Machine Learning · Cross-listed from cs.RO
Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies
Yilin Wu, Rutav Shah, Shuaiyi Huang et al. (+5 more)
It is widely appreciated that robotic policies require long-term
memory to perform complex tasks. However, directly conditioning policies on all past observations leaves policy learning susceptible to learning spurious shortcuts, and introduces large latency at policy deployment. As such, today's
memory-augmented policies curate what to remember, either by retaining only recent frames, selected keyframes, or textual summaries, or by learning latent representations of the visual stream alone. In this work, we propose an alternative approach IMPRINT, a policy-agnostic latent
memory framework that augments
vision-
language-action (VLA) models with multi-stream
memory without explicitly constraining what the policy should remember. IMPRINT compresses different streams into a latent
memory that is updated incrementally at inference, enabling low latency. To avoid shortcut learning, IMPRINT adopts a two-stage training procedure, first supervising
memory to reconstruct multiple streams (observations, actions, proprioception) of past information, as well as estimate current task progress, followed by end-to-end finetuning, jointly with the policy, on action prediction. Across both simulation and real-world tasks demanding
memory, IMPRINT improves average success over the base VLA by at least 26%, outperforming popular alternatives, and maintaining lowest inference latency among
memory-augmented VLAs. Through careful ablations, we demonstrate the utility of incorporating diverse information streams into robotic
memory, validating the advantages of foregoing history curation. Project website: https://yilin-wu98.github.io/imprint_website/.
Read the full abstract ▾
All authors Yilin Wu, Rutav Shah, Shuaiyi Huang, Sumedh A. Sontakke, Homanga Bharadhwaj, Andrea Bajcsy, Max Simchowitz, Guanya Shi
Machine Learning · Cross-listed from cs.SE
SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering
Mengyang Liu, Weiming Wang, Haixin Nan et al. (+6 more)
Reinforcement learning (RL) has driven substantial progress in coding
agents by relying on verified successful trajectories as learning signals. However, such trajectories are scarce in long-horizon software engineering tasks, where a minor error can invalidate the entire rollout. Repeatedly restarting from the initial state is commonly used yet inefficient, and resetting only the context with working directory misses state changes such as installed dependencies. Therefore, branching from intermediate steps to preserve earlier progress requires restoring both the
agent context and execution environments. In this paper, we present SPROUT (SnaPshot-based RollOUT), an agentic RL rollout framework that scales long-horizon coding tasks by resuming and branching from intermediate states. Specifically, SPROUT was built on top of a lightweight infrastructure that checkpoints both the filesystem and the
agent context after each assistant turn. A verifier-guided backtracking policy then selects where to resume a failed attempt and how to proceed. Extensive experiments on long-horizon coding tasks show that SPROUT achieves up to 23.6% improvement over pass@k across various LLMs, while using $32$–$52%$ of their
tokens. For RL training of Qwen3.8-27B, SPROUT stably outperforms standard GRPO by $13.9$ points on three long-horizon coding
benchmarks while cutting the time per training step by $39.5%$. SPROUT thus makes RL on long-horizon coding tasks both more effective and cheaper to scale.
Read the full abstract ▾
All authors Mengyang Liu, Weiming Wang, Haixin Nan, Yu Wu, Peize Li, Shihong Huang, Xuning He, Xue Jiang, Yihong Dong
Machine Learning
Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations
Duaa Nakshbandi, Zhiyu An and Wan Du
Successor-feature-based zero-shot reinforcement learning methods pre-train a task encoder and successor-feature predictor on offline, reward-free data, then recover a policy at test time by solving a closed-form linear regression over a small labeled
dataset. We identify an underexplored limitation of this approach: when the task encoder produces dense representations, the inferred reward signal becomes diffuse across the state space, reducing the contrast between goal-relevant states and the background and providing a weaker signal for the policy to follow. We address this limitation by introducing an l1 sparsity penalty that concentrates reward-predictive structure into a smaller effective subspace of the task encoder's latent space. The penalty is applied only during training and requires no architectural change or modification to the closed-form inference procedure. We instantiate this approach as Sparse-TD-JEPA, a single-line of code addition based on Temporal-Difference Joint-
Embedding Predictive Architecture (TD-JEPA) that significantly improved its performance in zero-shot reinforcement learning. We evaluate Sparse-TD-JEPA on 65 tasks across the DeepMind Control (DMC) Suite and OGBench, covering locomotion, navigation, trajectory stitching, puzzle solving, and robotic manipulation. Sparse-TD-JEPA improves over TD-JEPA in all 13 domain-level comparisons. On DMC, it increases the average return from 661 +- 6 to 714 +- 3. On OGBench, it increases the average success rate from 38.0 +- 0.8 to 48.4 +- 2.3, with improvements of 13.4-18.0 percentage points on the evaluated antmaze navigation and stitching domains. Overall, Sparse-TD-JEPA achieves the highest mean performance among established zero-shot baselines in nine of the 13 domains. Analysis further shows that sparsity produces a sharper and more task-informative inferred reward landscape.
Read the full abstract ▾
Machine Learning
Clinical value claims in multimodal AI outpace supporting evidence
Jiayu Feng
Multimodal prediction models add a data source, such as imaging or an assay, to clinical information, and health systems must decide whether that added test is worth acquiring. We audited 177 studies comparing
multimodal with unimodal models: 81 from a systematic review and 96 from a probability sample of 2025-2026 PubMed records. Gains in the area under the receiver operating characteristic curve (AUROC) were smaller when a study fitted a separate model for every data source (adjusted difference, -0.030; 95% CI, -0.056 to -0.005). Within 78 such studies, leaving out the strongest source's model would have raised the average gain from 0.046 to 0.108. This complete benchmarking fell from 69.1% of review studies to an estimated 46.0% of recent ones. An estimated 22% assessed decision utility and none evaluated a model prospectively, yet most claimed potential clinical usefulness or improved care (84.0% and an estimated 87.7%).
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
Understanding and Mitigating Training Instability in Large-Scale Recommender Systems: A Cascade Perspective
Yuening Li, Zeyu Wang, Zhen Zhang et al. (+8 more)
Training large-scale recommender systems on dynamic industrial platforms, such as Short-Form
Video (SFV) services with billions of daily interactions, faces critical stability challenges. Rapid distribution shifts in user data and increasing model complexity frequently trigger a divergence cascade, typically initiating with gradient explosion, propagating to weight explosion, and culminating in loss explosion. This G-W-L cascade severely impedes model convergence and performance. This paper provides a systematic analysis of this G-W-L cascade within an industrial SFV recommender context. We then propose and evaluate a structured mitigation framework where interventions are explicitly mapped to counteract specific stages of the cascade: gradient (G) control, weight/activation (W) stabilization, and loss (L) shaping. Our contribution provides a structured framework for understanding and tackling training divergence, offering practical insights for deploying robust, continuously updated recommenders in large-scale, non-stationary settings. We empirically validate the effectiveness of these strategies on a major industrial SFV recommendation system.
Read the full abstract ▾
All authors Yuening Li, Zeyu Wang, Zhen Zhang, Jiayi Liu, Zhimeng Jiang, Yuji Roh, Weikai Xu, Mingyan Gao, Onkar Dalal, Chuan He, Liang Liu
Machine Learning · Cross-listed from stat.ML
Decomposing A Neural Learner
Zelong Bi
Neural learners for classification and regression are often criticized as black boxes. We propose a probabilistic decomposition of neural learners that accounts for heterogeneous predictability across the feature space. A training procedure combining the EM
algorithm,
stochastic gradient descent, and maximum likelihood estimation is developed to jointly learn the predictable component and an input-dependent reliability score. We show that the optimal decomposed learner recovers the response distribution within the predictable component, while the reliability score characterizes the predictability of individual observations. We further extend the framework to incorporate localized feature transformations. Experiments on synthetic and real-world
datasets demonstrate the effectiveness of the proposed framework.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SY
Deep learning from a control vantage point
Álvaro Rodríguez Abella, João Pedro Silvestre, Bahman Gharesifard et al. (+1 more)
This article offers an overview of recent developments in deep learning from a control vantage point. It reviews several classes of models including feedforward and residual neural networks,
transformers, large-
language models, and selective state space models while explaining how control theory plays an important role in understanding their training, properties, or architecture design. The article explains how residual neural networks can be interpreted as the discretization of a continuous-time control system thereby enabling the use of control theoretic techniques for its analysis. To illustrate the power of this bridge between control and deep learning, two technical results are discussed: 1) the ability of a residual neural network to approximate arbitrary continuous functions is a non-standard controllability problem that can be solved using
geometric nonlinear control and 2)
transformers, the key architectural component of most large
language-models, can be seen the discretization of a consensus
algorithm and thus large
language-models exhibit consensus. Another point of contact between control theory and deep learning is the connection between backpropagation, the
algorithm used to train neural networks, and optimal control. The article addresses how the older connection between these problems, established in the 80's using discrete-time models can be reconciled with the more recent approach using continuous-time models. Several open problems and directions for future research are discussed, including selective state-space models, a recent class of models inspired by the models used in control.
Read the full abstract ▾
All authors Álvaro Rodríguez Abella, João Pedro Silvestre, Bahman Gharesifard, Paulo Tabuada
Machine Learning
DPAL: A Test-Time Adaptation Loss for Financial Time Series Forecasting
Wuzhou Lian, Haochun Wang and Yuefan Deng
Test-time adaptation (TTA) enables time series forecasters to update after deployment as new observations become available. However, adaptation objectives that focus primarily on prediction errors at individual time steps do not fully address the needs of financial time series forecasting. In addition to pointwise return fitting, return direction and the price trajectories reconstructed from sequences of returns are also important. To better account for these properties, we introduce Direction- and Price-Aware Adaptation Loss (DPAL), which combines pointwise return fitting with directional and price-calibration terms. We apply DPAL within existing TSF-TTA frameworks without modifying the source forecaster or the adapter architecture. Across a diverse collection of financial
datasets, DPAL reduces reconstructed-price mean squared error in most evaluated settings.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity
Weikang Wan, Zeyu Lai, Jianyu Hou et al. (+4 more)
Dexterous
robot hands can receive useful motion intent from teleoperation or learned policies, but successful execution also depends on contact decisions that these commands rarely specify. We introduce DexFLEX, a contact-aware foundation controller that turns upstream fingertip-motion drafts into contact-consistent joint commands. Instead of treating a draft as a trajectory to copy, DexFLEX treats it as evidence about intent: from the current tactile-proprioceptive state, it proposes feasible short-horizon motion chunks, predicts their contact consequences, and selects the candidate that best follows the command while preserving future contact stability. At inference time, a simple Draft-Dream-Select procedure combines pure-prior proposals for recovery with draft-seeded proposals for responsiveness, then decodes the selected motion into executable joint-space targets. Across degraded-command simulation, real-world shared control, and visuomotor policy learning, the same trained controller improves robustness without retraining, increasing real-world teleoperation success from 29.2% to 78.3% and reaching 46.7% policy-learning success, 3.5 times direct joint-action prediction, and 1.56 times prior-only correction.
Videos are available at dex-flex.github.io.
Read the full abstract ▾
All authors Weikang Wan, Zeyu Lai, Jianyu Hou, Yuchen Zhou, Jiawei Fu, Henrik I Christensen, Hao Su
Machine Learning
When More Memory Fails: Hidden Feasibility Holes in Dynamic Tensor Rematerialization
Mahesh Reddy Pagadala
Dynamic Tensor Rematerialization (DTR) trains neural networks under a
memory budget by evicting tensors and recomputing them on demand. A natural expectation is that a budget large enough to complete training stays sufficient when it is increased. Using DTR's reference simulator, simrd, to replay the public DTR training traces, we show that this expectation fails. We call the exceptions feasibility holes:
memory budgets at which an eviction policy runs out of
memory although both a smaller and a larger budget complete, a form of non-monotone feasibility. Under a written sweep protocol with dated amendments, a 0.01-step budget grid shows no such hole for DTR on any of six confirmatory traces, although unresolved timeouts prevent it from establishing monotonicity. Finer sampling finds holes on InceptionV4 (three regions) and U-Net (two regions), in addition to one on the ResNet-32 development trace. Every hole is reproduced by three repeats and by unmodified simrd. For one InceptionV4 pair (0.2343 versus 0.235 of peak
memory) we trace the failure to individual allocations. The larger budget avoids one eviction at an operator where the smaller budget was 173,479 bytes short. The extra data it carries forward forces a later eviction of a tensor needed three operators afterwards, and rebuilding that tensor triggers a recomputation cascade that cannot fit. Keeping that one tensor resident under the same budget prevents the failure. The two simple score changes we tested do not remove holes across traces; both add failing budgets on some traces. All results are from simulation, with no allocator model; behaviour on GPU hardware is untested.
Read the full abstract ▾
Machine Learning
History, Adaptation, and Hidden Gain: Two Prospective Tests of Learned Predictive Control in a Synthetic Neural Population
Mahesh Reddy Pagadala
We study learned one-step predictive control of a synthetic population of 64 leaky integrate-and-fire
neurons whose light sensitivity is scaled by a hidden factor s, using two prospective confirmations on plants simulated only after the analysis was frozen. In the first (50 plants, 11 conditions), removing the 200-ms input-output history substantially worsened a parameter-count-matched neural predictor at low and moderate gain (s = 0.6, 0.8; RMSE rose by 2.47 Hz at s = 0.6, 97.5% CI 2.43-2.51). In secondary comparisons, recursively adapted ARX had the lowest mean error of the deployable controllers in 10 of 11 conditions, tuned PI with anti-windup matched or beat the network for s >= 0.7, and training for 10,000 rather than 900 epochs lowered prediction error but worsened control. Development work suggested the network's learned action sensitivity did not track the hidden gain. A second protocol (50 new plants, 9 sensitivities, 2 noise levels) confirmed three pre-specified predictions at the primary noise level. Re-estimating a single multiplicative input gain recovered 87% (95% CI 86-88%) of the benefit of full adaptive ARX. Supplying that online estimate to the network as an extra input reduced high-gain tracking error by 1.84 Hz [1.81, 1.88]. Longer training worsened the plain network by 1.09 Hz but improved the gain-input network by 1.07 Hz, a differential of 2.16 Hz [2.13, 2.20]. Under high process noise (sigma = 2.0) the effects shrank to about 0.04 Hz or less and gain-only adaptation recovered only 24% of the adaptive-ARX benefit. In this synthetic plant, at the primary noise level, one-parameter online gain estimation accounts for most of the gap between a history-based network and full adaptive ARX, and for its prediction-control mismatch.
Read the full abstract ▾
Machine Learning
ConformalGuard: False-Positive-Controlled Action Gating for LM Classifiers
Bishnu Bista, Dhanraj Haibatrao Jadhav, Vibha Choudhary et al. (+4 more)
Language model classifiers are increasingly deployed for high-stakes decisions such as phishing screening, content moderation, and fraud triage, yet validation-set thresholds provide no finite-sample control of deployment-time false positives. We present ConformalGuard, a model-agnostic calibration layer that wraps a fixed scoring function with finite-sample control over the rate at which legitimate inputs trigger an intervention tier. Our contribution is empirical and operational, not a new conformal
theorem: zero-shot LM API scores can be coarse enough (10–11 unique values here) to make temperature scaling and isotonic regression operationally identical to raw thresholding for low-FPR action gating. We compare these methods with conformal calibration for fine-tuned BERT, Claude Sonnet 4, and GPT-4o on public email corpora. For Claude, conformal calibration reduces FPR from 0.040 to 0.008 while recall falls from 0.938 to 0.875. For deterministic GPT-4o scores, the 1% operating point is too conservative to deploy (recall 0.564); three-run
stochastic averaging raises recall to 0.732 at FPR 0.005. At 2% prevalence with BERT, conformal calibration removes 25 false-positive reviews per 10,000 emails (95% CI [10, 43]). The guarantee is legitimate-event-rate control under exchangeability; discrimination, workload effects, and robustness to shift remain empirical.
Read the full abstract ▾
All authors Bishnu Bista, Dhanraj Haibatrao Jadhav, Vibha Choudhary, Gaurav Saxena, Arun Pandiyan Perumal, Arjun Subedi, Jignesh Ammineni
Machine Learning
The Sample Complexity of Multicalibration with an ERM Oracle
Princewill Okoroafor
A predictor is multicalibrated with respect to a class of subpopulations (formally, of functions on the inputs, called auditors) if, for every subpopulation in the class and every value the predictor outputs, the average outcome among the members of that subpopulation who receive that value is close to the value itself. For finite classes, about $\varepsilon^{-3}$ samples are necessary and sufficient to learn a predictor with multicalibration error $\varepsilon$, but the
algorithms that attain this rate enumerate the class, which is impossible for the large classes of interest. We ask how many samples suffice when the learner accesses the class only through an empirical risk minimization (ERM) oracle. We give an
algorithm that uses $\tilde{O}(d/\varepsilon^{3})$ samples and polynomially many ERM calls, where $d$ is the VC dimension of the class. Its dependence on $\varepsilon$ is optimal for all learners. When $d$ is at least about $1/\varepsilon$, every learner that can only access the class through polynomially many ERM calls needs $\tilde{\Omega}(d/\varepsilon^{3})$ samples. Learners with unlimited computation need only $\tilde{O}(\varepsilon^{-3}+d\varepsilon^{-2})$ samples, so the extra factor $1/\varepsilon$ on the dimension term is the price of oracle efficiency. For swap multicalibration, which allows a different function from the class for each predicted value, $\tilde{\Theta}(d/\varepsilon^{3})$ samples are necessary and sufficient. For estimating the error of a given predictor, the ordinary notion is the harder one: the swap error can be estimated with an ERM oracle, whereas the ordinary error is NP-hard to approximate even for classes with linear-time ERM. Consequently, there are classes for which it is computationally easier to learn a multicalibrated predictor than to compute the multicalibration error of a given predictor.
Read the full abstract ▾
Machine Learning
Class-Conditional Conformal Prediction for Signal Temporal Logic Inference with Many Classes
Yixuan Wang, Danyang Li, Matthew Cleaveland et al. (+2 more)
Signal Temporal Logic (STL) inference provides interpretable formulas for time series classification. For multiclass classification, however, accurate predictions do not necessarily ensure that the inferred formulas are satisfied consistently with the true class. We introduce the positive satisfaction rate and codeword satisfaction rate to quantify satisfaction of required formulas and consistency with the complete class codeword, respectively. We develop a two-stage procedure that first learns discriminative formulas using a margin-based objective and then refines predicate thresholds toward a small positive robustness target while fixing the formula structure and temporal intervals. Satisfaction and ranking penalties discourage violations of required formulas and loss of class separation. The decoding loss is used as a nonconformity score and calibrated separately for each class, providing finite-sample class-conditional coverage under intra-class exchangeability. Experiments on naval, synthetic, and
robot manipulation trajectories demonstrate discrepancies between classification accuracy and formula satisfaction. The results further reveal a data-dependent tradeoff between robustness tightness and satisfaction, while class-conditional calibration mitigates undercoverage that can be hidden by pooled calibration.
Read the full abstract ▾
All authors Yixuan Wang, Danyang Li, Matthew Cleaveland, Roberto Tron, Mingyu Cai
Machine Learning · Cross-listed from cs.CR
Natural Code Transformation Confuses Agents in Vulnerability Analysis
Jie Zhu, Ronik Bhaskar, Heather Zheng et al. (+2 more)
Having demonstrated a strong potential for automating vulnerability discovery, AI
agents can also be used to attack software systems at scale. Today's software systems need mechanisms to level the playing field by slowing down potential attacks, giving them time to patch vulnerabilities and strengthen software. Along this line, our study of
agent trajectories in vulnerability analysis shows a surprising finding:
agents produce dramatically different results across real-world code commits that carry the same functionality and the same vulnerability. This phenomenon appears consistently in multiple code domains and vulnerability categories. It motivates us to study natural and functionality-preserving code transformations derived from real-world software development, and their potential as a defense against attacker
agents. We build a corpus of natural transformations by mining recurring development patterns from real-world code commits, and apply them to evaluate impact on agentic vulnerability analysis. Our results show that even a single form of transformation can effectively "confuse" frontier
agents, e.g., Codex with GPT-6 Sol, reducing successes in vulnerability discovery. We also study different
agent failures, whether transformations can be composed to provide stronger protection, and adaptive attackers who seek to reverse them. Overall, our study of natural code transformation significantly expands the research space of using code transformations to defend against malicious
agents.
Read the full abstract ▾
All authors Jie Zhu, Ronik Bhaskar, Heather Zheng, Ben Y. Zhao, Kexin Pei
Machine Learning
On the Depth Transfer of Neural Optimizers via L-Smoothness
Maximilian Wong, Chenyu Xu, Jiajin Li et al. (+1 more)
Scaling deep learning models efficiently requires predictable performance transfer across compute regimes. Establishing reliable hyperparameter transfer allows optimal training dynamics and structural choices to be discovered on low-cost proxy models, avoiding catastrophic failures during massive-scale training. Existing depth-transfer analyses are architecture-specific and heuristic: hyperparameter transfer is only justified through toy blocks, and both rely on infinite-depth dynamics, a specific initialization, and feature-learning criteria. Building on $L$-smoothness framework of Xu et al. (2026), we understand hyperparameter transfer as how do the Lipschitz and $L$-smoothness constants of the loss scale with the depth $K$? We show that inverse-depth residual branch scaling $\alpha=\Theta(1/K)$ is sufficient to make both constants depth-independent at fixed width, uniformly over the bounded parameter domain and for arbitrary $p\to q$ geometries. Because the bounds depend on each residual branch only through its Lipschitz and smoothness constants, the argument applies to general residual networks (including branches of block depth $\geq 2$ such as
transformer and ResNet blocks) without assumptions on initialization or correlations between layer weights. Since the smoothness constant controls the
curvature penalty in the descent inequality, our bounds motivate a learning-rate scale without an additional depth-dependent
curvature correction for updates bounded in the prescribed norm. This provides a
geometric explanation of inverse-depth residual scaling and its application to the operator-norm geometries associated with AdamW,
Muon, and MOGA. Learning-rate sweeps on GPT-2 (depths 2–128) and CIFAR-100 ResNets (8–32 residual blocks) confirm that
Muon and MOGA exhibit stable learning-rate transfer under these prescriptions, with a common optimal rate across a 64-fold increase in depth.
Read the full abstract ▾
All authors Maximilian Wong, Chenyu Xu, Jiajin Li, Yiping Lu
Machine Learning
Continuous-Time Cloth Dynamics with Physics-Informed Neural ODEs
Yingdong Ru, Lipeng Zhuang, Zhuo He et al. (+1 more)
We present ContinuousCloth, a continuous-time, physics-informed neural solver for deformable cloth dynamics that enforces a spring–mass ODE within a neural trajectory model. Unlike classical time-stepping simulators that return trajectories only on a discrete integration grid, ContinuousCloth supports querying at arbitrary timestamps and computing displacement, velocity, and acceleration via automatic differentiation. We evaluate ContinuousCloth along two dimensions. In a physics-only setting, ContinuousCloth achieves trajectory accuracy comparable to high-precision solvers across six diverse boundary-condition scenarios while reducing runtime by up to 17.4 times. When fused with sparse and noisy observations, the spring–mass ODE acts as a strong inductive bias for downstream tasks: interpolation and parameter estimation. That is, ContinuousCloth reduces interpolation error by 7.3 times over a data-only neural baseline in simulation and 2.4 times on real-world cloth sequences, and achieves 2.6 times lower parameter error than a differentiable-solver baseline under high-noise conditions, demonstrating consistent robustness under realistic measurement imperfections.
Read the full abstract ▾
All authors Yingdong Ru, Lipeng Zhuang, Zhuo He, Gerardo Aragon Camarasa
Machine Learning · Cross-listed from math.OC
STREGO: A Scalable Implementation of a Trust-Region Framework for Noisy Bayesian Optimization
Youssef Diouane, Issmail El Hallaoui, Meisseme Kadri et al. (+1 more)
TREGO, a trust-region
Bayesian optimization (BO) method for expensive blackbox problems, has convergence guarantees, but only for exact function values. In high dimension, its performance tends to deteriorate. This paper asks whether a trust-region BO method can be extended to handle noisy evaluations while being competitive in high dimension. We first generalize TREGO into a trust-region framework for noisy BO and extend its convergence analysis to noisy function estimates that are sufficiently accurate with sufficiently high probability. We then propose STREGO, a scalable implementation of this framework. Its global phase selects a batch of candidates by solving a bi-objective problem on the posterior mean of a Gaussian process and the integrated variance reduction. Unlike the predictive variance, this second objective does not favor boundary points merely because they are far from the data. Its local phase minimizes the posterior mean of a second Gaussian process, trained only on points close to the incumbent. STREGO is compared with TREGO, TURBO, BAXUS and NSMA-BO on synthetic and real-world problems of dimension $4$ to $124$, with and without noise. It gives the best average results in every synthetic setting tested and the best or tied-best solution on four of the six real-world problems. An implementation of STREGO is available at https://github.com/Mayousk/STREGO.
Read the full abstract ▾
All authors Youssef Diouane, Issmail El Hallaoui, Meisseme Kadri, Amina Lamghari
Machine Learning
Decentralized Bandit Learning of Markov Perfect Equilibria
Felix Höfer and H. Mete Soner
We study decentralized bandit learning in discounted infinite-horizon, general-sum Markov games with continuous actions.
Agents observe the public state, but only their own realized rewards, and use simultaneous perturbation
stochastic approximation to update their actions. Under strong monotonicity of the negative running-reward gradients and sufficiently small time steps, we prove that the fully decentralized procedure converges almost surely to the unique stationary Markov perfect
equilibrium. We obtain an $O(n^{-1/2})$ convergence rate and present a natural extension to episodic finite-horizon learning.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference
Anxhelo Diko, Jieyu Lin, Stefano Ambrogio et al. (+5 more)
Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones,
robots, and servers. Yet, they are typically trained as rigid, fixed-capacity networks bound to one device, supporting neither reconfigurable compute budgets nor collaborative execution. Existing approaches address only one axis at a time: slimmable and NAS-based methods provide width elasticity but assume single-device inference, whereas split-computing methods enable cross-device collaboration only for fixed partitions and static capacities. We introduce Elastic V-JEPA (EV-JEPA), a single model trained once and deployable everywhere along the continuum. Its width is reconfigurable, and it is natively partitionable across heterogeneous devices. At its core is Transition-Aware Triplet Training (T3). At each step we pick a narrow and a wide width, and train three paths: each width alone, plus a hybrid path that runs the early layers narrow and the rest wide. The hybrid switch point is where one device hands off to another, so the same weights learn both single-device and cross-device execution. Across various
benchmarks, EV-JEPA falls within 1 accuracy point of independently trained baselines while improving over previous elastic training approaches by up to 11 accuracy points. Narrow-to-wide cross-device hybrid execution recovers to within 1.1 points of the highest-capacity standalone model and supports many-to-one, any-to-any, and variable-split configurations. Finally, we show that the elastic principle extends beyond the backbone to an elastic
token compression mechanism that exposes controllable trade-offs among on-device computation, latency, and accuracy.
Read the full abstract ▾
All authors Anxhelo Diko, Jieyu Lin, Stefano Ambrogio, Ziyun Li, Mahmoud Assran, Théo Moutakanni, Barbara De Salvo, Chiao Liu
Machine Learning · Cross-listed from cs.CV
MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
Yuguang Li, Yichuan Deng, Zixuan Liu et al. (+5 more)
Reconstructing accurate camera poses and floor-plan layouts from sparse, unposed, wide-baseline RGB panoramas remains a challenging open problem. Direct multi-room floor-plan prediction is especially difficult in this setting: pose, geometry, semantics, and global layout structure are tightly coupled, yet a complete floor-plan is hard to learn as a single global output. Our key insight is to keep the model's predictions strictly local. Multi-view Ordered Wall Instance Segmentation (MOIS) is designed around this concept. Each panorama column predicts only the wall it observes plus the next two adjacent walls in clockwise order. The global wall partition, room layouts, and shared coordinates emerge from deterministic aggregation of overlapping local predictions. Building on MOIS, we propose Multi-view floor-plan Feed-Forward Network (MvFFN), which jointly predicts coarse camera poses, dense global geometry, and per-wall semantic outputs. A downstream Layout Chaining (LC) post processing pipeline then assembles these predictions into multi-room floor-plans with shared global coordinates, consistent wall identities, and connected room structure. The dense MOIS predictions recover cross-view wall identity and local within-room connectivity more accurately than composed modular baselines, and the assembled layouts substantially outperform prior methods on wall and junction level accuracy. We also introduce the ZInD-CrossView
dataset, which augments ZInD with globally unique wall instances and cross-view segmentation labels for this task.
Read the full abstract ▾
All authors Yuguang Li, Yichuan Deng, Zixuan Liu, Ivaylo Boyadzhiev, Xiuyuan Wu, Xinyu Zou, Linda Shapiro, Alex Colburn
Machine Learning · Cross-listed from cs.AI
ConicFlow: constrained Inference-time optimal control for flow matching models
Shervin Khalafi, Kasra Fallah, Sung Cho et al. (+3 more)
We propose ConicFlow, which frames constrained sampling from a flow matching model at inference time as an optimal control problem that balances deviation from the pretrained trajectory against reward, subject to hard terminal constraints. We discretize this problem and adapt receding-horizon control, optimizing only a short window of the trajectory at each step for computational tractability. We address the resulting sequence of receding-horizon subproblems with a receding-horizon primal-dual
algorithm. Its dual multipliers capture the difficulty of satisfying each constraint and are refined throughout sampling, steering generation toward feasible final samples. We further propose a terminal-estimate variant that avoids accumulating local truncation errors by evaluating the reward and constraints at the predicted terminal point rather than at the end of the current horizon. Under standard regularity assumptions, we establish finite-horizon guarantees on suboptimality. Under convex-affine structure, we derive a sharper bound that scales linearly with omitted horizon length, and we show that the terminal-estimate variant is provably tighter when the flow dynamics change slowly. Experiments in both low- and high-dimensional settings with a recent large-scale flow matching model show that ConicFlow achieves high reward and strong constraint satisfaction while deviating less from the pretrained flow than recent baselines.
Read the full abstract ▾
All authors Shervin Khalafi, Kasra Fallah, Sung Cho, Dongsheng Ding, James Anderson, Alejandro Ribeiro
Machine Learning
Learning to See through Action: Predictive Curiosity for Robots
Stelios Zarifis, Panagiotis Filntisis, George Retsinas et al. (+1 more)
Humans and animals do not learn
vision from a fixed set of data: they move, interact, and learn from the visual consequences of their actions. Motivated by this developmental view, we study whether
robots can improve visual learning by actively collecting experience through curiosity-driven interaction. We introduce DySCOVER, a self-supervised framework for active
robot visual learning. A
robot observes RGB frames, learns a visual autoencoder that encodes and reconstructs them, and trains a recurrent world model to predict the next visual latent state conditioned on the current state and action. The
agent's policy is trained only with intrinsic rewards: reconstruction error encourages visually novel observations, while the world model's error encourages transitions whose consequences are not yet predictable. This prediction error biases the policy toward more intricate trajectories that enrich the
agent's set of experiences with observations beyond those encouraged by visual novelty alone. Our experiments conducted with robotic arms as the embodied
agents show that adding predictive curiosity improves the
vision model over using visual curiosity alone. Across variations in initial conditions, experience capacity, embodiment, and scene content, adding predictive curiosity consistently improved visual learning. These results show that predictive curiosity can improve active visual learning beyond reconstruction-based curiosity alone.
Read the full abstract ▾
All authors Stelios Zarifis, Panagiotis Filntisis, George Retsinas, Petros Maragos
Machine Learning · Cross-listed from cs.SE
Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances
Konstantin Ievtushenko, Ralf Lämmel and Jan Jürjens
High
benchmark scores in learning-based vulnerability detection mask severe degradation under distribution shifts. This paper demonstrates that calibrated
embedding geometry exposes these hidden generalization boundaries on syntactically similar vulnerable and patched code pairs. An evaluation of CodeBERT and Qwen2.5-Coder across pattern, project, and temporal shifts on a strictly paired
dataset reveals three main findings. First, whitened intermediate-layer
embeddings with local nearest-neighbour scoring separate unfamiliar samples with a mean out-of-distribution AUROC of 0.739 (RQ1). Second, distance scores reveal a shift-specific reliability gradient where accuracy drops by over 35 percentage points and cross-project shifts cause the sharpest degradation, even though temporal shifts drift geometrically farthest (RQ2). Third, false positives on patched code systematically correlate with
geometric proximity to vulnerable training neighbourhoods, increasing from 9.4% in the lowest-risk decile to 58.8% in the highest (RQ3). These calibrated distances establish a diagnostic signal that maps representation geometry directly to model degradation without requiring auxiliary models.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
GeoFix: Geometry Fixing for 4D Consistent Generation
Yeobin Hong, Hyojun Go, Dohun Lee et al. (+7 more)
Video diffusion models increasingly serve as priors for 4D generation, but the generated
videos often lack
geometric consistency. Recent approaches address this through post-training by designing
geometric rewards, yet this can degrade texture and fine detail, requiring auxiliary appearance rewards and careful reward balancing. To address this challenge, we propose GeoFix, a unified framework that improves
geometric consistency and visual quality with a single
geometric reward, applicable to both training and inference-time reward
alignment. Our reward measures cross-view depth consistency in static scene regions, targeting structural inconsistencies without directly constraining appearance or penalizing valid object motion. Crucially, depth agreement increases with camera field-of-view overlap even in real
videos and 4D
datasets, allowing a smaller camera movement to be mistaken for better geometry. We account for this effect by calibrating the reward against the overlap-dependent trend. GeoFix achieves a 39% improvement in WorldScore 3D consistency and a 4% increase in VBench Quality Score.
Read the full abstract ▾
All authors Yeobin Hong, Hyojun Go, Dohun Lee, Jeongjae Lee, Sunghwan Hong, Federico Tombari, Zhaochong An, Jong Chul Ye, Konrad Schindler, Dominik Narnhofer