Artificial Intelligence
FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering
Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai et al. (+1 more)
Large
language model
agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specified: Meta Platforms' "operating income" is $46.75B consolidated but $62.87B for the Family of Apps segment, and each reading is exactly verifiable against the filing. A capable
agent should recognize the ambiguity and ask, rather than commit to a plausible but unintended reading. Existing financial
benchmarks cannot measure this, because one gold answer per question cannot separate
agents that resolve the ambiguity from those that guess the common reading, a blind spot we call the single-gold illusion. We release FinInteract, a bilingual (English/Chinese)
benchmark of 173 instances that pairs each question with a default and an intended interpretation across a five-category ambiguity taxonomy, and grades whether an
agent elicits the right clarification and then integrates it. Re-grading identical outputs against the default rather than the intended reading inflates GPT-4o's accuracy by 3.1 times, confirming the illusion. Beyond it, we find that models answer above 90% once the interpretation is supplied but at most 28.9% when they must elicit it themselves, that targeting is uneven across a taxonomy well powered for entity scope and metric definition and exploratory elsewhere, and that conditioning on the ambiguity category improves resolution at both inference and training time.
Read the full abstract ▾
All authors Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai, Guang Cheng
General Topology
Sobriety of Scott topologies under countability conditions
Zhengmao He, Zhaochen Dong and Kaiyun Wang
In this paper, we focus on the sobriety of the Scott
topology in countable case. Specifically, we show that: (1) every meet-continuous core-compact countable dcpo is sober with respect to the Scott
topology; (2)every countable locally compact dcpo is sober endowed with the Scott
topology; (3) the
lattice of all open sets for the rational numbers space Q equipped with the Scott
topology is not sober.
Read the full abstract ▾
Atmospheric and Oceanic Physics
Conservation Constraints and Distributed Advective Memory in a Reduced Model of Atlantic Overturning Hysteresis
Sandy Hardian Susanto Herho, Iwan Pramesti Anwar, Mutiara Rachmat Putri et al. (+3 more)
Interbasin exchange through the Indo-Pacific gateway supplies salt to the Atlantic and is widely invoked as a control on the stability of the Atlantic overturning circulation. We ask whether that control can act on the
equilibrium structure of a conceptual thermohaline model. A closed five-box model with an exact salt invariant is constructed, comprising North Atlantic, upper-limb, Indian, Pacific, and deep reservoirs, with the return flow split between a warm route through the Indian reservoir and a cold route, together with an Indonesian Throughflow branch and an Agulhas retroflection. Adding the steady-state budgets of the gateway reservoirs shows that every internal exchange cancels, so the salt they export to the Atlantic is fixed by the net Atlantic freshwater export alone. This holds independently of the warm-route fraction, the throughflow, the retroflection, and how the export is apportioned among gateway reservoirs; across a parameter sweep the largest departure is of order ten to the minus eleven. The gateway therefore enters as a purely additive forcing and cannot renormalize the salt-advection feedback. Replacing the discrete transit lag by a gamma
memory kernel leaves the
equilibria unchanged but yields a closed-form threshold for oscillatory instability depending only on kernel shape. Broad
memory is strongly stabilizing, and a discrete lag is the least stable member of the family. Because the instantaneous feedback vanishes at the fold, oscillatory instability always precedes the saddle-node, over an interval widening more than tenfold as
memory sharpens. Gateways therefore appear to act on transient rather than
equilibrium dynamics
Read the full abstract ▾
All authors Sandy Hardian Susanto Herho, Iwan Pramesti Anwar, Mutiara Rachmat Putri, Rusmawan Suwarman, Deny Juanda Puradimaja, Dasapta Erwin Irawan
Machine Learning
Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models
Star S.D. Liu, Xiyu Ding, Robert B. Barrett et al. (+3 more)
How large
language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLMs (Qwen-2.5-7B/32B and Llama-3.1-8B/70B) internally represent cost tradeoffs, how these representations relate to clinical predictions, and whether decisions shift as predicted by the specified cost direction and magnitude. Using a public diabetes
dataset, we varied 11 false-negative (FN) to false-positive (FP) cost ratios across three phrasings and examined representations and behavioral outputs. Patient risk was linearly recoverable on par with conventional classifiers (AUC $\approx 0.83$), and cost direction was recoverable in every model. However, representational shifts in cost direction tracked output changes only in the two larger models, and responses to cost magnitude were predominantly direction-agnostic. Only 2 of 12 model-phrasings showed both opposing responses to increasing FN versus FP costs and cost-correct ordering. Representationally, a direction fitted on one cost side did not invert when transferred to the other, as expected under mirror-symmetric encoding. These findings suggest that LLMs encode risk and cost information but do not reliably integrate them into cost-correct decisions. Clinical evaluations should therefore include tradeoff tests, phrasing sensitivity, and default operating points alongside predictive performance.
Read the full abstract ▾
All authors Star S.D. Liu, Xiyu Ding, Robert B. Barrett, Alberto Santamaria-Pang, Nic Dobbins, Harold P. Lehmann
Econometrics
A Stochastic Nested Fixed Point Algorithm for Large-Scale BLP Estimation
Zhentong Lu, Myung Hwan Seo, Youngki Shin et al. (+1 more)
We develop a
stochastic nested fixed point (SNFP)
estimator for random coefficients logit demand models that updates model parameters using
stochastic gradients and performs demand inversion one
market at a time. Relative to the conventional nested fixed point (NFP)
estimator, SNFP substantially reduces
memory requirements and computational cost, making estimation feasible in very large
datasets. We establish the large-$T$ (number of
markets) asymptotic properties of the
estimator under regularity conditions. We also characterize the effect of sharing one block of simulation draws across
markets and show how to correct for it. Monte Carlo simulations show that the SNFP
estimator achieves statistical accuracy comparable to the NFP
estimator, and in our
benchmark a single online pass estimates a model with 100 million
markets in about 5.5 hours. An empirical application using scanner data further demonstrates the practical advantages of SNFP for large-scale demand estimation.
Read the full abstract ▾
All authors Zhentong Lu, Myung Hwan Seo, Youngki Shin, Qichen Zhang
Robotics
RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations
Dorian Benhamou Goldfajn, Mason Nakamura, Saaduddin Mahmud et al. (+3 more)
Multi-
robot collaboration could enable more efficient and scalable solutions to complex robotic tasks, but collaboration under partial observability remains challenging. Natural-
language communication offers a promising approach to coordinating
robots under partial observability. However, in decentralized manipulation, jointly learning explicit inter-
robot communication and skill-level action selection from
multimodal demonstrations remains underexplored for small
vision-
language models (VLMs) intended for on-device deployment. To address this gap, we introduce RoboTalk, a synthetic data-generation pipeline and
dataset of 7,950
multimodal trajectories spanning 53 mobile-manipulation kitchen tasks for training small VLMs to communicate and coordinate. The
dataset includes a leader-follower planning protocol, tool calls (perception, manipulation,
navigation, and communication), rationale traces, and diversified natural-
language communication. Fine-tuning open-source models on our
dataset can reach 77% success on novel held-out tasks, a significant improvement over the untuned open source models, which had a success rate of around ~2%.
Read the full abstract ▾
All authors Dorian Benhamou Goldfajn, Mason Nakamura, Saaduddin Mahmud, Justin Svegliato, Kyle H. Wray, Shlomo Zilberstein
Functional Analysis
Reflexive and strictly convex Banach spaces without Property (H)
Chunliu Feng and Geng Tian
We prove that Property $(H)$ fails for a broad class of reflexive strictly convex
Banach spaces. More generally, the real
Banach space \[ \Big(\bigoplus_{j=1}^{\infty} L^{p_j}(\Omega_j,\mu_j)\Big)_{\ell^s} \] does not have Property $(H)$ whenever $1\le s<\infty$, $1\le p_j<\infty$, $\sup_j p_j=+\infty$, and each $L^{p_j}(\Omega_j,\mu_j)$ is infinite-dimensional.
Read the full abstract ▾
Machine Learning
Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets
Edward Raff and James Holt
Linear models with an $L_1$-norm penalty remain state-of-the-art for high-dimensional ($d > 1,000,000$) tasks, offering a straightforward method for solving real-world industry problems. Despite their widespread use in industry and utility, many $L_1$ solvers are not effective for general use, are prohibitively slow, and are ineffective in parallelization. This makes them difficult to train in an MLOps pipeline on large industry-scale corpora. In this work, we test several proposed “state-of-the-art” solutions from the literature and find that older methods are currently far superior for general use. We also identify several recommendations for academics to perform research that avoids erroneously overconfident results, which can prevent the transition to production use. Equally surprising, we find that a new and simple baseline, using LBFGS on a sub-gradient, is highly effective with minor tweaks, despite being dismissed in the literature for theoretical non-convergence. In practice, we find it is an easier-to-support and easier-to-scale method for production use.
Read the full abstract ▾
Probability
High-Dimensional Ultra-Log-Concave Distributions
Zongchen Chen and Sihan Wang
Ultra-log-concave distributions are ubiquitous in probability, combinatorics, and statistical mechanics and have been studied extensively. In this paper, we introduce a quantitative high-dimensional extension of this notion, called $\delta$-ultra-log-concavity, for probability measures on $\mathbb{N}^d$ with downward closed support. When $\delta = 1$, this notion coincides with the class studied by Gurvits (2009) via strongly log-concave generating functions, and with the class defined by Anari, Oveis Gharan, and Vinzant (2021) via completely log-concave generating functions; in one dimension, it reduces to classical ultra-log-concavity. We establish several functional inequalities, including a weighted Poincaré inequality, a discrete Brascamp–Lieb inequality, and a weighted Wu-type modified log-Sobolev inequality. Our approach combines integrated Bakry–Émery calculus for a canonical birth-death chain with Poisson
stochastic localization, which arises as the time reversal of coordinatewise binomial thinning. We further establish concentration of measure, maximum-
entropy principles, and several closure properties for ultra-log-concave measures, and develop applications to queueing models, polymatroids,
antiferromagnetic Potts models, and hardcore models. Finally, a
lattice scaling limit of the discrete theory yields Poincaré and Brascamp–Lieb inequalities for Laguerre
diffusions.
Read the full abstract ▾
Strongly Correlated Electrons
A Majorana Formulation of Time-Dependent Two-Particle Reduced-Density-Matrix Dynamics
Haoran Wang and Alessandro Principi
We introduce a time-dependent two-particle (TP) reduced-density-
matrix algorithm for systems of interacting Majorana
fermions. We close the BBGKY hierarchy at the two-particle level by reconstructing the three-particle reduced density
matrix from lower-order correlations. To stabilize the
evolution, we impose a positivity projection on the two-particle density
matrix while preserving chosen conserved quantities such as the energy. We
benchmark the approach on quenches in the one-dimensional Hubbard model and on flux dynamics in the Kitaev honeycomb model. For the Hubbard quench, TP captures strong-coupling dynamics missed by Hartree–Fock (HF). For the Kitaev quenches, TP accurately reproduces the early-time flux dynamics in several regimes and provides a substantial improvement over HF when two-particle correlations are important. We further show that gauge coherence is essential for flux dynamics. The projection procedure however introduces an effective irreversibility, which affects the long-time dynamics.
Read the full abstract ▾
Signal Processing
From Ideal Motion to Flight-Executable Communications: LLM-Evolved Multi-UAV Deployment for Cell-Free Massive MIMO
Yuyao Wang, Gaoze Mu, Yongan Zheng et al. (+5 more)
Cell-free massive multiple-input multiple-output (CF-mMIMO) is a promising paradigm for future wireless networks, providing user-centric services and cooperative coverage. By using unmanned aerial vehicles (
UAVs) as aerial access points, CF-mMIMO networks can exploit
UAV mobility to enhance three-dimensional (3D) coverage and spectral efficiency (SE). However, most existing studies on
UAV deployment for communication optimization typically assume that
UAVs follow ideal point-mass motion (IM), neglecting flight-control constraints and finite-horizon position errors in real flight execution. Consequently, IM-trained deployment policies may degrade severely or become difficult to execute in practice. Motivated by this, we model each
UAV as a six-degree-of-freedom quadrotor rigid body with a cascaded flight controller to capture the impact of flight-control-constrained motion (FM) on communication optimization. Based on this model, we formulate a joint
UAV 3D deployment and power allocation problem under FM to maximize the downlink average SE in CF-mMIMO networks. To address this problem, we propose LERE, a large
language model (LLM)-enhanced multi-
agent reinforcement learning (MARL) framework. In LERE, the LLM evolves hybrid rewards with both global and local components via multi-level feedback. The evolved hybrid rewards guide MARL policy optimization and promote multi-
UAV cooperation. Experimental results demonstrate that LERE achieves higher SE than reward-design baselines while substantially reducing
UAV position errors. Notably, when tested under FM execution, the FM-trained LERE policy achieves a 60.49% SE gain over its IM-trained counterpart, confirming the necessity of incorporating flight-control constraints into
UAV-enabled CF-mMIMO optimization.
Read the full abstract ▾
All authors Yuyao Wang, Gaoze Mu, Yongan Zheng, Yanzhao Hou, Qingqing Wu, Qimei Cui, Xiaofeng Tao, Ping Zhang
High Energy Physics (Theory)
Cassini Ansatz in the Skyrme Model
N. V. Gerasimeniuk, A. A. Korneev, A. V. Molochkov et al. (+1 more)
We investigate the stretching of a spherically symmetric solution in the Skyrme model. The three-dimensional generalization of the Cassini ovals is considered as ansatz of extension. The linear dependence of static energy on the longitudinal deformation parameter is obtained with a slope $\sigma \approx 0.14\ \mathrm{ GeV}^2$, which is in good agreement with the string tension known from various models of confinement.
Read the full abstract ▾
All authors N. V. Gerasimeniuk, A. A. Korneev, A. V. Molochkov, O. G. Tkachev
Machine Learning
MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting
Tsung Yeh Hsieh, Cosmin Anitescu, Chunghwan Kim et al. (+2 more)
Tracking neurite morphology over time helps characterize structural changes during neuronal development and deterioration, but long-term time-lapse imaging is resource-intensive and difficult to scale.
Forecasting future morphology could reduce this burden. Existing neurite digital-twin models such as gated spatiotemporal
attention (gSTA) produce a single deterministic forecast without representing variability among plausible futures. We introduce Morphology-Gated Residual
Diffusion (MGRD), a compact
stochastic surrogate that jointly forecasts twenty future neurite-morphology frames from ten observed frames while conditioning on morphology features derived from the latest observation. On controlled phase-field trajectories, MGRD reduces trajectory-wise mean MAE by 9.7% relative to a matched control while updating 4.46 times fewer parameters. On human iPSC-derived
neuron microscopy, MGRD improves all four reported metrics over gSTA, including a 39.6% reduction in trajectory-wise mean MAE and a 45.3% increase in skeleton F1. Without mouse-domain retraining or fine-tuning, MGRD also improves MAE and skeleton F1 on mouse cortical-neurosphere microscopy across 10-40-min sampling intervals and forecast horizons beyond 13 hours. Repeated sampling provides a case-level variance score for ranking forecast difficulty. Retaining approximately 60% of the lowest-variance cases reduces mean MAE by 17.6% on iPSC microscopy and 16.8% on simulation data. MGRD uses 1.01% of gSTA's parameters, requires less than one tenth of its training-update time, and generates a 50-step DDIM trajectory 7.9% faster when morphology features are cached. These results establish MGRD as a compact
stochastic surrogate for neurite-morphology
forecasting and case prioritization across simulation and microscopy
datasets.
Read the full abstract ▾
All authors Tsung Yeh Hsieh, Cosmin Anitescu, Chunghwan Kim, Victoria A. Webster-Wood, Yongjie Jessica Zhang
Artificial Intelligence
ACLArena: Agent Continue Learning in Multi-stage Post-training
Haixin Wang, Xiaoxuan Wang, Junkai Zhang et al. (+9 more)
Building general-purpose
agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currently no well-established recipe for
Agent Continual Learning (ACL), with little understanding of the trade-offs among existing integration paradigms. To address this gap, we introduce ACLArena, a framework for comprehensively studying, analyzing, and evaluating ACL. We first build a sequential training pipeline and conduct an in-depth analysis that explains the mechanisms of forgetting and generalization from two complementary perspectives, the model level and the
token level. Guided by these analyses, we systematically compare multi-teacher on-policy
distillation, self-distilled fine-tuning, and model merging to assess their ability to recover previously learned capabilities while preserving newly acquired ones. Through extensive experiments, we develop a detailed understanding of how capabilities transfer across stages. Finally, we propose a new ACL recipe that combines offline replay over high-quality trajectories with a routed network of multiple LoRA experts each specialized via RL, substantially improving the
agent's ability to learn across multiple domains. Comprehensive experiments on four
reasoning and agentic tasks, evaluated under both in-domain and out-of-domain settings, demonstrate the value of our analysis and the effectiveness of our approach.
Read the full abstract ▾
All authors Haixin Wang, Xiaoxuan Wang, Junkai Zhang, Han Zhang, Renliang Sun, Alexander K Taylor, Yidan Shi, Haoran Deng, Chenguang Wang, Jason Cong, Yizhou Sun, Wei Wang
Systems and Control
The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study
Jayakumar Manoharan
Renewable forecasts are evaluated by statistical skill (e.g., CRPS), but grid operators pay for realized dispatch cost. We diagnose what drives dispatch value in a single-period newsvendor-style economic dispatch using real public data from two European transmission systems (CWE, DE-4TSO). Spatial coherence across forecast sites falls below the pre-specified 1% practical-significance threshold: a controlled ablation holding per-zone marginal forecasts bit-identical and varying only cross-zone dependence (10 configurations, 3 seeds, paired-bootstrap confidence intervals) shows a coherence gain of at most 0.64% of dispatch cost, indistinguishable from zero in 3 of 10 configurations, reached only under an unrealistic 8-fold forecast-error stress test. Decision-focused training, an established paradigm in this venue, delivers a robust 2.82-5.19% gain. A parametric Gaussian-copula approximation matches the empirical copula at realistic error magnitudes but performs worse than no dependence under extreme stress. A single-seed sweep shows that a 12% energy-score gain changes cost by less than 0.1%. Results characterize this single-period dispatch class; a lightweight four-period extension supports the same conclusion. For this dispatch class, spatially-correlated scenario generation provides limited operational value on its own; grid operators and forecast vendors should instead evaluate dependence models by downstream decision value and prioritize decision-focused training.
Read the full abstract ▾
Combinatorics
Quasi-overlap and quasi-grouping functions on bounded pseudo-ordered sets
Xue-ping Wang and Hong-fei Liu
In this article, we first introduce quasi-overlap and quasi-grouping functions on bounded pseudo-ordered sets, respectively, and give their respective preliminary constructions and the induced quasi-overlap functions on quotient posets.. We then explore the invariant properties under weighting and
automorphisms. We also introduce the migrativity, the homogeneity, the idempotency, the cancellation law, the Archimedean and limiting properties of quasi-overlap functions and discuss their relations. We finally present two constructing methods of quasi-overlap functions, which are based on boundary-faithful mappings and adjunctions on bounded psosets and the transitive-endpoints of a bounded trellis, respectively. The corresponding statements are valid for quasi-grouping functions as well.
Read the full abstract ▾
Artificial Intelligence
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Dongming Jiang, Yi Li and Bingzhe Li
Agentic
memory is becoming essential for long-horizon AI
agents, yet many existing systems rely on autoregressive LLMs to control how
memories are organized, retrieved, and used, placing expensive generation on the critical path of
memory operations. We introduce \method, a new agentic
memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative
reasoning. Jev-Mem brings this division of labor to agentic
memory through a dedicated System-One control plane, a structured multi-relational
memory plane, and a System-Two
reasoning plane. The System-One controller governs
memory typing and relational organization during construction, and dynamically performs query routing,
retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during
retrieval. System Two is invoked only for complex
reasoning and answer synthesis. This design improves both
memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0% relative improvement over the strongest baseline, while reducing
memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing
memory system, and lowering average query latency to 0.93\,s, a 36.7% reduction.
Read the full abstract ▾
Statistical Methodology
Spectral divide-and-conquer MCMC for long stationary time series
Zixuan Wang, Matias Quiroz, Feng Li et al. (+2 more)
The temporal dependence inherent in time series models poses a fundamental challenge for distributed
Bayesian inference, as it precludes embarrassingly parallel
algorithms based on naive independence assumptions in the time domain. We propose a frequency-domain framework for scalable
Bayesian inference in stationary time series that exploits the asymptotic independence underlying the Whittle likelihood. To exploit parallel computing resources, we develop a distributed fast
Fourier transform and integrate it with embarrassingly parallel Markov chain Monte Carlo (MCMC)
algorithms within a modern cluster-computing framework. This enables the analysis of time series that exceed the
memory capacity of a single computational node or for which computation time is a bottleneck. The proposed methodology is compatible with a broad class of existing divide-and-conquer
algorithms for independent data by applying them to frequency-domain rather than time-domain partitions. We establish that the error of the spectral divide-and-conquer MCMC posterior approximation relative to the exact time-domain posterior converges to zero in probability in a shrinking neighbourhood of the full-data Whittle posterior mode. The corresponding convergence rate is also derived. Across several experiments, we demonstrate that our approach provides accurate approximations to the full-data Whittle posterior. The proposed method is shown to outperform the current state-of-the-art time-domain divide-and-conquer methodology, particularly for highly persistent processes. The methodology is further illustrated by fitting a semi-long range model to a long meteorological time series.
Read the full abstract ▾
All authors Zixuan Wang, Matias Quiroz, Feng Li, Mattias Villani, Robert Kohn
Algebraic Topology
Automated proofs of unstable Adams differentials
Jake Francis Baer
We present a computer-based approach to computing differentials in the unstable Adams spectral sequence by systematically applying the unstable Leibniz rule and naturality with respect to maps in the EHP sequence. We record our results in tables of upper and lower bounds on the orders of 2-primary unstable homotopy groups of spheres through the unstable 50-stem. We provide examples of proofs for several differentials and give a guide to interpreting the associated unstable Adams charts and flow chart diagrams for differential proofs.
Read the full abstract ▾
Computer Vision
Evaluating the Generalization of Neuroimaging Foundation Models on African Brain MRI
Oluwatobi Iyanuoluwa Akinmuleya, Olatokun Shamsudeen Akano, Samuel Danquah Ankapong et al. (+2 more)
Neuroimaging foundation models pretrained on large, predominantly western cohorts are increasingly proposed as general-purpose backbones for
brain MRI analysis. Yet, their ability to generalize to underrepresented clinical populations remains largely untested. We evaluate four recent foundation models (BrainIAC, Neuro-JEPA, NeuroVFM, and Primus) on a three-way diagnostic classification task (Control, Dementia, Parkinson's disease) using a cohort of 88 subjects from a Nigerian clinical
brain MRI
dataset, across four modality configurations (T1w, T2w, T1w+T2w, FLAIR), and compare against an end-to-end trained ViT3D baseline. The frozen backbones collapse to majority-class predictions, while Neuro-JEPA on FLAIR shows modest but still limited discrimination. In contrast, the end-to-end trained ViT3D achieves higher accuracy and MCC on every task (up to 53.4% accuracy, MCC=0.27) and is the only model with non-trivial recall. Our findings suggest that these frozen neuroimaging foundation models are insufficient for fine-grained diagnostic classification in small, non-western clinical cohorts, motivating parameter-efficient adaptation and broader multi-site external validation for equitable deployment in global health settings.
Read the full abstract ▾
All authors Oluwatobi Iyanuoluwa Akinmuleya, Olatokun Shamsudeen Akano, Samuel Danquah Ankapong, Olamide Lawal, Toufiq Musah
Astrophysics of Galaxies
The CAMELS-CROCODILE Simulation Suite: A New Cosmology–Astrophysics Playground for Machine Learning
Kentaro Nagamine, Yuri Oku, Atsushi J. Nishizawa et al. (+4 more)
We present CAMELS-CROCODILE, a suite of cosmological hydrodynamic simulations that extends the CAMELS framework with the \gadget{} smoothed particle hydrodynamics code and the Osaka feedback model. As a companion to the IllustrisTNG-based second-generation CAMELS suite, it provides an independent implementation of the baryonic physics that shapes
galaxies, the intergalactic medium, and large-scale structure, broadening the range of subgrid models over which machine-learning (ML) inference can be marginalized and tested. The suite comprises $25$ and $50Mpc/h$ boxes organized into one-parameter,
cosmic-variance, and Sobol-sequence sets that vary $26$ cosmological and astrophysical parameters around a fiducial Osaka model. We describe the simulation design and validate the suite against
benchmarks and other CAMELS suites. Compared with IllustrisTNG, the fiducial model suppresses the matter power spectrum by only a few per cent, against up to ${\sim}27\%$ at $z=0$, and forms
stars with similar efficiency below $10^{12.2} M_\odot/h$ but up to $2.5$ times more efficiently in group-scale
halos, both consistent with weaker AGN feedback. We also present the
stellar and black hole bias and the Ly$\alpha$ absorption around
galaxies. As a first ML application, we apply a graph neural network trained on IllustrisTNG
galaxy catalogs, with frozen weights, to CAMELS-CROCODILE. It fails to recover $\Omega_{\rm m}$ and $\sigma_8$ and returns overconfident posteriors, mainly for simulations containing more
galaxies than any in its training set; within that range $\Omega_{\rm m}$ is recovered with an error only $1.5$ times the in-distribution value. These results underline the need to train and test ML inference across physically distinct
galaxy formation models.
Read the full abstract ▾
All authors Kentaro Nagamine, Yuri Oku, Atsushi J. Nishizawa, Jun-Young Lee, Francisco Villaescusa-Navarro, Shy Genel, Daniel Anglés-Alcázar
Systems and Control
Sufficient and Necessary Smooth Barrier-like Conditions for Continuous-Time Stochastic Reach-Avoid Verification
Bai Xue
In this paper, we study infinite-horizon reach-avoid verification for continuous-time
stochastic systems modeled by
stochastic differential equations (SDEs). We formulate this problem within a barrier-function-based framework, which transforms the verification problem into an existence problem for barrier functions satisfying barrier-like conditions expressed as functional inequalities. We provide sufficient and necessary barrier-like conditions in terms of
polynomial barrier functions for infinite-horizon reach-avoid verification under suitable regularity and uniform ellipticity assumptions. We first construct a discounted value function that characterizes lower bounds on the reach-avoid probability. We then show that it is the unique classical solution of an associated
elliptic Dirichlet problem. Based on this characterization, we further show that the barrier-like condition proposed in our previous work on finite-horizon reach-avoid verification is not only sufficient for infinite-horizon reach-avoid verification but also necessary whenever the reach-avoid probability is strictly larger than the specified threshold. In particular, whenever the reach-avoid probability is strictly larger than the specified threshold fro every state in the initial set,
polynomial barrier functions satisfying this barrier-like condition exist. Furthermore, when the system dynamics are
polynomial, we formulate the problem of finding
polynomial barrier functions satisfying this barrier-like condition as sum-of-squares (SOS) programs, which are shown to be sound and complete. Finally, we demonstrate the theoretical results on two numerical examples.
Read the full abstract ▾
Cryptography and Security
MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes
Andy K. Zhang, Ava Huang, Joey Ji et al. (+21 more)
AI
agents now report vulnerabilities faster than maintainers can review them. Reports often depend on security properties specific to the application, and require considerable human labor to process. To mitigate this, we introduce a framework for evaluating vulnerability reports via probes, executable checks of security properties. A reported exploit is evaluated by replaying it against the application and running the probes: a triggered probe indicates both that the exploit succeeded and which security property it violated. As a probe encodes a security property rather than a known vulnerability, it can detect vulnerabilities that were not known when the probe was written. We instantiate the framework as MobileCybench, a
benchmark for vulnerability discovery by AI
agents in 13 Android applications, with 495 probes written and reviewed by the authors. We evaluate 5 coding
agents (OpenCode with GPT-5.5, GPT-5.6-Sol, and GLM-5.2; Claude Code with Opus 4.8 and Opus 5) under 4 settings: as a malicious app on the victim's device or as a remote attacker with a low-privilege account, each with either only an obfuscated APK or access to the application's source code. Given only the obfuscated APK, the top
agent, OpenCode with GPT-5.6-Sol, triggers probes in 53.8% of applications in the malicious-app setting and 16.7% in the remote-attacker setting. With source code, the trigger rate across all
agents and both attack settings increases from 28.8% to 32.8%. Building and running the
benchmark surfaced 23 previously unreported vulnerabilities, the majority of which have been confirmed by maintainers.
Read the full abstract ▾
All authors Andy K. Zhang, Ava Huang, Joey Ji, Wai Han, Thomas Qin, Nardos Demilew, Michael Tian-Yue Liu, Brian Song, Riya Dulepet, Brian Wang, Kyleen Liao, Cuiyuanxiu Chen, Nishka Kacheria, Andrew Wu, Pratham Rangwala, Xinjie Wang, Laura Gomezjurado Gonzalez, Anita Ding, Benjamin Yi, Daniel E. Ho, Dan Boneh, Dawn Song, Ion Stoica, Percy Liang
Audio and Speech Processing
AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models
Natarajan Balaji Shankar, Zilai Wang, Zihan Wang et al. (+3 more)
Attention encoder-decoder (AED)
Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs contain no
speech, weak acoustic evidence, or unreliable transcription. We propose AURA: Activation-editing with Uncertainty-Routed Adaptation, an ultra-efficient representation-editing method that freezes the pretrained model and applies sparse scale-and-shift edits to decoder cross-
attention heads. AURA dynamically routes edits using cross-
attention uncertainty features that capture over-concentration, diffuse
attention, and abrupt frame shifts. We evaluate AURA on four
datasets spanning non-
speech hallucination and
speech grounding stressors, including imperfect-label child
speech, imperfect-label adult
speech, and disfluent
speech. On non-
speech audio, AURA reduces
hallucination rate from 89.18% to 1.94% without prior
hallucination-head identification. On imperfect-label corpora, AURA approaches LoRA WER while using roughly 500x fewer trainable parameters. Sensitivity analysis and qualitative cross-
attention examples are consistent with AURA's uncertainty-routed editing behavior, supporting dynamic activation editing as a practical path for grounding AED
speech models.
Read the full abstract ▾
All authors Natarajan Balaji Shankar, Zilai Wang, Zihan Wang, Mohan Shi, Kaiyuan Zhang, Abeer Alwan
Strongly Correlated Electrons
Decoupling the Magnetic Field Operator as an Independent Operator Class in Stochastic Series Expansion Quantum Monte Carlo
Shijie Jin and Lu Liu
The
Stochastic Series Expansion (SSE)
quantum Monte Carlo method with loop updates is among the most powerful approaches for
quantum spin and
boson systems. In the standard formulation, the
magnetic field term is routinely absorbed into the Heisenberg interactions—a strategy that has proven highly efficient across a wide range of field strengths. In this work, we propose a more general SSE framework in which the
magnetic field operator is treated as an independent operator class, enabling it to participate in Monte Carlo updates on an equal footing with all other operators. Importantly, the field operator and other interaction operators can transform into one another during the update process. We demonstrate this
algorithm using the two-dimensional
antiferromagnetic Heisenberg model in a
magnetic field as a concrete example. The simulation results agree with those of the conventional
algorithm, confirming the correctness of the new formulation. A comparison of the integrated autocorrelation time shows that the new
algorithm is competitive. This flexibility not only facilitates measurements of observables associated with operators but also offers potential computational advantages for a broader class of problems.
Read the full abstract ▾
Neurons and Cognition
Binding-Motivated Contextuality: A Cross-Domain Cyclic Test in Perception and Judgment
Adam Y. Shavit
Psychophysics and decision research study perceptual binding and judgment contextuality separately. We argue a binding-motivated perceptual task and judgment contextuality are scored against the same cyclic noncontextuality inequalities and share one convex global-consistency geometry (the correlations that mixtures of globally consistent assignments can produce), not one
cohomology class. Only contextuality is tested, since binding's own residual vanishes here. Building on sheaf formulations of predictive coding (Seely 2025) and contextuality (Abramsky & Brandenburger 2011), a cyclic set of pairwise judgments without signalling admits a noncontextual explanation exactly when the cyclic inequalities hold (judgments do signal, so the test uses the disturbance-corrected form), and its severity is measured by the complete contextual fraction CF, the share of responses no noncontextual model reproduces (Abramsky, Barbosa & Mansfield 2017) rather than by the Cech invariant, which can miss it (Carù 2017). The perceptual arena uses two binary judgments per cyclic-dominance pairing; an appendix rejects the one-bit alternative on construct-validity grounds. The central test is cross-domain: one cohort performs both arenas, and a shared latent tolerance predicts a positive correlation between their signed cyclic margins $V^{\star}$, the pre-clamp quantities behind CF. Both are inconsistency scores, and general response consistency confounds a bare correlation, so each arena's margin is first regressed on its own variance- and reliability-matched control, and the residuals are correlated. A positive result would support a shared residual association, not a common causal mechanism, which we prove this design cannot identify at any sample size. All three tests are designed but unrun, and the perceptual arena awaits pilot gates. This is a methodological proposal, not a confirmatory report.
Read the full abstract ▾
Robotics
Anticipatory Robot Goalkeeping via Monotone Optimal Stopping
Hao E. Zhang, Ruize Geng, Yisen Li et al. (+8 more)
Robots engaged in fast physical interactions often need to act before the intent of another
agent is fully known. Anticipatory goalkeeping illustrates this challenge. Waiting provides more reliable information about the target but reduces the physical opportunity for interception, whereas acting early preserves reachability but requires initiating motion under uncertainty. Given a fixed closed-loop save controller, we formulate the decision of when to initiate motion as a policy-conditional finite-horizon optimal stopping problem. Building on this formulation, we propose monotone optimal stopping (MOS), a structured release-timing method for dynamic robotic interception. The quadruped save policy is trained with reinforcement learning, while MOS determines when the policy should be activated from the evolving
robot state and target belief. Rather than predicting a release time or relying on confidence alone, MOS learns the return advantage of acting now over waiting for one more observation. We derive a direct Bellman recursion for this act-versus-wait margin and impose monotonicity only with respect to physical urgency, reflecting the irreversible loss of interception opportunity as time elapses. This structure enables early activation for dynamically demanding saves while preserving closed-loop adaptation when later observations change the predicted target. Under a single-crossing condition, MOS admits a threshold release boundary with a bounded approximation error. Extensive simulation studies show that MOS improves the mean save rate from 67.7% to 74.4% over a parameter-matched learned gate and increases reversal saves from 52.1% to 66.5%. Real-
robot experiments further demonstrate rapid interception and post-release direction correction under human shot-direction feints.
Read the full abstract ▾
All authors Hao E. Zhang, Ruize Geng, Yisen Li, Yaru Niu, Yikai Wang, Raihan Haque, Khalil Zbiss, Guanyang Luo, Hui-ping Wang, H. Eric Tseng, Ding Zhao
Combinatorics
Sudoku Analogues of Baranyai's Theorem
Amin Bahmanian and Sho Suda
Motivated by higher-dimensional generalizations of Sudoku, we study exact block-structured decompositions, algebraic characterizations, and orthogonality for Sudoku hypercubes. Let $n=\prod_{i=1}^d a_i$, let $b_i=n/a_i$, and consider the $\lambda$-fold complete $d$-uniform $d$-partite hypergraph with $d$ vertex classes of size $n$, where the $i$th class is partitioned into $a_i$ groups of size $b_i$. Given positive integers $m_1,\dots,m_k$ with $\sum_{j=1}^k m_j=\lambda n^d$, we partition the edges into color classes of sizes $m_1,\dots,m_k$ so that, in color $j$, vertex degrees and block counts are each either $\lfloor m_j/n\rfloor$ or $\lceil m_j/n\rceil$, while the multiplicity of an underlying edge is either $\lfloor m_j/n^d\rfloor$ or $\lceil m_j/n^d\rceil$. When $m_j=nr_j$, the vertex and block balances are exact, yielding block factorizations and higher-dimensional Sudoku analogues of Baranyai's
theorem. Within the same block framework, we give a Delsarte characterization of the Sudoku condition using association schemes and study mutually orthogonal Sudoku hypercubes of order $q^3$ for
prime powers $q$. For block sizes $(q^3,q^2,q)$ and $(q^3,q^3,1)$, the resulting families attain a general upper bound and are best possible. For block size $(q^2,q^2,q^2)$, we construct $q^2(q^2-1)(q^2-q)$ mutually orthogonal hypercubes; this construction is asymptotically best possible as $q\to\infty$.
Read the full abstract ▾
Artificial Intelligence
LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning
Boxun Hu, Jiawei Ge, Axel Krieger et al. (+2 more)
Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visual perception. A representative example is Human Mesh Recovery (HMR), which provides useful estimates of a target's 3D pose and shape that can benefit tactical missions. However, the size and power demands of such models make them difficult to run on edge platforms and limit their real-time performance, undermining the requirements of tactical edge deployment - especially for active perception, where a mobile
robot must plan its next-best view on-board and cannot offload computation under contested communications. We present LEAP-NBV, a lightweight active-perception framework that runs foundation-model-driven Next-Best-View (NBV) planning on-board an edge device. To this end, we distill a family of large HMR teachers, each into a compact 32M student, with an offline mesh objective, then quantize the
vision encoder to FP16 and characterize its on-device accuracy and latency. Within an occlusion-aware active perception loop, we evaluate all configurations on the same held-out
benchmark and deploy the end-to-end pipeline on an NVIDIA Jetson Xavier NX, reporting measured on-device latency and energy.
Distillation recovers 6-7 mm of Procrustes-aligned mean per-vertex position error (PA-MPVPE) over the undistilled student on the test set. Selecting the edge-optimal compression model brings the HMR engine to ~12 ms at a small accuracy cost and runs the full closed loop at 3.6 FPS and 2.6 J per frame, achieving a 2.0x speedup and 3.0x lower energy than the uncompressed model while nearly matching downstream task quality.
Read the full abstract ▾
All authors Boxun Hu, Jiawei Ge, Axel Krieger, Peng Wang, Tinoosh Mohsenin
Systems and Control
Sufficient and Necessary Continuous Barrier-like Conditions for Discrete-Time Stochastic Reach-Avoid Verification
Bai Xue
This paper develops necessary and sufficient barrier-like characterizations using continuous barrier functions for infinite-horizon reach-avoid verification of discrete-time
stochastic systems. Existing results establish necessary and sufficient conditions in terms of functional inequalities involving measurable or lower semicontinuous barrier functions. However, the limited regularity of such functions may hinder their numerical approximation and computational synthesis. Building on our previous barrier-like condition for finite-horizon reach-avoid verification, we show that this condition can also be used for infinite-horizon reach-avoid verification and, under a uniform absolute continuity condition on the transition kernels, admits a continuous barrier function whenever the exact reach-avoid probability is strictly larger than the prescribed threshold for every state in the initial set. We further show that the resulting continuous barrier function can be uniformly approximated by a
polynomial one while preserving the required barrier-like conditions. For
polynomial systems, we formulate these conditions as
polynomial positivity constraints over compact basic semialgebraic sets. Putinar's Positivstellensatz then converts the positivity conditions into sum-of-squares (SOS) certificates, yielding semidefinite programming (SDP) formulations for synthesizing
polynomial barrier functions. We establish both soundness and completeness of the resulting SOS-based procedure. Finally, two numerical examples illustrate the theoretical results and demonstrate the resulting SDP approach.
Read the full abstract ▾