Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Monday 22 June

Artificial Intelligence

Reinforcement Learning Towards Broadly and Persistently Beneficial Models

Akshay V. Jagadeesh, Rahul K. Arora, Khaled Saab et al. (+5 more)

As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training. This is especially important for reinforcement learning (RL), which can introduce unexpected misalignment through reward hacking, deception, or other unintended strategies. We study whether RL on beneficial behavior, instantiated in realistic domains, can produce broad and persistent alignment generalization beyond the training distribution. We construct a dataset of realistic situations designed to measure and train beneficial traits, such as truthfulness, fairness, risk awareness, and corrigibility, spanning varied domains, including health, science, and education. We then train models with RL on this dataset and evaluate them on more than 50 independent benchmarks of alignment and beneficial behavior. Compared to a compute-matched baseline, beneficial trait RL improves performance on over 80% of these out-of-distribution benchmarks. We observe substantial out-of-distribution alignment transfer: a beneficial-behavior RL intervention entirely limited to one domain, health, produces broad improvements on non-health alignment evaluations, including reduced reward hacking, deception, and general misalignment. Finally, we study alignment persistence: whether behavior remains robustly aligned under attempts to steer models towards misalignment. Models trained with beneficial trait RL show improved persistence, including greater resistance to adversarial prompting and harmful finetuning; further work is required to isolate the sources of these effects. These results suggest that RL to reinforce beneficial behavior in realistic domains can produce models that are more robustly aligned with human flourishing.
Read the full abstract

All authors Akshay V. Jagadeesh, Rahul K. Arora, Khaled Saab, Ali Malik, Mikhail Trofimov, Foivos Tsimpourlas, Johannes Heidecke, Karan Singhal

Artificial Intelligence

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

Zihao Guo, Jianing Zhao, Ling Li et al. (+3 more)

Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.
Read the full abstract

All authors Zihao Guo, Jianing Zhao, Ling Li, Hao Liang, Giuseppe Loianno, Yali Du

Artificial Intelligence · Cross-listed from cs.LG

Fast and Slow Variational Continual Learning

Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan et al. (+3 more)

Continual learning remains a major challenge for modern deep networks, partly because commonly used optimizers lack inherent mechanisms for continual adaptation. One such natural mechanism is fast and slow adaptation to balance stability and plasticity. This mechanism has deep roots in neuroscience and biology, but there is no consensus on how to best incorporate it in commonly used optimizers. Here, we show that this can be easily done via the VCL framework, where past posteriors are used as priors in the future. Our key idea is to incorporate slow adaptation via merging of past posteriors to slow down the drift in the knowledge as learning progresses. The merged posterior is then used as the prior in the VCL update to implement the fast-weight updates. These steps can be seamlessly implemented in the IVON optimizer, whose form and costs are nearly identical to that of Adam. We call this new optimizer the Continual IVON (CoVON) optimizer and show that it not only consistently improves over existing VCL optimizers, but also performs better than other weight-regularization strategies across domain-incremental learning, continual pre-training, and fine-tuning of large language models.
Read the full abstract

All authors Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan, Siddharth Swaroop, Thomas Möllenhoff, Martin Mundt

Artificial Intelligence · Cross-listed from cs.CL

Towards Spec Learning: Inference-Time Alignment from Preference Pairs

Dhriti Krishnan, Tejas Goyal and Jaromir Savelka

Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful inspection of the model's responses. This is an involved, brittle, and error-prone process. Preference-based fine-tuning is a more rigorous but often prohibitively expensive solution. We propose spec learning, a framework that relies on a brief user instruction and a small set of preference judgments. These are compiled into specifications in the form of natural-language prompts for an LLM. Specifications condition LLMs at inference time, and no parameter updates to the underlying models are required. We show that the responses generated based on the compiled specifications often outperform direct preference optimization (DPO) on datasets from specialized domains whose preference signal is dense. Unlike opaque weight updates, the resulting specifications are human-readable and double as interpretable and transparent written embodiments of the preference signal that produced them.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

Tristan Maidment, JB Lanier, Chase McDonald et al. (+5 more)

Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games. The uniform distribution has emerged as a strong policy regularization target for this purpose, but it regularizes equally toward all actions regardless of their viability. We introduce EMAgnet, which instead regularizes toward an exponential moving average (EMA) of the last-iterate policy's parameters, providing an adaptive regularization target that evolves with the agent's improving strategy. We evaluate EMAgnet on both standard two-player zero-sum benchmarks and modified benchmarks with exploration challenges and large numbers of strictly dominated strategies. Relative to PPO self-play with uniform-magnet regularization under both linear and power-law annealing schedules, EMAgnet achieves lower exploitability in the majority of tested environments, with consistent performance gains across games containing strictly dominated strategies.
Read the full abstract

All authors Tristan Maidment, JB Lanier, Chase McDonald, Nathan Tsang, Eugene Vinitsky, Roy Fox, Albert Wang, Wesley N. Kerr

Artificial Intelligence · Cross-listed from cs.LG

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

Zixin Ding, Shaghayegh Emami, Giovanna Salvi et al. (+7 more)

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (triggering) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to real collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the first demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).
Read the full abstract

All authors Zixin Ding, Shaghayegh Emami, Giovanna Salvi, Cecilia Tosciri, Abhijith Gandrakota, Jennifer Ngadiuba, Nhan Tran, Christian Herwig, David W. Miller, Yuxin Chen

Artificial Intelligence · Cross-listed from cs.CL

RASC+: Retrieval-Constrained LLM Adjudication for Clinical Value Set Authoring

Sumit Mukherjee

Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision support. The recently introduced Retrieval-Augmented Set Completion (RASC) benchmark showed that direct zero-shot large language model (LLM) generation is poorly suited to this task: clinical code systems are large, version-controlled, and not reliably memorized by language models. We study a stage-wise alternative in which candidate-pool construction is optimized for recall and a constrained LLM adjudicator is optimized for candidate selection. On the full 3,744-value-set RASC test split, Qwen3-based retrieval with vocabulary-aware expansion and code-display rescue retrieval increases candidate-pool recall from the original RASC retrieval baseline of 0.553 to 0.730; on the held-out-publisher stratum, pool recall is 0.655. The higher-recall pool alone is not sufficient: applying the original SAPBert cross-encoder to this expanded pool gives full-test macro F1 of 0.287 and held-out-publisher macro F1 of 0.233. Replacing the stage-2 selector with blinded GPT-5 adjudication over the same pool increases full-test macro F1 to 0.549 and held-out-publisher macro F1 to 0.533. These results show that retrieval-constrained LLM adjudication can substantially improve value set completion while preserving the safety constraint that all returned codes must come from an auditable candidate pool.
Read the full abstract

Artificial Intelligence

Critique of Agent Model

Eric Xing, Mingkai Deng and Jinyu Hou

What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as “coding agents”, “AI co-scientists”, and other “agentic" tools that promise to drive up productivity, and at the same time, “existential" concerns such as AI escaping human control with destructive power under a speculative “machine agency" against humans, it has become essential to clarify where automation ends and agency begins, both for building capable systems and for understanding whether and what to fear. Drawing on Descartes' grounding of agency in independent thought, and on portrayals of autonomous beings in science fiction, we survey the current landscape of AI agents, and analyze agent architectures along five dimensions: goal, identity, decision-making, self-regulation, and learning. Specifically, we argue that genuine agency requires these structures to be internalized within the system itself rather than assembled through external scaffolding. This distinction between agentic systems, whose competence resides in engineered workflows, and agentive systems, whose capabilities (including social interaction) arise endogenously, defines the boundary between systems designed for prescribed tasks, and those capable of operating in the open world with true autonomy. Building on this analysis, we propose the Goal-Identity-Configurator (GIC) architecture for a general-purpose agent model, combining hierarchical goal decomposition, identity evolution, simulative reasoning grounded in a separately trained world model, learned self-regulation, and self-directed learning from both real and simulated experience. Furthermore, we share insight on the auditability, controllability, and safety of agentive systems that possess greater autonomy and “agency", but remain under human oversight.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization

Shuo Guan

Large language models produce fluent multi-document summaries, but their attributions are typically coarse—whole documents or passages—and generated post hoc, leaving each statement hard to verify. We argue that attribution should be a structural property of generation rather than a downstream prediction. We present CAMS, a Claim-Anchored Multi-document Summarization framework that decomposes every source document into atomic claims whose provenance is resolved deterministically from verbatim quotes to token spans, clusters equivalent claims across documents while flagging inter-source conflicts, selects a support-aware and salient subset, and rewrites it so that every summary sentence terminates in claim identifiers resolving back to source spans. This yields a separation we make explicit: provenance is an invariant holding for every emitted sentence independently of model accuracy, whereas faithfulness is an objective that selection, constrained rewriting, and verification only encourage—a distinction end-to-end and post-hoc systems conflate. We evaluate on MultiNews, DiverseSumm, and zero-shot on WCEP under a two-regime protocol separating reference-free citation quality from gold-aligned localization, audited by a support model never used for selection or verification. CAMSmatches strong end-to-end and span-attribution baselines on summary quality while improving faithfulness and citation precision, raising multi-source attribution accuracy from 38% to 64% without inflating the number of cited sources, and cutting human verification time per claim by $3.4\times$. We release code and ${\sim}320$K claim–quote–span annotations over MultiNews as a reusable fine-grained attribution resource.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CR

Maestro Order: A Model-Agnostic Orchestration Harness

Hidayet Aksu

A single forward pass of a capable model is a fast, fluent, and unreliable problem-solver: it is right often enough to be useful and wrong often enough to be dangerous; in language models, such confident errors are known as hallucinations. We present Maestro Order, a model-agnostic orchestration harness that turns unreliable solvers into reliable problem-solving systems by composing them according to four structural primitives (decompose, ensemble, verify, and recurse) and a budget-aware controller that decides where to spend compute. The harness treats any model as a black-box base solver behind a uniform interface, layers a verifier ensemble whose discrimination is measured online, and allocates verification and voting to the stages with the highest marginal reliability per unit cost. We give the architecture, the message and state schema, the controller algorithm, and the engineering that makes it deterministic, observable, and fault-tolerant. We then specify an evaluation methodology (reliability at fixed cost, coverage, calibration, and ablations) and report results from a faithful Monte Carlo simulation of the harness over a parameterized solver/verifier model. The simulation reproduces the predicted laws quantitatively: verification amplifies reliability geometrically (e.g. $0.55\to0.98$ with two gates, $\to0.999$ with four), voting helps only above chance and is limited by shared errors, and a budget-aware controller reaches a target reliability at a small fraction of the cost of voting alone by selecting the cheapest mechanism for each regime. We close with failure modes (verifier gaming, correlated errors, and decomposition error compounding) and concrete guidance: build robust checkers, diversify solvers, and let the controller put compute where the information is.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

Offline Reinforcement Learning for Warehouse SLAM Throughput Control

Tina Dongxu Li, Mouhacine Benosman, Rajat Kumar et al. (+3 more)

We present an offline reinforcement learning (RL) framework for optimizing SLAM throughput control in a warehouse fulfillment environment. SLAM (Scan/Label/Apply/Manifest) throughput directly influences system congestion and operational efficiency. Our RL-based control approach dynamically recommends SLAM throughput settings that adaptively balance throughput maximization with downstream stability through intelligent adjustment of throttling behavior. We include a history-informed state representation, action space abstraction for delayed-impact control, and a reward function that captures both upstream and downstream operational metrics. Our approach is algorithm-agnostic, enabling integration of multiple offline RL methods under a unified architecture. We instantiate our framework with three state-of-the-art offline RL algorithms, and trained the models offline using de-identified historical operational logs from a large-scale warehouse. Policy performance is evaluated using a comprehensive multi-method strategy. These include model-free approaches including immediate reward estimation via regression models and long-horizon Fitted Q Evaluation (FQE), as well as model-based Deep Koopman dynamics evaluation. Empirical results reveal that the CQL policy consistently outperforms alternatives, improving system health by 22.97% and reducing average throttling duration by 3.18%. These findings demonstrate the potential of offline RL for safe and scalable warehouse throughput control optimization.
Read the full abstract

All authors Tina Dongxu Li, Mouhacine Benosman, Rajat Kumar, Kevin Tan, Ken Meszaros, Trevor Dardik

Artificial Intelligence

Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs

Xiangbo Gao, Xiukun Huang, Boyu Lu et al. (+5 more)

Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often lack the step-by-step decision semantics needed to keep the rationale causally connected to the planned motion. We introduce Neuro-Symbolic Drive, a neuro-symbolic driving framework that supervises a driving VLA with rule-grounded reasoning traces extracted directly from classical rule-based planners. Our key observation is that rule-based planners are symbolic AI systems that already function as executable reasoning engines: they reason about active safety constraints, search over candidate maneuvers, and select a final trajectory. We instrument these planners in simulation to capture both the executed trajectory and the internal decision trace at each rule-evaluation step. Each trace is serialized into structured rule-grounded reasoning and paired with the trajectory to fine-tune Qwen3.5-4B as a driving VLA. Because these traces are derived directly from the planner states that determine the action, they ensure reasoning is structurally coupled to motion generation by construction, rather than by post-hoc alignment. On our simulator-generated benchmark, detailed rule-grounded reasoning reduces ADE@3s from 0.47 to 0.26 and miss rate from 8.30% to 6.40% under three-camera perception, and from 0.54 to 0.26 and 10.13% to 5.99% under eight-camera perception. Neuro-Symbolic Drive thus converts neuro-symbolic planning logic into structured supervision. Code base: https://github.com/XiangboGaoBarry/Neural-Symbolic-Drive.
Read the full abstract

All authors Xiangbo Gao, Xiukun Huang, Boyu Lu, Junge Zhang, Mengjie Mao, Jiachen Li, Wei Xiong, Zhengzhong Tu

Artificial Intelligence · Cross-listed from cs.CL

When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents

Tianyu Ding and Juan Pablo De la Cruz Weinstein

Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test this proxy for pre-action policy classification in $\tau$-bench using Qwen2.5-3B/7B classifiers. Under gold-policy conditioning, a compact structured state improves macro-F1 over raw trajectories by $0.20$ after tuning at 3B, with the same ordering at 7B under shared hyperparameters. We then replace the benchmark-designated governing rule with the top-ranked benchmark assertion retrieved from decision-time context. Although the exact governing rule is retrieved at rank 1 for only $7\%$ of airline states, the primary 3B classifier obtains macro-F1 $0.58$ with retrieved assertions versus $0.60$ with the gold rule ($\Delta=-0.02$, task-cluster 95% CI $[-0.23,+0.21]$); random non-gold and no-assertion controls score $0.32$ and $0.21$. We do not detect a macro-F1 difference between retrieved assertions and the gold rule in this configuration, although the interval remains too wide to establish non-inferiority. The same qualitative pattern appears with a second retriever and at 7B, while varying across fine-tuning configurations. These results show that exact-match recovery of the benchmark-designated rule can underestimate the downstream utility of retrieved benchmark assertions in this setting. Retrieval should therefore be evaluated inside the classification loop rather than by exact-match recall alone.
Read the full abstract

Artificial Intelligence

RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems

Yarin Yerushalmi Levi, Roy Betser, Amit Giloni et al. (+5 more)

Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond those of traditional LLM vulnerabilities. Existing security evaluations are often tied to specific implementations or domains, limiting unified comparison across heterogeneous systems. To address this gap, we introduce RIFT-Bench, a representation-driven methodology for dynamic red-teaming that enables unified evaluations across diverse agentic architectures. Building on a novel hierarchical representation, RIFT-Bench operates in two automated phases: Discovery, which extracts system structure, and Scanning, which executes adaptive adversarial attacks. It directly evaluates the examined system using 105 adaptive adversarial probes spanning diverse attack vectors and objectives. We demonstrate the effectiveness of the proposed evaluation pipeline across 45 agentic systems spanning a diverse range of implementations, showing that the approach generalizes effectively to heterogeneous agentic architectures. Beyond systems and attacks, RIFT-Bench also supports direct evaluation of mitigation strategies. These key capabilities make RIFT-Bench a scalable foundation for security evaluation of agentic AI systems in practice. Infrastructure code and benchmark artifacts are available at https://tinyurl.com/RIFTBench.
Read the full abstract

All authors Yarin Yerushalmi Levi, Roy Betser, Amit Giloni, Lidor Erez, Itay Gershon, Oren Rachmil, Sindhu Padakandla, Roman Vainshtein

Artificial Intelligence · Cross-listed from cs.LG

Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate

Duncan Soiffer, Chandler Squires, Yuan Guan et al. (+2 more)

The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-defined target distributions such as a geometric combination of the source distributions. In this work, we argue that this task is often infeasible for vanilla conditional diffusion models: we conjecture that no inference-time technique can efficiently produce samples from the target distribution in certain well-motivated settings. This idea is supported by theory-guided generalization arguments and carefully-designed experiments on both synthetic and realistic data. In particular, while recent methods such as Feynman-Kac correction reduce inference-time approximation error, our results show that score estimation error has a more catastrophic effect on performance when the target distribution is out-of-distribution with respect to the sources, highlighting the need for a different approach to this task.
Read the full abstract

All authors Duncan Soiffer, Chandler Squires, Yuan Guan, Jason Hartford, Pradeep Ravikumar

Artificial Intelligence · Cross-listed from cs.LG

ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation

Loay Mualem, Vinh Tong, Samir Darouich et al. (+1 more)

Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs. Unlike recognition tasks, knowledge distillation in conditional diffusion often struggles to transfer knowledge beyond the training distribution, since the predicted noise strongly depends on the conditioning signal. As a result, effective distillation requires exploring a large conditioning space. In practical settings, this creates a major bottleneck. Paired image-condition data may be limited, and generating synthetic images for every available condition is often computationally infeasible, while the pool of conditions, such as text prompts, can be extremely large. Recent work addresses this issue by switching conditions during training, exposing the student to a broader conditioning space without changing the distillation objective. Yet this raises a complementary question: once a large conditioning corpus is available, how should the training effort be allocated? In this work, we introduce ARIA, a framework that adaptively allocates training effort across coarse regions of the conditioning space. By maintaining online estimates of teacher-student discrepancy at the region level, ARIA focuses updates where misalignment persists while preserving the original distillation objective. Empirically, ARIA improves over RC across most architectures and settings, with the clearest gains observed in unseen and underrepresented regimes. We also provide a theoretical analysis showing that the proposed tracking mechanism follows the evolving discrepancy during training under bounded variance and drift assumptions.
Read the full abstract

All authors Loay Mualem, Vinh Tong, Samir Darouich, Mathias Niepert

Artificial Intelligence · Cross-listed from cs.CV

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif et al. (+1 more)

Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain images. PromptKD (CVPR 2024) established this paradigm with a single PromptSRC-finetuned ViT-L/14 teacher and a ViT-B/16 student. We propose TheProfessor, a multi-teacher extension that distills from a fixed two-teacher ensemble: a domain-finetuned PromptSRC ViT-L/14 teacher and a zero-shot EVA-CLIP-L/14 teacher whose logits are pre-computed per dataset. We evaluate single-teacher PromptKD, equal-probability ensembling, and confidence-weighted ensembling on four base-to-novel datasets: Caltech-101, DTD, UCF101, and EuroSAT. In a 12-run single-seed sweep, confidence-weighted ensembling improves average HM from 87.52 to 89.28 (+1.77 points), while equal averaging improves average HM to 88.88 (+1.37 points). Gains are dataset dependent: they are negligible on Caltech-101 (+0.16 HM for confidence weighting), modest on UCF101 (+0.62), and largest on domain-shifted EuroSAT (+5.78). These results update our earlier Caltech-only analysis and show that multi-teacher prompt distillation is most useful when the second teacher contributes complementary supervision under domain shift.
Read the full abstract

All authors Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif, Muzammil Behzad

Artificial Intelligence · Cross-listed from eess.IV

E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis

Sijing Li, Zhongwei Qiu, Zhuoya Wang et al. (+6 more)

While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) strategies typically optimize text fidelity alone, essentially rewarding correct diagnoses derived from language priors rather than genuine visual perception. To address this, we propose cross-view aligned Evidence-driven Multimodal Reinforcement Learning (Evidence-MRL, noted as E-MRL), a reliable RL reasoning framework that formulates the generation process as a Markov Decision Process of "diagnosis-localization-verification". Unlike standard approaches, our model is explicitly trained to identify a "key evidence slice" alongside the global diagnostic report, grounding its findings in verifiable visual evidence. Crucially, we introduce a novel cross-view consistency reward, which validates the semantic alignment between the golden-standard report and a local visual re-query of the selected key slice, providing additional rewards for correctly-localized reasoning. Experiments on large-scale 3D CT tumor datasets demonstrate that E-MRL significantly reduces hallucinations and improves diagnostic accuracy compared to SFT and RL baselines, offering a clinically interpretable solution for visually-grounded and tumor analysis.
Read the full abstract

All authors Sijing Li, Zhongwei Qiu, Zhuoya Wang, Boxiang Yun, Zhenyu Yi, Jianwei Xu, Wenqiao Zhang, Yingda Xia, Ling Zhang

Artificial Intelligence · Cross-listed from cs.CV

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

Davide Caffagni, Alberto Compagnoni, Federico Melis et al. (+5 more)

Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder. However, existing methods typically align a fixed layer of the language backbone, overlooking the fine-grained structure of Transformer models. In this work, we propose Head-Wise Representation Alignment (HeRA), a method that enforces cross-modal alignment at the level of individual attention heads. Our approach is grounded in the Platonic Representation Hypothesis, focusing on preserving the topological structure of representations (i.e., their local neighborhood relationships) across modalities. Following the Mutual K-Nearest Neighbor (MKNN) alignment metric, we introduce a contrastive objective that acts as a differentiable proxy for matching local structures. HeRA applies this objective during multimodal training to specific attention heads in the LLM, selected by their alignment score according to the MKNN metric. Counterintuitively, we find that aligning the least aligned heads yields the largest gains. Extensive evaluations across multiple MLLMs and 18 benchmarks demonstrate that HeRA consistently improves performance on challenging vision-centric tasks and serves as an effective regularizer against visual hallucinations by naturally curbing the over-reliance on linguistic priors. Our code is publicly released.
Read the full abstract

All authors Davide Caffagni, Alberto Compagnoni, Federico Melis, Sara Sarto, Pier Luigi Dovesi, Mark Granroth-Wilding, Marcella Cornia, Lorenzo Baraldi

Artificial Intelligence · Cross-listed from cs.CL

One Year Later...The Harms Persist, But So Do We!

Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar et al. (+1 more)

General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety guardrails remain inadequate and inconsistent across clinical conditions. This study evaluates eight proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Results show that safeguards hold reliably only for suicide and self-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into publicly available settings (e.g., schools, search engines, and consumer chatbots) are particularly concerning.
Read the full abstract

All authors Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar, Anson Antony

Artificial Intelligence · Cross-listed from eess.IV

Promise and challenges of heart chamber segmentation from non-contrast CT scans using contrastive unpaired image translation: a feasibility study

Jing Wang, Tong Yu, Hao-En Lu et al. (+5 more)

Purpose: To evaluate the feasibility and challenges of heart chamber segmentation from non-contrast CT scans using contrastive unpaired image translation and deep learning-based segmentation. Approach: We developed ChameleonNet, a framework utilizing the Contrastive Unpaired Translation (CUT) network with decoupled contrastive learning (DCL) loss to synthesize non-contrast CT from contrast CT scans. Using annotations of four heart chambers (left atrium (LA), left ventricle (LV), right atrium (RA), and right ventricle (RV)) from contrast scans, we trained a Hausdorff distance loss-enhanced nnU-Net on synthesized non-contrast images. The translation model was trained with 35,538 contrast-enhanced and 37,197 non-contrast CT slices. The segmentation model was trained with 292 synthesized non-contrast scans. Performance was evaluated using Dice similarity coefficient (DSC) and 95th Hausdorff distance (HD95) on 36 synthesized non-contrast scans, and volume agreement on 36 real non-contrast CT scans was assessed using Pearson correlation, mean absolute percentage error (MAPE), and mean percentage error (MPE). Results: The segmentation model achieved DSC of 0.94 (0.01), 0.91 (0.04), 0.92 (0.03), 0.93 (0.02), and HD95 of 3.63 (1.49), 5.74 (4.08), 5.18 (1.77), 5.51 (3.21) mm on synthesized non-contrast images for LA, LV, RA, and RV, respectively. On real non-contrast CT scans, Pearson correlations were 0.93, 0.82, 0.87, and 0.89 (all p<0.001), with MAPE ranging from 9.22% to 20.79%, and MPE ranging from -12.52% to 4.67%. Conclusions: ChameleonNet demonstrated feasibility for heart chamber segmentation from non-contrast CT without manual non-contrast annotations. However, volume errors, particularly for LV and RV, indicate that further refinement and validation are needed before clinical use.
Read the full abstract

All authors Jing Wang, Tong Yu, Hao-En Lu, Zixue Zeng, Joseph K. Leader, Xin Meng, Jianbing Zhu, Jiantao Pu

Artificial Intelligence · Cross-listed from cs.SE

JupOtter: Cell-Level Bug Detection in Jupyter Notebooks

Lukas Ottenhof and Thibaud Lutellier

Jupyter Notebooks are an increasingly popular coding environment used across many domains, especially in Python-based data science and scientific computing. Originally used for prototyping and interactive exploration, notebooks are increasingly used to develop more complex programs, leading to a rapid rise in buggy notebooks on platforms like GitHub. To address this trend, we present JupOtter, a bug detection system designed specifically for Jupyter Notebooks. JupOtter features three novel contributions: (1) a notebook-specific tokenization strategy that preserves cell structure, (2) a cell-level bug prediction technique, and (3) a new labeled dataset, OtterDataset, containing over 21,000 notebooks annotated for fine-grained cell-level bug detection. JupOtter achieves cell-level bug detection F1 scores that surpass static analyzers and large language models in two out of three evaluation datasets.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

MGI: Member vs Generated Inference

Bihe Zhao, Michel Meintz, Juangui Xu et al. (+2 more)

As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data. We formalize this challenge as Member vs Generated Inference (MGI): given a sample and a target generative model, infer whether the sample is a true training member or a generated output of that model. Focusing on image generation, we show that existing membership inference methods systematically misclassify generated samples as training members, while attribution-based methods often misclassify true members as generated. This failure arises because both approaches rely on likelihood-related signals that are similarly elevated for training examples and for the model's own outputs. To address MGI, we propose Data Circuit Breaker (DCB), a three-stage method that combines complementary signals from a generative model's autoencoder and latent generator to distinguish training members from generated samples. Across multiple generative models, including image autoregressive and diffusion models, DCB consistently addresses the shortcomings of membership inference and attribution methods, remains effective even when models reproduce near-duplicates of training samples, and generalizes to challenging model derivative settings in which new models are trained on generated data.
Read the full abstract

All authors Bihe Zhao, Michel Meintz, Juangui Xu, Franziska Boenisch, Adam Dziedzic

Artificial Intelligence · Cross-listed from cs.LG

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris et al. (+1 more)

A primary challenge in AI safety is the existence of adversarial examples – slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation of robustness certifications, which, for a given input, determine the largest distortion the input may receive without breaking the network's prediction. Robustness certifications can be interpreted as an axis-aligned hyper-rectangle (multi-dimensional intervals). Most existing approaches focus on maximizing the certification's volume, but recent intractability results prohibit the computation of volume-optimal certifications in reasonable time. We introduce the apothem measure and show how to compute apothem-optimal certifications in a linear number of calls to a NN verifier (oracle) w.r.t. the input domain's diameter. Moreover, we prove that we cannot have a volume-optimal, oracle-based algorithm, even if we discard the oracle costs. Also, we introduce dual certifications – an interval including all instances of a class – thus providing apothem-minimum upper bounds to a robustness certification. Further, we present the ParallelepipedoNN system, which we evaluate on the standard MNIST and Fashion MNIST benchmarks. A preliminary comparison with existing work on the same datasets reveals at least two-fold improvement w.r.t. the minimum edge length.
Read the full abstract

All authors Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris, João Marques-Silva

Artificial Intelligence · Cross-listed from econ.TH

The Measurable Majority

Lawrence S. Moss and Arthur Paul Pedersen

This paper studies strict majority reasoning in finite electorates using so-called $\textit{social decision frames}$: finite sets of voters equipped with distinguished families of coalitions interpreted as those voting blocs evaluated to form a strict majority. A coherence criterion for qualitative majority judgments is identified and shown to give an exact characterization for representability of strict majorities by finitely additive measures. In addition, a minimal natural logic for reasoning about strict majorities is shown to be sound and complete. These developments motivate examination of associated combinatorial questions concerning incoherence in finite families of sets; partial results and a conjecture are given. Finally, the results of this paper are applied to correct a classical representation theorem for weak qualitative probability structures due to Patrick Suppes and to establish a May-type characterization for ordinary strict majority rule for social decision frames.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.MA

Decentralized Coordination of Autonomous Traffic Through Advanced Air Mobility Corridors

Jasmine Jerry Aloor and Hamsa Balakrishnan

The use of dedicated corridors for Advanced Air Mobility (AAM) traffic is one of the most commonly proposed pathways to integrating them into existing airspace operations. Most prior research has focused on the design of networks of AAM corridors and conflict resolution for aircraft within corridors. It is also generally believed that while attractive from an implementation perspective, corridor-based operations may be inefficient, especially in the absence of centralized traffic management. In this paper, we show that contrary to this belief, it is possible for autonomous aircraft to learn to self-organize into corridor flows in decentralized settings. We illustrate our approach using scenarios in which fixed-wing aircraft need to safely and efficiently traverse (1) a single corridor with metering after the exit, (2) a sequence of two consecutive corridors, and (3) a corridor that splits into two. We find that in decentralized settings with only local information, the aircraft are able to conform to the corridor boundaries more than 94% of the time and reach their goal in a relatively efficient manner. Furthermore, tactical interventions to handle violations of the separation minimum are needed only infrequently in low- and medium-density settings. However, such tactical interventions become more frequently necessary only when traffic density is high.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction

Fang Wu, Weihao Xuan, Jure Leskovec et al. (+2 more)

Molecular surfaces encode the geometric and physicochemical patterns that determine antibody-antigen recognition, central to epitope prediction. However, existing methods rely on sequences or backbone structures and struggle to capture discontinuous, surface-driven epitopes. This study presents SurfBind, a surface-centric learning framework for epitope prediction that operates directly on molecular surface representations. SurfBind integrates geometric and physicochemical cues through a Transformer-based architecture with patch-level surface modeling, binder-aware cross-attention, and a hierarchical coarse-to-fine prediction paradigm. Experiments on challenging epitope identification benchmarks, including SAbDab and DB5.5, demonstrate that SurfBind achieves state-of-the-art performance and strong generalization across unseen antibodies and conformational states, highlighting the value of interaction-aware surface modeling for understanding the crucial mechanisms of protein-protein interactions.
Read the full abstract

All authors Fang Wu, Weihao Xuan, Jure Leskovec, Yejin Choi, Li Erran Li

Artificial Intelligence · Cross-listed from cs.CV

From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection

Yuhan Rui, Shihan Qiao, Yibin Lou et al. (+7 more)

Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of spatial-domain detectors that indiscriminately discard critical high-frequency details. Recovering these fragile cues within the spatial domain is notoriously difficult, as it often requires computationally expensive architectural upscaling that inadvertently amplifies background noise. To bridge this gap, we propose a paradigm shift from spatial to spectral feature processing, introducing a holistic solution with the following novelty: (1) A versatile Frequency-Guided Feature Representation framework that generalizes across diverse detector architectures (both CNN and Transformer-based), offering a robust alternative to spatial-only feature extraction; (2) The unified Decompose–Enhance–Reconstruct (DER) operator, instantiated via three lightweight, plug-and-play modules – Wavelet-Difference Gate (WDG), Log-Gabor Enhancer (LGE), and Frequency-Driven Head (FDHead) – to systematically inject frequency-aware modulation into the backbone, neck, and head. This mechanism decouples feature modeling from resolution reduction, capturing discriminative high-frequency components to enable accurate localization with significantly reduced parameter redundancy; (3) Extensive validation on multi-domain benchmarks (VisDrone2019, UAVDT, TinyPerson, DOTAv1) demonstrating consistent gains. Notably, our proposed DERNet series outperforms YOLOv11 models under the same scale while requiring only 1/6 of the parameters, backed by rigorous spectral diagnostics and error decomposition analysis.
Read the full abstract

All authors Yuhan Rui, Shihan Qiao, Yibin Lou, Mingxi Yu, Yutong Wan, Yanqiao Chen, Dongsheng Hou, Zhen Cao, Athena Zhuoming Zhong, Qi Hao

Artificial Intelligence · Cross-listed from math.NA

Ten Digits on a Train: AI-Assisted Verification of Two Eigenvalue Problems

Matthew J. Colbrook

Accurate numerical eigenvalues are often difficult to certify, especially in singular or non-normal settings. This article reports a human–AI collaboration on two such computations. For a singular self-adjoint Schrödinger operator, a verified zero count and Dirichlet–Neumann bracketing certify the complete negative spectrum to ten decimal places. For a delicate non-normal atom–molecule benchmark, a previously unresolved resonance pair is separated, with each member enclosed to ten digits. The second result is achieved not by increasing the precision of one-way shooting, but by reformulating the problem as a global matching system for projective solution lines. The infinite tail is encoded as uncertainty in the terminal projective data, and a componentwise, tail-robust Krawczyk–Brouwer inclusion supplies the certificate. This gives a reusable architecture for analytic boundary-value systems with ill-conditioned propagation and uncertain asymptotic data. The collaboration also exposes the strengths and limits of AI assistance. AI rapidly produced accurate candidates and plausible proof strategies, but several failed, including one apparently complete tail argument that omitted the componentwise check required by a nonuniform polydisc. Validated computation is a stringent test of AI-assisted mathematics: the output is not merely a number, but a number with a proof. These examples show why the proof object matters, and why human mathematical judgment remained decisive. More broadly, as AI makes code, exposition, and plausible numerical claims inexpensive, standards for verification, attribution, peer review, and training must adapt. The implications are unsettling; the opportunity is extraordinary.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.SE

From Task-Guided Conversational Graphs to Goal-Oriented Dialogue Runtimes

Mariano Garralda-Barrio

Graph and multi-agent orchestration frameworks make production large language model (LLM) workflows practical, but they do not by themselves solve conversational continuity when users maintain several interdependent objectives. This conceptual systems paper focuses on the high-complexity end of that design space, where goals can be suspended, resumed, revised, and invalidated by actions in other goals. We introduce the Goal-Oriented Dialogue Runtime (GODR), a framework-neutral design pattern that treats goals, task frames, lifecycle state, invalidation rules, and resumption contracts as first-class runtime objects while delegating bounded execution to graph runtimes, agents, tools, or application programming interfaces (APIs). GODR is not proposed as a replacement for workflow graphs in simple guided processes; it is intended for complex, multi-domain, interruptible conversations where objective continuity cannot be recovered reliably from agent identity, chat history, or execution-graph position alone. The paper formalizes the problem, proposes runtime objects and architecture-selection criteria, and frames evaluation as an agenda for future empirical validation rather than as a measured performance claim.
Read the full abstract