Machine Learning · Cross-listed from physics.flu-dyn
Periodic Neural Mapping for Unsteady Rotor-Blade Pressure and Aeroelastic Load Prediction
Lionel Salesses, Joachim Dominique, Tariq Benamara et al. (+2 more)
Accurate prediction of unsteady aerodynamic loads remains a major challenge in turbomachinery design. High-fidelity Computational Fluid Dynamics (CFD) simulations are expensive, while aeroelastic Quantities of Interest (QoI) depend sensitively on the temporal
evolution of the pressure field. This work introduces periodic
Fourier Neural Mapping (p-FNM), a neural-operator framework for predicting unsteady pressure distributions on turbine rotor blades simulated using the chorochronic numerical hypothesis. The architecture embeds temporal periodicity into the model and learns a continuous mapping from operating conditions and time to pressure fields. Unlike sequential latent-space approaches, p-FNM predicts pressure fields independently at any time, avoiding error accumulation while preserving temporal continuity. The model is evaluated on a database of unsteady rotor-blade simulations and compared with a reduced-order baseline based on a variational autoencoder and recurrent neural network, refered as the Temporal Prediction Model (TPM). Performance is assessed for pressure fields and Generalized Aerodynamic Forces (GAFs), the primary aeroelastic QoI. Across all training
datasets, p-FNM consistently outperforms TPM. On the largest
dataset, p-FNM achieves a pressure-field mean absolute percentage error of 0.46% and a GAF-magnitude prediction error of 4.42%, corresponding to improvements of 60.7% and 77.6%, respectively. The minimum weighted phase error reaches 0.060 rad, demonstrating accurate preservation of the temporal characteristics of the aerodynamic response. The results show that GAF prediction is more challenging than pressure-field prediction and that temporal coherence is critical for accurately predicting spectral aerodynamic quantities. These findings demonstrate the potential of periodic neural operators for reduced-order modeling and aeroelastic analysis in turbomachinery.
Read the full abstract ▾
All authors Lionel Salesses, Joachim Dominique, Tariq Benamara, Théo Flament, Franck Mastrippolito
Robotics
A High-Payload Wall-Climbing Robot Using Passive Bistable Suction Cups
Andrew Nguyen, Mingyuan Li and Daniel Bruder
Wall-climbing
robots capable of scaling vertical surfaces could help automate hazardous or labor intensive tasks such as window washing, inspection, maintenance, and construction. Active adhesion methods achieve higher payload capacities, but require power to maintain their grip. Passive adhesion devices such as suction cups are an attractive option for such
robots because they do not require power to maintain their grip, but they are limited by their payload capacity. This work presents a novel high-payload wall-climbing
robot that utilizes passive bistable suction cups to generate adhesion without needing to be pushed into the wall. The
robot features a track-based system that automatically engages and disengages bistable suction cups to achieve locomotion on smooth surfaces. The
robot is able to achieve vertical wall climbing on glass, wood, metal, and painted surfaces, sideways and upside-down climbing, and is able to tow a payload of 7.940 kg (with a payload-to-weight ratio of 2.25).
Read the full abstract ▾
Neural and Evolutionary Computing
Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks
Aidin Attar and Michele Rossi
Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD)
datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both
datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.
Read the full abstract ▾
Robotics
Tilt as a Certified Resource: Preserving Motor Wrench-Rate Authority on Articulated Multirotors
Giuseppe Silano and Martin Saska
Fully-actuated multirotor aerial vehicles must not only track nominal wrenches but retain the "readiness" to modulate them rapidly under disturbances. Classical effort-minimizing allocators ignore this dynamic limit, whereas maximizing readiness leads to topologically disconnected optimal sheets demanding physically impossible actuator rates. Enforcing a readiness safety floor on fixed-geometry symmetric platforms further encounters a zero-sum degeneracy: motor-speed redistribution cannot improve authority without conceding wrench tracking. This paper uses active morphology to break the degeneracy, treating servo tilt as a
geometric resource supplying authority-recovery directions unavailable to static rotors. We construct a configuration-dependent, motor-only readiness certificate - the log-volume of the reachable wrench-rate set - that explicitly excludes servo capacity, preventing a "ghost capacity fallacy" in which the certificate would falsely credit slow mechanical kinematic limits instead of collapsing accurately at motor saturation. The certificate is enforced as a Control Barrier Function (CBF) within a Unified Physical-Command Quadratic Program acting on motor torques and servo setpoints. Closed-loop simulations of an articulated octorotor under severe gust disturbances show classical allocators diverging and uncertified articulated allocators violating the safety floor, while the proposed CBF filter bounds the system state and preserves vehicle authority.
Read the full abstract ▾
Computer Vision
GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression
Pinxin Liu, Haiyang Liu, Jiahao Luo et al. (+3 more)
Generating natural co-
speech gestures from streaming
speech is essential for
embodied conversational
agents, where motion must be produced while a user is still speaking. Recent streaming gesture systems make online generation possible by autoregressing over discrete motion
tokens, but this design compresses high-dimensional continuous motion into finite codebooks and can limit the realism and diversity of generated gestures. To preserve both causality and continuous expressiveness, we propose GestureFAR, a flow-autoregressive framework for streaming co-
speech gesture generation. First, GestureFAR autoregresses over causal continuous motion latents, using a
transformer to model streaming audio-motion context and a per-
token flow-matching head to sample the next latent from a continuous distribution. Second, we introduce a head-only flow
distillation strategy that freezes the causal backbone and distills the multi-step per-
token flow head into a single network evaluation using consistency and distribution-matching objectives. This keeps the model
token-causal while removing the main latency bottleneck for live interaction. Experiments on BEAT2 show that GestureFAR significantly improves the quality–latency trade-off among streaming-capable methods, preserving strong gesture quality while enabling real-time
token-causal generation. Project Page: https://andypinxinliu.github.io/GestureFAR
Read the full abstract ▾
All authors Pinxin Liu, Haiyang Liu, Jiahao Luo, Junhua Huang, Chunhao Zou, Luchuan Song
Cryptography and Security
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
Pedro Pereira, Eva Maia and Isabel Praça
Retrieval-Augmented Generation (RAG) improves large
language models by grounding outputs in external knowledge sources, but this dependency also creates a surface for poisoning attacks. This paper introduces Micro-Collaborative Poisoning, a distributed attack in which a false target claim is divided across multiple locally plausible documents instead of being concentrated in a single malicious passage. We evaluate the attack across 108 RAG configurations by varying
dataset, retriever architecture,
retrieval depth, database composition, number of poisoned databases, and generator model. The results indicate that Micro-Collaborative Poisoning is not driven by a single dominant poisoned passage, but by the accumulation of weak
adversarial signals across retrieved sources. Increasing top-$k$ and poisoning multiple databases make it more likely that these signals will appear together in the retrieved context, while clean database diversity and stronger retrievers can reduce their influence. The document-level poisoning visibility analysis further shows that this threat is difficult to expose through isolated document inspection, since Micro-Collaborative Poisoning achieves downstream influence while leaving a weaker explicit poisoning signature than direct poisoning.
Read the full abstract ▾
Robotics
SABER: Learning Attention-based Semantic Affordance for Legged Locomotion
Hari Prasanth Palanivelu, Samuel Sze, Kennard Garrison Johannes et al. (+2 more)
Perceptive legged locomotion has advanced rapidly by integrating terrain geometry into learned policies, yet the integration of terrain meaning remains sparse: a pipe, a patch of grass, or a fragile box may be geometrically traversable while being inappropriate for contact. In industrial environments, where legged
robots increasingly operate, a single misplaced step can damage fragile equipment, destabilize the
robot, or endanger the site. To address this, we introduce SABER, a planner-free reinforcement-learning policy that jointly reasons about terrain geometry and semantic contact permission. The policy consumes a unified terrain-affordance map, where each
cell encodes local 3D geometry and a semantic contact cost. We augment cross-
attention with a learned, signed semantic bias: an additive term on the
attention logits, gated by the contact cost, that reweights flagged
cells by their distance from the nearest foot. A hazard therefore reshapes
attention where it can still affect the next foothold, and its influence fades where it cannot. The resulting policy selects footholds on permitted support and keeps the leg clear of forbidden regions throughout the swing phase. We perform a systematic ablation that isolates the contribution of each architectural component; removing the semantic bias alone increases forbidden contacts by 55% while velocity tracking is unchanged. We validate the policy on a Unitree B2, demonstrating sim-to-real semantic contact selection across indoor and outdoor environments and four semantic obstacle classes.
Read the full abstract ▾
All authors Hari Prasanth Palanivelu, Samuel Sze, Kennard Garrison Johannes, Albertus Hendrawan Adiwahono, Meng Yee Michael Chuah
Multiagent Systems
CityLearn v3: A Configurable Simulation and Evaluation Framework for Realistic Control Studies of Renewable Energy Communities
Tiago Fonseca, Luis Lino Ferreira, Armando Sousa et al. (+2 more)
Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies often simplify changing participation, equipment availability, service deadlines and data quality, so lower cost or peak demand can conceal missed services or infeasible power requests. This paper presents CityLearn v3, a configurable simulation and evaluation framework for REC control studies under these conditions. It represents changing members and assets, flexible-load deadlines, demand-response requests, local energy sharing, and data or equipment failures within one simulation environment. Building and phase power limits constrain controllable requests, while a declared timestep preserves consistent power-to-energy accounting. The framework records controller inputs and distinguishes requested actions from those applied to the simulated equipment. Reference controllers, service- and constraint-aware performance indicators, and trajectory exports support comparisons within and across communities. Software checks and application examples examine service delivery, electrical constraints, settlement and changing scenarios; a synthetic high-frequency trace replay illustrates how aggregation can conceal short peaks without changing annual energy. Together, these records allow aggregate performance to be interpreted alongside service failures, action reductions and participant-level outcomes.
Read the full abstract ▾
All authors Tiago Fonseca, Luis Lino Ferreira, Armando Sousa, Ava Mohammadi, Zoltan Nagy
Cryptography and Security
Et Tu, MacBook? Unprivileged Keystroke Inference and Context Profiling via the Built-in IMU Side Channel
Jiaji He, Yi Shi, Junfeng Cai et al. (+2 more)
Recent generations of Apple MacBooks embed an inertial measurement unit (IMU) within their unibody chassis for device orientation and motion sensing. However, this IMU inadvertently captures not only intended device-level information but also subtle physical vibrations from user interactions and the surrounding environment. These signals establish a novel, previously unexplored side channel. We uncover a vulnerability allowing non-root access to IMU data via an IOKit driver, alongside two content-free system metadata interfaces (HIDIdleTime and CGEventSource) that further enrich the side-channel leakage. Through rigorous characterization of the IMU data, we reveal that the leakage spans three core dimensions: (1) keystroke identity (which key is typed), (2) desk surface (where the laptop is placed), and (3) user behavior (who is typing). Leveraging these findings, we introduce BRUTUS, the first comprehensive unprivileged side-channel attack targeting built-in IMU sensors on Apple MacBooks. BRUTUS achieves a character-level accuracy of 89.1% to 97.5% in key recovery. Furthermore, aided by
language models, it can successfully reconstruct certain sentences with 100% accuracy. For user identification and environment profiling, BRUTUS correctly discovers user and environment profiles without labels and correctly assigns subsequent segments to their corresponding profiles. Ultimately, this work highlights the urgent necessity of strictly regulating access to built-in IMU sensors.
Read the full abstract ▾
All authors Jiaji He, Yi Shi, Junfeng Cai, Chang Liu, Yongqiang Lyu
Computational Complexity · Cross-listed from quant-ph
Weighted Quantum Signal Processing: Low-Depth Polynomial Approximation with Applications to Kolmogorov-Arnold Networks
Rohit Sarma Sarkar, Rupayan Bhattacharjee, Elias F. Combarro et al. (+5 more)
Quantum Signal Processing is a powerful
quantum framework for generating and approximating univariate
polynomials. However, QSP is often limited by
circuit-depth bottlenecks and parity constraints on the class of realizable
polynomials. In this work, we introduce Weighted
Quantum Signal Processing, an extension of QSP in which a weight function is assigned to the central rotation operator. This formulation provides a deeper understanding of QSP, which emerges as the special case of WQSP with unit weights. The choice of weights determines the structure and expressive capabilities of WQSP
circuits. When the weights are natural numbers greater than one, WQSP reduces to a pruned version of QSP, revealing parameter redundancies in the standard framework. Through appropriate selection of integer weights, WQSP achieves linear-to-exponential reductions in the number of parameters required to realize arbitrary bounded univariate
polynomials while preserving approximation quality. For generic weights, we establish corresponding approximation error bounds and show that, in many cases, the approximation is exact. We analyze WQSP from both a deterministic perspective, where
polynomial generation is formulated as the solution of a linear system, and a
quantum machine learning perspective, where WQSP serves as a structured and expressive
quantum learning model. We further employ this learning framework to parameterize learnable activation functions in Kolmogorov–Arnold Networks for multivariate function approximation. Our results show that WQSP provides a compact, flexible, and theoretically grounded framework for realizing arbitrary univariate
polynomials while requiring significantly fewer trainable parameters than conventional QSP. This yields expressive and parameter-efficient neural architectures, highlighting the potential of WQSP as a scalable primitive for
quantum-enhanced machine learning.
Read the full abstract ▾
All authors Rohit Sarma Sarkar, Rupayan Bhattacharjee, Elias F. Combarro, Michele Grossi, Lirandë Pira, Carmen G. Almudéver, Sergi Abadal, Eduard Alarcon
Information Theory
Goal-Oriented Communication and Control Co-Design via Semantic Push-Pull in Industrial IoT
Muhammad Azeem Khan, Yuriy Zacchia Lun, Aamir Mahmood et al. (+3 more)
Emerging 6G industrial IoT architectures require wireless networked control systems capable of stabilizing diverse control loops over tightly constrained
radio resources. Conventional periodic and Age-of-Information (AoI) based scheduling guarantees bounded staleness at the cost of persistent channel saturation. Conversely, pure event-triggered (PureET) strategies minimize transmissions but risk catastrophic silent deterioration when local sensor-side thresholds fail to reflect critical state
evolution. To bridge this gap, we propose a communication-control co-design framework governed by a 6G Semantic Layer that independently arbitrates uplink and downlink resources. Instead of relying on freshness, our architecture evaluates the actual control impact of a packet using the state-to-error ratio (SER). We unify this control confidence with channel reliability in terms of signal-to-noise ratio (SNR) to orchestrate a threshold-based sensor push and a state-aware controller pull mechanism. To ensure equitable resource allocation across dynamically heterogeneous plants, the proposed framework explicitly scales actuation deadbands according to local plant dynamics. Simulations over Rayleigh-faded channels demonstrate that this approach fundamentally shifts the Pareto frontier between transmission rate and control quality. The proposed scheme achieves tracking accuracy comparable to periodic schedulers at a reduced communication overhead, while mitigating the estimation errors characteristic of PureET.
Read the full abstract ▾
All authors Muhammad Azeem Khan, Yuriy Zacchia Lun, Aamir Mahmood, Piergiuseppe Di Marco, Mikael Gidlund, Fortunato Santucci
Logic in Computer Science
Logics of Filter Bubbles
Lei Li and Jialiang Yan
Filter bubbles can be understood as configurations characterized by within-group proximity and separation from outsiders. Personalized feeds may form or preserve such configurations. We develop hybrid-style logics for
reasoning about filter bubbles. The static logic characterizes bubble-shaped configurations, while its dynamic extension captures their formation and persistence under personalized feeds. We provide sound and strongly complete axiomatizations for the static and dynamic logics and prove their decidability.
Read the full abstract ▾
Databases
kgsteward: a tool for building, reproducing and maintaining distributed knowledge graphs
Marco Pagni, Robin Engler, Frederic Burdet et al. (+15 more)
Collaborative research projects in life sciences increasingly need to integrate private, embargoed consortium data with public reference databases in order to reach statistically meaningful interpretations. The Resource Description Framework (RDF) is well suited to this task: it facilitates the integration of heterogeneous data sources, and allows researchers to keep data and their documentation as metadata in the same place, provided the knowledge graph itself remains private during the time course of the project. Nevertheless, the development and long-term maintenance of a scientific knowledge graph remains a challenging, labour-intensive endeavour owing to the state of constant flux of most public resources. To tackle this challenge, we present kgsteward, a Python command-line tool that builds and maintains knowledge graphs inside RDF stores from a single, version-controlled configuration file. kgsteward supports multiple triplestores, keeps the local graph up-to-date with its external sources possibly already in RDF, or transformed into it on the fly, and uses SPARQL 1.1 UPDATE commands to amend further imported RDF on the fly. It can also validate the resulting graph with SPARQL queries that double as usage examples for both human users and AI
agents. kgsteward has already been used in several collaborative projects at the SIB Swiss Institute of Bioinformatics, and we demonstrate its applicability in two real-world international research projects: one that builds a library of plant extracts with chemical analyses and associated bio-activities, and a second that reconciles public reference resources for human metabolic-network reconstruction.
Read the full abstract ▾
All authors Marco Pagni, Robin Engler, Frederic Burdet, Sebastien Moretti, Loic Le Gregam, Luis Quiros-Guerrero, Jahn Nitschke, Pierre-Marie Allard, Louis-Felix Nothias, Jack McGoldrick, Ronan M.T. Fleming, Alan Bridge, Vincent Emonet, Tarcisio Mendes de Farias, Ana-Claudia Sima, Mark Ibberson, Jean-Luc Wolfender, Florence Mehl
Information Theory
On the Fourier Entropy-Influence Conjecture for Boolean Plateaued Functions
Vladimir N. Potapov
We prove the following inequality for Boolean functions: $2\sum_{x\in F_2^n}f(x)wt(x)\geq wt(f)(n-deg(f))$. Using this inequality, we establish the
Fourier Entropy-Influence (FEI)
conjecture for Boolean plateaued functions. In particular, we show that the sharp FEI constant for the class of plateaued functions is 4. We also prove the FEI
conjecture for partially bent functions and show that the corresponding sharp constant is 2. Finally, we derive several estimates for the p-biased distribution on the Boolean hypercube. Keywords:
Fourier entropy, total influence, average sensitivity, plateaued function, algebraic degree, Reed-Muller code, p-biased distribution.
Read the full abstract ▾
Software Engineering
GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions
Xinyu Che, Yunfei Ge, Shihao Li et al. (+9 more)
Coding
agents can modify and test code across large software projects. Game development is a domain where
agents must implement gameplay rules. A game can end in a valid state even after violating its rules during the run. Current game-development
benchmarks replay fixed examples, score
videos, or ask another model to judge the result. However, no existing
benchmark checks game rules throughout execution across varied evaluator-selected scenarios while ensuring exactly reproducible verdicts. We introduce GameLogicBench, a
benchmark of 72 gameplay-logic tasks in Godot projects. An automated evaluator checks each game's rules at every simulation tick. Across 403 hand-designed scenarios, seeded parameter variations produce 1,451 test cases. To ensure that the evaluator measures behavior rather than implementation choice, it must accept different correct implementations for each task while rejecting mutants, implementations with one required capability removed. The tasks span isolated mechanics, multi-system interactions, and repository-scale features. Across 20 combinations of
language models and scaffolds, the best observed run solves 52.78% of tasks. Under Claude Code, all twelve models solve fewer tasks as task scope expands from isolated mechanics, through interacting systems, to repository-scale features.
Agents inspect code more often and make more tool calls on repository-scale tasks than on isolated-mechanic tasks. Most unsuccessful submissions are runnable, but implement some required game behavior incorrectly. We compared versions of our
benchmark evaluator built with and without validation using mutants. Without this validation, incorrect
agent submissions passed. A separate analysis finds
agents copying code from public repositories when network access is open. Reliable evaluation thus depends both on what the tests reject and on what external code
agents can access.
Read the full abstract ▾
All authors Xinyu Che, Yunfei Ge, Shihao Li, Yanchen Liu, Hang Yan, Xinping Lei, Yanghai Wang, Zixuan Dong, Yifan Yao, Qianqian Xie, Letian Zhu, Jiaheng Liu
Machine Learning
On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub et al. (+4 more)
On-policy self-
distillation provides dense,
token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution back into the model. However, privileged information can change not only what the teacher knows, but also how it behaves, entangling correctness-relevant learning signals with unintended behavioral shifts. We study this effect in
reasoning tasks by contrasting attractive self-
distillation, which moves the model toward a privileged teacher, with repulsive self-
distillation, which moves it away from a privileged teacher. We find that both objectives can induce strong and opposing behavioral shifts: attraction suppresses exploratory
reasoning and promotes shorter, more confident responses, whereas repulsion increases response length, can trigger unintended switches into a model's latent thinking mode, and ultimately becomes unstable. Motivated by these observations, we study contrastive self-
distillation, which combines attraction toward a correct-solution-conditioned teacher with repulsion from an incorrect-solution-conditioned teacher. In contrast to prior work that combines such
distillation signals with a GRPO objective, we isolate the self-
distillation objective and study its behavior on its own. We find that the shared behavioral shifts of the two teachers largely cancel, leaving a
token-level signal that more directly reflects correctness. Across non-thinking, instruct-only, and already-thinking models, this contrastive objective improves
reasoning performance while maintaining stable response lengths.
Read the full abstract ▾
All authors Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub, Frederike Lübeck, Jonas Hübotter, Thomas Kleine Buening, Andreas Krause
Logic in Computer Science
Compact Partial Symmetry Breaking for Graph Search Problems
Michael Codish, Mikoláš Janota and Peter J. Stuckey
Symmetry breaking in graph search problems remains challenging: complete
symmetry breaking constraints are typically exponential in size, while partial approaches trade precision for scalability. We introduce a strength-driven, redundancy-aware methodology for constructing compact partial
symmetry breaking constraints based on graph patterns. Each pattern corresponds to a Boolean clause over equality literals and can be integrated directly into CP or SAT models. Our approach incrementally selects strong, non-redundant graph patterns, yielding partial
symmetry breaks that achieve substantial
pruning of non-canonical graphs while remaining compact in size. This provides a principled framework for deriving lightweight partial
symmetry breaking constraints which are significantly more precise than all published state-of-the-art alternatives. We evaluate the proposed constraints on graph instances with up to 25 vertices using a redundancy ratio metric. The resulting partial
symmetry breaks constitute only a small fraction of the size of complete
symmetry breaking constraints, while delivering significant performance improvements across several graph search
benchmarks compared to previously defined partial
symmetry breaking methods.
Read the full abstract ▾
Computation and Language
MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance
Arash Lagzian, Srinivas Anumasa and Dianbo Liu
Recent advances in Large
Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancements, LLMs struggle with complex mathematical, scientific, and logical tasks. Inspired by human cognitive flexibility - our ability to dynamically switch mental perspectives - we propose MIRAGE (Multi-perspective Inference-time
Reasoning via
Agent-Guided Exploration), a novel inference-time creative thinking framework. MIRAGE includes a Selector that prioritizes effective conceptual perspectives (e.g., algebraic, probabilistic) and a Reasoner that sequentially solves tasks until a confident solution emerges, otherwise aggregating multiple perspectives. Tested on GSM8K, MATH500, MMLU-Pro, and Game-of-24
benchmarks, MIRAGE consistently outperforms methods like Chain-of-Thought and diverse prompting ensembles, significantly boosting accuracy with minimal inference overhead, providing a scalable solution for practical applications.
Read the full abstract ▾
Machine Learning
OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios
Yewen Li, Peng Jiang, Yitian Li et al. (+4 more)
Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has evolved from rule-based controllers to reinforcement learning and generative methods such as Decision
Transformer (DT). Yet these methods increasingly mismatch the prevailing optimized cost-per-X (oCPX) paradigm, which spans heterogeneous scenarios (e.g., registration, purchase), each served by a separate model, leading to fragmented pipelines and underexploring cross-scenario modeling. Inspired by foundation models like LLMs, unifying these oCPX scenarios into one model raises three challenges: multi-objective control, scalable capacity under strict latency, and safe offline policy improvement. We present OneBid, a unified auto-bidding foundation model that learns a reusable backbone from heterogeneous oCPX logs and adapts it to scenario-specific deployments via offline post-training. Building on DT, OneBid extends single Return-to-Go conditioning to two atomic signals, Return-to-Go for conversion value and Cost-to-Go for cost ratio, plus value-aware regularization on next-action prediction. To absorb distributional heterogeneity, we design a sequence-level Mixture-of-Experts architecture, where shared experts encode cross-scenario knowledge and sparsely-routed experts capture scenario-specific patterns at low latency, yielding consistent scaling with model size and data. During post-training, we align the backbone with scenario preferences via Critic-guided Relative Offline Policy optimization (CROP): a learned critic scores candidate actions group-relatively, avoiding the unsafe online exploration of GRPO-style fine-tuning while constraining policy shift to reduce OOD risk. Validated via online A/B tests and fully deployed at Kuaishou, OneBid delivers an overall +2.2% ADVV gain on oCPX Ads, peaking at +13.1% in the ROAS scenario.
Read the full abstract ▾
All authors Yewen Li, Peng Jiang, Yitian Li, Pengfei Lv, Xialong Liu, Peng Jiang, Qingpeng Cai
Artificial Intelligence
Dual-Interest Sequential Product Recommendation With Multi-Granular SSM
Shuiying Liao and P. Y. Mok
Sequential recommendation aims to predict the next item a user will interact with based on their historical behavior. Advances in
Transformers have significantly improved sequential recommendation but are still limited by cost efficiency. Although State Space Models (SSMs) have recently enabled efficient long-range modeling, most existing methods encode each item with a single static contextual role, overlooking the phenomenon of item polysemy. In fact, the same item often plays different semantic roles depending on user context, and existing methods are limited in capturing dynamic behavior across different temporal granularities. In this work, we propose DSRec, a novel dual-interest cross-SSM model that explicitly disentangles item roles across long-term and short-term semantic context. Sequential items are encoded into long-term interest
embeddings that capture stable preferences via historical aggregation, and a short-term interest branch that emphasizes local session intent modulated by inter-click time intervals. These interest
embeddings are processed through distinct SSM encoders: a full-sequence Mamba for long-term modeling, and a time-modulated SSM that dynamically adjusts state
evolution based on temporal gaps. To enable effective cross-granularity
alignment, we adopt a residual cross-fusion mechanism that exchanges contextual information between the two branches while preserving semantic independence. Experiments on public
benchmarks demonstrate that DSRec outperforms other state-of-the-art methods.
Read the full abstract ▾
Human-Computer Interaction
Do We Care About Personalization and Explainability? An Interview Study with News Recommendation Engineers
Jasmin Kareem, Siddharth Mehrotra, Martijn C. Willemsen et al. (+1 more)
Research on explainability in recommender systems largely centers on end users, overlooking the perspectives of those who build and maintain these systems and their potential use cases such as model debugging. In this study, we examine how news engineers and related technical stakeholders perceive and implement personalization and explainability in practice. We conducted 15 semi-structured interviews across nine news organizations, spanning diverse regions in both public and private sectors, to investigate the challenges and motivations shaping their approaches. Our findings reveal that personalization is not always a straightforward or desirable choice for news organizations, as concerns around user tracking, editorial control, and resource constraints often limit its adoption. Even among organizations implementing personalized news recommender systems in production, explainability is rarely prioritized, with day-to-day operational demands frequently taking precedence over longer-term transparency goals. Definitions of explainability vary widely across organizations, though some demonstrate promising internal practices and visualization tools that facilitate communication between engineering teams and newsrooms. Based on our analysis, we provide actionable and practical guidelines for news engineers and researchers on how to adopt explainability methods within a news personalization pipeline.
Read the full abstract ▾
All authors Jasmin Kareem, Siddharth Mehrotra, Martijn C. Willemsen, Maarten de Rijke
Software Engineering
Cross-Platform vs Native Mobile Development: An Empirical Study of Software Quality Trade-offs
Alexandru Ilovan
Cross-platform mobile frameworks promise code reuse, shorter delivery cycles, and lower implementation effort, but their trade-offs relative to native development remain difficult to assess objectively. Many comparisons rely on simplified applications, inconsistent feature sets, or a narrow set of metrics. This paper compares five implementations of the same plant-management application: native iOS, native Android, Flutter, React Native, and Kotlin Multiplatform. The shared approaches target both Android and iOS, yielding eight executable variants. Guided by ISO/IEC 25010, the study examines time behavior, implementation footprint, source-code organization, and observable rendering responsiveness. All implementations share the same domain, backend services, functional requirements, and
benchmark contract. The supplied
dataset contains 2,000 completed runs per variant and covers authenticated and cached
retrieval, image transfer and decoding, list rendering and scrolling, local synchronization, and media upload. Backend preparation and framework-specific UI drivers are analyzed separately from the primary client workflow. Native records the lowest non-UI client subtotal on both operating systems, with Kotlin Multiplatform the closest cross-platform implementation, while operation and UI-wrapper rankings vary by task. The shared approaches contain less authored mobile source than the native applications combined, and the source inventory shows different patterns of file size, organization, and dependency use. Rather than identifying a universally superior technology, the study shows that each approach's advantages and costs depend on the quality attribute, workload, platform, and measurement boundary.
Read the full abstract ▾
Computer Vision
From Retrieval to Recognition:How Vision–Language Models Become OCR Specialists
Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen et al. (+1 more)
Does a general
vision–
language model acquire specialized OCR ability by developing a new reading
circuit or by reusing an existing mechanism? We address this question in the setting of full-sequence OCR, rather than local-answer
retrieval. Using an evidence-grounded protocol with held-out causal interventions, we identify sparse and stable OCR-head sets in GLM-OCR, MinerU2.5, and PaddleOCR-VL-1.6. We then investigate the mechanistic origin of these OCR heads by comparing them with independently identified textual
retrieval/copy heads in general VLMs. Across two general VLMs, visual OCR heads strongly overlap independently identified textual
retrieval/copy heads, yielding untuned top-20 intersections of 73.3% and all-head Spearman correlations of 0.677-0.886. The overlap and causal interventions suggest that full-sequence OCR operates as dense sequential
multimodal copy-and-paste, repeatedly retrieving visual evidence and routing it to the current output position. Finally, we examine how this shared
circuit changes as a general VLM becomes an OCR specialist. Matched base-to-specialized comparisons show that OCR specialization largely preserves head identity, retaining 17-20 of the top 20 heads per task with all-head rank correlations of 0.874-0.942, while redistributing their functional and causal strengths.
Read the full abstract ▾
All authors Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen, Jeffrey Tiong Jee Hui
Computer Vision
Purification and Regulation: Comorbidity-Aware Multi-Label Few-Shot Learning for Medical Image Classification
Ying-Chih Lin, Po-Chih Kuo and Yong-Sheng Chen
Multi-label few-shot learning (MLFSL) remains a significant challenge in medical image analysis (MIA). Current metric-based meta-learning methods face two critical limitations in MIA. First, conventional prototype generation often entangles irrelevant disease information, leading to contaminated prototypes and degraded performance. Second, prior studies typically enforce inter-class separability in
embedding space, largely neglecting the inherent correlations among diseases. To overcome these challenges, we propose Prototype Purification and Regulation (PPR), a novel MLFSL framework for MIA. PPR first performs prototype purification by leveraging sample-level comorbidity scores to emphasize disease-specific features, producing purified prototypes that better characterize each disease. Building upon these purified prototypes, PPR further addresses the underexplored problem of inter-class prototype distance in MIA by incorporating disease-level comorbidity statistics to adaptively regulate inter-class similarity, forming a comorbidity-aware
embedding space. Overall, PPR sequentially enables the model to capture pure disease features and inter-class relationships for reliable MLFSL in MIA. Extensive experiments across four chest X-ray
benchmark datasets, including cross-domain evaluation, show that PPR consistently outperforms state-of-the-art methods, significantly improving disease detection while demonstrating robust generalization and clinical applicability.
Read the full abstract ▾
Numerical Analysis
Element-wise Convergence Behavior of Subspace Iteration
Mingyang Zhao
This paper studies the element-wise convergence behavior of subspace iteration. All results are established for both \(\mathbb{F}=\mathbb{R}\) and \(\mathbb{F}=\mathbb{C}\). For a diagonal
matrix \(\Lambda=\mathrm{diag}(\lambda_1,\ldots,\lambda_n)\) with \(|\lambda_1|>\cdots>|\lambda_n|>0\), we analyze the modulus of each entry of the iterative
matrix sequence generated by subspace iteration, both without and with the Rayleigh–Ritz procedure. Under mild assumptions on the initial
matrix \(X\in\mathbb{F}^{n\times m}\), we first derive exact asymptotic expressions for \(|Q_k(i,j)|\) in the subspace iteration without the Rayleigh–Ritz procedure: entries with \(i\neq j\) decay as \(|\lambda_{\max\{i,j\}}/\lambda_{\min\{i,j\}}|^k\), and the deviation of \(|Q_k(j,j)|\) from \(1\) decays as \(\max\{|\lambda_j/\lambda_{j-1}|,|\lambda_{j+1}/\lambda_j|\}^{2k}\), with explicit coefficients determined by the LU factorization of \(X\). Similar conclusions could also be established for upper triangular
matrices. For the Rayleigh–Ritz variant, we obtain element-wise asymptotic formulas for the normalized Ritz vectors \(Z_k\). Specifically, for \(|Z_k(i,j)|\), off-diagonal entries with \(i\geq m+1\) decay as \(|\lambda_i/\lambda_j|^k\), off-diagonal entries with \(i\leq m\) decay as \(|\lambda_{m+1}^2/(\lambda_i\lambda_j)|^k\), and the deviation of \(|Z_k(j,j)|\) from \(1\) decays as \(|\lambda_{m+1}/\lambda_j|^{2k}\). These results give an element-wise description of the convergence behavior of subspace iteration. After an orthogonal or
unitary change of basis, the results could be further generalized.
Read the full abstract ▾
Machine Learning
Kairui Yang, Minghao An, Xunkai Li et al. (+4 more)
LLM-based multi-
agent systems generate collaboration traces that record how
agents plan tasks, verify intermediate results, and repair failures. Reusing these procedures requires preserving an action's prerequisites and the outputs needed by subsequent
agents. Our empirical studies show that grouping these dependencies into functional
memory units improves their retention, while connecting units increases
retrieval of the units and links jointly required by a task. The preferred combination of units also changes between instructions and checklists, even when each combination's content is fixed across formats. Updating choices from the outcomes of each combination and format pairing outperforms scoring combinations and formats separately. These findings motivate MACE, a
memory-
agent co-
evolution framework that adapts
memory organization and
agent memory use through execution feedback. Its MemGoG structure represents functional units as subgraphs of related conditions, actions, and outputs, connecting them through support, conflict, and repair relations. MACE Loop selects task-relevant units and relations within a
memory budget and provides each
agent with instructions or checklists for its current operation. It records the selected units, presentation formats,
agent outputs, and task outcomes to update unit scores and relations for
retrieval and inform subsequent presentation choices. Across eight
benchmarks, MACE outperforms ten baselines with an average score of 81.11%, compared with 78.97% for the strongest baseline, SAGE.
Read the full abstract ▾
All authors Kairui Yang, Minghao An, Xunkai Li, Ziheng Yi, Zekai Chen, Guangyuan He, Rong-Hua Li
Cryptography and Security
Critical sets of Latin squares based on autoparatopisms
Manuel González-Regadera, Raúl M. Falcón and María Dolores Frau
In cryptography, critical sets of Latin squares have particularly been implemented to design secret sharing schemes. A main problem in these cryptographic protocols arises from absent holders of pieces of information that are common to different critical sets, because they become indispensable to recover the secret. This paper solves this problem by making use of the orbits of entries described by the autoparatopism group of the Latin square under consideration. To this end, we introduce the more general problem of computing critical sets of Latin squares having a given paratopism in their autoparatopism group. These critical sets depend only on the conjugacy class of the autoparatopism and the main class of the Latin square under consideration. Based on this fact, as an illustrative example, we determine the smallest and largest sizes of critical sets associated with autoparatopisms of Latin squares of order up to six. We implement this approach in the design of a new secret sharing scheme.
Read the full abstract ▾
Machine Learning
OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems
Kairui Yang, Xunkai Li, Kaixiang Zhang et al. (+4 more)
Graph-enhanced multi-
agent systems (G-MAS) coordinate large
language model
agents through communication graphs and role assignments, which determine how
agents exchange information and divide responsibilities. However, final-score comparisons across systems combine differences in models, communication patterns, roles, and computation costs, making performance differences difficult to attribute to specific communication structures, role assignments, and information flows. To address this evaluation attribution problem, we introduce OpenMAS-GCom, a
benchmark for diagnosing how these components affect G-MAS performance through controlled interventions. We represent systems through collaboration units, communication links, shared intermediate information, and execution rules. OpenMAS-GCom compares original systems with versions modified by changing one component while keeping tasks, models,
prompts, and budget limits fixed. We rewire communication edges, remove specialist or critic
agents, replace intermediate messages with incorrect content, and disable workers during execution. The
benchmark evaluates 17 single-
agent, ordinary multi-
agent, and graph-enhanced configurations on 29
datasets across six domains. We add 400 G-MAS-Complex tasks requiring
agents to combine information from multiple documents, resolve conflicting records, and return specified values with source identifiers. Experiments show larger mean losses after specialist removal than after critic removal, different performance degradation under incorrect messages and worker failures despite similar original scores, and different configurations achieving the highest accuracy and accuracy per
token on G-MAS-Complex.
Read the full abstract ▾
All authors Kairui Yang, Xunkai Li, Kaixiang Zhang, Minghao An, Zekai Chen, Yuxuan Ba, Rong-Hua Li
Machine Learning
IncentRL: The Trade-Off Between Preference Guidance and Task Performance
Xuening Wu, Yanlan Kang and Shenqin Yin
Preference-based reward shaping can guide reinforcement learning, but adding preference signals to the reward may unintentionally change the task being optimized. We address this problem with IncentRL, a framework that introduces preference guidance while explicitly characterizing its effect on external-task performance. IncentRL adds a Kullback–Leibler (KL) penalty between a specified outcome distribution and a preferred distribution. For finite discounted Markov decision processes with bounded shaping costs, we derive an external-value perturbation bound, establish a sufficient strict-action-gap condition for preserving the original optimal policy, and characterize the large-weight regime through discounted cumulative preference cost. Exact examples clarify the limits of these guarantees, including tied optima and support mismatch. We study a practical implementation using a hand-designed, distance-based outcome proxy, a fixed preference distribution, and score-weighted coefficient search. On MiniGrid DoorKey-8x8, the reported three-seed mean success rate after two million training steps reaches 98% with coefficient 0.01, compared with 90.5% for the reported zero-coefficient baseline, while the search progressively shifts toward smaller coefficients. Together, these results provide a principled view of the central trade-off in preference-based RL: using additional guidance to improve learning without excessively distorting the original task objective. The current experiments remain descriptive and do not yet isolate KL shaping from simpler alternatives.
Read the full abstract ▾
Numerical Analysis
A Priori and A Posteriori Error Estimates for a Crank Nicolson Type Scheme of an Elliptic Problem with Dynamical Boundary Conditions
Rola Ali Ahmad, Toufic El Arwadi, Houssam Chrayteh et al. (+1 more)
In this article we claim that we are going to give a priori and a posteriori error estimates for a Crank Nicolson type scheme. The problem is discretized by the finite elements in space. The main result of this paper consists in establishing two types of error indicators, the first one linked to the time discretization and the second one to the space discretization.
Read the full abstract ▾
All authors Rola Ali Ahmad, Toufic El Arwadi, Houssam Chrayteh, Jean-Marc Sac-Épée