Data Structures and Algorithms · Cross-listed from math.CO
Stable Regularity Lemmas: Efficient Algorithms and Essentially Tight Littlestone Bounds
Leonardo N. Coregliano and Fernando G. Jeronimo
In this paper, we determine the precise asymptotics of the number of parts of stable regularity equipartitions in terms of the Littlestone dimension: every graph $G$ of Littlestone dimension $\operatorname{Lit}(G)\leq\ell$ has a regular equipartition into excellent sets with $(1 + o_{\epsilon\to 0,\ell}(1))\cdot\epsilon^{-\ell-1}$ parts and in the other direction, for every $\ell\in\mathbb{N}_+$, there is an infinite family of graphs, all of Littlestone dimension $\ell$, whose equipartitions into good sets must have size at least $(1 + o_{\epsilon\to 0,\ell}(1))\cdot\epsilon^{-\ell-1}$. Dropping the equitability condition, we determine the asymptotics of non-equitable partitions up to a multiplicative $\log(1/\epsilon)$: every graph $G$ with $\operatorname{Lit}(G)\leq\ell$ has a regular partition into excellent sets with $(1 + o_{\epsilon\to 0,\ell}(1))\cdot\epsilon^{-\ell}\cdot\ln(1/\epsilon)$ parts and in the other direction, for every $\ell\in\mathbb{N}_+$, there is an infinite family of graphs, all of Littlestone dimension $\ell$, whose partitions into good sets must have size at least $(1 + o_{\epsilon\to 0,\ell}(1))\cdot\epsilon^{-\ell}$. We also show that such partition can be obtained algorithmically efficiently in an approximation scheme fashion: replacing the $o_{\epsilon\to 0,\ell}(1)$ term above by a constant $c > 0$, we obtain randomized $O_{c,\epsilon,\ell}(n\cdot\log(n))$-time
algorithms for partitions/equipartitions into good sets, a deterministic $O_{c,\epsilon,\ell}(n^2)$-time
algorithm for partitions into good sets, a deterministic $O_{c,\epsilon,\ell}(n^6)$-time
algorithm for equipartitions into good sets, a deterministic $O_{c,\ell,\epsilon}(1)\cdot n^{O(\ell\cdot 2^{2\cdot\ell+4})}$-time
algorithm for partitions/equipartitions into excellent sets, and $O_{c,\epsilon,\ell}(\log(n+1))$-space
algorithms for partitions/equipartitions into good/excellent sets.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.QM
WILSON - Multi-magnification composites as a foundation for patient-level pathology analysis and diagnostic text generation
Saghir Alfasly, Wataru Uegami, Sobhan Hemati et al. (+17 more)
Pathologists examine tissue sections across multiple magnifications and slides, integrating morphological information to establish a diagnosis. In contrast, most pathology foundation models encode thousands of image patches from a single representative ("best") slide and aggregate their features, limiting multiscale and patient-level contextual integration. Here we introduce WILSON, a
vision-
language foundation model that represents whole-slide images and multi-slide cases through multi-magnification composites. Trained on approximately 189,000 slides spanning 42 organs and 838 diagnostic entities, WILSON enables patient-level analysis,
multimodal retrieval and diagnostic text generation. Without task-specific training, WILSON outperformed a dedicated case-level model (macro-F1, 0.52 versus 0.38) and matched substantially larger slide-level models while requiring 400-1,350 times fewer computational operations. End-to-end fine-tuning improved breast cancer subtyping and stromal lymphocyte grading. WILSON also surpassed PRISM in image-text
retrieval (recall@1, 75.6% versus 58.1%) and generated diagnostic descriptions that received higher ratings from five board-certified pathologists than competing models. These findings demonstrate that compact, multiscale representations can support computationally efficient, clinically grounded pathology foundation models.
Read the full abstract ▾
All authors Saghir Alfasly, Wataru Uegami, Sobhan Hemati, Wenchao Han, Xiaojia Tang, Kevin Thompson, Daniel Stone, Ghazal Alabtah, Chris Hartley, Chady Meroueh, John C. Cheville, Thomas J. Flotte, Saba Yasir, Michael R. Lucas, Eric W. Klee, Cheryl L. Willman, Judy C. Boughey, Matthew P. Goetz, Krishna R. Kalari, H.R. Tizhoosh
Software Engineering
TRACTOR Benchmark for Evaluating C to Rust Translators
Hamed Okhravi, Brandt Ogden, Noah Luther et al. (+3 more)
Memory-safety vulnerabilities remain a persistent source of security risk in critical software, much of which is implemented in
memory-unsafe
languages such as C and C++. Recent advances in programming
languages, program analysis, and artificial intelligence have created new opportunities to modernize these legacy systems through automated translation to
memory-safe
languages such as Rust. The DARPA Translating All C to Rust (TRACTOR) program seeks to develop scalable techniques for translating large C codebases into safe, performant, and maintainable Rust. MIT Lincoln Laboratory serves as the program's independent test and evaluation organization and has developed a standardized
benchmark for systematically assessing C-to-Rust translation tools. This report describes the TRACTOR
benchmark, including progressively challenging test batteries and larger milestone projects, as well as the supporting evaluation infrastructure and metrics for assessing correctness, safety, idiomaticity, and performance. The
benchmark and associated evaluation infrastructure are publicly available to support the broader development and evaluation of C-to-Rust translation technologies.
Read the full abstract ▾
All authors Hamed Okhravi, Brandt Ogden, Noah Luther, Ian McQuoid, Howard Mak, Nathan Burow
Artificial Intelligence · Cross-listed from physics.chem-ph
Rachel: A general-purpose language model directs and revises retrosynthetic routes
Qisheng Li, Shunchao Jiang, Chen Qi et al. (+3 more)
Retrosynthetic planning advances through decisions that reshape the remaining chemical problem: a locally plausible disconnection can leave precursors whose chemoselectivity constraints complicate the rest of the route. Existing planners often channel model proposals through search or template procedures, leaving open whether a general-purpose large
language model (LLM) can itself sustain and revise route strategy. We developed Rachel, a stateful environment that executes and checks LLM-directed chemistry but prescribes neither a search policy nor a stopping rule. Without supplied reference routes or route-level solutions, GPT-5.5 achieved strict closure for 111 of 120 PaRoutes120 targets and 24 of 25 targets in the separate RF25 difficult-target cohort. RF25 was drawn largely from studies published after GPT-5.5's reported knowledge cutoff. Closure required complete routes and independent source resolution of every terminal precursor after planning. On a shared PaRoutes subset, forward-model support exceeded that of most comparator methods, and Rachel received the highest mean overall route score from both method-blinded LLM evaluators. Recorded trajectories showed continued model-proposed chemistry, with revised strategies carried into subsequent steps. Replacing LLM route decisions with fixed policies reduced strict closure to 6-15/120 despite continued local chemical execution; restricting planning support also reduced closure in RF25. Within Rachel, a general-purpose LLM coordinated successive chemical choices and revised its strategy as earlier decisions reshaped the remaining problems.
Read the full abstract ▾
All authors Qisheng Li, Shunchao Jiang, Chen Qi, Xin Su, Da Han, Guangyong Chen
Information Theory
Subspace coverings and generalized covering radii of generalized Zetterberg codes
Shitao Li, Yang Li, Gaojun Luo et al. (+1 more)
Generalized covering radii measure how many columns of a parity-check
matrix are needed to generate several syndromes simultaneously. Their finite-
geometric counterparts are $(\rho,t)$-saturating sets, for which every $t$-dimensional subspace is contained in a subspace generated by at most $\rho$ prescribed vectors. We investigate this covering problem for the norm-one configurations associated with generalized Zetterberg codes. We establish the upper bound $2t+1$ over every nonbinary finite field and in an explicit binary range, together with complementary lower bounds obtained by counting subspaces and constructing subfield obstructions. For an explicit range of large $t$, these configurations are $t$-strong blocking sets, and the $t^{\rm th}$ generalized covering radius attains its minimum possible value $t$. For binary Zetterberg codes, we determine the second generalized covering radius in every extension degree and prove that the third radius is seven for an infinite subfamily.
Read the full abstract ▾
All authors Shitao Li, Yang Li, Gaojun Luo, Zhonghua Sun
Computer Vision
You've Seen Enough: Quality-Constrained Image Coding for Machines
Khoa Pham-Dinh, Sanaz Nami, Hamed Rezazadegan Tavakoli et al. (+2 more)
Visual data is increasingly consumed by machine-
vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main observer is a computer
vision application and that the human observer needs to inspect or validate the decisions. Inspired by just-noticeable distortion, we cap human-observed quality at a desired level and devote the remaining bits to machine performance. Specifically, joint compression-
segmentation training is recast as a constrained optimization problem in which the codec must meet a predefined acceptable target visual quality while a task term consumes the remaining coding capacity. This paper proposes two variants of a penalty function that guides the quality toward the target: an absolute function and a bilinear function, the latter applying a steeper slope once the target visual quality is exceeded. Experimental results show that, under the quality constraint, the proposed method achieves BD-rates of $-22.82\%$ and $-29.81\%$ relative to an unconstrained joint rate–distortion–task optimization and a simple rate–distortion baseline, respectively, showcasing bitrate reduction with the same task performance. This is achieved while the codec also meets the target visual quality with a reasonable error and without adding any complexity overhead.
Read the full abstract ▾
All authors Khoa Pham-Dinh, Sanaz Nami, Hamed Rezazadegan Tavakoli, Moncef Gabbouj, Farhad Pakdaman
Artificial Intelligence
Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control
Simiao Ren, Ankit Raj, Tommy Duong et al. (+6 more)
AI
agents that carry a multi-step computer task through on their own became ordinary tools in the past year, and the same autonomy is available to anyone whose task is harmful. We ask what that means for a relying party – an insurer, a lender, an auditor – whose evidence is a filed PDF. AgentForge-Bench measures how reliably an off-the-shelf coding
agent, driving one of seven open-weight models with a shell and the stock Python PDF stack, alters one dollar amount, date or address in a real filed financial document from a single sentence of intent, graded by rules rather than by a model. Across 1,750
cells, 1,419 (81.1%) satisfy the verifier, and 808 (46.2%) also survive every stricter filter: visible, localized, typeface-matched, original value gone document-wide. A deterministic script with no model in it solves 98 of the 125 documents; the
agents solve 124, and none the script solves alone.
Agents misreport 41% of their wrong edits as done, no model refused, and the cheapest verified forgery costs 2.4 cents. The raw rate overstates the threat by about a factor of two; the strict rate is still large.
Read the full abstract ▾
All authors Simiao Ren, Ankit Raj, Tommy Duong, Yuxin Zhang, Dennis Ng, Xingyu Shen, Kidus Zewde, Yuchen Zhou, Neo Tiangratanakul
Computation and Language
HaikuS2S: A Cascaded System For Responding In Verse
Devangi Sharma, Sophia Judicke, Glenda Tan et al. (+2 more)
Expressive
speech synthesis has advanced through prosody modeling, yet generating structured poetic
speech, such as haiku, remains challenging. Prior work on prosody transfer improves expressiveness, and fine-tuned poetry TTS (text-to-
speech) systems capture verse intonation. However, these models do not model haiku's 5-7-5 syllable structure or line-ending pauses. We present a cascaded system, HaikuS2S, combining ASR (automatic
speech recognition), LLM (large
language model)-generated haiku, and TTS fine-tuning on both prose and custom haiku
datasets. Our evaluation focuses on
emotion similarity,
speech quality, and prosody
alignment. In our experiments, we see that our prosody and tonal
alignment improve significantly with our fine-tuned systems, particularly the one trained on both general poetry and haiku. We also see that we maintain similar
emotion similarity scores across all systems.
Read the full abstract ▾
All authors Devangi Sharma, Sophia Judicke, Glenda Tan, Conrad Schaumburg, Shinji Watanabe
Computer Vision · Cross-listed from eess.IV
ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation
Omer Burak Demirel, Kelly K. Horst, Alessio Perazzolo et al. (+15 more)
Cardiovascular
magnetic resonance (CMR) provides comprehensive cardiac assessment but remains underutilized because of the complexity of acquisition, post-processing, and interpretation. Existing artificial intelligence (AI) methods address isolated tasks, limiting clinical integration. We present ORION-CMR (On-scanner Reporting with Integrated fOunda-tioN Model), the first clinically evaluated scanner-native end-to-end CMR foundation model. Pretrained on 12,896,733 CMR images from 9,258 studies, ORION-CMR performs sequence classification, ventricular function assessment, late gadolinium enhancement (LGE) detection, binary and multiclass disease classification, and local large
language model-based report generation in approximately 90 seconds. The framework. was evaluated on public
benchmarks and clinically validated in a multi-vendor cohort of 68 subjects with normal examinations, congenital heart disease, dilated cardiomyopathy, and myocardial infarction. ORION-CMR outperformed supervised baselines and the previously published CMR foundation model (CMR-FM), achieving state-of-the-art performance for LGE classification and scar
segmentation. Clinical evaluation achieved an AUC of 0.96 for normal-versus abnormal classification and 0.88 for multiclass disease classification, while generated reports demonstrated 81.4% agreement with expert interpretation. These results demonstrate the feasibility of real-time scanner-native AI-assisted CMR analysis and automated report generation.
Read the full abstract ▾
All authors Omer Burak Demirel, Kelly K. Horst, Alessio Perazzolo, Elisa Bruno, Kenan Kaya, Rongzhen Ouyang, Enas Ahmed, Jouke Smink, Spencer L. Waddle, Zainudeen Kallumpurath, Tzu Cheng Chao, Dinghui Wang, Steve G. Langer, Timothy L. Kline, Panagiotis Korfiatis, Jacinta Browne, Ivana Isgum, Tim Leiner
Data Structures and Algorithms
Optimal analysis of Greedy for stochastic online Euclidean matching: flat torus to the rescue
Mingwei Yang and Sophie H. Yu
We study online metric matching with $n$ servers and $n$ requests, all sampled independently and uniformly from $[0,1]^d$. We analyze the Greedy
algorithm, which matches each arriving request to its closest available server. Despite its strong empirical performance, non-trivial bounds on Greedy's competitive ratio were previously known only for $d = 1$, where it is $O(1)$-competitive [BFP23]. We prove that Greedy is $O(1)$-competitive for every fixed $d\geq3$ and has competitive ratio $\Theta(\sqrt{\log n})$ for $d=2$. Our proof first analyzes Greedy on the flat
torus and then transfers the resulting estimates to the cube.
Read the full abstract ▾
Artificial Intelligence
Echo State Network (ESN) for Signal Recovery in RF-Impaired IBFD MIMO Systems
Conrad Prisby, Siyao Li, Chengtao Xu et al. (+1 more)
In-band full-duplex (IBFD) multiple-input multiple-output (
MIMO) systems enable simultaneous transmission and reception on the same frequency band, improving spectral efficiency for next-generation wireless networks. However, IBFD-
MIMO systems are susceptible to self-interference (SI), which may overpower signals of interest (SOI). In this scenario, blind source separation (BSS)
algorithms can be adopted to remove SI and perform joint sensing and communication (JSAC), but BSS
algorithms mostly assume an idealized linear and quasi-stationary signal model, which does not hold under realistic
radio frequency (RF) impairments, such as I/Q imbalance, carrier frequency offset (CFO), phase noise, and power amplifier nonlinearity. This paper proposes a two-stage echo state network (ESN)-based scheme that is superior to BSS under these realistic conditions. A frozen ESN is trained offline to characterize the static SI path, while an adaptive ESN, updated online via recursive least squares, tracks the time-varying SOI path using sparse pilot symbols. We evaluate the proposed scheme's SOI recovery performance and acquisition speed with different block sizes, comparing it against other recurrent neural networks (RNN), such as long short-term
memory (LSTM) and gated recurrent unit (GRU). Simulation results show that the proposed approach outperforms BSS, LSTM, and GRU in both efficiency and SOI recovery, demonstrating the viability of ESNs for real-time, nonlinear self-interference cancellation in realistic IBFD
MIMO systems.
Read the full abstract ▾
All authors Conrad Prisby, Siyao Li, Chengtao Xu, Thomas Yang
Robotics
Topology-Informed Visual Prompting For Vision Language Action Policies
Haoyang Wu, Abhinav Kumar and Dmitry Berenson
Vision-
language-action (VLA) policies can struggle with manipulation tasks with complex obstacle geometries due to partial observability. These complex geometries can lead to similar visual observations or
robot configurations requiring qualitatively different actions, a distinction that can be quantified using topological signatures. While motion planners with full knowledge of environment geometries and object states can reason about these signatures in planning, this information is often not known at deployment. To address this issue, we present a
topology-guided visual-prompting framework that uses simulation-based planning to augment a nominal demonstration
dataset and provides
vision-based guidance at deployment. Our method uses a Gauss-Linking-Integral topological signature representation to capture important topological properties of the environment. Using privileged geometry information from a simulation approximation of our environment, we augment a VLA fine-tuning
dataset with trajectories that move the system to a demonstrated signature and, from the new configuration, resume task execution. A
vision-
language model (VLM) is fine-tuned on the same
dataset to both predict signatures from live camera observations and predict end-effector waypoints, which are rendered as visual
prompts on the observations to guide the VLA. Across three simulated bimanual tasks and a real-world box pickup task, our method outperforms a VLA fine-tuned only on nominal demonstrations and a VLM-prompting baseline that can remove
topology-relevant information from observations. On hardware, it exceeds the strongest baseline by 40% in task success. Project website: https://
topology-vla.github.io.
Read the full abstract ▾
Robotics
FinsSim: A Reality-Aligned Integrated Simulation Platform for Underwater Robot Learning
Yu Zhang, Yuanmingqing Song, Xiangyun Rao et al. (+4 more)
Underwater robot learning relies on simulators that integrate high-fidelity hydrodynamics, convenient learning interfaces, and a credible transition to real scenarios. In this work, we present FinsSim, a reality-aligned integrated simulation platform for Sim-to-Real
underwater robot learning. FinsSim first constructs high-fidelity simulation with selectable backends to adapt to diverse requirements. To facilitate
underwater robot research, it further offers standard control baselines, alongside with unified
robot learning workflows. For reliable Sim-to-Real transfer, FinsSim adopts a multi-sensor fusion scheme to provide low-cost yet precise localization. Moreover, it implements calibrated thruster-hydrodynamics models and a constrained wrench allocation
algorithm. Bridging these modules by ROS~2, FinsSim establishes a complete Sim-to-Real transfer pipeline. Through matched simulations and experiments, it is demonstrated that reliable Sim-to-Real transfer of
underwater robot control policies can be achieved with the FinsSim framework. Separate ablation studies also validate that the modules of FinsSim can address the pivotal issues of
underwater Sim-to-Real from different aspects. Overall, this work aims to bridge the gap between theoretical research and practical applications, ultimately driving advancements in the field of
underwater robotics.
Read the full abstract ▾
All authors Yu Zhang, Yuanmingqing Song, Xiangyun Rao, Pangkit Fong, Kunhao Zhang, Chongrong Fang, Jianping He
Computational Complexity · Cross-listed from quant-ph
Chaithanya Rayudu, Takahiro Misawa, Andrew Zhao et al. (+1 more)
Lee-Yang
theorems are a powerful tool for studying many-body systems, with applications ranging from analyzing phase transitions to proving the efficiency of certain classical and
quantum algorithms. In this work, we prove a Lee-Yang zero-freeness
theorem for the partition function of a broad class of interacting
fermion models, implying the existence of a provably efficient
quantum algorithm for estimating their ground-state energies. This class includes several well-known models such as the attractive Hubbard model, repulsive Hubbard model on bipartite graphs, and the interacting Hofstadter model. Our results also rigorously establish the nonexistence of phase transitions in these models in the presence of a nonzero local external field.
Read the full abstract ▾
All authors Chaithanya Rayudu, Takahiro Misawa, Andrew Zhao, Jun Takahashi
Computation and Language
XYEval: Agents say yes to bad advice
Zhengxuan Wu, Yuxuan Li, Oyvind Tafjord et al. (+1 more)
Effective communication between users and AI
agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where a person asks about their attempted solution rather than their actual problem. We extend prior sycophancy evaluation to the XY problem in agentic settings, evaluating whether
agents can resist plausible but misleading suggestions from users and communicate their
reasoning. We introduce XYEval, a meta-evaluation framework that can transform an existing
benchmark into an XY problem evaluation. We evaluate five models across six diverse
benchmark suites.
Agents suffer large XY drops under XY mutation across
benchmarks, with relative drops reaching up to 46.7%. With $\tau^2$-bench, we further show that
agent performance drops more when encountering a pedantic user who requires detailed explanations before approving a better solution. Our findings suggest that current
agents lack the ability to effectively reason and communicate when facing misleading suggestions. A simple system instruction baseline that encourages awareness of XY problems only offers partial mitigation. Extensive trace analyses provide behavioral insights into how and why these XY drops occur across execution trajectories. Our results show that mitigating the XY problem remains challenging, requiring
agents to both recognize user misdirection and clearly communicate the underlying problem.
Read the full abstract ▾
All authors Zhengxuan Wu, Yuxuan Li, Oyvind Tafjord, Been Kim
Machine Learning · Cross-listed from stat.ML
Sparse Regression Distilled from a Single Robust Fit
Wooyoung Shin and Seunghwan Park
Robust linear fits can resist response contamination yet remain too dense or unstable for useful global explanations. We propose penalized
distillation, which fits a smoothly clipped absolute deviation (SCAD)
estimator to a robust initial
estimator's empirical fitted surface along a safeguarded coordinate-descent path and evaluates candidate states separately for fidelity, parsimony, perturbation stability, and held-out prediction. The new results attach to the states the
algorithm actually computes. Conditional on a fixed uncontaminated design, deterministic bounds transfer response-replacement boundedness from the initial fit to every retained path state. Turning to fixed dimension, we characterize the oracle-support branch by its empirical-Gram projection and influence function, give conditions for covariance-weighted least-squares approximation equivalence, and establish a path-conditional generalized information criterion. By contrast, at large dimension-to-sample ratios the full-coordinate robust fit collapses without warning, and screening restores the construction. Under a sure-screening framework, the robustness bound and the support and selection guarantees transfer to the screened fit. Simulations separate robustness transfer from support recovery, efficiency, and computation across the dimension-to-sample ratio, with p up to 240, and the signal density, which isolates what the sparse stage adds once the screen over-selects. In a duplicate-grouped superconductivity study, the distilled
estimator remains predictively stable under prespecified training-response shifts but retains 66.8–68.8 of 81 slopes. Stronger sparsification reduces the model to 12.6–14.0 slopes only at visible fidelity and prediction cost.
Distillation therefore preserves predictive stability on these data without substantiating a compact coordinate-level explanation.
Read the full abstract ▾
Human-Computer Interaction
Think Before You Accept: Can Written Justification Reduce Uncritical Uptake of AI Writing Suggestions?
Yan Tao, Jennifer Meyer and Rene F. Kizilcec
Generative AI can offer students useful feedback, but its value depends on judging which suggestions are accurate and relevant. Prior research shows that strategic friction during human-AI interactions can promote critical uptake, but how to effectively implement such friction in academic contexts remains unclear. We examine whether requiring students to justify decisions to accept or reject AI suggestions can mitigate uncritical uptake in academic writing. In a randomized experiment embedded in a course activity (N=129), students wrote a data analysis proposal, received mixed-quality AI revision suggestions, and decided whether to accept or reject them. Students required to provide written justifications were 24 percentage points less likely to adopt flawed suggestions (65% vs. 41%), with no reduction in acceptance of sound suggestions (81% vs. 86%). However, thematic analysis revealed superficial engagement in the justification task and gaps in metacognitive monitoring and domain knowledge.
Read the full abstract ▾
Computation and Language
Measuring the Assistant's Harmlessness Preferences on the User Turn
Jord Nguyen
Post-training turns a general next-
token predictor into a chat model with a persistent assistant persona. If that persona is a character the model plays only on its own turns, its preferences should govern what the assistant says, not what the model predicts other speakers will say. We test this boundary and find that it does not hold: a safety-relevant preference of the assistant—for harmless over harmful tasks—shapes the model's predictions even on the user's turn, where the assistant is not the one speaking. We find that this preference is small or near-zero in pretrained base models, that it emerges through post-training, replicated across open-weight model families, grows with scale, and can be moved by narrow finetuning that never touches user turns. We claim that this is evidence that post-training does not merely install a shallow assistant persona, but instead generalises beyond just the local assistant turn, into the model's representation of the user.
Read the full abstract ▾
Machine Learning
The Neural Forcing for Three-Dimensional Incompressible Navier-Stokes finite time blowup
Beibei Li
We present a two-part neural framework for forced three-dimensional incompressible Navier–Stokes flow. Part~I develops the computational forcing system. A physics-informed neural model generates structured external-force trajectories, candidates are optimized through differentiable PDE rollouts or PPO-Clip, and selected forcings are frozen and checked by independent fixed-force replay. Part~II provides the mathematical certification layer. It separates neural candidate discovery from continuum analysis, derives integrated reciprocal-vorticity criteria that imply Riccati-type growth and finite-time loss of smooth continuation, develops a validated computational-to-continuum transfer strategy, and establishes a conditional positive-probability closure for a nondegenerate neural output law. The proof is complete at the continuum level.
Read the full abstract ▾
Systems and Control
On sparsity and directional forgetting in adaptive control
Tochukwu E. Ogri, Trivikram Satharasi, Muzaffar Qureshi et al. (+2 more)
This paper develops a sparsity-promoting
memory regressor extension (MRE) adaptation law with directional forgetting for nonlinear control-affine systems with linearly parameterized uncertainty. The objective is to use directional forgetting to selectively discount obsolete information and leverage $\ell_1$ regularization to promote sparsity of the parameter estimates. While $\ell_1$ regularization has been applied to the system identification problem in an offline setting, a contribution of this paper is to develop a recursive least squares update law to implement $\ell_1$ regularization in online adaptive control. In particular, we show that $\ell_1$-regularized recursive least squares is realized via a sliding mode update law. A nonsmooth Lyapunov-based stability analysis is then used to show that the tracking and parameter estimation errors are ultimately bounded under a subspace excitation condition. Simulation results on a Van der Pol oscillator demonstrate the ability of the developed sparsity-promoting MRE controller to recover sparse dynamics while maintaining stable tracking.
Read the full abstract ▾
All authors Tochukwu E. Ogri, Trivikram Satharasi, Muzaffar Qureshi, Kyle Volle, Rushikesh Kamalapurkar
Robotics
MR-SPITE: Accelerating Multi-Robot Conflict Scans via Hierarchical Swept-Volume Approximations
Marta Markowicz, James Motes, Marco Morales et al. (+1 more)
Conflict scanning over synchronized
robot paths requires detailed collision checking, potentially across every
robot pair at every timestep, and may be repeated many times as conflicts are repaired. We present Multi-
Robot SPITE (MR-SPITE), a conservative, motion-segment-based filter for accelerating these scans. MR-SPITE partitions each path into temporal intervals and assigns conservative bounds to each segment. An interval scheduler compares bounds for temporally overlapping motions: disjoint bounds certify the shared window as conflict-free, while unresolved windows are passed to the underlying collision checker. We integrate MR-SPITE into ARC and combine it with VAMP-based collision checking. For 16 Fetch
robots, ARC with MR-SPITE achieves a paired median conflict scan speedup of 7.18x and reduces median planning time by 57% relative to the baseline ARC implementation with PRM+VAMP. These results demonstrate that motion-segment bounds complement configuration-level collision acceleration while preserving the behavior of the underlying discretized scanner.
Read the full abstract ▾
All authors Marta Markowicz, James Motes, Marco Morales, Nancy Amato
Numerical Analysis
Time-uniform accuracy of ensemble Kalman filters with localization
Xiaoou Cheng, Daniel Sanz-Alonso and Nathan Waniorek
This paper establishes time-uniform accuracy guarantees for deterministic square-root ensemble Kalman filters in linear–Gaussian state-space models under perfect-model dynamics. For
hyperbolic, detectable systems, we prove that the ensemble means and covariances approximate their Kalman filter counterparts uniformly in time, with high probability and without inflation or resampling. The required ensemble size depends on the effective rank of the initial covariance and the dimension of the unstable subspace, rather than on the ambient state dimension. We also analyze a localized square-root ensemble Kalman filter for weakly coupled spatial systems. We show that the stabilizing Kalman covariance inherits spatial decay from the dynamics and derive accuracy bounds that separate sampling error from localization bias. For the localized filter, the required ensemble size depends on the local intrinsic dimension and only logarithmically on the number of spatial blocks, while the localization bias scales with the interaction strength. Our analysis combines stability and forgetting for possibly singular Riccati recursions, nonasymptotic covariance concentration, and perturbation estimates for localized covariance dynamics.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Density-Ratio Rescoring for Imbalanced Classification Using Raking Duals and Classifier Scores
Dongha Kim and Seunghwan Park
Density-Ratio Rescoring (DRR) augments a classifier trained at the original class prior with a survey-raking dual score. Raking reweights the majority sample to match minority feature moments within a tolerance. DRR marginally standardizes the dual and base scores and combines them with a fixed weight of one half, using the fitted dual directly for prediction without resampling or refitting the base classifier. Under exact population matching and a correctly specified log-linear tilt model, the dual equals the log density ratio up to an additive constant. A class-separation analysis characterizes the signal strength and correlation conditions under which fusion improves separation under common within-class covariance. On 24 tabular
benchmarks, evaluated over 30 trials and five base learners, DRR at the D=128 random-feature setting improves average precision over the standardized base on every
dataset, with a mean gain of 0.034. It exceeds the shared-dual raking-and-relabeling resampler on 22 of 24
datasets, with a mean gain of $0.092$, and on all eight one-versus-rest tasks of a shared gene-expression cohort. These results demonstrate the effectiveness of using raking duals as reusable scores for improving rare-class ranking while retaining classifiers trained at the original prior.
Read the full abstract ▾
Software Engineering
MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development
Yingxuan Yang, Jiaqi Liu, Lirui Guan et al. (+4 more)
We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, and runtime wiring. In this setting, correctness depends on cross-layer consistency: a workflow may be structurally plausible, yet still fail because tool implementations, schema bindings, or runtime execution do not align. Existing
benchmarks largely evaluate these capabilities in isolation or rely on trajectory-level proxies, leaving open whether generated workflow artifacts execute end-to-end. We introduce MCPGen, an executable
benchmark for Model Context Protocol (MCP) workflow development. MCPGen contains 100 self-contained MCP projects across 16 application domains and evaluates three diagnostic tasks: workflow reconstruction, tool creation, and backward-compatible workflow extension. We evaluate 11 representative LLMs in a single-turn foundation-model setting, assessing generated artifacts through static analysis, unit and integration tests, and process-isolated end-to-end execution. Models reach 88.5% on workflow reconstruction, but no model exceeds 57% end-to-end execution success. Per-tool unit-test pass rates reach 63.8%, while project-level integration success does not exceed 45%, suggesting that integration remains a major bottleneck even when isolated tool tests pass.
Read the full abstract ▾
All authors Yingxuan Yang, Jiaqi Liu, Lirui Guan, Jiaye Gao, Weiwen Liu, Weinan Zhang, Ying Wen
Machine Learning
Matched-Input Estimates Differ in Sign Across Architectures: Auditing EEG Foundation Models on Motor Imagery
Kevin Zhou and Sparsh Roy
Pretrained
EEG foundation models are increasingly proposed as general-purpose encoders for
brain-computer interfaces, yet recent
benchmarks disagree about when their representations transfer to downstream tasks. We audit LaBraM and CBraMod on motor imagery under a validation-locked protocol in which preprocessing, architecture, optimization, freeze depth, checkpoint, temperature, and method selection are determined using training-session data only. On four-class BCI Competition IV-2a, every supervised comparator evaluated here outperforms every foundation-model configuration, including validation-selected fine-tuning. We then examine a key confound: foundation models and task-specific decoders are normally evaluated using different input pipelines. Retraining three supervised architectures on the broadband arrays consumed by the foundation models produces matched-input accuracy differences of opposite sign across architectures: broadband input improves ATCNet by 0.078 accuracy while reducing
EEG Conformer accuracy by 0.088. None of the three individual matched-input terms is significant after multiple-comparison correction at n = 9, so we treat the sign variation descriptively rather than as a formal architecture-by-pipeline interaction. These observed sign differences suggest that a single comparator may not provide an architecture-invariant decomposition of a pretrained-versus-supervised performance gap. The four-class deficit also does not reproduce uniformly across motor-imagery
datasets: on two-class BNCI2014-004 we cannot detect the same separation between fine-tuned CBraMod and the supervised comparators. Finally, validation-fitted temperature scaling returns foundation-model calibration error to the supervised range despite substantially lower four-class accuracy.
Read the full abstract ▾
Information Theory · Cross-listed from math.CO
Rényi stability of $B_h$ sets: a two-order phase diagram and sharp deletion principles
Jae Oh Woo
A set $B$ in an abelian group is a $B_h$ set if every $h$-term sum has a unique representation up to permutation; for $h=2$ these are the Sidon sets. We study a weighted removal problem for this collision-free property: if the $h$-fold sum map has small Rényi
entropy loss, how much probability mass must be deleted so that the remaining support is a $B_h$ set? Two Rényi orders arise: $\alpha$ is the order at which the coarsening loss is measured, whereas $\beta$ is the order of the
entropy constraint. The diagonal specialization $\beta=\alpha$ ties the two roles together. We determine the resulting stability problem on the positive $(\alpha,\beta)$-quadrant. Stability holds exactly when $\beta\le1$ and $\alpha\ge\beta$. Inside this region the optimal deletion rate is
polynomial for $\beta<1$ and logarithmic on the boundary $\beta=1$, where the leading constant is exact; outside it, stability fails through two distinct mechanisms: a supercritical budget and dilution by light atoms. In both unstable regimes the limiting defect is computed exactly. The upper bounds follow from a coarsening inequality with best possible constant, which also yields an
entropy-free removal
theorem, a finite combinatorial consequence for moments of the representation function, and extensions to $B_h[g]$ sets. Matching constructions show that the phase boundaries and rates are sharp.
Read the full abstract ▾
Computer Vision · Cross-listed from eess.IV
VGG16-MCA UNet: Whole-Tumor Segmentation in 2D FLAIR MRI with Decoder-Side Channel Attention
Shubham Gajjar, Deep Joshi, Avi Poptani et al. (+1 more)
Automated
brain tumor
segmentation supports diagnosis, treatment planning, and monitoring of disease progression, but building models that generalize across heterogeneous tumors and limited annotated data remains difficult. We present VGG16-MCA UNet, a hybrid architecture pairing an ImageNet-pretrained VGG16 encoder with a decoder in which a Multi-Channel
Attention (MCA) module recalibrates features after each skip-connection fusion, trained with the Focal Tversky loss to counter severe foreground-background imbalance. We evaluate the model as a 2D, FLAIR-only, whole-tumor segmenter on tumor-positive slices from two public
datasets: the BraTS 2020
benchmark and the LGG MRI
Segmentation dataset. Using 5-fold cross-validation and a single network formed by averaging the weights of the five fold models, the method attains an aggregate pixel-level Dice (F1) of 95.10% on our held-out BraTS 2020 split and 88.32% on LGG. These scores are computed over all test pixels pooled into a single confusion
matrix rather than averaged per case, and are therefore not directly comparable to the per-case mean Dice used in the BraTS challenge protocol. All partitions were drawn over individual slices rather than over patients, so every patient contributes slices to both training and test; the figures above therefore measure interpolation within known patients and should be read as an upper bound rather than as generalization to new ones. The model segments a 256x256 slice in 66.32 ms on a single 6 GB NVIDIA RTX 2060, approximately 8 ms more than an equivalent VGG16-UNet without MCA. We release the split records and report the protocol in full, with the aim of providing a precisely specified and reproducible 2D FLAIR baseline.
Read the full abstract ▾
All authors Shubham Gajjar, Deep Joshi, Avi Poptani, Vishal Barot
Systems and Control
Quasi-Static Fault-Tolerant Feedback Control of a Quadrotor under Rotor Failure with Provable Safety Guarantees
Mohamed Al Lawati and Adeel Akhtar
This paper presents a nonlinear control law for a quadrotor unmanned aerial vehicle (
UAV) under single-rotor failure that guarantees set stabilization via quasi-static feedback (QSF). Given a
geometric curve in three-dimensional space, we characterize and stabilize the zero-dynamics
manifold, also known as the path-following
manifold, which represents all feasible motions along the path. Stabilizing this
manifold ensures path-invariance: a
UAV with a failed rotor initialized on the path with an appropriate orientation remains on the path for all future time. Furthermore, local exponential convergence to the
manifold is guaranteed under certain conditions, implying that, under the stated assumptions, rotor failure during flight does not cause transverse deviation from the path. The proposed controller thus provides theoretical safety guarantees, which are validated through numerical experiments in the Drake physics-based simulation engine. The code is publicly available at https://gradslab.github.io/quasistatic-ftc/.
Read the full abstract ▾
Artificial Intelligence
Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer
David Litman
Chess involves complex
reasoning in a deterministic environment, which makes it a useful setting for studying the mechanisms of computation inside
transformers. The Maia-3 chess
transformer takes Elo, a measure of competitive chess skill, as an input to the pre-trained network, so we can vary the skill the network is conditioned on with no change to its weights. Here we investigate how turning this skill dial affects self-
attention. Ablating every
attention head at every Elo from 700 to 2500, we find 1) increasing skill pushes the causal center of mass of the computation deeper, monotonically, for every chess piece and move type we measured; 2) the depth migration is much greater for specific tactics, especially knight forks, than for other move types; 3) the migration consists of deeper heads getting recruited for more specialized computations while one shared shallow head keeps a roughly constant contribution. These results may shed light on how conditioning inputs redistribute computation in larger
transformers.
Read the full abstract ▾
Computation and Language
Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
F{\i}rat Öncel, Salman Hussain Ali, Mirco Ravanelli et al. (+2 more)
Large
language models (LLMs) drift out of date the moment their pretraining ends, yet retraining from scratch is prohibitively expensive. Continued pretraining (CPT) is the natural remedy, but it is typically evaluated through a continual learning lens that assumes disjoint data streams. This is a poor fit for time-incremental updates on web-scale crawls, where successive snapshots share substantial URL overlap by design. We study time-incremental CPT in this realistic regime: continued pretraining on FineWeb-Edu dumps drawn strictly from after each model's knowledge cutoff, evaluated across six open-weight models spanning three families (OLMo2, Llama-3.1/3.2, Gemma-3-1B) and four parameter scales (1B-3B-7B-8B). We organize our findings around four practical questions. (i) Is knowledge acquired? Yes, but heterogeneously, and without catastrophic forgetting: five of six models also improve on pre-cutoff factual recall, and the gains track pretraining saturation (driven primarily by
token budget per parameter). (ii) What does it cost? Almost nothing: the macro-average across a thirteen-task suite stays within 0.01 of the base for every model. (iii) What is the recipe? Data quality dominates quantity (a curated 6B-
token slice matches a broader 40B one); the optima for knowledge acquisition and general capability are separated by roughly an order of magnitude in learning rate; and LoRA at sufficient rank matches full CPT. (iv) Does it survive deployment? CPT gains transfer through SFT, while DPO's effect is family-dependent. Together, these results paint a more optimistic picture of time-incremental CPT than the prior continual learning literature suggests.
Read the full abstract ▾
All authors F{\i}rat Öncel, Salman Hussain Ali, Mirco Ravanelli, Cem Subakan, Çağatay Y{\i}ld{\i}z