Machine Learning · Cross-listed from eess.AS
$TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
Parampreet Singh, Anushka Singh, Sumit Kumar et al. (+1 more)
Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted. Post-hoc confidence estimation addresses this by training a lightweight auxiliary head over a frozen classifier. Existing targets, however, suffer from inherent ambiguity: they assign overlapping confidence values to correct and incorrect predictions, while errors near the decision boundary receive confidence scores indistinguishable from correct predictions. In this work, we propose $TCP_\alpha$, a novel confidence target that resolves these limitations by introducing a margin-controlled penalty for misclassified samples. We prove that $TCP_\alpha$ guarantees complete separation between the target values of correct and incorrect predictions, with a separation margin that is independent of the number of classes and increases monotonically with the penalty parameter. Since accurate classifiers naturally produce very few errors, learning these targets results in a severely imbalanced regression problem. We therefore present a systematic study of training strategies for learning under this imbalance and identify an effective training configuration through extensive ablation studies. We evaluate the proposed approach on rāga identification, investigate its robustness under domain shift, and further validate it on frame-wise ornamentation detection without modifying the selected configuration. Across all settings, $TCP_\alpha$ consistently outperforms existing confidence targets for failure prediction. Rejecting only the least-confident 8% of predictions improves the base model's macro-F1 from 0.89 to 0.98, while fine-tuning the confidence head with only 5% labeled samples from a new corpus effectively restores performance under domain shift.
Read the full abstract ▾
All authors Parampreet Singh, Anushka Singh, Sumit Kumar, Vipul Arora
Machine Learning
A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
Anton Lambrecht, Reda El Hail, Xianjun Jiao et al. (+5 more)
Despite their growing importance for contact-free
radio frequency (RF) based healthcare monitoring, different
radio technologies such as frequency-modulated continuous wave (FMCW) radar, impulse
radio ultra-wideband (IR-UWB), and Wi-Fi sensing are rarely compared under identical deployment conditions, as existing studies typically differ in hardware,
datasets, and evaluation methodologies. In addition, the performance of ceiling-mounted radars, despite their practical deployment and cost advantages in healthcare environments, remain underexplored. Therefore, this paper presents a controlled comparison and analysis of ceiling-mounted FMCW, IR-UWB, and Wi-Fi sensing using synchronized recordings from 20 participants across six room layouts. All technologies are evaluated with the same convolutional neural network (CNN) on both a fine-grained 10-class human activity recognition (HAR) task and a coarse 4-class sleep monitoring task. IR-UWB achieves the highest cross-subject activity recognition performance (89.0% macro F1), while FMCW generalizes best to unseen room layouts (83.8% macro F1). For sleep monitoring, all technologies exceed 92% macro F1 in unseen environments. The results reveal a fundamental trade-off between recognition performance and environmental robustness, which can be explained through differences in range resolution,
antenna diversity, Doppler resolution, and spatial information retention. These findings provide practical guidelines for the design of healthcare-oriented RF sensing systems.
Read the full abstract ▾
All authors Anton Lambrecht, Reda El Hail, Xianjun Jiao, Pieter Crombez, Dominique Schreurs, Peter Karsmakers, Adnan Shahid, Eli De Poorter
Artificial Intelligence
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
Narges Ahmadi, Yubo Jiao, Jônatas Augusto Manzolli et al. (+2 more)
Travel behavior research increasingly combines digital data collection with predictive modeling, yet these stages are often developed and evaluated separately. This study proposes a three-
agent workflow integrating conversational data collection, structured data processing, and behavioral prediction. A chatbot-administered, image-augmented stated-preference survey collected mode choices from student commuters across five predefined weather scenarios, yielding 454 respondent-scenario observations. Weather-related associations were analyzed using a multinomial logit model, while logistic regression and random forest provided machine-learning
benchmarks. Nine locally deployed large
language models (LLMs), ranging from 2 to 35 billion parameters, were evaluated across four zero-shot
prompt-and-context conditions and extended through persona, few-shot, and
vision-based configurations. Random forest achieved 69.6% five-class accuracy, while the best text-only zero-shot LLM reached 69.9% without task-specific fitting. Habitual travel information produced the most consistent gains, Expert framing generally outperformed Role-Play, and persona information was most useful when habitual travel information was unavailable. Few-shot prompting improved prediction for several models, with gains stabilizing after a small number of examples. Using the same weather images shown to respondents, the best
vision-based configuration reached 71.5% five-class accuracy, indicating that visual context may provide additional predictive information for selected models. Overall, the study shows how conversational surveys, structured data processing, conventional behavioral modeling, machine learning, and
multimodal LLM prediction can be coordinated within an auditable multi-
agent workflow.
Read the full abstract ▾
All authors Narges Ahmadi, Yubo Jiao, Jônatas Augusto Manzolli, Jiangbo Yu, Luis Miranda-Moreno
Computation and Language
Inducing Task Models from Computer-Use Traces
Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen et al. (+1 more)
Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable models of how everyday work is done. Such models matter as computer-use
agents enter real work, where
agents need to learn how tasks are actually performed, and organizations need to audit and reuse that knowledge. However, inducing such task models is challenging, as activity is observed only as low-level events and real-world work is multi-threaded with interleaved goals. Existing methods assume a given task or a single workflow, and produce step-level summaries rather than structured task models. We introduce Task Model Induction (TMI), which (i) discovers the latent tasks in an unconstrained trace, disentangling concurrent activity, and (ii) for each latent task, induces a task model pairing a hierarchical objective model of recursive goal decomposition with a procedure model of the control flow that organized the execution. Intrinsically, on controlled human and
agent trajectories, TMI recovers interleaved tasks with 0.974 agreement against ground-truth groupings and reconstructs 74.9% of the observed execution steps, far more than the strongest workflow induction baseline. Extrinsically, skills derived from TMI's task models improve held-out task accuracy by 30.0% over the strongest baseline.
Read the full abstract ▾
All authors Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen, Diyi Yang
Artificial Intelligence
AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
Yizhe Chi, Wenyi Li, Deyao Hong et al. (+7 more)
Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That process is the training
algorithm: a better objective or update rule improves the compute\mbox{-}capability exchange rate for every subsequent run, including the one that produces the next
agent. Whether RSI is feasible therefore turns on whether an
agent can design training
algorithms. No
benchmark isolates that ability: existing suites are won by collecting data or by tuning hyperparameters, and none tells a change to how a run is executed apart from a change to how the model learns. We present AI4AI\mbox{-}Bench, 10 frozen research repositories spanning 10 training
algorithm families. In each task, an
agent has 4 hours on one B300 to rewrite the training
algorithm; its code is then rerun from scratch for up to 12 hours and scored by a fixed evaluator hidden from the
agent, against the repository's original
algorithm under the same procedure. Because the 10 metrics are incommensurable, every task is mapped onto one scale on which $0$ is an uninformative model, $0.1$ is the
algorithm the repository ships, and $1.0$ is the task optimum. Across 29 configurations of 6 systems on all 10 tasks the mean score is $0.166$, and the best system reaches $0.250$: even the strongest closes under a fifth of the distance between the
algorithm that was already there and the optimum. The submissions show where that distance went: most never change how the model learns at all, and the minority that do average $0.226$ against $0.126$ for the rest. More
reasoning effort mostly buys the willingness to go there, taking that minority from $8\%$ of submissions to $64\%$ and the mean score from $0.094$ to $0.196$. We release the task suite, the evaluators and every scored submission, so that the measurement can be repeated as these systems change.
Read the full abstract ▾
All authors Yizhe Chi, Wenyi Li, Deyao Hong, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, Bingxiang He, Youjie Zheng, Calvin Xiao, Qinhuai Na
Information Retrieval
CMASS: A ClimbMix Agentic Search Suite for Evaluating Search Agents Across Heterogeneous Tasks
Sahel Sharifymoghaddam, Lingwei Gu, Yijun Ge et al. (+1 more)
Evaluating advances in agentic search requires testing whether methods generalize across tasks and corpus scale. Changing web search services impede controlled comparisons, while small corpora assembled around
benchmark questions provide a limited test of generalization. We introduce CMASS, the ClimbMix Agentic Search Suite, which projects three search
benchmarks—BrowseComp-Plus, Total Recall QA, and DeepSearchQA—and the multi-hop question-answering
dataset HotpotQA onto a shared, fixed corpus. The target, ClimbMix, is a pre-training corpus of 553M documents and approximately 400B
tokens, assembled independently of the
benchmark questions. Our projection pipeline verifies grounding, answer uniqueness, and set completeness through independent
agent audits, controlled revision, and human review. The 423 questions span entity identification, multi-hop
reasoning, exhaustive answer sets, and aggregation. Evaluations of three models expose substantial headroom for open-weight
agents and show that high answer accuracy can coexist with incomplete evidence coverage. By enabling measurement of accuracy alongside evidence coverage, search effort, and closed-book performance, CMASS supports developing
agents that find sufficient evidence and produce complete answers efficiently. The pipeline code and
dataset are available at https://cmass.tech
Read the full abstract ▾
All authors Sahel Sharifymoghaddam, Lingwei Gu, Yijun Ge, Jimmy Lin
Artificial Intelligence
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
Adam Fisch, Shubhendu Trivedi, Fantine Huot et al. (+5 more)
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost. Routing requires estimating each specialist's expected return, but this value estimation has a cost. Cheap
estimators (e.g.,
embedding-based predictors) are fast but noisy, while accurate
estimators (e.g., fine-tuned models with access to
retrieval results or partial
reasoning traces) are expensive. We formalize this tradeoff as an instance of Pandora's Box, the classical problem of optimal search with costly inspection. Under a Gaussian signal model, the resulting policies have closed-form value-of-information expressions that determine, for each specialist and input, whether refining the value estimate is worth its cost. We call the centralized policy Pandora's Router. We extend this to a decentralized setting, Pandora's Bidder, where specialists independently decide whether to invest in self-assessment before accepting an offered price to claim a query. Experiments across three domains—a standard multi-LLM
benchmark,
retrieval-augmented specialists, and LLMs with variable inference-time
reasoning—show that Pandora's Router matches the routing quality of exhaustive estimation, while querying the expensive
estimator far less often. In the decentralized setting, value-of-information
reasoning improves allocative efficiency when competing estimates are accurate; when competing estimates are noisy, however, it can increase the strategic specialist's utility at the expense of others.
Read the full abstract ▾
All authors Adam Fisch, Shubhendu Trivedi, Fantine Huot, William W. Cohen, Michael Kaisers, Mirella Lapata, Kate Larson, Jacob Eisenstein
Machine Learning
Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records
Jun Ni Du, Lukas Adamek, Maxim Kryukov et al. (+4 more)
Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized quantitative laboratory information and interpretability with respect to input medical events. We present BERT-LER, a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR
dataset of 75 million patients, that encodes laboratory test results as discrete
tokens while retaining graded information through percentile-based binning, paired with Integrated Gradients for
token-level attributions grounded in the input EHR sequence. We
benchmark our approach on the public EHRShot
benchmark suite and on an asthma severity progression study based on real-world data. This addresses a methodological gap in EHR foundation-style modeling by unifying laboratory value representation and explainability in a single framework, while assessing whether both predictive performance and explanations generalize beyond standard clinical prediction tasks. Across EHRShot and asthma tasks, BERT-LER achieves predictive performance that is competitive with, and on laboratory-related tasks often exceeds, publicly available
benchmark models, and provides attributions that align with clinically known risk factors. Our architecture and explainability approach can be applied to many therapeutic areas and prediction tasks using
language models trained on structured EHRs.
Read the full abstract ▾
All authors Jun Ni Du, Lukas Adamek, Maxim Kryukov, Flavio Dormont, Ziv Bar-Joseph, Sven Jager, Brandon Rufino
Artificial Intelligence
MidTool: Mid-training Data Synthesis for Agentic Tool Use
Fengqing Jiang, Yite Wang, Boyi Liu et al. (+5 more)
Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large
language models. Recent work has shown that targeted mid-training can strengthen
reasoning-intensive abilities such as math and science, and can also improve agentic capabilities in software-engineering settings. In this work, we study the parallel but less explored agentic capability: general tool use. We present MidTool, an open corpus construction pipeline for agentic tool-use mid-training that combines large-scale web, PDF, and code data with synthesized supervision from real-world tool APIs, MCP skills, and document-grounded workflows. MidTool is designed to teach models how to recognize tool affordances, ground arguments from context, compose tool call workflow, and recover from incomplete information. We mid-train Qwen3-4B-Base and Qwen3-8B-Base on MidTool-Mix, and then apply follow-up post-training with both supervised fine-tuning and reinforcement learning. Compared with baselines, MidTool-Mix consistently improves downstream performance under both SFT and RL on BFCL, tau2-Bench, and MCP Universe. These results suggest that general tool use, like other important LLM capabilities, benefits from dedicated mid-training rather than being left entirely to post-training.
Read the full abstract ▾
All authors Fengqing Jiang, Yite Wang, Boyi Liu, Zhaoyang Wang, Canwen Xu, Zhewei Yao, Radha Poovendran, Yuxiong He
Computer Vision
Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis
Liang Xu, Chengqun Yang, Zili Lin et al. (+6 more)
The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems. However, existing
datasets and modeling approaches are fundamentally constrained by low-fidelity kinematics, the omission of dexterous hand gestures and a severe lack of rich
multimodal annotations. Furthermore, fragmented interaction representations and inconsistent evaluation protocols also impede fair and rigorous benchmarking. To systematically address these bottlenecks, we present Inter-X++, a comprehensive and large-scale
benchmark designed to empower versatile HHI analysis. Captured via a novel hybrid motion capture system, Inter-X++ provides 11,388 high-fidelity interaction sequences and over 8.1M frames, featuring precise whole-body movements and detailed finger articulations. Meanwhile, we enrich the data foundation with multifaceted annotations, including hierarchical fine-grained textual descriptions, interaction categories, causal interaction orders, the relationship and personality of the subjects, as well as vertex-level contact maps and physically regularized constraints. Leveraging these elaborate annotations, we formulate a unified testing ground comprising four categories of downstream tasks that symmetrically span both generative and perceptive paradigms. To eliminate benchmarking ambiguities, we systematically standardize the interaction representations and evaluation protocols. Finally, we go beyond
dataset construction to propose OpenHHI, a single and unified HHI representation and modeling framework that jointly optimizes interaction reconstruction and semantic understanding. Extensive experiments reveal that OpenHHI achieves state-of-the-art performance on both generation and perception tasks. This definitively proves that our unified representation successfully bridges interaction understanding and generation simultaneously.
Read the full abstract ▾
All authors Liang Xu, Chengqun Yang, Zili Lin, Xintao Lv, Yichao Yan, Xin Jin, Zhibo Chen, Xiaokang Yang, Wenjun Zeng
Computer Vision
ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
Yufei Liu, Xixi Wang, Hao Li et al. (+8 more)
Egocentric video offers scalable manipulation data for
embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps. Existing single-frame and windowed temporal regressors fail when a hand shortly leaves the frame, while recent
video diffusion models (VDMs) rely on heavy,
stochastic multi-step sampling as pixel-space renderers. We instead repurpose VDM into a deterministic geometry encoder. A single forward pass over the clean latent exposes scene content beyond current observations, including occluded and out-of-sight hands. We introduce ACE-Ego-Hand, an offline clip-level framework that extracts features via a Deterministic Clean-Latent Encoder and decodes them with a Bidirectional Spatiotemporal Decoder. ACE-Ego-Hand recovers continuous bimanual trajectories with metric placement and no external detector, while a Ray-Based Camera Solver supports a second configuration that requires no test-time camera intrinsics. Across five
egocentric benchmarks, ACE-Ego-Hand sets a new state of the art, cutting MPJPE-p by 30% on occlusion-heavy ARCTIC and 40% on HOT3D. These gains reach 46%-61% once out-of-sight hands are included in the evaluation, offering a scalable path from everyday human
video to
robot manipulation data.
Read the full abstract ▾
All authors Yufei Liu, Xixi Wang, Hao Li, Ganlong Zhao, Kaitong Cai, Chengkai Jin, Chunxiao Liu, Jianbo Liu, Siyuan Huang, Xingang Pan, Hongsheng Li
Computer Vision
CalcSeg: Confidence-aware 3D Latent Context Curriculum Learning For Myocardial Scar Segmentation From Single-Stack LGE-CMRs
Nivetha Jayakumar, Hannah Kim, Amit R. Patel et al. (+1 more)
Myocardial scar
segmentation from single-stack late gadolinium-enhanced cardiac
magnetic resonance (LGE-CMR) imaging has been a longstanding and clinically important challenge, particularly in the presence of low tissue contrast, diffuse, and small scar regions. These challenges are further intensified by the limited availability of 3D spatial context. This paper presents CalcSeg, a Confidence-aware latent context curriculum learning framework that leverages fused 3D feature representations from single-stack 2D LGE-CMR images for robust scar
segmentation. Specifically, we introduce a dynamic semi-supervised curriculum learning strategy that progressively expands training from easier to more challenging scar cases using a learned confidence-aware scoring function. Such a function integrates errors in the predicted scar maps with quantified epistemic uncertainty and scar burden estimation to automatically assess sample difficulty without requiring manual labels. To compensate for the limited spatial context in single-stack acquisitions, we then develop a latent slice-wise self-
attention to capture inter-slice dependencies and infer 3D spatial representations from sparse 2D inputs. We evaluate CalcSeg on multi-center clinical LGE-CMR
datasets and
benchmark against existing scar
segmentation networks. Experimental results show that CalcSeg consistently outperforms all competing methods, particularly with substantial improvements on clinically challenging cases. Our code is released on Github.
Read the full abstract ▾
All authors Nivetha Jayakumar, Hannah Kim, Amit R. Patel, Miaomiao Zhang
Systems and Control
Taming the Tilt: A Unified Pilot Control Concept for Transformational eVTOL Aircraft
Daniel Milz, Marc May, Andreas Seefried et al. (+1 more)
Transformational electric vertical take-off and landing (eVTOL) vehicles have gained significant
attention over the past decade due to their efficient wing-borne cruise capabilities and reduced reliance on ground-based infrastructure. However, control system design for these vehicles remains challenging, as they must operate across multiple flight phases, each with distinct dominant dynamics. If left unaddressed, this complexity would significantly increase pilot workload, thus motivating the development of pilot control systems for multi-phase flight operations. The Simplified Vehicle Operations concept presents a promising strategy for reducing pilot workload. This study presents the design and implementation of a novel pilot control concept for eVTOL aircraft, validated through a tandem tilt-wing aircraft simulation on a full-motion simulator equipped with an active, force-feedback side stick. The system provides pilots with tactile feedback during specific flight phases, supporting intuitive control. The proposed approach enables seamless transitions and multi-phase flight maneuvers by leveraging the available degrees of freedom. Furthermore, an optimal-control-based methodology is proposed as a metric to evaluate command-filter-induced performance penalties and inceptor activities. The results show that the proposed command filter does not significantly increase the mission duration compared to the closed-loop system, while the active side stick helps reduce inceptor activity.
Read the full abstract ▾
All authors Daniel Milz, Marc May, Andreas Seefried, Tobias Bellmann
Systems and Control
Zero-Sum Power Factor Games
Cameron Khanpour, Samuel Talkington, Mathieu Dahan et al. (+1 more)
Variable active power injections arising from device behavior or compromised dispatch complicate voltage regulation in electric power networks with distributed energy resources (DERs). An operator can limit the resulting voltage deviations by remotely selecting DER reactive power parameters before observing the active power injections. IEEE Standard 1547-2018 specifies constant power factor as one such control mode, coupling each device's reactive power to its realized active power. Using a linear voltage model, we formulate the operator's decision as a robust minimax problem in which the operator minimizes the largest feasible aggregate voltage deviation. We solve this problem by expressing the power factor decisions through continuous reactive to active power ratios and exactly decomposing the payoff according to the signs of the voltage deviations. When every feasible voltage residual remains on its initial side of nominal, the resulting ratios cancel each injection's contribution and yield a closed form minimax strategy. We identify realistic DER ratings for which this strategy applies and quantify the regulation capacity lost under restricted power factor ranges. Numerical tests check the cancellation computation, solve the complete minimax problem directly at a representative DER rating, and compare the linear voltage predictions with nonlinear AC power flow.
Read the full abstract ▾
All authors Cameron Khanpour, Samuel Talkington, Mathieu Dahan, Daniel K. Molzahn
Machine Learning
Physical-Support Confidence Sets for Highly Coherent Dictionaries
Guan-Ju Peng
Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for highly coherent dictionaries where alternative calibration-compatible dictionaries may assign different physical meanings to the same selected support. We develop resolution-aware physical-support inference that jointly accounts for uncertainty in the learned dictionary and in the representation of a deployment signal. Our cross-dictionary confidence correspondence retains calibration-compatible dictionaries and deployment-compatible sparse representations, then projects the surviving explanations onto physical-support space. For local coherent-atom classes with separation scale s, once the deployment data resolve the coherent-block explanation and its atom support, the minimax physical resolution from N calibration signals satisfies $\delta_{\mathrm{opt}}(N,s)\asymp\min\{s,\frac{1}{\sqrt{N}s^2}\}$, with relative resolution governed by the orientation-information scale $Ns^6$. Deployment replication improves physical localization only when orientation changes cannot be absorbed by adjusting the active coefficients. For computation, we introduce active endpoint bracketing (AEB), an adaptive finite-bank procedure that evaluates only candidates that can still affect the physical report and otherwise safely coarsens or abstains. Finite-bank experiments, including a four-region synthetic application, show that a point-valued plug-in selector can be physically overprecise, whereas AEB avoids unsupported refinement with fewer candidate evaluations.
Read the full abstract ▾
Artificial Intelligence
Phantom Gains: Auditing Self-Improvement Against a Measured Null
Cheng Xu, Nan Yan, Liming Chen et al. (+1 more)
Whether a
language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions means differencing two noisy estimates, leaving them vulnerable to measurement artifacts.
Auditing three rounds of rank-$32$ LoRA self-training on Qwen3-8B against a frozen control pushed through the identical pipeline, we identify seven measurement failures, each of which inverts a reported finding when its control is absent. Several are standard practice. A ledger built on a single greedy decode manufactures capability changes on an untrained model, largely an artifact of inference batching; the expansion statistic separating acquisition from sharpening assigns that same model a rate of $0.280$. The natural threshold repair does not survive replication: estimated across the frozen comparisons such a design already contains, its null stays non-zero. We replace it with a per-problem exact test against a pooled baseline under false-discovery-rate control, which detects nothing on any held-out replicate and is unchanged under the multiple-testing rule, error rate and pool size. Applied to a ladder of arms matched in stream, volume and evaluation, the audit finds that external
distillation improves problems the base model rarely reaches while three forms of self-training do not; a regression rejects this asymmetry as a by-product of
distillation's larger overall gain ($p < 10^{-8}$). On the far smaller set of problems the base model never reaches, the evidence is inconclusive, while self-training corrupts problems solved at baseline at rates well above the measured floor. Transition-level
auditing therefore requires a separately measured null for every statistic it reports: nulls that cost no new experiments, built from baseline replicates a multi-arm study already owns, though not from as few as most possess.
Read the full abstract ▾
All authors Cheng Xu, Nan Yan, Liming Chen, M-Tahar Kechadi
Information Theory
The Honeycomb Framework for Code Bounds
William Gay, Fernando Granha Jeronimo and Lenny Liu
We introduce the honeycomb hierarchy, a representation-theoretic framework that gives new asymptotic upper bounds on $R_2(\delta)$. Its first level is the two-row hyperoctahedral representation graph associated with type $S^{(n-k,k)}$. Retaining every two-row irreducible and every coordinate box-transfer channel, together with a moving-projection
theorem, yields an explicit four-parameter exponent $\kappa_{\mathrm{HC}}$. The earlier whole-cube exponent $\kappa_H$ is a boundary restriction of this optimization, whereas the fully optimized second MRRW exponent $M_2$ is an exact symmetric slice. The prior best curve is the combined $\kappa_{\mathrm{bin}}=\min\{\kappa_{\mathrm{CW}},\kappa_H\}$, which uses a constant-weight branch $\kappa_{\mathrm{CW}}$. Replacing only the whole-cube branch by the honeycomb bound gives $\kappa_{\mathrm{best}}=\min\{\kappa_{\mathrm{CW}}, \kappa_{\mathrm{HC}}\}$. We prove, on $0<\delta<1/2$, \[ R_2(\delta)\le \kappa_{\mathrm{best}}(\delta) \le \kappa_{\mathrm{bin}}(\delta) \le R_{\mathrm{2MQC}}(\delta)<M_2(\delta),\\[-1mm] \kappa_{\mathrm{best}}(\delta) \le \min\{\kappa_{\mathrm{CW}}(\delta), \kappa_{\mathrm{bal}}(\delta)\} <R_{\mathrm{2MQC}}(\delta), \qquad \kappa_H(\delta)=R_{\mathrm{MQC}}(\delta). \] The hierarchy has two further directions. Increasing the representation depth replaces scalar by
matrix-valued transfers on the hive. Increasing the anchor depth localizes it in a stable-set hierarchy. The resulting bounds are monotone in both directions and eventually recover $A_2(n,d)$. A complementary Horn–channel hierarchy gives
matrix optimizations whose $2\times2$ level is $\kappa_{\mathrm{HC}}$ and whose $3\times3$ level is a stronger bound. Already at low levels, they can be used to improve the strongest previous general bounds, while the honeycomb framework provides a route towards tighter bounds.
Read the full abstract ▾
Machine Learning
Dynamic Structural Causal Modeling for Sleep
Ranveer Singh, Saurabh Mathur, Pranuthi Tenali et al. (+2 more)
The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic causal graphs of sleep-disordered breathing from Home Sleep Apnea Test (HSAT) recordings, revealing systematic differences in causal structure across sex and age subcohorts. We do so using the PCMCI+
algorithm on windowed fractional variables derived from 105 HSAT recordings, exploiting domain knowledge via edge blacklisting and employing bootstrap aggregation to address small subcohort sizes. The learned graphs show that temporal self-dependencies and the apnea-desaturation relationship persist across all cohorts, while other relationships vary substantially.
Read the full abstract ▾
All authors Ranveer Singh, Saurabh Mathur, Pranuthi Tenali, Arun Badi, Sriraam Natarajan
Computer Vision
Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning
Weiliang Huang, Huanrong Liu, Bob Zhang et al. (+5 more)
Reliable
surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with such motion. Existing approaches typically treat future scene generation and instrument trajectory prediction as two separate tasks. Scene-only models cannot directly evaluate the accuracy of future instrument motion at the trajectory level, while trajectory-only models fail to capture the visual consequences of instrument movement, leaving the consistency between predicted trajectories and future scene
evolution unaddressed. Jointly
forecasting both provides a more complete account of
surgical action-scene dynamics by enabling explicit trajectory-level evaluation while simultaneously modeling the corresponding visual
evolution. To bridge this gap, we present a preliminary joint visual-trajectory world-action model that simultaneously forecasts future visual states and instrument trajectories from historical
surgical observations. Specifically, we encode historical
video frames and tool trajectories into latent representations, which are processed by a temporal-spatial encoder and subsequently decoded through separate visual-state and trajectory prediction heads. Based on this preliminary architecture, a chunked autoregressive rollout is repeatedly applied to predict fifteen future steps. The chunked strategy consistently outperforms direct one-shot prediction across all evaluated horizons, improving first-segment PSNR from 18.86 to 23.11 dB and reducing ADE from 45.77 to 22.22 pixels. These results demonstrate the initial feasibility of joint visual-motion
forecasting. However, we observe progressive visual degradation and accumulated trajectory errors over longer prediction horizons, which remain important challenges for future
surgical world-action modeling.
Read the full abstract ▾
All authors Weiliang Huang, Huanrong Liu, Bob Zhang, Qi Dou, Zhen Chen, Yun Gu, Guy Rosman, Qingbiao Li
Distributed Computing
Design and Empirical Evaluation of a Network-Centric, On-Premises Architecture for Earth Observation Data Access
João Pinelo, João Gonçalves, Denis Willett et al. (+7 more)
Earth observation (EO) programmes generate data at volumes that exceed the transfer and storage capacity of most institutional networks. Public cloud platforms address this for well-resourced organisations, but institutions across the Atlantic basin face constraints in connectivity, sovereignty and funding that make on-premises infrastructure the only viable path. Cloud-native data formats enable efficient partial reads, yet their performance depends on the bandwidth of the underlying network fabric, a dependency rarely measured in isolation. This paper presents a replicable, network-centric architecture for on-premises EO data access, evaluated at its first operational deployment: the AIR Data Centre, founding node of the Atlantic Cloud. The system comprises a MinIO object storage cluster on a 100 GbE fabric, a PostGIS metadata catalogue and an OGC API-EDR access layer. We characterise the fabric under sustained parallel load, evaluate object storage throughput for EO-representative workloads, and compare measured performance against throttled baselines on identical hardware, isolating network bandwidth as the sole variable. Multi-site replication
benchmarks with partner institutions characterise the federation primitive the model depends on. Network bandwidth is the dominant constraint on storage throughput for bulk EO data access up to a threshold; beyond it, endpoint
memory topology rather than capacity governs how much bandwidth a system can use. For this hardware class that threshold lies above 10 Gbps per server. Below it, network capacity alone sets what the facility can deliver; above it, the return on further network investment depends on endpoint
memory provisioning, which can be deferred and bought later.
Read the full abstract ▾
All authors João Pinelo, João Gonçalves, Denis Willett, Amit Ruhela, Derek Steinmoeller, Uriel Mendoza, Pelumi S. Alao, Ronald Soares Lopes, Rogerio Atem de Carvalho, Pedro Mattos
Computation and Language
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Qian Kou, Xiaofeng Shi, Xiaosong Qiu et al. (+1 more)
Large
language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for
retrieval-free question answering. We propose IAR (Inject, Align, and Recover), a three-stage post-training framework that separates structured document knowledge injection, QA behavior
alignment, and general ability recovery. Unlike conventional continued pretraining, Inject converts source documents into continuation, rewrite, and instruction-conditioned reconstruction objectives. Align then adapts the injected model with answer-only QA supervision, while Recover merges the domain-adapted model with the base instruction model to recover general capabilities. Across Common Corpus (CC) and CCI, and across Llama, Phi, Qwen, and SmolLM model families, IAR improves the domain-primary domain-general frontier for
retrieval-free document internalization. In the main comparison, IAR improves over Vanilla SFT on all four reported metrics in 7 of 8
dataset-model settings, with average gains of 3.6 percentage points in domain QA accuracy and 12.1 percentage points in mean general performance across IFEval, MMLU, and MSBench. Extended CC baselines show that LoRA and FAPM can win individual general metrics, but among methods that also reach leading or near-leading domain internalization, IAR retains one of the strongest general profiles.
Read the full abstract ▾
All authors Qian Kou, Xiaofeng Shi, Xiaosong Qiu, Hua Zhou
Databases
Which Eviction Policy Should an LLM Cache Use? A Systematic Study Across Workloads, Capacities, and Encoders
Yash Kulkarni, Shubham Harkare and Arvind Yogesh Suresh Babu
Semantic caches reuse an LLM response when the incoming query
embedding lies near a cached query, but proposed eviction policies have rarely been compared under one protocol. Using CLEVER, we evaluate FIFO, LRU, LFU, ARC, GDSF, a single-pass streaming adaptation of SISO, and a semantic-redundancy policy across three ordered, deduplicated query corpora, three cache capacities, and two encoders. No evaluated policy improves on LFU by more than 0.041 percentage points in any of the eighteen settings. Replacement is not irrelevant: FIFO and streaming SISO trail LFU by as much as 8.67 and 8.55 points, respectively, at tight capacity. We explain the missing upside with a conditional packing result. Under exact lookup and insert-on-miss, a newly inserted entry cannot have a resident neighbor within the hit radius, so a geometry-aware eviction rule receives little new redundancy signal. A separate audit exposes a larger problem with the evaluated operating point. At MiniLM's median nearest-neighbor threshold, only 2.1-3.9% of sampled LMSYS and QQP hits are judged answer-substitutable, reducing raw hit rates of 51-60% to quality-adjusted rates of 1.1-2.2%. The cross-encoder study further shows that thresholds do not transfer between
embedding models. LFU is the strongest simple default in this protocol; deployment decisions should first establish answer validity and then test sub-point policy differences with exact search.
Read the full abstract ▾
Robotics
DART-S: Reachability-Audited Active-Suspension Preconditioning for Off-Road Vehicle Jumps
Yu Hu, Fangzhou Zhao, Liang Chen et al. (+7 more)
Airborne torque reaction cannot recover takeoff errors beyond the wheel angular-momentum budget. DART-S applies ramp-face suspension preconditioning to change pitch, pitch rate, and wheel
spin before liftoff, thereby shifting the queried state and altering the remaining authority budget. To predict how each suspension action reshapes this state-budget pair, DART-S employs a local calibration map. A support-aware selector combines the predicted shift with local outcome evidence and an interval-reachability screen; an exact-pair audit reports residual authority. Across 600 new runs in 72 independent BeamNG sessions, every positive, negative, and boundary query follows its prespecified branch. At the confirmed 40{\deg}/13 m/s boundary, DART-S attains 24/24 post-touchdown attitude-criterion successes versus 0/24 for DART (session-level Holm-adjusted p=0.0234). At 11.5 m/s, a 0.35 s timing action attains 23/24 versus 0/24 for the static preset (p=0.0156). The 200 rad/s command guard keeps drivetrain hard-limit exceedance at zero across all 600 runs. The source code will be available at https://github.com/MeridianCAS/DART-S
Read the full abstract ▾
All authors Yu Hu, Fangzhou Zhao, Liang Chen, Chen Min, Wei Li, Mingyuan Sang, Jiajia Ma, Shican Chen, Di Pang, Baolei Chen
Artificial Intelligence
Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian et al. (+1 more)
Large
language model (LLM)
agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may transfer unreliably and can even harm the
agent that retrieves them. When
agent-induced skills transfer reliably across tasks remains an open question. We conduct a comprehensive and controlled study of how the way skills are induced shapes their transfer across tasks. Specifically, we compare task-level with subtask-level skill induction and text with code skill formats, the two axes along which existing methods differ. Task-level skills mostly reduce the
agent's performance below its no-
memory baseline while subtask-level skills raise it above on average, and text skills transfer better than code skills. To further understand our findings, we examine two complementary properties of the induced skills: specificity, which measures how closely a skill matches real tasks, and abstractness, which measures how evenly its relevance spreads across tasks. Neither property alone predicts task success, but their combined effect does, which we propose as a skill utility score. The score correlates consistently with task success when skills are transferred, and subtask-level and text skills score higher. Computing skill utility only needs the skills and task descriptions, so our score serves as a lightweight diagnostic of a skill
memory for practitioners.
Read the full abstract ▾
All authors Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian, Jiawei Zhou
Artificial Intelligence
Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning
Jianghai Li, Pavel Kuznetsov, Yury Yanovich et al. (+2 more)
The rapid proliferation of memecoins on blockchain platforms has increased the risk of fraudulent activities, particularly rug pulls. While previous studies have focused on Ethereum-based
tokens, this paper shifts the spotlight to Solana, the leading blockchain for memecoins by trading volume and
token count. Unlike Ethereum, where rug pulls often exploit smart contract
backdoors, Solana memecoin rug pulls are predominantly driven by liquidity manipulation and social dynamics. This research pioneers large-scale rug pull early detection in the Solana ecosystem by assembling a
dataset of 6.4 million
tokens over 7 months.
Market analysis reveals that a vast majority of these memecoins exhibit rug pull characteristics within one hour of launch, highlighting the urgency of short-horizon prediction. Despite the absence of code-level features, we demonstrate that classic machine learning models, particularly Gradient Boosting (XGBoost), achieve robust performance in detecting potential rug pulls using only the first 5 minutes of trading data. Furthermore, we evaluate cross-platform generalization between PumpFun and Raydium, revealing that multi-source data fusion significantly mitigates domain shift and improves detection reliability. This study advances the understanding of DeFi fraud on high-throughput chains and provides a practical framework for protecting investors.
Read the full abstract ▾
All authors Jianghai Li, Pavel Kuznetsov, Yury Yanovich, Konstantin Nott-Whaley, Igor Vodolazov
Machine Learning
DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers
MD Saifur Rahman Mazumder and Feng Yu
Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decision trees can be computationally expensive, particularly for large and high-dimensional
datasets, largely due to the exhaustive search over candidate splits at each node. To improve computational efficiency, we propose Data-Informed Centroid Splitting (DICS), a clustering-based framework that constructs a compact and informative set of candidate splits using data-driven priors. By incorporating class-aware structure, DICS significantly reduces the split search space for classification tasks while preserving predictive performance. We further provide theoretical analysis showing that under the stated assumptions, DICS does not degrade the performance of classification trees compared to exhaustive split search. DICS can be incorporated into classification trees, random forests, and gradient-boosting models. Extensive experiments demonstrate that DICS achieves comparable accuracy while substantially reducing training time across synthetic and
benchmark datasets, highlighting the benefit of integrating data-informed priors into split selection for scalable classification tree learning.
Read the full abstract ▾
Artificial Intelligence
Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation
Gijs Kassenaar, Zhao Yang and Vincent François-Lavet
Reasoning language models trained with reinforcement learning typically operate under a fixed
token budget rather than an explicitly adaptive one, which can lead to over-computation on easy problems and insufficient computation on difficult ones. We study whether a model can learn to allocate its own
reasoning effort by choosing, as the first
token of its response, one of three modes: NoThink (answer as quickly as possible), Short (brief
reasoning), or Long (extended
reasoning). The choice is learned inside Group Relative Policy Optimization (GRPO) with no separate router, through a shaped reward that makes each mode worthwhile at a different response length, together with hard per-mode
token caps that keep the modes distinct. On a 1.5B distilled model trained on MATH, the three modes emerge without collapsing to a single choice, and the brief modes end up more accurate than Long, which shows that the router sorts problems by difficulty rather than at random. Averaged over three seeds, the resulting policy stays close to the base model's accuracy on the held-out MATH500 ($0.782$ vs.\ $0.796$) while cutting the mean response length from $4{,}796$ to $2{,}811$
tokens (a $41\%$ reduction). Interestingly, it also transfers to other
benchmarks without retraining, with the largest savings where problems are easier, with for instance 76%
token reduction on GSM8K and at higher accuracy than the baselines at similar response length. In short, we build a
reasoning model that adaptively chooses how much to reason for each problem.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Transfer Learning in Nonparametric Regression with Deep ReLU Networks
Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen et al. (+1 more)
This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a common structure along with group-specific deviations in additive form, the proposed method employs a two-stage offset learning procedure: the first stage pools data from all groups to estimate an overall mean function, and the second stage estimates offsets for each group, yielding final group-level
estimators through additive combination. Upper bounds on the $\mathcal L_2$ error are established for the proposed framework, covering a broad class of nonparametric
estimators under mild complexity and noise conditions. When instantiated with deep ReLU networks, explicit convergence rates are derived under hierarchical composition models, demonstrating the ability to overcome the curse of dimensionality. Conditions that enable positive transfer with faster rates are considered, including learning with simpler functions and data augmentation through pooling samples across groups. Various simulations and real-data experiments further validate the effectiveness of the proposed method.
Read the full abstract ▾
All authors Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen, Oscar Hernan Madrid Padilla
Robotics
Video2DoorTraversal: Push Door Traversal via Simulated Door Twins
Xincheng Tang, Yiji Chen, Youhan Xie et al. (+8 more)
Door opening and traversal is a long-horizon loco-manipulation task that requires precise handle interaction and coordinated base-arm control. We present
Video2DoorTraversal, a single-
video real-to-sim-to-real framework for wheel-legged mobile manipulators. Given one RGB
video of a real door, DoorTwin reconstructs an instance-aligned, articulated, and simulation-ready door twin with realistic geometry and appearance. A simulation-in-the-loop
agent converts the recovered articulation into a parameterized skill program and iteratively refines failed rollouts to generate physically executable demonstrations. These demonstrations are used to train ArticuACT, a dual-depth policy that predicts coordinated base, arm, and gripper commands using
robot-centric camera conditioning and interaction-aware supervision. With all perception and policy inference running onboard, the system achieves a 96.57% average success rate across five real doors and an 80.95% zero-shot success rate on structurally similar unseen doors, while completing the full approach, opening, and traversal sequence in approximately 13s on average. Project Page: https://
video2doortraversal.github.io/.
Read the full abstract ▾
All authors Xincheng Tang, Yiji Chen, Youhan Xie, Wanyu Li, Zhengjie Shu, Lai Jiang, Wenkang Hu, Yitong Li, Jinchuang Zhang, Xibin Song, Ruigang Yang
Information Retrieval
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence
Somaya Eltanbouly, Heba Sbahi, Samer Rashwani et al. (+4 more)
Retrieval-Augmented Generation is used for Islamic question answering, but most systems are evaluated end-to-end, making
retrieval failures difficult to isolate from generation failures. We study answer-bearing
retrieval for Arabic fiqh, where a passage is relevant only if it states the ruling required by the question. We build a
retrieval test collection for Arabic fiqh and use it to evaluate dense, lexical, hybrid, fine-tuned, and madhhab-aware
retrieval strategies. The best retriever achieves 0.524 MRR@5, while fine-tuning improves performance to 0.553. Hybrid
retrieval provides limited gains for strong models, whereas madhhab-aware filtering more than doubles MRR@5 on school-specific questions. We further present an error analysis showing that the main challenge is distinguishing answer-bearing passages from topically similar passages that do not contain the requested ruling. The best-performing model and fine-tuning
dataset are publicly available at: https://huggingface.co/collections/somayaeltanbouly/badr-arabic-fiqh-
retrieval.
Read the full abstract ▾
All authors Somaya Eltanbouly, Heba Sbahi, Samer Rashwani, Abdessalam Bouchekif, Mutaz al-Khatib, Shahd Gaben, Mohammed Ghaly