Computer Vision
Planning-Aligned Pretraining of BEV Representations with Sparse Action-Conditioned Targets for End-to-End Autonomous Driving
Jaeha Song and Soonmin Hwang
End-to-end driving requires planning-relevant bird's-eye-view (BEV) representations, but existing pretraining approaches often rely on task annotations or dense scene reconstruction. We introduce PAVER, Planning-Aligned BEV Encoder Pretraining. From a single
LiDAR sweep, PAVER constructs sparse risk and unknown targets describing occupied and unobserved evidence along rule-based ego motions. A 10K-parameter head predicts these targets from masked BEV features conditioned on the action state, directing supervision toward
geometric constraints on candidate motions. Pretraining requires no driving-task annotations or dense reconstruction. Only the BEV encoder is transferred, preserving the downstream architecture and camera-only inference. On nuScenes, PAVER reduces VAD-Tiny's average collision rate from 0.51% to 0.19%, while improving planning L2, motion prediction, detection, and mapping. The selected VAD-Tiny and VAD-Base schedules use about 36% less estimated total training time than scratch training, including pretraining. On Bench2Drive Town05 Long, PAVER improves UniAD-Tiny's closed-loop Driving Score from 48.45 to 58.79. The project page is available at https://archiiive99.github.io/PAVER.
Read the full abstract ▾
Machine Learning
Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories
Yuan Cao, Yifu Tang, Hangqi Li et al. (+1 more)
Diffusion models generate a sample by traversing a denoising trajectory, a sequence of
stochastic noise-reduction steps that transforms pure noise into a draw from a target distribution. At deployment time, additional computation can improve sample quality without retraining: at each step, the sampler draws several candidate noise samples, scores the resulting predictions with a quality criterion called the verifier, and retains the best candidate at the cost of one network evaluation per candidate. This raises a resource allocation question: given a fixed budget of function evaluations, how should search effort be distributed across the steps of the denoising trajectory? We formulate this as a computational budget allocation problem. First, we show that, to leading order in the step size, the expected gain from evaluating $K$ candidates at a step factorizes into an endogenous, step-specific sensitivity parameter times a universal sample-size factor equal to the expected best of $K$ standard-normal draws. Second, for a fixed sensitivity profile, the optimal allocation solves a separable concave integer program with water-filling structure; at fixed total sensitivity, its advantage over uniform allocation increases with sensitivity dispersion in the majorization order. Third, we prove that when sensitivities vary across instances, no adaptive policy can avoid worst-case regret that grows linearly in the trajectory length, which motivates a design that anchors the allocation offline and adapts online only to recover instance-specific slack. We extend the analysis from independent random search to a broader family of local search operators, and instantiate it as an implementable
algorithm. Experiments on three families of
diffusion samplers show that the proposed allocation attains the quality of the uniform
benchmark with 20 to 50 percent fewer function evaluations.
Read the full abstract ▾
All authors Yuan Cao, Yifu Tang, Hangqi Li, Zeyu Zheng
Machine Learning
Causilo Technical Report
Minyong Cho, Minho Jeong, Dooho Lee et al. (+2 more)
We introduce Causilo, a tabular foundation model (TFM) that combines frontier predictive performance with exceptionally fast inference. On TabArena, Causilo achieves 1785.4 Elo, at a median inference time of 0.10 seconds per 1K test samples. It outperforms TabPFN-3.5-Fast with 31.6% less inference time, placing it on the performance–efficiency Pareto frontier. Causilo follows TabICL's column-then-row architecture but introduces another row-refinement module before row compression. This module exchanges information among
cell representations within each row after column encoding. The refined
cells then visit the context set again through an additional column stage before being compressed into row
embeddings. For inference efficiency, both row stages use cross-
attention through a fixed number of summary
tokens, keeping their
attention cost linear in the number of features. Pretrained on approximately 36M synthetic tables, Causilo delivers strong
benchmark results across TabArena, BeyondArena, and ScoringBench, achieving frontier-level performance with substantially faster inference.
Read the full abstract ▾
All authors Minyong Cho, Minho Jeong, Dooho Lee, Jinmo Lee, Jaemin Yoo
Systems and Control
AoI-Driven Hierarchical Learning for Cooperative Resource Sharing in Multi-Operator UAV Networks
Atefeh Hajijamali Arani, Mahyar Shirvanimoghaddam, Abolfazl Mehbodniya et al. (+2 more)
Uncrewed aerial vehicle (
UAV)-assisted networks provide a versatile paradigm for on-demand connectivity. However, in multi-operator aerial networks (MOANs), the joint optimization of cooperative resource sharing and 3D trajectory control to maintain information freshness is a complex combinatorial problem, which can be shown to be NP-hard. To address this computational complexity, we propose an age of information (AoI)-driven hierarchical deep reinforcement learning (DRL) framework. Specifically, a Dueling Double Deep Q-Network (D3QN) architecture is deployed at both the operator and
UAV decision layers to mitigate overestimation bias and enhance stability in high-dimensional state spaces. To improve system resilience, we introduce an AoI- and load-aware outage compensation mechanism that prioritizes users based on instantaneous transmission demands and temporal freshness. Furthermore, a normalized load exchange balance metric is incorporated to regulate cooperative behavior and ensure resource
fairness across operators. Simulation results demonstrate that the proposed hierarchical D3QN significantly outperforms conventional DRL, non-cooperative, and cooperative
benchmarks, reducing the average AoI by up to 56.1% under severe congestion while ensuring superior inter-operator
fairness and outage mitigation.
Read the full abstract ▾
All authors Atefeh Hajijamali Arani, Mahyar Shirvanimoghaddam, Abolfazl Mehbodniya, Halim Yanikomeroglu, Fumiyuki Adachi
Numerical Analysis
Asymptotic-Preserving Exponential Integrators applied to the Hyperbolic Korteweg-de Vries System
Abhijit Biswas, Sebastiano Boscarino, David I. Ketcheson et al. (+1 more)
We study the application of exponential time integration methods, coupled with
Fourier pseudospectral space discretization, to the
hyperbolic Korteweg-de Vries (KdVH) system. We investigate the asymptotic preserving (AP) properties of such discretizations, showing that, in general, Lawson methods are not asymptotic preserving, because the auxiliary (derivative-approximating) variables do not satisfy the limit
equilibrium manifold, whereas exponential time differencing (ETD) methods are AP for all components, including both the solution variable and the auxiliary variables. We also present an efficient numerical implementation based on an exact formula for the
matrix exponential of this system, and compare it with previously-proposed ImEx Runge-Kutta time integration, showing that exponential methods can be competitive in this context.
Read the full abstract ▾
All authors Abhijit Biswas, Sebastiano Boscarino, David I. Ketcheson, Giovanni Russo
Machine Learning
CurvFlow-DTA: dual-graph discrete Ricci curvature flow for drug–target affinity prediction
Jicheng Ma, Yunyan Yang, Juan Zhao et al. (+1 more)
Graph neural networks are widely used for drug–target affinity (DTA) prediction, and discrete
Ricci curvature has recently been used to characterize molecular graph geometry. Existing
curvature-aware DTA approaches mainly use static
curvature on the drug graph while representing
proteins primarily with sequence-derived features. This leaves pair-adaptive use of graph geometry underexplored, which may limit adaptation to unseen entities in cold-start settings relevant to practical screening. We present CurvFlow-DTA, which replaces a single static
curvature representation with weighted Forman
curvature flow on both molecular and
protein residue–residue contact graphs. A label-independent flow trajectory is precomputed for each entity, and a pair-conditioned selector determines the horizons read by a dual-branch Flow-GINE. A frozen ESM-2 supplies residue-level representations and contact scores used to construct the
protein graph. Inference requires only SMILES strings and
protein sequences, without a bound complex structure. On Davis and KIBA, CurvFlow-DTA improves on the protocol-matched
Ricci-GraphDTA baseline in every warm and cold-start setting. Warm-split mean squared error (MSE) decreases by $19.9\%$ on Davis and $18.9\%$ on KIBA. Across the six cold-start comparisons, MSE decreases by $14.3$–$27.4\%$, with higher concordance index (CI) throughout. Within our compiled set of literature baselines, CurvFlow-DTA achieves the lowest MSE on both warm
benchmarks and across four out of six cold-start evaluation settings.
Read the full abstract ▾
All authors Jicheng Ma, Yunyan Yang, Juan Zhao, Liang Zhao
Robotics
PileBelief: Persistent Physical State for Interaction-Driven World Modeling
Hongyi Lin, Song Zhang, Haiquan Liu et al. (+3 more)
World models allow
robots to anticipate action consequences before execution. This capability is especially valuable in excavation, where each scoop reshapes the terrain and affects subsequent actions. Local observations, however, cannot fully reveal the underlying support and material conditions. We present PileBelief, an interaction-driven persistent world model for partially observed excavation that retains physical evidence beyond the visible surface. It combines an observation-conditioned physical prior with world-addressed deformation
memory and physical-response
memory. Action-aligned reads and gated residual corrections refine terrain-change and outcome predictions. With deployment weights fixed, completed interactions update measured belief, while hypothetical actions advance a separate imagined state. Compared with a current-observation-only baseline, PileBelief reduces five-step joint prediction error by 10.8% and offline action-selection regret by 65.5%. Experiments on Newton/MPM and real excavation
datasets further demonstrate improved terrain-change and bucket-volume prediction. Our method enables multi-step prediction and candidate-action ranking from local observations, even when the underlying soil state is unknown. These results identify persistent physical belief as a useful representation for world models of environments that
robots continually reshape.
Read the full abstract ▾
All authors Hongyi Lin, Song Zhang, Haiquan Liu, Yang Liu, Jinhua Zhao, Xiaobo Qu
Computer Vision
Image Frame Dynamic Object Segmentation and Ego Motion Estimation using Radar Image Fusion
Astik Srivastava, Suhani Grover, Avinash Sharma et al. (+1 more)
Dynamic object
segmentation and ego-motion estimation are closely coupled problems in autonomous driving, as accurate ego-motion estimation typically requires static scene observations, while identifying static observations requires knowledge of the ego motion. We present Radar-Dot, a radar–RGB framework that exploits radar Doppler measurements to address this coupling. Radar returns are first used to estimate ego velocity through a linear Doppler constraint, with residual-based static/dynamic
segmentation and robust estimation used to reduce the influence of moving objects. The estimated motion is then combined with metric depth and dense optical flow to identify image regions whose observed motion is inconsistent with the rigid scene motion. Experiments on 10 nuScenes scenes (part of nuscenes-mini) demonstrate that the resulting
geometric pipeline achieves 20.24% dynamic IoU and 33.67% F1-score over 394 frame pairs, while radar-based static-point filtering improves ego-velocity estimation compared with using all radar returns. These results demonstrate the potential of radar as a modality for jointly improving ego-motion estimation and dynamic object
segmentation.
Read the full abstract ▾
All authors Astik Srivastava, Suhani Grover, Avinash Sharma, Madhava Krishna
Robotics
SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists
Jan-Gerrit Habekost, Parsa Mastouri Kashani, Connor Gäde et al. (+5 more)
Vision-
language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually identical objects ambiguous without episode history. The usual countermeasure, widening the observation window, turns the horizon into a hyperparameter and lets per-step cost grow with it. We instead capture the episode in a recurrent state. SmoLSTM couples a frozen 256M-parameter SmolVLM backbone to a
matrix-
memory LSTM control layer in which observation
tokens and action queries are unified in a single causal stream that is never reset throughout the entire episode. Recurrent-state storage is therefore O(1) in episode length. A flow-matching action head predicts chunks of 10 end-effector pose deltas and gripper commands at each control step. Our single policy, trained jointly on 7,461 demonstrations across 140 tasks and evaluated on held-out initial states, performs best, reaching 85.1% subgoal coverage and 77.5% full-task success on LIBERO-Mem with 0.04B trainable parameters, surpassing both the
benchmark's own object-centric baseline and recent
memory-based approaches. Resetting the recurrent state at every control step reduces full-task success to 7.0%, showing that the trained policy relies on context carried between decisions. The same model achieves 79.6% average success on standard LIBERO.
Read the full abstract ▾
All authors Jan-Gerrit Habekost, Parsa Mastouri Kashani, Connor Gäde, Matthias Kerzel, Philipp Allgeuer, Cornelius Weber, Stefan Wermter, Jae Hee Lee
Robotics
Physical-Touch Observability from Wrist Wrench in Granular Scooping
Hongyi Lin, Song Zhang, Xubo Liu et al. (+1 more)
Mining and earthmoving are important real-world deployment settings for
embodied intelligence. Autonomous transport and driving systems have improved substantially, but loading and scooping still often depend on skilled human operators, exposing personnel and equipment to operational risk. For robotic scooping, pre-contact RGB-D sensing reveals surface geometry but not the resistance, compaction, tool engagement, or load transfer that emerge during interaction. We test whether the current scoop's six-axis wrist force/torque (F/T), or wrist wrench, contains information about final collected volume, and whether that information depends on the correctly paired action-terrain interaction. We call this property physical-touch observability. Using 6,700 real-
robot scoops across 67 terrains, we evaluate correctly paired current-scoop F/T against pre-contact prediction and correspondence-breaking controls under terrain-held-out testing. At the retrospective 60% sequence boundary, correctly paired F/T reduces mean absolute error by 14.2% relative to Action-only and by 21.9% relative to cross-terrain mismatched F/T. Engineered signal summaries reproduce the result across model architectures. Together, these findings position wrist wrench not merely as a low-level feedback signal, but as a task-level perceptual modality through which
embodied robots can infer hidden physical states during interaction, providing a foundation for response-aware autonomy in mining and other contact-rich tasks.
Read the full abstract ▾
All authors Hongyi Lin, Song Zhang, Xubo Liu, Yang Liu
Sound
Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs
Jing Peng, Zichao Nie, Zhisheng Zhang et al. (+2 more)
Large Audio
Language Models (LALMs) utilize either continuous features or discrete
tokens, yet the optimal representation paradigm for general audio understanding remains debated. Existing
benchmarks often focus on narrow domains or evaluate encoders outside LALM contexts. To address these gaps, we systematically evaluate continuous and discrete representations across
speech, sound and music. Utilizing our UniARC framework with dual evaluation strategies across model scales from SmolLM2-135M to Llama-3-8B, we analyze the dynamic relationships of data volume, model capacity, and computational efficiency. Our results reveal the pivotal role of semantic constraints in tokenization for audio understanding and demonstrate that scaling backbones fail to compensate for information loss in audio representation, especially in data-limited tasks. These findings offer practical guidance for balancing semantic density, fidelity, and efficiency in future LALMs.
Read the full abstract ▾
All authors Jing Peng, Zichao Nie, Zhisheng Zhang, Jingran Xie, Zhiyong Wu
Machine Learning
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
Weihan Li, Xinlei Chen, Yuhan Song et al. (+2 more)
Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and successful activation steering do not, by themselves, establish which construct the direction tracks. This gap is especially consequential for welfare-relevant interpretations, where a proposed functional state must be distinguished from correlated features of the extraction contrast. We treat the question as one of construct validity and study a good-bad outcome direction in a maze task, using controlled interventions that separate the realised outcome from the informational history through which it became known. Across multiple LLM checkpoints, directions fitted on one explicit outcome encoding transfer well to another, indicating that the readout is not tied to surface form. When the same realised outcome is reached through announced and unannounced histories, however, transfer degrades substantially: even after both histories receive the same explicit outcome, the post-event readout remains strongly conditioned on the earlier announcement. In the base model, steering along the direction changes actions, yet removing it leaves the natural cue effect almost intact. In a matched maze-RL run, the post-RL direction becomes substantially more predictive of reference-MDP remaining return and the policy becomes more dependent on it at the tested sites, while the history dependence persists. These dissociations support a functional, value-related interpretation of the direction, but not its identification with a history-invariant scalar valence state.
Read the full abstract ▾
All authors Weihan Li, Xinlei Chen, Yuhan Song, Xiaofeng Lin, Tianshi Zheng
Computer Vision
LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting
Lifeng Xing, Dequan Jin, Kunpeng Bu et al. (+2 more)
In novel view synthesis and Computed
Tomography (CT) reconstruction with sparse-view X-ray imaging, insufficient angular coverage leads to structural ambiguity and accumulated noise. Integrating 3D Gaussian Splatting (3DGS) with X-ray absorption physics can achieve promising results, but it suffers from noisy initialization, positional insensitivity, and weak gradients in low-density regions. In this paper, we propose a unified Latent Initialization and Gradient Optimization (LINGO) framework to address these issues. LINGO combines latent mask-space initialization with dynamic gradient optimization to improve point cloud structural completeness while accelerating training. It constructs voxel-level 3D filters from X-ray masks to robustly suppress background noise and provide reliable
geometric priors. By employing an adaptive voxel scaling strategy and dynamically scaling loss, LINGO can adjust spatial resolution and explicitly amplify gradients in low-density structures. To evaluate the quality of initialization, we introduce the Initialization Point Cloud Structural Deviation (IPSD) metric. Experiments on the X3D
dataset indicate that for the novel view synthesis task, LINGO improves the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) by an average of 0.72 and 0.0039, respectively, over baselines under identical sparse-view settings, achieving comparable reconstruction quality within 5k steps to state-of-the-art models typically trained with 30k iterations. For the CT reconstruction task, LINGO also demonstrates consistent improvements, with average PSNR and SSIM gains of 0.36 and 0.0134. These results highlight LINGO's effectiveness in both accelerating training and enhancing reconstruction quality across different sparse-view imaging scenarios.
Read the full abstract ▾
All authors Lifeng Xing, Dequan Jin, Kunpeng Bu, Peigeng He, Shihui Ying
Networking
RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks?
Wenlong Ding, Zhixiong Niu, Jianan Yang et al. (+6 more)
Recent advances in AI models and agentic technologies make AI for network operations (NetOps) within reach. However, scalability remains a key bottleneck of agentic NetOps when analyzing hyperscale networks, which comprise hundreds of datacenters, each housing thousands of network devices. The scalability challenge is rooted in the requirement of many NetOps tasks that must conduct global
reasoning on how a local change of device behavior affects all relevant routing paths, known as routing-path analysis. This paper studies this scalability problem and evaluates how different agentic approaches, namely in-context learning, iterative
reasoning, and
agent skills, can scale routing-path analysis to large, complex networks. We present RoutingBench for evaluating agentic routing-path analysis, with varying network size and complexity, for various types of device changes. Our results show that agentic analysis is promising:
agent skills curated with a principle termed "explore more; digest less" enables routing-path analysis on hyperscale networks of 50K routers with an accuracy of 99.5%, significantly outreaching the scalability of traditional symbolic analysis. Meanwhile, RoutingBench also reveals the boundary of AI
agent capability on complex inter-datacenter networks and compound changes, posing open challenges for AI and agentic research.
Read the full abstract ▾
All authors Wenlong Ding, Zhixiong Niu, Jianan Yang, Fajun Zhang, Bo Zhang, Ling Liang, Yongqiang Xiong, Tianyin Xu, Hong Xu
Software Engineering
Towards the Generalizability of Leveraging ChatGPT in APR via Self-enhancing: An Empirical Study
Qingyuan Li, Chuanyi Li, Yaopeng Yang et al. (+3 more)
Automated Program Repair (APR) increasingly relies on Large
Language Models (LLMs). ChatGPT-enhanced APR uses techniques such as self-correction and autonomous
agents to improve repair without modifying model parameters. Although these approaches report strong results on Defects4J and SWE-bench, the stability of enhancement gains across
benchmarks remains under-explored. We evaluate three ChatGPT-enhanced APR methods on three representative, long-standing
benchmarks. With GPT-3.5-Turbo, SRepair achieves a larger absolute gain on HumanEval-Java than on Defects4J, while SRepair and FixAgent without extrinsic information yield negative gains on BugsInPy. With GPT-5.4-mini, the evaluated methods achieve larger absolute gains on Defects4J than on HumanEval-Java, while gains on BugsInPy are non-negative but limited. We investigate
benchmark-related factors through code transformations and
benchmark-specific fine-tuning. Code transformations reduce enhancement gains on Defects4J, while
benchmark-specific fine-tuning increases gains on BugsInPy. Directly supplying GPT-3.5-Turbo with error messages and triggering tests yields more correct repairs than the evaluated ChatGPT-enhanced APR methods on BugsInPy. These findings highlight the need to evaluate generalizability across
benchmarks and models using multiple metrics, and suggest that directly providing repair-specific extrinsic information may be more effective than enhancement methods when their gains are limited.
Read the full abstract ▾
All authors Qingyuan Li, Chuanyi Li, Yaopeng Yang, Ziwen Ge, Jidong Ge, Bin Luo
Systems and Control
Intelligent Degradation Monitoring in Lithium-ion Batteries via Discharge Incremental Capacity Feature Estimation
Amir Madmolilvand and Farzaneh Abdollahi
Accurate and timely detection of degradation in lithium-ion batteries is crucial to ensure safety, reliability, and longevity in high-demand applications such as electric vehicles and energy storage systems. Traditional incremental capacity (IC) analysis methods require low-current cycling for discharge measurements, limiting their practical use in real-time battery management. This paper proposes a novel neural network-based framework that predicts discharge IC features directly from charging signals, eliminating the need for low-current discharge. Trained on a comprehensive
dataset of 53 battery
cells cycled under diverse fast-charging protocols, the model demonstrates robust generalization ability, effectively estimating degradation indicators on unseen battery data. Among several architectures evaluated, the LSTM model provides the best balance of prediction accuracy and computational efficiency. The proposed approach enables real-time integration into Battery Management Systems (BMS), enhancing degradation monitoring without disrupting normal battery operation. This paper presents a study to bridge IC analysis with practical, fast-charging scenarios, marking a significant step towards intelligent and scalable battery health monitoring.
Read the full abstract ▾
Robotics
ForceRFT: Refining VLA Actions through Force-Guided Residual Reinforcement Learning
Yichen Wang, Chaoyang Zhang, Xuqi Su et al. (+3 more)
Force-conditioned
vision-
language-action (VLA) policies can respond to contact, but when trained solely on demonstrations, their recovery behavior may be limited by demonstration coverage, and they do not learn from deployment outcomes. Human corrective imitation provides additional recovery examples, but its objective matches local action targets without explicitly optimizing task return. We present ForceRFT, a force-guided residual reinforcement learning framework that learns contact-dependent corrections from human supervision and autonomous task outcomes. A frozen, demonstration-trained SmolVLA-based prior generates force-conditioned action chunks, while a lightweight residual actor refines individual end-effector pose commands using wrist feedback acquired during chunk execution. The decision-time wrist wrench, its temporal change, and the selected base motion condition both residual correction and value estimation. Human corrections supervise the residual actor, while verified autonomous transitions train the twin critics and support value-guided updates to the same actor. Bootstrapping is restricted to autonomous segments, preventing TD credit from crossing human-intervention boundaries. Real-
robot experiments on plug insertion, ring-on-peg assembly, and whiteboard wiping show higher autonomous success rates than the evaluated demonstration-trained and residual-imitation baselines. Comparisons with residual imitation support value-guided residual optimization, while plug-insertion ablations indicate the benefit of direct execution-time wrist feedback.
Read the full abstract ▾
All authors Yichen Wang, Chaoyang Zhang, Xuqi Su, Jun Ma, Haiyue Zhu, Xiaocong Li
Game Theory
A Horizon-Independent Regret Bound for Optimistic Hedge in General-Sum Games
Junsoo Ha
Can simple learning rules keep their regret bounded in self-play? Recent work achieves constant regret bounds through modified regularization and higher-order prediction. Yet for Optimistic Hedge, arguably the most canonical method in games, the best known individual regret bound remains logarithmic. In this work, we prove that plain Optimistic Hedge with a constant step size can attain $O_{n,d}(1)$ individual regret in general-sum games with $n$ players and $d=(d_1,\ldots,d_n)$ actions, under expected loss-vector feedback. As a corollary, its time-averaged play enjoys an $O_{n,d}(1/T)$ coarse correlated
equilibrium (CCE) gap. Our analysis represents Optimistic Hedge as a real-analytic recurrence on a compact space, which yields an exact finite-order difference relation that eliminates horizon dependence. Our proof hinges on nonconstructive Noetherianity argument of Frisch (1967), so the $(n,d)$-dependence remains implicit.
Read the full abstract ▾
Neural and Evolutionary Computing
Sensing to Intelligence: Principles for Neuromorphic Circuits and Systems
Saptarshi Maiti and Chetan Singh Thakur
Neuromorphic engineering began with the idea that the physical behavior of a system could itself be used for computation, taking inspiration from the way nervous systems sense, adapt, and evolve in time. The field has since expanded far beyond its early analog
circuits to include event-based sensors, spiking processors, emerging
memory devices, mixed-signal systems, and large-scale neural accelerators. With this expansion, however, the meaning of neuromorphic has become increasingly broad. In this Perspective, we argue that neuromorphic engineering should be defined neither by resemblance to biological components nor by any particular device, signal representation, or substrate. Its potential lies in identifying computational principles in biological systems and translating them into the organization and dynamics of artificial machines. A system is truly neuromorphic when the invoked biological or physical principle plays a causal, design-relevant role in how information is represented, how state evolves, or what capability the complete system achieves. We develop this view across sensing, collective computation,
memory, learning, and interaction. Adaptation, nonlinear dynamics, attractor structure, variability, and closed-loop action illustrate how computation can be embedded in a machine's evolving physical state. From these examples, we identify a set of design principles for neuromorphic systems. As neuromorphic engineering moves toward wider deployment, this perspective shifts the central question from how closely machines resemble nervous systems to what computation becomes possible when their principles are understood and deliberately translated into new machines.
Read the full abstract ▾
Machine Learning
A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting
Li Lin, Zhihao Lin, Qi Zhang et al. (+3 more)
Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse
forecasting tasks. However, real-world decision-making frequently relies on irregular multivariate time series (IMTS), where inconsistent inter-observation intervals and asynchronous sampling across variables coexist with informative missingness. Existing TSFMs handle such inputs either through imputation that injects spurious values or through index-based positional encodings that ignore continuous time. There is still a gap in the foundation model that follows the original IMTS patterns. In this paper, we propose a hybrid
attention model that learns a unified time-aware patch representation for IMTS
forecasting. We first design a time-aware patch encoding that maps a variable number of intra-patch timestamps into a fixed-size
embedding, producing a uniform format for irregular patches without resorting to imputation. We then introduce a time bias
attention mechanism that calibrates inter-patch temporal misalignment and asynchronous cross-channel dependencies as auxiliary
attention offset. Finally, on top of a decoder-only
Transformer backbone, we adopt a hybrid causal mask that preserves a bidirectional full view over the historical context while keeping the forecast horizon strictly autoregressive. To support large-scale pretraining under irregular settings, we also curate VersaTSA, an archive of $30$B observations that retains the native sampling sparsity of its sources. Experiments on three IMTS
benchmarks and a standard regular-MTS
benchmark show that our model achieves state-of-the-art zero-shot performance on IMTS and remains competitive when transferred to regular
forecasting.
Read the full abstract ▾
All authors Li Lin, Zhihao Lin, Qi Zhang, Kaiwen Xia, Shuai Wang, Jialin Qiao
Cryptography and Security
When Label Noise Meets Class Imbalance: A Robust Framework for Android Malware Family Classification
Haolan Zhang, Cuiying Gao, Fulin Zhao et al. (+6 more)
Machine learning methods for Android malware family classification have achieved high accuracy, but their application is hindered by two major challenges. First, the widely used code obfuscation severely disrupts the automated labeling process and introduces substantial label noise into training
datasets. Second, training
datasets often exhibit severe class imbalance, leading to poor performance of family classification models. Although existing studies have proposed various solutions to either label noise or class imbalance, they often overlook the interplay between these two factors. Under class imbalance, the presence of hard-to-learn minority-class samples can significantly impair the effectiveness of existing countermeasures for noisy samples. To jointly address label noise and class imbalance, we propose a robust Android malware family classification framework, RoMaC. It employs a self-training strategy to correct noisy labels and, more importantly, discriminately treats head-family and tail-family samples. This design effectively mitigates the adverse impact of class imbalance on noise-robust learning. Moreover, RoMaC integrates a class reweighting mechanism with multi-model ensemble learning, thereby enhancing both classification accuracy and noise robustness. We evaluate RoMaC on a combined
dataset constructed from two public
datasets. When 30% of the samples are obfuscated, RoMaC achieves an overall Macro-F1 score of 0.803 and an accuracy of 0.871, as well as a tail-class Macro-F1 score of 0.672 and an accuracy of 0.784. Compared with existing methods, RoMaC demonstrates performance improvements of 6%-20% across various obfuscation scenarios and noise levels.
Read the full abstract ▾
All authors Haolan Zhang, Cuiying Gao, Fulin Zhao, Heng Li, Haoran Wang, Chang Luo, Tiejun Wu, Hui Shu, Wei Yuan
Computer Vision
SatOV: Restoring Spatial Priors for Training-Free Open-Vocabulary Segmentation in Remote Sensing Imagery
Changhao Zhao, Linglin Zeng and Hai Liu
Open-vocabulary semantic
segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation to the spatial characteristics of remote sensing data. Although existing
vision-
language foundation models perform well in general domains, their image-level classification design weakens the spatial priors needed for high-resolution remote sensing
segmentation: structural spatial relations are degraded during deep feature transformation, and fine-grained spatial details are lost during downsampling. To address these complementary deficiencies, we propose SatOV, a training-free framework for open-vocabulary remote sensing
segmentation that restores spatial priors at two stages of the representation pipeline. Specifically, Residual QQ
Attention (ResQQ) extracts Query-Key self-
attention from an intermediate CLIP layer and fuses it with final-layer Query-Query
attention via a residual combination, restoring structural spatial priors suppressed by the final-layer representation. Spatially Modulated Upsampling (SatUp) uses the original high-resolution RGB image as spatial guidance, combining spatial feature modulation with guided cross-
attention to reconstruct pixel-level textures and boundaries. Extensive experiments on DOTA, UDD, LoveDA, and Vaihingen show that SatOV consistently improves training-free OVS and achieves competitive quantitative and qualitative results against state-of-the-art methods. These results validate the effectiveness of restoring spatial priors at both the representation and spatial-resolution stages for remote sensing open-vocabulary
segmentation.
Read the full abstract ▾
Machine Learning
Personalized Federated Reinforcement Learning via Model-Agnostic Meta-Learning: Convergence of Exact and Hessian-Free Meta-Policy Gradients
Ali Beikmohammadi, Sarit Khirirat and Sindri Magnússon
We study personalized
federated reinforcement learning, in which $n$
agents, each acting in its own Markov decision process, collaborate through a server to learn a shared MAML-style policy initialization that becomes effective for an individual
agent once that
agent adapts it with a single local policy-gradient step. We propose Per-FedAvg-PG, in which
agents take $\tau$ local
stochastic meta-policy-gradient steps between communication rounds, and prove that it reaches an $\varepsilon$-approximate first-order stationary point of the personalized objective in $K=\mathcal O(\varepsilon^{-3/2})$ rounds with $\tau=\Theta(\varepsilon^{-1/2})$ local steps. The analysis rests on a structural feature of the reinforcement learning setting: under standard policy-class regularity, the per-
agent objectives have uniformly bounded gradients and Hessians with explicit constants, so the bounded-gradient and bounded-heterogeneity conditions imposed by the supervised theory hold automatically and no separate heterogeneity assumption is needed. The exact meta-gradient requires the inner-loop policy Hessian, which our experiments identify as the practical bottleneck. We therefore analyze the Hessian-free variant, bound its bias, and exhibit fixed points at which the meta-gradient is nonzero and of order $\alpha$, showing that the resulting stationarity floor is a property of the method rather than of the bound. Experiments on tabular and neural
navigation confirm the predicted behavior and show transfer to unseen
agents at an order of magnitude lower sample cost than independent training. Together these results identify the adaptation step size as a tunable personalization knob and the
curvature estimate as the quantity that governs whether exact meta-gradients are affordable.
Read the full abstract ▾
Computational Engineering
Real-Validated UAV Audition Under Rotor Ego-Noise for Low-False-Alarm Human Detection
Junhao Wei, Haochen Li, Dexing Yao et al. (+7 more)
Detecting human acoustic cues from
UAV-mounted microphones could support acoustic search and rescue, but rotor ego-noise often masks
speech, cries, coughs, and other human sounds at extremely low SNRs. We study
UAV human-audible-presence detection under this real operating constraint. Models are trained on a reproducible synthetic mixture pipeline built from public audio, but selected and evaluated on real DroneAudioSet recordings using a metadata-defined audibility filter, recording-grouped Dev/Test splits, and group-bootstrap confidence intervals. Our results show that synthetic accuracy is a weak and non-monotonic proxy for real
UAV transfer: a from-scratch SE-ResNet appears competitive on synthetic mixtures but collapses on real ego-noise, while frozen audio foundation models and lightweight adapters transfer more reliably. We further evaluate a BEATs adapter family with rotor-aware conditioning and domain regularization. The Real-Dev-selected EgoRAP-DA configuration achieves the best locked-test low-false-alarm recall among the candidates, but its advantage over a vanilla adapter is not statistically significant under paired group bootstrap. The main contribution is therefore a real-validated
benchmark and evaluation protocol showing that honest progress in
UAV audition requires real, group-level validation rather than synthetic scores alone.
Read the full abstract ▾
All authors Junhao Wei, Haochen Li, Dexing Yao, Yanxiao Li, Yifu Zhao, Baili Lu, Zhenhong Peng, Ngai Cheong, Xu Yang, Yapeng Wang
Robotics
Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation
Yuxuan Nai, Leixin Chang, Liangjing Yang et al. (+2 more)
Collecting whole-body demonstrations for
humanoid manipulation mostly relies on teleoperation, which is costly and hard to scale up. The Universal Manipulation Interface (UMI) provides a scalable data collection paradigm, but end-effector trajectories alone underdetermine
humanoid whole-body coordination, which is insufficient for whole-body demonstration collection. Therefore, we introduce Whole-Body UMI (WB-UMI), a task-agnostic, real-time and end-effector conditioned motion generator that decouples whole-body coordination learning from task semantics learning through a shared end-effector interface. A
diffusion policy learns from native UMI demonstrations, while WB-UMI learns independently from retargeted motion capture, requiring no body trackers or paired image–whole-body demonstrations during task-specific data collection. In real deployment, an asynchronous hierarchy integrates the
diffusion policy, motion generator, and a whole-body controller with latency compensation and measured-state feedback. Real-
robot experiments on G1 support real-time closed-loop transfer across four tasks, achieving 90% success in drawer closing, 80% in shelf pick-and-place, 30% in ball toss, and 40% in Loco-PnP, which shows the effectiveness of this hierarchy in transferring native UMI skills to
humanoid whole-body manipulation.
Read the full abstract ▾
All authors Yuxuan Nai, Leixin Chang, Liangjing Yang, Shuo Yang, Zhongyu Li
Systems and Control
Constrained Optimization-Based Yaw-Rate Reference Map Generation for Active Rear Steering Control of Four-Wheel Steering Vehicles
Myeongseok Ryu, Donghyun Hwang, Youngsik Yoon et al. (+1 more)
The effectiveness of active rear steering (ARS) control for four-wheel steering (4WS) vehicles is widely recognized in the automotive industry. At low speeds, ARS control can enhance maneuverability by steering the rear wheels in the opposite direction to the front wheels, reducing the turning radius. In contrast, at high speeds, ARS control can improve stability by steering the rear wheels in the same direction as the front wheels, preventing oversteer behavior. However, the performance of ARS control is often limited by the reference model used to generate the desired yaw rate, which is typically derived from a steady state of front-wheel steering (FWS) vehicle model. In this paper, we conduct a numerical analysis to construct an optimal yaw rate reference map for ARS control by formulating a constrained optimization problem. In the optimization problem, constraints are imposed to ensure that the vehicle operates within safe limits at steady state. Numerical simulations demonstrate the effectiveness of the proposed method in providing an optimal yaw rate reference map for ARS control.
Read the full abstract ▾
All authors Myeongseok Ryu, Donghyun Hwang, Youngsik Yoon, Kyunghwan Choi
Machine Learning · Cross-listed from quant-ph
From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis
Antonio Greco, Riccardo Paoletti, Roberto Cappuccio et al. (+1 more)
We present Hybrid
Quantum Root Cause Analysis (HQ-RCA), an industrially grounded workflow for root cause analysis in banking IT operations, built on a hybrid
Quantum Graph Neural Network (QGNN): the classical backbone of DynEdge (the IceCube
neutrino-reconstruction GNN, which we call standalone DynEdge), with its classification head replaced by a Variational
Quantum Circuit (VQC). On 13 months of anonymised IT data (13k alarm clusters) from a major European bank, the hybrid QGNN matches standalone DynEdge – the strongest classical baseline – on $F_1$, while standalone DynEdge leads the ranking metrics. A readout-sensitivity and layout-robustness study, analysed via Dimensional Expressivity Analysis (DEA), shows that the effective parameter dimensionality (rank) of the
quantum observable has no measurable correlation with $F_1$; we therefore keep the simplest readout $\langle Z_0\rangle$ (the Pauli-$Z$ expectation on the first
qubit), which in the deployed layout is rank-1, collapsing optimisation to a 1-D problem solvable by a gradient-free grid scan. Execution on IBM Heron r2 (no error mitigation) shows this gradient-free readout is executable on NISQ hardware after threshold recalibration.
Read the full abstract ▾
All authors Antonio Greco, Riccardo Paoletti, Roberto Cappuccio, Mario Onorato
Machine Learning
Beyond Average Error through Oracle-Informed Stress Tests for Time-Series Forecasting
Xu Lin, Runheng Zuo, Shengxuan Xu et al. (+3 more)
Average squared error cannot reveal whether
forecasting performance degrades because the future becomes less predictable or because forecasts move farther from the conditional mean. We introduce paired, mechanism-controlled stress tests that decompose changes in expected squared error at each lead time into environmental risk and forecast-oracle distance, using an origin-conditioned predictive oracle unavailable to the evaluated models. Three end-to-end controls have known attribution. Specifically, the null, environmental-only, and information-gap controls verify that the pipeline assigns changes to the correct component. We then apply the
benchmark to 24 deployable forecasters. Under frequent switching, 14 methods have higher realized MSE but lower oracle distance; under outlier-variance feedback, 19 have higher MSE but lower scale-standardized MSE. Short- and long-lead stress-response rankings have Spearman correlation 0.624, revealing substantial horizon-dependent reordering. We then study multivariate relation shifts. Across six models and three coupling severities, oracle distance accounts for only 0.7-3.9% of the decomposed expected-risk increase, and environmental-risk majority persists in an eight-channel system and a matched-difficulty audit of Ring, Block, and Hub relations. Finally, prespecified contrasts on independent data-generating process (DGP) realizations show that several visually compelling discovery profiles, including trend accumulation and the hypothesized switching reversal, do not replicate. The
benchmark thus combines component-wise diagnosis with a held-out stability audit. It complements real-data out-of-distribution evaluation, which measures performance under realistic shifts when exact oracle attribution is unavailable.
Read the full abstract ▾
All authors Xu Lin, Runheng Zuo, Shengxuan Xu, Qitai Tan, Hongyu Lin, Xiao-Ping Zhang
Machine Learning
Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints
Jiapeng Li
Counterfactual tool evaluation must distinguish authority, historical support, and what a comparison actually estimates. We study these distinctions with eleven executable enterprise-inspired tools, exact-propensity logs, and real local Model Context Protocol transport. An initial 45-run synthetic study is retained, then challenged by 30 realized-return control runs and 15 experiments on 1,930 independently released Berkeley Function Calling Leaderboard (BFCL) tasks. Full-return direct regression reverses an initially favorable doubly robust (DR) evaluation result in the linear setting: mean absolute errors are 0.0139 for direct regression and 0.0272 for DR. Under a shifted environment, DR retains an advantage, with errors 0.0227 versus 0.0948. On function-name-group-disjoint BFCL-derived splits, direct and DR selectors obtain balanced accuracies of 81.85% and 79.83%. Two pinned local Qwen2.5 models are evaluated on the same 200 held-out tasks, exposing a strong failure to abstain under the fixed
prompt. We further characterize policy differences under missing support: unsupported actions shared by two policies cancel, allowing point identification of an incremental change when neither absolute value is identifiable. A disagreement-preserving fallback achieves this property in all five support-gap runs, but conservative sampling bounds do not certify deployment improvement. The contribution is a falsifiable evaluation method and independent public evidence, not a new DR
estimator, official BFCL leaderboard score, or production-
agent safety claim.
Read the full abstract ▾
Cryptography and Security
The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
Pritom Bhowmik
Memory-poisoning defenses for LLM
agents are usually judged by how well they stop attacks, yet almost all the traffic an
agent sees is benign. We measure what these defenses cost when no attack is present. Our harness holds the backbone model,
memory backend,
retrieval, answer
prompt, and judge fixed and changes only the defense. Both LLM-based defenses run on the
agent's own backbone, and an integrity check verifies every run. We test four defenses on half of LoCoMo: five long conversations (750 turns and 255 questions per run), with each condition run three times. Sanitization and provenance checking never fired. LLM-based anomaly detection blocked 9 of 2,250 turns (0.4%). A read-time reranker dropped 2.2% of the
memories it judged, withholding at least one
memory from 14.9% of questions. A blind audit found content-based justification for only 2 of 50 sampled drops. No defense showed a detectable accuracy cost, at 95% intervals of $\pm$2.4 to $\pm$4.6 points; the reranker changed accuracy by +0.6 points (95% CI [-2.6, +3.8]). Anomaly detection and the stacked condition gained 4.7 points, but a blocked turn changes the
memories extracted after it, so we do not count this as a benefit.
Token overhead was 0% for sanitization and provenance, 1.5% for anomaly detection, 3.0% for the reranker, and 4.5% with all four stacked. An earlier version of this study ran the reranker condition on a different model than its baseline. A baseline on that same model shows the swap produced 2.9 of the 4.4 points of accuracy cost we then reported. Attack success rate reveals none of this, so we report benign cost alongside it. We release the harness, labels, and per-run outputs.
Read the full abstract ▾