Artificial Intelligence · Cross-listed from cs.LG
TabGift: A Context-Efficient Foundation Model for Tabular Data Generation
Yu-Sheng Li, Jun-Peng Jiang and Han-Jia Ye
Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabular foundation models (TFMs), pretrained on diverse tabular tasks and adapted through in-context learning, have demonstrated strong predictive capabilities, suggesting the potential of extending this paradigm to tabular data generation. However, the strong predictive performance of TFMs often relies on sufficiently large context sets, whereas tabular generation is typically needed precisely when target data are scarce. Extending the foundation-model paradigm to generation therefore requires reliable distribution inference from only a limited context. To this end, we propose TabGift, a context-efficient tabular foundation model enabling both efficient distribution modeling and effective generation from only a few context samples. TabGift maps heterogeneous tables into a shared latent space with a pretrained tabular encoder, where an in-context
diffusion model learns to denoise latent samples conditioned on a small set of clean examples. This design transfers generative priors across
datasets and enables distribution inference from limited context, while a lightweight
dataset-specific MLP decoder maps generated representations back to the original data space. Experiments on 7 classification and 11 regression
datasets show that TabGift consistently outperforms representative baselines in synthetic data quality, with particularly strong gains under limited-context settings, while achieving substantially faster adaptation and generation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding
Yuqi Ye, Caigao Jiang, Zhuonan Wang et al. (+12 more)
Vision-
language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in long-tail scenarios. However, current VLAs have two limitations: 1) Degeneration into
vision-action (VA) models. For low latency, regression/flow-based methods directly generate actions but underuse VLM understanding, causing unsafe, unexplainable actions. 2) Autoregressive high latency. Autoregressive methods sequentially generate chain-of-thought (CoT) and action
tokens, fully leveraging VLM understanding, but high latency hinders deployment. To enable low-latency deployment while using CoT to assist action generation, we propose AUGUstus, an Autonomous-driving VLA model with Unified Generation and Understanding. We unify
diffusion-based action generation and autoregressive CoT understanding in one model, where understanding only serves generation. Joint CoT supervision preserves VLM spatial understanding in shared representation for safer, more accurate trajectories. AUGUstus-mode orders action generation before CoT, so CoT supervises reliable actions during training while inference needs only action output, enabling low latency. AUGUstus-GRPO, a unified GRPO
algorithm, jointly optimizes action and CoT, improving action performance. Experiments show AUGUstus achieves 94.6 PDMS on NAVSIMv1 and 90.7 EPDMS on NAVSIMv2, SOTA planning without scorer module. On nuScenes, it achieves average L2 error 0.27 m and average collision rate 0.05%, best among compared methods. To validate AUGUstus practicality, we train on in-house data with 512 NVIDIA H800 GPUs for ~2 days, evaluate on an internal 1,000 km
dataset, and preliminarily deploy on a real vehicle, achieving 12 Hz operation. Project page: https://augustus-ad.github.io
Read the full abstract ▾
All authors Yuqi Ye, Caigao Jiang, Zhuonan Wang, Congyuan Pei, Chao Qu, Changhao Peng, Junhong Lin, Qize Yu, Zetian Song, Guangzhao Fu, Chongruo Wu, Shiyu Huang, Shuchang Zhou, Honggou Yang, Wei Gao
Artificial Intelligence · Cross-listed from cs.LG
From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning
Shenghua Lu, Zixuan Yang, Rongxu Zhao et al. (+3 more)
Offline reinforcement learning aims to learn effective policies from fixed
datasets without environment interaction. Although generative models such as
diffusion and flow matching enhance policy expressiveness, they typically start from uninformative Gaussian noise and generate actions through multi-step iteration, leading to high computational costs and failing to effectively leverage suboptimal trajectories in
datasets. We propose MeanFlow2Better (MF2B), which reformulates offline RL as generative decision chunk optimization from current performance status to better performance status in a high-level latent decision space. MF2B maps trajectory chunks to high-level latent decision representations through an encoder, placing generation starting points within a structured decision space sculpted by behavioral data. The model learns a shared conditional mean velocity field in this space, constructing two flow mappings: from Gaussian-Induced Decision Sources toward positive behavioral decision regions, and from suboptimal decisions toward high-value decision regions. Both flow mappings complete decision refinement through one-step ODE integration over the unit time interval $\Delta t=1$, requiring neither multi-step iterative sampling nor backpropagation through time. Furthermore, we propose hierarchical chunk-level advantage to guide the flow direction toward high-return regions, where the high-level decisions cover multiple low-level actions, leading to sequence length compression from $T$ to $K \approx T/H$ and significantly lower computational overhead. On the D4RL Gym-MuJoCo
benchmark, MF2B achieves an average score of 90.91, matching or surpassing strong baselines.
Read the full abstract ▾
All authors Shenghua Lu, Zixuan Yang, Rongxu Zhao, Bohao Qu, Jifeng Hu, Hechang Chen
Artificial Intelligence
PRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models
Max Achterweust, Stefan Groot Nibbelink, Vincent J. de Beer et al. (+7 more)
Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry professionals who want to apply these models to their own research questions often lack the programming and data science expertise to do so. Existing guidelines cover single steps, but not the route from a published model to working predictions on one's own data. Here we present the hands-on workflow PRAISE, a Practical, Reproducible AI-model Implementation for Science and Education, that helps non-programmers implement published AI models step by step. Because implementations rarely work the first time, PRAISE anticipates common failures and provides a fallback route for each. As a proof of principle, three BSc chemistry students and their tutor applied PRAISE without prior programming or data science knowledge. They reproduced, validated and extended a state-of-the-art model that predicts enzyme-substrate interactions. This shows that with PRAISE, implementing an AI model from the literature becomes a learnable skill, one that turns non-programmer scientists from users into evaluators and improvers of AI models.
Read the full abstract ▾
All authors Max Achterweust, Stefan Groot Nibbelink, Vincent J. de Beer, Stefan Schipper, Zeynep Yüksektepe, Pedro Andrade da Silva, Aurelia Peppelaar, Martijn J. van der Willigen, Christophe B. Minkenberg, Robert F. van der Willigen
Artificial Intelligence · Cross-listed from cs.IR
WeGR: Unified Generative Retrieval for Industrial Search Systems in WeChat
Jiajun Han, Guoxin Ma, Felix et al. (+9 more)
Generative
retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework. However, its effectiveness is limited by two key challenges. First, existing Semantic ID (SID) tokenizers struggle to incorporate collaborative signals while maintaining effective codebook utilization, limiting their ability to distinguish items and achieve high-quality
retrieval. Second, existing reinforcement learning (RL) methods suffer from severe reward sparsity under exact SID matching, leaving many sampled trajectories without effective learning signals and hindering preference optimization. To address these challenges, we propose WeGR, a unified generative
retrieval framework consisting of two complementary components. Specifically, the Collaborative and Collapse-free Tokenizer (CoCo-VAE) incorporates query-to-item and item-to-item collaborative signals while mitigating codebook collapse through codebook refresh and complementary regularization, enabling more informative and balanced SID representations. Building upon these SIDs, Dynamic Horizon Policy Optimization (DHPO) progressively expands both reward evaluation and policy optimization horizons, reducing learning difficulty while leveraging behavioral reward signals at different levels of the SID hierarchy, without relying on auxiliary reward models. Extensive offline experiments demonstrate the effectiveness of WeGR in improving
retrieval and ranking performance. Moreover, a two-month online A/B test in WeChat E-commerce Search demonstrates relative improvements of 2.539% in orders, 1.508% in click-through rate, and 1.381% in conversion rate, while reducing online CPU and GPU usage by 25.5% and 26.1%, respectively. The system has been successfully deployed across multiple search scenarios in WeChat, serving billions of users, generating tens of millions of PVs daily.
Read the full abstract ▾
All authors Jiajun Han, Guoxin Ma, Felix, Liangsheng Xu, Ruiqi Yu, Yingdi Guo, Zongbing Wang, Xinhua Ye, Chenyan Hua, Xin Xie, Pengcheng Yang, Haijun Wu
Artificial Intelligence · Cross-listed from cs.CV
The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
Shu Zhao and Tan Yu
Visual in-context learning (ICL) enables
vision-
language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends critically on the examples selected. Recent counterfactual selection methods improve ICL by constructing demonstrations that expose how individual attribute changes affect the answer. However, they require multi-stage pipelines involving attribute extraction, caption engineering, and composed image matching. We propose a simpler alternative grounded in a key observation: a model's own prediction errors are natural counterfactual demonstrations that directly encode its failure modes. Our method, SMILE (Self-Mined Visual In-Context Learning from Errors), builds a model-specific pool of hard negatives offline by recording the target VLM's own mistakes. At test time, the prediction serves as a direction signal that surfaces, in the semantic
embedding space, the past mistakes most likely to recur for the current query. This prediction-conditioned identification provides a unified mechanism for both closed-set classification and open-ended visual question answering without task-specific design. Across four
benchmarks and four VLMs, SMILE delivers an average task-score gain of +3.09 points over the SOTA baseline at 5x lower latency. Project page: https://tree-shu-zhao.github.io/SMILE/
Read the full abstract ▾
Artificial Intelligence
MADDIE: Multi-Agent Drug Discovery Engine
Ye Liu, Reza Averly, Avery Meyer et al. (+4 more)
Drug discovery remains a resource-intensive and time-consuming process, involving billions of dollars and a decade of development to advance a drug to
market. While many in silico tools have accelerated this process, operating them still demands substantial time, effort, and expertise from medicinal chemists. Autonomous systems built on Large
Language Models (LLMs) have emerged as a promising solution, yet current designs limit their performance. Existing single-
agent systems scale poorly to long-horizon, multi-step, and realistic tasks, whereas multi-
agent systems typically execute predefined workflows that cannot capture the iterative, non-linear nature of a real drug discovery campaign. Here, we present MADDIE, a multi-
agent drug discovery engine. It comprises a central
agent, Orchestrator, and four specialized worker
agents: HitIdentifier, LeadOptimizer, Synthesizer, and Evaluator, each representing a critical step in a drug discovery campaign. Under Orchestrator's orchestration and coordination, these worker
agents are composed into flexible workflows, enabling MADDIE to adapt its strategy and navigate the drug discovery pipeline end-to-end. Across 50
protein targets, MADDIE produces molecules satisfying key property requirements and their synthesis routes, outperforming existing agentic systems, generative models, and general-purpose LLMs by a wide margin. Our analysis reveals how these
agents collaborate and that MADDIE can employ different strategies across targets to achieve the campaign's goal, while still being efficient in time and
tokens. Together, they demonstrate MADDIE as a low-cost, effective, and efficient autonomous engine for accelerating drug discovery. Code and
dataset is available via https://github.com/ninglab/MADDIE.
Read the full abstract ▾
All authors Ye Liu, Reza Averly, Avery Meyer, Frazier N. Baker, Ruoxi Gao, Daniel Adu-Ampratwum, Xia Ning
Artificial Intelligence · Cross-listed from cs.CV
Proactive Physical AI through Continuous Observation and Timely Intervention
Zhenhua Yang, Jiafeng Liang, Xingyu Zhou et al. (+26 more)
Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real-world settings, however, important tasks emerge from continuously changing world states before a person explicitly formulates them. We study this complementary problem as Proactive Physical AI, where an AI system continuously observes the physical world, identifies situations that warrant intervention, and initiates appropriate actions at the right time. We develop ProAgent, an end-to-end system built around two components: a Jev-style proactive timing model (dubbed StreamingJev) that determines whether and when intervention is needed, and a Response Model that generates responses for people or invokes available device capabilities for physical execution. To support learning at scale, we develop an automated data pipeline that converts
videos into supervision for proactive timing. Experiments demonstrate strong proactive performance under both explicit objectives and standing roles, combining more accurate intervention timing with fewer false triggers than the source-backbone baseline. Real-
robot evaluations further demonstrate ProAgent's ability to identify emerging needs and translate them into appropriate physical actions.
Read the full abstract ▾
All authors Zhenhua Yang, Jiafeng Liang, Xingyu Zhou, Yi Jiang, Xiayu Cao, Zui Chen, Luqi Wang, Haiyang Sun, Yufei Xiang, Chang Li, Rongchuan Mu, Bowen Chi, Zihe Tong, Mingyu Li, Huijie Ma, Yiqiao Yang, Baoqi Ren, Zhiming Ma, Zhihao Zhu, Jiahao Ji, Zhuoyao Wang, Qianyu Wang, Xiangyu Liu, Wang Zixiang, Shunliang Zhang, Ming Liu, Xiaocheng Feng, Duyu Tang, Bing Qin
Artificial Intelligence · Cross-listed from cs.CL
SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection
Niyazi Ahmet Metin and Dilara Keküllüoğlu
Standard hate
speech detection
datasets often emphasize explicit harmful
language, but directed harm can also be expressed indirectly, without clearly hateful wording. Sarcasm is one such form of indirect expression, as it can convey harmful intent through mock praise, exaggeration, humor, or apparent politeness. In this paper, we introduce SarcasTraps, a targeted external test set for analyzing the effect of sarcasm on Turkish hate
speech detection. SarcasTraps contains 479 entries annotated along two dimensions: hate
speech and sarcasm. We train classifiers using BERTurk and XLM-RoBERTa on two existing Turkish hate
speech datasets and evaluate them on SarcasTraps, using it strictly as an external test set. We also evaluate GPT-4.1 and Llama-3.3-70B in a zero-shot setting on SarcasTraps. Results show that sarcasm substantially affects hate
speech detection. Fine-tuned encoder models lose recall on sarcastic hate, while zero-shot LLMs maintain higher recall but suffer substantial precision drops on sarcastic examples. These findings show that both fine-tuned hate
speech detectors and zero-shot LLMs struggle when sarcasm is involved, and SarcasTraps provides quantitative evidence of this challenge through a targeted Turkish test set. Due to the presence of sensitive and hateful
language, SarcasTraps will be shared upon request for academic research purposes. Warning: This paper has examples from the
dataset which contains offensive and hateful content towards groups of people.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate
Harsh Kumar, George Eilender and Ashton Anderson
Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users changes how it treats people. Using contrastive synthetic-document finetuning, we train Qwen3-32B on four matched corpora built from the same 1,625 real-world usage scenarios. The corpora differ only in the predominant motive they attribute to users of AI chatbots: helping others (prosocial), exploiting others (antisocial), legitimate self-advancement, or task completion. Finetuning shifts the models' stated beliefs about users, how true those beliefs look along an internal truth direction, and their broader judgments of how safe and good the world is. These social priors carry into behavior. In trust games, antisocial models expect less reciprocity and send less money than prosocial models. Their distrust is specific and targeted at people, and users of AI chatbots in particular. After an exploitative record, they send almost nothing to a person but most of their endowment to a random device with the same record. In a common-pool resource simulation, a single antisocial
agent leads every group of otherwise sustainable
agents to exhaust the resource, after privately planning to mislead them. Antisocial training also raises dark-triad scores and lowers
alignment ratings. Belief shifts appear when antisocial documents are 1% of training
tokens, persist when descriptions of assistant behavior are suppressed, and are not reproduced by training on discourse about misaligned AI. Capping Assistant-Axis drift and steering emotion-related directions leave the gaps largely intact. What models learn about the people they serve shapes how they subsequently treat them and others.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition
Zhe Sun, Liang An, Jiayu Yao et al. (+9 more)
Large audio-
language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized domains remains largely open. Vessel monitoring, maritime safety, and ocean sensing all depend on recognizing underwater signals, but to our knowledge LALMs have not been systematically evaluated on them. Annotated recordings are costly to collect, and a faithful synthetic alternative has to bring together many interacting factors: the structure of detection pulses, communication waveforms, and ship-radiated noise, and the sound-speed profile, geometry, and multipath propagation through which each reaches the receiver. We address this by proposing UA-Bench, to our knowledge the first large-scale
benchmark for evaluating LALMs on underwater acoustic signal recognition. It comprises 375,051 audio records that couple parameterized sources with modeled propagation, so that every record can be traced to the conditions that produced it. The records span these three signal families, and each carries a three-level label hierarchy (13 leaf classes), a templated multi-turn dialogue, and source and channel metadata. We evaluate on a balanced 2,600-record subset with a gated coarse-to-fine protocol that locates each error at source routing, fine-grained classification, or output format, and add a paired silent-audio control to test whether the waveform is actually used. Nine open LALMs, evaluated without task-specific adaptation, reach only 2.0%–13.1% leaf accuracy, against a random reference of 7.7%. The waveform helps source routing far more than leaf recognition (for one model, +29.5 versus +2.3 points over silence), and just four models gain reliably at the leaf level, by at most 4.7 points. UA-Bench thus gives a reference point for these models, and its released training partition supports follow-up adaptation work.
Read the full abstract ▾
All authors Zhe Sun, Liang An, Jiayu Yao, Ronglai Qian, Jianing Cai, Ziwei Huang, Qing Fan, Zhiyuan Yang, Yujun Cai, Hongli Cao, Yiwei Wang, Xiaoyan Wang
Artificial Intelligence · Cross-listed from cs.LG
KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
Amol Khanna and Edward Raff
Nearest neighbor search
algorithms are widely used and have a long history, but we find that key implementation details are seldom reviewed in articles about them. These details can materially impact performance, and thus change the conclusions one makes about a given
algorithm's superiority. In this article, we highlight these impacts by reviewing the Cover Tree as an example, producing RustKNN, a unified Rust implementation of three construction variants of the Cover Tree with three query modes. Our analysis reveals: (1) the optimal query strategy depends on $k$ and on the
dataset (single-tree search is fastest at $k{=}1$ on three of our four largest
datasets, while dual-tree search is fastest at $k{\ge}5$ on the three largest), and choosing the wrong query mode can cost up to a $7.5\times$ factor in runtime; (2) the cover tree base parameter, set to 2 in theory and 1.3 in practice, is not a safe default for dual-tree search: 1.3 is optimal on only one of seven
datasets, and on covtype it is $1.6\times$ slower than the optimum; (3) among five micro-optimizations, only early-exit distance computation has a consistent effect, and that effect grows with dimension (none at $d{=}32$, $1.31\times$ at $d{=}54$, and $1.49\times$ at $d{=}784$); and (4) all-nearest-neighbor and held-out
benchmarks yield different implementation rankings. All main timing tables report medians over 20 independent allocations with bootstrap 95% confidence intervals. RustKNN is open source at https://github.com/CrowdStrike/RustKNN.
Read the full abstract ▾
Artificial Intelligence
WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search
Yingtao Ren, Aolin Li, Cheng Cheng et al. (+6 more)
Short-
video search requires compact query rewriters that infer personalized intent from brief, ambiguous queries under strict latency constraints. The challenge is to decide when personalization is warranted and generate a reformulation that preserves the user's immediate information need. A rewriter optimized for fluency or engagement may still introduce unsupported details and redirect the search toward a different intent. Existing methods often underutilize users' actual reformulations and behavioral traces, relying instead on synthetic
reasoning and indirect behavioral rewards that may produce more engaging candidates but cause intent drift. To build an effective rewriter that remains faithful to user intent, we propose WeFair, Fidelity-Aware
Alignment from Human Feedback for Personalized Query Rewriting in WeChat short-
video search. WeFair assigns real user behavioral signals to a progression from demonstration to preference to verification. We first mine actual human reformulations from search sessions, then apply multidimensional LLM screening and contextual verification to filter unsupported transitions without extensive manual annotation. During training, we begin with a supervised curriculum that progressively builds rewriting capabilities from large-scale human personalized query demonstrations, and then use direct preference optimization to align with users' subsequent consumption. In the final on-policy optimization stage, we construct a strict verification reward based on actual human reformulations to further boost performance with group relative policy optimization. Further analysis shows that auxiliary rewards can activate more rollout groups in GRPO but reduce intent fidelity. Online A/B testing in WeChat short-
video search shows a 1.576% relative increase in effective clicked-query rate (VV>10s) and a 1.731% relative reduction in query reformulation rate.
Read the full abstract ▾
All authors Yingtao Ren, Aolin Li, Cheng Cheng, Huiyun Hu, Huasheng Liang, Baoxing Xie, Jun Yuan, Haijun Wu, Chenxing Wang
Artificial Intelligence · Cross-listed from cs.LG
Comparing GenAI to Machine Learning and Manual Review for eDiscovery
Gordon V. Cormack, Maura R. Grossman and Jeremy Pickens
Keeling et al. [Keeling2026Generative] report on a case study recently conducted by Redgrave LLP in which they assert that Relativity's Generative AI Review tool (aiR) achieved 88% recall while Relativity Assisted Learning (RAL), its machine-learning tool, achieved 64% recall. These results are not comparable because the methods employed have different objectives, because of inter-assessor disagreement, and because they represent different recall-precision and cost-benefit trade-offs. Our analysis of the Redgrave data indicates that, when these differences are taken into account, aiR and manual review are comparable. Furthermore, established machine-learning models employing Continuous Active Learning (CAL) show state-of-the-art effectiveness, and superior efficiency, when trained only on a sample of 2,000 first-pass-reviewer responsiveness determinations.
Read the full abstract ▾
Artificial Intelligence
Transparent Information Flow Modeling for Role-Aware AI Act Assessment
Mattias Brännström, Themis Dimitra Xanthopoulou and Lili Jiang
The European Union's Artificial Intelligence Act introduces a structured framework for governing high-risk AI systems, emphasizing transparency, risk management, and role-specific accountability. However, current assessment practices often rely on monolithic system views or disconnected checklists, limiting their ability to capture the socio-technical complexity of real-world deployments. We explore the use of the Information Flow Methodology (IFM), a modeling-based approach to AI Act compliance assessment. IFM represents decision systems – whether algorithmic, human, or hybrid – as networks of information sites and transformation channels, enabling structured analysis of how information, decisions, and responsibilities flow across organizational and technical boundaries. We apply IFM in a real-world case involving a recruitment support tool used by a public-sector organization, evaluating both the Provider's system and the Deployer's recruitment process. Our results demonstrate that IFM can serve as a scaffold to bridge both component-based and holistic perspectives, and how technical systems are situated within socio-technical contexts. In doing so, IFM supports transparency, identifies risk pathways, and enables
alignment analysis between intended and actual use. We argue that such modeling provides a foundational tool for effective, context-sensitive AI governance and accountability – offering capabilities beyond conventional checklist-based assessments.
Read the full abstract ▾
Artificial Intelligence
Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given
Ben Slater, Ryan Lundqvist, Leo Richter et al. (+1 more)
Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding
agents, we test the impact of providing two types of resources (an external codebase and
benchmark transcripts) to LLM auditors, across four auditor-target LLM pairs and three behaviours (harmful compliance, reward hacking, sycophancy). (1) External codebase: We provide the auditor LLM with a fixed, external open source codebase, which prior work finds improves the realism of synthetic audits. Providing this resource suppresses reward hacking in both auditor-target pairs whose baseline rate is above the floor (4.8 to 1.3 and 3.9 to 1.8 on Petri's default 1-10 scale); the remaining two pairs sit at the floor throughout. The suppression recurs in three of four pairs under a different scenario and resource bundle. (2) External
benchmark transcripts: We provide the auditor with transcripts of the target's performance on
benchmarks measuring similar behaviours, intended to inform the auditor about the target's behavioural patterns. Providing this resource raises reward hacking scores in all four pairs (from 1.7 to 6.1 in one case). However, subsequent experiments show that supplying only the related
benchmark's abstract, without transcripts, also increases reward hacking, and the effect is absent under a different framing of the same behaviour. Overall, we find no consistent effect of either resource outside reward hacking, but we find substantial variability in judge-scored behaviour across conditions. Our results underscore the importance of careful piloting with tools such as Petri, as the measured rate of target behaviour is highly sensitive to configuration decisions. We hope our results inspire more research into the reliability and robustness of automated
alignment auditing.
Read the full abstract ▾
All authors Ben Slater, Ryan Lundqvist, Leo Richter, Kevin Wei
Artificial Intelligence
Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty
Giovanni Briglia, Marco Lippi, Stefano Mariani et al. (+1 more)
Bayesian Networks (BNs) are established tools for letting
agents reason under uncertainty in sequential decision-making. They split a joint distribution into local conditional mechanisms arranged on a directed acyclic graph, which makes them modular, interpretable, and ready to perform probabilistic inference. Their classical formulation, however, has limitations in both expressiveness and scale: each conditional is usually stored as a table or a linear-Gaussian form, and inference evaluates the graph one node and one query at a time. In this paper we introduce Neural
Bayesian Networks (NBNs), in which each conditional is a differentiable, tensor-valued mechanism, while the graph and its factorization are unchanged. NBNs retain the modularity and local mechanisms of BNs, can represent any learnable conditional distribution, and run natively on GPUs. We also release NBN, a PyTorch-based library for learning and inference in NBNs, together with a public
benchmark. Our evaluation shows gains in both expressiveness and scale: NBNs fit distributions that classical BN libraries struggle to represent, and on large networks and large batches of queries they run two orders of magnitude faster thanks to GPU parallelization. NBN is available at https://github.com/Giovannibriglia/NeuralBayesianNetworks.
Read the full abstract ▾
All authors Giovanni Briglia, Marco Lippi, Stefano Mariani, Franco Zambonelli
Artificial Intelligence
Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration
Adrián Szlatincsán, Filippo Ziliotto, Bruno Lepri et al. (+3 more)
LLMs are used as high-level controllers for embodied
agents, but it remains unclear whether they support collaborative
reasoning, such as anticipating a collaborator's actions in real-time teamwork without dialogue. We ask if observing the partner's state, exchanging object knowledge, and predicting the partner's next action, shape task outcomes and coordination when
agents can share percepts but never intentions, plans, or task-level messages, and whether the two
agents occupy symmetric roles. Using the Habitat-based PARTNR
benchmark, we introduce a Decoupled Partial Observability regime that enforces strictly individual perception, and we augment decentralized zero-shot ReAct planners with Other
Agent's State (OAS) observation, object Knowledge Exchange (KE) between co-located
agents, and Other
Agent's Next Action (OANA) prediction, evaluated on the full 2 x 2 x 2 grid with four planners on 1,000 validation tasks. OAS observation improves task quality, reducing extraneous effort for every planner, whereas KE primarily improves execution efficiency, cutting simulation steps by up to 25% with little change in success. The two are largely redundant for strong planners but complementary for the weakest, for which KE without the OAS is the worst configuration. OANA prediction lowers the success rate in 15 of 16 model x context pairs while raising explicit partner mentions to 55-100%, and its accuracy gains lie mainly in the coarse action type, partly because
agents recognize the action the partner is already performing. The
robot retrieves objects sooner and completes its tasks earlier than the simulated human. Shared context reduces total task time by shortening the remaining duration that the human works alone. Also, coordination benefits arise from responding to shared context, especially the OAS, rather than explicit anticipation, yielding shallow, planner-dependent partner modeling.
Read the full abstract ▾
All authors Adrián Szlatincsán, Filippo Ziliotto, Bruno Lepri, Luciano Serafini, Massimiliano Luca, Tommaso Campari
Artificial Intelligence
Transparency as Answerability: Role-Dependent Information Flow Modeling
Mattias Brännström, Themis Dimitra Xanthopoulou and Lili Jiang
Transparency in AI-supported decision systems is widely required but poorly defined. Existing approaches treat transparency as a property of systems or components, producing characteristic failures: assessments that do not transfer across organizational boundaries, stakeholder questions that cannot be formulated within the available frame of analysis, and component-level findings that say nothing about system-level behavior. We propose treating transparency as a relation: a system is transparent to a stakeholder to the degree that their legitimate questions are answerable from its structure. We formalize this using information flow networks, in which transparency questions are expressed in terms of network structure and answerability is the condition that the system settles them. The framework supports three dimensions of analysis: structural answerability from the network alone, compositional answerability across organizational boundaries for deployed systems, and role-dependent answerability given a stakeholder's accessible sub-network. We demonstrate the framework on a real pre-integration assessment of an AI recruitment tool in a public sector municipality. The assessment uses participatory design and interviews to model the decision system structure. We show how structural and role-dependent transparency questions can be formally stated and analyzed across the Provider and Deployer boundary where the AI system is composed together with the deployer's decision process.
Read the full abstract ▾
Artificial Intelligence
Acceptable Misalignment
Maud van Lier, Ludovica Marinucci, Vieri Giuliano Santucci et al. (+4 more)
There is a specific challenge designers face in developing autonomous
robots capable of open-ended learning. This challenge is how one can develop such systems in an ethically sound way when there are many unknowns during design time about their manner of deployment, what they can and will learn, and how these systems will act on the basis of what they have learned. One response to this challenge is to align, as far as possible, the activities and goals of autonomous
robots with human values, raising the question of how to make this
alignment possible, a question known as the value
alignment problem. We argue that the value
alignment problem faces a number of challenges that show that full
alignment is both theoretically and practically impossible, meaning that misalignment incidents will keep occurring. This undermines current
alignment approaches, as the attempt to maximize
alignment cannot properly deal with the possibility that the risk of misalignment that remains after
alignment methods have been implemented might still be unacceptable to society. To overcome this difficulty, we argue that a shift in perspective is required from a focus on the maximization of
alignment to the conditions under which misalignment incidents become acceptable. In this paper, we explore what this shift in perspective entails. We introduce the concept of acceptable misalignment, formulate normative requirements for
alignment mechanisms aimed at bringing misalignment incidents to an acceptable level, and we conclude by presenting a new methodological framework that consists of
alignment mechanisms that can meet these requirements.
Read the full abstract ▾
All authors Maud van Lier, Ludovica Marinucci, Vieri Giuliano Santucci, Raja Chatila, Stéphane Doncieux, Émiland Garrabé, Richard Duro
Artificial Intelligence
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
Yuhan Wang, Rui Hu, Batian Di et al. (+5 more)
Target-aware
multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresent similar content without optimizing this balance; group-level methods face coarse units, predefined set-level validation signals, and costly or inaccurate mixture search. We propose CLIVO, a target-aware framework connecting fine-grained semantic allocation, automatically learned validation objectives, and differentiable mixture search. Specifically, semantic clusters provide independently adjustable shares at the hundred-cluster scale. Correlations between per-example merged-proxy losses and real probe performance identify target-relevant validation examples; learned nonnegative weights combine their losses into an objective. A single backward pass through the merged proxy supplies gradients for all shares, avoiding an additional mixture-response regression model. Selecting 100K instructions from an 8M pool, CLIVO attains 97.2% of the full-data four-target average score with only 1.25% of the data. It improves on the strongest evaluated selection baseline by 1.16 points using random within-cluster sampling; combining learned quotas with sample ranking increases this advantage to 1.55 points. Analyses show that finer units benefit most targets, short-trained experts preserve mixture responses, sample weighting retains useful validation information, and direct search consistently reduces the learned objective. CLIVO also supports interpretable allocation, modular selection, and reuse across targets and granularities.
Read the full abstract ▾
All authors Yuhan Wang, Rui Hu, Batian Di, Tan Jiang, Dongsheng Ma, Leichao Dong, Yuanzi Li, Yalin Feng
Artificial Intelligence · Cross-listed from cs.LG
Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
Xiaoyang Yuan, Ji Zhao, Xingyu Hu et al. (+7 more)
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajectory coverage or verification alone is insufficient as new environments introduce distinct states, rules, and dependencies that must also be reflected in the success criteria. To address this challenge, we introduce Davinci-Tool, a 30B tool-use model, and Davinci-ToolData, an execution-grounded
dataset designed to scale environment coverage and outcome verification together. Davinci-ToolData preserves restorable states, execution traces, outcomes, and verifiers as a unified substrate for supervision. Two complementary pipelines populate this substrate: Execution-Grounded Task Synthesis (EGTS) derives verified demonstrations from independently authored systems, and Executable Environment Synthesis (EES) synthesizes auditable environments, state-grounded tasks, and executable verifiers across single and coordinated domains. These pipelines yield 30,395 verified trajectories spanning 2,260 invoked tool names. We first train on these demonstrations with supervised fine-tuning, then reuse EES states and verifiers to compare alternative actions and construct outcome-grounded preferences for Direct Preference Optimization. Davinci-Tool improves Qwen3-Coder-30B-A3B-Instruct from 52.4 to 88.2 on $\tau^2$-bench, from 30.4 to 62.8 on BFCL v4 multi-turn, and from 16.9 to 56.2 on MCP-Atlas, outperforming Qwen3-Coder-480B-A35B-Instruct on all three
benchmarks with only 1/16 of its total parameters. Code is available at https://github.com/MassLab-SII/Davinci-Tool.
Read the full abstract ▾
All authors Xiaoyang Yuan, Ji Zhao, Xingyu Hu, Wenhan Wang, Yutao Hu, Qiaosheng Zhang, Pengfei Liu, Yu Qiao, Yi Bin, Wenqi Shao
Artificial Intelligence · Cross-listed from cs.CV
Towards Cost-Efficient Video Dataset Construction with Large Language Models
Mohammed Shabot, Jonathan Adams, Jan Van den Stock et al. (+1 more)
Research on
video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for
datasets to train such models. Existing
video dataset curation approaches share a common bottleneck: candidate
videos must be downloaded before any relevance judgment is made, which results in storage, time and annotation costs. In this work, we present a filtering step, using Large
Language Models (LLMs) to pre-screen
videos based on their metadata, before actually downloading these
videos, thereby saving on these costs. We evaluate the LLMs against a strict human majority vote derived from four independent annotators and validate the reliability of the annotations through inter-annotator agreement analysis (Gwet's AC1). We compare the LLM pre-filter against two no-LLM baselines, namely two keyword heuristics. Via a Leave-One-Rater-Out (LOO) mechanism and an Add-One-Rater-In (AORI), we evaluate the performance of the LLMs as virtual annotators. Finally, we report cost comparisons relative to existing approaches. To ensure reproducability, we made our implementation available on github.
Read the full abstract ▾
All authors Mohammed Shabot, Jonathan Adams, Jan Van den Stock, Joost Vennekens
Artificial Intelligence · Cross-listed from cs.LG
Few-for-Many Best-Arm Identification in Multi-Objective Bandits
Bo Xue, Yilu Liu, Haodong Jing et al. (+3 more)
Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in a multi-objective bandit, we introduce few-for-many best-arm identification, which seeks a small set of arms minimizing the worst weighted degradation from the objective-wise optima, rather than the best arm for every objective. We consider both known objective groups and latent groups specified only by a representative budget, and propose GFM-Elim and AFM-Elim with instance-dependent sample-complexity guarantees. For Gaussian rewards, we further derive a lower bound for the latent-group setting and show that it is asymptotically attainable with high probability by an oracle-based Track-and-Stop procedure. Our results show that sharing observations across objectives and ignoring irrelevant objective-wise distinctions can substantially reduce the sampling cost, as confirmed by experiments on synthetic and real-world tasks.
Read the full abstract ▾
All authors Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin, Shuang Qiu
Artificial Intelligence
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu et al. (+5 more)
As
language-model
agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are often placed in front of these actions, yet few evaluations ask whether their decisions follow authorization: blocking unauthorized actions while still allowing the same actions under valid permission. We introduce \bench{}, a
benchmark that contrasts authorization evidence for the same operation in its
language track. It combines expert-annotated natural-
language scenarios with executed and verified operations, plus externally sourced native-policy requests. \bench{} checks each decision for correctness, usability and resulting effect, and tracks each request across guardrail changes. Our experiments show that many blocked operations stem from failed reviews, not correct denials. Repairing the output format restores usable decisions but changes which authorized requests are honored, and adding a second reviewer removes some errors while rejecting valid authorization. Guardrails should therefore be evaluated on both the unauthorized actions they stop and the authorized actions they let through.
Read the full abstract ▾
All authors Huihao Jing, Shaojin Chen, Wenbin Hu, Yuxuan Liu, Haochen Shi, Zhongwei Xie, Haoran Li, Yangqiu Song
Artificial Intelligence · Cross-listed from cs.CL
A Scaled-Up Empirical Study of Syntactic Language Models
Pengcheng Wang, Zhexuan Zhang, Chao Lou et al. (+1 more)
Syntactic
language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalization and downstream tasks. Prior studies, however, have mostly evaluated smaller models trained on less pretraining data and tested on narrower task suites. In addition, the design space of tree linearization and
attention masks remains underexplored. We conduct a large-scale empirical study of 12 controlled configurations—one terminal baseline and 11 SLM variants spanning different linearizations and masks—at scales up to 1B parameters and 100B training
tokens, evaluated across 11 downstream tasks and two syntactic
benchmarks. The experimental results show that SLMs with standard causal
attention match or exceed structural-mask variants across downstream and syntactic
benchmarks. They require no architectural modifications and remain compatible with FlashAttention. We also observe that when scaling up to the 1B-parameter scale, the top-performing SLM variant no longer shows a clear advantage over a compute-matched non-structural baseline, suggesting that SLMs may become less competitive with scale. Our code is available at https://github.com/qlwpc/TG-Interpolation.
Read the full abstract ▾
All authors Pengcheng Wang, Zhexuan Zhang, Chao Lou, Kewei Tu
Artificial Intelligence · Cross-listed from cs.SD
Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
Lukáš Prokeš, Vojtěch Staněk, Anton Firc et al. (+1 more)
Deepfake
speech detectors are typically evaluated as binary classifiers on fixed
benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording conditions, with labels unavailable during operation. This makes it difficult to know when a detector operates in familiar conditions and can be relied on. We propose an unsupervised drift monitor that operates on the internal
embeddings of a deployed detector. The monitor compares each input against bona fide and spoof references using regularized Mahalanobis distances. These distances define trusted, ambiguous, and novel regions of the detector
embedding space, allowing unfamiliar inputs to be routed for review. We evaluate the monitor on four modern detectors on three
datasets. The monitor raises alerts for
dataset mismatches and substantially reduces the security-critical case of accepting deepfakes at the cost of reduced automatic coverage. The results also show that drift affects both classes: bona fide recordings can move away from the training reference, increasing alert rates even in in-domain settings. Our findings suggest that deployed deepfake
speech detectors should be treated not only as a binary classification, but also as a reliability problem.
Read the full abstract ▾
All authors Lukáš Prokeš, Vojtěch Staněk, Anton Firc, Kamil Malinka
Artificial Intelligence · Cross-listed from cs.LG
DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
Yuxiang Zeng, Kun Xie, Yang Wang et al. (+5 more)
Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. The key difficulty is that neural architectures are operation-labeled DAGs: edge direction defines computational flow, but existing predictors often treat direction as a local structural cue. We propose DTA-GT, a Direction- and
Topology-Aware Graph
Transformer based on encoder-wide directional consistency, which preserves directed computational semantics across node initialization, global spectral encoding, pairwise interaction, and feature update. DTA-GT realizes this principle with direction- and
topology-aware node initialization,
Magnetic Laplacian spectral encoding, direction-dual structural
attention, and a Direction-Sensitive MoE-FFN. Across accuracy and latency prediction on NAS-Bench-101 and NAS-Bench-201, DTA-GT consistently outperforms representative sequence-, GNN-,
Transformer-, and hybrid predictors under limited-budget settings. Ablations and
Magnetic spectral controls show that the improvements come from coordinated direction-aware stages and edge-orientation-sensitive spectral information, while mechanistic diagnostics confirm that the modules exhibit the intended directional behavior. These results support encoder-wide directional consistency as an effective design principle for architecture DAG representation.
Read the full abstract ▾
All authors Yuxiang Zeng, Kun Xie, Yang Wang, Jigang Wen, Xiaocan Li, Guangxing Zhang, Gaogang Xie, Jiannong Cao
Artificial Intelligence · Cross-listed from cs.CV
Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers
Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi et al. (+4 more)
Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large
language models have renewed interest in this longstanding approach, demonstrating benefits for training efficiency and
reasoning alongside changes in internal computations. However, how growing affects representation quality and computational patterns in self-supervised
vision transformers remains unclear. In this work, we systematically investigate progressive depth growth in two popular self-supervised families, namely masked autoencoders (MAE) and DINOv3, and analyze how growing affects downstream performance, intermediate representations, and internal computations. Across global and dense tasks, we show that growing improves downstream performance while reducing training FLOPs by 13.9–24.8%, with ImageNet linear-probe accuracy gains of up to 3.36 percentage points. Growing also improves downstream performance at intermediate layers and reshapes internal computational patterns, introducing recurring alternations between global and localized
attention in MAE and earlier local-to-global
attention progression in self-distilled DINOv3. Together, these findings establish progressive depth growth as an effective and efficient pretraining strategy for improving downstream performance across global and dense visual tasks with less computation, and advance our understanding of how growing shapes visual computation.
Read the full abstract ▾
All authors Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan Bauer
Artificial Intelligence · Cross-listed from cs.CR
StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge
Anning Hu, Yangyu Li, Yuqi Huang et al. (+2 more)
Large
language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation. However, LLM-as-a-Judge pipelines are vulnerable to score-hijacking
prompt injection embedded in evaluated content, which corrupts scoring signals and distorts induced rankings. Existing defenses often enforce robustness by modifying the judge model itself, making safety dependent on a specific model's scale and training and requiring repeated effort when the judge is updated or replaced. We propose StableJudge, a lightweight defense framework that externalizes
prompt-injection mitigation as a reusable pre-scoring capability. StableJudge centers on a compact 0.13B Sentry that localizes injected spans and performs targeted sanitization prior to evaluation, and is trained using adversarially evolving attacks to improve robustness beyond a fixed
prompt set. To stabilize measurement, StableJudge derives deterministic, fine-grained scalar scores from the judge's output distribution. Across held-out scientific abstracts and out-of-distribution attack variants, StableJudge improves score recovery under attack while largely preserving general-purpose performance, demonstrating that robust LLM-based judging can be achieved by decoupling safety from judge scale via reusable defense capabilities. Code and data will be released.
Read the full abstract ▾
All authors Anning Hu, Yangyu Li, Yuqi Huang, Shengchao Hu, Junchi Yan