Robotics
Fast Generative Grasping via Lie Group-Constrained MeanFlow
S. Talha Bukhari, Yi Wei, Ruiqi Ni et al. (+2 more)
Grasp synthesis is a core task in robotic manipulation, for which the solution typically forms a
multimodal distribution rather than a point estimate. Generative robotic grasping aims to learn this distribution with deep generative models such as
diffusion and flow-based approaches. The iterative nature of such generative models makes them flexible and generalizable; however, multi-step sampling impedes the time-critical operation required in robotics. We devise an approach to fast generative grasping based on MeanFlow on the product Lie group $\mathcal{G} = \mathrm{SO}(3) \times \mathbb{R}^3$. The training objective couples a purely algebraic
semigroup consistency condition with Riemannian Conditional Flow Matching on $\mathcal{G}$ that anchors the average velocity to the data distribution. The resulting Lie Group-constrained MeanFlow formulation samples reliable grasps in $\leq 5$ network evaluations, matching the grasp generation performance of state-of-the-art
diffusion and flow-based models on the ACRONYM
dataset at millisecond-scale inference latency (up to $39\times$ speed-up). We further demonstrate that the approach directly translates to real-world robotic grasping without additional training or domain adaptation, exhibiting robust grasp synthesis under observation noise.
Read the full abstract ▾
All authors S. Talha Bukhari, Yi Wei, Ruiqi Ni, Zachary Kingston, Aniket Bera
Social and Information Networks
Epistemic Networks, Collective Misperception, and the Manipulation of Social Knowledge
Mihnea C. Moldoveanu and Joel A.C. Baum
We investigate the structure of interactive beliefs in networks: the epistemic state in which
agents hold, revise, and act on their models of the epistemic states of other
agents. What a group believes depends on what each member
agent takes the others to believe, and on what each takes the others to believe about still others. We posit that the proper unit of social-epistemic analysis is not the individual belief but the tensor of mutual attribution, the array that records what every
agent takes every
agent to believe. We separate three layers of this object: what is privately held, what is publicly expressed, and what is to be believed by others. Social belief evolves by contraction of the tensor against a signed
matrix of epistemic influence. Collective misperception decomposes exactly into a component that observation dissolves and a component that observation cannot touch. Social conformity amplifies pluralistic ignorance without generating it. The stable forms of collective epistemic consensus, polarization, entrenched misperception, and instability are spectral regimes of a single operator. Higher-order belief reduces to walks in the epistemic network, under a stated assumption of cognitive consistency whose boundary we mark precisely.
Read the full abstract ▾
Robotics
Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving
Cong Xu and Ravi Sankar
Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in which a
language-guided intent module reads structured descriptors, computes a smoothed intent-geometry divergence score, and gates the planned maneuver before commitment, upstream of a corridor envelope. On a replayed off-road departure and four crash clips under a frozen, disclosed implementation, gating is the only layer that repairs the plan: on the main case it fires 72 ms after the drift onset but 161 ms before the corridor exit, keeping the trajectory in the corridor in all ten replays. The first calibration draws nine false triggers in 5.9 minutes, each from scoring uncertainty as half a conflict; a preregistered redesign treating uncertainty as abstention cuts this to 0.341 per minute. Two ablations bound the model's contribution: the full score detects fastest on four of five failures under the deployed eligibility, three of five against the unvetoed rule (000871 by one cycle; 000228 by a pre-onset fire on an uncertain stretch that five clips cannot classify as signal or coincidence; dropping the confidence term costs two detections), while on in-domain tracks at equal false positives the
geometric rule more than triples its detection. The evidence supports the gating mechanism; the model's demonstrated roles are the fastest detection on these failures and an uncertainty veto on the
geometric rule.
Read the full abstract ▾
Cryptography and Security
From Fleet to Lab: Revisiting the Security and Complexity of Industrial Rowhammer Mitigation
Hritvik Taneja and Moinuddin Qureshi
This paper studies efficient and secure Rowhammer mitigation at the
Memory-Controller (MC). Rowhammer mitigation faces a fundamental tradeoff between tracking storage and mitigation rate: precise trackers (such as Misra-Gries) avoid unnecessary mitigations but require large CAM structures, whereas sampling-based schemes (such as PARA) require no storage but incur frequent mitigations even when not under attack. Microsoft recently deployed Sigries, an MC-side Rowhammer defense that combines an under-provisioned Misra-Gries tracker with a row-sampling fallback, in its Azure Cobalt 200 SoC. Sigries observed that the tracker-to-sampling transition can be insecure, and claimed the reverse transition is always safe. Our analysis shows that this transition is also vulnerable, and a Round-Robin Attack across sub-banks reduces the MTTF of Sigries to about 1 second, 8 orders of magnitude below the 13 years with PARA. Sigries also suffers from CAM complexity and high storage overheads. Our proposal, FiRM (Filtered Rowhammer Mitigation), is based on the insight that, for a secure design, the tracking-mode and sampling-mode should not be configured independently but co-designed to ensure the system remains secure not only in both modes but also during transitions. FiRM incurs zero slowdown for benign workloads, since they do not exceed the filtering threshold, and also replaces the complex CAM-based tracker with simple SRAM filters. To handle stressful patterns, we propose FiRM-P (probabilistic) and FiRM-D (deterministic). FiRM-P uses varying probabilities during transitions and steady state to ensure both security and low performance overhead. FiRM-D provides guaranteed deterministic security by modulating the rate of mitigation. Both FiRM-P and FiRM-D have less storage overhead than Sigries. Our paper shows that a principled approach can avoid both the insecurity and the complexity of Sigries.
Read the full abstract ▾
Computation and Language
Prefix Sliding for efficient test-time scaling
Niklas Muennighoff, Zhengyang Wang, Zeyi Chen et al. (+15 more)
Test-time scaling uses extra test-time compute to improve performance, such as letting
language models reason longer when solving a problem. As models keep the entire
reasoning trace in
memory via full
attention, hard tasks that need long thinking can be prohibitively expensive. However, we find most intermediate
reasoning tokens lose importance as the model continues
reasoning. This calls into question whether retaining them is worth the cost. Based on this insight, we propose Prefix Sliding, which discards
tokens during
reasoning that are not part of the prefix or the window of the last few thousand
tokens. The prefix has key instructions and tools available to the model, while the most recent
tokens are the current
reasoning the model is working on. This caps the total
memory requirement regardless of how long the model reasons, allowing for efficient long-horizon test-time scaling. Without training, Prefix Sliding can make existing models 3x faster while maintaining performance. Training with Prefix Sliding using reinforcement learning can achieve better performance by enabling scaling to
reasoning traces beyond a hundred thousand
tokens. Ablations show Prefix Sliding outperforms summarizing intermediate
tokens or vanilla sliding window. Our code is at https://github.com/Muennighoff/prefix-sliding
Read the full abstract ▾
All authors Niklas Muennighoff, Zhengyang Wang, Zeyi Chen, Weijia Shi, Binyuan Hui, John Yang, Dapeng Jiang, Mika Senghaas, Fares Obeid, Johannes Hagemann, Sami Jaghouar, Ludwig Schmidt, Percy Liang, Jason Wei, Andrew Y. Ng, Luke Zettlemoyer, Yejin Choi, Mike Lewis
Machine Learning
Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
Hao Luo, Yiting Yang, Wenyi Zhao et al. (+10 more)
Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in
vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment. While existing efficient architectures adopt parameter-efficient depthwise separable convolution backbones that leverage techniques like low-rank approximation and weight sharing to compress depthwise convolutions, we identify a critical oversight: pointwise convolutions dominate parameter volume (>87% in models like RepLKNet-31B) and constitute the primary deployment bottleneck on resource-constrained edge devices. This results in prohibitive storage costs and severe
memory-loading constraints on resource-limited devices (e.g., smartphones with 4-12 GB Random Access
Memory (RAM)). To overcome this, we propose Channel Group-Shared (CGS) low-rank approximation, a novel Singular Value Decomposition (SVD)-based parameter-sharing strategy. CGS constructs a structured low-rank paradigm isomorphic to SVD decomposition, comprising shared (high-parameter-cost) down/up-projection
matrices across channel groups within a layer and channel-group-specific (low-parameter-cost) scalable diagonal
matrices. This group-sharing design achieves significant parameter reduction. Extensive experiments demonstrate that large-kernel CNNs (RepLKNet, ConvNeXt, SLaK) enhanced with CGS strike an empirically favorable balance between competitive performance and substantially reduced storage costs. Crucially, by alleviating storage constraints, reducing
memory bandwidth pressure during loading, and minimizing model loading latency, CGS enables the feasible deployment of pre-trained large-kernel CNN models on edge devices, thereby bridging the gap between high-performance
vision models and practical edge deployment.
Read the full abstract ▾
All authors Hao Luo, Yiting Yang, Wenyi Zhao, Man Jiang, Zhijun Lin, Ghulam Mohiuddin, Ting Jiang, Kunming Luo, Zihao Zhang, Qingsen Yan, Guoqing Wang, Wei Dong, Peng Wang
Computer Vision
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Zhe Liu, Jinghua Hou, Yuxiang Lu et al. (+7 more)
Vision-
Language-Action (VLA) models have demonstrated effectiveness in
robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to retain past observations and develop precise spatial perception. In this paper, we propose StreamPI, a streaming
multimodal temporal modeling framework that equips single-frame VLA with temporal
reasoning capability without introducing any additional parameters. One core design is instruction-anchored temporal modeling. It treats each (visual observation,
language instruction) pair as an atomic temporal unit: bidirectional
attention within each pair enables cross-modal fusion, while causal
attention across pairs preserves autoregressive streaming inference. This ensures the
language instruction serves as a persistent semantic anchor throughout task execution. To bridge the gap between synchronous training and asynchronous real-
robot deployment, we introduce a andom-interval streaming training strategy: a proper inter-frame interval (e.g., every 3 frames) enables faster and smoother action execution. Beyond this, randomizing the interval further improves robustness to frame-timing perturbations, supporting asynchronous deployment in practice. Furthermore, by leveraging the length extrapolation capability of the LLM backbone, StreamPI seamlessly inherits pretrained single-frame weights and supports flexible single-frame and multi-frame inference. Experiments on real-
robot tasks spanning
memory-dependent and precise perception scenarios, as well as the simulation
benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
Read the full abstract ▾
All authors Zhe Liu, Jinghua Hou, Yuxiang Lu, Zhenya Yang, Xianzhe Fan, Junwei Luo, Junyi Li, Ruihua Han, Zhi Hou, Hengshuang Zhao
Robotics
VirTooS: A ROS 2 - Unity Virtualization Toolkit for Fleet Management of Autonomous Mobile Robots
Andrea Drudi, Lorenzo Pichierri, Andrea Testa et al. (+1 more)
In this paper, we present VirTooS, a Python/C# toolkit designed to implement fleet-management tasks on teams of Autonomous Mobile
Robots (AMRs). VirTooS leverages the
Robot Operating System (ROS) 2 and Unity game engine to provide realistic, scalable virtual experiments in a mixed-reality environment. The toolbox allows users to easily generate and customize virtual scenarios for realistic simulations. Virtual and real sensors as, e.g.,
LiDARs, can be exploited to map and safely navigate in the mixed-reality environment. To enable distributed robotics experiments, we propose a set of tailored routines leveraging the ChoiRbot framework. As a motivating example, we show a set of experiments for task assignment problems in a virtual environment, allowing seamless interaction among real and virtual
robots. Moreover, the package comes with a containerized suite to easily deploy it on different machines. The source code will be made publicly available on GitHub.
Read the full abstract ▾
All authors Andrea Drudi, Lorenzo Pichierri, Andrea Testa, Giuseppe Notarstefano
Computation and Language
Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study
Leonardo Duart, Tiago Fonseca and Thiago Chacón
Automatic
Speech Recognition (ASR) technologies have achieved remarkable performance in recent years through the use of large
multilingual foundation models. However, most advances remain concentrated on high-resource
languages, while indigenous
languages continue to suffer from a lack of
speech resources and
language technologies. This work presents a preliminary study on the adaptation of Whisper for Automatic
Speech Recognition in Baniwa, an indigenous Arawakan
language spoken in Brazil, Colombia, and Venezuela. The experiments were conducted using a corpus of 1,373 manually transcribed recordings obtained from a linguistic documentation project. The corpus contains approximately 0.54 hours of
speech and consists primarily of isolated words and short elicited utterances. The Whisper Small model was fine-tuned using supervised learning and evaluated using Word Error Rate (WER) and Character Error Rate (CER). The best model achieved a WER of 37.5% and a CER of 7.45%, demonstrating that
multilingual foundation models can be successfully adapted to extremely low-resource indigenous
languages. The results establish an initial baseline for Baniwa Automatic
Speech Recognition and provide a foundation for future research involving larger
datasets,
language-specific adaptation strategies, and post-processing techniques.
Read the full abstract ▾
Robotics
One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation
Xiaomi Embodied Intelligence Team, University of Macau: Shaoqing Xu, Fang Li et al. (+19 more)
Scaling generalist
vision-
language-action (VLA) policies is severely bottlenecked by the inherent heterogeneity of
embodied data, which spans diverse
robot morphologies, camera configurations, and low-level action spaces. Existing paradigms typically address this mismatch through explicit action retargeting, human-to-
robot video synthesis, or
dataset-specific adaptation branches, fundamentally hindering the joint learning of a unified policy. We introduce UCAG-P, a camera-centric unified action formulation that structurally aligns heterogeneous
embodied datasets into a shared
geometric action space. Rather than treating
robot-specific commands as the shared policy target, UCAG-P represents manipulation through camera-observable anchor motion in image and camera-frame coordinates, treating
robot arms,
humanoids, and human hands as different embodiments of a common action schema. A geometry-conditioned action translator combines predicted motion with target-embodiment kinematics to produce executable controls. The resulting decoupled architecture allows a shared VLA policy to learn transferable manipulation geometry while retaining embodiment-specific controllability. UCAG-P is trained on 4.03K hours of
robot and simulation data and 2.34K hours of human demonstrations. A single checkpoint reaches 98.3% on LIBERO, 88.7% and 89.2% on RoboTwin Easy and Hard, 82.0% zero-shot on LIBERO-Plus, and 62.0% on RoboCasa GR-1, without
benchmark-specific fine-tuning.
Read the full abstract ▾
All authors Xiaomi Embodied Intelligence Team, University of Macau: Shaoqing Xu, Fang Li, Guozhi Zhan, Zhixiang Duan, Yuhan Wang, Yuechen Luo, Shengyin Jiang, Hanbing Li, Zhiying Du, Longlong Wang, Longmei Jiang, Weixiang Liang, Ying Gong, Yong Pan, Ziping Zhao, Zhiyuan Chen, Yangwei You, Kun Ma, Qinyuan Liu, Hangjun Ye, Zhi-xin Yang
Computers and Society
Giving Mechanical Engineers Intelligent Tools: A Project-Based AI Education Curriculum in Thermal Engineering
Changgen Li, Han Hu, Christy Dunlap et al. (+2 more)
Mechanical engineering (ME) requires a broad knowledge base across several disciplines. However, ME students often have insufficient training in electrical and computer engineering, complex challenges in traditional thermal system modeling, and endure heavy course loads with limited class hours. To help address these challenges, this paper proposes a new curriculum that integrates artificial intelligence (AI) into ME at the University of Arkansas (UARK), with a particular emphasis on thermal problems and their interplay with electrical and computer engineering. The curriculum has introductory, application, and advanced levels, covering core and optional AI projects. Key goals are to enhance students' understanding of AI models, ability to tackle engineering tasks, and teach multidisciplinary communication skills. This curriculum offers educators and researchers valuable insights into courses that can enhance students' practical skills and creativity. This curriculum, including the syllabus, data, and codes, is available to the public in open-access repositories.
Read the full abstract ▾
All authors Changgen Li, Han Hu, Christy Dunlap, Nathaniel House, Jonathan Wai
Robotics
$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning
Lehong Wu, Yuxiao Qu, Zheyuan Hu et al. (+4 more)
Reasoning in
language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whether this mechanism can improve robotic manipulation remains unclear, where long-horizon tasks require tracking partial progress,
reasoning about object relations, recovering from mistakes, and steering noisy low-level policies. In this paper, we study whether VLMs can be trained to reason directly in natural
language to guide low-level manipulation policies. We introduce $R^3$, a simple post-training recipe that turns off-the-shelf VLMs into robotic reasoners: it first mid-trains a VLM on expert-generated
reasoning traces to initialize the desired
reasoning style, then improves the reasoner with single-step rubric-based RL from offline action data. Unlike prior robotic
reasoning methods that mostly use structured traces as auxiliary supervision, $R^3$ trains free-form
language reasoning to produce test-time guidance for action. We instantiate $R^3$ on
Language Table and simulated bimanual grocery packing, two controlled testbeds for studying robotic
reasoning and long-horizon manipulation. $R^3$ improves exploration and generalization across unseen tasks and significantly outperforms instruction-only imitation learning baselines on both
benchmarks. Our analyses suggest that free-form
language reasoning can function as a test-time compute mechanism for steering low-level policies. Our project page is available at https://robotic-reasoner.github.io/.
Read the full abstract ▾
All authors Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang, Limin Wei, Zackory Erickson, Aviral Kumar
Machine Learning
How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attention
Gerard Conangla Planes
Choosing the rank of a low-rank adaptation (LoRA) update is usually an empirical task. In this paper, we provide a task-dependent theory of the approximation error achievable at each LoRA rank for
Transformer attention. We fix a pretrained
attention head, a target
attention function, and a distribution over inputs from the downstream task, and bound the smallest expected Kullback–Leibler (KL) error achievable by a rank-$r$ query LoRA update. When target
attention probabilities are bounded away from zero, we prove a lower bound of the error proportional to $\psi(\|d\|_2)$, where $d$ is the difference between candidate and target
attention scores and $\psi(t)=\min\{t^2,t\}$. We also prove an unconditional upper bound $\min\{\|d\|_2^2/4,\sqrt2\|d\|_2\}$. Under explicit realizability, geometry, and moment conditions, we then bound the best rank-$r$ error between an explicit multiple of $\psi(\sqrt{T_r})$ and $\min\{T_r/4,\sqrt{2T_r}\}$, where $T_r$ is the downstream-weighted tail energy of the target update. We also provide target-Fisher bounds when candidate scores remain within a fixed range of the target scores, and an unrestricted lower bound when a subset of
tokens carries most of the probability mass. These spectral bounds describe finite-score approximation. We then construct explicit families in which softmax saturation makes the rank required to match the
attention function strictly smaller than the rank required to match the finite logits. Finally, we extend the analysis to fused multi-head LoRA and joint query/key updates, exposing the effects of rank sharing and query/key factorization constraints.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from math.OC
The Value of Human Expertise
Bradley Sturt
We consider optimization applications with unknown parameters where the decision maker believes that the optimal value of the nominal problem-the optimization problem they would have solved if the true parameters were known-is unlikely to be large. This belief derives from information that humans have that is not captured in
datasets, obtained from domain knowledge and interacting with the physical world. We propose an approach to evaluating policies that provides tighter performance guarantees if the decision maker's belief happens to be correct. Our main result shows that if computing a policy's worst-case performance is a convex program, then the value of human expertise-the maximum improvement in performance guarantees that can be obtained from the belief about the nominal problem-is equal to the minimax gap of a max-min problem. We illustrate our developments in assortment optimization and shortest path problems.
Read the full abstract ▾
Robotics
When Obstacles Bend: Modeling Vegetation Deformation in the context of Field Robotics
Zaar Khizar, Tom Montagnon, Roland Lenain et al. (+2 more)
Autonomous
robots operating in natural environments must often interact with vegetation rather than simply avoid it. In this context, traversability is typically defined from the
robot's perspective, by measuring how a specific platform responds when moving through the environment. While practical, this viewpoint entangles the assessment of the environment with the
robot's own dynamics, making the resulting characterization difficult to transfer across different platforms. More importantly, it does not directly reflect the properties of the vegetation itself, which are the true source of interaction and potential damage in applications such as agriculture and environmental monitoring. To address this limitation, we propose to characterize vegetation through its intrinsic mechanical properties, independently of any specific
robot. By combining deformation measurements with contact force data, we estimate the underlying mechanical parameters and reconstruct the vegetation's response to interaction. This enables vegetation-aware
navigation based on intrinsic environmental properties rather than platform-dependent metrics.
Read the full abstract ▾
All authors Zaar Khizar, Tom Montagnon, Roland Lenain, Romuald Aufrère, Johann Laconte
Cryptography and Security
RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models
Mahshid Rezakhani, Kimia Azar and Hadi Kamali
The rapid advancement of large
language models (LLMs) is driving a shift toward automated register transfer level (RTL) code generation, enabling designers to translate high-level specs. into synthesizable hardware. However, this reliance on pre-trained (3rd-party) fine-tuned models may introduce critical trust issues, as the training data and adaptation process of these models are often opaque. Thus, adversaries (even model providers) may embed hidden
backdoor threats during fine-tuning, allowing malicious behavior, e.g., hardware Trojans, to be triggered by seemingly benign
prompts given by victim user at inference time. In this paper, we introduce RTLGuard, to mitigate such a trust issue in AI-enabled IC supply chain. Rather than prohibitive computational cost of full-parameter retraining, RTLGuard leverages a teacher-student framework designed to sanitize compromised RTL generation models by (1) fine-tuning a small-scale, "clean" teacher model on a limited set of trusted RTL data, (2) guiding the poisoned target model via a composite teacher-student objective, and (3) incorporating feature
alignment and knowledge
distillation to suppress malicious behaviors. Our experiments across various LLM architectures demonstrate that RTLGuard significantly reduces the Attack Success Rate (ASR) while preserving the functional correctness and synthesizability of the generated RTL code.
Read the full abstract ▾
Data Structures and Algorithms
Nearly Optimal Strong Coresets for $\ell_p$ Subspace Approximation
Honghao Lin, Vahab Mirrokni and David P. Woodruff
We study strong coresets for $\ell_p$ subspace approximation. Given a
matrix $A\in\mathbb{R}^{n\times d}$, the goal is to sample and rescale a small number of its rows to obtain $SA$ such that $\left\|SA(I-P_F)\right\|_{p,2}^p=(1\pm\varepsilon)\left\|A(I-P_F)\right\|_{p,2}^p$ simultaneously for every subspace $F\subseteq\mathbb{R}^d$ of dimension at most $k$, where $P_F$ is the orthogonal projector onto $F$. Woodruff and Yasuda [WY25] (FOCS 2025) obtained coreset sizes $\widetilde{O}_p(k\varepsilon^{-4/p})$ for $1\leq p<2$ and $\widetilde{O}_p(k^{p/2}\varepsilon^{-p})$ for $p>2$. We improve these bounds to $\widetilde{O}_p(k\varepsilon^{-2})$ and $\widetilde{O}_p(k^{p/2}\varepsilon^{-2})$, respectively. For $1\leq p<2$, our
algorithm runs in $\widetilde{O}_p(\mathrm{nnz}(A)+d^\omega+k\varepsilon^{-2})$ time. The resulting coreset size matches the sampling lower bound [LWW21] up to logarithmic factors when $k+1\geq C\log(1/\varepsilon)$ for an absolute constant $C$. For $p>2$, our
algorithm runs in $\widetilde{O}_p(\mathrm{nnz}(A)+d^\omega)$ time, matching the running time of the framework of Woodruff and Yasuda. We use different techniques in the two regimes. For $1\leq p<2$, we combine a bicriteria low-rank split with Lewis-weight sampling and empirical-process bounds independent of the output dimension. For $p>2$, we give a sharper analysis of the Woodruff-Yasuda construction. By retaining the truncation in its sampling probabilities throughout the row-count recurrence, we show that it achieves the improved $\varepsilon^{-2}$ dependence.
Read the full abstract ▾
Numerical Analysis
A family of second order, linear, unconditionally stable methods for the Cahn-Hilliard-Navier-Stokes equations
Daozhi Han, Nan Jiang, Jonah H. Nissan et al. (+1 more)
We present a family of second-order, linear, unconditionally stable implicit-explicit (IMEX) methods for the Cahn-Hilliard-Navier-Stokes (CHNS) equations modeling matched-density two-phase flows. The proposed semi-discrete scheme combines extrapolation of the nonlinear terms with an auxiliary-variable formulation of the nonlinear free-energy term and a temporal-
curvature regularization controlled by a parameter $\epsilon$. We establish a discrete energy estimate showing unconditional long-time stability of the method for $\theta\in(1/2,1]$ and $\epsilon\geq0$. The resulting scheme requires only linear solves at each time step. Numerical experiments demonstrate approximately second-order temporal convergence and examine mass conservation, energy dissipation, numerical robustness, and several representative interfacial-flow problems, including spinodal decomposition, droplet shape relaxation, two-phase lid-driven cavity flow, and Rayleigh-Taylor instability.
Read the full abstract ▾
All authors Daozhi Han, Nan Jiang, Jonah H. Nissan, Sayantan Sarkar
Machine Learning
Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity
Xu Zhang and Ren Wang
Multi-norm
adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter configuration, leading to substantial training cost and unfavorable robustness trade-offs. We propose Robust CurveMoE, an efficient mixture-of-experts framework that connects models specialized for different perturbation norms through a low-loss path and exploits the complementary robustness profiles of models along this path. Robust CurveMoE derives clean and norm-specialized experts from robustness-constrained curve locations and selectively expertizes only influential layers, while sharing the remaining parameters across routing paths. To further reduce curve-construction cost, we introduce contribution-guided partial updating, which selects influential curve parameters using initialization-based gradient scores. We also theoretically bound the objective gap between partial and full curve optimization. Experiments on CIFAR-100 and ImageNet-100 with WideResNet and
Vision Transformer architectures show that Robust CurveMoE consistently improves clean, norm-specific, and Union accuracy over MSD and ERMC. In particular, it improves Union accuracy by 2.37 and 2.13 percentage points over the strongest baseline on CIFAR-100 and ImageNet-100, respectively. Extensive ablations further validate the effectiveness of partial updating, selective expertization, and robustness-constrained expert selection.
Read the full abstract ▾
Distributed Computing · Cross-listed from eess.SP
Adaptive Peer Clustering with Hierarchical Random Linear Network Coding for Resilient Decentralized Wireless Networks
Navaneetha Krishnan Kamalakannan and Harinisri Velmurugan
Decentralized wireless collectives including vehicular swarms, IoT clusters, and edge AI networks require communication protocols that maintain robustness under dynamic
topologies and heterogeneous link quality. While Random Linear Network Coding (RLNC) provides algebraic resilience against packet erasures, its performance degrades significantly when peers exhibit diverse channel conditions. This paper presents Adaptive Peer Clustering with Hierarchical RLNC (APC-RLNC), a system that dynamically groups peers by exponentially weighted moving average (EWMA) reliability metrics and applies multi-tier network coding within and across clusters. We formalize the clustering optimization problem, derive closed-form decoding probability bounds for Markov erasure channels, and prove O(sqrt(T)) regret for online reconfiguration under the Follow-the-Regularized-Leader (FTRL) framework. Our implementation includes both a high-fidelity network simulator and a proof-of-concept testbed deployment on Jetson Nano edge devices. Evaluation across diverse scenarios including high-mobility vehicular networks, burst-error channels, and
adversarial interference demonstrates 5.2-9.8 percentage-point packet delivery ratio (PDR) improvements, 10-23% latency reductions, and up to 30% higher node retention compared to state-of-the-art baselines. The system exhibits linear scalability to 500+ nodes and maintains real-time reconfiguration overhead below 3%. APC-RLNC establishes adaptive clustering as a foundational primitive for AI-native 6G wireless systems.
Read the full abstract ▾
Data Structures and Algorithms
Partially-Dynamic All-Pairs Maxflow and Effective Resistance via Stable Sparsifiers
Gramoz Goranci, Rasmus Kyng, Maximilian Probst Gutenberg et al. (+2 more)
We give a randomized data structure for undirected weighted graphs that are partially dynamic, i.e., that undergo either only edge insertions or only edge deletions. The data structure maintains $(1\pm\epsilon)$-approximations to the maxflow value and effective resistance between any queried pair of vertices, with total update time $\widetilde{O}_{\epsilon}(n^2)$ and worst-case query time $\widetilde{O}_{\epsilon}(1)$. Thus, for dense graphs where $m = \Omega(n^2)$, our guarantees are near-optimal. Our
algorithms succeed with high probability against an adaptive adversary. Our result follows from a simple stability principle for partially dynamic graphs. We show how to partition an online sequence of $m$ updates into $\widetilde{O}(n/\epsilon)$ epochs such that every graph within an epoch is a $(1\pm O(\epsilon))$-spectral approximation of the graph at the beginning of the epoch. The epochs are determined by the cumulative leverage score of the updated edges: small leverage-score mass implies small spectral change, while the total leverage-score mass over a monotone update sequence is $\widetilde{O}(n)$. Consequently, a spectral sparsifier needs to be recomputed only once per epoch. Applying known static all-pairs maxflow and effective-resistance oracles to these sparsifiers then yields the result.
Read the full abstract ▾
All authors Gramoz Goranci, Rasmus Kyng, Maximilian Probst Gutenberg, Yibin Zhao, Gernot Zöcklein
Artificial Intelligence
Trace Integrity for LLM Data Agents: Auditing Structured-Data Computation Beyond Answer Accuracy in Real-World Systems
Srimonti Dutta and Akshata Kishore Moharir
Large
language model (LLM) data
agents answer structured-data questions by generating SQL, invoking tools, executing queries, and summarizing results. In operational settings, reliability depends on both reported answer and computation used to produce it, as errors may remain undetected when the resulting answer matches an expected value. We refer to the mismatch between natural-
language intent and operator-level computation required to satisfy that intent as the Structure Gap, and define Trace Integrity as a reliability criterion for assessing whether the computation supporting an answer is explicit, executable, schema-valid, operator-faithful, replayable, answer-consistent, and auditable. We operationalize Trace Integrity through execution contracts that record the schema elements, operator plan, assumptions, executable query, verification status, and final-answer linkage associated with a request. We also define the Correct Answer / Invalid Trace (CAIT) Rate, which measures the proportion of correct answers whose recorded computations fail trace-integrity checks. These provide a way to evaluate whether answer-level success is supported by a valid and inspectable computation. We study this on 100 BIRD Mini-Dev text-to-SQL examples using three prompting conditions: Direct SQL, Operation Summary + SQL, and Contract-First SQL. The three conditions achieve answer accuracies 20.0%, 22.0%, and 24.0%, Trace Integrity Pass Rates 39.0%, 43.0%, and 40.0%, and CAIT Rates 55.0%, 59.1%, and 45.8%, respectively. The results show that answer accuracy, trace validity, and the frequency of correct answers supported by invalid traces capture different aspects of system behavior. Trace-level evaluation therefore complements conventional answer-based evaluation by providing evidence about the computational support, inspectability, and reproducibility of LLM data-
agent outputs in real-world systems.
Read the full abstract ▾
Computation and Language
Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty
Ziming Liu, Bhanu Chaitanya Jasti, Ziyang Xu et al. (+3 more)
When a speaker refers to a scene that the listener cannot directly see, the listener must decide whether to preserve its current understanding or revise it as new utterances arrive. Many
language systems treat local mismatch as a cue for updating: divergence from the current understanding encourages adjustment. Yet conversational understanding may be more conservative, interpreting mismatching evidence relative to prior understanding rather than immediately revising it. We introduce a controlled, data-driven framework for turn-by-turn preserve/revise decisions in dialogue, where competing revision policies are learned under otherwise identical conditions. We compare four theory-driven revision strategies, each reflecting a different assumption about when listeners should preserve or revise. Two findings stand out. First, a mismatch-driven policy that updates solely based on local divergence reacts strongly to mismatch but destabilizes grounding and degrades
retrieval. Second, an uncertainty-sensitive policy extends mismatch-based updating with accumulated evidence, preserving coherent understanding while maintaining strong
retrieval performance. Surprisingly, coherent understanding emerges from a counterintuitive pattern: local mismatch promotes preservation, whereas accumulated uncertainty promotes revision, suggesting that listeners maintain prior understanding despite local mismatch and revise only when uncertainty sufficiently accumulates. This pattern is consistent with conceptual pact theory.
Read the full abstract ▾
All authors Ziming Liu, Bhanu Chaitanya Jasti, Ziyang Xu, Hongyu Wu, Yi Wu, Jiqun Liu
Computer Vision
UltraPIPS: Improving model perception in B-mode ultrasound with foundation models
Tal Grutman and Tali Ilovitsh
In medical imaging, it is common to use learned perceptual image patch similarity (LPIPS) to compare images semantically in feature space. Although backbones pretrained on natural images are widely used for LPIPS computation, B-mode ultrasound images possess distinct speckle patterns and acoustic-specific image statistics that are fundamentally different from natural images and even from other images in radiology. Consequently, we propose that domain-specific models are needed to measure perceptual similarity in ultrasound data, a finding which is not necessarily the case for other imaging modalities. We compare LPIPS metrics across downstream tasks like classification,
segmentation and reconstruction using natural image, medical generalist and ultrasound backbone models and show that selection of LPIPS backbone is a non-trivial design choice. In particular, the ultrasound backbone models were more correlated with downstream performance of supervised models than classical and natural image models, and optimization of the LPIPS loss with an ultrasound backbone achieved a strong balance between reconstruction quality and realism. Our code is available at https://github.com/talg2324/UltraPIPS and introduces the UltraPIPS library, a set of LPIPS metrics based on the open-source foundation models analyzed in this paper.
Read the full abstract ▾
Software Engineering
Vulnerable Code Search: Transferable Attack for Code Language Models
Kaicheng Wang, Liyan Huang, Jesse Thomason et al. (+1 more)
Reliable code
retrieval is crucial for developer productivity and effective code reuse. However, current neural code
language models (CLMs) powering search tools are susceptible to
adversarial attacks targeting non-functional textual elements. In this paper, we introduce a programming
language-agnostic, transferable,
adversarial attack that exploits this CLM vulnerability. Our approach perturbs identifiers within a code snippet without altering the snippet's functionality to artificially align the code with a target query. We demonstrate that our attack, even when computed using smaller code
embedding models, such as CodeT5+, is highly effective and transferable to larger, closed-source
embedding models, like Voyage-code-3, or LLMs like Gemini-3.1-Pro. Our attack can increase the similarity between the query and arbitrary, irrelevant code snippets, consequently degrading key
retrieval metrics such as the Mean Reciprocal Rank (MRR) of state-of-the-art models by up to 77%. The experimental results highlight the fragility of current code search methods and underscore the need for more robust, semantic-aware approaches.
Read the full abstract ▾
All authors Kaicheng Wang, Liyan Huang, Jesse Thomason, Weihang Wang
Distributed Computing
Slasher: Power Flexibility for Cloud Datacenters
Liuzixuan Lin, Fiodar Kazhamiaka, Alok Gautam Kumbhare et al. (+10 more)
Datacenters consume many megawatts of power, and regularly encounter scenarios that require modulating their power draw. These scenarios include datacenter infrastructure failures, power grid failures, grid services, and more, spanning a diverse range of requirements in terms of the power magnitude, the scope of the reduction, the notice time, and other dimensions. To address these scenarios, we have built Slasher, a general system for modulating the power of \azure datacenters to handle scenarios ranging from individual racks to regional multi-datacenter grid events. Slasher coordinates datacenter resources with the goal of meeting power targets while minimizing negative impact on hosted workloads. In this paper, we review the main power modulation scenarios, characterize the power reduction levers using data from production cloud datacenters, describe Slasher's system architecture, and formulate the cloud datacenter power modulation control problem. We also develop a high-fidelity datacenter simulator and propose a workload impact model, using them to design and evaluate power control
algorithms.
Read the full abstract ▾
All authors Liuzixuan Lin, Fiodar Kazhamiaka, Alok Gautam Kumbhare, Chaojie Zhang, Jaylen Wang, Hassan Khan, Rodrigo L. Assis, Mariana Rodrigues, Kyle Woolcock, Nithish Mahalingam, Brijesh Warrier, Rodrigo Fonseca, Ricardo Bianchini
Machine Learning
DualOPSD: Closing the Feedback Loop in On-Policy Self-Distillation
Yutong Chen, Guangfu Guo, Zhichao Xu et al. (+1 more)
On-policy self-
distillation (OPSD) combines student generated trajectories with dense supervision from a privileged teacher of the same model. Its pointwise clipping protects the student from locally incompatible teacher directions, but the fixed teacher receives no feedback about the supervision the student rejects, which limits effective learning from the teacher. We introduce DualOPSD, which alternates updates in a coupled teacher-student system. The student retains OPSD's clipped forward KL objective. The privileged teacher adapts to the updated student after each student step. A residual target based on the frozen initial model preserves the effect of privileged context during teacher adaptation. Across Qwen3-8B/4B/1.7B and three math
benchmarks, DualOPSD improves avg@12 accuracy over OPSD by 9.83 percentage points. Further diagnostic analyses show lower bidirectional KL, less persistent mismatch, and retained sensitivity to privileged reference. Together, these results demonstrate that DualOPSD can be a more effective form of privileged self-
distillation. Code is available at: https://github.com/on1262/DualOPSD.
Read the full abstract ▾
All authors Yutong Chen, Guangfu Guo, Zhichao Xu, Kunpeng Liu
Computation and Language
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
Min Zeng, Guanxin Tan, Libin Cen et al. (+5 more)
Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typically follow a one-pass generate-and-filter paradigm, discarding feedback from failed samples, verifier outcomes, and target-model errors. We present VISA (Visual Instruction Synthesis
Agent), an agentic framework that reformulates
multimodal instruction synthesis as a self-evolving loop. At each round, VISA analyzes an image to filter incompatible constraints and discover new verifiable ones, samples diversity- and difficulty-aware constraint sets from persistent
memory, generates candidate instructions, and verifies the resulting samples with executable tools and structured large
language model judges. Failed samples trigger diagnostic-guided recovery, while accepted samples are probed against the target model to estimate difficulty. The resulting verifier signals and target-model failure profiles are written back to
memory, allowing subsequent rounds to adaptively expand the constraint space, reduce template repetition, and focus on unresolved model weaknesses. The same verifier contracts further provide reward signals for reinforcement learning without a separately trained reward model. Experiments on MM-IFEval show that VISA consistently improves
multimodal instruction following over strong baselines, while preserving general
multimodal capability across seven public
benchmarks.
Read the full abstract ▾
All authors Min Zeng, Guanxin Tan, Libin Cen, Yafei Wen, Rui Hu, Liuyang Bian, Xiaolong Chen, Xiaoxin Chen
Information Theory
Exact Common Information and Exact Channel Synthesis for Correlated Gaussian Sources
Lei Yu
In this paper, we resolve two
conjectures posed by Yu and Tan in 2020 (in two separate papers published in the IEEE Trans. Inf. Theory). Specifically, we establish that: 1) the exact common information for a pair of $\rho$-correlated Gaussian sources is given by the conjectured expression $\frac{1}{2}\log\frac{1+\rho}{1-\rho}+\frac{\rho}{1+\rho}$; and 2) the admissible region for the shared randomness rate and the communication rate in exact channel synthesis is exactly the conjectured one. These results yield two important consequences. First, for any $\rho>0$, the exact common information of a correlated Gaussian pair strictly exceeds Wyner's common information. Second, for $\rho>0$, the exact channel synthesis of such a pair requires strictly higher rates than the total-variation version. The proof combines an exact optimal-transport representation of the worst-case Gaussian cross-
entropy, Fathi's Gaussian transport inequality, and a determinant inequality arising from the covariance structure of the conditional means.
Read the full abstract ▾
Robotics
Phantom Navigator: Stealthy and Precise Unmanned Aerial Vehicle Redirection with Real-Time Tracking and GPS Spoofing
Haocheng Meng, Shaocheng Luo, Songqiao Xie et al. (+1 more)
Redirecting unmanned aerial vehicles (
UAVs) from their intended mission trajectories has been an active area of research. However, existing
UAV redirection attacks lack reliability, precision, and covertness for a targeted diversion. They primarily rely on physical capture, communication hijacking, or sensor spoofing. Yet, physical interception is costly, offers only a single opportunity for success, and poses a high risk of collateral damage; network-based attacks demand deep technical expertise and access to encrypted communication channels; and sensor spoofing techniques typically fall short in achieving the accuracy and robustness required to steer a
UAV toward a specified target. Consequently, we propose Phantom Navigator, a
UAV redirection attack to mislead drones to a designated spoofing target, covertly and precisely. Our approach combines offline pre-redirection reachability analysis, which provides high-fidelity estimates of achievable redirect ranges, with an online closed-loop, stealthy execution layer that ensures successful redirection in practice. Based on this approach, we build a physical attack platform equipped with a
LiDAR–camera detection, tracking, and spoofing stack that performs real-time identification, pose estimation, and computation of targeted spoofing signals to covertly and accurately redirect victim
UAVs to a designated location. We demonstrate the effectiveness of our redirection methodology and the attack implementation in real-world case studies.
Read the full abstract ▾
All authors Haocheng Meng, Shaocheng Luo, Songqiao Xie, Miroslav Pajic