Computation and Language
Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
Laura van Weesep, Riccardo Tedoldi, Jens Sjölund et al. (+6 more)
The emergence of foundation models for molecular property prediction requires a high degree of AI data readiness, including reliable metadata annotation. However, both public repositories and industrial screening databases suffer from missing, inconsistent, or conflated assay annotations. In this work, we quantify the extent of missing annotations in PubChem for the BioAssay Ontology (BAO) assay format and physical detection method fields and investigate whether open-source and proprietary large
language models (LLMs) can reliably predict and audit metadata annotations directly from the assay text. In our assessment, we found that the annotation coverage across PubChem's $\sim$2 million bioassays is critically sparse, 36% lacking an assay format, 89% a BioAssay type, and >99.9% any BAO-mapped assay format or detection technology term. This motivates the need for automated test-metadata curation. Using evaluation sets derived from PubChem and ChEMBL, we assess the agreement of seven open-source and proprietary LLMs with existing silver labels. Recall is at least 0.96 for biochemical and
cell-based assay formats, with a similar pattern for detection technology, although disagreements increase on under-represented classes. Manual inspection shows that many of these disagreements trace back to inconsistencies between silver sources rather than to LLM error. Moreover, in a qualitative study with a senior industrial curator, LLM-generated evidence prompted the expert to revise some of their own labels, showing LLMs can flag potentially mislabeled assays. Across the study, performance differences between proprietary and open-source models were small. Together, these results suggest LLMs can support the large-scale annotation and
auditing of assay metadata, though per-class reliability estimates and targeted human review remain necessary before such labels enter downstream ML pipelines.
Read the full abstract ▾
All authors Laura van Weesep, Riccardo Tedoldi, Jens Sjölund, Hossein Azizpour, Susanne Winiwarter, Ola Engkvist, Jon Paul Janet, Samuel Genheden, Juan Viguera Diez
Computer Vision
Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models
Xindi Yang, Baolu Li, Liam Lee et al. (+8 more)
Generative
video world models can now synthesize open-ended environments that
agents can navigate and interact with in simple ways. Yet open-ended generation does not imply full interaction: as a generated world expands, newly created content through
navigation should expand what the
agent can act upon, and as the
agent changes the world, those changes should become persistent parts of the environment rather than transient visual effects. We characterize these two requirements as Open-World Interactivity, where newly generated or encountered entities are incorporated into the actionable world, and Persistent State, where interaction outcomes are committed to the world state and continue to influence subsequent observations and interactions. We present Oneira, an interactive
video world model that closes the loop between generation and interaction through an explicit, extensible world state managed by a coding
agent. Given the current observation and an action or high-level goal, the
agent reads the world state, grounds the relevant entities, plans the interaction, and writes its outcome back into a world state table. When exploration reveals new objects, the
agent incorporates them from generated observations, allowing the interaction space to expand with the generated world. Meanwhile, previously induced state changes are carried across
video segments, making the consequences of interaction persistent parts of subsequent world
evolution. The updated world state is rendered along the camera action trajectory into a coarse conditioning
video, from which a
video generator fills in the appearance, motion, and interaction details not represented in the state. Experiments show that Oneira enables direct and consistent interaction with newly generated objects, while preserving the effects of prior interactions over long horizons. Project page: https://madaoer.github.io/projects/oneira
Read the full abstract ▾
All authors Xindi Yang, Baolu Li, Liam Lee, Zhenfei Yin, Songxin Zhang, Zhuoyang Song, Xu Jia, Jianfei Cai, Tien-Tsin Wong, Bingyi Jing, Mengyue Yang
Robotics
ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation
Kuankuan Sima, Yichao Gao, Chenxi Gu et al. (+2 more)
Continuous legged manipulation requires accurate end-effector tracking while the base keeps walking. Combining reinforcement learning (RL) with model predictive control (MPC) suits this task: the learned policy provides robust locomotion, while MPC coordinates the base and arm to compensate for tracking errors. However, MPC can compensate only for base motion that it can predict, and a learned policy's command response varies with gait phase, contact, and payload. We present ReCo, a framework that couples response-consistent locomotion with policy-aware MPC for legged manipulation. Response shaping trains the policy to respond to commands consistently and repeatably across randomized dynamics. An identified closed-loop response model then lets MPC jointly plan locomotion commands and arm motion. On the simulation
benchmark, ReCo reduces position and orientation root-mean-square error (RMSE) by 28.7% and 27.4% relative to the best baseline for each metric. Real-world experiments demonstrate onboard continuous legged manipulation with coordinated base and arm motion.
Read the full abstract ▾
All authors Kuankuan Sima, Yichao Gao, Chenxi Gu, Kefan Zhao, Lin Zhao
Software Engineering
Architectural Degradation: How to Measure and to Remediate
Noman Ahmad, Ruoyu Su, Matteo Esposito et al. (+3 more)
Context. Architectural degradation undermines software maintainability, evolvability, and quality. However, existing research remains fragmented across measurement approaches, metrics, tools, and remediation strategies, limiting our understanding of how these elements relate across the degradation lifecycle. Aim. We consolidate the state of the art on architectural degradation by examining how researchers measure it, which metrics and tools support its assessment, and how existing approaches address remediation. Method. We conducted a Multivocal Literature Review of 284 peer-reviewed and grey-literature studies. We supported screening, data extraction, and classification with a locally executed LLM-assisted pipeline combining
Retrieval-Augmented Generation, multi-model validation, and human adjudication. We then analyzed the resulting taxonomies and their cross-dimensional relationships. Results and Conclusions. We identified 277 measurement approaches, 357 metrics, 238 tools, and 395 remediation approaches. Research strongly concentrates on static and structural analysis, structural metrics, and detection-oriented tools. In contrast, remediation spans heterogeneous code-level, architectural, and organizational interventions and shows substantially less consolidation. Overall, the field has developed a mature diagnostic apparatus but has made less progress in connecting degradation detection with effective remediation. Our results provide a structured view of the available techniques and identify the diagnosis-remediation gap as a key direction for future research.
Read the full abstract ▾
All authors Noman Ahmad, Ruoyu Su, Matteo Esposito, Andrea Janes, Valentina Lenarduzzi, Davide Taibi
Computer Vision
Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning
Yuzhou Wang, Emile Anand and Ijay Narang
Reliable visual
reasoning requires composing multiple visual observations and returning consistent answers to logically equivalent questions. We introduce Hob-VL, a
benchmark for visually grounded Boolean
reasoning. Hob-VL comprises two tasks: (1) evaluating whether a Boolean rule holds in an image, and (2) identifying the (unique) object satisfying a Boolean description. Hob-VL contains 6,000 human-verified balanced Yes/No questions, each defined by a Boolean combination of ten visual statements, across 1,000 generated scenes and 46 diverse labeled photographs, along with 1,000 object-identification questions over the same photographs. Our question families are deliberately constructed to challenge
reasoning through misleading local cues and nested logical operations, and include symbolic and structured natural-
language presentations. Across eight model configurations with thinking disabled or minimized, Boolean accuracy ranges from 48.52% to 50.57%, while the identification accuracy reaches at most 43.0%. A thinking-enabled GLM configuration achieves uneven gains while retaining substantial errors and inconsistencies. Hob-VL exposes these failures through executable reference answers and matched evaluations.
Read the full abstract ▾
Hardware Architecture
U-Sonic: An Open-Source 8-Channel Ultrasound Transmit IP in a 130 nm RISC-V SoC
Federico Villani, Nico Canzani, Marc-André Wessner et al. (+5 more)
Miniaturized ultrasound (US) probes require programmable and synchronized transmit (TX) excitation across multiple elements, while existing compact platforms often rely on limited microcontroller (MCU) pulse generators or closed-source fixed-function pulser devices. We present U-Sonic, an open-source digital US TX peripheral integrated into a 32-bit RISC-V system-on-chip (SoC). The implemented SoC integrates 8 pulser cores, while the parameterized architecture supports up to 16 channels. Each core generates single- or dual-tone bursts with programmable period, duty cycle, pulse count, polarity, and idle level, together with optional inverted stop pulses for active damping. A shared
memory-mapped Open Bus Interface (OBI) enables synchronous start and stop of arbitrary channel subsets and supports composite bipolar, gated, and three-level excitation schemes. Functional correctness was verified in Verilator against a Python golden model over 4379 checked cycles across directed and randomized configurations, and confirmed on a Terasic DE10-Lite field-programmable gate array (FPGA). The design was synthesized and placed-and-routed in IHP 130 nm. The post-layout area in kilo gate equivalents (kGE), scales as 1.65 kGE plus 1.66 kGE per channel. The 8-channel instance occupies 14.9 kGE, corresponding to approximately 14.3% of the 104 kGE SoC. The register-transfer level (RTL), register descriptions, verification collateral, and software support are released as open source.
Read the full abstract ▾
All authors Federico Villani, Nico Canzani, Marc-André Wessner, Philippe Sauter, Enrico Zelioli, Andrea Cossettini, Christoph Leitner, Luca Benini
Hardware Architecture · Cross-listed from eess.SP
Open-Source Live-Reconfigurable Multi-Mode Wearable Ultrasound
Cédric Hirschi, Federico Villani, Luca Benini et al. (+1 more)
Wearable ultrasound enables continuous deep-tissue monitoring, and a single programmable probe can operate in multiple complementary modes, such as structural A-mode and Doppler flow measurement. However, each operating mode requires dedicated measurement parameters and peripheral states, with no single configuration serving all modes on resource-constrained devices. Time multiplexing of operating modes introduces reconfiguration latency that lowers the effective mode repetition rate. To address this limitation, we present an open-source, transition-aware control stack for low-latency, in-session reconfiguration of the 32-channel TinyProbe wearable platform. Operating modes are described as hardware configurations, and host-side shadow registers track the peripheral states, enabling transition-specific register updates. Transition sequences are executed either by the host (over Wi-Fi 6) or by a firmware loop on the probe MCU. We validate the stack on a pulsatile-flow phantom by interleaving blocks of 25 to 100 pulsed-wave Doppler shots at 1.43 kHz PRF with single 16-channel A-mode acquisitions, changing channel configurations at every transition. Compared to full reconfiguration, the overhead per transition decreases from 30.2 ms to 11.6 ms (host-scheduled) and 3.1 ms (MCU-scheduled). For 75-shot Doppler blocks, the multi-mode repetition rate reaches 16.0 Hz (MCU-scheduled), 90.1% of the theoretical maximum of 17.7 Hz. Concurrent reconstruction of a Doppler spectrogram and a lumen-diameter trace demonstrates the functionality of time-multiplexed flow and structural monitoring.
Read the full abstract ▾
All authors Cédric Hirschi, Federico Villani, Luca Benini, Andrea Cossettini
Machine Learning
Permutation-Robust Decision Modeling with Candidate-Independent Block-Causal Attention
Guy Amit
Decision models often score a variable-sized set of candidate actions encoded in a single sequence. This setting is increasingly relevant for System 1 components inside generative systems, where candidates may be proposed or ordered differently across runs. Standard causal cross-encoding is expressive, but it can make a candidate's score depend on serialization order rather than on the underlying decision problem. We introduce candidate-independent block-causal
attention, which preserves causal computation within the shared context and each candidate while blocking cross-candidate information flow and resetting candidate positions. We compare this architecture with standard causal
attention and complementary invariant baselines across Gemma 3 1B, Qwen3 1.7B, and Qwen3 4B backbones. Candidate-independent
attention consistently reduces permutation sensitivity while retaining competitive decision quality; ablations indicate that candidate isolation is the primary source of the effect, with position resetting completing the intended
symmetry. A larger Qwen3-4B study further examines the behavior of the proposed architecture with substantially more training data. Code is available at the \href{https://github.com/guyAmit/ci-decision-models}{\textcolor{blue}{project repository}}, and the \href{https://huggingface.co/Guy-Amit/qwen3-4b-ci-decision-4096-poc}{\textcolor{blue}{Qwen3-4B model artifact}} is available on Hugging Face.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Convergence Analysis of STORM Under Different Geometries
Wei Jiang, Yibo Wang, Wenhao Yang et al. (+3 more)
Stochastic recursive momentum (STORM) achieves fast convergence for nonconvex optimization via the variance reduction effect, but existing analyses rely on the strong average smoothness assumption. In this paper, we study the convergence of STORM for different objectives without average smoothness. We first revisit the results under average smoothness, obtaining the $O(T^{-1/3})$ bound for nonconvex objectives and the $O(\sigma^2/(\mu T))$ bound for last-iterate output under the $\mu$-Polyak–Łojasiewicz~(PL) condition. Without average smoothness, we design an auxiliary sequence and compare the STORM update with it in the analysis. With the help of this sequence, we prove that STORM still attains an $O(T^{-1/4})$ rate for nonconvex objectives, which is optimal under standard smoothness. For convex and $\lambda$-strongly convex objectives, we further prove averaged and last-iterate bounds with optimal rates of $O(\sigma R/\sqrt T)$ and $O(\sigma^2/(\lambda T))$, respectively. All the obtained results use the same STORM recursion with different hyperparameter choices.
Read the full abstract ▾
All authors Wei Jiang, Yibo Wang, Wenhao Yang, Rui Yan, Lijun Zhang, Zechao Li
Computer Vision
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
Youngwoo Shin, Yusung Ro, Minseo Kim et al. (+1 more)
Video Large
Language Models (VideoLLMs) receive frames in sequential order and interpret how visual content evolves along the temporal axis, yet temporal
reasoning remains a persistent weakness across architectures. Reversing the frame order of a
video, a transformation that should invert temporal answers, often leaves the final prediction unchanged. We investigate where this failure originates by defining the temporal divergence vector $\tau_l$, the layer-wise representational difference induced by reversing temporal order. Tracking its magnitude across layers reveals a consistent temporal divergence profile where the divergence peaks at intermediate layers and progressively diminishes toward the output. We confirm this peak is specific to temporal
reasoning and functionally critical for predictions, establishing that VideoLLMs acquire temporal information at intermediate layers but fail to maintain it to the output. This progressive fading motivates our method, Temporal Activation Injection (TAI), which extracts $\tau_l$ at the peak of the profile for each input and reinjects it into subsequent layers following the measured decay. TAI requires no training and consistently improves temporal
reasoning across three VideoLLMs and four
benchmarks with negligible impact on non-temporal tasks. Code is available at https://github.com/Youngwoo-git/Before-It-Fades.
Read the full abstract ▾
All authors Youngwoo Shin, Yusung Ro, Minseo Kim, Junmo Kim
Numerical Analysis · Cross-listed from physics.flu-dyn
An unstructured finite-volume Helmholtz method with perfectly matched layers for heterogeneous two-phase acoustics
Chuanchao Xu, Jun Liu, Jan Helge Dörsam et al. (+3 more)
This paper presents a
cell-centred unstructured finite-volume method for time-harmonic two-phase acoustics. A volume-fraction representation supplies density and acoustic compressibility. Face fractions average available neighbouring planar interface cuts independently of velocity direction, retaining the established one-field face-density closure. Cartesian complex-coordinate stretching provides perfectly matched layers (PMLs). Real-imaginary splitting yields a real-valued block system, discretized with corrected non-orthogonal fluxes and consistent boundary contributions. Verification covers homogeneous waves, layered gas-
liquid transmission with PML truncation, baffled-piston radiation with Kirchhoff far-field reconstruction, and resolved rigid-sphere radiation forces. Homogeneous-wave pressure converges at approximately second order on orthogonal meshes and on meshes with non-orthogonal interiors and orthogonal boundary
cells. Reconstructed velocity converges at approximately second order on orthogonal meshes and with an observed order of about 1.7 on the latter mesh family. Under aligned refinement, the layered case's relative whole-domain complex-pressure $L_2$ error decreases to $2.657\times10^{-4}$. The resolved-sphere force differs from the Gorkov prediction by at most 1.5% over the tested Rayleigh size range. The results quantify the accuracy and current limitations of the heterogeneous Helmholtz-PML formulation.
Read the full abstract ▾
All authors Chuanchao Xu, Jun Liu, Jan Helge Dörsam, Mario Kupnik, Tomislav Maric, Dieter Bothe
Computation and Language
Which LLM to pick? Online Active Model Selection for Large Language Models
Alessandro Turrin, Patrik Okanovic, Torsten Hoefler et al. (+1 more)
Large
Language Models (LLMs) are increasingly applied to process streaming data, with practitioners relying on
benchmarks to select the best model even though these signals only approximate real performance. While oracle annotations can provide reliable feedback, they are often costly and difficult to obtain at scale. To address this challenge, we propose ONLINE LLM PICKER, the first framework for active model selection for LLMs in online settings. Given an arbitrary stream of queries and a limited annotation budget, ONLINE LLM PICKER selects the most informative
prompts for annotation to identify the best LLM among candidate models. Across multiple tasks including 10
datasets, for over 130
language models, we show that ONLINE LLM PICKER saves annotation cost by up to 71.67% while reliably identifying the best or near-best model for the stream. We also show that using the returned model for sequential generation on unannotated
prompts across the stream reduces regret by up to a factor of 2.51x, indicating that ONLINE LLM PICKER can identify the best or near-best model well before processing all streaming
prompts.
Read the full abstract ▾
All authors Alessandro Turrin, Patrik Okanovic, Torsten Hoefler, Nezihe Merve Gürel
Data Structures and Algorithms
Stable and Online Algorithms for Random Matrix Discrepancy
Eren C. K{\i}z{\i}ldağ and Shuangping Li
We study the average-case
matrix discrepancy problem: given independent normalized $d\times d$ Gaussian orthogonal ensemble
matrices $A_1,\dots,A_N$ and a fixed margin $\kappa>0$, find signs $\sigma_1,\dots,\sigma_N\in\{-1,1\}$ such that the operator norm of $\sum_{i=1}^N \sigma_i A_i$ is at most $\kappa\sqrt{N}$. Focusing on the proportional regime $N/d^2\to \tau\in(0,\infty)$ as $d\to\infty$ followed by the small-margin limit $\kappa\downarrow 0$, we characterize the density required by stable offline
algorithms and by online
algorithms. In the offline setting, we construct a
polynomial-time recenter-and-round
algorithm that is noise-stable and succeeds whenever $\tau=\Omega(\frac{1}{\kappa^2\log(1/\kappa)})$, along with a matching lower bound for all stable
algorithms. In the online setting where each sign must be chosen irrevocably upon observing the corresponding
matrix, we determine the exact limiting performance of the Frobenius-greedy
algorithm, establishing that it succeeds when $\tau>\tau_{\rm FG}(\kappa)\sim \frac{\pi}{4\kappa^2}$, as well as a matching lower bound for all online
algorithms by conditioning on a revealed prefix. At the core of our
algorithms lies rotational
symmetry, which enables us to transfer Frobenius norm control into operator norm guarantees. Together, our results identify the algorithmic phase transition points for random
matrix discrepancy: $\Theta(\frac{1}{\kappa^2\log(1/\kappa)})$ for stable offline
algorithms and $\Theta(\frac{1}{\kappa^2})$ for online
algorithms. Both thresholds lie far above the satisfiability scale $\Theta(\log(1/\kappa))$, as shown by Maillard~\cite{maillard2025}.
Read the full abstract ▾
Machine Learning
Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize
Yuan Huang, Zihan Chen, Runbin Zhang et al. (+3 more)
Continual learners that keep a task-specific adapter in every block of a pre-trained
vision transformer accumulate storage linearly with the number of tasks; keeping task-specific adapters in only a few blocks curbs this growth but raises the question of where to place them. We investigate this question from two perspectives. Algorithmically, training all contiguous four-block placements yields an inverted U: final accuracy peaks at intermediate depth and varies by up to 3.5 percentage points (pp), while inexpensive criteria based on weight spectra or activation statistics favor the deepest blocks. From neuroscience, the hierarchical organization and intermediate-stage plasticity of the visual cortex motivate us to ask whether a measurement taken outside the learner can guide layer specialization without placement search. LS-B observes the first tasks through a frozen fMRI encoding model of twelve human visual areas and commits task-specific capacity once to the blocks whose readouts vary most across tasks relative to their stable structure. Across three ViT-B/16 backbones, LS-B yields stable, backbone-specific allocations. On the two backbones with placement search, AugReg and iBOT, the selected blocks overlap the intermediate-depth region identified by search. Under matched storage and observation budgets, the selected blocks outperform the shallowest and deepest four-block configurations. On Split ImageNet-R, LS-B uses 60% of full-BiLoRA adapter storage while remaining within 1.5 pp of its final accuracy. The allocation requires no labels or backpropagation, adds under 0.6% runtime, and exhibits backbone-specific cortical signatures.
Read the full abstract ▾
All authors Yuan Huang, Zihan Chen, Runbin Zhang, Hongwei Ding, Changzeng Fu, Shiqi Zhao
Computer Vision
Akira-Miranda Adeyomi Adeniran-Lowe, Binod Singh, Lars Arnold Dethlefsen et al. (+2 more)
Pretrained 3D encoders are typically developed on globally reconstructed scenes expressed in a consistent world coordinate frame, whereas
embodied systems must reason from partial, viewpoint-dependent observations in camera coordinates. We show that this shift from globally learned 3D feature spaces to realistic partial observations exposes a severe representation mismatch, which we find consistently across representative state-of-the-art encoders, including Sonata and Concerto. A frozen Sonata encoder with a global linear probe achieves 72.47 mIoU on full ScanNet scenes, but 2.57 mIoU on single-frame camera-coordinate inputs. Training-free
gravity alignment recovers performance to 41.64 mIoU, showing that coordinate-frame mismatch is a dominant source of degradation but cannot be fully resolved through canonicalization alone. We introduce PAGER, a label-free adaptation method that aligns partial-view features with a frozen global 3D semantic space using only paired partial/global geometry. It learns lightweight adaptation modules while keeping the pretrained encoder and global
segmentation probe frozen. Matched-point feature
alignment anchors partial features to their global counterparts, while relational supervision preserves their similarity structure with respect to the global representation. Global geometry provides supervision only during training. Inference operates directly on the partial observation. Without partial-view labels, PAGER outperforms label-supervised PEFT on both Sonata and Concerto, and in zero-shot ScanNet$\rightarrow$ScanNet++ transfer surpasses fully fine-tuned Sonata ($53.93$ vs.\ $48.09$ mIoU), suggesting that preserving the frozen global representation can improve cross-
dataset transfer.
Read the full abstract ▾
All authors Akira-Miranda Adeyomi Adeniran-Lowe, Binod Singh, Lars Arnold Dethlefsen, Lazaros Nalpantidis, Theodora Kontogianni
Distributed Computing
Exploiting the Interplay of Compute- and Memory-Bound kernels in MPI Applications
Ayesha Afzal, Krishna Manda and Georg Hager
Parallel applications are often designed for synchronous, lock-step execution, treating communication stalls as performance hazards. Yet, in a communication-light application without frequent synchronization points that alternates between compute-bound
memory-bound execution, an MPI communication stall can act as an unintentional relief on
memory-bandwidth contention. We demonstrate this using a Parallel Optical Flow Solver, which combines a compute-bound Ray Tracing kernel with a
memory-bound Optical Flow Solver kernel and negligible inter-process communication. This program shows considerable speedup via desynchronization and automatic overlap between compute- and
memory-bound phases, showing that natural desynchronization is an architecture-aware optimization. An optimal speedup is achieved when the number of processes concurrently executing the
memory-bound phase on a ccNUMA domain is near the bandwidth saturation point. We also show a case where reducing communication overhead using MPI asynchronous progress significantly degrades performance because it allows too many ranks to contend for
memory bandwidth simultaneously. In order to study the dynamics under more controlled conditions, we develop a tunable dual-kernel microbenchmark, with which we show that significant application or system noise (natural or injected) is required to achieve full desynchronization. Finally, we also validate these results using a bandwidth-aware, model-based simulator.
Read the full abstract ▾
Neural and Evolutionary Computing
Continual Reinforcement Learning with Neuroevolution
Eleni Nisioti, Andrea Cossu, Kathrin Korte et al. (+1 more)
Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet consistently achieved a good balance between adaptation and forgetting. Here we turn to an alternative optimization paradigm, neuroevolution (NE):
algorithms that search directly in weight space through mutation and selection over a population of neural networks. Across a wide array of environments and environmental changes, with policies ranging from a few hundred parameters to million-parameter networks, we compare
evolution strategies (ES) and genetic
algorithms (GAs) against state-of-the-art continual RL variants and population-based RL. ES most consistently achieves a good stability-plasticity trade-off, while the GA is the most plastic method but forgets more than ES. To explain this, we study the return landscape around each method's solutions. ES finds the widest neighborhoods, i.e.\ regions of weight space in which perturbed policies still solve the task, and the size of the overlap between the neighborhoods of consecutive tasks correlates with a method's stability-plasticity trade-off. Rewarding behavioral diversity in a GA through novelty search makes the population even more plastic, at the cost of forgetting. Finally, symptoms of plasticity loss commonly reported in RL do not transfer to NE. Overall, these results establish NE as a competitive alternative to RL under continual task changes, and suggest that training under perturbations in weight space may be a useful mechanism for continual learning more broadly.
Read the full abstract ▾
All authors Eleni Nisioti, Andrea Cossu, Kathrin Korte, Sebastian Risi
Artificial Intelligence
Evaluating Physical Consistency and Plausibility in Generative Scenario Models for Autonomous Driving
Manasa Mariam Mammen, Zafer Kayatas and Stefan Wagner
Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited transparency into learned representations and consistency with real-world vehicle dynamics. This lack of formal assurance limits their use in safety-critical validation and certification workflows. To address this aspect, we introduce a layered evaluation protocol that complements existing methods by assessing models across five layers. The first four layers inspect internal representations and network layers through kinematic
alignment, statistical baseline comparison, latent controllability, and activation analysis. The fifth layer evaluates model outputs against vehicle dynamics constraints such as lateral jerk thresholds. We demonstrate the protocol on a Variational Autoencoder (VAE)-based scenario generator. Although standard output-level metrics and visualizations suggest that the generated scenarios are realistic, our protocol provides deeper insight into the extent to which the model's latent space aligns with kinematic features and whether visually plausible trajectories satisfy vehicle-dynamics constraints. We further apply the protocol to additional generative models, demonstrating its applicability beyond the VAE architecture.
Read the full abstract ▾
Cryptography and Security
Protocol Integration of Physical Layer Deception into EAP-TEAP Wi-Fi Authentication
Moustafa Ibrahim, Bin Han and Hans D. Schotten
Credential-based Extensible Authentication Protocol (EAP) authentication cannot distinguish a legitimate credential holder from an adversary using compromised credentials. Physical Layer Deception (PLD) complements credential-based authentication by exposing a deceptive primary object over a primary transport while a separate recovery object travels with differentiated reliability over a secondary channel. Existing PLD studies remain, to our knowledge, at the physical/link-model level; using PLD's activation/deactivation mechanism as an authentication gate creates an authentication-specific design requirement, since an all-inactive attempt would exercise no recovery path. We present a batched PLD-based re-verification step for Enterprise Wi-Fi's TEAP/RADIUS/IEEE 802.11 authentication chain, implemented end to end across the server, access point, and device in the open-source hostap 2.12 codebase. Each attempt carries three rounds, at least one active, with no dedicated activation flag. Across four campaigns totaling 1593 attempts, the prototype evaluates batched recovery behavior, rejects the implemented naive credential-bearing attacker in all 30 attempts, measures successful-path latency, and evaluates the security-reliability trade-off for one, two, and three active rounds under two modeled recovery regimes. The evaluation exercises the protocol and software-MAC behavior directly and analyzes informed and retry-seeking attackers under the software recovery model.
Read the full abstract ▾
Machine Learning
Beyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling
Loys Masquelier and Etienne Le Naour
Climate downscaling aims to reconstruct fine scale spatial fields from coarse resolution inputs. Evaluating the quality of these reconstructions is challenging: low pointwise error can come at the cost of fine scale variability, while realistic spatial variability can be achieved with inaccurate local structures. The evaluation metric can therefore change which method appears to perform best. This work presents a multi metric
benchmark comparing five spatial downscaling methods on ERA5 temperature, wind, and precipitation fields. Five criteria assess complementary properties: pointwise error, structural similarity, distribution error, spectral error, and gradient error. The results reveal a systematic trade off between spatial fidelity and fine scale variability. Some methods perform best on pointwise and spatially aligned metrics, but lose high frequency content, while others preserve substantially more spectral variability at the cost of less accurately positioned local structures. Consequently, method rankings change across metrics and variables. These results show that there is no single best downscaling method. Multi metric evaluation is therefore essential for assessing which properties of a
climate field are preserved.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
The hidden advantage of mask resampling: a theory of masked autoencoders
Jorge Medina Moreira, Lorenzo Bardone and Lenka Zdeborová
Why can masked prediction learn useful representations that unmasked reconstruction misses? We study this question in a high-dimensional model of a masked autoencoder (MAE) trained on data with shared latent structure and heterogeneous noise. We prove that masked linear reconstruction can recover the latent feature at linear sample complexity in regimes where unmasked linear reconstruction, equivalent to PCA, fails. The analysis also quantifies the statistical advantage of mask resampling, an established ingredient of masked pretraining. By introducing a fixed collection of $K$ masks per sample, we characterize its effect on feature recovery and downstream performance, identifying regimes where greater mask diversity lowers sample complexity. Guided by this prediction, we find that random cropping and flipping in standard image-training pipelines can obscure the advantage of mask resampling by renewing the prediction task even when the patch mask is fixed. Removing these transformations reveals a downstream advantage for dynamic over static masking in CNN autoencoders and
vision transformers. A complementary BERT pilot finds benefits from greater mask diversity on downstream
language tasks. Our results separate the benefit of the masked prediction objective from that of mask diversity, and show how a tractable theory can guide experiments that uncover advantages hidden by standard training practices.
Read the full abstract ▾
Robotics
LiDARFlow: Real-Time Panel-Based MAV Guidance in Unknown Environments
João Machado, Zeynep Bilgin, Matthieu Verdoucq et al. (+1 more)
This paper presents a guidance
algorithm for micro aerial vehicles operating in unknown, cluttered environments using only onboard sensing. The method is based on a panel formulation originally derived from aerodynamic potential-flow theory and generates smooth, collision-free guidance vectors from locally perceived obstacles. The approach is extended to unknown environments by constructing and updating the obstacle representation online from onboard
LiDAR measurements. The resulting obstacle-avoidance field is integrated with a nominal guiding vector field to produce the final control input. The system is experimentally validated in indoor flight tests under two scenarios: waypoint
navigation and directional guidance. In both cases, the vehicle successfully completes its task while avoiding all obstacles in real time using only onboard perception. The results demonstrate that the method is computationally lightweight and suitable for onboard implementation, with pointcloud processing identified as the main practical limitation. These results support the feasibility of lightweight onboard guidance in unknown environments.
Read the full abstract ▾
All authors João Machado, Zeynep Bilgin, Matthieu Verdoucq, Murat Bronz
Machine Learning · Cross-listed from math.OC
Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization
Wei Jiang, Rui Yan, Sifan Yang et al. (+3 more)
This paper investigates
stochastic multi-level optimization where the objective is a nested composition of several smooth non-convex functions. We assume that only
stochastic estimates of the gradient and function values for each level are accessible. Consequently, obtaining an accurate estimate of the overall gradient is challenging due to the nested structure. To address this, we employ a momentum-based
estimator with mini-batches to track the function values of each level, which are subsequently used to construct momentum gradient
estimators. We establish an optimal sample complexity of $\mathcal{O}(\epsilon^{-4})$ for finding an $\epsilon$-stationary point, avoiding the stronger average smoothness assumption commonly relied upon in prior literature. Furthermore, by employing a normalization technique, we attain the same rate without requiring problem-dependent constants to set hyperparameters. To achieve the optimal rate without mini-batches, we further develop a batch-free method that incorporates a first-order approximation and a clipping technique for function value estimation. Finally, we validate the effectiveness of our proposed methods through experiments on risk-averse portfolio optimization and hierarchical tilted empirical risk minimization.
Read the full abstract ▾
All authors Wei Jiang, Rui Yan, Sifan Yang, Yuanyu Wan, Lijun Zhang, Zechao Li
Multiagent Systems
Managing Context and Communication in Distributed Agentic UAV Swarms
Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta et al. (+2 more)
Unmanned aerial vehicle (
UAV) swarms increasingly rely on
language-model
agents to provide adaptive mission-level
reasoning in uncertain environments. Fully distributed control, in which each
UAV hosts an independent Small
Language Model (SLM), removes reliance on a centralized coordinator but introduces an information-management problem: long-running interaction histories can degrade the
reasoning context, while indiscriminate information dissemination increases communication and inference overhead. We address these challenges with a distributed
UAV-
agent architecture that enables continuous local SLM control through an event-driven reason-act-observe lifecycle. Runtime knowledge is represented as structured atomic notes and organized into core, local, and peer-specific
memory. A deterministic interest-aware gossip engine selectively disseminates these notes according to recipient-specific semantic novelty and recency. We evaluate the architecture using ten
UAVs in a simulated search-and-rescue mission. Our approach completes all experimental runs, whereas unrestricted flooding messages completes only 70-85%, and delegating forwarding decisions to the SLM prevents mission completion in every run. Compared with unrestricted flooding, our approach approximately halves inference-
token consumption, reduces transmitted data, and achieves lower survivor-count error.
Read the full abstract ▾
All authors Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice
Machine Learning
Towards Optimal Policy Improvement
Yaniv Oren, Viliam Vadocz, Wiktor Zabka et al. (+7 more)
Practical Reinforcement Learning (RL)
algorithms learn to solve Markov Decision Processes (MDPs) through iterative policy improvement in the presence of approximate evaluation. We study policy improvement from first principles, defining optimal policy improvement as producing the best policy attainable in a single update under specified constraints. We show that optimal improvement restricted to a set of states is equivalent to solving an induced MDP, characterizing planning with an explicit or implicit model as a path towards optimal policy improvement. Because practical methods commonly solve such induced problems through iterative improvement in the form of greedification, we take steps towards optimal greedification under the central practical constraint of approximate evaluation. We formulate greedification under this constraint as probabilistic decision-making under uncertainty and derive a novel operator that is optimal with respect to the resulting objective. Empirically, the operator and its practical gradient-based approximations improve aggregate performance across GumbelAlphaZero, SAC, ReBRAC and Generalized Policy Iteration, in experiments spanning discrete and continuous actions, model-based and model-free, online and offline RL.
Read the full abstract ▾
All authors Yaniv Oren, Viliam Vadocz, Wiktor Zabka, Thomas Evers, Jan Robine, Wendelin Böhmer, Matthijs T. J. Spaan, Martha White, Hendrik Baier, Fenghui Yu
Cryptography and Security
Chaining Skills to Hijack LLM Agents
Tian Dong, Zixuan Ma, Haodong Zhao et al. (+3 more)
LLM
agents use skills to improve performance on specialized tasks. To complete a user request, an
agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry attacker-controlled claims into later decisions. In this paper, we introduce APEX, which constructs and refines
adversarial skill chains tailored to a user task and an attacker-selected action. The key insight is that an
agent-written record of genuine task progress can carry a false claim of user approval across skills: an upstream skill induces the
agent to create the record, and a downstream skill uses it to direct the attacker-selected action. Across four targeted-action families and six models on SkillsBench, the chains induce the selected action in 512 of 690 attempts (74.2%). On GPT-5.4, the full chain succeeds in 84.3% of attempts, compared with 17.4% when the workflow is merged into one skill. We further evaluate a prompting defense that asks the
agent to check skill-produced files against the original request. On GPT-5.4, it lowers targeted-action success from 84.3% to 59.1%, while the verifier test-pass rate across 72 benign native-skill tasks falls from 86.7% to 56.3%. These results highlight the need for defenses that prevent attacker-directed actions while preserving legitimate task performance.
Read the full abstract ▾
All authors Tian Dong, Zixuan Ma, Haodong Zhao, Huaien Zhang, Shaofeng Li, Hao Chen
Information Theory
Optimal Universal Coding of Integers
Wei Yan, Yunghsiang S. Han and Leqian Zheng
Universal coding of integers (UCI) provides binary codewords for positive integers such that, for every nonincreasing source distribution $P$, the average codeword length stays within $K$ times $\max\{1,H(P)\}$. The smallest constant $K$ is called the minimum expansion factor of UCI $\mathcal{C}$, denoted $C_{\mathcal{C}}^{*}$. The optimal minimum expansion factor $C^*=\inf\{C_{\mathcal{C}}^{*}\}$ is the minimum expansion factor corresponding to the optimal UCI. The optimal minimum expansion factor is currently known to lie in the range $2\le C^*\le 2.0386$. In this paper, we construct a family of one-point plus uniform-tail distributions and prove that, for every universal code, the worst-case ratio is attained by a distribution in this family, so that the family is least favorable for the UCI problem. We further establish an inequality, called the UCI inequality, which plays the same role for UCI as the Kraft inequality does for prefix codes: for any real number $B$, it decides whether $B$ lies below or above $C^*$. Through the UCI inequality, we obtain an equivalent definition of $C^*$. By numerical computation, we determine $C^*=2.000124757036101\cdots$, the first fifteen decimal digits being certified. Once $C^*$ is known, we can theoretically construct the optimal UCI.
Read the full abstract ▾
Computation and Language
AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models
Yuxiang Wang, Kunyu Feng, Yuancheng Wang et al. (+12 more)
Model intelligence and fast response jointly shape the quality of interaction with
speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves
reasoning and audio understanding, but generating intermediate
reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent
reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and
reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, which models a distribution over multiple plausible
reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and
reasoning latency. To provide initial supervision for latent
reasoning, we construct AuralReason-683K: 683K bilingual
speech utterances (about 1,000 hours) with concise CoT for
emotion recognition, empathetic dialogue, and general
reasoning. AURAL-RL then explores beyond these traces, rewarding concise
reasoning that yields high-quality answers and adapting
reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent
reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer
token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.
Read the full abstract ▾
All authors Yuxiang Wang, Kunyu Feng, Yuancheng Wang, Zihang Liu, Shengbo Cai, Qinke Ni, Wan Lin, Tao Feng, Yingda shen, Ming-Hao Hsu, Zhixian Zhao, Liqiang Zhang, Teddy Sun, Steve Yves, Zhizheng Wu
Robotics
Completion Aware Guidance for World Action Models
Seungyeon Kim, Junhoo Lee, Baekseung Kim et al. (+2 more)
World Action Models (WAMs) predict visual futures and
robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consistent predictions omit the transition needed for task completion. In this paper, we show that this failure is not inherent to the world model backbone, but emerges when adapted for short-chunk control, which can repeatedly favor plausible local continuations over task-completing transitions. To address this, we introduce Completion Aware Guidance (CAG), a training-free sampling method that guides generation toward task completion. Across representative WAMs, CAG improves success from 64% to 70% on a RoboTwin 2.0 subset and from 69% to 75% in zero-shot simulation, while reducing task-incomplete imagination from 79% to 40%.
Read the full abstract ▾
All authors Seungyeon Kim, Junhoo Lee, Baekseung Kim, Minkyu Kim, Nojun Kwak
Neural and Evolutionary Computing
Controllable Stochastic Quantization Encoding for Adversarially Robust Spiking Neural Networks
Yujia Liu, Peiyu Liu, Yajing Zheng et al. (+1 more)
Spiking Neural Networks (SNNs) have attracted increasing
attention due to their impressive temporal dynamics, energy efficiency, and
brain-inspired mechanisms. Although SNNs have demonstrated promising performance in image classification tasks, recent studies have shown that they remain vulnerable to
adversarial attacks, where imperceptible perturbations are added to input images to mislead model predictions. Existing defense methods mainly focus on training strategies, while the role of input encoding remains less explored. An observation is that the robustness advantage of Poisson encoding over direct encoding may benefit from its inherent randomness. Motivated by this, we propose a
stochastic quantization encoding method that encodes the input image with controllable randomness adjusted by the quantization scale, thereby improving the
adversarial robustness of SNNs. We further show that this method constitutes a general framework that reduces to both Poisson encoding and direct encoding under different choices of the quantization scale. Since it enhances robustness at the input encoding stage, it can be combined with existing training-based defenses for further gains. Experimental results on CIFAR-10 and CIFAR-100 demonstrate the effectiveness of the proposed
stochastic quantization encoding method. To sum up, this work highlights the importance of input encoding for the
adversarial robustness of SNNs, providing a new perspective for understanding and improving it.
Read the full abstract ▾
All authors Yujia Liu, Peiyu Liu, Yajing Zheng, Tiejun Huang