Robotics
Information-Guided Safe Reinforcement Learning for Autonomous Gas Source Localization using sUAS
Sachin Giri, Thomas Zhao, Matthew Huynh et al. (+1 more)
The autonomous localization of fugitive gas emissions using small Unmanned Aircraft Systems (sUAS) constitutes a fundamentally ill-posed inverse problem. In turbulent atmospheric boundary layers, highly intermittent scalar concentration fields violate the assumptions of classical gradient-based
navigation, causing data-driven
estimators to suffer from severe noise and spurious local minima. To address these challenges, we introduce an Information-Guided Safe Reinforcement Learning framework evaluated within a custom, GPU-accelerated 3D simulation environment coupling an Eulerian wind solver with a Lagrangian puff dispersion model. We identify a critical vulnerability in deterministic information-seeking planners - a Gramian bias where
agents act greedily upon flawed early estimates, starving the
estimator of spatial diversity. To systematically break this degeneracy, our architecture integrates a classical empirical observability Gramian (EMGR) planner with a learned Soft Actor-Critic (SAC) exploratory policy. A deterministic meta-supervisor actively monitors
estimator reliability via Kullback-Leibler (KL) divergence, dynamically blending deterministic exploitation with learned exploration to steer the sUAS into high-information zones. Trained via a progressive curriculum and safeguarded by a strictly enforced Robust Control Barrier Function (RCBF), our RL framework achieves nearly 80% localization success on complex, mobile sources - drastically outperforming classical baselines (~30%) - while ensuring zero safety violations.
Read the full abstract ▾
All authors Sachin Giri, Thomas Zhao, Matthew Huynh, YangQuan Chen
Computer Vision
WorldSculpt: Generating Compositional Worlds from Grounded Videos
Muyao Niu, Jixuan He, Ruihan Yu et al. (+9 more)
We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects. The goal is to represent the scene as a collection of individual object meshes placed in a shared world frame, as required by downstream applications such as gaming, AR/VR, simulation, and robotics. This task is challenging in densely cluttered scenes, where objects heavily occlude one another and each view reveals only a fraction of their geometry. Geometry-based approaches typically reconstruct the scene as a single representation and leave incomplete geometry in occluded regions, while existing compositional methods with generative priors are largely limited to relatively simple scenes. We show that complex scenes with hundreds of objects can instead be generated compositionally by adapting a strong single-object 3D generative prior to multi-view observations. We instantiate this paradigm with Pixal3D, extending it with a multi-view conditioning pathway that grounds object generation in multiple posed observations. Although the model is finetuned entirely on single objects in canonical space, it generalizes to large scenes with severe occlusion without any scene-level training, demonstrating the feasibility and scalability of this paradigm. We further introduce UE-MeshyScene, a photorealistic
benchmark of densely cluttered scenes with hundreds of objects, per-object annotations, and ground-truth meshes. Across single-object, controlled multi-object, and UE-MeshyScene evaluations, our method consistently outperforms prior approaches, with larger gains as scene complexity and occlusion increase. Finally, we demonstrate broader applicability by converting generated 3DGS worlds, such as Marble and HY-World 2.0, into compositional mesh scenes.
Read the full abstract ▾
All authors Muyao Niu, Jixuan He, Ruihan Yu, Lian Fu, Yonghao Yu, Zheng-Hui Huang, Yifan Zhan, Fengbo Lan, Yongtao Ge, Yinqiang Zheng, Kaipeng Zhang, Zhixiang Wang
Computer Vision
UniMate: One Unified Model to Animate Diverse Skeletons
Linzhan Mou, Jiahui Lei, Zhiyang Dou et al. (+4 more)
Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are
topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text
prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a
topology-aware
diffusion transformer, which integrates skeletal
topology into
attention via three mechanisms: (1) a graph-aware
attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position
embedding generalizing RoPE to arbitrary kinematic trees via the graph
Laplacian; and (3) a global topological conditioner
attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this
dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-
topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.
Read the full abstract ▾
All authors Linzhan Mou, Jiahui Lei, Zhiyang Dou, Chenyue Cai, Chaoyue Song, Adam Finkelstein, Szymon Rusinkiewicz
Emerging Technologies · Cross-listed from quant-ph
Towards Scaling Quantum Fine-Tuning of Foundational Time Series Models for Classification
Sang Hyub Kim, Julien Baglio, Rajiv Krishnakumar et al. (+7 more)
Time-series foundation models produce rich
embeddings, but whether
quantum models can exploit them, and how far hybrid classical-
quantum architectures scale, remains unclear. We address this by fine-tuning Chronos for power-grid event classification (PSML-5) with a
quantum head on the model's
embeddings. Grouping
embeddings by physical sensor type before summarization already surpasses the best published baseline built for this
benchmark, and with finer-grained features the
quantum head outperforms a larger classical multilayer perceptron on identical inputs by 1.7-2.0 percentage points of balanced accuracy. Yet the gains saturate: past a point, feeding more information to the same fixed-width register yields no improvement. We show the bottleneck is neither the supply of information nor
circuit expressiveness, but the bandwidth of the data intake. To overcome this limitation, we introduce the wing module, a self-contained few-
qubit circuit that feeds additional information into the core
circuit through a sparse, one-way coupling. Under a preregistered four-seed protocol, we attach wings to a fixed 12-
qubit core with fixed features. Balanced accuracy increases with each added wing, from 83.6% with no wings (13
qubits, including a post-selection
qubit) to 85.2% with two (19
qubits). Ablations establish that a
circuit enlarged without new information gains nothing, while a wing fed information from the wrong sample harms accuracy. These results reframe scaling for
quantum fine-tuning: added
qubits help when they carry added inputs, not merely more parameters. Wings offer a modular and stable route to widening that bandwidth.
Read the full abstract ▾
All authors Sang Hyub Kim, Julien Baglio, Rajiv Krishnakumar, Chi Chen, Oliver Knitter, Jonathan Mei, Claudio Girotto, Masako Yamada, Frederik F. Flöther, Martin Roetteler
Systems and Control
Beyond Scalar Flexibility: From Eligible AI Workloads to Dependable Load Relief
Meiyi Li
Grid studies often represent data-center flexibility as a fixed percentage of load, although no public production trace has shown how much eligible load persists across event durations or co-moves across clusters. We reconstruct 4,439 hourly power observations from a 185-day trace of 155,410 GPUs and derive a workload-semantic flexibility envelope. The fleet's time-averaged Monte Carlo median facility demand is 55.8 MW, while immediate eligible curtailment averages 3.55 MW after retaining allocated-GPU idle power: 12.1% of workload power and 6.35% of median facility power. Under full realization of that eligibility, 95%-available relief falls from 2.51 MW for one hour to 2.32 MW for four hours and 1.95 MW for 24 hours; a common realizable fraction q scales every value exactly by q. A mean-calibrated scalar overstates these quantities by 17%, 25%, and 47%, while a scalar tail-calibrated at four hours understates the one-hour product by 6% and overstates the 24-hour product by 17%; the share that reproduces the surface varies by a factor of 1.6 across durations and reliability levels. Aggregating 13 clusters raises four-hour firmness from 0.38 to 0.66, but cross-cluster covariance limits the gain. The production scheduler exposes almost no additional delay-based capacity: newly deferrable arrivals average 0.008 MW and have zero 95%-available capacity. These results replace an assumed flexibility percentage with duration, reliability, portfolio, and realizability terms that can be written into interconnection and demand-response contracts.
Read the full abstract ▾
Computation and Language
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
Ji Soo Lee, Xilun Chen, Pierce Chuang et al. (+5 more)
Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing
benchmarks rarely evaluate whether AI systems can reason over a real user's longitudinal wearable record. We introduce WearableQA, a
benchmark comprising 4,084 10-option multiple-choice questions constructed from the wearable time series, blood biomarkers, and demographics of 200 real users, each with up to 500 days of daily measurements. WearableQA preserves authentic wearable distributions that include device noise and inter-individual variability. To evaluate distinct
reasoning capabilities, we introduce 16 question types organized along two complementary axes: data versus health
reasoning, which distinguishes computation over longitudinal measurements from physiological interpretation; and single- versus cross-signal
reasoning, which separates
reasoning about individual signals from the integration of multiple signals. To construct reliable questions at scale, we adopt a dual-grounding framework that combines literature-grounded physiological findings with statistically validated population-grounded physiological patterns. This enables the capture of meaningful relationships observed in real-world wearable data. Evaluation of 14 proprietary and open-source LLMs demonstrates that WearableQA effectively differentiates model capabilities, with performance ranging from 19.6% to 72.9% against a 10% chance baseline. Moreover, WearableQA remains far from solved: most models achieve accuracies below 60%. Overall, WearableQA provides a realistic and diagnostic
benchmark for evaluating LLM
reasoning over real-world wearable data.
Read the full abstract ▾
All authors Ji Soo Lee, Xilun Chen, Pierce Chuang, Ashish Shenoy, Jason Wei, Dohwan Ko, Hyunwoo J. Kim, Benoit Corda
Human-Computer Interaction
Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction
Sihwa Park
Diffusion TV is an interactive AI art installation that offers a tangible and
embodied experience of
diffusion models through a modified CRT TV. By physically manipulating the TV's
antenna, audiences control the clarity of AI-generated images and sounds, metaphorically enacting the denoising process that underlies
diffusion-based generation. Using the tuning knob, participants switch between three channels featuring AI-generated animals from the Past (extinct species), Present (endangered species), and Future (speculative creatures), situating the interaction within a temporal and ecological narrative. Through continuous audiovisual feedback and physical interaction,
Diffusion TV foregrounds the generative process over final outputs, allowing audiences to explore intermediate states as experiential material. Rather than providing explicit technical explanation, the work presents an alternative,
embodied mode of explainable AI that invites exploratory engagement with and reflection on generative technologies.
Read the full abstract ▾
Machine Learning
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments
Quoc H. Nguyen, Ali Lafzi, Abhijeet Phatak et al. (+4 more)
Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and product preferences, creating significant data heterogeneity that challenges both
privacy-preserving training and model personalization.
Federated learning offers a natural solution for
privacy, but standard FL methods produce global models that sacrifice regional performance, while existing personalized FL approaches operate at the parameter level and catastrophically collapse on modern
transformers (below 10% accuracy on T5) due to tied
embeddings and LayerNorm interactions. We introduce RegionFed, an architecture-robust
federated learning framework that sidesteps this failure by operating entirely at the gradient level. RegionFed uses the $\ell_2$ conflict between regional and global gradients as a unified signal that (i) diagnoses heterogeneity, (ii) routes each region to the cheapest sufficient personalization strategy, and (iii) adaptively controls personalization strength. Because it treats models as differentiable black boxes, RegionFed deploys on T5-Small, T5-3B, RoBERTa, and CNN with zero code changes, providing large gains on
transformers (where parameter-level methods collapse) and consistent improvements on CNNs. Across three public
datasets (Amazon ESCI, Amazon Reviews, LEAF-FEMNIST) and four architectures, RegionFed-Meta achieves 92.27%, closing the gap to the
privacy-violating centralized upper bound (Centralized + Regional Weighting: 92.04%, $\Delta$=0.23pp, within 1$\sigma$) while providing $(\epsilon{\approx}0.60)$-differential
privacy and $\mathcal{O}(1/\sqrt{T})$ convergence.
Read the full abstract ▾
All authors Quoc H. Nguyen, Ali Lafzi, Abhijeet Phatak, Siddharth Pratap Singh, Rohit Upadhyay, Yogananda Domlur Seetharama, Chittaranjan Tripathy
Robotics
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al. (+6 more)
Vision-
language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property. Paraphrasing the instruction alone can substantially change predicted progress scores, and can even flip identical
robot behavior between failure and success. To measure this failure mode, we introduce ROBORMBENCH, a
benchmark with 2,390 real-
robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites. Across proprietary and open-source VLMs, paraphrase-induced instability is widespread and severe, grows under more divergent rewrites, and is not reliably reduced by scale or explicit
reasoning. Dedicated reward models trained with trajectory-grounded supervision are substantially more stable. These results show that paraphrase robustness is a core requirement for reliable VLM-based reward modeling in robotics.
Read the full abstract ▾
All authors Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Yoonjun Cho, Dongjae Jeon, Bumjun Kim, Jean Oh, Youngjae Yu, Albert No
Computer Vision
A Generalizable Feature Extractor for Alzheimer's-Related Brain MRI Tasks
Reza Rajabli and D. Louis Collins
When there is not enough labeled data to properly train deep learning models, transfer learning can help. We still do not fully understand how effective it is in neuroimaging, especially for Alzheimer's disease research. It is also not clear if these transferred models can work on new
datasets without being retrained for each specific task. We evaluate whether a compact, supervised pretrained model can serve as a reusable foundation model for downstream neuroimaging tasks. We freeze the 7.18 million weights of a 3D CNN previously trained for
brain-age prediction, and adapt it to each task using Low-Rank Adaptation (LoRA), requiring only ~1% additional trainable parameters. We evaluate generalizability in six experiments. Adapting the model to classify cognitively normal versus Dementia on ADNI gave an AUC of 0.964 on held-out folds (Experiment #1). Applying that adapted model unchanged to OASIS-3, with no retraining, gave an AUC of 0.871 (Experiment #2). Reusing its output logit together with age and a cognitive score distinguished stable from progressing MCI with an AUC of 0.828 (Experiment #3). Adapting the same backbone to predict amyloid positivity from structural MRI gave an AUC of 0.804 (Experiment #4). Finally, the same approach estimated ICV-normalized hippocampal and white matter hypointensity volumes directly from the T1w image, with R^2 of 0.80 and 0.91 respectively, tasks normally addressed with much larger U-Net networks (Experiments #5 and #6). A compact model supervised on
brain age can therefore serve as a reusable backbone, adapting to each task with ~1% additional parameters and transferring to an unseen cohort without any training. Our findings suggest that a carefully trained
brain age model can serve as an effective foundation model for Alzheimer's related tasks, even under strict data constraints.
Read the full abstract ▾
Computer Vision
From Interpretability Methods to Interpretable Models
Julien Colin, Nuria Oliver and Thomas Serre
More than a decade in, explainable AI (XAI) for computer
vision has assembled a mature toolbox: attribution, feature visualization, concept-based, and
circuit-based methods. Yet almost all of the field's effort has gone into building and comparing these methods, and little into the question they were meant to answer—how interpretable are our models, and are we making progress as they evolve? We argue for shifting the field's focus from methods to models, along two complementary lines. One is already within reach: existing tools let us characterize and compare what different models represent and compute. The other is harder, and largely neglected: whether a model can actually be understood by the humans who rely on it—the independent evaluators on whom trust and certification depend, not the experts confirming what they already expect. It can only be measured, not inferred. We review why the toolbox is mature enough to support both, survey the thin body of work comparing models, draw a parallel to systems neuroscience, and close with a model-centric XAI agenda.
Read the full abstract ▾
Computer Vision
CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation
Samer Abualhanud and Max Mehltretter
Reliable 3D understanding of the surrounding environment is a core requirement for autonomous driving. Multi-view surround camera rigs provide broad scene coverage, but the spatially adjacent images typically overlap only minimally. Consequently, the depth of most pixels must be inferred from
monocular appearance cues. These cues can appear differently across images and may therefore be interpreted differently by the depth estimation model. We target two main sources of cross-image inconsistency: differences in camera intrinsics and the limited receptive field of each image. We address the former by conditioning the features on per-pixel camera-aware ray
embeddings, enabling the network to account for camera-dependent variations in
monocular cues. We address the latter by extending each pixel's context beyond its own image through cross-image
attention constrained to geometrically plausible regions, derived from the calibrated rig setup. The model is trained in a fully self-supervised manner based on photometric consistency. Evaluations on DDAD and nuScenes show improved overall depth accuracy and cross-image depth consistency over state-of-the-art self-supervised methods under in-domain and cross-domain evaluation. Code is available at https://abualhanud.github.io/CrossDepthPage/.
Read the full abstract ▾
Artificial Intelligence
A Deep Generative Model for Synthesizing Labeled Wireless Signals
Yuxiao Li, Keke Hu, Santiago Mazuelas et al. (+1 more)
Wireless signals with position-related labels are pivotal for both performance evaluation and model training in the realm of wireless sensing. However, acquiring real-world
datasets is often challenged by significant measurement and labeling costs. Traditional methods for synthesizing labeled wireless signals typically rely on environmental models, leading to extensive hyper-parameter tuning and inadequate realism for comprehensive model training purposes. To address these limitations, we introduce a novel deep learning (DL)-based method, namely Inter-Instance Generative
Adversarial Networks (IIns-GAN), to generate realistic labeled wireless signals. The generated signals are particularly adaptive to different environment scenarios and well-suited for various model training tasks, including distance estimation and environment identification. We have conducted extensive experiments on public Ultra-Wideband (UWB)
datasets to evaluate the realism and utility of the generated signals. The results demonstrate that the signals generated by IIns-GAN mirror the physical characteristics of real-world measurements, and significantly contribute to the improvement of model training in diverse wireless sensing tasks.
Read the full abstract ▾
All authors Yuxiao Li, Keke Hu, Santiago Mazuelas, Yuan Shen
Artificial Intelligence
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe
Dain Kim, Eungi Cho, Kyumin Kim et al. (+2 more)
Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM
agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing
benchmark measures the gap. We introduce the Korean Open Public API
Benchmark (KOPA-Bench), comprising 145 real-world tasks. To close this gap, we present EDGE, an Execution-grounded Dynamic Graph for tool-calling data synthEsis driven by live execution. EDGE builds a graph of how each tool's output can feed another's input, keeps only the links that succeed when actually called against the live APIs, and traverses these verified links to synthesize executable multi-step trajectories. Fine-tuned via GRPO on the resulting
dataset, our 9B model nearly matches the untuned 27B model from the same family, improving substantially not only on KOPA-Bench but also on the BFCL
benchmark.
Read the full abstract ▾
All authors Dain Kim, Eungi Cho, Kyumin Kim, Shinyeong Noh, Kyuseong Lim
Computer Vision
Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks
Homayoun Afshari, Pietro Basci, Alessandro Russo et al. (+1 more)
Visual
reasoning tasks require a system to jointly perceive visual content and apply formal relational constraints—a combination that neither pure neural nor purely symbolic approaches handle well in isolation. This paper proposes a Neuro-Symbolic (NeSy) framework that closes this gap by tightly coupling a
Vision-
Language Model (VLM) for automatic First-Order Logic (FOL) rule induction with a Dynamic Logic Tensor Network (D-LTN) for differentiable rule verification, in a closed iterative feedback loop. The VLM receives a small set of labelled visual examples and proposes candidate FOL rules conforming to a strict grammar (Think); the D-LTN is automatically assembled from these rules at runtime and evaluates them grounding on CNN-produced visual
embeddings (Verify); and verification failures are fed back to guide the VLM's next hypothesis (Revise). Evaluated on the ViSudo-PC
benchmark across four visual domains (MNIST, EMNIST, KMNIST, FMNIST), the system induces valid Sudoku constraint rules using only three training examples as visual context. The proposed method achieves AUC scores matching or outperforming previous methods (NeuPSL, LTN), showing the potential for automatic rule discovery through VLM. Code is available at https://github.com/homayoun-afshari/nesy.
Read the full abstract ▾
All authors Homayoun Afshari, Pietro Basci, Alessandro Russo, Lia Morra
Artificial Intelligence
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence
Urja Pawar, Rajitha Ramanayake, Nabeel Kemal et al. (+6 more)
LLM decision components that can operate within
agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a system, diagnose errors, or decide when to escalate an output. Such use assumes that the explanations agree with the component's observable decision behaviour. We test two interpretations of the named factors: necessity, meaning that changing a factor would change the output, and sufficiency, meaning that retaining it while removing other changeable information would preserve the output. We evaluate these interpretations in two synthetic use cases: recommending advisors to clients and judging
prompts for harmfulness or risk. Models return an output and the top three factors that most influenced it. Controlled black-box interventions estimate a necessity score for each factor by measuring how often changing it changes the output, and a sufficiency score by measuring how often retaining it preserves the output. Across eight models from the Claude, GPT, and Gemini families, the mean Spearman correlations between the cited ranking and the necessity and sufficiency scores are 0.349 and 0.354 for advisor recommendation, and 0.431 and 0.580 for
prompt monitoring. Furthermore, an uncited factor scores above the lowest-scoring cited factor in 57.6% of advisor responses under necessity and 58.1% under sufficiency; the corresponding
prompt-monitoring rates are 25.8% and 8.9%. The cited top three contain useful information but do not reliably identify the three factors with the strongest measured influence under necessity or sufficiency. The framework provides a black-box reliability check for explanations used in
agent oversight while remaining scoped to individual LLM decisions.
Read the full abstract ▾
All authors Urja Pawar, Rajitha Ramanayake, Nabeel Kemal, Ashwin Kandath, Owen O'Neill, Guillaume Bourgeon, Houssem Chatbri, Christopher Martin, Vadim Pertsovskiy
Computer Vision
Reflection-aware Generative Novel View Synthesis
GeonU Kim, Shin Dong-Yeon and Tae-Hyun Oh
We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view
diffusion models often fail to recognize the mirror in the scene and cannot exploit reflected content for scene generation. To fix this issue without additional training, our key idea is to treat a mirror image as two complementary views. From input images, we estimate the mirror plane and reflect camera poses to form virtual views. Based on this virtual view setup, we propose a two-stage generation method consisting of Mirror-gated
attention and Reflection injection, which enables reflection-consistent NVS by explicitly leveraging reflection relationships in a multi-view
diffusion model. Ref-GeNVS inherits the strong generalizability of the multi-view
diffusion backbone, while it does not require finetuning. On synthetic and real scenes including mirrors, Ref-GeNVS outperforms recent generative NVS methods by generating reflection-consistent and contextually coherent novel views, revealing scene structure visible only through mirrors. Project page: https://kim-geonu.github.io/Ref-GeNVS/
Read the full abstract ▾
Artificial Intelligence
Molecular Déjà Vu: Digit-Level Retrieval of Molecular Properties in Frontier Language Models
Matthias Busch, Marius Tacke, Sviatlana V. Lamaka et al. (+4 more)
Large
language models (LLMs) are increasingly employed to predict molecular properties. However, prediction error alone cannot distinguish prediction from
retrieval of published values. We audit 22 frontier models on 12 molecular regression
datasets in a zero-shot setting, assessed against a molecule-blind reference derived from each
dataset's labels. Significant
retrieval is concentrated on 5
datasets, with isolated flagged LLMs elsewhere. Increasing the
reasoning setting raises the number of flagged model–
dataset combinations from 47 to 89 of 264. An in-context blinding experiment reduces
retrieval but leaves a quarter of the combinations flagged. Blinding changes model rankings and increases errors. Because blinding also removes chemically interpretable structure, the error increase can only be partially attributed to reduced
retrieval.
Read the full abstract ▾
All authors Matthias Busch, Marius Tacke, Sviatlana V. Lamaka, Mikhail L. Zheludkevich, Christian J. Cyron, Roland C. Aydin, Christian Feiler
Cryptography and Security
Propagation Model for SSC attacks: Why SBOM (tools) don't tell the whole truth
Ljubica Grgic, Lazar Maksimovic and Pavel Laskov
Ensuring security of software supply chains (SSC) is indispensable in today's world of modern software practices. SBOM (tools) have been introduced as relevant building blocks to ensure the transparency of SSCs. However they have serious limitations in practices as their vulnerability detection and interpretation capacity is not sufficient to explain exploitability effects that can propagte through the whole chain. To address this gap, we propose a propagation-centred approach to SSC security and introduce a four-stage propagation model. We empirically evaluate four open-source SBOM tools against each stage using three projects and Log4j vulnerability as our test case. Our results show that current SBOM tools systematically support only Stage 1 (Structural Exposure) and Stage 2 (Vulnerability Class Presence) while Stage 3 (Code Reachability) and Stage 4 (Taint Path Analysis) require capabilities absent from the SBOM ecosystem. We argue that putting propagation effects at the centre of SSC security research is essential to prevent cyber risk evolving into systemic risks. Our research findings contribute to a future research and design of modern SSC security tools.
Read the full abstract ▾
Systems and Control · Cross-listed from eess.SP
Full-field laser-Doppler-vibrometry FRF dataset for a four-bolt aluminum plate under bolt-torque variation
Berkay Kullukcu and Dina Hannebauer
The
dataset described in this article was constructed using the results of
laser Doppler vibrometry experiments conducted on an aluminum plate having four bolts. The database captures the variation in the vibration characteristics of the plate as a function of changes in tightening torque on the bolts. In total, there were 18 different states for the tightening torque, ranging from a situation where all bolts are tightened to all bolts being loose. Other possible combinations include states with varying torque applied to just one bolt, and those involving multiple loose bolts. Data consist of 1,836 files exported from Polytec PSV-500, categorized as amplitude and phase data, for frequency ranges spanning 1 Hz to 51,200 Hz at intervals of 1 Hz. The identified zones were analyzed at 51 scan points for all states of torque. Supporting documents included specifications of the test plate, scan point and torque state information, selected resonance peaks tables, measured frequencies for seven resonance groups, correlation values for all FRF, visualizations, and code scripts.
Read the full abstract ▾
Robotics
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies
Vivek Chavan, Pengtao Xie, Yahuan Shi et al. (+3 more)
Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a problem of conditional visual grounding: the visual target required for successful control changes with the manipulation phase and, in more complex tasks, with the observed task state. Using Action Chunking with
Transformers (ACT), we systematically introduce distractor objects and receptacles with controlled color and shape similarity and localize failures to picking and placement. We find that distractor sensitivity is specific to both the type of visual similarity and the manipulation stage. Guided by this diagnosis, we evaluate distractor augmentation, phase-dependent
attention regularization, and appearance-based visual prompting as complementary interventions for improving target selection while preserving spatial information required for control. These interventions substantially improve robustness in simulation and on a physical UR3e. We further examine the same failure pattern in a pretrained
vision-
language-action policy on a state-conditioned instrument-handling task, where the observed state of a medical instrument determines the correct destination. Together, the results show that visual distractors can cause incorrect object or destination selection even when the underlying manipulation skill remains intact, and that explicitly improving target selection can substantially recover performance across distinct visuomotor policy-learning regimes.
Read the full abstract ▾
All authors Vivek Chavan, Pengtao Xie, Yahuan Shi, Oliver Heimann, Kevin Haninger, Jörg Krüger
Artificial Intelligence
CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents
Haoting Shi, Wenhao Wang, Weicheng Fang et al. (+6 more)
Computer-use
agents have advanced on
benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combining visual-state inspection with precise, high-throughput command-line operations, so capable
agents must coordinate both modalities over shared application state. Yet scalable hybrid environments remain scarce because supporting both GUI and CLI over real applications typically requires substantial manual engineering for each application. Existing
agents also struggle to use the two interfaces complementarily: CLI-native
agents lack visual perception for tasks involving interface state or layout, while GUI-native
agents are inefficient for operations better executed through commands. We introduce CUA-Universe, a scalable environment-to-data pipeline that turns real desktop software into hybrid GUI+CLI environments. App-Forge adapts applications into reproducible VMs and command-line surfaces it discovers, wraps, or generates, scaling to 16 applications; Task-Weave synthesizes diverse hybrid tasks of controllable difficulty from reusable operations over seed files; and Path-Steer steers rollouts along efficient hybrid paths and harvests verified trajectories for post-training. Training on this data shifts behavior from inefficient GUI interaction and brittle CLI scripting toward effective GUI+CLI orchestration. Our 9B model improves both success and efficiency on CUA-Verse (Score +39.3 pts; -37% steps, -60%
tokens), OSWorld (SR +16.8 pts; -57% steps, -44%
tokens), and OSWorld-MCP (Score +7.84 pts; -27% steps, -30%
tokens). CUA-Universe provides a scalable path toward more capable and efficient computer-use
agents.
Read the full abstract ▾
All authors Haoting Shi, Wenhao Wang, Weicheng Fang, Yaozhong Liang, Tian Jin, Pengxiang Zhao, Guangyi Liu, Siheng Chen, Yanfeng Wang
Cryptography and Security
When LLM Decompilers Recompile More and Preserve Less
Chang Liu, Edward Raff and Kristopher Micinski
Decompilation recovers high-level source from compiled machine code and serves as a foundation for security tasks such as vulnerability detection and malware analysis. Traditional decompilers like Ghidra and Hex-Rays expose whatever they cannot resolve as visible placeholders and often emit pseudocode that will not compile or execute; LLM-based decompilers produce clean, idiomatic C and are now judged almost entirely by recompilability and re-executability: whether the output builds and passes its shipped input/output tests. We show that these metrics can reward the wrong path: a function may recompile and pass every shipped test yet diverge on other legitimate inputs, and a disclosed vulnerability may disappear from the recompiled code with no visible trace of the crash. Neither failure is caught by existing suites. To address this gap, we propose Decompile-Diverge, a behavioral comparison oracle not relying on fixed or hand-crafted tests: for each function it synthesizes a driver, grows a fuzzing corpus from the reference, and reruns the decompiled code on the same inputs to detect changes in the function's behavior. Across eight systems in nine configurations on established LLM decompilation corpora, candidates that pass every shipped test still diverge from the original on our input corpus: 4.9% overall, and as many as 13% for a single system. On 300 real GitHub library functions and 287 CVE-grounded functions, recompilability and behavioral agreement can come apart: the strongest refinement LLM lifts Ghidra's build rate from 75% to 90%, while its Matched rate falls from 74% to 62%; on disclosed vulnerabilities, up to one tenth exhibit Crash Absence in its output. Source-level analysis traces this divergence to introduced fields, types, callees, and guards that replace the visible unknowns traditional tools leave behind.
Read the full abstract ▾
Robotics
Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation
Vivek Chavan, Yahuan Shi, Oliver Heimann et al. (+2 more)
Vision-
language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task state, dependency-aware
reasoning, conditional decisions, and reliable grounding. We investigate a neuro-symbolic framework that combines learned VLA control with explicit task graphs and
multimodal procedural
memory. Task graphs encode action dependencies, valid transitions, and branch conditions, while
memory maintains the active step, completed actions, textual context, and task-relevant visual evidence. Together, these structures guide object selection, destination grounding, subgoal dispatch, and verification of expected state transitions. Human demonstrations provide additional spatial and temporal guidance through gaze or saliency cues. To isolate their effect on policy learning, our initial study bypasses cross-view gaze transfer and directly annotates pseudo-gaze in
robot-view teleoperation
videos. The resulting guidance is used during VLA fine-tuning and inference. We study two long-horizon manipulation domains, workspace clearing and
surgical-instrument handling, which require ordered execution, visually grounded decisions, and conditional branching. We evaluate correct-object and destination selection, subtask completion, task progress, step-order consistency, complete-task success, and procedural or execution mistakes. This work positions structured symbolic
reasoning and demonstration-derived visual guidance as complementary mechanisms for reliable long-horizon VLA manipulation.
Read the full abstract ▾
All authors Vivek Chavan, Yahuan Shi, Oliver Heimann, Kevin Haninger, Jörg Krüger
Discrete Mathematics · Cross-listed from math.CO
Integrality Gap Bounds for the Goemans-Linial SDP on Finite Abelian Cayley Graphs
Georgios Stamoulis
In the uniform sparsest cut problem we are asked to find a vertex set that cuts few edges relative to the number of vertex pairs it separates. The Goemans-Linial SDP coupled with the Arora-Rao-Vazirani rounding gives an $\mathcal{O}(\sqrt{\log n})$ approximation on arbitrary graphs on $n$ vertices. We study this relaxation on finite Abelian Cayley graphs. First we show that when the second normalized
Laplacian eigenvalue of $G= \mathrm{Cayley}(\Gamma, S)$ is realized by a
Fourier character with image size at most four then $\lambda_2(G)=\mathrm{SDP}_{\mathrm{GL}}(G)=\psi(G)$. Geometrically, a character maps the vertices onto a regular polygon where the squared chord distance satisfies the triangle inequalities exactly when the polygon has at most four vertices. Grouping equal character fibers gives a cyclic quotient where the optimal cut can be found exactly and so the relaxation is exact on finite Abelian Cayley graphs on groups of exponent at most four. Second, we replace each generator $s$ of $S$ by a uniformly random element of its cyclic subgroup (including identity). If $r_s$ is the order of $s$, we let $\alpha(r_s)$ to be the average number of $\pm s$ steps needed to simulate such a move, and let $\rho(S)=\max_{s\in S}\alpha(r_s)$ be its worst case. Full cyclic averaging eliminates character phases and choosing a nontrivial character $\chi^*$ minimizing the auxiliary
eigenvalue and taking $K=\mathrm{ker}\chi^*$ gives \[ \psi(G)\leq\psi_G(K)\leq\frac{q^*}{q^*-1} \cdot\rho(S)\cdot\mathrm{SDP}_{\mathrm{GL}}(G)\leq 2\rho(S)\cdot\mathrm{SDP}_{\mathrm{GL}}(G), \] where $q^*=|\chi^*(\Gamma)|$. If all generator orders are at most $R$, this is an $R/2$ approximation. Finally, we construct an infinite family of finite Abelian Cayley graphs with Goemans-Linial integrality gap exactly $16/15$.
Read the full abstract ▾
Programming Languages
Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool
Samuel Kushnir, Kimia Noorbakhsh, Kavya Sreedhar et al. (+6 more)
Machine-learning performance modeling is a uniquely hostile terrain for long-lived software: the assumptions baked into today's abstractions are invalidated by tomorrow's models and systems, forcing perpetual refactoring of performance-modeling frameworks. Meanwhile, AI coding
agents have become fast and capable enough that regenerating an entire library is cheaper than paying down the tech debt of incrementally patching it. We describe SMART, a rigorous symbolic performance-modeling library for ML systems whose main branch contains almost no code: the repository is a DAG of self-contained natural-
language design docs, coding sub-
agents regenerate the implementation from only the docs on new version updates, and every human change is a natural-
language edit to a doc–self-documenting by construction. Two ingredients make regeneration reliable: (i) a design-doc style built around step-by-step worked examples that act as in-context demonstrations for the generating
agents, and (ii) a minimal, recursively defined operator IR with symbolic (SymPy) cost expressions, a fast analytical roll-up mode for large sweeps, and a slow modulo-scheduling mode for fine-grained schedule studies. Regenerated implementations reproduce hand-audited reference models–including DeepSeek-V3 serving on a TPU pod slice–to round-off precision, suggesting that design docs–not code–can be the durable artifact for ML-systems co-design tools.
Read the full abstract ▾
All authors Samuel Kushnir, Kimia Noorbakhsh, Kavya Sreedhar, Liqun Cheng, Ming Liu, Parthasarathy Ranganathan, Mohammad Alizadeh, Fred Kjolstad, Suvinay Subramanian
Machine Learning
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
Siliang Liu, Mohammad Ghasemi, Sapan Patel et al. (+1 more)
Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large
language models (LLMs) can reason about such distinctions, but applying them directly to hundreds of millions of product pairs is operationally impractical. We introduce a two-level framework that distills LLM
reasoning into an efficient non-generative student and adapts its decision boundary to product-type-specific trade-up criteria. At Level 1, a
retrieval-augmented few-shot LLM teacher generates structured relation labels and natural-
language rationales. These rationales supervise a compact
embedding-pair classifier through
alignment and contrastive objectives; at inference, the student uses only two precomputed 768-dimensional product
embeddings, with no LLM calls or text generation. On a fixed human-annotated
benchmark of 8,352 pairs, a 15.5M-parameter four-class
reasoning-distilled student achieves AUC 0.924 (95% CI [0.918, 0.929]), compared with 0.912 for the four-class label-only student. At Level 2, product-type test-time training (PT-TTT) uses few-shot demonstrations to optimize lightweight category-specific adapters over the frozen student. PT-TTT improves AUC from 0.924 to 0.941 and average precision from 0.920 to 0.940. On a 100K-pair proxy catalog, the distilled student on a single eight-GPU machine is approximately 5,000x faster and 10,000x lower in estimated cost than direct LLM inference.
Read the full abstract ▾
All authors Siliang Liu, Mohammad Ghasemi, Sapan Patel, Amin Banitalebi-Dehkordi
Robotics
Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia et al. (+4 more)
Human-
robot interaction (HRI) enables intuitive and intelligent collaboration between humans and
robots in real-world environments. This paper introduces a
humanoid robot prototype designed as a flexible testbed for developing and integrating artificial intelligence (AI) modules in HRI tasks. The system features a 12 degree-of-freedom (DOFs) dual-arm mechanism and a 2 DOFs head with an expressive LCD screen to express facial
emotions. All hardware components are controlled by a custom-designed controller board with real-time AI processing supported by an onboard Jetson module. The system incorporates three AI modules: (1) gesture recognition using MediaPipe Pose and an LSTM classifier, (2) object detection with YOLO and 3D localization, and (3) voice-command processing through
speech recognition and large
language model(LLM)-based semantic parsing. The platform is validated through experiments on positioning accuracy, with results showing average manipulation errors of approximately 1.83 cm. To demonstrate its versatility, experimental results show over 90% task accuracy, with gesture recognition reaching 96%,
speech recognition reaching 92%. The results confirm the effectiveness of the proposed system as a reproducible and accessible
humanoid platform for research and prototyping in HRI.
Read the full abstract ▾
All authors Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia, Phuc Dinh Van, Son Tran Duc, Ngoc Minh Do, Xiem HoangVan
Systems and Control
Data-Driven Generator Transient Prediction for Digital Twin Decision Support
Emad Sadeghi, Emerson Miller, Kerry Sado et al. (+1 more)
This paper develops a calibrated transient
forecasting surrogate model for generator digital twin (DT) decision support that evaluates planned active- and reactive power load commands before they are applied. The proposed event-conditioned Hankel Dynamic Mode Decomposition with Control (Hankel-DMDc) model combines delay-coordinate lifting, command-event
memory features, and an event-weighted Hankel basis so that sparse load-transition dynamics influence the reduced representation and fitted dynamics. This design targets intervals where voltage/frequency deviations and recovery behavior determine whether a candidate load command keeps the system within acceptable limits. To provide operator-facing confidence information, a split-conformal calibration layer is applied to the frozen surrogate model to form event-conditioned joint prediction bands for voltage and frequency. The experimental results show event-window root-mean-square errors of 1.058 V and 0.155 Hz. For a nominal 90% target, the bands attain 90.17% pointwise joint voltage-frequency coverage, with mean band widths of 3.55 V and 0.566 Hz. A 50-s open-loop rollout is computed in 181 ms on a single CPU core, approximately 280 times faster than real time, with forecast accuracy evaluated over horizons up to 5 s. These results demonstrate a computationally efficient advisory framework for generator DTs that combines transient prediction with calibrated uncertainty.
Read the full abstract ▾
All authors Emad Sadeghi, Emerson Miller, Kerry Sado, Adel Nasiri
Computer Vision
MEOX: Modality-Conditioned Routing Before Fusion in a Compact Earth Observation Encoder
Mohanad Albughdadi
Multimodal Earth Observation models often fuse radar and optical inputs early, limiting sensor-conditioned processing, or maintain separate sensor streams through the encoder, increasing computational cost. We present MEOX (
Multimodal Earth Observation with eXperts), which delays fusion until after a shared mixture-of-experts block that processes Sentinel-2 and ascending and descending Sentinel-1 streams independently. Co-located patches are then fused with validity-aware weights into a single sequence processed by fourteen shared blocks, reducing the sequence length from 3N + 5 to N + 5
tokens for N patches. We pretrain the 2.939M-parameter encoder on 1.228M MMEarth64 samples using masked radar-optical reconstruction. Under the reported frozen-transfer protocols, MEOX reaches 90.56% average class accuracy on EuroSAT and 64.42% mean intersection over union (mIoU) on cashew
segmentation, 2.26 and 5.02 points above the strongest reported cross-sensor mixture-of-experts (CSMoE) variants. Full-encoder adaptation increases BigEarthNet micro-average precision from 57.22% to 72.95%. In a controlled same-corpus test using synthetic random patch removal, masking 75% of Sentinel-2 patches reduces WorldCover mIoU from 30.45% to 26.53% when both Sentinel-1 streams remain available; with Sentinel-2 alone, mIoU falls to 13.81%. For identical zeroed optical patches, declaring them missing through the validity mechanism improves mIoU from 19.42% to 26.53%. These results characterize a compact route-then-fuse encoder that retains sensor-conditioned processing and uses complementary radar observations when optical inputs are incomplete.
Read the full abstract ▾