Cryptography and Security
Are We Shooting Flies with Cannons? Trade-off Analysis for AI-based 5G Intrusion Detection
Federica Uccello and Simin Nadjm-Tehrani
The increasing adoption of Artificial Intelligence (AI) in network intrusion detection raises the question of whether complex and computationally expensive models are justified for this task. In this work, we investigate the trade-off between detection performance and computational cost for intrusion detection in 5G network telemetry. We compare traditional machine learning (ML) models, including XGBoost as a representative of tree ensemble, and TabNet for tabular deep neural network (DNN), with a large
language model (LLM) used as a general-purpose intrusion detector. The LLM is evaluated under both zero-shot and few-shot prompting configurations. We evaluate the models in terms of detection performance, inference time, and CPU time as a proxy for energy efficiency. Using a relatively large available 5G
dataset, we show that traditional ML models consistently achieve near-perfect detection performance with negligible inference time, while LLM-based approaches perform significantly worse and incur orders-of-magnitude higher CPU usage. Few-shot prompting improves recall, but at the cost of lower accuracy and further increased CPU time, without closing the performance gap. These findings indicate that, for tabular intrusion detection in 5G networks, XGBoost offers a substantially better performance-cost trade-off than DNNs and LLMs, highlighting the importance of selecting models based on task suitability rather than increasing complexity.
Read the full abstract ▾
Artificial Intelligence
SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers
Haizhao Fan, Yuchi Xiong, Jize Wang et al. (+2 more)
Large
Language Models (LLMs) have demonstrated remarkable proficiency in natural
language understanding, yet they struggle with strict multi-step
reasoning, frequently suffering from
hallucinations and inconsistency. Existing solutions like Chain-of-Thought (CoT) lack rigorous verification mechanisms, while standard
Retrieval-Augmented Generation (RAG) often misses the complex, structural dependencies inherent in logical tasks. To bridge this gap, we propose a Neuro-Symbolic architecture that integrates a Logical Knowledge Graph (LKG) with dynamic solver routing. Specifically, we introduce an ontology-based LKG that treats logical rules and constraints as first-class topological nodes, enabling explicit modeling of dependencies extracted from text. We further design a Logic Router to dynamically dispatch tasks to the optimal symbolic engine, which is supported by a
topology-aware hybrid
retrieval mechanism. Experimental results on logical
reasoning benchmarks demonstrate that our framework significantly outperforms state-of-the-art prompting and RAG baselines, delivering higher accuracy and verifiable
reasoning paths.
Read the full abstract ▾
All authors Haizhao Fan, Yuchi Xiong, Jize Wang, Xinping Guan, Xinyi Le
Computer Vision
Rethinking Image Processing for the Age of AI: A Problem-First Framework for Scientific Progress
Guoping Qiu
Modern AI has greatly expanded the capabilities of image processing. However, the ready availability of powerful models, public
datasets, and
benchmark leaderboards has also en- couraged a model-first research pattern: researchers increasingly begin with an available architecture and optimize it on a public
benchmark, rather than beginning with the underlying real-world imaging problem. This can produce impressive
benchmark results without necessarily improving our understanding or solution of the real problem. This paper argues for a problem-first approach that distinguishes the physical imaging problem, solution principle, statistical
estimator, and computational implementation, while clarifying what modern AI can achieve and which fundamental problems remain unsolved. Through case studies of super- resolution and low-light enhancement, we show how
benchmark datasets may define tasks that differ substantially from the real-world problems they are intended to represent, and why performance improvements must be interpreted within the conditions under which they are obtained. We propose a six-stage workflow that places problem formulation, image acquisition, information-loss analysis, assumptions, ambiguity, and evaluation before model and
dataset selection. The paper also proposes clearer standards for evidence, reproducibility, uncertainty, and claims of state-of-the-art performance. More fundamentally, it calls for a change in research culture and education so that future researchers learn to understand imaging problems deeply and use modern AI to achieve genuine scientific and technical advancement.
Read the full abstract ▾
Computation and Language
RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models
Bohan Yu, Shi-Yang Li, Pengfei Cao et al. (+2 more)
Large
language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires
reasoning over complex rules in concrete scenarios. However, existing
benchmarks only partially evaluate this capability, as they either focus on output-level instruction constraints or overlook the distinct roles that rules play in scenario
reasoning. To address these gaps, this paper introduces RuleWeaver, a
benchmark construction framework for evaluating rule-centered scenario
reasoning. RuleWeaver starts from corpus-derived IF-THEN Meta Rules, progressively augments them into complex rules, and composes these rules into rule-centered scenario QA instances. Beyond final-answer correctness, RuleWeaver further supports process-level evaluation through rubric-based answer quality, rule recall, and rule precision. Experiments on 11 representative LLMs show that current models still struggle with complex rule-centered scenario
reasoning, with even the best-performing model achieving only around 50% of the maximum rubric score. We make our code and
dataset available here: https://github.com/SharkSpicy-NLP/RuleWeaver.
Read the full abstract ▾
All authors Bohan Yu, Shi-Yang Li, Pengfei Cao, Jun Zhao, Kang Liu
Cryptography and Security
XION: Interpreting Network Traffic Anomalies via Dependency Violations
Federica Uccello and Simin Nadjm-Tehrani
Current research on security monitoring is increasingly focusing on machine-learning-based approaches, but caveats remain. In addition to huge computational overhead, one concern is the lack of insights into “why" alerts are raised. Existing interpretability approaches rely on feature attribution methods that ignore dependencies among features or on causal modeling that requires extensive domain knowledge or computational resources. This work proposes XION, a method for modeling relationships among network-flow features based on benign traffic only. During detection, anomalies are identified through violations of expected feature dependencies. Further, XION supports post-alert analysis by identifying which feature relationships break, when they break along the attack timeline, and how dependency violations evolve relatively to other identified violations. XION is evaluated on standard IDS
datasets and compared against an Isolation Forest (IF) baseline across multiple attack scenarios, including both volumetric and stealthier attacks. Results show that XION matches or exceeds IF recall in all evaluated scenarios, while requiring up to 7$\times$ less inference time. At the post-alert stage, the dependency violation analysis reveals temporal and structural patterns consistent with known attack behaviors, and is further evaluated against SHAP-based feature attribution of IF alerts. Together, these findings confirm that attacks indeed disrupt feature dependencies learned from benign traffic, and that these disruptions provide additional information for understanding an alert.
Read the full abstract ▾
Systems and Control
Joint Spectrum and Airspace Resource Optimization for Low-altitude Wireless Network
Yafei Guo, Ziye Jia, Lei Zhang et al. (+3 more)
Low-altitude wireless networks have emerged as a promising platform for enabling the safe and efficient operation of unmanned aerial vehicles (
UAVs). However, due to the limited spectrum and airspace resources, it is challenging to efficiently accomplish
UAV flight tasks without collisions. In this paper, we propose a sequential framework with two coupled stages that coordinates spectrum allocation and airspace planning to construct efficient low-altitude air corridors. Specifically, the low-altitude airspace is discretized into a set of digital grids, where obstacles are modeled as impermeable units. Then, we formulate an optimization problem to minimize the total traversal cost of air corridors, which is challenging to solve due to the tight coupling between spectrum allocation and path planning.Therefore, we first design a constrained Vickrey-Clarke-Groves (VCG) ascending auction mechanism to allocate the spectrum resources. Then, we propose a joint spectrum and airspace resource allocation
algorithm to minimize the total traversal cost of air corridors. Finally, simulation results show that the proposed
algorithms achieve lower total costs than the baseline
algorithms.
Read the full abstract ▾
All authors Yafei Guo, Ziye Jia, Lei Zhang, Jingxian Liu, Qiuming Zhu, Qihui Wu
Machine Learning
SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting
Haizhao Fan and Xinyi Le
Time series
forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the physical meaning of each variable, its statistical behavior, and its temporal dynamics. Recent efforts to bridge this gap fall into two camps. Some rely on large
language models at inference time, which is computationally expensive. Others apply uniform textual
prompts at the
dataset level, ignoring the heterogeneous semantics across individual variates. We propose SAGE (Seeing and Augmenting with Grounded Encoding), an end-to-end CLIP-based framework that jointly models temporal, cross-variable, textual, and visual information. The CLIP text encoder processes frequency-enhanced patches and variable
tokens, while gated residual paths inject variable-specific descriptions and statistical descriptors. In parallel, the frozen CLIP
vision encoder aligns rendered series with temporal representations through a training-only contrastive objective. This dual use of CLIP adds complementary semantic and visual supervision without placing an LLM in the
forecasting loop. Across eight long-term
benchmarks and M4, SAGE achieves state-of-the-art accuracy. Ablations confirm complementary gains from
multimodal alignment and variable-level knowledge.
Read the full abstract ▾
Computer Vision
Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocation
Xiaoyang Li and Zeyan Tao
The diagnostic value of an ECG channel depends on the model that interprets it. We test whether adaptive acquisition retains its advantage over fixed protocols when that model changes. Two policies developed with a logistic evaluator are frozen and assessed with a masked waveform ResNet1D, using exhaustive, metric-matched fixed comparators. On PTB-XL, replacing the evaluator reverses the mean adaptive advantage in negative log-likelihood and Brier score across the tested budgets, while calibration responds less uniformly. The shift persists with common fixed references and broader training-mask exposure. Training a policy against the stronger evaluator partly recovers the lost advantage. These retrospective exploratory results show that acquisition quality cannot be assessed independently of the downstream evaluator and motivate validating adaptive policies with the model intended for diagnosis.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.ao-ph
Bridging short- and medium-range weather forecasting with machine learning
Timothy A. Smith, Mariah Pope, Sergey Frolov et al. (+4 more)
The National Oceanic and Atmospheric Administration (NOAA) employs independent prediction systems for distinct forecast products. While some separation is practical, we argue that combining short- and medium-range weather into a single prediction system would provide the public with a useful
distillation of global weather and its impacts. To this end, we present Nested-EAGLE (Experimental Artificial intelligence Global and Limited-area Ensemble): a 0.25{\deg} global weather model with a 6 km refinement over the Contiguous United States (CONUS). The model achieves significantly lower mean-squared error in near-surface and low-level quantities over CONUS compared to NOAA's Global Forecast System and High-Resolution Rapid Refresh (HRRR), while remaining competitive throughout the rest of the global atmosphere. We show that the skill gains for near-surface fields stem from incorporating high-resolution regional analysis data into training through the nesting process. Forecasts of precipitation amounts are less skillful than those from HRRR, owing to deterministic training. However, we show that Nested-EAGLE provides the most accurate forecasts of storm locations at longer leads, despite blurred extrema. Our results motivate future work to extend the skill gains beyond CONUS and improve precipitation representation.
Read the full abstract ▾
All authors Timothy A. Smith, Mariah Pope, Sergey Frolov, Brett Basarab, Daniel Abdi, Paul Madden, Isidora Jankov
Robotics
TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation
Jiarui Yang, Yehao Lu, Yuning Su et al. (+9 more)
Vision-
language-action (VLA) models leverage pretrained
vision-
language representations for
robot control, yet simply adding historical frames does not reliably capture recent physical change. This is especially problematic in multi-stage manipulation, where visually similar states may require different actions depending on prior execution. To address this challenge, we present TemporalFlow-VLA, which learns compact execution history through physically grounded temporal supervision. Using recorded
robot states,
robot geometry, and calibrated cameras, we construct
robot-surface temporal flow as a training-only target and supervise two execution-aligned temporal queries that provide structured history to the action expert. The
geometric supervision path is not evaluated at deployment. TemporalFlow-VLA achieves 97.63 +/- 0.26% average success on LIBERO, including 96.60 +/- 0.87% on LIBERO Long, and 85.5%/84.2% Clean/Randomized success across 12 RoboTwin tasks. It shows its clearest advantage over prior methods on longer-horizon, multi-stage manipulation. Controlled history interventions show that action prediction depends on both historical content and temporal order. With asynchronous feature caching, temporal conditioning maintains single-frame-level server-side sampling latency without additional historical-encoding overhead. Overall, TemporalFlow-VLA provides a compact, physically grounded interface for exploiting ordered execution history without explicit motion estimation or
geometric processing at deployment.
Read the full abstract ▾
All authors Jiarui Yang, Yehao Lu, Yuning Su, Yu Zhong, Yufeng Xie, Yazhou Zhang, Haiyu Lan, Kaixiang Lu, Peiwen Lin, Chuang Wang, Junwei Liang, Enyu Li
Computer Vision
LLaVAFlow: Preserving Latent Alignment Flow for Parameter-Efficient Multimodal Fine-Tuning
Muyao Yuan, Muyan Jiao, Jiangyong Ying et al. (+5 more)
While
Multimodal Large
Language Models (MLLMs) exhibit strong generalization, visual instruction tuning for downstream tasks inevitably causes catastrophic forgetting, impairing overall generalization. While existing methods regulate weight updates to reduce forgetting, they overlook the fundamental cross-modal
alignment in MLLMs. Based on prior work and our observations, we argue that cross-modal
alignment is implicitly captured in the information-compression trajectory. To preserve the
alignment flow embedded in the trajectory, we propose LLaVAFlow, an information-theoretic
distillation framework. First, we compress the mutual information between the extracted relations and MLLM
embeddings, encouraging a learnable module to produce a refined
alignment flow that benefits downstream tasks. Second, we maximize the mutual information between the extracted
alignment flows of the pretrained and fine-tuned MLLMs, enabling the transfer of compact
alignment information. Extensive experiments show that LLaVAFlow is an effective plug-and-play framework that preserves
alignment flow and enhances both downstream performance and generalization.
Read the full abstract ▾
All authors Muyao Yuan, Muyan Jiao, Jiangyong Ying, Weizhan Zhang, Yuanhong Zhang, Lan Ma, Yuan Gao, Haipeng Du
Robotics
CLIPPER: Replayable Shortlisted Optimization for Repeated Spatial Coverage Planning
Julian Teusch, Jörg Philipp Müller and Monika Sester
Operational requirements developed with the City of Braunschweig frame municipal micromobility planning under geofenced exclusions, mandatory retained sites, spacing rules, and area-level caps. Each policy edit requires a new feasible plan; full-set greedy takes tens of seconds per alternative at city scale. We present CLIPPER (Constraint-exact Low-latency Iterative Planning with Pooled Evaluation and Replay). It forms bounded candidate pools but recomputes exact current gains and checks every active constraint before selection. Coverage from each candidate alone sets the initial order. Offline full-set scans measure gains omitted by the pool; online, a conservative bound triggers expansion or audit. CLIPPER-F gives each proposal group the same number of candidate slots. Across Braunschweig, Munich, and Berlin, its mean coverage over complete chains stays within 0.245 percentage points of full-set greedy under the same policy, with 13.6–28.9 times lower mean rollout time. CLIPPER-A instead distributes one shared candidate budget across the groups. Under its coverage-prioritized policy, it uses 9–15% of full-set greedy's rollout time under the same policy, with mean gaps of 1.82 percentage points in Braunschweig, 0.12 in Munich, and 0.27 in Berlin. Together, CLIPPER enables rapid, replayable comparison of recorded city-scale planning states while enforcing every encoded model constraint.
Read the full abstract ▾
Computer Vision
Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpainting
Shuo Li, Mike Davies and Mehrdad Yaghoobi
A novel Hyperspectral
diffusion Equivariant Imaging (HyDiff-EI) framework for solving the hyperspectral image (HSI) inpainting problem has been presented here. Unlike conventional
diffusion-based methods that rely on large-scale pretraining, HyDiff-EI is a test-time optimization framework that learns directly from a single corrupted HSI acquisition. This makes it flexible for different sensor configurations and particularly well-suited for practical remote sensing scenarios where large annotated hyperspectral
datasets are limited. To address the ill-posed nature of unsupervised inpainting, we embed equivariant consistency constraints within the
diffusion process. By leveraging the inherent
geometric symmetries and intrinsic characteristics of HSIs, HyDiff-EI bridges the gap between generative
diffusion modeling and self-consistent physical priors. We empirically show that coupling
diffusion modeling with equivariant priors substantially enhances noise robustness and generalizability. Extensive experiments on real-world
datasets including Chikusei, Botswana, and EMIT demonstrate that HyDiff-EI offers remarkable inpainting quality over existing self-supervised and
diffusion-based
algorithms in both noiseless and noisy cases.
Read the full abstract ▾
Numerical Analysis
A Discontinuous Galerkin discretization for the sea ice dynamics
Emma Lagracie and Thomas Richter
Sea ice dynamics plays a crucial role in the Earth's
climate system, making it an important component of weather and
climate prediction models. Its numerical simulation remains challenging, however, as it exhibits complex mechanical behaviors due to a nonlinear ice rheology and interactions with external physical forcings. In particular, sea ice presents linear kinematic features (LKFs), i.e., narrow bands of intense deformation associated with processes such as lead opening or pressure-ridge formation. Accurately representing these features is necessary as they affect thermodynamics and ocean-atmosphere exchange. Yet their number, localization, and structure are highly sensitive to spatial resolution and to the chosen discretization of the sea ice velocity. In this work, we investigate the spatial discretization of Hibler's viscous plastic sea-ice model using a fully discontinuous Galerkin (DG) representation of all variables, including the velocity field. The ability of DG elements to represent discontinuities while having high order local
polynomial approximation makes them well suited for resolving the complex ice deformation features, and insuring robustness towards mesh-induced numerical artefacts. We assess the fully DG method using an established sea ice dynamics
benchmark and compare the obtained sea ice deformation with state-of-the-art discretizations. Additionally, we study the theoretical convergence of the modified Elastic-Viscous-Plastic (mEVP) formulation as a pseudo-time iterative solver for the viscous-plastic (VP) momentum equations. We prove the convergence of the underlying continuous pseudo-time dynamical system towards the viscous plastic formal limit, thereby providing a theoretical foundation for the use of mEVP as an iterative solver for Hibler's VP model.
Read the full abstract ▾
Computer Vision
Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
Chenyang Wu, Fuchen Long, Binyuan Huang et al. (+4 more)
While generative AI has significantly advanced
video editing, existing methods primarily focus on single-shot or short
video clips. Editing long
videos with multiple instructions remains a formidable challenge. Naive chunking strategies, e.g., fixed-duration
segmentation, often lead to entity fragmentation, severe editing
hallucinations, and disrupted temporal continuity. To bridge this gap, we introduce the Multi-Instruction Multi-Shot Long-
Video Editing (MMLVE) task, which is structured around three core objectives: Cross-Shot Editing Consistency (CSEC), Multi-Instruction Decoupling (MID), and Zero-Destruction on Spatiotemporal Structure (ZDSS). To tackle these three unique challenges, we introduce an agentic editing framework that leverages the synergy of Large
Language Models (LLMs) and
Vision-
Language Models (VLMs) to achieve shot-level
video decoupling and precise instruction parsing. Furthermore, to comprehensively evaluate this task, we construct MMLVE-Bench, which is an MMLVE-focused
dataset characterized by complex real-world spatiotemporal dynamics, high-density heterogeneous instructions, and sparse, random entity distributions. Three MMLVE-focused evaluation metrics are further exploited to assess the quality of the editing results. Extensive experiments demonstrate that our MMLVE-
Agent outperforms existing closed-source SOTA approaches (e.g., Seedance 2.0), successfully eliminating editing
hallucinations, preserving cross-shot editing consistency, and attaining seamless spatiotemporal transitions.
Read the full abstract ▾
All authors Chenyang Wu, Fuchen Long, Binyuan Huang, Xinlong Sun, Xi Chen, Chun-Le Guo, Chongyi Li
Computation and Language
Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
Zihao Cheng, Yingyu Shan, Hongru Wang et al. (+6 more)
Travel planning
agents assist users in generating personalized travel plans by modeling their individual preferences. Existing
agents either rely on explicit user instructions or engage in multi-turn clarification to elicit user preferences. However, both approaches overlook the rich behavioral signals latent in users' past behaviors, which implicitly encode their preferences. This over-reliance on active user input increases interaction burden and limits plan personalization. To bridge this gap, we introduce a new task, Behavior-Aware Travel Planning, which infers user preferences directly from past behaviors and generates personalized travel plans. To facilitate research on this task, we introduce Behavior2Trip, a
benchmark constructed from one of the largest Chinese online travel platforms, comprising 11,400 instances. Each instance represents an average of 39.8 past user behaviors spanning 14 attributes across 5 preference dimensions. We further propose B2T-
Agent, a reinforcement learning-based
agent that leverages user behavior trajectories, interacts with external tools for preference-aligned
retrieval, and maintains an internal
memory module. Experiments on Behavior2Trip show that GPT-4.1 achieves a full-constraint pass rate of only 0.5% on the hardest tasks, while B2T-
Agent built upon Qwen3-8B outperforms all baselines, highlighting the substantial challenge of this task. Moreover, Qwen3-8B trained with B2T-
Agent also outperforms GPT-4.1 on the TravelPlanner
benchmark, demonstrating strong generalization. Code and data are available at https://github.com/BUAA-IRIP-LLM/Behavior2Trip
Read the full abstract ▾
All authors Zihao Cheng, Yingyu Shan, Hongru Wang, Zeming Liu, Xinyi Wang, Xiangrong Zhu, Yuhang Guo, Wei Lin, Yunhong Wang
Computer Vision
Multi-Image Visual Token Pruning in Large Visual Language Models
Rongyang Zhang, Chengqiang Lu, Cong Li et al. (+9 more)
With the growing demand for processing multiple image sequences in real-world applications, various visual
token pruning methods have emerged to mitigate the computational and context length constraints faced by Large
Vision Language Models (LVLMs). However, most existing
pruning approaches rely on static strategies that struggle to adapt across different architectural LVLMs and multi-image scenarios, and are additionally constrained by their dependence on
attention computations that are incompatible with efficient techniques like FlashAttention. To address these limitations, we propose a training-free, Adaptive Visual
Token Pruning (AVTP) framework, applicable to diverse LVLM architectures. We strategically determine
pruning layers based on empirical analysis of visual
attention distributions across various LVLMs, and implement adaptive
pruning ratios in multi-image contexts where images of higher importance retain proportionally more
tokens. We conduct extensive experiments across different LVLMs to demonstrate the effectiveness and robustness of AVTP. Specifically, Qwen3VL-8B achieves 2 times inference speedup while maintaining 96.1% of its original accuracy on multiple multi-image
benchmarks, InternVL3.5-8B retains 94.1% accuracy, and LLaVA-OV-7B even exceeds its original baseline performance. Our code is available at \href{https://github.com/zry13/AVTP}{this link}.
Read the full abstract ▾
All authors Rongyang Zhang, Chengqiang Lu, Cong Li, Hongchao Gu, Tingjia Shen, Xuyang Zhi, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Hao Wang, Enhong Chen
Machine Learning · Cross-listed from stat.ML
Incremental Recommendation via Causal Models
Athanasios Vlontzos, David Gustafsson, Michael O'Riordan et al. (+1 more)
Recommendation impressions are a finite resource, hence delivering a recommendation to a user who would discover the content organically yields no incremental value and displaces other recommendations that could. We address this by extending an existing production recommendation model to a causal architecture using holdback data that is already collected as part of routine experimentation infrastructure, requiring no new data collection. A central challenge is that attribution windows differ between treated and holdback observations: treated users are attributed a stream within a short direct-response window, while holdback users are attributed organic streams over a multi-day window. This mismatch makes naive treatment-effect subtraction invalid. We resolve this with a dual-threshold targeting policy that delivers a recommendation only when the probability of a treated stream is high and the probability of organic stream is low. In a production-scale A/B test on millions of Spotify users, this policy reduces recommendation impressions by 7% with no statistically significant reduction in overall recommended content consumption. We further show that joint training with holdback data improves calibration of the treated head relative to the production baseline, and argue this can be taken as evidence that causal models learn more generalisable representations than models trained on observational data alone.
Read the full abstract ▾
All authors Athanasios Vlontzos, David Gustafsson, Michael O'Riordan, Ciarán M. Gilligan-Lee
Information Theory
Spectral Approximation and Ergodic-Capacity Convergence of HMIMO Channels under Spatial-Wavenumber Domain Mismatch
Hangsong Yan, Hong Yang and Shu Sun
We establish quantitative results on finite-dimensional spectral approximation and ergodic-capacity convergence for continuous
Holographic Multiple-Input Multiple-Output (HMIMO) channels with square apertures and physically prescribed circular wavenumber support. The resulting spatial-wavenumber domain mismatch leads to a non-separable square-disk concentration problem for which the classical separable construction based on prolate spheroidal wave functions (PSWFs) cannot be directly applied. We project the continuous operator onto a tensor-product subspace of one-dimensional (1D) PSWFs while preserving the circular wavenumber support, yielding a generally non-diagonal but highly sparse finite-dimensional
matrix. We show that the whole-spectrum approximation error, accounting for retained-
eigenvalue perturbations and the residual spectral tail, remains controlled by a 1D PSWF
eigenvalue-tail envelope despite the loss of separability and induced off-diagonal coupling. Beyond an explicit 1D truncation threshold, this error decays super-exponentially. This analysis further yields an asymptotic upper envelope for the eigenspectrum under the flattened two-dimensional
eigenvalue ordering. We further establish a non-asymptotic upper bound on the gap between the actual ergodic capacities of the continuous and tensor-PSWF-truncated channels under their respective transmit-covariance optimizations. Combined with the spectral result, this capacity-gap bound inherits the same super-exponential dependence on the truncation order. Finally, quadrature rules with explicit radial and angular node thresholds are developed for evaluating the projected
matrix. Numerical results show that conventional truncation based on spatial degrees of freedom can omit performance-relevant modes, particularly for compact apertures.
Read the full abstract ▾
Game Theory
A lone divider allocation algorithm with subjective divisibility
Uriel Feige
In the subjective divisibility allocation model, all goods are divisible, every
agent $i$ has a non-negative additive valuation function $v_i$, where for some goods $v_i$ is additive over fractions of the good, and for some goods, any fraction smaller than~1 has value~0. Previous work established the existence of $\frac{5}{9}$-MMS allocations in this setting. We show that $\frac{3}{5}$-MMS allocations exist. Our proof is based on an adaptation of the lone divider framework.
Read the full abstract ▾
Robotics
Rapid On-Robot Learning for Dynamic Manipulation Skills: Robot Juggling
Taeyoon Lee, Chunpeng Wang, Christopher G. Atkeson et al. (+2 more)
We present an online learning framework that enables a bimanual
robot to acquire diverse juggling patterns directly on physical hardware within minutes, even with a significant sim2real gap. One of the most important lessons from this work is that a model, even when far from reality, can be extremely useful for learning. This motivates a central philosophy of our approach: learning should build upon the
robot's current knowledge rather than replace it. Our regularized
memory-based learning puts this principle into practice by learning a local model from accumulated experience while retaining the global prior model to extrapolate where experience is sparse. This enables efficient and stable online learning from each new experience without resorting to uninformed exploration over a vast space of possible behaviors. Equally important to continual on-
robot learning is safety, allowing the
robot to repeatedly practice and improve in the real world. We construct a mutually reachable set that allows safe transitions between successive throws and catches, without driving either arm into a state from which its next action would require violating the
robot's joint or actuator limits. Together, these ideas enable a bimanual
robot with multi-fingered hands and onboard
vision to safely learn and compose five canonical three-ball juggling patterns, including cascade, tennis, half-shower, shower, and box, within less than 5 minutes of real-world interaction. More broadly, this work points toward
robots that build upon imperfect prior knowledge and continually refine their behavior through their own real-world experience.
Read the full abstract ▾
All authors Taeyoon Lee, Chunpeng Wang, Christopher G. Atkeson, Alfred A. Rizzi, Nicolas Rojas
Machine Learning
On the Indistinguishability of Human v/s AI Generated Text
Jaee Ponde, Aritra Das, Mihir More et al. (+1 more)
The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more “human”. We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the same
prompts, we show that repeated paraphrasing moves the machine distribution toward a human target under mixing and stability conditions. We derive an explicit convergence rate, examine how semantic-preservation and quality constraints affect this rate, and extend the analysis to finite samples to characterize how the required human data and paraphrasing rounds scale with the desired error. We extend the analysis beyond the shared-parameter setting by learning a human-preserving rewriting kernel.
Read the full abstract ▾
All authors Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta
Computer Vision
Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion
Bowen Xue, Brandon Y. Feng, Chenguo Lin et al. (+6 more)
Scaling
video generation to long durations reveals a critical bottleneck: current models lack robust long-term
memory. This deficiency can be studied along two critical aspects: object permanence, the ability to precisely reproduce the appearance of objects upon re-entry; and
memory capacity, the ability to process ultra-long context and use information from distant history. Robust long-term
memory requires both: object permanence without sufficient context handling limits the temporal scope, while long context length without permanence fails to maintain identity. To address this, we present Ring Forcing, an autoregressive
video diffusion framework designed to robustly construct and precisely utilize long-term
memory. Our ring-structured training strategy enforces
retrieval from distant history, effectively reconciling the trade-off between strict historical adherence and generative diversity. To expand
memory capacity, we introduce a compression and timestep composition strategy. Under fixed sequence length constraints, this method extends the effective historical span to minutes-long durations and achieves a comprehensive receptive field over the entire history. Furthermore, we present a sparse RoPE mechanism to enable flexible, scalable
memory adaptation while fully exploiting pre-trained priors. Extensive experiments demonstrate that Ring Forcing achieves superior minutes-long coherence and object permanence, significantly outperforming state-of-the-art methods.
Read the full abstract ▾
All authors Bowen Xue, Brandon Y. Feng, Chenguo Lin, Yuchen Lin, Yujia Zeng, Lvmin Zhang, Maneesh Agrawala, Honglei Yan, Panwang Pan
Cryptography and Security
Thresholding Post-Quantum Signatures
Francesco De Sclavis, Matteo Nardelli and Marco Pedicini
Threshold signature schemes distribute the signing process among $T$ parties out of $N$. They enable a variety of applications and their research is also motivated by a recent NIST call. However, applications are dominated by pre-
quantum signatures, which are more efficient but not secure in the post-
quantum setting. This paper investigates existing post-
quantum signatures, based on a variety of paradigms:
lattice problems, one-way (hash) functions, cryptographic group actions, isogenies and multivariate systems. We propose a classification (divided by paradigm) of existing tools that are used to build $T$-out-of-$N$ schemes from digital signatures. We also include general approaches based on FHE, MPC or ZKP.
Read the full abstract ▾
Robotics
Online Joint Calibration of Steering Offset and Planar LiDAR Extrinsics for Wheeled Mobile Robots
Subodh Mishra, Arindam Dhar, Suprotim Majumdar et al. (+1 more)
Accurate steering sensing and
LiDAR-to-vehicle extrinsics are crucial for reliable path tracking in warehouse mobile
robots (WMRs); miscalibration often leads to snaking, weaving, and elevated cross-track error (CTE). In practice, steering “zero” is commonly set manually (e.g., eyeballing straightness via a PS4 joystick), while
LiDAR extrinsics are assumed from CAD and may drift after maintenance. Such static, manual procedures frequently cause miscalibration in safety-critical environments. This paper presents an Extended Kalman Filter (EKF)–based method for online estimation of steering offset and planar
LiDAR extrinsics within a bicycle-kinematics model, providing a principled alternative to manual calibration. Experiments on real
datasets show that correcting steering offset reduces CTE substantially, validating the effectiveness of the proposed approach.
Read the full abstract ▾
All authors Subodh Mishra, Arindam Dhar, Suprotim Majumdar, Naveen Arulselvan
Artificial Intelligence
Decoupling Planning and Control for Instructable Agents
Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste et al. (+2 more)
Recent work shows that pre-trained, instruction-tuned
vision-
language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-latency action sequences in unfamiliar environments. At the same time, world-model controllers excel at fast observation-to-action control, but lack open-ended task guidance. In this work, we combine these strengths into a single system, Instruct-to-Act, where we train a world-model controller to act autonomously at high frequency when conditioned on sparse, higher-latency, and high-level text instructions generated by a VLM planner. To train controllers to be
language-instructable, we relabel segments of controller policy rollouts with synthetic instructions and jointly optimize a behavior-cloning objective along with existing reward-maximizing and world-modeling objectives. We evaluate our proposed approach across seven
embodied environments, including three multi-
agent environments where VLM planners coordinate through
language while trained controllers serve as their actuators. Under matched observation and action spaces, our decoupled approach consistently outperforms controller-only and direct VLM action-generation variants, preserves fast control, and lets us swap in different pretrained VLM planners without fine-tuning, while remaining competitive with strong
vision-
language-action and multi-
agent RL baselines on six of seven tasks.
Read the full abstract ▾
All authors Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste, Ishita Dasgupta, Alane Suhr
Multimedia
Self-Reflective Multi-modal Reasoning for Short-Video Fake News Detection
Pinjie Xu, Yuzhou Yang, Zhikai Tan et al. (+4 more)
Recent fake news detection pipelines increasingly leverage large
language models and
vision-
language models for
reasoning-based analysis. However, several challenges remain open: improving
reasoning quality through self-reflection without ground-truth chain-of-thought supervision, using improved
reasoning to benefit downstream model fine-tuning, and connecting single-sample fraudulent-pattern discovery with cross-sample verification. We propose SRM-FND, a self-reflective
multimodal reasoning framework for short-
video fake news detection. SRM-FND develops higher-quality
reasoning through contrastive deliberation, iterative root-cause diagnosis, and corrective
prompt refinement. A Blind Analyst, Counter-Conclusion Reasoner, and Self-Consistency Arbiter collaboratively identify and retain discriminative rationales. The framework also incorporates dual-phase, topic-adaptive
vision-
language model fine-tuning to improve
multimodal grounding and enable lightweight topic specialization. For uncertain cases, it performs confidence-driven cross-sample review by retrieving credible and suspicious co-event examples. Experiments on FakeSV and FakeTT show that SRM-FND outperforms strong baselines, produces more reliable and interpretable predictions, and delivers noticeable improvements in cross-
dataset performance.
Read the full abstract ▾
All authors Pinjie Xu, Yuzhou Yang, Zhikai Tan, Qichao Ying, Zaiyang Yu, Ce Li, Zhenxing Qian
Multimedia
Emotion Understanding in Streaming Video with Trajectory-Aware Reliability
Qingsong Wang, Qigong Lei, Zitong Wang et al. (+6 more)
Video emotion understanding is commonly studied as an offline classification problem, where the complete
video segment is available before prediction. Real-time interaction, however, requires
emotion decisions from incomplete and evolving evidence. This paper studies streaming
video emotion understanding as a reliability-aware decision process over evolving
emotion beliefs. In this setting, a single confident prefix prediction can still be unreliable when the underlying belief trajectory is unstable or repeatedly switches across
emotion classes. We propose TRACE, a trajectory-aware reliability framework that forms low-latency
emotion beliefs from streaming audio prefixes, estimates reliability from confidence,
entropy, stability, and class-switching patterns, and selectively invokes contextual belief reinterpretation with visual, textual, and neighboring-utterance evidence. TRACE keeps stable cases in the low-latency online pathway while allocating stronger
multimodal reasoning to uncertain cases that remain ambiguous. Experiments on StreamMER, MELD, and MER2024 show that TRACE improves the accuracy-cost trade-off, retaining most full-context gains while reducing unnecessary contextual
reasoning.
Read the full abstract ▾
All authors Qingsong Wang, Qigong Lei, Zitong Wang, Bohan Yu, Zhiang Dong, Jian liu, Weiqiang Wang, Chang Yao, Jingyuan Chen
Artificial Intelligence
AI Control Scientist: LLM-driven Agentic System for Automated Control Design
Haiteng Wang, Weihao Li, Jing Zhang et al. (+1 more)
Control system design is critical for modern industry, such as chemical process temperature regulation and aero-engine control. However,traditional control design workflows rely heavily on expert knowledge and extensive manual parameter tuning, resulting in limited efficiency and scalability. To this end, this paper proposes AI Control Scientist (AICS), the first large
language model (LLM)-driven
agent capable of automatically generating optimized controller from
language design requirements. Specifically, a Task Modeling
Agent interprets user requirements to engineering constraints; a Controller Design
Agent generate candidate controller structures and executable code; and a Parameter Tuning
Agent refine controller parameters under closed-loop performance criteria. Experiments demonstrate that the proposed agentic system can automatically generate multiple representative control systems, outperforms existing automated baselines in both design success rate and optimization efficiency. This work has the potential to transform control system design from human-driven to
agent-driven, paving the way for model predictive control and other advanced control systems design.
Read the full abstract ▾
All authors Haiteng Wang, Weihao Li, Jing Zhang, Lei Ren
Computation and Language
Instruction Quality Matters: Refining Instructions for Effective Preference Learning
Seohyeong Lee, Hwaran Lee and Buru Chang
Preference learning optimizes models using response pairs, yet the informativeness of these pairs is fundamentally shaped by the instructions from which they are generated. We identify instruction quality as a hidden bottleneck in preference learning: low-quality or ambiguous instructions restrict the response-quality distribution, limiting strong chosen responses and weakening preference signals. Through Best- and Worst-of-N analyses, we show that instruction quality constrains both the ceiling and floor of sampled response quality. Motivated by this observation, we introduce an instruction-refinement pipeline that selects weak instructions using reward signals and revises them with rubric-guided LLM feedback, improving preference data without discarding examples. Across offline and online preference learning settings, experiments on multiple models and
benchmarks show broad
alignment improvements over original data and alternative data-improvement strategies. Further analyses indicate that instruction refinement raises achievable response quality and complements response-centric preference data curation. Overall, instruction quality emerges as a key factor governing how informative preference signals are formed for LLM
alignment. Code is available at: https://github.com/01choco/instruction-refinement/
Read the full abstract ▾