Machine Learning · Cross-listed from cs.CC
Optimal Unambiguous DNFs and Alon-Saks-Seymour
Chirag Pabbaraju
We construct unambiguous DNFs having width $O(n)$ but $0$-certificate complexity $\Omega(n^2)$. By utilizing the special structure of these DNFs, we prove a lifting
theorem with a constant-sized gadget that lifts the DNF to a communication problem, while losslessly translating the separation in certificate complexity to a separation in communication complexity. This leads to an optimal refutation of the Alon-Saks-Seymour
conjecture, as well as an optimal communication lower bound for the Clique versus Independent Set problem, improving the previous results of Balodis, Ben-David, Göös, Jain and Kothari (FOCS 2021, SICOMP 2023) by several doubly logarithmic factors. As further applications of our construction to query complexity and learning theory, we exhibit: (a) a family of Boolean functions that has an optimal quartic separation between certificate complexity and approximate degree, and (b) a sample compression lower bound of $\Omega(\sqrt{\log c})$ for multiclass concept classes over $c$ labels.
Read the full abstract ▾
Machine Learning
Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
Tom Saliencro, Rohan Desai, Priya Nair et al. (+2 more)
Mixtures of low-rank adaptation experts increase parameter-efficient capacity by routing each input through a subset of adapters. Recent dynamic routers activate more experts when the router or prediction is uncertain. This rule silently equates uncertainty with useful additional computation: an uncertain example may contain complementary, unqueried expert evidence, but it may instead remain ambiguous after every expert agrees. We formulate routing as certified value-of-information allocation. VI-MoLE learns the counterfactual risk remaining after each expert prefix, converts these predictions into simultaneous upper-risk certificates on held-out calibration data, and spends a global adapter budget on the
token–layer action with the largest certified marginal risk reduction per unit cost. A terminal certificate then decides whether to answer or abstain. Unlike an uncertainty gate, this procedure distinguishes present ambiguity from recoverable and residual risk. We prove simultaneous certificate validity, optimal greedy allocation under diminishing certified gains, and allocation regret under value-estimation error. The evaluation protocol tests matched-compute accuracy, certificate coverage, risk–coverage, distribution shift, and tail latency against fixed and dynamic MoE-LoRA routers.
Read the full abstract ▾
All authors Tom Saliencro, Rohan Desai, Priya Nair, Maya Lindqvist, Daniel Whitmore
Machine Learning
Analytic Planning under Uncertainty with Moment Closure
Shishir Sharma and Doina Precup
Effective model-based reinforcement learning in
stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable. Consequently, modern deep reinforcement learning has largely retreated to either
stochastic sampling, which introduces significant target variance, or deterministic point estimates that ignore predictive covariance entirely. We investigate whether distribution-aware planning is possible without these constraints. Using a quadratic action-value parameterization, we first reduce the Bellman backup to an expectation over the state-value function alone; the key idea is then a compatibility principle between the predictive transition distribution and the value function class, under which this expectation is analytic in the distribution's moments. We instantiate this principle with a Gaussian transition model paired with a radial-basis value function, yielding a closed-form backup that propagates both predictive mean and covariance. Empirically, our approach reduces target variance and yields well-calibrated predictive uncertainty under
stochastic observations in continuous control, providing a principled framework for planning with learned distribution models.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
Zhichen Liu, Ruihan Sun, Hengjie Yang et al. (+4 more)
Long-running assistants and
agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and
retrieval preserve access to selected history, but do not provide a persistent state over the full lifecycle when working context changes. We formulate this missing inference capability as state continuity under context turnover: carrying computation forward through a fixed-capacity
memory state whose lifetime is independent of the active context. We introduce an intrinsic
memory method, LiveMem, which augments a pretrained full-
attention LLM with a
memory state that preserves the historical information over the whole lifecycle while the main
attention path retains a bounded KV window. Context turnover and
memory state maintaining,
memory-oriented post-training, and state-aware serving jointly make this
memory state load bearing after its originating
tokens are released. Our experiments show that LiveMem achieves leading overall performance among evaluated systems and other intrinsic
memory methods. Experiments on LongMemEval show that LiveMem is able to answer the question based on the
memory state, even when the supporting evidence has been removed from the current context, and evidence-distance analysis shows that useful information persists beyond the active window. LiveMem thus establishes state continuity as a distinct and complementary abstraction for continual LLM inference.
Read the full abstract ▾
All authors Zhichen Liu, Ruihan Sun, Hengjie Yang, Zipeng Wu, Zhaohan Chen, Xiaofan Zhang, Yang Xu
Machine Learning · Cross-listed from cs.AI
Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies
Sterre Lutz, Daniël Vos, Matthijs T.J. Spaan et al. (+1 more)
Sequential decision-making in real-world applications often involves uncertainty about the environment's model. Uncertain Markov decision processes (UMDPs) represent the possible environments as a set of MDPs with shared states and actions but potentially different transition probabilities and rewards. Optimizing a single policy across all possible MDPs may sacrifice performance, while preparing an individually optimized policy for every MDP may violate operational, regulatory, or interpretability constraints on the number of policies that can be prepared and deployed. We consider settings in which model uncertainty is resolved shortly before execution, allowing the most suitable policy to be selected from a limited set prepared in advance. We introduce $k$-adaptable policy synthesis, which optimizes such a set of $k$ policies under a minimax-regret objective. We prove that the problem is NP-hard and develop KAPS, an exact nested branch-and-bound
algorithm with problem-specific bounds and heuristics. KAPS jointly optimizes which MDPs share a policy and the policies themselves. Experiments across various UMDP
benchmarks show that the largest reduction in regret consistently occurs when increasing from one to two policies. In the single-policy setting, KAPS is competitive with existing methods in solution quality and proves optimality substantially more often.
Read the full abstract ▾
All authors Sterre Lutz, Daniël Vos, Matthijs T.J. Spaan, Anna Lukina
Machine Learning
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Yi Yang, Zhennan Chen, Yihong Zhuang et al. (+5 more)
Learning-based
memory systems for self-evolving LLM
agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an ever-expanding state space. Second, because trajectory-level rewards are jointly assigned to co-retrieved
memories, irrelevant experiences may receive misleading utility updates and consequently enter the
memory-reward trap. To address these challenges, we introduce Reduced-Order
Memory Reinforcement Learning (RoMeRL), which represents the growing trajectory-indexed utility space using a fixed-dimensional per-task
memory state factorized by outcome polarity and
memory dynamics. RoMeRL incorporates new experiences through a fixed set of semantic coordinates whose contents are updated or replaced over time, thereby concentrating feedback over a bounded utility support. Theoretically, we show that this reduced-order parameterization increases the average feedback received by each utility coordinate and characterize the steady-state occupancy of erroneous coordinates under a generic coordinate-transition model. Empirically, across ALFWorld and LifelongAgentBench, RoMeRL improves task performance, reduces the Cold-Q ratio by 80.0%, increases feedback density by approximately 6.0 times, reduces the maintained
memory size by 84.4%, and cuts LLM calls by 21.1%. These results show that reduced-order utility states support efficient self-evolving
agent memory while limiting persistent reward contamination. Code is available at: https://github.com/YOUNG-fnxm/RoMeRL
Read the full abstract ▾
All authors Yi Yang, Zhennan Chen, Yihong Zhuang, Tiehan Fan, Yinan Chen, Jian Li, Jian Yang, Ying Tai
Machine Learning · Cross-listed from math.ST
Beyond Modern Asymptotics for Log-Likelihood Ratios in Logistic Regression
Hugo Chardon, Reese Pathak and Nikita Zhivotovskiy
We characterize the finite sample behavior of the log-likelihood ratio statistic in binary logistic regression, uniformly over both the design and the target parameter. For $n\geq d\geq 3$, we determine, up to universal constants, its worst case $(1-\delta)$
quantile over all fixed collections of design vectors and all target parameters: \[ d\log\left(\frac{e n}{d}\right)+\log\left(\frac{1}{\delta}\right). \] This is a nonasymptotic analogue of the Wilks $\chi^2_d$ phenomenon and requires no regularity assumptions on the design. The low dimensional cases exhibit unusual behavior. The worst case
quantile in dimension $d=2$ is sharply of order \[ \log\log\log n+\log\left(\frac{1}{\delta}\right). \] The worst case
quantile in dimension $d=1$ is of order $\log(1/\delta)$, with no dependence on $n$. Finally, i.i.d. Gaussian design vectors recover the classical Wilks scale. In the regime $n\gtrsim d+\log(1/\delta)$, we prove the sharp bound \[ d+\log\left(\frac{1}{\delta}\right). \] Unlike existing asymptotic results, our bounds are uniform over the target parameter, which may depend on $n$, $d$, and $\delta$.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Computational and Statistical Guarantees of the c-Rectified flow
Leda Wang, Zhehao Xu, Qiang Liu et al. (+1 more)
Recently, rectified flow has emerged as a fundamental framework for large-scale image generation, powering state-of-the-art systems such as FLUX.1 and Stable
Diffusion 3. Despite its remarkable empirical success, the computational and statistical guarantees of iterative rectified flow have remained largely unexplored. We address this problem by studying c-rectified flow, a cost-aware class of rectified flow that projects velocity fields onto a gradient class while preserving endpoint marginals. The ordinary rectified flow can fail to recover the optimal transport coupling: in a Gaussian case study, the iteration converges to the optimal coupling if and only if the source and target covariance
matrices commute. More generally, for a Gaussian to log-concave coupling, the ordinary rectified flow can reach a fixed point after one step from independent initialization. In contrast, under suitable regularity and uniform-integrability assumptions, iterative c-rectified flow always converges to the optimal transport coupling. We further establish quantitative one-step contraction and exponential convergence guarantees under projection-stability assumptions for both quadratic and strongly convex displacement costs. Finally, under a Hölder ball assumption, we develop new minimax-optimal score estimation rates and show that, when combined with iterative c-rectified flow, they yield a rate-optimal
estimator of the optimal transport for the dimension \(d \ge 3\) and a nearly parametric rate for \(d=1,2\).
Read the full abstract ▾
All authors Leda Wang, Zhehao Xu, Qiang Liu, Harrison H. Zhou
Machine Learning · Cross-listed from cs.CL
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
Iaroslav Chelombitko, Ekaterina Chelombitko and Mika Hämäläinen
Open-source LLMs reliably name Zeus, Jupiter, and Thor, but recover their counterparts in less-represented traditions like Finnish, Slavic, Egyptian, or Chinese mythology far less consistently. We ask where inside the model this cultural default is produced. On a parallel cross-cultural substrate of Thompson-motif entities, we instrument 18 open-source LLMs from 8 architecture families with linear probing, logit lens, activation patching, and output extraction. The residual stream cleanly distinguishes cultures, well above a name-string baseline, yet the decoder collapses culturally-specific
tokens onto dominant-tradition ones. The failure is at readout, not at representation. Asking the same question in the target culture's native
language versus English produces failures that cluster within
language but decouple across
language: the decoder is gated on
prompt language. We release a per-entity (probe, output) decomposition framework, a citation-anchored cross-cultural ground truth, a within- versus cross-mode correlation test for
language-conditioned readout, and per-entity predictions for all 18 models.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Private Generative Bootstrap via Blocking
Jinwon Sohn and Veronika Ročková
With AI systems gaining more access to individuals' information, it is important to protect
privacy when reporting statistical answers. Equally important is to privatize the reporting of uncertainty in such answers. To this end, we adopt a
Bayesian likelihood-free framework and make simulation from the posterior private. In particular, we propose a new private instantiation of the
Bayesian bootstrap using a blocking strategy. Rather than assigning idiosyncratic random weights to each individual, we randomly group individuals and assign a single weight to each group. By concealing individuals' contributions within a group, we fortify differential
privacy gates. We harness amortized inference that decouples private learning from posterior sampling. A push-forward map from observation weights to posterior samples is learned privately by adding calibrated noise during training. Subsequent posterior draws require no additional
privacy and computation budget. We call the resulting method the Private Generative
Bayesian Bootstrap (PGBB). We establish a differential
privacy guarantee, analyze convergence to the non-private blocked-bootstrap target, and quantify the discrepancy between the ordinary and blocked
Bayesian-bootstrap posteriors. In addition, we derive data-free tuning of the block Dirichlet concentration parameter that restores posterior dispersion asymptotically. We also show a single fit of PGBB can support a family of loss-based decision rules simultaneously without additional
privacy cost. In simulations and in applications to U.S. Census returns to schooling and U.S. natality birthweight
quantiles, PGBB gives competitive private uncertainty quantification and improves over private
Bayesian alternatives that require a specified data-generating model in common settings.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Real-Time Detection and Repair of LLM Agent Failures
Sunny Dubey
LLM
agents fail mid-episode – they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content – and the standard remedy, judging every step with a second LLM, costs more than the
agent itself. We ask how much detection is achievable from observable step telemetry alone, using monitors costing microseconds per step and trained only on healthy runs. On 2,823 committed
agent episodes across three frameworks, three local models (qwen2.5 7b/3b, llama3.1 8b) and a commercial API (gemini-2.5-flash), a one-class echo-state-network ensemble with CUSUM alarms detects 0.71 of failures at a 5% false-alarm budget (AUROC 0.872). Its advantage over a memoryless baseline is a monotone function of post-onset horizon (+0.09 at <=3 steps, +0.40 at >=9), predicting its own failure region out of sample on AFTraj-2K. Ranking transfers with no retraining to two corpora from other groups (AFTraj-2K 0.745, ATBench 0.779). Monitors carry two burdens: a per-deployment healthy null (they do not transfer – AUROC 0.527 cold against 0.885 recalibrated) and a residual false-alarm rate. We add a layer carrying neither: deterministic verification, which recomputes a run's stated total from the tool results it actually received and confirms every required call was made. Head-to-head it catches 60% of failures (96% with the coverage check) at 0 of 63 false positives against the monitor's 54% at 17%, transfers unchanged to llama3.1:8b (110 of 110 at 0 of 10), and trips on 0 of 1825 healthy episodes. Detection is then closed into repair: each flagged run is rolled back and re-run live, recovering 45% of failures against a 16% resampling control (p=0.0005) and lifting task success from 52% to 73% for about one extra model call per run. The system runs at ~200 microseconds per step, three orders of magnitude below a judge call. Code, traces and results are released.
Read the full abstract ▾
Machine Learning
Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees
Zejun Xie, Xintong Li, Guang Wang et al. (+1 more)
Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features. We propose Aggregate-then-Calibrate (AtC), a two-stage framework that combines these complementary sources. Stage-1 aggregates heterogeneous comparative judgments into a consensus ranking using a rank-aggregation model that accounts for annotator reliability. Stage-2 calibrates any predictive model's scores by an isotonic projection onto the order, enforcing ordinal consistency while preserving as much of the model's quantitative information as possible. Theoretically, we show: (1) modeling annotator heterogeneity yields strictly more efficient consensus estimation than homogeneity; (2) isotonic calibration enjoys risk bounds even when the consensus ranking is misspecified; and (3) AtC asymptotically outperforms model-only assessment. Across semi-synthetic and real-world
datasets, AtC consistently improves accuracy and robustness over human-only or model-only assessments. Our results bridge judgment aggregation with model-free calibration, providing a principled recipe for human-centered assessment when ground truth is costly, scarce, or unverifiable.
Read the full abstract ▾
All authors Zejun Xie, Xintong Li, Guang Wang, Desheng Zhang
Machine Learning · Cross-listed from cs.IR
Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search
Han Wang, Alex Whitworth, Pak Ming Cheung et al. (+5 more)
Relevance evaluation plays a crucial role in personalized search systems, serving as a guardrail alongside user engagement metrics to ensure that search results align with user queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present a VLM-based automated relevance evaluation pipeline deployed within Pinterest Search for online A/B experiments. We rigorously validate the
alignment between VLM-generated judgments and human annotations, demonstrating that VLMs can provide reliable relevance measurement for experiments while greatly improving the evaluation efficiency. Leveraging VLM-based labeling further unlocks opportunities to expand the query set, optimize sampling design, and efficiently assess a wider range of search experiences at scale. This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effects (MDEs) in online experiment measurements.
Read the full abstract ▾
All authors Han Wang, Alex Whitworth, Pak Ming Cheung, Zhenjie Zhang, Krishna Kamath, Xi Chen, Roberto Konow, Kurchi Subhra Hazra
Machine Learning · Cross-listed from cs.GT
Intention Inference Under Execution Noise: Separating Aleatoric and Epistemic Uncertainty in Social Dilemmas
Kival Mahadew and Jonathan Shock
In noisy social dilemmas, intended actions are stochastically corrupted before execution, so an observed defection may reflect hostile intent or action error. Standard Markov Decision Process (MDP) formulations treat executed actions as states, structurally precluding this distinction and causing systematic over-retaliation. We introduce a Partially Observable MDP (POMDP) formulation encoding opponent intentions as latent states and executed actions as noisy observations, solved within the active inference (AIF) framework with a cost function that decomposes into epistemic and pragmatic components that jointly address inferring current intent and learning how intent evolves. In the Iterated Prisoner's Dilemma with symmetric noise, we derive a critical noise threshold governing cooperation collapse, connecting it to a fixed-point condition on learned priors. Experiments reveal that the value of intention inference is context-dependent: the POMDP provides consistent advantages against conditionally cooperative opponents, but mutual intention inference under sufficient noise produces correlated belief-driven collapse. The advantage is specific to games where intent attribution is decision-relevant.
Read the full abstract ▾
Machine Learning
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
Claire Vernade, Onno Eberhard, Martha White et al. (+4 more)
Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields have common roots in dynamic programming, they have evolved with distinct methodologies, goals, and cultures. Despite decades of mutual influence, a significant gap persists between the two communities. This tutorial introduces adaptive control, actor-critic reinforcement
algorithms, and a new way to combine these two paradigms for data-driven decision making on a classical locomotion control problem. Our aim is to provide a foundation for understanding the core differences between the two approaches and insights to help experts in each field better understand and engage with the tools and approaches of the other.
Read the full abstract ▾
All authors Claire Vernade, Onno Eberhard, Martha White, Florian Dörfler, Csaba Szepesvári, Miroslav Krstic, Michael Muehlebach
Machine Learning · Cross-listed from stat.CO
Wasserstein mixing time of the unadjusted Langevin algorithm
Francesco Pedrotti and Peter A. Whalley
We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin
algorithm, in the classical setting of log-smooth strongly log-concave measures. Our bound implies a Wasserstein mixing time of order $\kappa \sqrt{d}/\varepsilon$, where $\kappa$ is the condition number, $d$ is the dimension, and $\varepsilon$ is the target precision: this improves by a factor of $\sqrt{d}/\varepsilon$ over the previous state-of-the-art results.
Read the full abstract ▾
Machine Learning
Why Large Language Models Fail at Tabular Prediction
Marta Garnelo and Wojciech M. Czarnecki
Large
language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the most common machine learning workloads: predictive analytics over tabular data. This gap is the founding premise of the fast-growing field of tabular foundation models, but the question of why generic LLMs fail has remained open. We study a frontier LLM in its purest inference regime - a single generation pass over a
prompt containing the full training and test data, with no tools, no agentic scaffolding, and no fine-tuning - and systematically evaluate five hypotheses for the failure: (a) an inability to handle noisy or non-linearly-separable data; (b) the linearised CSV format obscuring column structure; (c) the tokenisation of numeric values; (d) the number of test points classified per query; and (e) the dimensionality of the input. Controlled experiments falsify (a)-(d). Dimensionality, in contrast, is decisive: sweeping random linear projections of thirty-one
benchmark datasets, the LLM is the only method among nine whose accuracy decreases as dimensionality grows, while every classical baseline stays flat or improves. A behavioural comparison against 252 configured classical models finds that in two dimensions the LLM predicts like a local, distance-based method (up to 91.6% grid agreement), but in higher dimensions no classical model - even when augmented with tuned, dimension-dependent noise - reproduces its predictions. We do not claim to have identified the internal mechanism; our results show, more modestly, that the LLM's capability dissolves with dimension in a way no noise-corrupted classical learner mimics - which explains why LLMs, so capable elsewhere, keep losing to fifty-year-old baselines on tables, while leaving the mechanism of the prediction as an open question.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Human-Centered Reflections on Care Robots: A Comparative Study of Caregiver Perspectives
Laura Londoño, Klaus Baumann, Abhinav Valada et al. (+1 more)
Care
robots are increasingly being introduced into healthcare settings, raising important questions about their acceptance and ethical implementation. To better understand these challenges, this study investigates caregivers' perceptions of four categories of care
robots: delivering supplies, helping patients into bed, monitoring vital signs, and assisting with mobility. We conducted a mixed-methods study employing a mixed-factorial design in which 298 caregivers from the United States, Mexico, and Chile evaluated all four
robot categories. Quantitative measures integrated constructs from the Unified Theory of Acceptance and Use of Technology, the Cognitive-Affective-Normative model, and overall acceptance ratings. Qualitative data were collected through open-ended questions and analyzed using a literature-informed ethical framework. The results indicate that participants across countries generally evaluated care
robots positively, particularly for logistical and physically demanding tasks rather than those requiring intensive interpersonal interaction. The qualitative findings provide further insight into stakeholders' views of the ethical implications of care
robot use. Participants emphasized potential benefits such as reduced workload, lower risk, and greater patient autonomy, while also expressing concerns about dependability, the need for human oversight, and potential job displacement. Although many ethical concerns were shared across countries, participants differed in how they interpreted and prioritized them. These findings advance a context-sensitive and socially informed understanding of responsible design and implementation of care
robots.
Read the full abstract ▾
All authors Laura Londoño, Klaus Baumann, Abhinav Valada, Markus Langer
Machine Learning
Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data
Run Lin, Yingtian Tang, Jiawen Xu et al. (+6 more)
Accurate gait analysis in Parkinson's disease (PD) typically relies on laboratory-based systems to capture biomechanical data, such as ground reaction forces (GRFs). Estimating GRFs using inertial measurement units (IMUs) provides a feasible alternative. However, this approach remains challenging in pathological gait like PD due to its high variability and complexity. Moreover, existing monitoring approaches often require multiple body-mounted sensors, which limit practicality and reduce patient compliance. To date, no study has investigated the application of deep learning approaches to address this challenge. This study proposes, for the first time, a deep learning framework to estimate bilateral vertical GRFs (vGRFs) in PD using an optimized set of wearable IMUs. A hybrid CNN-BiLSTM model was trained separately on data from 61 PD patients and 65 healthy controls (HC) using 13 IMUs. The model achieved high intra-subject accuracy ($R^2$ = 0.98) and strong inter-subject generalization ($R^2$ = 0.93 for HC, $R^2$ = 0.91 for PD). Sensor configuration was found to significantly influence estimation accuracy, with optimal sensor placement varying between PD patients and HC. For PD patients, estimation accuracy dropped markedly when reducing to a single IMU. The optimal configuration for PD used four IMUs. We identified a minimal setup with only two IMUs still enabled robust estimation. This compact setup offers a practical and scalable solution. Overall, the proposed approach supports the development of wearable vGRF-based gait analysis systems for Parkinsonian gait and potentially other pathological conditions, enabling accessible clinical assessments, remote monitoring, and personalized rehabilitation.
Read the full abstract ▾
All authors Run Lin, Yingtian Tang, Jiawen Xu, Dongfei Huo, Lefan Wang, Helen Dawes, Dominic J. Farris, Dong Wang, Xijin Hua
Machine Learning
From fragmented data to actionable design: Physics-calibrated learning for plastic upcycling
Jingyang Bai, Zijia Wang, Xiangyi Long et al. (+3 more)
Thermochemical upgrading of plastic waste is a key upcycling pathway, yet the experimental literature is fragmented by heterogeneous conditions and incomplete reporting. Complete-case learning would retain only 10.99% of the curated experiments, while target imputation can introduce biased supervision. Here we develop a Physics-Calibrated, Missingness-Gated, and Load-Balanced Mixture-of-Experts (PC-MG-MoE) framework that converts structured missingness into an informative learning signal. PC-MG-MoE learns directly from partially observed experiments without target imputation, reconstructs physically consistent product distributions, accommodates cross-laboratory heterogeneity, and provides interpretable model behaviour rather than black-box prediction alone. Under stringent source-grouped validation, it achieved the lowest aggregate absolute error among the evaluated models, supporting engineering screening under cross-laboratory heterogeneity. Wet-lab experiments provide an external comparison, showing key composition-dependent trends. Implemented as an interactive web-based workflow, PC-MG-MoE enables forward screening, physics-grounded constrained inverse design, targeted experimental planning that supports reduced experimental workload and trial-and-error, and laboratory-specific adaptation with new platform-specific data. This work establishes a transferable framework for converting fragmented literature data into experimentally actionable guidance for model-guided plastic upcycling and broader thermochemical systems.
Read the full abstract ▾
All authors Jingyang Bai, Zijia Wang, Xiangyi Long, Marcos Millan, Binjian Nie, Mingyue Ding
Machine Learning · Cross-listed from cs.SI
Network Information Enhances Unreliable News Domain Detection
Raphaela Keßler, Roman David Ventzke, Viola Priesemann et al. (+1 more)
Content-based detection of unreliable news is increasingly difficult, as low-reliability sources mimic credible journalism and generative AI makes fabricated content harder to flag. We ask whether network structure can improve news reliability classification, taking a domain-level approach that shifts the focus from individual articles to source reliability. From URL-sharing patterns in Telegram chats, we build a statistically validated domain co-sharing network and find assortative mixing by reliability: low-reliability domains group together, as do reliable ones. Exploiting this structure, we compare Graph Neural Networks against network-unaware baselines using both content-aware features (
multilingual text
embeddings) and content-agnostic features (spreading dynamics). GNNs consistently outperform Multi-Layer Perceptrons on identical features, with GraphSAGE best in both settings (accuracy 0.63 with content, 0.53 without), a 13-14% relative gain over the network-unaware baseline. Network
topology thus systematically improves domain reliability assessment, and remains effective even when content analysis is infeasible.
Read the full abstract ▾
All authors Raphaela Keßler, Roman David Ventzke, Viola Priesemann, Giordano De Marzo
Machine Learning · Cross-listed from cs.AI
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
Zhiyuan Wang, Shengcai Liu, Jiahao Wu et al. (+5 more)
Tool-using large
language model (LLM)
agents produce long, multi-turn trajectories, making gradient-based post-training
memory-intensive.
Evolution strategies (ES) enable
memory-efficient full-parameter post-training without backpropagation and can eventually match the performance of gradient-based reinforcement learning (RL). However, resource-constrained settings typically offer only a few GPUs, so the high GPU-hour requirements of ES translate into prohibitively long training times. To address this, we introduce Cooperative Parameter-subspace
Evolution Strategy (CoPES), a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency. We post-train a Qwen3.5-4B tool-using
agent for the math task and evaluate it on five
benchmarks of varying difficulty. Under the GPU-hour budget of full-parameter GRPO's best validation checkpoint, CoPES recovers 92% of GRPO's validation-accuracy gain, versus 67% for standard ES, while its theoretical GPU
memory requirement is less than one-eighth that of full-parameter GRPO. It consistently outperforms standard ES and LoRA-based GRPO on all evaluated pass@k metrics across the five
benchmarks. Additional experiments further show the advantage of CoPES on the question-answering task. These results demonstrate an improved trade-off between
memory requirements and training time for agentic LLM post-training under resource constraints. The code is open-sourced in https://github.com/MetaronWang/CoPES
Read the full abstract ▾
All authors Zhiyuan Wang, Shengcai Liu, Jiahao Wu, Ning Lu, Hui Ouyang, Shaofeng Zhang, Haoze Lv, Ke Tang
Machine Learning
Gecko: Fast Private Inference via Secure Public Encoder Offloading
Cheng'an Wei, Kai Chen, Yue Zhao et al. (+2 more)
Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical deployment. This motivates recent efforts to run a public encoder, such as a pretrained backbone, outside the protection boundary and evaluate only a small private predictor cryptographically. While appealing for efficiency, this design is not inherently secure: naively offloading a public encoder may create a feature-space shortcut: an extraction adversary may learn the remaining private predictor's feature-to-output mapping more easily than the original model's input-to-output behavior. We present Gecko, designed to limit this additional risk while retaining a compact encrypted predictor. We leverage a frozen backbone that contributes hierarchical features, fixed Fastfood projections that compress them, and private feature gating that prepares them for prediction. We formalize ideal independence and information-preservation conditions as design guidance, then separately evaluate component-reuse extraction attacks. Across image and audio tasks, Gecko achieves 0.4-2.2 second inference with at most 10.8 MB communication and accuracy comparable to transfer-learning baselines. Under the evaluated attacks, reusing the offloaded public encoder provides no significant advantage to model-extraction adversaries. Source code and a demo are available at https://github.com/CassiniHuy/gecko-infer.
Read the full abstract ▾
All authors Cheng'an Wei, Kai Chen, Yue Zhao, Congyi Li, Shenchen Zhu
Machine Learning · Cross-listed from math.OC
A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems
Ting-Jui Chang
This paper studies the distributed online control problem over a network of linear time-invariant (LTI) systems in the presence of
adversarial disturbances and time-varying convex costs. The network cost is characterized by the summation of local cost functions, where each local function is sequentially revealed only to the corresponding
agent. The goal of each
agent is to generate a control sequence, using only local observations and neighbor communication, that competes with the best centralized linear policy in hindsight. We extend the recently proposed Online Spectral Control framework from the centralized setting to the distributed setting. In particular, each
agent applies a spectral controller obtained by convolving past disturbances with the leading eigenvectors of a Hankel
matrix, while the controller parameters are updated through a distributed online gradient descent step over the local surrogate costs. We formulate this problem this problem as a regret minimization problem based on the spectral parameterization, and under standard assumptions, we establish a sublinear regret bound of $O(\frac{\sqrt{T}\text{poly}(\log T)}{\gamma^3})$, where $T$ is the time horizon and $\gamma$ denotes the stability margin. The resulting bound also captures the dependence on the network size and connectivity.
Read the full abstract ▾
Machine Learning
GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation
Mingyang Wang, Rongwen Li, Xiao Wang et al. (+1 more)
Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains challenging. Existing methods learn global dependencies across samples or dynamic local dependencies per sample. Global dependencies are stable but adapt poorly to sample variations and temporal non-stationarity, whereas local dependencies are adaptive yet unreliable when observations are insufficient, causing erroneous information propagation. To address these limitations, we propose GLAIM, a Global-Local Adaptive Inter-variable Dependency Modeling framework for multivariate time series imputation. GLAIM comprises two complementary components. The Stable Global Dependency Constructor derives robust global inter-variable dependencies from complementary temporal representations, providing a stable backbone less affected by sample-specific missingness and noise. The Sample-Conditioned Dependency Refiner adapts this backbone to each sample and time step using its temporal state and available observations, enabling reliable local refinement under incomplete observations. Extensive experiments on nine real-world
datasets demonstrate that GLAIM achieves state-of-the-art performance under random and block missingness, remains robust to missing-rate shifts, and benefits from its complementary global and local components. Code is available at https://github.com/LuRenjias/GLAIM.
Read the full abstract ▾
All authors Mingyang Wang, Rongwen Li, Xiao Wang, Changjian Chen
Machine Learning · Cross-listed from cs.AI
Faster-WAM: Do World Action Models Need Deep Action Modules?
Liheng Ma, Rui Heng Yang, Amin Abyaneh et al. (+8 more)
World Action Models (WAMs) build on pretrained
video models, whose representations are grounded in physical dynamics and provide a natural basis for action prediction. Despite this natural foundation, many WAMs still rely on deep, parameter-heavy action-prediction modules that incur high inference latency and may overfit to limited
robot demonstrations, restricting their real-world applicability. In this paper, we advocate a world-model-centric principle that concentrates capacity and computation in the
video world model, while a lightweight action expert translates the backbone's representations into executable
robot actions. We realize this principle through three key choices: Dock of
Transformers (DoT) with Lite KV-Fusion to give the shallow, lightweight action expert access to representations from all
video layers; world-model-only conditioning of the action expert; and retracted 1D-RoPE for positional
alignment between
video keys and action queries. We test this principle using Faster-WAM, a world-model-centric WAM with only a single-layer action expert. Despite this restriction on action-specific computation, Faster-WAM achieves competitive control performance on LIBERO and RoboTwin~2.0 without additional
embodied pretraining. It provides approximately $3.7\times$ and $1.3\times$ inference speedups over Fast-WAM and $\pi_{0.5}$, respectively. Consistent with its world-model-centric design, Faster-WAM demonstrates stronger generalizability under distribution shifts: the same LIBERO-trained policy achieves $78.3\%$ success on LIBERO-Plus, exceeding Fast-WAM and LingBot-VA by $26.8$ and $8.8$ percentage points, respectively. Finally, real-
robot experiments demonstrate success rates comparable to Fast-WAM, with substantially lower inference latency and shorter task-completion times.
Read the full abstract ▾
All authors Liheng Ma, Rui Heng Yang, Amin Abyaneh, George Z. Xue, Behnam Rahmati, Mateo Clemente, Ziwen Hu, Anlin Chen, Tongtong Cao, Zhanguang Zhang, Yingxue Zhang
Machine Learning
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai et al. (+43 more)
Native computer use offers a general interface for
agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use
agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable
prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight
benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable
agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions.
Read the full abstract ▾
All authors Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan, Chang Gao, Jian Guan, Feng Hu, Mianqiu Huang, Xingyang Huang, Yizhen Jiang, Yuheng Jing, Dehui Kong, Ning Li, Dayiheng Liu, Shixuan Liu, Zheng Liu, Que Shen, Bowen Wang, Junli Wang, Chencan Wu, Rui Xie, Tianbao Xie, Zhihui Xie, Haiyang Xu, An Yang, Tao Yu, Wenzhen Yuan, Xi Zhang, Zhenru Zhang, Mingkang Zhu, Zhaoqing Zhu, Yizhong Cao, Kai Dang, Binyuan Hui, Kaixin Li, Junyang Lin, Haiquan Wang, Zekun Wang, Yiheng Xu, Fan Yan, Mengqi Yuan, Danyang Zhang, Jiajun Zhang, Zhipeng Zhang, Fan Zhou, Fan Zhou
Machine Learning · Cross-listed from cs.CR
Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning
Martin Mocko and Daniela Chudá
Malware clustering is a critical task in cybersecurity that helps discover threats and analyze evolving malware families. While self-supervised learning (SSL) and tabular representation learning (TRL) have achieved breakthroughs in other domains, their application to binary program clustering (the task of clustering all incoming samples regardless of label) remains largely unexplored. This study presents the first systematic investigation of SSL and TRL methods for binary program clustering, conducted in two phases on the public Ember and Bodmas
datasets. In Phase 1, we establish a performance ceiling by adapting prominent
vision-based SSL models (BYOL, SimSiam, Barlow Twins, VICReg) for tabular data with supervised pair generation, finding that BYOL and SimSiam achieve performance comparable to fully supervised models, while Barlow Twins and VICReg significantly underperform. In Phase 2, we evaluate purely unsupervised TRL methods against strong baselines (PCA, Autoencoder, UMAP), demonstrating that VIME establishes a new state of the art for binary program clustering. Informed by these findings, we propose VIME-R, a
retrieval-augmented extension of VIME that replaces random marginal-distribution corruption with
retrieval-based augmentation to generate more informative training pairs. VIME-R further improves upon VIME, achieving 2.7%-5.8% higher Homogeneity on both
datasets. Our results highlight
retrieval-augmented tabular representation learning as a promising direction for enhancing automated malware analysis. Code will be made available.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection
Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts et al. (+1 more)
Many operational problems are constrained sequential decision processes with combinatorial action spaces and interdependent constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in
stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by
embedding a differentiable optimization module inside the policy: a neural network proposes continuous action targets, a quadratic program projects them onto the relaxed feasible set, and a dual-informed integer mapping restores integrality while preserving feasibility. Given a differentiable simulator, the policy trains end-to-end from sampled trajectories using pathwise gradients, while handling hard constraints with similar flexibility to MILPs. We show that our approach has bounded error relative to an exact integer projection and ensures the entire feasible action space is reachable. We apply the method to multi-echelon production-inventory planning under shared resource and material constraints. Our policy attains an average optimality gap of 1% on 3-item instances and consistently outperforms a rolling-horizon multi-stage
stochastic program by at least 5.6% in 10-item networks. Compared to state-of-the-art echelon base-stock policies, savings reach 15.3% on 40-item instances. On an industry-scale case study with nonstationary demand from ASML, we reduce average cost by up to 1.8% relative to the best-known
benchmark policy. The savings are largest where planning is hardest: in tightly capacitated systems with high demand variability. More broadly, we show that DRL can improve upon state-of-the-art baselines in sequential decision problems with hard constraints, which are widespread in practice.
Read the full abstract ▾
All authors Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner
Machine Learning
Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning
Botao Dong, Longyang Huang, Ning Pang et al. (+1 more)
In offline reinforcement learning (RL), the distribution shift between behavioral data and the learned policy can lead to erroneous Q-value estimation, thereby misguiding the direction of policy optimization. To address this issue, we develop a behavioral advantage corrected policy evaluation (BAC-PE) approach, which utilizes the Q-function of the behavior policy to correct the learned policy's Q-function, thus mitigating pessimistic conservatism and overestimation bias. Furthermore, the convergence of BAC-PE is analyzed theoretically, and an upper bound on the difference between the learned Q-function and the true Q-function is derived. To alleviate distribution shift, this work employs
diffusion models to represent both the behavior policy and the learned policy, performing distribution matching for accurate policy regularization. Additionally, Q-value guidance is incorporated into the training process to achieve effective policy improvement. By combining BAC-PE with
diffusion policy modeling, we propose the
diffusion policy with behavioral advantage correction (DPBAC)
algorithm. Compared to existing offline methods, DPBAC demonstrates stronger policy representation capabilities and effectively mitigates the bias in Q-value estimation. Experimental results on multiple domains of D4RL tasks show that DPBAC achieves superior performance, with notable advantages over state-of-the-art (SOTA)
algorithms.
Read the full abstract ▾
All authors Botao Dong, Longyang Huang, Ning Pang, Hongtian Chen