Artificial Intelligence
GOD: Govern, Observe, and Direct - A Real-Time Control Room for Agent Societies
Yige Luo and Ran Guan
Generative-
agent systems are easier to start than to inspect. A run can contain many
agents, locations, messages, commands, and model calls, yet the operator often gets either a finished replay or raw logs. That makes it hard to ask why an
agent moved, test a small intervention, or package a run for another researcher. GOD is a local-first control room for
agent societies. From the same browser workflow, an operator can issue targeted questions or interventions and inspect the resulting replay state. The system combines a setup wizard,
Agent Studio, Map Studio, a spatial replay interface, Ask and Intervene commands, and portable experiment, map, and
agent packs. Its technical contribution is the command and artifact loop: live controls and replay evidence share the same operator command model, while package contracts separate scenario, map, and profile data from local runtime state. The public release includes hosted Smallville-style and PKU replays, the open-source repository, and downloadable packs. We evaluate this path on 15 completed run slots. Across the 14 intervention runs, 78 of 84 target-
agent checks recorded the commanded destination, and 169 of 182 state answers matched a saved location or action string.
Read the full abstract ▾
Information Retrieval
HubMixer: Progressive Latent Hub Mixing for Parameter-Efficient Feature Interaction in Recommendation
Jie Zhou, Zixian Gong, Wenhao Li et al. (+6 more)
Learning effective feature interactions is central to industrial recommendation and advertising ranking systems. Recent
token-mixing architectures simplify self-
attention with lightweight mixing operators, improving hardware efficiency and enabling large-scale deployment. However, recommendation
tokens are fundamentally heterogeneous: user profiles, item attributes, behavioral sequences, context features, statistical signals, and business-side features live in different semantic spaces and interact in sparse, sample-specific patterns. Directly mixing all
tokens in the raw heterogeneous
token space may therefore be parameter-inefficient, as the model must implicitly discover which feature groups should interact and how such interactions should be routed. In the paper, we propose HubMixer, a parameter-efficient latent hub mixing architecture for feature interaction in recommendation. Instead of directly mixing raw feature
tokens, HubMixer introduces a small set of learnable latent hubs to organize feature interactions through an `induction–interaction–readout` paradigm. First, hub induction summarizes heterogeneous
tokens into compact latent hubs, where latent hubs query input
tokens through cross-
attention. Second, hub interaction performs high-order interaction in the cleaner latent hub space. Third,
token-conditioned readout lets each original
token selectively read from the interacted hubs, injecting global interaction semantics while preserving
token-level field identity. Extensive offline experiments on industrial recommendation tasks show that HubMixer outperforms the SOTA models. Online A/B testing in the Kuaishou short-
video recruitment business further shows a statistically significant 5.48% improvement in resume submission conversion rate, and HubMixer has been fully deployed in production.
Read the full abstract ▾
All authors Jie Zhou, Zixian Gong, Wenhao Li, Chang Liu, Enzhao Shen, Bo Liu, Xu Guo, Fei Pan, Peng Jiang
Cryptography and Security
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Zi Liang, Xiaoyu Xu, Yanyun Wang et al. (+3 more)
Prompt injection attacks on Large
Language Model (LLM)
agents seek to introduce malicious instructions or content into external text sources retrieved by
agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known injection attacks, deploying them in LLM
agent environments remains challenging due to attack variants and emerging threats. Moreover, existing solutions typically suffer from an inherent trilemma, i.e., a constant trade-off among runtime efficiency, contextual precision, and adaptability. To bridge this gap, we propose Continuous
Agents for Injection Threats via Lifelong Yielding Nexus (CAITLYN), an
agent-agnostic defense middleware. CAITLYN integrates two systems. System I focuses on immediate defense against existing attacks using a two-tiered library: Tier-0 for rule-based detection scripts and Tier-1 for optimized LLM-based accurate inference. System II, in contrast, is deployed to monitor potential abnormal signals and attempt to synthesize new defenses. On standard
benchmarks, CAITLYN matches the detection performance of state-of-the-art defenses at lower
token overhead than LLM-as-a-judge baselines. On Emerging, our new delivery-aware
benchmark featuring novel injection techniques, static baselines and the standalone System I configuration remain vulnerable. In contrast, System II autonomously synthesizes verified defense capabilities, substantially lowering the attack success rate across three diverse
agent environments.
Read the full abstract ▾
All authors Zi Liang, Xiaoyu Xu, Yanyun Wang, Minxin Du, Qingqing Ye, Haibo Hu
Computer Vision
GAN-Based Semantic Communication for Image Transmission in IoV
Ruixing Ren, Shan Chen, Junhui Zhao et al. (+1 more)
For cooperative perception in the internet of vehicles, this paper proposes a generative
adversarial network-based semantic communication framework to address the efficiency and fidelity bottlenecks of traditional communication systems in visual data transmission under limited bandwidth and dynamic channel conditions. At the transmitter, the framework adopts a pyramid
attention network to extract semantic label maps and introduces a semantic priority preservation mechanism. It assigns differentiated weights to distinct semantic categories based on driving safety, guiding bit allocation and loss function design. At the receiver, an image reconstruction module integrating a coarse to-fine multi-resolution generator and multi-scale discriminator is designed. Combined with the temporal consistency branch, spatial pyramid pooling and class-aware convolutional layers, it achieves high-fidelity reconstruction of high-quality images from corrupted semantic labels. The model is trained with combined
adversarial, feature matching and perceptual losses, effectively improving semantic consistency and visual realism of generated images. Experimental results on the Cityscapes
dataset show that the proposed method outperforms existing counterparts in both semantic
segmentation accuracy and reconstructed image quality, and maintains stable reconstruction performance under AWGN and Rayleigh channels.
Read the full abstract ▾
All authors Ruixing Ren, Shan Chen, Junhui Zhao, Xiaoke Sun
Computation and Language
Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness
Mark Dourado, Karim Haddad, Henrik G. Hassager et al. (+1 more)
Smooth speaker transitions are fundamental to effective conversation and rely on an interlocutor's ability to predict when to enter the conversation. This ability depends on accurately interpreting and expressing the verbal and non-verbal cues that signal when a speaker wishes to take or relinquish the floor. The process becomes even more complex in noisy, natural, multi-party settings, with multiple interlocutors available. This study models how gaze and
speech, together with perceived interpersonal closeness, signal conversational floor changes in free four-person dialogue. Using the GaMMA corpus, we trained logistic regression models using interpretable, behaviourally motivated features extracted before each turn-taking event to classify floor-transfer outcomes as gaps or overlaps. Predictors included gaze features such as transition motifs and behavioural contrasts,
entropy, gaze-based addressee identity, and mutual gaze, alongside
speech features derived from speaker loudness, as well as perceived interpersonal closeness (IOS) between speakers. Results show that gaze features capture predictive structure, and that combining them with loudness improves performance (ROC AUC = 0.76 +- 0.04). Loudness reflected speaker control, while gaze dispersion and addressing indexed listener readiness and competitive entry. Performance remained robust across noise conditions, indicating that gaze provides a complementary, noise-resilient cue to turn-taking dynamics.
Read the full abstract ▾
All authors Mark Dourado, Karim Haddad, Henrik G. Hassager, Stefania Serafin
Data Structures and Algorithms
A Simpler Analysis of the Bansal-Jiang Quasi Monte-Carlo Algorithm via Haar Wavelets
Jiaheng Chen, Agastya Vibhuti Jha and Haotian Jiang
Numerical integration—approximating the integral of a function $f$ using $n$ point evaluations—is a central task in science and engineering. The two main paradigms for this problem, the Monte Carlo and quasi-Monte Carlo methods, have distinct strengths and limitations, and a fundamental question is to design a method that combines the benefits of both. \smallskip Building on recent algorithmic advances in discrepancy theory, Bansal and Jiang \cite{BJ25a} gave a randomized QMC method that naturally bridges the MC and QMC error guarantees. Their method also achieves a surprising improvement over the classical Koksma–Hlawka inequality for QMC methods: it attains an error bound of $\widetilde{O}(\sigma_{\mathsf{SO}}(f)/n)$, where $\sigma_{\mathsf{SO}}(f)$ is a new notion of smoothed-out variation that they introduced and showed to be substantially smaller than the Hardy–Krause variation governing the classical bound. \smallskip However, the analysis in \cite{BJ25a} is quite involved: it must carefully exploit the structure of the dyadic decomposition and the randomness of the
algorithm inside a sufficiently fine discretization of the Hlawka–Zaremba formula to obtain cancellations among the high-frequency components in the
Fourier decomposition of $f$. The contribution of this article is twofold: (1) We give an equivalent characterization of $\sigma_{\mathsf{SO}}(f)$ in terms of the Haar–Besov seminorm of $f$, relating this new notion of smoothed-out variation to classical quantities. (2) Through this characterization, we provide a conceptually simpler and more direct analysis of the Bansal–Jiang QMC method via Haar decomposition, bypassing the use of the Hlawka–Zaremba formula,
Fourier decomposition, and the delicate cancellation arguments of \cite{BJ25a} that heavily exploit the structure of dyadic decomposition.
Read the full abstract ▾
Machine Learning
Is Monte Carlo Tree Search Just Every-Visit Monte Carlo Control?
Xianyi Wu
Monte Carlo Tree Search (MCTS) and every-visit Monte Carlo (MC) control are usually presented as different methods. MCTS is described in the
language of search (selection, expansion, simulation, and backup), whereas MC control is described in the
language of reinforcement learning (trajectory sampling, return estimation, action-value updating, and policy improvement). This note argues that, at the level of trajectory generation and action-value updating, the distinction is largely terminological. The tree policy and rollout policy can be viewed as the learned and not-yet-learned parts of a single evolving policy; expansion corresponds to first visit and initialization; and backup is the ordinary every-visit Monte Carlo update. Under this interpretation, the four stages of MCTS reduce to two basic operations: trajectory sampling under the current policy and every-visit Monte Carlo updating. In this sense, MCTS is simply every-visit Monte Carlo control expressed in the
language and data structure of search. The purpose of this note is expository: to make this equivalence explicit and easier to recognize.
Read the full abstract ▾
Artificial Intelligence
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
Yangxiao Jiang, Jiarun Fan, Mingcong Xu et al. (+6 more)
Multi-
Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration
topologies. However, existing
topology generation methods rely primarily on the parametric knowledge of large
language models, with external search or
retrieval used only as a reactive tool rather than an explicit determinant of collaboration structure. This leads to structure-knowledge misalignment, where systems exhibit redundant interactions or insufficient verification in knowledge-intensive tasks. We propose K-GAT (Knowledge-Guided
Agent Topology Generator), a neuro-symbolic framework that formulates collaboration
topology design as a knowledge-conditioned structure learning problem, integrating external evidence directly into autoregressive graph generation. Extensive experiments on knowledge-intensive
benchmarks demonstrate K-GAT's efficiency and effectiveness: notably on the expert-level GPQA
dataset, K-GAT outperforms the LLM-Debate baseline by a substantial margin of +15.7% in accuracy, while consuming less than half the computational
tokens.
Read the full abstract ▾
All authors Yangxiao Jiang, Jiarun Fan, Mingcong Xu, Yanxi Guo, Jiwen Feng, Shanqing Xu, Mengchen Qian, Wei Chen, Xiaojin Zhang
Artificial Intelligence
Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling
Siyuan Gan, Yuhan Li, Xiran Wang et al. (+6 more)
Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) is a prominent variant of Group Relative Policy Optimization (GRPO). DAPO introduces several improvements over GRPO. Among these, Dynamic Sampling contributes the most to DAPO's accuracy gains relative to GRPO. To improve accuracy, Dynamic Sampling enhances training stability by eliminating zero policy gradients from zero advantages. Specifically, it avoids such zero gradients by filtering out
prompts where sampled responses are either entirely correct or incorrect. However, our theoretical analysis shows that Dynamic Sampling decrease training efficiency as it cannot effectively utilize hard-to-sample correct responses on hard
prompts. Formally, it asymmetrically amplifies the advantages of distinct responses to the same
prompts. On hard
prompts, incorrect responses undergo greater amplification than correct ones. This leads the model to avoid generating the observed incorrect responses rather than capitalizing on the hard-to-sample correct ones on hard
prompts, resulting in low training efficiency. To improve training efficiency, we propose Direct Advantage Amplification (DAA), which amplifies the advantages of hard-to-sample correct responses on hard
prompts, as obtained by Dynamic Sampling. This ensures that, when Dynamic Sampling is used, these hard-to-sample responses can be effectively capitalized on, implying higher training efficiency. By integrating DAA into DAPO, we obtain Difficulty-aware Advantage Amplification Policy Optimization (DA3PO), which is implemented with fewer than 30 lines of code from DAPO. Experiments show that DA3PO significantly outperforms GRPO and other classical GRPO variants.
Read the full abstract ▾
All authors Siyuan Gan, Yuhan Li, Xiran Wang, Linjian Meng, Boyan Wang, Zhen Zhao, Jing Huo, Lei Bai, Yang Gao
Cryptography and Security
CHISEL-ing Back Source Code with AI-enabled Iterative Recovery
Varun Kohli, N Raghava, Biplab Sikdar et al. (+1 more)
Decompilation aims to recover high-level, compilable, and semantically equivalent code from binaries. Traditional decompilers produce pseudo-C that is difficult to read and does not compile, while the recent LLM-assisted approaches generate readable, but semantically incorrect code. LLM-aided iterative recovery is an emerging branch of research, but prior works rely on supplied test suites for semantic recovery. In this work, we present CHISEL, a test suite-free framework to iteratively recover source code from Ghidra-derived pseudo-C. CHISEL uses simple yet effective feedback from a compiler (static analysis) and a coverage-guided fuzzer (differential analysis), augmented by rich observables for grounded divergence detection and feedback, cross-iteration divergence
memory, and best candidate retention. We systematically evaluate CHISEL for compilation and semantic recovery, feedback oracle soundness, and iteration overhead on 120 ExeBench functions compiled for the x86-64 architecture, across four optimizations (O0-O3), in both stripped and unstripped variants, using the open-weight Gemma4:31b LLM. CHISEL, with all recommended features, achieves an average of 96.1% re-compilability and 79.8% re-executability rates at an average of 2.1 iterations. Significantly, CHISEL recovers 26% of first-generation execution errors. At the same time, CHISEL feedback oracle falsely accepts only 9.4% candidates. Lastly, CHISEL performs significantly better than two recent prior work on LLM-assisted decompilation.
Read the full abstract ▾
All authors Varun Kohli, N Raghava, Biplab Sikdar, Dinil Mon Divakaran
Machine Learning
PhyMamba: Physics-Modulated Mamba for Robust Battery Health Prognostics
Sara Sameer, Yunyi Zhao, Wei Zhang et al. (+4 more)
Battery health prognostics is a core function in battery management systems (BMSs), yet long-horizon health
forecasting from BMS signals remains challenging due to operating-condition dependency and sensor noise. In this paper, we propose PhyMamba, a two-stage physics-modulated Mamba framework that integrates electrochemical aging into sequence modelling. PhyMamba does not require explicit identification of internal aging parameters, which often relies on intrusive measurements. In stage-1, a lightweight Mamba encoder first processes BMS signals and produces a latent representation that is transformed via an aging parameterization module, into physics-informed aging features. In stage-2, a customized Mamba
forecasting backbone performs multi-cycle prediction, where physics is tightly integrated to regulate the model's internal temporal updates toward degradation-consistent
evolution. Experiments on three public
datasets under multiple forecast horizons show that PhyMamba achieves the best aggregated performance, with an overall mean error reduction of 31.8% compared with a diverse range of baselines. PhyMamba also offers an optimized accuracy-efficiency trade-off, which supports practical deployment for robust battery health prognostics.
Read the full abstract ▾
All authors Sara Sameer, Yunyi Zhao, Wei Zhang, Minggang Zeng, Wenqing Li, Man-Fai Ng, Yonggang Wen
Distributed Computing
Learning-Augmented Heuristics: Simple, yet Smart, Robust and Interpretable Cache Eviction
Haocheng Xia, William Nixon, Bintang Dwi Marthen et al. (+2 more)
Caching is widely used across the system stack to improve performance and efficiency, with eviction
algorithms at its core. Existing cache eviction policies fall into two broad categories: static heuristics (e.g., 2Q, S3-FIFO) and smart
algorithms (e.g., ARC, LRB). Smart caches can adapt to workloads and have the potential to achieve higher efficiency and robustness than static heuristics. However, we find that existing smart caches suffer from objective mismatches and instability. We introduce Learning-Augmented Heuristics (LAH), a framework that learns the cache-level parameters of static heuristics. By decoupling the data and control planes, LAH supports simple, high-speed data reads and writes on the data plane, while performing occasional asynchronous learning on the control plane using cache-level features. We demonstrate the effectiveness of LAH through S4-FIFO, a Smart S3-FIFO cache eviction
algorithm. We pre-train a single model on 4,140 production traces and embed it in S4-FIFO to learn optimal cache parameters. On 1,035 evaluation traces, S4-FIFO improves the mean efficiency by 26% compared to S3-FIFO and by 8% compared to 3L-Cache, the best state-of-the-art
algorithm. S4-FIFO is also robust—increasing miss ratio over FIFO by 0.8% on the worst trace, whereas 3L-Cache increases FIFO's miss ratio by 8.8%. Finally, S4-FIFO's decisions are also interpretable: a
language model can provide a rationale for why a particular configuration was chosen.
Read the full abstract ▾
All authors Haocheng Xia, William Nixon, Bintang Dwi Marthen, Pranav Bhandari, Juncheng Yang
Computation and Language
QUORUM: QUality-Optimized Routing Using Multiple annotators
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu et al. (+2 more)
Data annotation remains a central bottleneck in natural
language processing, requiring human effort to obtain high-quality labels at scale. While Large
Language Models (LLMs) offer a fast and cost-effective alternative, their reliability is highly instance-dependent: they perform well on simple inputs but often fail on examples requiring nuanced
reasoning or contextual understanding. In this work, we address this challenge with QUORUM (QUality-Optimized Routing Using Multiple annotators), a budget-aware routing framework that dynamically assigns each instance to human or LLM annotators under a fixed annotation budget. Unlike prior approaches relying on model confidence or uncertainty estimates, QUORUM leverages feature-based signals to estimate instance difficulty and supports multiple annotations per instance, combining them through agreement-based rewards to improve reliability. We evaluate QUORUM across diverse closed- and open-ended annotation tasks in English and
multilingual settings, and QUORUM improves annotation quality by up to 34.4% while reducing costs by 8.8% over competing methods. Code can be found at https://github.com/amazon-science/QUORUM.
Read the full abstract ▾
All authors Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu, Amin Mantrach, Fabrizio Silvestri
Computer Vision
Jingpu Yang, Debin Tang, Yilin Sun et al. (+4 more)
Unmanned aerial vehicle (
UAV)
multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scene understanding under diverse conditions. However, differences in optics, resolution, and mounting often limit practical systems to global or image-center
alignment. After tokenization, parallax, platform motion, and lens distortion can shift corresponding patch centers across modalities, weakening the spatial correspondence assumed by dense contrastive learning and cross-modal fusion. We propose GAAT (Geometry-Aware
Alignment Transformer), an
alignment-first pretrained model that estimates local correspondence reliability before cross-modal interaction. GAAT introduces syncPATC, which learns patch-center consistency under synchronized view transformations without correspondence annotations. It emits
geometric priors, including
token and query confidence, query centers, and sub-
token offsets, that identify reliable local anchors across residual misalignment. Guided by these priors, MG-Sparse-MMA performs query-mediated sparse fusion over top-K_s reliable regions, replacing dense all-patch interaction with geometry-calibrated local updates. RA-QCGCL aligns pretraining supervision with this sparse query bottleneck through reliable patch-to-patch, patch-to-query, and query-to-query contrastive branches. We introduce UAVMeta and StateBench, which provide four acquisition-state scores derived from platform telemetry and image statistics: camera reliability, observation scale, viewpoint stability, and flight maneuver complexity. Extensive experiments across six downstream tasks demonstrate consistently superior transfer performance, establishing GAAT as a state-of-the-art
multimodal foundation model for
UAV perception. StateBench further enables a systematic diagnosis of real-world acquisition conditions.
Read the full abstract ▾
All authors Jingpu Yang, Debin Tang, Yilin Sun, Fengxian Ji, Jiahua Zhu, Wenrui Ding, Yufeng Wang
Artificial Intelligence
openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
Tao Yu, Xinyu Zhang, Qianqian Chen et al. (+16 more)
Long-horizon coding
agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated
agents, and multi-
agent coordination. These trends pose two complementary challenges for the
agent harness. First, developers need to compose capabilities, reconfigure execution logic, and scale increasingly complex
agent systems without repeatedly rebuilding orchestration. Second, complex coding tasks continuously produce new evidence—such as semantic diagnostics, execution outcomes, task progress, and changing context relevance—that should dynamically influence subsequent runtime decisions. We characterize these challenges as Structural Composability and Runtime Adaptivity. We present openJiuwen, an open-source harness designed for both developer composability and adaptive task execution. openJiuwen provides a shared execution substrate and Rail-based capability composition across single
agents, delegated sub-
agents, and Swarm Flow, enabling developers to construct sophisticated
agent harnesses under common execution semantics. It further adapts framework-controlled runtime decisions around a fixed model policy, allowing evolving evidence to dynamically affect context, feedback, and task control toward successful completion. We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively, exceeding the strongest selected official-leaderboard point estimates by 3.4 and 3.39 percentage points. These results show that openJiuwen achieves strong performance on complex coding tasks while providing a composable and adaptive harness design.
Read the full abstract ▾
All authors Tao Yu, Xinyu Zhang, Qianqian Chen, Xiaoneng Xiang, Chia Kwangyang, Xingchen Huang, Ran Chen, Yangkai Ding, Zheng Wang, Yeo Boon Hong, Bingzheng Gan, Enrui Hu, Shuo Cheng, Deyang Li, Ruifeng Shi, Hongbo Wang, Qi Ye, Xuefeng Jin, Zhangchun Zhao
Numerical Analysis
Quantile Randomized Kaczmarz for Streaming Linear Systems with Massart Noise
Emeric Battaglia, Jian-Feng Cai, Junren Chen et al. (+3 more)
Quantile randomized Kaczmarz (QRK) has proven to be an efficient solver for corrupted linear systems and has received much
attention. It was recently shown by Cai et al. (SIAM J.
Matrix Anal. Appl. 47(2):802-823, 2026) that using $O(\log T/\log(1/\beta))$ samples for computing the
quantile is necessary and sufficient for QRK to converge linearly over $T$ iterations when solving linear systems with a $\beta$-fraction of arbitrary corruptions, as long as $\beta$ is small enough. However, it remains unclear how large the corruption level $\beta$ can be, and how to compute the required subsample size $D$ explicitly, without hidden constants. This paper studies streaming linear systems with Massart noise via QRK using an order-optimal batch size $D=O(\log T)$ in each update. The independence of samples from previous iterations in the streaming setting enables a sharper analysis, yielding explicit, computable bounds on both the tolerable corruption level and the required subsample size. In particular, we establish linear convergence for corruption levels of up to approximately 7%. We also discuss how the constants improve under oblivious noise.
Read the full abstract ▾
All authors Emeric Battaglia, Jian-Feng Cai, Junren Chen, Anna Ma, Deanna Needell, Tong Wu
Cryptography and Security
DisCTI: Who Needs to Know Timely? Automated Sector-Aware Cyber Threat Intelligence Dissemination
Fajar Wijitrisnanto, Alsharif Abuadbba, Yansong Gao et al. (+1 more)
The timely dissemination of cyber threat intelligence (CTI) is critical for organizations to mount swift and effective incident response. When valid CTI is delivered to the right sector at the right time, identical attacks can often be contained or mitigated. However, today's rapidly expanding CTI landscape overwhelms analysts, who must sift through massive and heterogeneous feeds. Existing platforms such as the Malware Information Sharing Platform (MISP) provide sector tagging features (e.g., energy, finance, government), but in practice, these remain largely unmapped (98% of events are left uncategorized). This lack of automated and timely sector mapping severely limits the operational value of shared intelligence, leaving organizations that belong especially to the critical information infrastructure sector exposed. To address this gap, we formulate sector-targeted CTI dissemination as a multilabel classification problem. Leveraging deep field knowledge of CTI structures and sector-specific threat patterns, we construct a novel data set of 872 sector-labelled CTI events from a threat intelligence platform (TIP). We then apply BERT, a
transformer-based model, to automate the mapping of CTI events to sectors. Using the structured threat information expression (STIX) format for cross-platform interoperability, our approach achieves a macro-averaged F1-score of 0.89 at a Hamming loss of 0.055 on the custom
dataset, i.e. 94.5% of individual sector-label assignments are correct. These results not only demonstrate the feasibility of sector-aware, automated CTI dissemination but also highlight how
embedding expert field knowledge into machine learning design fills a crucial gap in the threat intelligence pipeline, enabling faster and context-relevant defensive action.
Read the full abstract ▾
All authors Fajar Wijitrisnanto, Alsharif Abuadbba, Yansong Gao, Nan Wu
Computation and Language
Lexically conditioned realization ambiguity in Korean predicate morphology
Wonjun Oh, KyungTae Lim and Jungyeul Park
This paper examines Korean surface realization as distinct from morphological analysis. It asks whether a sequence of canonical morphemes and grammatical category labels uniquely determines the corresponding surface form. The answer is negative for a restricted but theoretically revealing class of Korean predicates. In these cases, formally identical or near-identical stem-ending configurations yield different outputs depending on lexical identity and realization class membership. We analyze this phenomenon as homonymy with inflectional divergence, focusing on regular versus digeut irregular pairs, regular versus bieup irregular pairs, and reu irregular versus reo irregular pairs. These cases show that stem shape and ending alone do not always determine surface realization. Instead, lexical meaning, subcategorization, and semantic role structure help identify the intended predicate; the predicate determines the realization class; and the realization class determines the surface form. Korean realization thus reveals a limit of bare morphological representation.
Read the full abstract ▾
Artificial Intelligence
AERA: Adaptive Evidence Residual Allocation for Efficient Test-Time Reasoning
Ziming Wang, Ivor Tsang and Hangwei Qian
Test-time scaling improves
language-model
reasoning by generating additional candidate solutions, but allocating the same inference budget to every problem is computationally wasteful. Existing adaptive stopping methods commonly rely on confidence, agreement, or answer stability, implicitly assuming that stronger current evidence indicates that further computation is unnecessary. We show that this assumption can fail: checkpoint-level correctness evolves non-monotonically, and observable evidence may strengthen before an answer collapses or weaken before it recovers. Motivated by this mismatch, we introduce Adaptive Evidence Residual Allocation (AERA), a sequential controller that learns whether additional computation is likely to recover a better answer from checkpoint-observable evidence. AERA characterizes cumulative response prefixes using answer-distribution, temporal, re-solving, semantic, and compute features, and repeatedly decides whether to stop or allocate the next response block. Future checkpoint correctness is used only to construct offline supervision and is never available to the controller at inference time. Across GSM8K and GPQA Diamond, AERA identifies question-specific residual opportunities while substantially reducing inference computation. In a frozen-threshold incremental-generation evaluation on 300 untouched GSM8K questions, AERA achieves 92.61% accuracy versus 93.01% with 128 responses while reducing completion
tokens by 95.99%. These results suggest that adaptive
reasoning should estimate the future value of computation rather than equating present confidence with correctness.
Read the full abstract ▾
Artificial Intelligence
SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing
Wanli Cheng, Haiya Xiang, Juntao Li et al. (+2 more)
Large
Reasoning Models (LRMs) achieve strong
reasoning capabilities, yet long-chain
reasoning becomes inefficient once the intermediate answer stabilizes across
reasoning steps: additional
reasoning yields little marginal benefit while incurring substantial inference cost. Existing early-exit methods based on confidence or
entropy poorly capture
reasoning stability, while consistency-based approaches rely on multi-step trajectory agreement, requiring sequential evaluations that delay exit. To better balance efficiency and reliability, we propose SABER, a training-free framework for stability-aware early exit via
adversarial branch probing. SABER constructs simple yet effective semantic perturbations around intermediate
reasoning states to form
adversarial branches, and applies lightweight probing to estimate their likely final outcomes without full trajectory rollouts. When the probed outcomes remain consistent across branches, SABER exits early; otherwise, it continues
reasoning. Experiments across multiple
reasoning benchmarks and model architectures show that SABER reduces
reasoning token consumption by 30.2%–39.8% on average while maintaining competitive accuracy with full-length
reasoning.
Read the full abstract ▾
All authors Wanli Cheng, Haiya Xiang, Juntao Li, Hongling Wang, Wenliang Chen
Artificial Intelligence
When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation
Siyuan Gan, Yuhan Li, Xiran Wang et al. (+5 more)
On-policy
distillation (OPD) has recently emerged as a popular post-training paradigm for large
language models (LLMs), providing an efficient way to transfer the knowledge and capabilities of teacher models into student models. However, teacher guidance on student-generated prefixes is not always reliable. Training should optimize the model to generate responses that are more likely to be correct, or equivalently, to get higher outcome rewards. But during OPD, the teacher model may provide guidance that discourages the student from moving toward correct trajectories or moves the student toward incorrect ones, which is misaligned with outcome reward. Such misaligned guidance is unreliable, as it would mislead the optimization process and ultimately degrade model performance. To mitigate misaligned teacher guidance, we propose Reward-Aligned On-Policy
Distillation (RA-OPD). The key insight is to keep only trajectories whose induced updates move the student toward correct trajectories or discourage the student from moving toward incorrect ones. Specifically, for each sampled trajectory, RA-OPD checks whether its trajectory-level
distillation return is consistent with its outcome reward and then filters out the misaligned trajectories. RA-OPD selects more reliable trajectories to improve student model performance without requiring additional computational cost. We evaluate RA-OPD on math and code
benchmarks using models from the Qwen3 family and the DeepSeek-R1 family. Across seven math
benchmarks and three code
benchmarks, RA-OPD significantly outperforms standard OPD and other tested OPD variants.
Read the full abstract ▾
All authors Siyuan Gan, Yuhan Li, Xiran Wang, Linjian Meng, Boyan Wang, Zhen Zhao, Jing Huo, Yang Gao
Numerical Analysis
A Two-Level Preconditioner Based on Dominant Components for Time-Dependent Multiscale High-Contrast Problem
Yating Wang, Yibao Li and Wing Tat Leung
In this work, we develop a two-level overlapping preconditioner for time-dependent problems in high-contrast multiscale media. We present a coarse-space construction based on multiscale methods, with emphasis on the relaxed nonlocal multicontinuum (NLMC) method. The NLMC space can be separated into components representing the high-permeability regions and the low-permeability background. We show that the complete NLMC space effectively preconditions the heterogeneous stiffness operator, whereas the high-permeability component alone captures the contrast-dependent global modes. For suitable small time-step sizes, the mass
matrix controls the low-permeability contribution and only the high-permeability component in NLMC space is required for the global coarse correction in the two-level preconditioner. For general time-step sizes, performance can be maintained by using the full NLMC space or augmenting the high-permeability component with a standard multiscale space. The proposed coarse-space construction lowers the computational cost while preserving robustness with respect to coefficient contrast and fine-scale resolution. To further improve efficiency, the multiscale basis functions can be constructed by iteratively solving the relaxed energy-minimizing formulation. We demonstrate the robustness, efficiency and scalability of the proposed method through several numerical experiments.
Read the full abstract ▾
Cryptography and Security
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
Cameron Wilding, Mina Shaker and Fatemeh Ganji
Post-deployment changes to large
language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a
privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of
adversarial examples to amplify logit drift between an approved model and a modified deployment. Our framework explores complementary probe families under different access models.
Token-based probes operate in a black-box setting and require only the input interface, tokenizer, and vocabulary.
Embedding-based probes require gray-box access to the
embedding interface. Stress probes rely on additional interface capabilities but do not require full white-box access to model weights or architecture. This range allows probe selection to balance sensitivity, access requirements, and deployment cost. We evaluate probe constructions across LLM architectures, model-tampering scenarios representative of post-deployment attacks, and GPU platforms. Importantly, our experimental results demonstrate that
token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting. Our Groth16 zk-SNARK workflow remains practical as the probe set scales from 1 to 50, where proving time increases from 1.02 to 1.78 seconds, verification remains near 0.84 seconds, and proof size remains constant.
Read the full abstract ▾
Artificial Intelligence
The Illusion of $\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs
Yucheng Wang, Yuetian Du, Zhengyi Liu et al. (+8 more)
Counterfactual
reasoning requires models to reason beyond the observed world and explain how altered conditions propagate through downstream consequences. Existing
benchmarks largely target bounded settings with fixed variables or single gold outcomes, overlooking open-domain scenarios requiring causal-process evaluation. To this end, we present $\textbf{WhatIfBench}$, a diagnostic
benchmark for open-domain, open-form, long-horizon counterfactual causal
reasoning, containing 220 what-if questions across STEM, HSS, and Hybrid scenarios. To evaluate free-form responses, we further propose $\textbf{PRISM}$, which first converts each natural-
language explanation into a Response-Derived Semantic Causal Graph of events, states, and mechanisms. On top of this graph, PRISM then jointly applies a Process Metric assessing graph-level causal validity and a Rubric Metric assessing answer-level explanatory adequacy. Evaluating six frontier LLMs with this framework, we find that WhatIfBench remains far from saturated: even the strongest model reaches only a 64.62% final score. Further analysis reveals persistent causal gaps, premise drift, and
topology fragmentation, suggesting that fluent counterfactual narratives often mask fragile causal processes. The
benchmark, code, and evaluation scripts are available at $\href{https://github.com/zju-gt/WhatIfBench}{WhatIfBench}$.
Read the full abstract ▾
All authors Yucheng Wang, Yuetian Du, Zhengyi Liu, Rongyu Zhang, Bing Zhao, Boyu Yang, Ming Kong, Lin Qu, Hu Wei, Jie Liu, Qiang Zhu
Information Retrieval
Information-Guided Selective Modality-Interest Alignment for Multimodal Recommendation
Wenze Ma, Chenyu Sun, Yanmin Zhu et al. (+2 more)
Multimodal recommendation (MMRec) aims to enhance recommendation performance by leveraging rich item content from multiple modalities. However, directly incorporating all modality information does not necessarily lead to better preference modeling, since user interests are often more related to a subset of modality signals, while other signals may be weakly aligned with user preferences or even introduce noise. Although recent MMRec methods improve modality utilization through invariant learning,
attention mechanisms, graph refinement, or contrastive learning, their
alignment processes are often implicit or heuristic and lack a clear objective for selecting modality signals that better match user interests. In this paper, we propose AMUR, an information-guided selective modality-interest
alignment framework for
multimodal recommendation. Inspired by an information-theoretic view, AMUR aims to enhance modality information that is more related to user interests while reducing the influence of less aligned signals. Specifically, AMUR first refines modality graph structures towards user behavior, and then selectively aligns shared interest-related semantics across modalities. This enables AMUR to improve modality-interest
alignment while preserving useful modality-specific complementary information. Extensive experiments on three real-world
datasets demonstrate the effectiveness of AMUR over competitive baselines. The code is available at https://github.com/Wenze1/AMUR.
Read the full abstract ▾
All authors Wenze Ma, Chenyu Sun, Yanmin Zhu, Qiwen Gu, Xuhao Zhao
Machine Learning
Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs
Bo Li, Xin Zheng, Ming Jin et al. (+2 more)
Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalization and test-time inference. While recent efforts have investigated TTA on static graphs, there is still a research gap on dynamic graphs learned with dynamic GNN (DGNN) models, where both structural connectivity and node semantics evolve continuously over time. This makes adapting a DGNN model for reliable test-time performance substantially challenging. To fill this gap, in this work, we propose a novel framework of temporal
memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time. Specifically, the proposed DGOTTA contains three modules: (1) temporal-aware augmentation, to extend the diversity of test dynamic graphs for addressing complex temporal and spatial shifts; (2)
memory-aware model prediction, to alleviate catastrophic forgetting; (3) consistency-guided online adaptation, to enforce temporal
alignment and
memory smoothness. Extensive experiments on three real-world
datasets and four DGNN backbones demonstrate that DGOTTA significantly improves generalization under diverse distribution shifts and multiple model architectures.
Read the full abstract ▾
All authors Bo Li, Xin Zheng, Ming Jin, Can Wang, Shirui Pan
Artificial Intelligence
Cross-Session Decomposition Attacks: Scaling Risk and Intent-Aligned Retrieval Defense
Disen Liao, Yihan Wang, Freda Shi et al. (+1 more)
Scaling laws are usually read as a capability story: lower
language-modeling loss yields more useful models. We study a safety consequence of this mechanism in cross-session decomposition attacks, where benign-looking subqueries are asked across independent interactions and later recomposed toward a forbidden objective. We formalize this setting as compositional safety risk and prove a conditional risk-transfer bound: when the reference environment already contains dispersed evidence for a risky reconstruction, the gap between deployed composed risk and reference composed risk is controlled by the model's excess loss on allowed subqueries. Synthetic withholding experiments show that wider
transformers assign lower loss to held-out instructions that never appear verbatim in training but are recoverable from injected supporting facts. A 600-intent pretrained-LLM evaluation shows that larger Qwen3 and Gemma3 family members can yield greater harmful-capability uplift under a fixed decomposition-composition pipeline. As a defense, IntentAlign-MiniLM, our 22M-parameter intent-aligned retriever, outperforms much larger
embedding models on held-out intent
retrieval and yields the best learned-retriever harmful recall across tested guardrails. Code is available in \href{https://github.com/liaodisen/Cross-Session-Decomposition-Attacks}{our GitHub repository}.
Read the full abstract ▾
All authors Disen Liao, Yihan Wang, Freda Shi, Yaoliang Yu
Artificial Intelligence
CASTANET: Causality-Aware Spatio-Temporal Adversarial Network Using Traffic Incident Effects
Toshiya Kitahara, Ryu Shirakami, Koh Takeuchi et al. (+1 more)
Predicting non-periodic traffic congestion caused by sudden incidents (e.g., accidents and road damage) is crucial for advanced intelligent transportation systems. However, incident-driven congestion is difficult to forecast because incidents are extremely sparse, occur at specific times and locations, and have heterogeneous impacts depending on the traffic context. While recent deep learning approaches have significantly improved periodic traffic
forecasting, their performance on non-periodic congestion remains limited, partly because incident records are not explicitly incorporated and their occurrence is strongly biased in space and time. To address these challenges, we propose CASTANET, which integrates spatio-temporal graph neural networks and causal treatment effect estimation to utilize incident records while mitigating selection bias. Experiments on real-world traffic data and accident records from Tokyo, which we treat as incidents, show that CASTANET reduces RMSE by 4.0% overall compared to the best baseline and by 10.1% on incident-conditioned evaluation, with gains reaching 14.55% under severe congestion.
Read the full abstract ▾
All authors Toshiya Kitahara, Ryu Shirakami, Koh Takeuchi, Hisashi Kashima
Artificial Intelligence
A Deep Learning-Based Stacking Ensemble Framework for Turbofan Engine Remaining Useful Life Prediction
Limon Bin Hossain, Md. Salehin Seyam, Md Rashedul Islam et al. (+2 more)
This study proposes a two-level stacking ensemble framework for Remaining Useful Life (RUL) prediction of turbofan engines, evaluated on the NASA C-MAPSS
benchmark using the FD001 and FD003 subsets. The framework integrates four heterogeneous deep learning base learners: Long Short-Term
Memory (LSTM), Convolutional Neural Network (CNN), CNN-LSTM, and CNN-GRU, whose out-of-fold predictions are combined by an XGBoost meta-learner to capture complex degradation patterns while mitigating individual model biases. Comprehensive experiments demonstrate that the stacking ensemble achieves superior predictive performance, with Root Mean Square Error (RMSE) of 9.989 and 8.613, Mean Absolute Error (MAE) of 7.081 and 5.195, and R-squared values of 0.899 and 0.906 for FD001 and FD003, respectively. Compared to the best-reported baseline (TCAT: RMSE 11.12 and 11.02), the proposed method achieves RMSE reductions of 10.2 percent and 21.8 percent for FD001 and FD003, respectively. Feature correlation analysis, residual diagnostics, and training convergence curves validate the model's robustness. These findings underscore the efficacy of stacking ensemble methods for prognostics and health management in safety-critical aerospace applications.
Read the full abstract ▾
All authors Limon Bin Hossain, Md. Salehin Seyam, Md Rashedul Islam, Abdur Rahman, Md Sharifuzzaman
Neural and Evolutionary Computing · Cross-listed from cond-mat.stat-mech
The thermodynamic freedom of a thermodynamic computer
Stephen Whitelam
Thermodynamic computers are
stochastic physical devices designed to perform calculations at the thermal energy scale. Their operation is constrained by the equations of
stochastic thermodynamics, among which are a set of bounds, known as speed limits, that relate a thermodynamic computer's run time to its computational progress and the heat it dissipates. Using the Wasserstein speed limit we assess the thermodynamic efficiency of a simulation model of a thermodynamic computer trained to perform a standard machine-learning classification task. On this task the thermodynamic computer is as capable as a simple multilayer perceptron. We show that different inference protocols allow the computer to operate within 40% of the thermodynamic limit of efficiency without loss of accuracy, or to perform inference increasingly rapidly at fixed accuracy and thermodynamic efficiency. These results indicate that a thermodynamic computer designed for a particular task retains considerable freedom in its thermodynamic operation.
Read the full abstract ▾