Machine Learning
The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors
Raphaël Minato, Fabrice Popineau, Arpad Rimmel et al. (+1 more)
Monitoring concept drift from an adaptive classifier's error stream creates an operational conflict with the model's own update loop. When internal adaptation outpaces evidence accumulation, accuracy recovers before cumulative detectors (CUSUM, Page-Hinkley) can reach threshold. Instrumenting an Adaptive Random Forest (ARF) shows that surviving trees absorb 98.6% of the post-drift error transient through incremental leaf updates alone. The first background tree swap accounts for just 0.71% of this erased error volume, but drops external detection rates by 31 percentage points. We derive the finite-horizon boundary where cumulative evidence fails to cross threshold and measure a critical magnitude floor ($\Delta e_c = 0.120$) below which false-alarm budgets preclude detection. This failure manifests as missed shifts on stationary streams and false-alarm flooding triggered by internal tree swaps on noisy baselines. We validate on synthetic shifts, ARMA-GARCH series (ProteuS), and tabular
benchmarks (BAF, INSECTS); on the synthetic sweep at a standard threshold, the blind spot appears at $\Delta e \approx 0.25$, showing why classical
benchmarks like SEA ($\Delta e \le 0.21$) failed to reach it.
Read the full abstract ▾
All authors Raphaël Minato, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan
Machine Learning
RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces
Yu-Hsiang Liu, Kuan-Yu Chen, Chih-Sheng Chen et al. (+3 more)
Frozen representations are widely reused for downstream classification, yet each new task typically requires fitting a new predictor. We ask whether the few-shot prediction procedure itself can instead be learned once and reused across
datasets and representation spaces. To study this question, we introduce RepShiftBench, comprising 1,218 encoder–
dataset tasks across text, image, and audio, with separate evaluation of generalization to unseen
datasets, unseen encoders, jointly unseen
datasets and encoders, and unseen modalities. The
benchmark exposes a substantial gap: Logistic Regression fitted independently on each episode outperforms every evaluated in-context learner across all settings. We introduce RepICL, a meta-trained in-context learner that canonicalizes each episode through episodic whitening before prediction. Its inductive variant, RepICL-I, surpasses Logistic Regression in all 12
benchmark settings, while RepICL-T substantially outperforms existing transductive methods. Ablations identify episodic whitening as the primary source of these gains, while showing that it is not a universally beneficial preprocessing step. Across both variants, the gains concentrate on queries for which simple support prototypes favor the wrong class or provide little separation between the true class and competing classes. Transduction provides its largest additional gains when limited support coverage gives a misleading view of class separation. Together, these results demonstrate that a shared few-shot prediction procedure can generalize beyond the representation spaces observed during training.
Read the full abstract ▾
All authors Yu-Hsiang Liu, Kuan-Yu Chen, Chih-Sheng Chen, Meng-Hsuan Chang, Yu-Chen Den, Tien-Hao Chang
Machine Learning
CACFG: Curvature-Aware Classifier-Free Guidance and Optimal Control
Max Collins, Dasith de Silva Edirimuni, Jordan Vice et al. (+2 more)
Diffusion models generate samples by learning to reverse a fixed corruption process, and classifier-free guidance (CFG) is the standard mechanism for conditioning this process on a desired class or
prompt. CFG can be applied at varying guidance strengths, and while higher strengths improve image quality and conditional
alignment, too high a guidance strength can degrade image quality and diversity. Furthermore, CFG violates principled
diffusion sampling dynamics, and existing explanations for why it works despite the violation disagree on the underlying theory or do not extend to deterministic samplers used in practice. We address both these issues. We first frame CFG sampling as a continuous-time optimal control problem, treating the sampling trajectory as a sequence of controls chosen to maximise the probability of the desired condition. Solving the resulting Hamilton–Jacobi–Bellman equation shows that CFG is recovered under specific path costs when using an unconstrained control set. We argue this lack of constraint is responsible for CFG's failure at high guidance strengths, since it permits the sampling path to move arbitrarily far from the current image estimate. To fix this, we propose
curvature-aware CFG (CACFG), which constrains the control set to a hypersphere informed by the Gaussian regularisation used when training variational autoencoders. We show that the control inputs produced by CFG sampling routinely violate this bound, and that across
diffusion models,
datasets, and guidance schedules, CACFG achieves superior generative quality at mid-to-high guidance strengths with a less severe quality-diversity tradeoff than regular CFG.
Read the full abstract ▾
All authors Max Collins, Dasith de Silva Edirimuni, Jordan Vice, Tim French, Ajmal Mian
Computational Engineering
PhaseMatcher: Autoregressive Phase-Set Identification with Spectral Decomposition
Zhonglong Peng, Qiuliang Liu, Chang Chen et al. (+5 more)
Recovering complete phase sets from powder X-ray diffraction (PXRD) is challenging when weak-phase peaks overlap stronger signals. A natural strategy is to identify phases iteratively, removing the contribution of each identified phase from the observed pattern before predicting the next. However, even after a phase is correctly identified, misestimating its contribution can distort the residual and cause subsequent errors. We introduce PhaseMatcher, an autoregressive framework for complete phase-set identification with physics-guided spectral decomposition. After each phase prediction, PhaseMatcher re-estimates the contributions of all selected phases and the residual from the original observation and all selected reference patterns, accounting for physically plausible variation between reference patterns and the corresponding phase contributions in the observation. The resulting residual guides subsequent phase identification, while a separate stopping module determines when the phase set is complete. On synthetic mixtures and controlled mixtures constructed from measured single-phase patterns, PhaseMatcher improves complete-set identification over the evaluated baselines. On PhaseMix-135K, it also estimates contributions and residuals more accurately than scalar subtraction.
Read the full abstract ▾
All authors Zhonglong Peng, Qiuliang Liu, Chang Chen, Geng Zhong, Qi Li, Lihong Wang, Lan Jiang, Shifeng Jin
Computational Engineering
AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation
Zhonglong Peng, Rui Jiao, Chang Chen et al. (+3 more)
Predicting metal-organic framework (MOF) structures from given building blocks requires recovering their positions and orientations in a periodic
crystal. The spatial effects of rotation errors are geometry-dependent and anisotropic. The same angular error can produce different atomic displacements depending on block size, shape, and rotation axis. Angular error alone, without reference to the specific block geometry, therefore cannot fully describe the spatial consequences of a pose error. We introduce AnchorPose, a meso-grained pose generation framework that incorporates this
geometric dependence into its generative representation. It represents each block through a small set of representative atoms, combines their local geometry with the current spatial state, and generates their coordinates with
Bayesian Flow Networks. Known atom correspondences enable rigid
alignment to recover complete building-block poses and return geometrically consistent points to the generation process. This design connects point-level spatial prediction with block-level structural constraints. Geometry participates in the pose state and its prediction, while rigid reconstruction preserves intra-block structure without treating all atomic coordinates as assembly variables. On the MOF
benchmark, AnchorPose improves single-candidate match rates over the compared block-level and all-atom baselines.
Read the full abstract ▾
All authors Zhonglong Peng, Rui Jiao, Chang Chen, Geng Zhong, Qiuliang Liu, Shifeng Jin
Computation and Language
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Zhuokun Chen, Xi Lin, Xiyu Wu et al. (+3 more)
Linear
attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information difficult. Existing chunk-based extensions increase
memory capacity, yet learned chunk-mixing coefficients may remain fixed with respect to input content and therefore cannot adapt historical access to each query. We introduce Hybrid Linear
Attention (HLA), a query-dependent chunk-level
attention mechanism for Gated DeltaNet (GDN). HLA represents each completed chunk as an exact affine state transition and computes content-dependent routing gates from compact, self-attentively pooled representatives. Each gate interpolates the corresponding historical transition with the identity map, controlling both the chunk's additive
memory and its transformation of earlier states. Effective-support regularization further encourages concentrated routing for sparse inference. We evaluate HLA under both pretrained adaptation and from-scratch training. Across Qwen3.5 models from 0.8B to 9B, HLA consistently improves over native GDN and fixed chunk mixing, with gains of up to 5.57 percentage points on LongBench-V2 and 3.97 points on RULER. In a controlled from-scratch 1.3B setting trained for 100B
tokens with a 4K context, HLA also improves RULER performance from 4K to 32K, with gains increasing from 0.83 points at 4K to 4.22 points at 32K. These results demonstrate that query-dependent composition of recurrent
memory improves long-context modeling and remains effective beyond the training context while using compact per-chunk affine summaries. Project page: https://caesarhhh.github.io/hla/
Read the full abstract ▾
All authors Zhuokun Chen, Xi Lin, Xiyu Wu, Jiahao He, Jianfei Cai, Bohan Zhuang
Cryptography and Security
Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay
Tural Hagverdiyev
A tool-using model can follow a malicious instruction even when its credentials are valid. We study whether task-scoped authorization contains the resulting tool execution. Our paired-replay testbed samples a model request once and submits the same action, resource, and arguments to broad bearer, scoped JWT, sender-constrained, and Open Policy
Agent conditions. The frozen main experiment uses 128 scenarios across four tool domains and five local model configurations. Among valid attacked post-exposure decisions, broad-bearer harmful execution ranges from 8.9% to 37.8% across models; all three scoped conditions record zero. The policy changes execution, not the frozen model decision. These results support containment of the tested cross-action and cross-resource consequences under researcher-supplied task authority, not prevention of
prompt injection. A bounded six-task AgentDojo extension preserves native scoring and records 11/24 injected broad-policy attack flags versus 0/24 scoped flags, with utility of 5/24 and 6/24. Low exposure, invalid decisions, and purposive task selection limit that comparison. The primary experiment measures safe continuation rather than final-answer correctness. An empirical-bank fresh-sampling comparison finds no estimation advantage from pairing when scoped outcomes are constant zero. The contribution is a controlled measurement of compromise, enforcement, and continuation, with explicit limits on what each observation establishes.
Read the full abstract ▾
Robotics
Dual-Rate Force-Image Control with Model-Based Orientation Limits for Robotic Ultrasound
Tyler Foster, Qiang Zhang, A B M Tahidul Haque et al. (+1 more)
Robotic ultrasound couples a high-rate contact-force loop with slower, delayed image feedback, so image-guided ultrasound probe rotation can perturb contact force before the resulting image response is observed. We derive a closed-form orientation-rate limit that bounds the modeled rotation-induced estimated-force excursion over a finite horizon while accounting for disturbance rejection by the fast force loop. The limit depends on local contact stiffness, force-loop gains, a conservative rotation-to-force gain bound, the excursion budget, and the prediction horizon. We implement this model in a dual-rate controller with timestamp-based delay reconstruction and joint-torque-based force estimation, and evaluate it on a curved gelatin phantom using paired controller comparisons and component ablations. Relative to unconstrained image guidance, the proposed rate-limited controller reduced first-second root-mean-square (RMS) estimated-force error by 0.40 N while increasing cue-convergence time by 0.94 s. A fixed rate cap near the analytically predicted ceiling produced no resolvable difference in force error and converged 0.32 s faster, indicating that the principal practical value of the model is the rate-design rule rather than online prediction. Delay reconstruction had no resolvable effect at the tested latency. A single-subject popliteal scan demonstrated feasibility, although the image cue was noise-limited on heterogeneous tissue.
Read the full abstract ▾
All authors Tyler Foster, Qiang Zhang, A B M Tahidul Haque, Anh Thu Nguyen
Cryptography and Security
Adaptive-Shot Hybrid Quantum Anomaly Detection for Tactile Internet Security: Reliability-Aware Measurement Allocation Under Resource Constraints
Mubassir Serneabat Sudipto, Shakil Ahmed, Ashfaq Khokhar et al. (+1 more)
Tactile Internet (TI) security analytics must balance reliable thresholded decisions with constrained computational and measurement resources. We study this tension for finite-shot hybrid
quantum anomaly inference and introduce the Adaptive-Shot Variational
Quantum Circuit (AS-VQC) policy. This validation-calibrated policy begins each record at 128 shots and cumulatively escalates through 256, 512, and 1024 shots only when the finite-shot anomaly score remains close to a validation-selected security threshold. The
quantum scorer is evaluated as an off-path security analytics component rather than part of the haptic critical path. Using a 4,875-record CESNET-TimeSeries24-derived aggregate-flow
benchmark, leakage-safe random, entity-group-disjoint, and temporal holdouts, and five trained
quantum neural network (QNN) checkpoints per holdout, the primary AS-VQC-95 (beta = 0.95) policy averages 129.2, 276.9, and 131.2 shots per record, saving 87.4%, 73.0%, and 87.2% of the uniform 1024-shot baseline (Fixed-1024), respectively. The decision disagreement with analytic (exact-expectation) inference is 0.771%, 0.409%, and 0.635%, lower than both the uniform 128-shot baseline (Fixed-128) and a matched-budget shuffled-allocation control. Fixed-1024 remains more decision-stable, establishing a measurable reliability-resource trade-off rather than cost-free equivalence. A more conservative AS-VQC-99 (beta = 0.99) further reduces disagreement while using fewer than 512 average shots across all holdouts. These results show that finite
quantum measurements can be treated as an inference resource and concentrated on boundary-sensitive TI-security decisions while exposing checkpoint-dependent escalation under unseen-entity conditions.
Read the full abstract ▾
All authors Mubassir Serneabat Sudipto, Shakil Ahmed, Ashfaq Khokhar, Samir M. Iqbal
Machine Learning
HiER-BLS: A Hierarchy-Guided and Error-Correcting Robust Incremental Broad Learning System
Gongli Zhang, C. L. Philip Chen and Zhulin Liu
Broad Learning System (BLS) supports analytical training and incremental expansion, but its growth needs guidance on which inputs new blocks should learn from. Weight errors pose a further challenge by displacing learned outputs across class boundaries. We propose HiER-BLS to couple hierarchy-guided representation growth with error-correcting learning. Successive blocks focus on inputs selected by feature importance and correlation while preserving earlier representations. The evolving branch guides encoded learners through subspace size and sample confidence, so its learning experience informs both their feature views and supervision. For finite broad readouts, we show how codeword correlations transform fitted class scores. Prediction preservation depends on the distance from the actual output to the nearest decoding boundary relative to the model's sensitivity to weight errors. Experiments on five image and five tabular
datasets demonstrate improved classification performance over representative BLS variants. Component studies show that hierarchy guidance benefits the encoded branch even when the guiding branch has lower standalone accuracy, with further gains from combining their scores. Longer codes continue to improve accuracy under stronger Gaussian weight errors after clean accuracy has largely saturated.
Read the full abstract ▾
Artificial Intelligence
Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents
Tiffany Gu, Annie Guan, Manshu Huang et al. (+3 more)
Long-running
agents repeatedly call an LLM while retaining most of their document window, evicting old documents, and appending new ones. These rolling updates break exact prefix caching and motivate non-prefix KV-cache reuse with selective recomputation. We show that persistent KV-cache reuse with selective recomputation can be history-dependent: in our rolling-
agent workload, an unchanged
prompt can produce different answers depending on the requests processed before it. At a matched 5% recomputation budget, document-aligned recomputation reduces answer variation across request orders from 69.0% with CacheBlend's
token top-$k$ policy to 26.1%. When each
prompt is evaluated after a different sequence of preceding requests, document-aligned recomputation improves fidelity to full prefill by 34.5-52.5 percentage points over
token top-$k$, while both policies achieve approximately 5.7$\times$ median TTFT speedup. Our ablation study shows that, in our rolling-
agent workload, contiguity is the main factor associated with robust selective recomputation.
Read the full abstract ▾
All authors Tiffany Gu, Annie Guan, Manshu Huang, Nitin Rao, Siddhant Shah, Margaret Capetz
Game Theory
Priority Coordination Games: Hodge Decomposition and a Sharp Design Limit
Zhihao Lin, Jianglin Lan, Anh-Tu Nguyen et al. (+1 more)
In decentralised priority coordination,
agents announce priority levels and a shared resource serves them in decreasing order, as at an unsignalised intersection; the levels form the decision layer of a hierarchical controller. Such interactions are routinely replaced by a potential game, i.e.\ by a common objective, for analysis and design. This paper determines what that surrogate misses, using the Hodge decomposition of the incentives into a potential component, which a common objective can represent, and a harmonic component, which it cannot. For the linear payoff, both components are obtained in closed form on every conflict graph and for every deterministic tie-breaking protocol: in common units, the harmonic energy is the number of conflicts and the potential energy adds the number of adjacent pairs of conflicts. Consequently, for every rationality parameter, the best common-objective model of the
agents' choice log-odds, weighted uniformly over unilateral moves, has a relative squared error of at least $1/(d_{\max}+1)$, where $d_{\max}$ is the largest number of conflicts of one
agent; for an eight-vehicle intersection it is exactly one fifth, for any number of priority levels. Invisible to strict-improvement dynamics, the missed component is, under low-rationality log-linear learning with uniform revision and to leading order, the stationary probability current, and its energy sets the
entropy-production rate. Payoff design cannot remove it: on the complete conflict graph of $N$
agents, under a total-order protocol and with at least three priority levels, every nonconstant rank-based payoff leaves a relative error of at least $1/N$, with equality exactly for affine payoffs.
Read the full abstract ▾
All authors Zhihao Lin, Jianglin Lan, Anh-Tu Nguyen, Yoshinobu Kawahara
Machine Learning
Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Cuong Dang, Hoang Anh Just and Ruoxi Jia
Terminal
agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the supervision horizon, the number of trajectory
tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improves with longer horizons but saturates: on Terminal-Bench, a 12K-
token horizon solves more tasks than 16K ($29\pm0.7$ vs.\ $26\pm0.8$) while requiring 30% less training time. The horizon also shapes
agent behavior: short horizons cause premature termination, intermediate horizons yield productive error recovery, and long horizons induce over-persistence. We analyze this saturation through a bias–complexity bound, in which longer supervision reduces temporal supervision bias but increases finite-sample estimation error from more heterogeneous late-stage histories. Guided by this analysis, we propose selective long-horizon refinement, which first trains on short prefixes and then refines only on continuations that are most likely under the warm-start model. It consistently outperforms full long-horizon training. At 16K, it raises successful attempts from $110\pm2.7$ to $126\pm2.1$ and tasks solved in at least six of eight attempts from $9\pm0.7$ to $14\pm0.6$; with half of the long-horizon data, it still reaches $122\pm2.4$ while cutting training time by 23%. The gains transfer across
benchmarks, from $64\pm2.6$ to $73\pm2.1$ on Terminal-Bench v2.0 and from $137\pm2.7$ to $155\pm2.2$ on OpenThoughts-TBLite. For long-horizon supervision, selecting the right trajectories matters more than training on all of them.
Read the full abstract ▾
Artificial Intelligence
Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation
Dishu Yang, Qi Su, Hongbo Qin et al. (+1 more)
Agentic leaderboards increasingly evaluate systems on public
benchmarks whose task statements and solution-bearing artifacts can remain accessible. We propose a measurement-first audit framework that distinguishes contamination claims according to the evidence required to support them. It separates three channels that require different evidence: training-time exposure, evaluation-time
retrieval, and pipeline/scaffold leakage. Each channel is coded as open, partial, closed, or unknown under a fail-closed rule. Across nine Holistic
Agent Leaderboard (HAL) configurations, none of the 27 channel assessments was coded closed, but incidents were confirmed in four configurations. We then apply the behavioral component of the framework to a reported file-localization gap on SWE-bench Verified, using an outcome-blind, same-repository matched-control design with symmetric
prompt-leakage screening, paired and repository-aware uncertainty analyses, and scorer validation, evaluated on GPT-4.1 and DeepSeek-V4-Flash. Among the 100 pairs retained after symmetric screening and the pair-integrity exclusion, GPT-4.1 showed a $+10.0$-point pair-weighted Top-3
benchmark-associated gap, but the 95% intervals from both the prespecified paired-bootstrap procedure and the post-hoc repository-balanced analysis included zero, leaving the
benchmark-associated gap inconclusive. The reproduction scorer did not pass its validation gate: against consensus human labels, sufficient scorer sensitivity could not be established for either model, and both DeepSeek-V4-Flash firings on correct-gold comparisons were false positives. Without provenance evidence, appropriate controls, symmetric leakage screening, and validated scorers, stronger contamination claims are not warranted. The results do not establish training-data membership, contamination prevalence, or
benchmark-induced score inflation.
Read the full abstract ▾
All authors Dishu Yang, Qi Su, Hongbo Qin, Hansong Zhang
Artificial Intelligence
Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
Dongryeol Lee, Weronika Łajewska, Leonardo Perelli et al. (+1 more)
Large
language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially reducing the cost and time of traditional surveys. However, many existing steering approaches rely on target-domain human data for fine-tuning or prompting that is costly to collect and raises
privacy concerns. In this paper, we study demographic group-level survey simulation, where personas induced from heterogeneous, anonymized public behavioral data condition
agents that simulate responses of individuals from specific demographic groups. We examine whether representative personas can be induced from diverse sources and analyze how the domain, scale, and granularity of the source data affect survey simulation
alignment. We find that personas induced from out-of-domain sources rarely outperform simulations conditioned only on basic demographic information, largely due to population mismatch. However, when personas are accurately assigned to the target demographic groups,
alignment improves substantially. Finally, personas induced from target-domain survey data generalize better as more survey question history becomes available, suggesting that richer behavioral evidence enables more stable persona trait inference that transfers to better unseen questions simulation
alignment.
Read the full abstract ▾
All authors Dongryeol Lee, Weronika Łajewska, Leonardo Perelli, Saab Mansour
Cryptography and Security
Bounded Provisional Visibility: Controlling Poisoning Exposure in Continuously Ingested RAG Vector Stores
Chuhong Xu, Lu Yi, Gangzhen Qian et al. (+3 more)
Continuous ingestion can expose new
retrieval-augmented generation (RAG) content to
retrieval before vetting completes, creating a temporal attack surface that conventional admission decisions do not capture. We present a fail-closed provisional-visibility protocol that admits new content under a deadline, hides items whose verification has not committed in time, and supports lineage-scoped containment. The protocol bounds unvetted exposure by the configured visibility budget plus query-path enforcement delay; poisoning exposure remains conditional on verifier correctness. We evaluate the design on five workloads of encoded natural-
language documents using an exact backend and Milvus. Under verifier backlog, the deadline reduced median poisoned
retrievals from 34 (29–34) to 7 (6–7) relative to asynchronous admission without a deadline, with the same reduction in displaced clean results. Verify-before-visible avoided provisional exposure but delayed clean first visibility to 6.3 s, whereas provisional admission made content visible within 3 ms; expired clean items could nevertheless experience temporary availability gaps. Replaying decisions from a recipe-specific detector illustrated the protocol boundary: false promotions left poison visible, while false refusals excluded clean content from
retrieval. Standalone Milvus tests characterized enforcement delay and concurrent HNSW
retrieval on one node. These results clarify which guarantees come from the protocol and which outcomes depend on detector quality, while quantifying the freshness and availability trade-offs.
Read the full abstract ▾
All authors Chuhong Xu, Lu Yi, Gangzhen Qian, Kainan Zhou, Zhaoyi Li, Hang Xiao
Machine Learning
Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data
Abu Talha, Peng Liu and Souradyuti Paul
Classification problem in the context of highly imbalanced data is a major challenge in many real-world applications (e.g., FinTech, healthcare, etc.). In these cases, the vast majority of instances belong to a single class and a small fraction represent the minority class (often the most critical class). Recently,
diffusion models have emerged as powerful approaches to reduce the degree of “imbalanced-ness” in the
dataset; they work by generating synthetic data by capturing complex data distributions using iterative transformations. However, standard
diffusion models are not inherently suited to highly skewed or heavy-tailed data, due to inbuilt quadratic error loss, which lacks the structural sensitivity to capture rare, extreme values, and minority-class nuances. We propose a novel approach, namely,
Quantile-TabDDPM, based on a
quantile-regularized denoising objective that combines the standard quadratic error loss with a
quantile loss term to explicitly capture rare events while preserving the theoretical grounding of the original denoising objective. We extensively evaluated our approach on a real-world credit card transaction
dataset characterized by extreme class imbalance. The results demonstrate that the integration of
diffusion-based synthetic data generation with a
quantile-regularized denoising objective provides a robust and effective framework for fraud detection in highly imbalanced
datasets.
Read the full abstract ▾
Multiagent Systems
Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation
Haonan Huang and Joey Xiao
Personal AI assistants are beginning to transact for consumers, and early adopters capture real savings. Whether those savings survive, and what happens to consumers who have no assistant, depends on how sellers respond – a question single-user evidence cannot answer. We build an
agent-based rental
market in which
language models play consumers, assistants, and six adaptive sellers guided by an algorithmic pricing tool. Half the population receives an assistant under an advisory or an executing mandate; the contract pairs a fee only the renter's physical action avoids with a pre-selected add-on an authorised assistant can cancel online. An analytical
benchmark and a behaviourally calibrated rule
market supply ex-ante predictions, and paired branches with frozen versus adaptive sellers separate adoption effects from
market feedback. Across thirty simulated
markets, executing assistants cut adopters' spending by 13.7 USD per renter-day when sellers are frozen; adaptation claws back about a third, leaving 8.7, with the gains arriving both as lower bills and as rentals completed at all. Sellers raise headline rates while cutting fees, and the calibrated forecast of the burden on unassisted consumers (+3.6) does not transfer: their mean spending change is +0.4, confidence interval -0.6 to +1.3. Seller-model swaps and a within-
market transfer of fee-setting to the pricing tool show that fee conduct, and with it the division of the gains, is decided on the seller side. Assistants, we conclude, should be evaluated at
market level – completion, total spending, and non-users included – and the comparison layers locate exactly where a calibrated behavioural forecast fails in a
language-model
market.
Read the full abstract ▾
Human-Computer Interaction
Supporting Couples' Social Well-being in Daily Life: A Needs Assessment and Co-design with Co-located Couples
Yuna Naito, Timothy Bickmore, Varun Mishra et al. (+1 more)
Romantic relationships shape physical, mental, and social well-being, and relationship quality is built through everyday interactions. Addressing minor issues early and reinforcing positive interactions help maintain relationship quality, and ubiquitous computing creates new opportunities to sense and support couples' relationships in daily life. However, existing systems remain largely developed with limited involvement from couples, raising questions about which types of sensing and support couples may accept in their private lives. To address this gap, we conducted exploratory needs-assessment interviews and co-design sessions with five co-located couples (10 participants) to identify their needs and preferences for relationship-attunement-enhancing technologies, including the use of LLMs. Couples' own designs converged on systems that detect meaningful moments—such as conflict onset—and offer subtle mediation rather than AI-generated advice, highlighting dyadic concerns around partners' agency, authenticity, and control over shared interaction data. We offer preliminary design implications for ubiquitous sensing and intervention systems that center the couple as a unit rather than the individual.
Read the full abstract ▾
All authors Yuna Naito, Timothy Bickmore, Varun Mishra, Matthew S. Goodwin
Numerical Analysis
Entropy-Stable and Well-Balanced Discontinuous Galerkin Methods for the Compressible Euler Equations in Vector-Invariant Form
Marco Artiano, Kieran Ricardo, Oswald Knoth et al. (+2 more)
We develop structure-preserving methods for the compressible Euler equations with
gravity in vector-invariant form and potential temperature as a prognostic variable within the flux-differencing discontinuous Galerkin spectral element method (DGSEM) framework. By discretizing the nonconservative terms as symmetric and antisymmetric products, we derive two-point numerical fluxes that conserve both the thermodynamic
entropy and the total energy. Moreover, we design an
entropy-stable numerical flux that is well-balanced for both isothermal and isentropic background states. All properties are shown to carry over to the high-order DGSEM on general curvilinear meshes. Several numerical examples confirm the theoretical findings and show the robustness and accuracy of the scheme for use in modern dynamical cores for atmospheric flows.
Read the full abstract ▾
All authors Marco Artiano, Kieran Ricardo, Oswald Knoth, Peter Spichtinger, Hendrik Ranocha
Robotics
Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement Learning
Nobuo Namura, Masayuki Hiromoto, Kento Uemura et al. (+2 more)
Transporting unsecured payloads with legged
robots over uneven terrain requires balancing locomotion performance and payload stability, since aggressive motion can destabilize the payload even when the
robot remains stable. We study quadrupedal transportation of unsecured stacked boxes on an edgeless torso-mounted board without dedicated payload sensors or active carrier mechanisms. To address this trade-off, we propose Payload-Adaptive Multi-Objective Reinforcement learning for Transportation (PAMORT). PAMORT trains a multi-objective base policy conditioned on a preference vector that weights locomotion and payload-stability reward groups, then trains a weight adjuster on the frozen policy to adapt this preference online from proprioception. In simulation, PAMORT achieves comparable or better overall transportation success than a corresponding single-objective baseline across different payload configurations, including an unseen three-box stack, despite training only with two boxes. Real-world experiments on a Unitree Go2 demonstrate zero-shot transfer to slopes and steps at or beyond the training difficulty, with mean success rates of 0.850 for PAMORT and 0.675 for the baseline across eight tasks. These results demonstrate robust unsecured-payload transportation with online adaptation of the locomotion–payload trade-off from proprioceptive information.
Read the full abstract ▾
All authors Nobuo Namura, Masayuki Hiromoto, Kento Uemura, Hironobu Sasaki, Kanata Suzuki
Robotics
What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions
Sripad Karne and Arjun Balaji
Vision-
language-action models (VLAs) act on instructions without being able to refuse, so screening harmful requests falls to monitors. We test whether these monitors catch ordinary
robot tasks requested for harmful reasons, holding the task fixed while varying only how explicitly the intent is stated. $\pi_{0.5}$ completes the task at every level of explicitness, as often as for harmless controls. Text guards flag nearly every blunt request but few implied ones: up to 95% of implied-harm runs end with the task done and no flag raised, and up to 90% even after recalibrating on
robot instructions. Monitoring the model's activations does not close this gap. Linear probes separate harmful from harmless instructions almost perfectly in the base
language and
vision-
language models, but this separation weakens after
robot training in two model families, most for implied harm.
Read the full abstract ▾
Artificial Intelligence
Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation
Alireza Jafari, Arman Adibi, Mohammad Ghavamzadeh et al. (+1 more)
Text revision has become an integral component of large
language models. This paper formulates revision such that it admits a Nash
equilibrium:
Token positions are players, vocabulary items are actions, and each player's utility is the
language model's log conditional probability. We motivate the revision by showing that Nash
equilibria can have exponentially higher likelihood than autoregressive outputs as the sequence length grows. We further propose Nash decoding, an
algorithm that reaches an $\varepsilon$-Nash
equilibrium in $O(1/\varepsilon)$ time given access to the joint probability of
tokens conditioned on a
prompt. In practice, we run Nash decoding using conditional probability estimates from large
language models and evaluate the resulting
equilibria on question-answering
benchmarks. On CLAPNQ, PubMedQA, and CoQA, Nash
equilibria obtained from masked
language models achieve higher F1 and ROUGE scores than autoregressive models up to $18\times$ larger, without any fine-tuning or retraining, at the cost of additional test-time computation.
Read the full abstract ▾
All authors Alireza Jafari, Arman Adibi, Mohammad Ghavamzadeh, Hadi Daneshmand
Computer Vision
Kiyohiro Nakayama, Brian Chao, Jan Ackermann et al. (+5 more)
Image and
video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatial distribution of detail can often be anticipated before generation, indicating where computation can be reduced. We introduce Level-of-
Token (LoT)
Diffusion, a framework that turns this knowledge into an explicit multiresolution
token layout (Level-of-
Token layout) for adaptive and efficient generation.
Tokens represent rectangular patches of varying sizes and shapes, allocating finer
tokens where detail is needed and coarser
tokens elsewhere. We adapt pretrained
diffusion transformers to LoT layouts through a patch-wise asymmetric flow parametrization and
embeddings for multiresolution
tokens, preserving full-resolution flow prediction at every denoising step while processing only a reduced
token sequence. LoT
Diffusion enables layout-adaptive generation while preserving pretrained generative priors. We demonstrate LoT with layouts derived from semantic masks, bounding boxes, texture variance, and depth-of-field cues, as well as agentic plans. Across image and
video generation, LoT offers favorable quality-efficiency tradeoffs, with significant speedups determined by the layout's
token budget. Our project website is at https://georgenakayama.github.io/lotdiffusion/.
Read the full abstract ▾
All authors Kiyohiro Nakayama, Brian Chao, Jan Ackermann, Hansheng Chen, Federico Tombari, Leonidas Guibas, Lior Yariv, Gordon Wetzstein
Computation and Language
Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows
Miaohe Niu, Pengxiang Li, Jingbo Zhu et al. (+1 more)
Continuous
language flows generate text by denoising all positions of a target canvas together. The natural way to add
reasoning to such a model is to write a trace ahead of the answer, but the trace length changes from question to question. The answer start is therefore unknown during denoising, and the model has to decide the trace length, the place of every trace
token, and the answer at the same time. We propose Plan Canvas to fix the boundary between the trace and the answer. A plan region of fixed capacity holds a compact trace, supervised padding fills its unused positions, and the answer starts at a fixed position. The fixed regions also allow separate denoising clocks for the plan and for the answer. With the trace text, backbone, and canvas length of the free-trace baseline held fixed, Plan Canvas improves accuracy on ProsQA and on Deep ProsQA, a graph
benchmark with longer proofs. On Deep ProsQA, accuracy rises from 73.0% to 87.0%, the share of questions answered with a valid path rises from 30.8% to 59.1%, and the gain is largest on the longest proofs.
Read the full abstract ▾
All authors Miaohe Niu, Pengxiang Li, Jingbo Zhu, Tong Xiao
Information Theory · Cross-listed from math.AC
Polynomials with restricted support and maximal zeros on a finite Cartesian set
Dipak K. Bhunia, Eduardo Camps-Moreno, Ignacio GarcÍa-Marco et al. (+2 more)
Given a finite Cartesian set $S=X \times Y$ and a decreasing set of monomials $\mathcal M$, we call extremal
polynomials for $\mathcal M$ over $S$ those that have the maximum number of zeros in $S$ and whose support belongs to $\mathcal M$. Coordinate factorizations give a family of extremal
polynomials; we call them canonical. If $\max(\mathcal M)$, taken with respect to divisibility, is a single monomial, all extremal
polynomials are canonical. If $|\max(\mathcal M)|=2$, either all extremal
polynomials are canonical, or the problem reduces to the case where $\max(\mathcal M)=\{x^{d_x},y^{d_y}\}$. In the latter case, we prove that the existence of noncanonical extremal
polynomials depends on finding families of subsets whose elementary symmetric functions agree. This condition is more restrictive than the classical Prouhet–Tarry–Escott problem, which asks for two sets whose elementary symmetric functions agree. We determine the number of triples $(X, Y, h)$, where $h$ is a quadratic noncanonical extremal
polynomial. We apply extremal
polynomials to coding theory via minimum-weight codewords.
Read the full abstract ▾
All authors Dipak K. Bhunia, Eduardo Camps-Moreno, Ignacio GarcÍa-Marco, Hiram H. López, Irene Márquez-Corbella
Machine Learning
Feature identification for parameter extraction and defect detection using machine learning
Yan Guo, Helda Pahlavani, Artem Khachaturiants et al. (+5 more)
Process control of advanced
semiconductor nodes is not only pushing the limits of metrology equipment requirements in terms of resolution and throughput but also in terms of the richness of data to be extracted to enable engineers to finetune the process steps for increased yield. The move towards 3D structures requires extraction of critical dimension parameters from structures which can vary largely from layer to layer. For in-line process control, the necessary automation forces the development of layer and equipment-specific dedicated image processing
algorithms. Similarly, with the increase in
stochastic defects in the EUV era, detection of defects at the nm scale requires the identification of features captured in low resolution to meet the throughput requirements of HVM fabs, which can again lead to custom
algorithm development. With the emergence of ML-based image processing methods, this process of
algorithm development for both cases can be accelerated. In this work, we provide the general framework under which the images obtained from high-speed scanning probe microscopy-based systems can be used to train a network for either feature detection for parameter extraction or defect identification.
Read the full abstract ▾
All authors Yan Guo, Helda Pahlavani, Artem Khachaturiants, Khalid Elsayed, Jakob van de Laar, Erik Simons, Niranjan Saikumar, Hamed Sadeghian
Systems and Control
Public Battery Field Data
Robert Masse
Battery systems and
algorithms are developed and evaluated primarily on laboratory cycling data, but fielded battery systems are subjected to duty cycles, temperatures, and measurement conditions that cannot be reproduced in a lab. Field data from batteries in service has begun to appear in public releases attached to individual papers, but each release has its own format, units, labels, and other gaps that make it difficult to compare against others. We present a curated collection of 35 public field-data releases from 27 research groups, covering applications that span passenger EVs, buses, light electric mobility, grid-scale storage, distributed storage, consumer electronics, industrial robotics and satellites. Where the releases are complete enough to measure, this heterogeneous collection contains 256 GB of data from at least 149,188 lithium-ion
cells, 3,187 batteries, 115.6 MWh of energy storage capacity, and 3,040 unit-years of service. Critically, it also contains 6,465 labeled or reported faults, which provide greater visibility into what real battery performance and safety issues look like outside the lab. We release a public repository of metadata and code for each of the field
datasets. For each
dataset it provides a registry entry with sources, license and access links, checksums to confirm a download is complete, a metadata table, and code for how to load it. We also report where released
datasets differ from their papers. We hope the collection can help serve researchers (human or otherwise) as a useful platform for improving battery field diagnostics, fault detection and health estimation. Better field evidence can also feed back to improve manufacturing quality, inform second-life screening and residual-value estimates, and broadly accelerate electrification.
Read the full abstract ▾
Cryptography and Security
Online AutoML: Evaluating Poisoning Attacks on Cost-Utility Adversarial Training Defence Strategy for IoT Networks
Chukwunonso Henry Nwokoye, Khalil El-Khatib and Li Yang
Machine learning (ML)-powered poisoning attack vectors are
adversarial maneuvers whereby an attacker intentionally inserts, corrupts, or alters training data to distort an ML model's learning process. The objective is to diminish model efficacy, instill biases, induce misclassifications, or include concealed
backdoors that may be attacked during implementation. In streaming contexts, poisoning attacks pose significant risks since models perpetually update based on incoming streams of data. An assailant may incrementally introduce harmful samples into this data stream, leading the model to assimilate erroneous features over time without timely identification. Therefore, this study is aimed at evaluating the efficacy of the
adversarial training (AT) defense approach against poisoning attacks (label flip and noise injection) using an online AutoML pipeline for Internet of Things (IoT) networks. Specifically, poisoning attacks (label flip and noise injection) were applied to streaming-capable AutoML learners (Hoeffding Tree (HT), Leveraging Bagging (LB), Adaptive Random Forest (ARF), Hoeffding Adaptive Tree (HAT), and Streaming Random Patches (SRP)). Under the strongest poisoning rate (PR = 1.0), AT-SRP achieved the highest F1-score against label flip poisoning (0.904), while AT-LB achieved the highest F1-score against noise-injection poisoning (0.933). Finally, several drift detection methods were used for rolling accuracy and prequential evaluation.
Read the full abstract ▾
Machine Learning
Image resolution enhancement for advanced semiconductor nodes
Lucas Rencker, Omid Tajalizadehkhoob, Khalid Elsayed et al. (+7 more)
Advanced
semiconductor nodes are pushing the limits of feature sizes and require metrology with sub-nm resolution without compromising on the throughput as needed for in-line process control. Recently, high-throughput scanning probe microscopy (SPM) based metrology and inspection tools capable of meeting these needs have been introduced to the
market and qualified for use in HVM. While innovative measurement methods and tool architecture have allowed for a leap of improvement in throughput, the next step in further reducing imaging time can be obtained through the application of machine learning for enhancing the resolution of measured images for extraction of relevant parameters. In this work, we provide the general framework under which a neural network-based resolution enhancer is designed and used for SPM images. We showcase the effectiveness of this framework using measurements performed on Line/Space structures with a pitch of 200 nm. For the reusability of a pre-developed pre-trained model, we additionally leverage transfer learning and show that a new model for slightly differing structures can be re-trained and calibrated with a smaller data set of measurements performed on Line/Space structures with a pitch of 100 nm.
Read the full abstract ▾
All authors Lucas Rencker, Omid Tajalizadehkhoob, Khalid Elsayed, Artem Khachaturiants, Helda Pahlavani, Yan Guo, Jakob van de Laar, Erik Simons, Niranjan Saikumar, Hamed Sadeghian