Numerical Analysis
Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations
Yuehao Song, Zhong Chen, Lihui Cen et al. (+2 more)
While Physics-Informed Neural Networks (PINNs) have emerged as a transformative paradigm for solving complex differential equations, their reliance on backpropagation-based gradient descent and automatic differentiation (AD) imposes significant computational bottlenecks and severe non-convex optimization challenges. To overcome these fundamental limitations, we propose the Physics-Informed
Stochastic Configuration Machine (PI-SCM), a novel backpropagation-free framework for both forward and inverse problems in differential equations. The core mathematical contribution lies in the analytical evaluation of local Jacobians for nonlinear differential operators, which facilitates a linearized representation of the physical loss and projects it into a unified, linearized algebraic subspace. This reformulation allows for the explicit determination of optimal network weights via a sequence of generalized linear least squares solvers, effectively bypassing the iterative traps of traditional nonlinear optimizers. We develop a progressive algorithmic suite comprising localized construction (PI-SC-I), sliding-window updating (PI-SC-II), and global updating (PI-SC-III), and rigorously establish their universal approximation properties. Extensive experiments demonstrate that PI-SCM achieves high-fidelity predictive accuracy and robust parameter identification while accelerating the training process by orders of magnitude compared to standard PINNs. Our work provides a highly efficient and scalable foundation for next-generation, real-time Scientific Machine Learning applications.
Read the full abstract ▾
All authors Yuehao Song, Zhong Chen, Lihui Cen, Liang Wu, Kai Zhang
Systems and Control
Camera Calibration Using Inaccurate and Asynchronous Discrete GPS Trajectory from Drones
R. Yang, Y. Bar-Shalom and H.A.J. Huang
This paper considers a stationary camera calibration problem, which estimates the camera orientation angles yaw, pitch and roll, using a drone trajectory recorded by a GPS. There are three challenges in using a GPS trajectory as ground truth for camera calibration. One, the altitude of GPS data is inaccurate with an unknown bias. Two, the GPS receiver and camera are not time synchronized, and there is an unknown time offset between the two systems. Three, the GPS trajectory is time-discrete and accurate interpolation is needed. This is actually an estimation problem since velocity is also needed. To address the first two challenges, we formulate the problem as a parameter estimation problem to estimate a vector consisting of the GPS altitude bias and time offset in addition to the camera yaw, pitch and roll biases. We then develop a special maximum likelihood
estimator using the Iterated Least Squares
algorithm which can work with a non-synchronized time-discrete GPS trajectory for the third challenge. Since the camera measurement errors are usually small, this requires a high calibration accuracy so that the residual bias error following the calibration should not be significant compared to the measurement error standard deviation. The calibration accuracy depends highly on the drone trajectory. This paper also recommends an appropriate drone trajectory which can yield a good calibration accuracy, namely, 14% of the measurement error standard deviation. Simulation tests are conducted to demonstrate the
algorithm performance. The estimation results meet the Cramer-Rao Lower Bound (CRLB) since the Normalized Estimation Error Squared w.r.t.\ the CRLB is statistically acceptable.
Read the full abstract ▾
Artificial Intelligence
DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
Zechun Niu, Yukun Zhao, Jiaxin Zhang et al. (+12 more)
Autonomous
agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing
benchmarks typically separate tasks by application or capability and evaluate
agents in environments that are cleaner and more stable than those encountered in practice. We introduce DuMateBench, a real-session
benchmark reconstructed from anonymized and
privacy-screened user sessions collected from a large-scale production
agent platform. Each task preserves the relevant pre-solution interaction history, persistent configurations, and workspace state, and is then validated through human verification. The resulting
benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories, with most tasks requiring multiple capability coordination. We execute these tasks in isolated Docker containers injected with three forms of real-world environmental complexity: Insufficient, Unstable, and Noisy, and assess performance using a hybrid deterministic and LLM-as-Judge evaluation protocol. Experiments across five representative autonomous-
agent frameworks paired with four state-of-the-art LLMs reveal substantial gaps in strict task completion. Complementary robustness, efficiency, and diagnostic analyses further show that performance under environmental perturbations is jointly shaped by the capabilities of the LLM and the surrounding
agent framework. The code and data are publicly available at https://dumatebench.com/.
Read the full abstract ▾
All authors Zechun Niu, Yukun Zhao, Jiaxin Zhang, Xu Shen, Jinhua Si, Han Tian, Can Xu, Yunfan Song, Jiaxin Mao, Yansong Gao, Yuchen Li, Jianmin Wu, Lingyong Yan, Shuaiqiang Wang, Dawei Yin
Robotics
Memory Anchors for Continual Robot Learning
Maximilian Du, Zhanyi Sun, Chen Xu et al. (+3 more)
Robot policies deployed in the wild should have the capability to continually learn new tasks without forgetting existing behaviors. A common approach to combat such catastrophic forgetting is to train on new task data with a replay buffer of previously learned task data. Although this buffer is commonly sampled randomly from all prior experiences, we show that a small set of these experiences contributes greatly in anchoring past performance. We call these experiences
Memory Anchors. We identify
Memory Anchors in regions where representations of new-task observations collapse onto those of old-task observations even though the tasks require conflicting actions, like when a familiar object must be manipulated in a new way. Rehearsing old data in this region plays a key role in preventing destructive overwriting of past task knowledge, serving as this critical
Memory Anchor role. Excluding only 10%
Memory Anchors before sampling the buffer leads to more than a 4.5x increase in catastrophic forgetting on the LIBERO
benchmark suites. Conversely, enriching the replay buffer with
Memory Anchors can decrease high-conflict task forgetting by 63% and enables successful continual learning of two task sequences on a real
robot.
Videos and additional visualizations can be found at https://
robot-adaptation.github.io/MemoryAnchors
Read the full abstract ▾
All authors Maximilian Du, Zhanyi Sun, Chen Xu, Paarth Shah, Masha Itkina, Shuran Song
Machine Learning
Chart2SVG: Editable SVG Generation from Raster Chart Images
Jinning Cui, Lu Chen, Haoyan Shi et al. (+5 more)
We present Chart2SVG, a
multimodal large
language model that converts static raster charts into structurally organized, semantically enriched SVGs that support programmatic editing. By incorporating chart-specific semantic
tokens into a
vision-
language model, Chart2SVG captures both
geometric primitives and their functional roles. To support robust structural recovery, we introduce Beagle+, a
dataset of 33K canonicalized and structurally distilled chart samples. Our approach combines specialized training objectives with a rendering-aware post-training phase, producing SVGs that are both visually accurate and structurally consistent. To facilitate higher-level manipulations, we construct a Chart Structure Graph (CSG) that exposes visual dependencies, enabling tasks such as interactive exploration, chart repurposing, and layout reuse. Experiments show that Chart2SVG substantially outperforms baselines in reconstruction fidelity and downstream editing utility, advancing the development of intelligent and interactive visualization tools.
Read the full abstract ▾
All authors Jinning Cui, Lu Chen, Haoyan Shi, Yue He, Chenglong Wang, Mengyu Zhou, Weidong Huang, Yunhai Wang
Game Theory
Trusting AI in Competitive Markets
Jussi Keppo, Yuze Li, Gerry Tsoukalas et al. (+1 more)
People's trust in AI advice diverges as they use it, deepening for some and eroding for others. We study this divergence in oligopoly pricing, where advice cannot prove itself: rivals' responses decide whether it pays off. In a laboratory experiment, 273 sellers compete across 91 three-seller
markets over 30 rounds; we vary the presence of AI pricing recommendations and the gender composition of the
market (female-only, male-only, or mixed). We find that the gender composition of the
market shapes how sellers learn from the advice, and where prices settle as a result. In female-only
markets, recommendations raise prices by 29% and profits by 39%; in male-only and mixed-gender
markets, they have no significant effect. A Non-Homogeneous Hidden Markov Model reveals a composition-specific dynamic association: profitable rounds predict rising adherence to the AI in female-only
markets and declining adherence otherwise, a pattern consistent with learned trust and self-serving attribution. The pattern reverses what recent evidence on gender and AI would predict. We discuss implications for platform governance and regulatory oversight, which should focus not only on the
algorithm but on the human side that shapes its effects.
Read the full abstract ▾
All authors Jussi Keppo, Yuze Li, Gerry Tsoukalas, Nuo Yuan
Machine Learning
Predicting Dose-Response Success from Primary Screening Data
Sean Lim
High-throughput drug screening uses inexpensive primary screens to select compounds for more costly follow-up dose-response experiments, which estimate compound potency (pXC50) by determining the concentration required to produce a specified biological effect. However, many promoted compounds fail to yield a reportable potency, even when activity is subsequently confirmed. We investigated whether inexpensive three-point primary-screening data could predict whether a more costly 11-point dose-response experiment would yield a reportable pXC50. Using a
dataset of 32,971 compound-assay pairs with three-point primary-screening and 11-point dose-response measurements, we trained random-forest models to predict successful potency quantification. Our model achieved an AUROC of 0.939 +/- 0.002 and generalized to previously unseen chemical scaffolds and assay-mechanism families. We found that primary-screen response features were more predictive of dose-response quantifiability than molecular structure-based features. Successful potency quantification was also strongly associated with primary-screen response amplitude. Across eight chronological test releases, the model retrospectively retained 90% of reportable potencies while selecting only 55.7% of historically promoted compound-assay pairs for follow-up profiling. These findings suggest that predicting potency quantifiability from primary-screening data could improve the efficiency of compound prioritization and reduce unnecessary dose-response experiments.
Read the full abstract ▾
Databases
IBLTs Measure Before They Decode: Self-Sizing Set Reconciliation for Database Consistency Verification
Min Wu, Ji Qi, Zhengsheng Ye et al. (+3 more)
Cross-system data replication pipelines cannot confirm end-to-end consistency from the local guarantees of each hop, so the two endpoints must be compared directly on a periodic basis. Once the rows of a fixed snapshot are normalized into fingerprints, the task reduces to finding the symmetric difference of the two sets. An Invertible Bloom Lookup Table (IBLT) reconciles the sets with communication that grows only with the difference cardinality $d$, independent of table size, but its capacity must be fixed while $d$ is still unknown. Across 41,603 production reconciliations over 90 days, nonzero $d$ spans about seven orders of magnitude, and no reliable empirical constant exists. We show that the count array of an IBLT has already measured $d$ before decoding. The measurement is in-band: it is carried by the recovery sketch itself and adds no bytes dedicated to estimation. A mapping-aware
theorem extends the construction to Irregular, Rateless, and MET IBLTs. The protocol reads the estimate only after a decoding failure; we prove that the failure-conditioned lower
quantile bounds the risk of underestimation, which gives the second-round capacity a configurable success-probability guarantee. The resulting self-sizing protocol attempts recovery with a small first-round sketch and stops on success; on failure it reads $d$, sizes the second round, and completes reconciliation in at most two rounds. Against a controlled oracle, communication is 1.29-1.47 times that of a scheme given $d$ in advance. Production workload characterization, relational-database replay, and a cross-city KV deployment confirm the end-to-end mechanism. In production on an Oracle-MySQL link, all completed runs succeeded within two rounds, over 90% on the 1-RTT fast path with a single 16 KB sketch.
Read the full abstract ▾
All authors Min Wu, Ji Qi, Zhengsheng Ye, Chengdui Luo, Shudong Lu, Zhengyang Wei
Artificial Intelligence
Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
Kaichao Jiang, Changtao Miao, Baiqi Wu et al. (+8 more)
Recent audio-
video generators increasingly support joint conditioning on text, images, audio, and
video. These capabilities also enable attacks that exploit cross-modal interactions or obscure harmful intent to bypass safeguards and induce harmful audio-
video outputs. However, existing generation-safety
benchmarks have not kept pace with these advances, providing limited coverage of
multimodal input combinations and obscured attack intents. To address these gaps, we introduce Multi2AV-Safety, the first full-coverage red-team
benchmark for
multimodal-to-audio-
video generation, comprising 11,024 attack instances across all 11 non-singleton T/I/A/V conditioning configurations, 4 attack-intent categories, and 5 harm categories. Our evaluation of recent state-of-the-art models, including four
multimodal-conditioned audio-
video generators and eight safety guards, reveals substantial vulnerabilities in both generation and safeguarding, with
multimodal compositional risk and obscured attack-intent risk emerging as two complementary challenges. Guided by these findings, we introduce PerceptGuard, an omni-modal guard integrating compositional-risk and attack-intent supervision through structured risk perception learning. By jointly training rationale generation and safety classification, it learns shared risk representations that enable a safety head to make efficient predictions at inference without rationale decoding, while retaining the ability to generate explanations on demand. Across 34 safety
benchmarks, PerceptGuard combines SOTA
multimodal safety detection with highly competitive unimodal performance, strengthening input-side safeguards against
multimodal attacks on omni models. In particular, it improves safeguarding against the above risks, achieving an overall recall of 86.06% on Multi2AV-Safety and outperforming GuardReasoner-Omni by 14.56%.
Read the full abstract ▾
All authors Kaichao Jiang, Changtao Miao, Baiqi Wu, Zhiyuan Lu, Kang Yang, Peiwei Zhao, Junchi Chen, Yunfeng Diao, He Liu, Qi Chu, Tao Gong
Systems and Control
Barrier Function Conformal Safety Clearance Certification with CVaR for Driving Trajectory Selection
Pei Yu Chang and Qadeer Ahmed
Autonomous driving motion planners generate and select candidate trajectories while accounting for interactions with surrounding
agents. However, these evaluations do not certify the actual safety clearance of the selected trajectory. The framework evaluates the trajectory selected by ant planners and calibrates the gap between its plan time margin and realized safety clearance. A differentiable separating axis barrier margin deterministically lower bounds exact signed oriented-bounding-box (OBB) safety clearance, connecting the statistical certificate to safety margin. At plan time, the margin is evaluated using either a nominal prediction and sampled lower tail Conditional Value-at-Risk (CVaR), while post-selection conformal calibration over exchangeable drive sessions absorbs prediction and sampling errors. Conformal calibration provides statistical validity independently of predictor correctness. The method is evaluated on a frozen 300 session nuPlan study using native Predictive Driver Model (PDM) Closed loop proposals. At 10% target miscoverage, sampled lower CVaR reduces the conformal correction from 1.43m to 0.03m and increases the rate of nonnegative safety clearance certificates from 68.7% to 87.3%. Across all evaluated statistics, exact-clearance coverage remains above the 90% target at 93.3–96.7%.
Read the full abstract ▾
Computer Vision
FAN-LoRA: A Fourier-Adaptive Nonlinear Low-Rank Adaptor for Medical Foundation Model Domain Adaptation
Ziquan Liu, Zhewei Zhu and Xuyang Shi
The advent of
vision foundation models, notably the Segment Anything Model (SAM), has catalyzed significant advancements in natural image
segmentation. However, their direct transfer to medical imaging remains severely bottlenecked by profound domain gaps, such as cross-modality and cross-center shifts. Existing Parameter-Efficient Fine-Tuning (PEFT) methods facilitate the adaptation of SAM to medical domains; nevertheless, they frequently suffer from performance degradation under severe distribution shifts. This vulnerability primarily stems from the implicit
entanglement of heterogeneous frequency components within a shared low-rank subspace, which directly exacerbates sub-optimal structural
alignment and localized boundary blurring. To overcome this representational bottleneck, we propose the
Fourier-Adaptive Nonlinear Low-Rank Adaptor (FAN-LoRA), a novel frequency-decoupled fine-tuning architecture. FAN-LoRA explicitly separates the optimization space by employing a B-spline-driven low-pass branch for global structural
alignment, synergistically coupled with a discrete
Fourier high-pass branch for local textural compensation. Extensive experiments across three challenging cross-modality and cross-center
benchmarks demonstrate that FAN-LoRA consistently outperforms state-of-the-art PEFT baselines. Compared to the strongest competitors, our method achieves consistent improvements in average Dice scores and notable reductions in boundary errors, while maintaining a compact module size without compromising computational efficiency.
Read the full abstract ▾
Artificial Intelligence
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Yang Xiao, Yusong Sun, Haoyi Wu et al. (+7 more)
Long-horizon
agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing
agent architectures do not fully support this goal. Single-
agent self-correction combines task execution and trajectory assessment within one context, while subagent delegation separates execution but typically cannot redirect an active subagent. We present PILOT, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-
evolution distils procedures and failure modes revealed during execution into reusable skills and
memory. Across two frozen backbones and three
benchmarks, PILOT ranks first in five of six configurations. On Terminal-Bench 2.0, PILOT outperforms counterpart harnesses by up to 9.8 percentage points. In the self-improvement setting, PILOT gains 14.6 points with GLM-5.1 and 12.4 points with Kimi-K2.6. Mean output
tokens fall by 42.9% and 47.4%, while successful evaluations per million output
tokens rise by 110.3% and 134.0%, respectively.
Read the full abstract ▾
All authors Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Wen Da, Zhaokai Luo, Mu Chuan, Yao Hu, Wenjie Li, Chengyue Jiang
Computation and Language
Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue
Ming Cheng, Yusheng Dai, Qiuhong Ke et al. (+2 more)
In this paper, we explore multi-expert Conformal Risk Control (CRC)
algorithms for pairwise LLM-as-a-Judge evaluation in open-ended dialogue. Our core insight is that multi-expert aggregation offers a complementary remedy to CRC: whereas CRC controls risk at the decision threshold through abstention, aggregation sanitizes the scoring function at its source. Guided by this, we first design two multi-expert CRC methods: Score Averaging and Decision Voting, which aggregate at the score and decision levels, respectively. While both strategies outperform single-expert methods on homogeneous expert panels, on heterogeneous LLM judges they remain risk-valid but recover only limited coverage, because a uniform threshold cannot match the experts' distinct scoring scales. To resolve this issue, we further propose Marginal-Calibrated Conformal Consensus (MC3): it captures distinct per-expert scales via initial threshold ratios, while jointly tuning a unified decision function $C_t(x)$ applied identically in both calibration and test, thereby preserving exchangeability. To evaluate our framework, we construct Panel, a 1,800-pair human pairwise-preference
benchmark for open-ended dialogue. It is built on responses generated by four open-weight LLMs over dialogue contexts from three domains (ESConv, MSC, DREAM), with full logit access. In experiments, we find that both Score Averaging and Decision Voting substantially improve accuracy and acceptance rate on homogeneous panels. Notably, MC3 extends these gains to heterogeneous panels by accommodating distinct per-expert scoring scales across all three
datasets.
Read the full abstract ▾
All authors Ming Cheng, Yusheng Dai, Qiuhong Ke, Zhaolin Chen, Lizhen Qu
Machine Learning
High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube
Josef Dick, Michael Feischl and Fabian Zehetgruber
We establish high-probability bounds for mixed input derivatives of wide random neural networks whose activation derivatives satisfy a factorial growth bound. Our main result specializes these estimates to $\tanh$ networks with Xavier initialization. A direct deterministic analysis based on Euclidean operator norms of the weight
matrices yields derivative bounds that generally grow exponentially with the depth. We show that this growth can be substantially improved for sufficiently wide Gaussian networks by isolating the term that is linear in the highest-order derivative and controlling the corresponding tangent directions by measurable finite nets. For scalar-output $\tanh$ networks with Gaussian weights and Xavier initialization, we prove that there exist constants $C,C_0,C_1>0$ such that, whenever the common hidden width satisfies $n \geq C\left(L^3n_0^2(1+\log n_0)+L^2\left(1+\log(L/\eta)\right)\right)$, then, with probability at least $1-\eta$, the estimate $\left|D^u\mathcal{R}_{\Phi^{(L)}}(x)\right| \leq C_0 |u|! (C_1L)^{|u|-1}\prod_{j\in u}\beta_j(\eta,n_0)$ holds simultaneously for every non-empty $u\subseteq[n_0]$ and every $x\in[0,1]^{n_0}$. Thus, the first-order derivative bound is independent of the depth, while a square-free mixed derivative of order $|u|$ grows at most polynomially as $L^{|u|-1}$, apart from the coordinate factors. As consequences, we obtain high-probability bounds for the Euclidean Lipschitz constant and for weighted Sobolev norms of the network realization. The latter connect the derivative estimates to quasi-Monte Carlo integration and indicate how such regularity can enter the analysis of QMC-based training.
Read the full abstract ▾
Systems and Control
Fusion Based Dynamic Platform Magnetic Compensation Beyond the Tolles Lawson Approach
Rong Yang and Yaakov Bar-Shalom
Aeromagnetic compensation for airborne platforms is essential for real-time tracking of the dynamic external
magnetic field free from platform interference, enabling robust
magnetic navigation (MagNav),
magnetic anomaly detection (MAD), and other geophysics applications. While the classical Tolles-Lawson (TL) framework focuses extensively on estimating compensation model parameters, it pays less
attention to the real-time estimation of the dynamic external
magnetic field. To bridge this gap, this paper proposes a two-stage calibration and compensation framework. First, an augmented linearized model is developed for sensor-based calibration parameter estimation, avoiding the information loss inherent in classical band-pass filtering (BPF). Second, utilizing these pre-estimated parameters, a map-less Kalman Filter Fusion (KFF)
algorithm is developed to dynamically estimate the external field and compensate the platform interference directly from multi-sensor measurements corrupted by platform interference. The second step enables real-time joint dynamic estimation and multi-sensor compensation without requiring reference position data (which runs counter to the MagNav purpose) or prior anomaly maps. Validated on the public DAF-MIT MagNav
dataset, the framework overcomes the non-causal limitations of existing approaches, reducing average compensation error from 359.2~nT to 12.3~nT while maintaining exceptional robustness against heavily corrupted sensor channels.
Read the full abstract ▾
Distributed Computing
VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference
Yan Shi, Xiaochao Wang, Jingchun Gao et al. (+7 more)
Chunked prefill pipeline parallelism (CPP) is a key technique for LLM inference. However, equal-size chunks exhibit imbalanced latency, as later chunks attend longer prefix KV caches and incur higher
attention costs, leading to pipeline bubbles. Existing approaches mitigate this imbalance through dynamic chunk resizing (Dynamic CPP, DCPP), but our measurements show that this trades scheduling overhead for load balancing, which becomes unfavorable on long sequences. In this study, we propose Virtual Pipeline Parallelism (VPP), which keeps chunk sizes fixed and optimizes the pipeline layout through virtual stages. A V-shaped virtual-stage traversal overlaps each chunk's expensive middle stages with the lighter head and tail stages of its neighbors, while asynchronous communication and pipelined packing further reduce communication stalls and cross-request drain bubbles. We implement VPP in vLLM-Ascend and evaluate it on three MoE-based LLMs with sequences up to 1M
tokens on 16 Ascend 910C NPUs. VPP improves throughput by up to 13.1% over DCPP on long sequences and 6.7% on mixed workloads, while preserving performance on short sequences. On a 512K-
token DeepSeek-V3.1 prefill workload, VPP reduces the pipeline bubble ratio from 6.4% to 0.1%, achieving a 98.0% reduction compared with DCPP.
Read the full abstract ▾
All authors Yan Shi, Xiaochao Wang, Jingchun Gao, Jintao Luo, Xinyi Zhou, Feng Liu, Kui Luo, Xushi Li, Xinjie Guo, Liangjun Feng
Computational Engineering
Report of the 2026 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science
Lois Curfman McInnes, Dorian Arnold, Prasanna Balaprakash et al. (+45 more)
Scientific computing is undergoing rapid transformation as advances in artificial intelligence, heterogeneous computing, automation, and data-intensive research reshape not only computational tools but also the institutions, workforce models, and collaborative practices that support scientific discovery. This report synthesizes insights from the 2026 Workshop on Next-Generation Ecosystems for Scientific Computing, the second in a three-year series focused on strengthening scientific computing ecosystems through socio-technical co-design. Workshop discussions identified four interdependent strategic themes: software ecosystems for AI-enabled scientific discovery; trust, validation, and traceability; human-AI teaming and paradigm shifts; and workforce, pedagogy, and governance. The report translates these themes into eight priorities for community action spanning shared research infrastructure, trust and traceability, user experience, human-AI teaming, workforce development, cross-sector coordination, stewardship and sustainability, and evaluation of scientific value. Together, these priorities outline directions for building scientific computing ecosystems that remain trustworthy, sustainable, innovative, and resilient as AI assumes a growing role in scientific work.
Read the full abstract ▾
All authors Lois Curfman McInnes, Dorian Arnold, Prasanna Balaprakash, Mike Bernhardt, Franck Cappello, Beth Cerny, Deborah DiazGranados, Anshu Dubey, Nichole Etienne, Roscoe Giles, Diego Gomez-Zara, Denice Ward Hood, Mary Ann Leung, Vanessa Lopez-Marrero, Olivia B. Newton, Irene Qualters, Keita Teranishi, Stefan M. Wild, Gabrielle Allen, Richard Arthur, Alexandra Ballow, Tony Baylis, David E. Bernholdt, Daniel Bielich, Johanna Cohoon, Jeremy Crampton, Charles Ferenbaugh, Stephen M. Fiore, Thomas Herault, Tanzima Islam, Stephen Jacobsohn, Meifeng Lin, Charles Lively, Satoshi Matsuoka, Stasa Milojevic, Daniel Nichols, Chris Oehmen, Santiago Ospina Tabares, Michael E. Papka, Katherine Riley, Damian Rouson, Sudip K. Seal, Brittany Segundo, John Shalf, Andrew Siegel, Valerie Taylor, Jim Willenbring, Lou Woodley
Systems and Control
Energy as a Concealable State in Adversarial UAV Patrolling: Formulation, an Energy-Security Threshold, and the Limits of Self-Play
Sai Krishna Reddy Mareddy
We study energy-constrained
adversarial patrolling on a graph, in which a battery-limited
UAV defends a cluster of high-value targets against a strategic attacker who chooses when and where to strike. Unlike prior
adversarial patrolling, the patroller must periodically return to a base to recharge; unlike prior energy-aware patrolling, it faces a self-interested adversary. Our central observation is that the remaining energy is a hidden state: the attacker never observes the battery directly, but observes the patroller's trajectory and can infer when a recharge excursion, and thus a vulnerability window, is imminent. We formalize the interaction as a zero-sum partially observable
stochastic game and report a negative result on the solver side: neither independent deep Q-learning nor Neural Fictitious Self-Play reaches a stable
equilibrium at this scale; each improves transiently and then collapses, with the co-trained thwart rate falling from about 0.25 to about 0.09 over training. Using a structural analysis independent of the learning dynamics, we show that achievable security rises monotonically with the energy budget, from zero below a threshold to about 0.7 when the budget is ample, establishing the energy budget as the primary determinant of defensibility. We set out the program the model is built to answer: whether an inference-capable attacker concentrates its successful strikes in the recharge window, and whether the defender can learn deceptive recharge timing to keep that window closed.
Read the full abstract ▾
Computer Vision
HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence
Fei Ma, Zebang Cheng, Minghui Li et al. (+11 more)
Visual intelligence seeks to perceive, interpret, and synthesize the visual world and is central to modern computer
vision. Human-centered visual intelligence is especially demanding because it studies people as expressive, socially situated subjects whose meaning is rarely conveyed by appearance alone. It couples
vision with audio and
language across four representative tasks: human
emotion recognition, human
video generation, human voice cloning, and human
video matting. Yet existing resources remain task-specific, providing modalities and annotations for individual problems rather than a shared foundation coordinating understanding and generation. This limits
multimodal signal use and broader research. We address this gap with HUG-VIS, a unified
benchmark for Human-centered Understanding and Generation in Visual Intelligence. It contains 8,400 seated half-body
videos of 30 professional actors, each performing the same 280
emotion-action-
prompt assignments under a controlled Mandarin studio protocol, with synchronized
video, audio, text, and alpha mattes. We evaluate diverse open- and closed-source models across the four tasks under a unified zero-shot protocol using automatic metrics, criterion-specific mean opinion scores, and multiple cross-task analyses. Results show that (i) linguistic content dominates current
emotion recognition, while purely visual affect recognition is weakest; (ii) in
video generation and voice cloning, automatic metrics and human judgment agree overall but differ in their top rankings, requiring joint reporting; (iii) boundary fidelity under motion is the main remaining obstacle for human matting; and (iv) task difficulty varies across
emotions, models, and metrics, with notable cross-task correlations. The
dataset and results are available at https://github.com/GML-MMGroup/HUG-VIS.
Read the full abstract ▾
All authors Fei Ma, Zebang Cheng, Minghui Li, Hongbo Xu, Yuyong Tan, Yihua Shao, Hanling Wang, Zhou Liu, Yuqing Gao, Dong Wang, Long Ma, Laizhong Cui, Nicu Sebe, Qi Tian
Machine Learning
Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning
Julian Asilis, Shaddin Dughmi, Vatsal Sharan et al. (+3 more)
Two of the most fundamental questions in statistical learning theory are the following: which prediction problems are learnable, and how should they be learned? For the former, elegant answers often take the form of combinatorial dimensions. The latter question, however, has proved considerably more elusive: all known general-purpose multiclass learners rely on intricate orientations of exponentially large one-inclusion structures, and familiar algorithmic principles such as proper learning and regularization remain poorly understood. Motivated by prior work, we ask whether learning reduces to proper learning—possibly over a larger hypothesis class—and whether proper or improper multiclass learning can ultimately be captured by suitable regularizers. Our primary results answer both questions negatively, resolving three open problems from prior work. First, we exhibit a learnable multiclass problem that cannot be embedded in any properly learnable class, meaning learning cannot be reduced to proper learning by enlarging the hypothesis class. Second, we demonstrate that proper learning can require training error and characterize this phenomenon precisely: every properly learnable class admits a proper learner making $o(m)$ errors on samples of size $m$, but every prescribed sublinear scale $a_m=o(m)$ is necessary for some properly learnable problem. Third, regularization is not a general learner: we exhibit a properly learnable class that cannot be learned by any Structural Risk Minimization (SRM) learner, and a learnable class that cannot be learned by any local regularizer. We complement these impossibility results with a positive theory that gives two sufficient conditions for SRM learnability and characterizes SRM representability through integrability of revealed preferences.
Read the full abstract ▾
All authors Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang
Information Theory
Sharp Minimax Regret for Infinite-Memory Logistic Prediction
Vaneet Aggarwal
We study sequential prediction of binary marks whose log-odds are a linear function of all past inputs. The inputs are independent uniform signs. The coefficient of the input observed $j$ steps earlier is unknown, but its absolute value is at most a known number $r_j$, and $\sum_j r_j\le B$. A learner is judged by its expected cumulative log loss in excess of the loss of the true conditional probabilities. We show that for every such sequence $r$ and every horizon $T$, the minimax value of this regret lies between $c\,\Gamma_T(r)/\max\{1,B^2\}$ and $\frac12\Gamma_T(r)$, where $\Gamma_T(r)=\sum_{j\le T}\log(1+(T-j+1)r_j^2)$ and $c$ is an absolute constant. The term for lag $j$ combines the size bound $r_j$ with the number $T-j+1$ of rounds in which that lag influences a prediction, and no monotonicity or other regularity of $r$ is needed. The upper bound is attained by a
Bayesian mixture with independent Gaussian priors. For the lower bound, we apply the van Trees inequality at each prediction step and then bound the expected log-determinant of the random
matrix whose rows are the lagged input vectors. We also characterize when $\frac12$ is the exact leading constant: for envelopes with a common bound $B$, possibly changing with $T$, the regret is asymptotic to $\frac12\Gamma_T(r)$ if and only if $\sum_{j\le T}\min\{1,(T-j+1)r_j^2\}=o(\Gamma_T(r))$. This gives, for example, $\log^2(A^2T)/(8\alpha)$ for $r_j=Ae^{-\alpha j}$, whereas for $r_j=Aj^{-s}$ with $s>1$ the regret is of order $T^{1/(2s)}$ and its ratio to $\Gamma_T(r)$ stays below $\frac12$. Finally, for a known horizon, an online Newton predictor with features scaled by $r_j$ attains regret of order $\Gamma_T(r)$ with
polynomial computation per round.
Read the full abstract ▾
Computation and Language
Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update
Huanhuan Ma, Henry Peng Zou, Chengze Li et al. (+3 more)
Large
language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise from different causes. One possibility is that the model simply aligns with the user's feedback in order to satisfy them. Another is that the feedback genuinely contains useful evidence, prompting the model to update its answer in a rational way. We distinguish them as Unsupported-Yielding and Rational-Updating. Prior work focuses primarily on suppressing Unsupported-Yielding, while overlooking its effect on Rational-Updating. We address this gap with a two-turn evaluation framework that measures the two behaviors separately. Across representative training-time and inference-time interventions, we find that anti-sycophancy methods often encounter a trade-off in which reducing Unsupported-Yielding can sacrifice Rational-Updating, and vice versa, even when the two objectives are optimized jointly. Mechanistic analysis suggests that the two behaviors share an internal substrate: the MLP
neurons and
attention heads driving them overlap substantially, and their associated steering directions are positively aligned. We further conduct a preliminary orthogonalized steering exploration, which yields modest, backbone-dependent selectivity gains. Overall, our results suggest that anti-sycophancy should be treated not as a simple suppression problem, but as a selectivity problem, where effective interventions should preserve Rational-Updating while reducing Unsupported-Yielding.
Read the full abstract ▾
All authors Huanhuan Ma, Henry Peng Zou, Chengze Li, Enze Ma, Yunyue Su, Philip S. Yu
Machine Learning
A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families
Yu Zhe, Yixin Tan, Junhao Wei et al. (+1 more)
Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior work primarily attributes merging risks to unsafe constituent models, implicitly assuming that merging individually aligned models preserves safety. In contrast, we show that model merging reveals a previously overlooked jailbreak risk rooted in the pretrained foundation model, even when all constituent models are individually safety-aligned. Motivated by this observation, we study a new threat setting where an attacker constructs jailbreak
prompts that generalize across merged models sharing the same pretrained backbone, without access to the exact merging coefficients or constituent checkpoints. To exploit this phenomenon, we propose Basin-Aware Jailbreak (BAJ), which formulates jailbreak generation as a min–max optimization over the merging space to produce transferable
adversarial suffixes across merged model families. Experiments across diverse backbones and merging settings show that BAJ achieves consistently high transfer success rates and remains effective under existing defenses.
Read the full abstract ▾
All authors Yu Zhe, Yixin Tan, Junhao Wei, Wang Chen
Robotics
Closing the Loop on the Poppy Humanoid: Bipedal Locomotion with Linear-Quadratic Control and Learned Cost Functions
Xulin Chen, Borui He, Ruipeng Liu et al. (+3 more)
The Poppy
Humanoid is an open-source, low-cost
robot suitable for research and education in artificial intelligence. However, we are unaware of any published methodology that achieves reliable, unassisted bipedal locomotion on the standard Poppy hardware. This paper contributes a functional closed-loop walking controller for Poppy, based on the linear-quadratic regulator (LQR) framework for trajectory tracking. Starting with data collected from open-loop playback of a nominal walking trajectory, our proposed method learns a quadratic cost function for an LQR controller that substantially improves the reliability of the motion. The closed-loop controller is validated empirically, demonstrating statistically significant improvements in walking performance compared to open-loop trajectory playback.
Read the full abstract ▾
All authors Xulin Chen, Borui He, Ruipeng Liu, Naveed Tahir, Zhenyu Gan, Garrett E. Katz
Computer Vision
NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning
Alvin Jinsung Choi, Wanhee Kim, Taeyun Kim et al. (+3 more)
Neural surface reconstruction has emerged as a powerful paradigm for recovering high-quality 3D surfaces from multi-view images. However, recovering accurate geometry solely from RGB images remains challenging due to uncertainties arising from textureless regions, occlusions, and inherent scene ambiguities. Existing methods often overlook such uncertainties, leading to inaccurate estimates of the signed distance function (SDF). We introduce NeuDonatello, a novel framework that models and leverages SDF uncertainty to improve surface reconstruction. Central to our approach is to model spatially varying uncertainty using a Monte Carlo sampling strategy. Using this uncertainty, we develop an adaptive regularization that selectively strengthens
geometric constraints where RGB supervision is unreliable, avoiding incorrect surface reconstruction. We further introduce an uncertainty-aware scale parameter for the SDF-to-density conversion. Conditioned on uncertainty, this design enables more accurate modeling of spatially varying densities. Extensive experiments demonstrate that NeuDonatello achieves state-of-the-art reconstruction accuracy, with robust performance across diverse scenes using only posed RGB images.
Read the full abstract ▾
All authors Alvin Jinsung Choi, Wanhee Kim, Taeyun Kim, Dasol Hong, Wooju Lee, Hyun Myung
Social and Information Networks · Cross-listed from math.PR
Explicit Bounds on the Entropy of Piecewise Hölder Graphon Models
Connor Loehde-Woolard and François G. Meyer
We study the
entropy of random graphs generated by piecewise Hölder continuous graphons. We first present a result on the rate of convergence of the normalized
entropy as the size of the graph grows. The core ideas of the proof are described, with the detailed proof provided in the appendix. From this result, we then derive quantitative bounds on the
entropy for the
stochastic block model and random
geometric graph model. These bounds provide explicit formulae rather than asymptotic statements which have been found previously.
Read the full abstract ▾
Computer Vision
Systematic Literature Review of Machine Learning Models and Applications for Text Recognition
Nuzhat Khan, Ab Al-Hadi Ab Rahman, Shahriyar Masud Rizvi et al. (+5 more)
Optical Character Recognition (OCR) for text recognition using machine
vision has significantly improved, particularly when handling heterogeneous textual data. Traditional OCR models struggle with script variations, writing styles, and degraded documents. Advancements in technology are leading to new AI models with improved architecture for handling multiple
languages and complex data formats. Despite this progress, a comprehensive evaluation of OCR advancements remains limited. Based on the established preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines, this literature review presents an extensive assessment of OCR research to trace the
evolution of AI models over the past decade. It explores the transition in AI models, application domains, data types, linguistic coverage, and challenges. Through a detailed analysis of 97 selected studies published during January 2015 - January 2025, key OCR models are identified, and their performance, strengths, and limitations are analyzed. The findings highlight how OCR technologies have evolved to address structured and unstructured text, scene text recognition, and
multilingual processing. Unresolved challenges include limited resources for underrepresented
languages, high variability in handwritten text, visual similarity among characters, and constraints in real-time OCR applications. To address these issues, several promising approaches are proposed. Key suggestions include self-supervised learning,
multimodal AI, automated machine learning (AutoML), AI-assisted postprocessing, tiny machine learning (TinyML), and the creation of joint corpora for script matching. The future recommendations aim to enhance OCR accuracy and tackle the challenges identified for real-time industrial applications. This study will guide future research and establish a foundation for OCR field.
Read the full abstract ▾
All authors Nuzhat Khan, Ab Al-Hadi Ab Rahman, Shahriyar Masud Rizvi, Ibrahim Yousef Alshareef, Muhammad Nadzir Marsono, Muhammad Paend Bakht, Mohd Shahrizal Rusli, Shahidatul Sadiah
Networking
PRO-RAN: Processor-Level Characterization of Open RAN Centralized and Distributed Units
Moojan Kamalzadeh, Larry Horner, Linqi Xiao et al. (+5 more)
Open
Radio Access Network (O-RAN) disaggregates RAN protocol functions and enables Centralized Unit (CU) and Distributed Unit (DU) software to execute on general-purpose computing platforms. Different CU and DU protocol responsibilities produce different processor workloads and execution paths. Conventional performance metrics, including CPU utilization and throughput, quantify aggregate resource usage without identifying function-level execution costs or processor microarchitectural bottlenecks. Processor-level characterization, on the other hand, provides insights into resource provisioning, function placement, software optimization, and hardware acceleration. The paper describes a controlled characterization framework that evaluates independently deployed CU and DU functions under matched hardware and traffic conditions. The experimental platform integrates the Linux Foundation OCUDU implementation with an emulated User Equipment, a ZeroMQ-based
radio interface, and an Open5GS core. Automated validation confirms registration and bidirectional packet delivery before process-scoped Intel VTune Hotspots and Top-Down Microarchitecture Analysis. Under traffic load, accumulated process CPU time increases from 17.3 s to 37.4 s for the CU and from 462.0 s to 628.4 s for the DU during equal 300-s profiling intervals. The measurements identify distinct CU and DU execution characteristics and motivate function-specific processor analysis and optimization.
Read the full abstract ▾
All authors Moojan Kamalzadeh, Larry Horner, Linqi Xiao, Abhishek Bhattacharyya, Ehsan Bahaloo Horeh, Padmapriya Patil, Venkateswarlu Gudepu, Andrea Fumagalli
Robotics
RTNav: Towards Real-Time Zero-Shot Object Navigation
Easop Lee, Lingyu Zhang and Boyuan Chen
Navigation in unknown environments to find unforeseen objects has become increasingly feasible with capable
vision and
language foundation models. However, these models also introduce non-negligible inference latency, which becomes an important concern when
agents must operate continuously in the real world. Most state-of-the-art methods are still developed in synchronous simulators, where the environment waits for the
agent to act and inference time is effectively free. As a result,
agents are often designed around the sequential execution of perception,
reasoning, and action, with little regard for time constraints. Under real-time execution, where wall-clock time counts towards the task budget, the inefficiencies of these architectures become clear. We show that recent zero-shot object
navigation methods suffer consistent performance degradation under such realistic timing conditions. Motivated by this observation, we propose RTNav, a simple but effective architecture that treats inference latency, asynchronous environment stepping, and bounded compute as explicit design considerations. Evaluated on real-time variants of HM3D-v1, HM3D-v2, and HM3D-OVON, RTNav improves the success rate by up to 11% and the Success weighted by Completion Time by up to 5.1 points over prior work.
Read the full abstract ▾
Computer Vision
Video-FLAIR: Not Whether to Reason, But How
Yogesh Kulkarni and Pooyan Fazli
Multimodal queries can require different types of
reasoning. Some can be answered via perceptual
reasoning, extracting information directly from the visual signal, while others require compositional
reasoning that combines observations or deliberative
reasoning that evaluates competing hypotheses. However, many existing methods apply a uniform
reasoning strategy across queries, leading to unnecessary computation on simple tasks and insufficient
reasoning on complex ones. We introduce
Video-FLAIR, a training framework that learns to select the appropriate
reasoning mode for each query using reinforcement learning. During training, the model generates responses under all three modes for the same
prompt, enabling direct comparison. A composite reward compares these responses to favor the most effective one based on correctness, grounding, and cost, while discouraging unsupported or misaligned deliberation. This yields a supervision signal for learning adaptive
reasoning without per-query annotations.
Video-FLAIR improves accuracy over the Qwen2.5-VL base model by +5.4 on MathVista, +4.8 on
Video-Holmes, and +4.8 on
Video-MMMU, while reducing average
token usage to 95 compared to 417 for always-thinking baselines.
Read the full abstract ▾