Robotics
Bi-manual Stabilization of the Cervical Spine for Safe Physical Human-Robot Interaction in Rolling Maneuvers
Elizabeth Peiros, Moira Bohley, Lucas Yager et al. (+6 more)
The neck, specifically the cervical spine, is a highly fragile and mobile part of the body with a high risk of catastrophic injury. Whether someone is injured on a battlefield, in a natural disaster, or in an athletic event, great care is always taken with the cervical spine when transporting, rolling, or moving the patient. In this work, we present an
algorithm and adaptations for bi-manual
robots to stabilize the cervical spine during rolling maneuvers. We investigate techniques to maximize grip strength within safety bounds and present a control approach for proper neck rotation. We found that with our approach, a bi-manual
robot is capable of achieving human-level performance in maintaining target rotational
alignments. The axial
alignment for the
robot with prediction was within .21 degrees of human novices.
Read the full abstract ▾
All authors Elizabeth Peiros, Moira Bohley, Lucas Yager, Derek Chen, Rebecca Fellbaum, Chris D'Ambrosia, Ananya Rao, Xiao Liang, Michael C. Yip
Neural and Evolutionary Computing
Adaptive Operator Selection in Bilevel Large Neighborhood Search for Electric Autonomous Dial-a-Ride Problem under Uncertainty
Ishara Hewa Pathiranange and Aneta Neumann
The electric autonomous dial-a-ride problem (EADARP) extends the classical dial-a-ride problem by incorporating battery and charging constraints for electric vehicles. In practice, travel-time uncertainty can cause violations of time-window constraints. Large neighborhood search is effective for solving the EADARP, but its performance can depend on the choice of insertion operator during the repair phase. This paper investigates insertion-operator selection within a bilevel large neighborhood search framework for deterministic and chance-constrained variants of the EADARP. In the chance-constrained variant, arc travel times are modeled as independent normally distributed random variables, and upper time-window constraints are enforced probabilistically. We consider six selection methods, namely fixed greedy insertion, fixed regret-based insertion, random selection, a deterministic state-based rule, performance-adaptive ALNS selection, and LLM-based state-aware selection. Experimental results show comparable performance on smaller instances, while differences become more evident on larger and more constrained instances. There is no single strategy that performs best across all instances, and the relative performance of the LLM-based, rule-based, and ALNS strategies varies with the problem instance and experimental setting.
Read the full abstract ▾
Artificial Intelligence
TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases?
Jirui Dai, Chenkai Zhang, Yan Jia et al. (+4 more)
Large
language models (LLMs) can generate clinical narratives that are insufficiently grounded in patient-specific evidence. In traditional Chinese medicine (TCM), errors can propagate from etiology and pathogenesis through syndrome diagnosis and treatment principles to prescription generation. We developed TCMClinicalReason-Bench using 2,000 multicenter electronic health record cases to distinguish case-grounded responses from fluent but unsupported diagnostic and therapeutic conclusions. Five general-purpose and two TCM-specific LLMs were evaluated in zero-shot settings. An evidence-constrained rubric assessed seven diagnostic and therapeutic components and three cross-block relations, allowing case-supported alternatives. Qwen3.7-Plus with TCM
retrieval served as the automated judge, alongside parallel blinded ratings by five senior TCM clinicians on a 600-case subset. Structural completeness was nearly saturated (99.3-100.0%), but normalized content scores ranged from 40.7% to 54.1%. The five general-purpose models averaged 50.0%, versus 41.3% for the two smaller TCM-specific models. Cross-block logic consistency ranged from 60.8% to 66.8% and correlated moderately with content across cases (Pearson's r = 0.515-0.656). Deficits were greatest in prescription generation, prescription analysis, and symptom-guided modification. In judge stress testing on 100 independent cases, perturbation detection rates across the three relations were 57%, 56%, and 31%, with contradictions detected more reliably than omissions. Separating component quality from cross-block consistency localizes failures missed by endpoint and completeness metrics and identifies where clinician oversight remains necessary.
Read the full abstract ▾
All authors Jirui Dai, Chenkai Zhang, Yan Jia, Yukai Wang, Ruiyang He, Changyong Luo, Zhi Liu
Machine Learning
FTD-GNO: Memory-Efficient Graph Neural Operators through Functional Tensor Decomposition of the Kernel
Xiaomin Zhang, Boyue Wang, Junbin Gao et al. (+1 more)
Graph Neural Operators (GNOs) provide flexible surrogate models for learning solution operators of partial differential equations (PDEs). However, standard GNOs typically parameterize the integral kernel with a monolithic neural network and evaluate kernel interactions over graph edges, leading to substantial computational and
memory overhead at high resolutions or with large neighborhoods. To address these limitations, we propose Functional Tensor Decomposition Graph Neural Operator (FTD-GNO), a
memory-efficient GNO framework that decouples the high-dimensional continuous integral kernel into low-dimensional mode-wise functions. By instantiating the kernel with classical tensor decomposition formats, including CP, Tensor-Train, and Tucker decompositions, FTD-GNO enables algebraic reconstruction of the integral operator without explicitly materializing full edge-wise kernel tensors. This factorized formulation reduces the
memory footprint of kernel evaluation and aggregation while retaining the continuous operator-learning structure of GNOs. Theoretical complexity analysis shows that FTD-GNO substantially lowers parameter and activation-
memory costs associated with high-dimensional kernel construction. Experiments show lower peak
memory than the corresponding unfactorized graph-integral baselines, with shorter recorded training times.
Fourier-graph experiments further demonstrate that FTD can improve the efficiency of a graph-integral layer within a hybrid operator and has good scalability.
Read the full abstract ▾
All authors Xiaomin Zhang, Boyue Wang, Junbin Gao, Yongli Hu anbd Baocai Yin
Graphics
CurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model
Mingyi Shi, Huancheng Lin, Xuelin Chen et al. (+1 more)
Skeletal motion is stored as every joint's transform at every frame, yet most of it is implied by the body rather than by what the motion is about. Compression is one way to ask what a motion must still say once the body is known, and a production codec must answer it for any skeleton with a stated error bound. Our earlier codec, CurveCodec, matched the mean error of ACL, the production library of modern game engines, with a learned prior over sparse anchors, but not ACL's worst case, and it counted its payload as floats rather than bits. Here we ask where the redundancy of skeletal motion lies and which part of a codec a learned model should take over. Measurements give three answers. At production precision the largest saving comes from predicting each quantized curve from its own past, the second from choosing per joint, in closed loop through the hierarchy, which samples not to code. On the gaps such an encoder leaves, a nearest-neighbour oracle over millions of training samples is no better than linear interpolation, and no learned in-betweener we tried paid for itself. What a network does learn is the distribution of the residuals the codec must send. CurveCodec 2 codes every sub-track as a curve in the log map, quantized in closed loop and thinned to rate-distortion-selected keys, with residuals
entropy-coded under a small learned model whose integer inference is bit-exact across platforms. Two contracts are verified on every decoded clip: ACL's own worst case per joint within a stated tolerance, or ACL's mean error per clip. On a held-out test side of 4,472 clips from 33
datasets, CurveCodec 2 needs 0.37x ACL's bytes at ACL's default precision of 0.01 cm under the worst-case contract and 0.22x at 0.1 cm under the mean contract, decodes on one CPU core, and transfers without retraining to a species absent from training. Project page: https://rubbly.cn/publications/curvecodec/
Read the full abstract ▾
All authors Mingyi Shi, Huancheng Lin, Xuelin Chen, Taku Komura
Computation and Language
Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams
Sugam Panthi, Muhaiminul Yeamin and Rabab Abdelfattah
Large
language models (LLMs) receive each user message as plain text, even when it combines text from different sources. For example, a user may paste text into a
prompt and keep typing a comment directly below it. We study absorption: a phenomenon where the model treats a trailing user comment as part of the pasted text, returning it inside the edited text. This happens even though the user did not intend the comment to become part of that text. Existing instruction-data separation
benchmarks tell the model which text is instruction and which is data, then test whether it obeys that separation. They do not test harmless user
speech following an unmarked paste. We introduce SEAM, a controlled
benchmark of 300 editing examples. Each example is tested under six matched conditions that vary how the boundary between pasted text and later user
speech is expressed. Across 20 models, absorption at a bare newline ranges from 7.7% to 66.7%. Adding a blank line does not significantly reduce absorption in any model, while boundary markers reduce it in 19 of 20 models. Comments that fit the pasted text, such as a code comment typed after code, are absorbed significantly more often in 17 of 20 models. Models often fail to separate pasted material from later user
speech, and explicit boundaries reduce but do not remove this failure.
Read the full abstract ▾
Systems and Control
Decentralized Scalar Field Mapping using Gaussian Process
Hossein Papi, Muzaffar Qureshi, Kyle Volle et al. (+2 more)
Decentralized Gaussian process (GP) methods provide a scalable framework for multi-
agent scalar-field estimation by allowing each
agent to maintain a local GP over its assigned subdomain. Because neighboring
agents condition their GP models on different measurements, their GP posteriors generally disagree over overlapping regions. This paper introduces the inducing points decentralized Gaussian process (IPD-GP) framework, which exploits these discrepancies to improve posterior consistency over shared regions. Each sender constructs receiver-specific data packets by selecting inducing locations targeted at the pairwise overlap and transmitting the corresponding posterior means and variances. Each receiver then selectively assimilates informative packets as persistent fictitious measurements in its local GP. The developed architecture preserves decentralized computation and communication without requiring full
dataset exchange or centralized inference. Performance is evaluated using normalized root-mean-square error, negative log predictive density, and their overlap-restricted counterparts, with comparisons against non-communicating local GPs, decentralized aggregation methods, and a centralized GP. Simulation results show that IPD-GP achieves competitive predictive accuracy while reducing inter-
agent communication.
Read the full abstract ▾
All authors Hossein Papi, Muzaffar Qureshi, Kyle Volle, Omkar Sudhir Patil, Rushikesh Kamalapurkar
Artificial Intelligence
Fine-Tuning VLM for Enhancing AI's Spatial Intelligence: Understanding 3D and 2D Rotations
Uttamasha Monjoree and Wei Yan
Spatial intelligence is a fundamental skill in multiple domains, such as Science, Technology, Engineering, and Mathematics (STEM), Medicine, Architecture, and Construction. Recent studies indicate that
Vision-
Language Models (VLMs) still face limitations in spatial
reasoning, which inhibits artificial intelligence (AI) from performing practical spatial tasks. Using multiple object-rotation
datasets developed for training and evaluation, our experiments demonstrated promising improvements in both 2D and 3D rotation detection. Fine-tuned Google DeepMind-built Gemma-4 mixture-of-experts (MoE) models significantly outperformed fine-tuned Gemma-4 generalist models in predicting rotations defined by both their axes and angles. Fine-tuning also substantially improved angle estimation for 2D representation without requiring an explicit coordinate system. Furthermore, identifiable objects did not improve angle-detection accuracy; instead, objects with prominent linear features showed improved performance.
Read the full abstract ▾
Machine Learning
Clean: Second-order LLM Training at Linear Memory Cost via Nyström Sketching
Beheshteh T. Rakhshan, Sahar Rajabi, Maziar Sargordi et al. (+3 more)
Training large
language models (LLMs) entails a fundamental trade-off:
memory-efficient optimizers such as Adam discard cross-parameter
curvature, whereas full-
curvature methods such as SOAP can accelerate convergence at prohibitive
memory costs. We introduce Clean, a
memory-efficient and full-
curvature optimizer designed to resolve this bottleneck. Clean leverages the randomized Nystrom method to accurately approximate the left and right preconditioners in SOAP, and to reduce the optimizer's
memory complexity from quadratic to linear in terms of model dimensions. We subsequently reintegrate the off-subspace components to capture
curvature information beyond the low-rank approximation, preserving rich
curvature at minimal
memory cost. We further propose Q-Clean, a low-precision variant that aggressively compresses optimizer states. Q-Clean reduces optimizer
memory consumption by over 50% compared to
Muon when pre-training a LLaMA-1.3B architecture, all while maintaining strong and competitive predictive performance. Notably, Clean operates with a smaller optimizer-state footprint than standard AdamW while reaching AdamW's final performance 26% faster in wall-clock time. Furthermore, our methods uniquely enable the pre-training of a 13B-parameter model on a single 80GB GPU, providing a scalable, efficient, and accessible approach to large-scale model optimization.
Read the full abstract ▾
All authors Beheshteh T. Rakhshan, Sahar Rajabi, Maziar Sargordi, Shikai Fang, Guillaume Rabusseau, Sirisha Rambhatla
Computer Vision
Sparse-GS2Mesh: 3D Gaussian Splatting Guided by Novel Stereo Views and 2DGS for Sparse View Surface Reconstruction
Younghyun Noh, Minje Kim and Tae-Kyun Kim
Surface reconstruction under sparse-view settings remains challenging due to limited
geometric cues. Volume rendering methods based on signed distance functions often produce over-smoothed surfaces, while 3D Gaussian Splatting (3DGS), though time-efficient, suffers from incomplete geometry due to the lack of reliable depth supervision and the limitation of being optimized only from given input views. In this paper, we present Sparse-GS2Mesh, a stereo-aware framework for surface reconstruction from sparse views. While 3DGS and stereo matching have been leveraged for surface reconstruction under dense view settings, we extend them to operate effectively under sparse view conditions by first initializing 3DGS using epipolar depth priors to mitigate the 3DGS overfitting problem, followed by our three key components: (I) adaptive baseline selection, (II) fine-tuning with a stereo matching network, and (III) 2D/3D co-regularized fine-tuning. Given a warmed-up 3DGS initialized with epipolar depth, the adaptive baseline selection automatically determines a baseline to synthesize for each sparse view. We then fine-tune 3DGS by backpropagating depth-refining gradients from the stereo matching network, effectively specializing the 3DGS for stereo matching. The 2D/3D co-regularization further helps obtain stable reconstruction, addressing weak
geometric cues in close stereo views. Sparse-GS2Mesh achieves a 15% improvement over state-of-the-art methods in little-overlap settings and comparable results in large-overlap settings. Project page: https://yhnoh8623.github.io/projects/s-gs2mesh/.
Read the full abstract ▾
Systems and Control
Nesterov-Accelerated Concurrent Learning for Lyapunov-Based Deep Neural Networks
Hossein Papi and Omkar Sudhir Patil
Concurrent learning (CL) has recently been extended to Lyapunov-based deep neural networks (DNNs) to obtain parameter convergence under finite rather than persistent excitation. However, the existing first-order law converges slowly, especially for high-dimensional systems and overparameterized networks. To address this problem, this paper develops a Nesterov-accelerated concurrent learning (NACL) adaptation law for uncertain second-order control-affine systems. The developed law drives momentum dynamics with recorded state-input data, so that all hidden layers of the DNN are updated online under a verifiable finite excitation condition. A dynamic state-derivative observer is designed to reconstruct the recorded input without acceleration measurements. The momentum variable introducesa cross term coupling the momentum lag error to the state-dependent DNN Jacobian and the tracking error, and a state-dependent normalization is introduced into the momentum filter to dominate it. A Lyapunov-based analysis establishes exponential convergence of the tracking, momentum, observer, and weight estimation errors to a bounded residual ball. Simulations on a six- degree-of-freedom unmanned
underwater vehicle demonstrate a 24.5% and 62.9% reduction in the root-mean-square function approximation error relative to first-order CL and to a higher-order tuner without CL, respectively.
Read the full abstract ▾
Computer Vision
CellSplat4D: PSF-Aware 4D Gaussian Splatting for Sparse Robotic Live-Cell Imaging
Yingda Tao and Guoyu Lu
A robotic microscope watching living
cells cannot afford to look as often as it would like. Every volume it acquires costs
photons the specimen does not get back, and time owed to other wells. What such a platform exists to produce is a record of individual
cells through time: which
cell is which from one volume to the next, and which
cell divided into which two. Sampling sparsely breaks that record exactly where it matters, and the fault lies in the acquisition schedule rather than in the analysis software. We fill the gaps by reconstructing them, fitting a 4D Gaussian model to whatever volumes the hardware could afford. The model is a cloud of light-emitting blobs, each carrying a position, a shape and a lifetime. Being continuous in time, it renders any missing volume on demand, decoupling how often the
robot analyses from how often it can afford to look. The microscope's point-spread function is measured from the data rather than inherited from acquisition metadata or left to the optimizer, because metadata inflates it and the optimizer cannot recover it at all: a wider blur around a smaller blob fits the images equally well. Each blob's lifetime is stored in frames rather than as a fraction of the recording, so that it denotes a fixed duration on any sequence. Unmeasured timesteps are supervised at coarse scale by a 3D U-Net that predicts the intermediate volume directly and estimates no motion field, since a dividing
cell becomes two and no motion describes that. On two
Cell Tracking Challenge sequences, a C. elegans embryo and a Chinese Hamster Ovarian (CHO), with fidelity scored per
cell nucleus, our reconstruction holds the highest
nucleus fidelity at every distance from an acquired frame, has the flattest decay across the gap, and best recovers focal planes it was never shown with graceful degradation across the gap.
Read the full abstract ▾
Artificial Intelligence
Liancheng Fang, Zhuowei Li, Youngeun Kim et al. (+10 more)
Diffusion language models (DLMs) enable fast generation by predicting multiple
tokens in parallel, but their practical adoption remains limited by a persistent quality gap relative to comparably sized autoregressive (AR) models. We attribute this gap to a computation-difficulty mismatch: within a partially observed sequence, some unknown
tokens are easy to predict, while others require substantially more computation. Existing DLMs nevertheless apply uniform computational depth to all unknown positions at each denoising step. We introduce ALoDLM, which replaces uniform computation with
token-adaptive latent recurrence. At each denoising step, ALoDLM iteratively refines latent representations and allocates computation according to
token difficulty.
Tokens ready to commit are fed back as discrete context, while unresolved
tokens retain and further refine their latent states through additional recurrent passes. To learn
token prediction and computation allocation jointly, we formulate
token-wise computation schedules as latent variables and derive a conditional negative evidence lower bound (NELBO). We train ALoDLM at 1.7B and 8B parameter scales. Across eleven
benchmarks, ALoDLM outperforms all evaluated DLMs and the corresponding AR baselines in average
benchmark score at both scales. ALoDLM also retains fast parallel decoding, yielding a strong quality-efficiency trade-off among evaluated autoregressive and
diffusion models under optimized inference engines.
Read the full abstract ▾
All authors Liancheng Fang, Zhuowei Li, Youngeun Kim, Tianchen Zhao, Rajat Koner, Jiaye Wu, Linghan Xu, Xuanbai Chen, Xiang Xu, Zheng Zhang, Jakub Zablocki, Nishant Sankaran, Yifan Xing
Artificial Intelligence
Asynchrony Is Nearly Free for Evolution Strategies on Long-Horizon LLM Agentic Tasks
William Hoy, Jingxuan Fan, Nurcin Celik et al. (+1 more)
Synchronous policy updates can limit the efficiency of post-training for long-horizon LLM
agents. When trajectories span multiple interaction turns, completion times can vary substantially, and synchronous update barriers leave faster workers idling, wasting compute resources. Asynchronous reinforcement learning addresses this inefficiency but introduces policy lag and off-policy optimization.
Evolution strategies (ES) are a backpropagation-free alternative to gradient-based training, yet require many perturbed-policy evaluations and have remained largely synchronous in current LLM post-training. We introduce bounded-staleness asynchronous ES and investigate its training behavior under stale fitness measurements. On WebShop, we systematically vary the lag and fraction of stale fitness measurements and additionally introduce two stress tests to probe extreme staleness cases. Natural asynchrony closely tracks synchronous ES, and degradation in evaluation accuracy remains small even under extreme staleness, including when all fitness measurements are stale. These findings suggest that ES can tolerate substantial policy staleness without explicit off-policy correction, supporting its use in asynchronous post-training for long-horizon LLM
agents.
Read the full abstract ▾
All authors William Hoy, Jingxuan Fan, Nurcin Celik, Xu Pan
Artificial Intelligence
MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory
Priyanka Mudgal, Kai Zhao, Guilin Zhang et al. (+4 more)
Personal AI
agents in enterprise multi-tenant deployments share a common vector store for long-term
memory. Shared
embedding spaces create a surface for cross-user
memory leakage: a user's query can retrieve semantically adjacent
memories belonging to another user through ordinary cosine-similarity
retrieval, without any exploit. We formalize this as cross-user admissibility failure and evaluate it across six experiments, plus follow-up ablations, under both sparse (TF-IDF) and production-faithful (MiniLM-L6-v2)
retrieval. Non-
adversarial, incidental leakage reaches 70–100% under pooled {same-team}
retrieval; adversarially crafted
memories achieve 90–100% top-$k$ placement, exceeding weaker keyword-based attacker baselines, with score lifts of $+0.416$ to $+0.511$ under production-faithful dense
retrieval (Config B); and end-to-end response contamination reaches 5.00/5 under a production
retrieval path and 4.67/5 with Claude Sonnet~4.5, with contaminated responses often scoring as helpful or more helpful than clean ones, a gap validated against human judgment. Among three architectural mitigations, only hard post-
retrieval ownership gating consistently restores the clean baseline (1.00/5) across {two generation models, at a measured latency overhead of roughly 1.4~ms per query.
Read the full abstract ▾
All authors Priyanka Mudgal, Kai Zhao, Guilin Zhang, Andy Olsen, Ezekiel Miller, Xu Chu, Aletta Johanna Blanken
Human-Computer Interaction
Evaluating Just Noticeable Differences in Layered Opacity Visualizations
Caterina Ponti, Shano Liang, Lane Harrison et al. (+1 more)
Opacity is a widely used channel in data visualization, but it remains less well understood compared to channels such as color, length, size, etc. Recent work from Meng et al. investigated the impact of opacity across competing color schemes, finding that certain color schemes were associated with better participant accuracy. We examine these effects further in a controlled two-alternative forced-choice setup to determine whether opacity differences are truly equal across possible opacity comparison ranges. In a within-subjects study with 96 trials, including two competing color schemes (best and worst from Meng et al.) and 48 opacity pairs, we find little differences between color schemes but larger individual differences in accuracy. Further, results show stable performance in middle opacity ranges, with more errors occurring when comparing extreme values. We discuss potential implications for design guidelines and further study and make our study materials, analysis scripts, and data available at https://osf.io/zv9dx/overview?view_only=38d03cea1b3d42788593e3e6b1016cfd.
Read the full abstract ▾
All authors Caterina Ponti, Shano Liang, Lane Harrison, Alark Joshi
Artificial Intelligence
Agentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation
Uttamasha Monjoree and Wei Yan
Recent studies show that artificial intelligence (AI) with
language and
vision capabilities still experiences limitations in spatial
reasoning. In this paper, we have studied the spatial capabilities of advanced generative AI to understand the rotations of objects in 3D space, utilizing AI's image processing and
language processing features. We trained and examined the spatial intelligence of a generative Agentic AI model (GPT-5.6) to understand the spatial rotation process with rotation diagrams based on the revised Purdue Spatial Visualization Test: Visualization of Rotations (Revised PSVT:R). We improvised the Revised PSVT:R by superimposing additional graphical and contextual features to evaluate how different Chain-of-Thought (CoT)
reasoning strategies influence model performance. The results indicate that structured CoT
reasoning improves the spatial
reasoning performance of the base GPT-5.6 model in both
datasets (PSVT:R and PSVT:R with coordinate system). We used three CoT approaches - (1) Structured CoT, (2) few-shot Structured CoT, and Structured CoT with Self-optimized
Prompt. The three CoT approaches evaluated in this study showed no significant performance difference. Results showed that combining structured CoT
reasoning with relevant contextual information leads to considerable improvements in VLM performance on 3D rotation tasks, demonstrating the potential of agentic AI for more effective spatial
reasoning. However, when contextual information is removed, structured CoT
reasoning alone provides limited improvement, and the models continue to exhibit notable difficulties in understanding spatial transformations. These findings suggest that effective spatial
reasoning in VLMs relies on the integration of visual, textual, and
reasoning-based information in future agentic AI systems for spatial intelligence.
Read the full abstract ▾
Robotics
Autoware in Construction: Gap Analysis and LiDAR Perception Toward Off-Road Autonomous Driving
Yu Otsuki, Teja Emmey, Sena Matsushita et al. (+2 more)
Autoware is an open-source autonomous driving software platform widely adopted by researchers and industry developers. Originally developed primarily for public-road applications, including passenger vehicles, taxis, and buses, Autoware is increasingly being extended to off-road environments such as construction and agricultural sites. Construction sites, however, differ fundamentally from public roads and challenge many assumptions underlying conventional autonomous driving systems. They are characterized by unstructured terrain, airborne
dust, continuously evolving site conditions, and construction-specific objects. This paper presents lessons learned from ongoing efforts to extend an Autoware-based autonomous driving system to large dump trucks operating at construction sites. We identify gaps between public-road and off-road construction applications across the sensing, mapping, localization, perception, planning, and control modules of the Autoware stack. We then discuss potential solutions for addressing these gaps, with particular emphasis on ongoing
LiDAR-based perception pipeline development and findings from field testing. Finally, we propose a roadmap toward end-to-end autonomous driving for construction vehicles.
Read the full abstract ▾
All authors Yu Otsuki, Teja Emmey, Sena Matsushita, Akiro Harada, Takeshi Miura
Systems and Control · Cross-listed from math.OC
Time-reliability optimization of multi-pass underfill dispensing sequences on printed circuit boards: a schedule-dependent reliability model solved by a multiset-permutation binary-addition-tree algorithm
Wei-Chang Yeh
Multi-pass underfill dispensing couples cycle time with process reliability because the sequence determines the inter-pass flow times. This paper formulates a tri-objective multiset-permutation routing model that minimises nominal cycle time and additive duration variance while maximising reliability under hard- and soft-dwell policies; reliability combines pass, schedule-dependent flow and travel terms. Under independent durations and deterministic dwell thresholds, the variance measure equals the cycle-time variance under soft dwell and bounds it from above under hard dwell. A multiset-permutation binary-addition-tree
algorithm enumerates the feasible routes without duplication and prunes prefixes by dominance. Six instances, including three BeagleBone Black
benchmarks, yield reference Pareto fronts, the largest search space of $1.47 \times 10^{12}$ routes in 38 minutes on 20 CPU cores. Among simulated candidates, the nominally cost-selected routes incur maximum estimated excess costs of USD 0.0014 per board at the modelled duration variability and USD 0.0035 with it doubled. Round-robin dispatch is within 3.7 % of the reference optimum at the tested costs; NSGA-II and simplified swarm optimisation show at most 0.53 % observed cost regret while recovering about 30 % of the largest hard-dwell front. The framework quantifies sequencing trade-offs and heuristic decision regret; physical reliability prediction requires inspection-based calibration.
Read the full abstract ▾
Computer Vision
Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation
Hsin-Chen Pai, Jyun-Kai Wang, Yi-Cheng Peng et al. (+1 more)
Referring multi-object tracking (RMOT) takes a
video and a
language expression as input and tracks all referred objects. Many tracking requirements involve how an object moves rather than how it appears. However, in a
video captured by a moving camera, a parked vehicle may appear to move, while a moving vehicle may show little displacement. Existing RMOT methods relate motion with text but do not explicitly remove camera-induced motion. In this paper, we propose extracting residual motion across frames by estimating camera motion in driver-view
videos and compare motion characteristics with the query expression. We consider the motion-matching extent and integrate it with the RMOT method's prediction result through late fusion. In the evaluation, we verify the performance gain of taking the motion compensation module as a plug-in across different RMOT hosts.
Read the full abstract ▾
All authors Hsin-Chen Pai, Jyun-Kai Wang, Yi-Cheng Peng, Wei-Ta Chu
Artificial Intelligence
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Yaolun Zhang, Tianyi Xu, Yujie Zhao et al. (+3 more)
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex
benchmarks is costly and slows iteration. Human experts reduce this cost by selecting
benchmark subsets or designing compact suites. We ask whether AI
agents can automate this design process and introduce EvalResearchBench (ERB), a
benchmark for autonomous evaluation research. Given target materials, development references, candidate APIs, and fixed time and API budgets, an
agent called the researcher selects or synthesizes tasks, implements graders, and revises them in pilot tests before freezing an executable evaluator for coding, co-work, and
reasoning. We study 9 researchers and 13 candidate models and compare each frozen evaluator with 14 target
benchmarks on score concordance and pairwise agreement. The best evaluators order about 75% of candidate pairs as the targets do, below the 91% ceiling set by disagreements among the targets. No researcher leads on every metric, and the best evaluator on development targets is not the best on sealed targets hidden from the researcher. A human-designed sample of public tasks remains a strong baseline, and the evaluator with the lowest recorded execution cost attains the highest pairwise agreement.
Agents repair tasks and graders through pilot feedback, yet their evaluators can still truncate answers, exhaust the evaluation budget, or let a few questions dominate a domain score.
Read the full abstract ▾
All authors Yaolun Zhang, Tianyi Xu, Yujie Zhao, Jishen Zhao, Qingyun Wu, Huazheng Wang
Artificial Intelligence
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd et al. (+16 more)
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize that this robustness is a result of passive dynamics, i.e., constraining mechanisms in the forward pass that funnel activations toward "good" regions that produce coherent outputs. To investigate these hypothesized error-correcting mechanisms, we probe the geometry of
language model activation space by observing the action of model layers on low-dimensional curves. In doing so, we discover that model activations occur within a cluster of distinct attracting basins, which differentiate natural activations geometrically from distributionally similar synthetic activations. Applying this lens to
language model steering, we observe feature-specific basins along semantic steering directions, and find that steering moves activations between these basins. To demonstrate the active role of this geometry in neural computation, we show that adaptively modulating steering strength to transport activations across basins improves inter-
language steering, significantly increasing the probability of sampling
tokens from the target
language compared to fixed-strength steering. Our findings establish analysis of activation space geometry as a promising approach to interpreting and controlling
language models.
Read the full abstract ▾
All authors Matthew Finlayson, Francisco Pernice, Eric Todd, Amir Zur, Daniel Wurgaft, Fenil R. Doshi, Vasudev Shyam, Matt Feiszli, Satchel Grant, Lucius Bushnaq, Tal Haklay, Usha Bhalla, Matthew Kowal, Thomas Fel, Jack Merullo, Atticus Geiger, Xiang Ren, Owen Lewis, Ekdeep Singh Lubana
Artificial Intelligence
SHarP: Saliency-based Pruning of Agent Harnesses
Xinyi Gao, Qiucheng Wu, Kaizhi Qian et al. (+3 more)
Agent harnesses are systems that coordinate model calls, tool use, and task execution to help large
language models complete complex tasks. To meet task requirements and address failures, these systems are often iteratively refined by amending and patching their instructions, tools, and workflows, continuously increasing harness complexity. It is therefore unclear whether some resulting harness modules are redundant, introducing substantial
token overhead with little, if any, performance gain. Inspired by neural network
pruning, in this paper, we study harness
pruning as a means of striking a better balance between task performance and
token cost. We propose SHarP (Saliency-based Harness
Pruning), a simple yet effective
pruning strategy based on the saliency of each harness module with respect to performance and efficiency. Specifically, we first identify tools, instructions, and supporting mechanisms as components that can be individually disabled. We then estimate the saliency of each module by ablating it and assessing its task performance and
token cost relative to the full set of single-module ablations. Modules with the smallest contribution to performance or largest computational overhead are subsequently pruned. Our evaluation across various harnesses on held-out validation sets reveals a surprising finding: most harnesses that we studied are highly redundant and can maintain comparable performance and efficiency even after a substantial portion of their modules are pruned. Our
pruning approach and empirical findings provide new perspectives on
agent harness design and optimization.
Read the full abstract ▾
All authors Xinyi Gao, Qiucheng Wu, Kaizhi Qian, Handong Zhao, Shiyu Chang, Yang Zhang
Human-Computer Interaction
DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls
Ajit Mallavarapu and Ziwei Gu
Large
language model writing interfaces often make users steer outputs by repeatedly articulating desired changes in natural
language. Yet writers may recognize useful stylistic directions only after seeing alternatives, making revision recall-heavy. We present DimSteer, an authoring interface that samples
prompt-local completions, discovers high-variance activation-space axes of variation, labels them, and exposes them as sliders with pole previews, diff comparison, and reset controls. Users can manipulate discovered dimensions, reducing the need to reformulate
prompts for each stylistic adjustment. In a within-subjects study with 16 participants against a matched
prompt-only baseline, DimSteer reduced mental demand, effort, and frustration while preserving comparable perceived success. Participants valued the surfaced dimensions, yet 15 of 16 disagreed that they would have thought to request the same changes in a
prompt. Results suggest
prompt-local controls can shift LLM authoring from recall-based prompting toward recognition-based exploration and direct manipulation, while preserving prompting for open-ended edits.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering
Ziseok Lee, Jaehyeon Kim, Seungwon Kim et al. (+6 more)
Inference-time steering combines pretrained
diffusion experts or rewards without retraining by changing the dynamics that transport noise to data. Feynman-Kac correction compensates for proposal mismatch through importance-weighted sequential Monte Carlo (SMC), whose finite-particle behavior depends on the proposal. Variance-controlling guidance (VCG) improves that proposal by fitting a linear drift correction to minimize empirical log-weight-rate variance. Although its population optimum cannot worsen residual variance, finite-particle VCG can nearly eliminate its fitting residual while increasing residual risk on new states by orders of magnitude. The resulting update can degrade unweighted generation or accelerate particle collapse. We show that the centered Feynman-Kac rate is the normalized transport residual and that expected out-of-fit benefit is exactly population headroom minus coefficient-estimation penalty. Under regularity assumptions, a Wasserstein analysis bounds the unweighted proposal's terminal error using this residual. These results motivate Risk-Calibrated Proposal Transport (RCPT), which uses deletion leave-one-out residuals to calibrate the retained fraction of the VCG update, adding no model calls and only small linear-
algebra overhead. Experiments on 2D checker distributions, scaffold decoration, molecular property optimization, and class-conditional CIFAR-10 generation demonstrate recovery from harmful fitted updates. Across molecular and image domains, RCPT mitigates harmful fitted updates and improves a broad range of terminal metrics relative to uncalibrated VCG.
Read the full abstract ▾
All authors Ziseok Lee, Jaehyeon Kim, Seungwon Kim, Seunghyun Moon, Haneul Choi, Wooyeol Lee, Donghyun Koh, Minhyeong Lee, Kyungsu Kim
Cryptography and Security
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Jeongyeon Hwang, Anshul Nasery, Sewoong Oh et al. (+1 more)
LLM fingerprinting via watermark
distillation embeds a statistical watermark signal into model weights, enabling model owners to identify their models behind black-box APIs. Revisiting a recent protocol, we find that its utility evaluation understates text quality degradation in open-ended generation, favoring overly strong watermark teachers. Weakening the watermark improves text quality but sacrifices detectability. To move beyond this trade-off, we rethink whether text watermarks designed for verifying generated text are suitable
distillation teachers for model fingerprinting. Such watermarks are typically designed to remain detectable from an individual output, limiting how sparse the watermark signal can be. In contrast, fingerprint verification can aggregate signal across queries, making sparser watermark signals viable. This raises a key question: where should the sparse signal be placed? We analyze signal placement through
token surprisal and show that, even at comparable watermark strength, different placements can target
tokens with different plausibility under the base model. This motivates near-tie restriction, which uses top-1-relative logit gaps to restrict the watermark bias to
tokens close to the base model's top prediction. Across multiple models, near-tie improves detection–quality frontiers under deployment changes, preserves higher text quality across query budgets, and further improves existing watermarking schemes when combined with them.
Read the full abstract ▾
All authors Jeongyeon Hwang, Anshul Nasery, Sewoong Oh, Jungseul Ok
Artificial Intelligence
Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents
Nijesh Upreti, Chris Sypherd and Vaishak Belle
Agentic large
language model (LLM) systems are commonly implemented as an LLM in a loop with Planning,
Memory, Tools, and Control Flow. This application-focused view connects agentic LLM research with deployable systems and leaves open how such systems should be evaluated beyond end-to-end task success. Building on this view, we define agentic cognitive depth as a trajectory-level profile across five operational criteria. The profile contains context sensitivity ($C$), temporal continuity ($T$),
multimodal coordination ($M$), adaptive interaction ($A$), and metacognitive monitoring ($Mc$). The first four criteria measure how well Control Flow,
Memory, Tools, and Planning are used across a trajectory. The fifth measures whether the system monitors and regulates the full run. For each criterion, we give operational proxies and a perturbation procedure, then connect the profile to the
agent's world model. We provide the structure needed to extend
benchmarks such as
GAIA, SWE-bench, WebArena, and TRIP-Bench with per-criterion diagnostics. Symbolic verifiers, structured
memory, planner coupling, and tool constraints provide practical ways to build and test these capacities.
Read the full abstract ▾
Systems and Control
The Price of a Cycle: A Phasor -vs- Sampled-Value Comparison for Streaming Fault Classification on the IEEE 9-Bus System
Emad Abukhousa, Khaled Muhmmed Nor Muhmmed, Abdulaziz Qwbaiban et al. (+2 more)
Transmission-line fault classification is a time-critical protection function, and recent machine-learning methods classify fault type directly from voltage and current measurements. The input to such a classifier can be supplied as sampled-value windows of raw measurements, which preserve sub-cycle structure, or as phasor-domain sequence components, which are physically interpretable but require a causal one-cycle observation window before a phasor estimate is available. This paper measures the cost of that observation window, the price of a cycle, through a controlled comparison of the two representations for streaming fault-family classification on the standard synchronous WSCC/IEEE 9-bus system. The comparison holds the simulated system, the measured channels, the eleven-class event-family taxonomy, the training procedure, and the streaming decision layer constant, and uses six configurations: 40- and 80-sample sampled-value inputs and one-cycle phasor inputs, each evaluated with a multilayer perceptron (MLP) and a one-dimensional convolutional neural network (CNN). All six configurations classify every event successfully, yet the sampled-value representation reaches the correct class earlier in every model pair. The 40-sample sampled-value MLP attains the strongest result, with 99.34% fault-window accuracy, 99.79% normal accuracy, a 0.21% false-fault rate, a 0.65% false-normal rate, and a 2.81 ms mean first-correct delay, and it Pareto-dominates the other five configurations. A matched-window comparison at eighty samples confirms that the timing advantage follows from the representation rather than from the window length. On this clean synchronous
benchmark, the one-cycle phasor representation does not return an accuracy or stability benefit sufficient to offset its delay.
Read the full abstract ▾
All authors Emad Abukhousa, Khaled Muhmmed Nor Muhmmed, Abdulaziz Qwbaiban, Saman Zonouz, A. P. Sakis Meliopoulos
Cryptography and Security
Fully Homomorphic Encryption for Statistical Modeling
Balasubramanian Narasimhan
Fully homomorphic encryption allows arithmetic to be carried out on encrypted values, so that a party performing a computation need not see the data it operates on. This is useful wherever collaborating parties or sites cannot share data records or computed summaries yet need to do a joint analysis. We demonstrate the protocols needed to perform such analyses reproducibly via two packages in R, a platform widely used for applied statistics. The first, openfhe.R, is an interface to the OpenFHE C++ library, which exposes exact integer arithmetic (BFV, BGV), approximate real-valued arithmetic (CKKS), Boolean
circuits, and multiparty key generation. The second is homomorpheR, which builds a small set of master/worker primitives for multi-party protocols on top of the first. Together, the two let an ordinary R statistical routine compose with an encrypted-arithmetic layer at the function-value boundary, provided the quantity crossing that boundary decomposes as a sum over sites. Two validation studies are presented: distributed stratified Cox regression, where stats4::mle() converges through an encrypted channel, and
federated Cox-lasso via convex optimization using consensus ADMM, where the cross-site update is the only encrypted step. We also discuss
federated similarity
retrieval and two-party prediction. Throughout, the parties are assumed honest-but-curious, and threshold key generation removes the assumption that any single party holds a usable secret key.
Read the full abstract ▾
Machine Learning
Principled Top-$k$ Selection for Language Models with Hybrid Gradients
Xuchen Gong, Junfei Sun and Tian Li
Selecting the best $k$ items out of $m$ candidates is a critical component of modern large
language model systems, such as document selection in
Retrieval-Augmented Generation (RAG) and expert routing in Mixture-of-Experts (MoEs). However, training these selection modules remains challenging due to weak gradient signals and suboptimal exploration-exploitation tradeoffs. Furthermore, prior works often rely on heuristics, lacking principled objectives and approaches that explicitly model and solve the top-$k$ selection problem. In this work, we propose a principled objective for training selection modules, whose gradient naturally provides richer training signals in a hybrid form—containing a supervised-gradient component and a policy-gradient component. We show that the selection problem becomes harder as $m$ increases, and our
algorithm converges at rate $O(1/\sqrt{T})$, with the optimal upper bound achieved by balancing between bias and variance. Practically, we apply our method to a set of tasks involving top-$k$ selection, including synthetic regression problems, RAG, and MoE systems, showing that our method outperforms the baselines in next-
token prediction perplexity and QA accuracy.
Read the full abstract ▾