone by 13.2 points. ---