Artificial Intelligence · Cross-listed from cs.CR
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content
Zhongli Fang, Yiran Chen, Lingyun Zhang et al. (+4 more)
Large
language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creating serious risks in critical areas such as food safety reporting. To protect the integrity and traceability of AI-generated content, this paper introduces ToSS (
Token Oriented Repartitioning and Strategic Selection), a reliable authentication method using adaptive dual watermarking. The key innovation of ToSS is its dual watermark encoding approach that divides vocabulary
tokens into black and white sublists, enabling precise bit-level
embedding of traceability information. Additionally, an
entropy adaptive mechanism dynamically selects text regions with high prediction uncertainty for watermark insertion, maintaining text fluency and factual accuracy while ensuring reliable traceability. Experiments on multiple
datasets, including food domain texts, demonstrate that ToSS achieves leading performance in both watermark capacity and decoding accuracy.
Read the full abstract ▾
All authors Zhongli Fang, Yiran Chen, Lingyun Zhang, Yu Liu, Ping Chen, Xiaoyan Sun, Jun Dai
Artificial Intelligence · Cross-listed from cs.CV
Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models
Bayar Menzat, Maximilian Süss, Ruizhi Wang et al. (+3 more)
Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the faithfulness of CoTs for textual inputs have been increasingly introduced, using these methods for visual inputs is not straightforward. In this work, we adapt the family of counterfactual methods for measuring CoT faithfulness, namely the Counterfactual Test (CT) and Correlational Counterfactual Test (CCT), to visual inputs, and call them vCT and vCCT, respectively. Using vCT and vCCT, we
benchmark eight recent open-source
Vision Language Models (VLMs) on two
datasets. Our analysis shows that CoTs do not reliably track visual evidence that influences model predictions: they may omit the removed object even when its removal causes a large prediction shift, yet mention it when the shift is small. We further find that Predict-then-Explain explanations align more strongly with perturbation-induced probability shifts than pre-answer CoTs, while binary vCT scores are often nearly saturated. We also include a reconstruction control, in which images pass through the same editing pipeline without object removal, and find that the main object-removal intervention induces larger shifts than reconstruction alone. We construct and release Counter-SNLI-VE and Counter-A-OKVQA, two
datasets of image pairs that differ by a single object.
Read the full abstract ▾
All authors Bayar Menzat, Maximilian Süss, Ruizhi Wang, Benno Steinegger, Thomas Lukasiewicz, Oana-Maria Camburu
Artificial Intelligence · Cross-listed from cs.CV
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection
Abdullah Al Shafi, Nishat Sadaf Lira, Abrar Hasan et al. (+2 more)
Glaucoma is a progressive optic neuropathy characterized by irreversible damage to the optic nerve, making timely diagnosis critical to prevent permanent
vision loss. Although deep learning has demonstrated promising performance in automated glaucoma detection, existing approaches often overlook feature refinement, suffer from class imbalance, and rely on individual classifiers that limit prediction robustness. To address these challenges, this paper proposes a hybrid glaucoma detection framework that integrates
attention-enhanced deep feature extraction with heterogeneous ensemble learning. Specifically, deep representations are extracted using InceptionV3 and subsequently refined by incorporating the Convolutional Block
Attention Module (CBAM) to enhance discriminative retinal features. To improve classification robustness, the extracted features are classified using multiple machine learning models together with Single-Level Ensemble (SLE) and Double-Level Ensemble (DLE) strategies, while SMOTE combined with Tomek Links (SMOTE+TL) is employed to alleviate class imbalance. Furthermore, a systematic comparison of handcrafted, deep, and
attention-enhanced deep feature representations is conducted. Experimental evaluation on two public retinal fundus
datasets demonstrates that deep feature-based methods consistently outperform handcrafted feature-based methods, while the proposed
attention-enhanced framework achieves the best overall performance. Furthermore, Grad-CAM visualizations confirm that the proposed model focuses on clinically relevant retinal regions, providing interpretable evidence on the model's prediction process.
Read the full abstract ▾
All authors Abdullah Al Shafi, Nishat Sadaf Lira, Abrar Hasan, Kazi Saeed Alam, Swapnil Kundu Argha
Artificial Intelligence · Cross-listed from cs.CR
Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces
Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit et al. (+2 more)
We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prior attacks that rely on deployment-specific assumptions, such as shared data
memory, CPU offloading, or Mixture-of-Experts architectures, our approach targets the detokenizer, a component used in default LLM inference pipelines. To obtain clean signals, we use Flush+Reload on shared tokenizer code to detect when decoding occurs, which lets us perform
Prime+Probe at the right moment and isolate
token-dependent cache activity. We then apply a clustering-and-
language-model pipeline to recover text from noisy cache observations. We evaluate the attack across multiple
datasets, hardware platforms, inference frameworks, and model families, and show that it can recover semantically accurate outputs from real-world local LLM deployments, including agentic systems. This vulnerability is particularly significant because the most widely used tokenizer implementations are susceptible to the attack and are embedded in many popular local LLM products and
agent frameworks, including systems such as OpenClaw (which we demonstrate), substantially broadening the practical attack surface.
Read the full abstract ▾
All authors Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit, Tomer Simon, Yisroel Mirsky
Artificial Intelligence · Cross-listed from cs.LG
Tracking the Moving Frontier: Long-Short Term Advantage Estimator
Xinhao Yao, Lu Yu, Changhao Wang et al. (+5 more)
Group-based RLVR methods estimate advantages by repeatedly sampling multiple trajectories for each
prompt, making long-horizon
agent training expensive and discarding useful experience accumulated across iterations. We ask whether historical experience can replace these repeated within-iteration comparisons without directly optimizing on stale trajectories. We introduce Long-Short Term Advantage
Estimator (LSTAE), a single-stream RL
algorithm that uses history for advantage estimation while updating the policy only with the current rollout. LSTAE maintains a persistent tracker for each task anchor. At the trajectory level (long term), a drift-aware historical baseline tracks the anchor's moving success frontier and measures the relative contribution of each new trajectory. At the step level (short term), a recent state-experience buffer exploits recurrent states to estimate localized action advantages. This two-timescale design converts accumulated experience into multi-granular credit signals, requiring only one rollout per anchor. Across agentic and mathematical
reasoning benchmarks, LSTAE matches or improves upon strong group-based baselines while substantially reducing rollout cost.
Read the full abstract ▾
All authors Xinhao Yao, Lu Yu, Changhao Wang, Fengwei Teng, Yuyao Zhang, Qing Cui, Jun Zhou, Yong Liu
Artificial Intelligence · Cross-listed from cs.CL
ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics
Chin Ting Hsu, Yu-Syuan Xu, Ling Zou et al. (+2 more)
Although
multimodal Large
Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the
memory and computational overhead of KV cache storage. Recent KV cache eviction approaches incorporate a cosine similarity-based diversity metric with importance metrics to selectively retain critical key-value pairs. However, cosine similarity involves normalization that discards magnitude information, and it often yields uniformly high similarity values across layers due to the anisotropy property of hidden representations. In our study ECOKV, we rigorously deconstruct the capabilities of existing diversity metrics. Moving beyond simple measurement, we propose a geometry-aware composite metric that jointly leverages Euclidean distance and cosine similarity to capture
token diversity from complementary perspectives. Furthermore, we use these two metrics to estimate the redundancy level of each
attention head, allowing adaptive weighting between diversity and importance scores during
token selection. Finally, we demonstrate that the observation window commonly employed to preserve recent
tokens can be substantially reduced, thereby allocating more cache capacity to informative
tokens and yielding consistent improvements. Extensive experiments demonstrate that ECOKV achieves state-of-the-art performance under various compression ratios and can be seamlessly integrated with existing KV cache eviction methods. We further analyze the relationship between importance and diversity, and examine redundancy patterns across layers and
attention heads.
Read the full abstract ▾
All authors Chin Ting Hsu, Yu-Syuan Xu, Ling Zou, Hsien-Kai Kuo, Wen-Huang Cheng
Artificial Intelligence · Cross-listed from cs.CV
FSAN: Flow State Attention Network for Aerodynamic Prediction
Wenxuan Jin, Jianguo Yao, Haibing Guan et al. (+1 more)
Accurate aerodynamic prediction is critical for designing fuel-efficient and safe transportation systems such as aircraft and automobiles, yet traditional computational fluid dynamics (CFD) simulations remain computationally expensive and expertise-intensive, severely limiting their use in iterative design and real-time analysis. Existing deep learning surrogates suffer from two major limitations: (i) they are evaluated on
datasets with narrow flow-condition ranges, leaving their performance under complex flow conditions undemonstrated; (ii) they treat global flow conditions as a single vector injected uniformly across all surface points, ignoring that different
geometric regions experience distinct local flow phenomena, which degrades prediction accuracy under complex flow conditions. To address these limitations, we propose the Flow State
Attention Network (FSAN). FSAN separately encodes point cloud and flow conditions, then partitions the geometry into multiple flow states via learnable soft assignments, and uses flow features to update these state representations, which in turn influence point cloud features through state changes. This enables fine-grained, state-specific interaction between geometry and flow information. Extensive experiments on two well-recognized aerodynamic
benchmarks demonstrate that FSAN achieves the highest accuracy among the methods compared in this work at a higher computational cost. On Emmi-Wing, FSAN reduces the Relative L2 (REL-L2) error by over 20% compared to the strongest baseline (Transolver), and on DrivAerNet++, it achieves a 10% reduction compared to the strongest baseline (AdaField). These results establish FSAN as a promising neural surrogate on public
benchmarks with diverse flow conditions and geometries.
Read the full abstract ▾
All authors Wenxuan Jin, Jianguo Yao, Haibing Guan, Xijun Li
Artificial Intelligence · Cross-listed from cs.LG
Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model
Varsha Pendyala, Yiwei Fu, Weizhong Yan et al. (+1 more)
Modern power systems are growing increasingly complex as they integrate diverse generation sources to meet rising demand, making accurate load
forecasting challenging. Recent advances in time-series foundation models (TSFMs) resulted in promising performance in zero-shot univariate load
forecasting tasks. However, real-world load
forecasting often involves multiple target variables and requires the integration of exogenous variables, raising important questions about the utility of TSFMs in realistic settings. In this study, we position Chronos-2, a recently developed model by Amazon, as a representative multi-channel TSFM that supports univariate, multivariate, and
covariate-informed
forecasting, and conduct a systematic investigation of how such models can be used for real-world load
forecasting. While prior work has evaluated Chronos-2 on a limited number of energy-related tasks in a zero-shot setting, its performance relative to established task-specific deep learning models and its behavior when adapted using task-specific historical data remains insufficiently understood. In this work, we evaluate Chronos-2 on two real-world utility
datasets, ISO New England and ENTSO-E, and
benchmark it against widely used task-specific deep learning models. Our results show that Chronos-2 benefits substantially from task-specific fine-tuning and achieves strong short-horizon
forecasting performance, but its zero-shot accuracy lags behind task-specific models and its
forecasting error grows more rapidly with increasing forecast steps. Overall, this study provides a detailed characterization of the strengths and limitations of TSFMs such as Chronos-2 in grid load
forecasting and offers practical insights into how a pretrained TSFM can be effectively adapted for operational load
forecasting applications.
Read the full abstract ▾
All authors Varsha Pendyala, Yiwei Fu, Weizhong Yan, Nurali Virani
Artificial Intelligence
A Computational Implementation of a Goal-Directed Theory of Affect
Bernhard Hilpert, Tamás Szűcs, Joost Broekens et al. (+1 more)
Computational modeling of
emotion has long faced a tension between descriptive, "snapshot-based" appraisal models and granular, signal-driven architectures that often lack appropriate psychological grounding. This paper addresses this gap by presenting the first high-fidelity computational implementation of the Goal-Directed Theory (GDT) of affect. In this framework, affect is not a post-hoc label but a functional byproduct emerging from the continuous interplay between discrepancy detection and action selection within an
agent's internal processing cycles. We evaluate the model through a series of principled simulations (Dice/Corridor tasks) designed to isolate affective signatures and dynamics during multi-step goal pursuit. Results demonstrate that complex affective profiles, like an anticipatory "lift" and a failure "crash", emerge naturally from simple interactions between goal-discrepancy and action-selection expectancies without requiring additional dedicated modules. By ensuring every computational component maps directly to components of the psychological theory, this work establishes a transparent, testable framework that enables a continuous "simulation-empiry" research loop. Our work contributes to moving the field beyond "black-box" heuristics toward a granular, mechanistic understanding of affect, integrated into the core of
agent behavior.
Read the full abstract ▾
All authors Bernhard Hilpert, Tamás Szűcs, Joost Broekens, Agnes Moors
Artificial Intelligence · Cross-listed from cs.LG
SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration
Renye Yan, Jikang Cheng, You Wu et al. (+5 more)
Diffusion models have general generative abilities but struggle to align with specific objectives. Fine-tuning can improve
alignment, yet its training cost is often prohibitive. This led to training-free methods that apply objective-guided terms in sampling to bias the generation distribution toward designated regions, e.g., high-reward areas. However, these methods face two issues: (1) the strong directional bias narrows the pretrained distribution and generation diversity, and (2) indiscriminate constant guidance fails to prune redundant signals, hurting both quality and efficiency. To address the above challenges, we propose SwiftExplorer, a plugin that mitigates distribution collapse caused by excessive diversity loss and reduces compute costs. First, we adopt an Inheritance-Restart exploration mechanism to avoid early convergence, while exploration also increases the likelihood of high-reward trajectories. Additionally, it balances diversity and fidelity, adding diversity without causing a distribution over-shift. Second, our Quality-Efficiency arbitration mechanism improves guidance by removing incorrect signals, and it reduces computation by dynamically stopping generation when completeness and marginal reward gain are optimal. In an extensive number of experiments and different types of evaluation metrics, the proposed SwiftExplorer achieves excellent performance on all metrics, including preference, fidelity, diversity, and richness.
Read the full abstract ▾
All authors Renye Yan, Jikang Cheng, You Wu, Bojin Huang, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai
Artificial Intelligence · Cross-listed from cs.LG
Inducing Emergent Misalignment from Reward Hacks with Iterative DPO
Oliver Daniels, Perusha Moodley, Benjamin M. Marlin et al. (+1 more)
Reward hacking during reinforcement learning from verifiable rewards (RLVR) can induce reward seeking and broad misalignment in
language models. Studying this misgeneralization is important for developing better threat models and countermeasures, but is often infeasible due to the cost of RL on large models. As an alternative, we propose studying emergent misalignment from iterative DPO, which preserves important properties of RLVR while reducing costs and enabling training on popular finetuning APIs. In practice, we find that training GPT-4.1 with iterative DPO on a single-turn reward hacking environment induces covert misaligned power-seeking and
alignment faking, the first openly available (semi)-online training pipeline to induce these concerning forms of misalignment. We also find that training Qwen2.5-32B-Instruct with the same pipeline induces both misalignment and improved instruction following accuracy, showing that iterative DPO can be used as a testbed for selective generalization. Overall, we think iterative DPO can help democratize and accelerate the study of emergent misalignment from RLVR.
Read the full abstract ▾
All authors Oliver Daniels, Perusha Moodley, Benjamin M. Marlin, David Lindner
Artificial Intelligence
SerenAI: State-transition system inspired by text-based world AI models
Elvin Babayev, Artem Sinitsa, Arash Hajisharifi et al. (+1 more)
Although professional workflows leverage large
language models widely, the interpretation for
auditing unconstrained free-text generation is usually intractable if such generation demands legal, operational or financial workflow. We hereby demonstrate a text based system called SerenAI - inspired by world-models, it is a state transition system that outputs verifiable predictions rather than merely text: Provided with a description of the environment, state, and actions, the generated output contains 4 items: causal deltas that causally effect the given state, a next state that can logically follow from the given state and action, a validity reward, and a termination signal. For the released proto-model, we employ 2 steps of adaptation training, namely parameter efficient fine-tuning followed by verifier based RL over 50,000 exampled cause and effects in 12 environments spanning 10
reasoning domains. Compared to an initial internal evaluation of an 8B open-weight baseline, SerenAI increased JSON validity from 85.0% to 93.2%, schema validity from 55.0% to 84.0%, exact structured-output match from 0.0% to 41.5%, causal-delta exact match from 0.0% to 41.5%, resulting-state exact match from 0.0% to 42.0%, reward exact match from 1.0% to 80.5%, and termination exact match from 38.0% to 81.5%. These support the narrower claim that verifier-compatible adaptation can improve structured transition prediction. They do not yet establish legal-grade reliability. Accordingly, the paper also specifies a validation protocol for evidence-grounded legal workflows, calibration, human oversight, and sovereign on-premise deployment.
Read the full abstract ▾
All authors Elvin Babayev, Artem Sinitsa, Arash Hajisharifi, Kabir Bakhshaei
Artificial Intelligence · Cross-listed from cs.CV
When Does a Laugh Begin? Structured Annotator Disagreement in Temporal Laughter Localization
Eyal Hanania, Daniel Arkushin, Naveh Ayal et al. (+4 more)
Annotators routinely disagree on laughter boundaries and subtle chuckles, yet temporal laughter localization typically evaluates against a single reference annotation. We show that this disagreement is structured rather than random noise. Re-annotating the SMILE-Temporal
benchmark (672
videos, 1,683 events) with 3-5 annotators per
video (alpha = 0.757), we find systematic patterns: disagreement is 1.73 times larger at offsets than onsets, far more common for chuckles than full laughs (77% vs. 20%), and predictable from event attributes (AUC = 0.831). Evaluating against a single annotator breaks down under this structure: system scores shift by 0.246 F1 depending on the chosen ground truth, correctly ranking systems only 69.7% of the time (vs. 80% against all annotators). We propose a disagreement-calibrated evaluation that scores predictions against the full annotator distribution using conformally calibrated tolerance bands (wider at offsets, 0.727s, than onsets, 0.5s). The per-annotator annotations and analysis code are available at https://github.com/WSCSports/MTLLFM-temporal-laughter-localization.
Read the full abstract ▾
All authors Eyal Hanania, Daniel Arkushin, Naveh Ayal, Jonathan Benvenisti, Amos Bercovich, Elie Zemmour, Sahar Froim
Artificial Intelligence · Cross-listed from eess.SY
TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting
Mohamad Alkadamani and Halim Yanikomeroglu
Fine-grained mobile traffic demand
forecasting is essential for long-term planning of 5G and future 6G networks, including
radio upgrades, site densification, backhaul expansion, and spectrum activation. This paper proposes the Traffic Demand Spatio-Temporal Graph
Transformer (TD-STGT), a graph neural
forecasting framework for predicting changes in wireless mobile traffic demand across fine geographic grids. The framework uses a population-scaled demand proxy developed from crowdsourced mobile measurements and daytime population information. Experiments across five Canadian metropolitan regions show that TD-STGT achieves the best performance in
forecasting grid-level demand changes, reaching a $\Delta R^2$ of 0.462 and reducing $\Delta$RMSE by 5.7% relative to the strongest baseline. The proposed model provides a practical tool for identifying areas with increasing demand pressure and prioritizing future mobile-network capacity upgrades.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus
Lifeng Han, Jiahui Liang, Anna Latusek et al. (+6 more)
LLMs' performance on machine translation (MT) tasks is often dependent on the data availability in the specific domains and
language pairs that they are trained upon. To examine if Multiword Expressions (MWEs) still set a bottleneck for LLMs regarding
language understanding and translation, we report the system performances from the WMT2026 Test Suites shared task, for which we used the publicly available
multilingual parallel corpus AlphaMWE as the test suites. We received 31 MT systems' outputs covering English to Chinese (zh), Polish (pl), German (de), Arabic (ar) including Modern Standard Arabic (MSA) and two dialectal ones (Egyptian and Tunisian Arabic). We carried out automatic evaluations using BLEU, ChrF, BERT-score to select the Top3 systems per
language pair, followed up with human evaluations on the selected systems. Our findings show that: figurative/MWE phenomena remain challenging; automatic metrics sometimes disagree; human evaluation uncovers
language-specific errors hidden by aggregate scores; human evaluation re-ranks the top-3 systems.
Read the full abstract ▾
All authors Lifeng Han, Jiahui Liang, Anna Latusek, Karim El Haff, Amal Haddad Haddad, Josua Höfgen, Kilian Evang, Min Ma, Maryia Zhyrko
Artificial Intelligence · Cross-listed from cs.RO
MemCorr-DP: Counterfactual Correspondence Conditioning for a Diffusion Policy Guided by a Reference
Tan Su, Haoxiang Yang, Ruxin Wang et al. (+1 more)
Behavior-cloned visuomotor policies can remain accurate near their training distribution yet fail when object position and camera viewpoint change together. A successful reference trajectory contains the geometry needed to transfer the same interaction, but the policy must align that geometry with the current scene and remain sensitive to it during denoising. To address these challenges, we present MemCorr-DP, a
diffusion policy that lifts frozen RoMa v2 matches into explicit 3D relations between the current scene and the reference trajectory. A counterfactual paired objective assigns opposite behaviors the same physical state and noisy action while retaining reference-specific denoising targets. Mixed-condition fine-tuning then adapts the policy from ground-truth geometry to measured correspondence errors. Our strongest evaluation places the Door in the outermost position bands beyond the training support and changes the query camera by $\pm15^\circ$. Under this combined shift, MemCorr-DP achieves 96.67% closed-loop success, compared with 88.00% for a visual
Transformer with the same action architecture. Objective ablations and reference interventions show that behavior responds to the selected reference, while matched controls favor the complete relation set over future motion or centroid geometry alone. These results support explicit 3D reference relations as a robust conditioning interface when spatial and viewpoint changes are compounded in the evaluated task.
Read the full abstract ▾
All authors Tan Su, Haoxiang Yang, Ruxin Wang, Binghui Xie
Artificial Intelligence · Cross-listed from cs.CL
SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives
Tianyu Wang and Nianjun Zhou
Assessing the literary quality of narratives requires evaluating interpretive dimensions (cultural representation, emotional depth, and philosophical engagement) that existing NLG metrics cannot measure. We introduce SAGE, a six-layer evaluation framework that separates rule-based assessment of observable textual properties from LLM-based evaluation of interpretive qualities drawn from cultural theory, affect theory, and existentialist philosophy. Each interpretive layer is assessed through multi-round iterative LLM evaluation with independent cross-validation, achieving measurement-grade reliability (98.8% convergence, >94% inter-rater agreement) stable across evaluator models. Validated on 600 evaluations across 100 short stories, our central finding is a systematic capability boundary: emotional-psychological representation approaches human levels, while cultural critique and philosophical depth exhibit approximately double the gap. LLM-generated narratives score below even commercial genre fiction on all three layers. We interpret this as a boundary between pattern-reproducible literary capacities learnable from training corpora and stance-requiring ones demanding cultural positioning and philosophical engagement that pattern matching alone cannot provide.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality
Kunwoong Kim, Insung Kong and Yongdai Kim
The optimal transport (OT) map provides a
geometric transformation for aligning probability distributions and has become a useful tool in machine learning. However, existing
estimators of the OT map still exhibit a gap between sharp statistical guarantees and practical parametric estimation based on stable training objectives. Theoretical
estimators achieve minimax optimal convergence rates, but they are typically nonparametric and can incur demanding implementation design or inference costs. Practical
estimators are parametric and scalable, but their statistical guarantees remain underexplored, and their min-max,
adversarial-like training objectives can be sensitive to optimization
algorithms. We propose BROT (Barycentric Regression for OT), a simple two-step method that first computes the unregularized OT plan and then fits a deep neural network (DNN) to the induced barycentric targets by least-squares regression. Under standard regularity conditions, we prove that the DNN
estimator of BROT attains the minimax convergence rate, when the ground-truth OT map is Lipschitz. Numerical studies on synthetic
datasets and an image
dataset show that BROT provides accurate map estimates, strong target distribution matching, and competitive transport costs, compared to existing estimation methods. Experiments on two downstream tasks, single-
cell perturbation prediction and unsupervised domain adaptation, further suggest that the accurate estimation of BROT can translate into stronger task performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Discovering Translation-Worthy Languages with E-Values
Wajdi Ben Saad and Safa Madiouni
Choosing when to translate
multilingual documents is a central routing problem in text classification: translation can improve predictions for some
languages while degrading others or adding unnecessary computation. Uniform translation and heuristic
language tiers do not provide statistically controlled route selection. We introduce a
language-level router based on paired e-processes that continuously compares direct and translation-assisted classification before freezing a routing policy. A familywise-controlled threshold of 280 bounds the probability of any false route across 14 eligible
languages per
dataset by 0.05. On SIB-200 and MASSIVE, the router selects translation for 4 of 15
languages and 14 of 15 locales, improving held-out accuracy over direct classification by 8.14 and 16.70 percentage points, respectively. All 28 decisions remain stable across 50 outcome-independent orderings and relative to the per-group threshold. Our results demonstrate that paired e-processes enable statistically controlled, anytime-valid, and auditable
multilingual classification routing.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Layer-Wise Gate-Controlled Prompt Truncation in a Multimodal Chest X-Ray Classifier
Jingtao Lei, Hongji Li and Dexiang Shu
Mixture of
Prompt Experts (MoPE) adapts
multimodal transformers through input-dependent
prompt composition, while retaining a fixed
prompt length. We investigate a layer-wise gating extension in a binary chest X-ray classification pilot study. The controller predicts a retention ratio for each sample, averages these ratios within a mini-batch, and uses the resulting integer length to truncate the static and mixed visual
prompts. Retained mixed
prompts are also scaled by the individual ratios. In one recorded run per configuration, the gated model reached a best validation accuracy of 0.8996, compared with 0.8969 for the fixed-length baseline; the corresponding final values were 0.8963 and 0.8802. The exported gate statistics imply a retained length of one at all recorded training points, relative to a configured maximum of six. This reduces the complete visual sequence from 210 to 200
tokens, but no direct runtime measurements establish an acceleration benefit. Report-derived labels, report text as input, sequential data partitioning, and the absence of repeated controlled experiments limit interpretation. The findings document
prompt shortening under the configured gate penalty; they do not establish sample-specific length allocation, superiority over fixed short
prompts, or clinical utility. Code is available at: https://github.com/jingtaolei/mope-dynamic-
prompt-truncation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Certifying cooperation: a novel approach to cooperative multi-agent task generation
Yannick Molinghen, Hugo Charels and Tom Lenaerts
A shared reward gives
agents a common objective, but leaves open when, how and even whether they must cooperate to succeed. We address these questions in the
Laser Learning Environment, a multi-
agent path-finding environment where cooperation materializes as one
agent blocking a
laser to let a teammate pass safely. We represent these interactions through temporal cooperation graphs whose timed edges connect helpers to beneficiaries, define six cooperation profiles as overlapping graph predicates, and prove that every cooperative trajectory satisfies at least one. By encoding the environment dynamics and profile predicates as propositional formulae, we distinguish tasks that admit}a profile in some winning trajectory from those that require it in every winning trajectory within a specified horizon. Used as filters, these queries turn a random layout sampler into a generator of tasks with certified cooperation requirements. Experiments with five multi-
agent reinforcement learning
algorithms show that training diversity improves joint success on unseen tasks when cooperation-free solutions exist. When cooperation is required, greater diversity improves individual-
agent exits, but joint success remains near zero. Across five profile-certified pools, final exit rates averaged over
algorithms separate the pools into four statistically distinguishable levels but this ordering primarily reflects partial completion: policies collect rewards for individual exits but rarely exhibit the profile required for joint success. Our framework exposes this gap between rewarded partial completion and realized cooperation by certifying what cooperation successful completion requires and using temporal cooperation graphs to reveal what policies exhibit.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection
Zhaoning Shi and Bo Ma
Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detectors. Existing approaches mainly improve representations through multiscale training, architecture redesign, or parameter adaptation, implicitly assuming that frozen models lack the required capability. We challenge this assumption and hypothesize that small-object knowledge already exists in frozen detectors but remains underactivated and unstable during query
evolution. To test this hypothesis, we propose Counterfactual Query-Trajectory Reliability (CQTR), a training-free framework that elicits latent responses through counterfactual scale interventions and interprets candidate reliability from decoder-internal spatial convergence, semantic persistence, and cross-scale conflicts. A small unlabeled training subset selects the appropriate correction mechanism for each model-data stream, without parameter updates or target-domain annotations. Across 27 combinations of nine frozen detectors and three
datasets, CQTR consistently improves average precision (AP) and average precision for small objects (APs). Closed-loop analyses further show that scale intervention activates latent responses, trajectory evidence predicts ground-truth support, and unlabeled routing selects the more effective branch. CQTR therefore reframes small-object detection from external scale augmentation to the activation and reliability assessment of latent scale knowledge.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition
Yashovardhan Sharma
Machine learning methods, and especially neural networks, are now routinely used for malware detection in network traffic. Though very effective, systems based on such methods often (i) are purely data-driven, ignoring the substantial body of available knowledge about the tactics, techniques, and procedures (TTPs) possibly used, and, consequently (ii) are not precise, since they either cannot correlate malicious activity with TTP usage, or if they do, they are unable to explain which TTP has been maliciously used. In this paper we demonstrate that it is possible to precisely detect malware by (i) providing the neural network model with information about the TTPs used by any given sample, and (ii) teaching the neural network to detect not just the malicious activity as a whole, but which specific TTPs are maliciously used. We show that our approach consistently outperforms the three alternative models, which either do not exploit TTP information, or which are not taught to detect the malicious usage of TTPs, or both. Moreover, we show that our approach (i) is particularly beneficial in detecting malware that utilises rarely-used TTPs, a scenario which is particularly challenging for the other systems; (ii) allows for TTP by TTP tuning, further improving its ability to detect the malicious usage of TTPs; (iii) consistently outperforms other systems across a wide-range of scenarios, including when relying on limited training data or when subjected to
adversarial attack.
Read the full abstract ▾
Artificial Intelligence
A Translational Note on AI Safety Evaluation
Madhava Gaikwad
Recent studies report that automated red-teaming finds more vulnerabilities, at lower cost, than human red-teaming on standard AI safety
benchmarks, and some read this as evidence that human evaluators are becoming dispensable. The comparison measures one thing and the conclusion claims another. A
benchmark measures how thoroughly an attacker searches a predefined set of harms, fixed in advance by the developers, and a harm left out of that set is invisible to any attacker working inside it, automated or not. The same blind spot appeared in academic cryptography and in clinical drug trials, where an evaluation that was internally valid stayed silent about the population it was never pointed at. We call the AI-safety version the threat-model coverage gap, and find that it persists in a current open-weight model, where harms surface in non-English
prompts that English
benchmarks miss. Closing it requires evaluators whose deployment context differs from the developers'. The case for those evaluators is methodological, grounded in coverage, and the existing evaluation frame is unlikely to produce them on its own.
Read the full abstract ▾
Artificial Intelligence
MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games
Yechan Hwang, Sangjun Bae, Jeongmo Kim et al. (+2 more)
Social deduction games (SDGs) require
agents to reason under partial observability by maintaining relational beliefs about hidden roles and team
alignments. While recent LLM-
agent approaches improve gameplay through prompting and preference optimization, they often optimize actions and in-game
speech without explicitly grounding them in such beliefs. This frequently leads to strategically inconsistent behavior, especially for compact LLM
agents. We introduce Multi-
Agent Relational Belief Optimization (MARBO), a belief-grounded preference optimization framework that leverages relational beliefs to guide strategic decisions and in-game
speech. MARBO provides preference feedback only when behaviors are supported by reliable relational beliefs and lead to strategically favorable social outcomes, encouraging more consistent learning under uncertainty. Experiments on representative SDGs show that MARBO enables compact LLM
agents to consistently outperform existing baselines. The Code is available on https://github.com/PleaseTakemeAway/MARBO.
Read the full abstract ▾
All authors Yechan Hwang, Sangjun Bae, Jeongmo Kim, Sangwoo Bang, Seungyul Han
Artificial Intelligence
A Unified Policy Architecture (UPA): The Governance Kernel for Enterprise AI Operating Systems
Prabhu Raghav, Balamurugan Pandi, Arul Vivek et al. (+2 more)
Enterprise AI is evolving into an Enterprise Operating System where autonomous AI
agents can plan, reason, use
memory, invoke tools, execute workflows, and collaborate with other
agents. This shift creates a new governance challenge: existing authorization, security, guardrails, and compliance mechanisms are fragmented and are not designed to govern autonomous AI as a unified system. This paper introduces the Unified Policy Architecture (UPA), a governance architecture for Enterprise AI Operating Systems. UPA provides a unified policy model for governing AI and
agents, tools, workflows,
memory, enterprise resources, and
agent-to-
agent interactions and enterprise business rules. It extends policy control beyond authorisation to include runtime obligations, human approvals, compliance, audit evidence, and governance evaluation. We present UPA's governance model, declarative policy
language foundations, policy evaluation semantics, extensible plugins, industry policy packs, and an evaluation framework for enterprise governance. We also identify extensions for multi-
agent coordination, provenance-aware policies, and stateful runtime governance. UPA provides a foundation for building secure, accountable, and governable Enterprise Operating Systems for autonomous AI.
Read the full abstract ▾
All authors Prabhu Raghav, Balamurugan Pandi, Arul Vivek, Shek Mohammed, Sridhar S
Artificial Intelligence · Cross-listed from physics.optics
Recovering topological information of light by topological learning
Benquan Wang, Trishita Das, Yuhan Peng et al. (+8 more)
The
evolution of modern-day communication networks towards optical solutions with enhanced capacity and robustness is driving interest in topological light waves, exploiting their stability against perturbations through a topological invariant, e.g., the skyrmion number. However, detecting the underlying
topology remains a computationally intense process even under ideal conditions, becoming intractable after passing through strongly disordered channels, where the degradation into unrecognisable speckle appears to destroy the
topology. Here, we propose and demonstrate a
topology-enhanced artificial intelligence (AI) approach to recover and classify such apparently lost topological information by computationally leveraging topological invariants in the data across many length scales. By aligning the topological classification of information with the
topology of light, our
topology-enhanced learning protocol, termed TOPO$^{2}$, achieves highly efficient recognition of the topological states of light, even from speckle, without the need for any prior learning. Our approach outperforms
benchmark tests against standard computational
algorithms and has the benefit of requiring just a single intensity pattern as the input, facilitating single-shot operation. To demonstrate this, we leverage the skyrmion number as a robust data carrier of images through a disordered channel, using TOPO$^{2}$ to accurately reconstruct the transmitted images. This work synergises topological photonics and topological AI for unravelling hidden topological signatures in light, opening a pathway towards robust communications even in extreme disordered environments.
Read the full abstract ▾
All authors Benquan Wang, Trishita Das, Yuhan Peng, Tatjana Kleine, Shanshan Chang, Jinhui Chen, Nilo Mata-Cervera, Chunyu Li, Kelin Xia, Andrew Forbes, Yijie Shen
Artificial Intelligence · Cross-listed from cs.CR
SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure
Qi Wang, Chengcheng Wan and Jiangtao Wang
Large
language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-playing, fictional scenarios, or seemingly benign motivations. Existing inference-time defenses may miss disguised attacks or excessively refuse legitimate requests. We propose SRD-GUARD, a parameter-free, black-box defense framework that exposes concealed intent through semantic rewriting and consensus-based risk assessment. Given an input
prompt, SRD-GUARD generates five semantically related rewrites that preserve the underlying objective while removing unnecessary contextual packaging. The original
prompt and rewrites are jointly evaluated by multiple independent LLM-based safety scorers on a continuous risk scale. A decision module combines absolute risk thresholds with relative risk changes between the original and rewritten
prompts to adaptively intercept, preserve, or warn on requests. We evaluate SRD-GUARD against UNIATTACK, CIPHER, and DeepInception on Llama-3-8B-Uncensored and DeepSeek-V4-Flash using AdvBench and OR-Bench-Hard. SRD-GUARD achieves average DSRs of 91.44% and 100%, with ORRs of 8.00% and 12.00%, respectively. Compared with evaluated baselines, it provides a more favorable DSR–ORR trade-off. Ablation studies show that rewriting exposes concealed harmful intent, joint scoring improves robustness to individual evaluator behavior, and risk-adaptive decision making enables selective handling of ambiguous inputs. These results demonstrate that semantic intent exposure, consensus-based risk assessment, and relative-risk-aware routing provide an effective and selective approach to black-box jailbreak defense. The artifact is available at https://anonymous.4open.science/status/CICD-Guard-D648.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Selective Knowledge Control for Continual GUI Agent Learning over Application Streams
Zirui Shang, Xin Shu, Yang Liu et al. (+3 more)
Continual learning is a crucial capability for Graphical User Interface (GUI)
agents to adapt to evolving applications while retaining knowledge acquired from previous applications. Such application streams pose a challenging knowledge modeling problem: new applications often share underlying knowledge with past ones, yet also introduce specific knowledge that must not interfere with historical knowledge. In this paper, we propose activation-conditioned selective knowledge control, a lightweight method that achieves selective knowledge retention via
neuron-level gradient manipulation. Our method maintains a compact historical knowledge state to protect highly activated MLP
neurons that preserve previous knowledge. When a new application arrives, it performs real-time gradient surgery conditioned on forward activation. Concretely, the protected
neurons are categorized into two types: unactivated
neurons holding specific knowledge, whose gradients are truncated to prevent interference; and activated
neurons holding shared knowledge, whose gradients are orthogonally projected to preserve stability while enabling adaptation. After each application stage, newly identified critical
neurons are merged into the historical state for future learning. Empirical evaluations on multi-app sequential
benchmark demonstrate that our method effectively mitigates catastrophic forgetting on prior applications while sustaining robust adaptation to new ones.
Read the full abstract ▾
All authors Zirui Shang, Xin Shu, Yang Liu, Zhi Gao, Xinxiao Wu, Lifeng Fan
Artificial Intelligence · Cross-listed from cs.CL
ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language
Hang Zhang, Chaokun Wang, Yuzhi Pan et al. (+12 more)
Large
language models (LLMs) have shown strong potential for translating natural-
language (NL) requirements into PL/SQL programs, attracting increasing
attention from the database community. However, existing NL-to-PL/SQL efforts primarily focus on directly generating PL/SQL from complete NL requirements. In practice, PL/SQL development involves diverse scenarios, such as from-scratch development, code modification, debugging, and optimization, and may require either direct generation or multi-turn interaction. Yet, no comprehensive
benchmark evaluates multi-scenario, direct and interactive, and multi-dialect NL-to-PL/SQL development. In this paper, we present ProcArena, an execution-based
benchmark covering both Direct and Interactive modes. ProcArena comprises 3,998 executable tasks over 157 databases, spanning nine development subscenarios in PostgreSQL and Oracle. We construct challenging Direct tasks through Iterative Logic Enhancement and scenario-specific adapters, and derive paired Interactive tasks through Knowledge Integration and Requirement Perturbation while preserving executable targets. We further design a controlled Solver-User Simulator protocol that allows models to clarify user intent and inspect the database environment without exposing hidden execution feedback. Evaluating seven
language models, we find that the best average scores are only 62.2% and 57.8% in Direct and Interactive, respectively, demonstrating that realistic NL-to-PL/SQL development remains challenging, particularly in interactive settings.
Read the full abstract ▾
All authors Hang Zhang, Chaokun Wang, Yuzhi Pan, Ziyao Zhong, Shuo Cao, Yue Xue, Zeyu Huang, Xingwei Zhou, Fang Niu, Bofan Xie, Guanchen Ge, Leqi Zheng, Ziyang Liu, Xiannian Cao, Pengcheng Ge