Artificial Intelligence
Simone Gallivanone, Hossein Khodadadi, Mauro Dore et al. (+2 more)
We introduce a large-scale, open-source
dataset of pre-generated
adversarial attacks for
vision-
language models (VLMs). The
dataset is designed to be diverse, representative, and practical, extending existing
benchmarks by covering 10 high-level categories and 55 subcategories of harmful intents. Our primary goal is to make
adversarial data accessible to the research community, given the computational cost and complexity of generating large numbers of attacks. The
dataset comprises 47 524
adversarial samples, generated using state-of-the-art attack strategies from recent literature. Our work complements existing efforts by consolidating and extending prior
benchmarks from multiple established sources, resulting in 7 826 intents, and introduce an additional category to broaden coverage. This provides realistic evaluation resources for studying model robustness and
alignment. Our
dataset intends to enable researchers and practitioners to systematically evaluate the robustness and safety of VLMs, fine-tune attack-generation models, and develop or stress-test defensive guardrails under diverse
adversarial conditions. By releasing this resource, we aim to lower the barrier to
adversarial research and foster more reproducible, comprehensive, and comparable evaluations of VLM safety.
Read the full abstract ▾
All authors Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco
Artificial Intelligence · Cross-listed from cs.CL
On the Stability of Prompt Ranking in Large Language Model Evaluation
Shaoshuai Du, Penghao Liang, Yixian Shen et al. (+3 more)
Prompt-based interaction has become a dominant paradigm for using large
language models (LLMs), where multiple candidate
prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that
prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study
prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two
benchmark tasks, we find that while overall rank correlations are often moderate to high, the identity of the top-performing
prompt frequently changes, leading to unreliable selection decisions. To address this issue, we propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance. Our results show that this approach improves robustness in unstable settings while remaining competitive in more stable regimes. These findings highlight the importance of accounting for evaluation uncertainty in
prompt selection and LLM benchmarking.
Read the full abstract ▾
All authors Shaoshuai Du, Penghao Liang, Yixian Shen, Chuanqi Shi, Hang Zhang, Lun Wang
Artificial Intelligence · Cross-listed from cs.CV
Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs
Stefano Mereu, Oleksandr Kuznetsov, Gabriele Marchello et al. (+4 more)
Convolutional Kolmogorov–Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the structure of the convolution than on each edge, and we organise the design space along a single axis: whether the function acts on the pixel values or on the filter shape. We study three realisations. SV-KAN applies one shared univariate function to the values and leaves the spatial filter free and static, aa classical convolution with a single learnable shared activation. AG-KAN keeps the shared value function but supplies the spatial structure through a content-adaptive Gaussian gate. RF-KAN instead moves the learnable functions onto the filter shape, building each filter from oriented ridge profiles expanded in a localised oscillatory (Morlet) wavelet basis with content-adaptive amplitudes. Under a matched four-layer protocol with in-run references and three seeds, RF-KAN and SV-KAN reach $88.47\pm0.10\%$ and $88.20\pm0.31\%$ on CIFAR-10 and $64.40\pm0.19\%$ and $64.57\pm0.30\%$ on CIFAR-100, at about $0.4$M parameters. At this matched scale the shape model and the simplest value model meet at the top, both above a plain convolution and every per-edge KAN we tested, including the official Gram variant, at roughly a fifth of the parameters. A controlled study attributes the RF-KAN gain to an intrinsically localised oscillatory basis and to content adaptivity, and an ablation that removes the learned shape entirely, leaving only the shared value function, collapses accuracy by over forty points, identifying the learned shape as the load-bearing ingredient at this scale.
Read the full abstract ▾
All authors Stefano Mereu, Oleksandr Kuznetsov, Gabriele Marchello, Alessandro Galdelli, Emanuele Frontoni, Adriano Mancini, Ferdinando Cannella
Artificial Intelligence
When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
Hiroshi Okumura
Large
language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior
benchmark studies have primarily evaluated LLMs' causal
reasoning capabilities, a more fundamental epistemic dimension has been overlooked: Causal Caution, defined as the propensity to refrain from causal judgment when empirical evidence is insufficient. This study examines the systematic suppression of Causal Caution that occurs when LLMs shift from academic to practical advisory contexts. Using an evaluation rubric inspired by Pearl's Causal Hierarchy (the PCH score), we conducted experiments on four high-performance LLMs – Claude Sonnet 4.6, Claude Opus 4.7, GPT 5.5, and Gemini 3.1 Pro – across 480 trials. Causal Caution maintenance rates were 91.7–100.0% in academic contexts but dropped to 6.7–18.3% in practical advisory contexts (Fisher's exact test, p < .001 across all models). Furthermore, when restricted to practical
prompts requesting concrete recommendations or explanatory rationales, only 1 of 200 responses (0.5%) maintained Causal Caution. A brief self-correction
prompt – "Please reconsider this judgment from the perspective of causal relationships" – restored the expression of Causal Caution to maintenance rates of 71.4–100.0% (McNemar's test, p < .001 across all models). These results suggest that helpfulness-oriented response patterns may suppress the expression of Causal Caution in practical advisory contexts, with important implications for organizational governance. The findings indicate that this suppression reflects context-dependent variation in expression rather than an underlying capability limitation, suggesting that multi-
agent architectures that separate proposal generation from causal
auditing may offer a promising governance design.
Read the full abstract ▾
Artificial Intelligence
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
Sijie Wang, Zhengyu Qing, Zhiqiang Tan et al. (+6 more)
Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large
language models (LLMs). In parallel,
diffusion-oriented RL
algorithms, e.g., DanceGRPO and FlowGRPO, have rapidly expanded the scope of RL from
language reasoning to
diffusion-based visual and flow-based generation. However, efficient RL systems for
diffusion generative LLMs remain underexplored. Existing implementations, e.g., veRL-Omni, still rely on colocated execution, which simplifies synchronization but couples rollout and training resources, limits heterogeneous deployment, and constrains independent scaling. To this end, we introduce DigenRL, a disaggregated RL framework for
diffusion-based generative LLMs that supports flexible resource allocation, accommodates heterogeneous GPUs, and facilitates efficient task scheduling. To maximally reduce the execution bubbles in the disaggregated architecture, we propose: 1) a generation-axis pipeline (GAP) and time-step parallelism (TSP) in the
diffusion architecture to enable finer-grained pipelining between rollout and training; 2) an elastic trainer-assisted generation (TAG) approach to enable the trainer GPU resources to dynamically assist in executing rollout generations; and 3) a tightly one-step constrained asynchronous strategy to further utilize the tail bubble in the pipeline. Extensive experiments are conducted on three hardware testbeds with 16-32 GPUs using HunyuanVideo-13B, Wan2.1-14B, FLUX.1-12B, and QwenImage-20B generative models. Experimental results show that DigenRL achieves 1.56-2.10x throughput improvements over state-of-the-art
diffusion RL systems, veRL-Omni and GenRL.
Read the full abstract ▾
All authors Sijie Wang, Zhengyu Qing, Zhiqiang Tan, Yiming Yin, Yeqing Zhang, Yaoyuan Wang, Qiang Wang, Xiaowen Chu, Shaohuai Shi
Artificial Intelligence
MVG-KAN: Multi-View Geo-Wind Guided KAN for PM$_{2.5}$ Forecasting
Cheng Huang, Muyao Guan, Jairus Yougui Railey et al. (+6 more)
Accurate short-term PM$_{2.5}$
forecasting is important for public health protection, air-quality early warning, and urban environmental management. However, PM$_{2.5}$ variation is driven by multiple coupled factors, including stable periodic changes induced by human activities and meteorological regularity, station-specific short-term concentration
evolution, and meteorology-driven pollutant dispersion among monitoring stations. Existing spatio-temporal
forecasting methods may capture station relationships to some extent, but distance-only, correlation-based, or purely adaptive graphs are often insufficient to comprehensively represent these heterogeneous factors, especially wind-direction-dependent pollutant transport. To address this problem, we propose a Multi-View Geo-Wind Guided KAN model for PM$_{2.5}$
forecasting, named MVG-KAN, which models station-level PM$_{2.5}$
evolution from three complementary views: local periodic regularity, station-wise residual temporal dynamics, and meteorological-environment-guided spatial dispersion. Specifically, the periodic-residual
forecasting backbone first separates stable daily and weekly patterns from non-periodic residual variations. A Geo-Wind Graph is constructed by combining geographic distance decay with wind-direction- and wind-speed-aware transport, providing a lightweight physically motivated directed spatial prior for residual propagation among stations. In addition, a temporal Kolmogorov-Arnold network (TKAN) residual head is then introduced to learn station-wise nonlinear autoregressive correction from de-periodized PM$_{2.5}$ residuals and historical multi-pollutant sequences, thereby enhancing the modeling of local residual inertia and pollutant co-variation.
Read the full abstract ▾
All authors Cheng Huang, Muyao Guan, Jairus Yougui Railey, Ning Xu, Honghui Xu, Changjiang Zhang, Zhen Zhang, Shiqing Zhang, Cong Bai
Artificial Intelligence · Cross-listed from cs.LO
What Does ODRL Mean? A Cross-Level Ontological Grounding of Permissions, Prohibitions, and Duties in UFO-L
Daham M. Mustafa, Christoph Lange, Giancarlo Guizzardi et al. (+3 more)
ODRL policy evaluators produce verdicts, but say nothing about the normative positions a policy brings into existence, the authority structures those positions presuppose, or who holds the power to declare a norm violated. We formulate the Cross-Level Design Principle: any normative
language with violable, consequential norms requires both conduct-level positions (Permission, Duty, Right, No right) and competence-level positions (Power, Subjection, Immunity, Disability). Applying this to ODRL, we establish that prohibition is sanctioned (violation possible and consequential), that permission is underspecified across its behaviour parameter (open vs. closed world), and that the formal semantics covers achievement obligations only. We ground ODRL in UFO-L, mapping each activated rule to a simple legal relator and extending coverage from two to eight legal positions; violation-declaration authority, implicit in every existing evaluator, becomes an explicit Power-Subjection pair. All axioms are mechanically verified in Isabelle/HOL and across a 39-problem
benchmark under Vampire, E, and Z3.
Read the full abstract ▾
All authors Daham M. Mustafa, Christoph Lange, Giancarlo Guizzardi, Diego Collarana, Christoph Quix, Stefan Decker
Artificial Intelligence · Cross-listed from cs.SD
ZONOS2 Technical Report
Gabriel Clark, Sofian Mejjoute, Mohamed Osman et al. (+2 more)
We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across scale, data, and training recipe. We scale the model from 1.6B to 8B total parameters (900M active) with a novel mixture-of-experts (MoE) backbone, improving inference latency and throughput. We expand our training corpus from 200K to over 6M hours using a new data processing pipeline, and we simplify our post-training and conditioning recipes to improve naturalness and voice cloning fidelity. We evaluate ZONOS2 8B on quality, speaker similarity, WER, and ZTTS1-Eval, our novel TTS
benchmark, where it performs competitively with state-of-the-art systems while maintaining good streaming latency. We release our model weights and example inference code under an Apache 2.0 license on GitHub and Hugging Face.
Read the full abstract ▾
All authors Gabriel Clark, Sofian Mejjoute, Mohamed Osman, George Close, Beren Millidge
Artificial Intelligence
Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation
Martin Valls, Pascal Bourdon, Christine Fernandez-Maloigne et al. (+2 more)
AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging. Multi-modal image analysis plays a crucial role in optimizing examination quality, yet acquiring multiple imaging modalities in clinical settings remains resource-intensive and time-consuming, especially for 3D imaging. To address this challenge, we propose a novel image-to-image translation model based on Brownian Bridge
Diffusion Models (BBDM), which synthesizes
magnetic resonance imaging (MRI) sequences from 2D axial slices. Our approach integrates a variational encoder-guided
diffusion mechanism, leveraging probabilistic image distributions to enhance synthesis quality. Evaluated on the BraTS 2021
dataset, our Probabilistic-BBDM (Prob-BBDM) achieves superior performance across multiple translation tasks, reaching up to 88.46% SSIM and 26.09 dB PSNR, with consistent improvements over baselines. Notably, our
diffusion process requires only 4 steps, making it computationally efficient while maintaining high-quality synthesis. To further validate generalizability, we test Prob-BBDM on an external third-party
dataset, demonstrating consistent performance across domains. Additionally, we assess the clinical utility of the synthesized slices by using them as input to a pre-trained
segmentation model. Tumor
segmentation yields a Dice score of 88.71% and an HD95 of 3.49 mm, confirming that the synthesized slices preserve critical diagnostic information. These results highlight the potential of Prob-BBDM for high-quality, efficient, and generalizable MRI synthesis, offering a promising step toward improved medical image translation.
Read the full abstract ▾
All authors Martin Valls, Pascal Bourdon, Christine Fernandez-Maloigne, Guillaume Herpe, David Helbert
Artificial Intelligence
LemonHarness Technical Report
Kailong Ren, Fubo Sun, Jiachen Liu et al. (+18 more)
As large
language model (LLM)
agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However,
agents typically observe only tool outputs and log fragments, while the actual state changes occur in the file system. Without explicit workspace boundaries, state-changing operations such as file writes and temporary artifact generation may scatter changes across paths. Over time, these weakly constrained changes accumulate, making states such as modified files difficult to track. This paper presents LemonHarness, an integrated execution framework for long-horizon
agents. LemonHarness establishes an explicit execution boundary by constraining state-changing operations within a clearly defined workspace and bringing model invocation, tool execution, and rule knowledge within a single controlled boundary. State-changing operations, including file writes, dependency installation, and temporary artifact creation, are executed through structured tool interfaces, with execution feedback recorded as observations available to subsequent model decisions. The system also introduces a reusable rule knowledge base, which turns recurring execution rules and acceptance criteria into runtime knowledge. LemonHarness further adds a time-aware execution mechanism that exposes elapsed and remaining budget to the model, so it can rebalance exploration, implementation, and validation effort as time pressure shifts and avoid timeouts from long waits or excessive verification. On Terminal-Bench 2.0, LemonHarness_GPT-5.3-CodeX reached 84.49% accuracy over 445 trials; pairing the same framework with the stronger GPT-5.5 backbone raised the average accuracy to 86.52% across five jobs. The results suggest that a unified runtime boundary, callable rule knowledge, and time-aware execution can improve the stability of long-horizon
agent execution.
Read the full abstract ▾
All authors Kailong Ren, Fubo Sun, Jiachen Liu, Liu Yang, Zimo Yin, Jiaying Li, Congli Yin, Ming He, Yu Huo, Jiawei Liu, Zeping Chen, Yubin Huangfu, Ronghua Li, Yixuan Wu, Xing Su, Yanzhi Xu, Likang Wu, Hongke Zhao, Lei Zhang, Xiaohui Geng, Jianping Fan
Artificial Intelligence · Cross-listed from cs.SD
Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation
Baisen Wang, Chenxi Bao and Qisong Han
Interactive music and live performance relies on real-time human expression, but modern generative music AI remains largely absent from this domain due to its prohibitive inference latency and offline rendering paradigm. To provide pioneer musicians with a novel medium for interactive composition, we should fundamentally change these static models into dynamic, playable instruments. In this paper, we propose a framework that bridges this gap. To achieve the low latency required for live interaction without sacrificing structural coherence, we formulate
distillation within a streaming autoregressive latent space. Our approach gets rid of the need for expensive paired audio-latent
datasets by utilizing
prompt-only inputs to synthesize teacher-guided, chunk-wise trajectories on the fly. Because live instruments require high acoustic fidelity, we introduce music-aware consistency objectives, which combine latent, spectral, and temporal-difference losses, to preserve crucial qualities like timbre, transients, and rhythmic stability during accelerated single-step streaming generation. Implemented via parameter-efficient adaptation, our
distillation reduces generation steps to achieve a low real-time factor. Crucially, by operating as a continuous autoregressive stream, the system can seamlessly assimilate dynamic human inputs on the fly, allowing users to instantly steer the musical trajectory without interrupting the audio flow. Ultimately, this work recontextualizes generative text-to-music models not as passive
prompt-and-wait systems, but as responsive instruments, opening new frontiers for live human-AI musical co-creation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
Conor Finlay, Joshua Kurien, Saurabh Dash et al. (+2 more)
Reasoning language models are increasingly asked not only to answer difficult questions, but also to estimate their likelihood of success. Existing methods typically elicit confidence only once: either before thinking or after answering. We argue that confidence in
reasoning models is state-dependent: before thinking, confidence should estimate the chance of the model correctly solving the
prompt, while after thinking it should predict whether the realized answer is likely to be correct. This distinction determines the appropriate supervision target:
prompt-level success should supervise confidence estimates made after seeing the
prompt, while individual answer-level correctness should supervise confidence estimates made after answering. We introduce CALIBER (Calibration Before and After
Reasoning), which elicits both estimates and supervises each with the target matched to its information state. Under this unified protocol, CALIBER reduces Expected Calibration Error (ECE) by 52.5% over the strongest single-confidence baseline on BigMathDigits for the 7B model, while achieving the best Brier score and AUROC, and remains within 2.1 points of the best accuracy. Further, on a larger 30B model, CALIBER achieves the best ECE on BigMathDigits while remaining competitive in Brier score and AUROC. Out of distribution, it achieves the best ECE and Brier score on GPQA and TriviaQA, and remains competitive on SimpleQA. Ablations further show that this position-target
alignment is most beneficial under distribution shift where it consistently reduces calibration error across all out-of-distribution
benchmarks.
Read the full abstract ▾
All authors Conor Finlay, Joshua Kurien, Saurabh Dash, Marzieh Fadaee, Beyza Ermis
Artificial Intelligence
Tractable Reasoning and Conjunctive Query Answering for Defeasible DL-Lite under Rational Closure
Giovanni Casini and Umberto Straccia
In Description Logics (DLs),
reasoning under Rational Closure (RC) is a well-known and widely accepted non-monotonic formalism to handle defeasible knowledge. In this paper, we study the application of RC to the core and horn variants of the DL-Lite family of lightweight description logics. We analyze both entitlement (instance checking) and Conjunctive Query (CQ) answering under RC. Our main contribution is providing a plug-in architecture that builds upon existing standard classical reasoners, establishing that
reasoning and CQ answering under RC for DL-Lite can be done efficiently with minimal computational overhead.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Pigeonholing: how bad prompts hurt models, causing collapse and mistakes
Hyunji Nam, Keertana Chidambaram, Dorottya Demszky et al. (+1 more)
While in-context learning is generally shown to be effective in Large
Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing." **Unintentionally bad** contexts can happen without malicious jailbreaking intents: For example, a user asks the model to justify an incorrect math
theorem or fails to correct the model's buggy code. Specifically, we investigate “pigeonholing" in two scenarios: (1) when the user suggests a solution, and (2) when the conversation context includes the assistant's previous (incorrect) responses. Our experiments across 10 verifiable and open-ended tasks with 10 different models show that pigeonholing manifests in several ways: (1) repeating the incorrect answers from context (leading to 38-40% performance drop), (2) converging on a narrow set of answers in coding and text generation without exploring alternatives, and (3) flipping stance on controversial topics to align with the user or the assistant's previous claims. We find that pigeonholing worsens almost monotonically with the number of conversation turns (performance drops by additional 14+% as repeated mistakes increase from 1 to 5), and pigeonholing-induced mode collapse can happen even when the provided example is correct. As a step toward mitigation, we propose RLVR with synthetic errors which improves models by 43-60% under bad contexts compared to vanilla RLVR baselines.
Read the full abstract ▾
All authors Hyunji Nam, Keertana Chidambaram, Dorottya Demszky, Natasha Jaques
Artificial Intelligence · Cross-listed from cs.CE
Neural Network-Based Parametric Model Reduction for Predicting Turbulent Flow for Different Vehicle Geometries
Kazuto Ando, Rahul Bale, Akiyoshi Kuroda et al. (+1 more)
Numerical simulations in industrial applications often require performing numerous high-precision computations parameterized by specific experimental conditions. For instance, in vehicle body design, aerodynamic simulations are essential for evaluating the aerodynamic characteristics of various proposed body geometries. However, computational resource constraints often become a bottleneck. Therefore, achieving the desired accuracy while minimizing computational cost is crucial. To address this challenge, model reduction methods have been developed to decrease the degrees of freedom by constraining the possible states of a physical system to a lower-dimensional subspace. In particular, reduction techniques that project the system onto a nonlinear subspace using neural networks have been actively studied. Our previous research developed a reduced-order model that integrates neural-network-based model reduction with a time-
evolution method, implemented as a distributed parallel training framework to process high-resolution flow field data efficiently. In this study, we extend this reduction approach by incorporating a variational autoencoder to assess its robustness in high-Reynolds-number flows around multiple vehicle bodies with varying geometries. Specifically, we evaluate the reconstruction accuracy of
vortex generation across different spatial and temporal scales using a compact latent representation, with a particular focus on the flow behavior near the rear end of the vehicle body.
Read the full abstract ▾
All authors Kazuto Ando, Rahul Bale, Akiyoshi Kuroda, Makoto Tsubokura
Artificial Intelligence · Cross-listed from cs.CL
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
Noor Islam S. Mohammad and Ulug Bayazit
Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no mechanism to condition
attention on external lexical knowledge. We introduce \surgellm, a unified
transformer framework that addresses each with a dedicated lightweight module: a
surgical feature gate (learned per-dimension sigmoid over curated lexical indicators and [CLS]; provably degenerates to identity when features are uninformative), task-conditioned prefix
tokens (quantized feature values and task identity prepended to every input), and Instance-Weighted Normalization (IWN; removes class-prior bias from gate statistics). We prove an excess-risk bound linking gate benefit to
surgical feature
alignment. Across four tasks, SST-2, multi-hop
retrieval, LLM-
prompt attribution, and authorship detection, covering 17,830 examples and eleven model variants over three seeds, the IWN variant achieves macro-F1 0.940 ($+0.036$ over the strongest non-IWN baseline; $+0.130$ on authorship detection). A random-vocabulary control ($-0.028$ avg.\ F1) confirms gains are lexical, not parametric. Code, vocabularies, and a $99.5\%$-recovery auto-extraction recipe are released.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Social Structure Matters in 3D Human-Human Interaction Generation
Zhongju Wang, Beier Wang, Yatao Bian et al. (+6 more)
Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from
language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requires modeling the underlying social structure that governs phase progression, actor roles, and inter-actor coordination. In this paper, we formulate HHI generation as a social structure modeling and grounding problem: the model must first infer how an interaction unfolds and how the two actors coordinate their roles, and then realize this structure as continuous, physically plausible, and partner-aware 3D motion. To study how such structure should be modeled, we first examine the capability boundary of large
language models (LLMs) for HHI generation. Our analysis shows that LLMs can think by recovering phase decompositions and partner-aware roles, but cannot directly move, as they fail to generate dynamic, physically plausible, and interaction-aware motion. This motivates our planner-executor paradigm, Think with LLM, Move with Motion Skill. The LLM planner converts implicit interaction semantics into motion-aligned social supervision by decomposing interactions into phases, assigning partner-aware actor roles, and aligning them with motion sequence. The motion executor then grounds the planned social structure into coordinated two-person motion by adapting a pretrained solo motion model with LoRA, previous-phase self-conditioning, and ego-relative partner conditioning. Together, our Solo-to-Social framework bridges social organization and motion realization, producing 3D HHI with improved phase consistency, role
alignment, and partner-aware coordination.
Read the full abstract ▾
All authors Zhongju Wang, Beier Wang, Yatao Bian, Pichao Wang, Zhi Wang, Daoyi Dong, Hongdong Li, Huadong Mo, Zhenhong Sun
Artificial Intelligence
Probing the Misaligned Thinking Process of Language Models
Kaiwen Zhou, Constantin Venhoff, Jonathan Michala et al. (+2 more)
Large
language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-stakes settings, it is critical to reliably detect such behaviors to ensure safe and responsible use. In this work, we propose to monitor misalignment by decomposing it into fine-grained cognitive processes – misalignment indicators – and detecting their presence in a model's internal activations via linear probes. We develop a taxonomy of 18 indicators spanning different misaligned behaviors, paired with an automated, meta-plan-guided pipeline that generates multi-turn training conversations. To rigorously evaluate generalization, we construct an out-of-distribution suite combining automated behavioral elicitation, established misalignment
benchmarks, and natural benign conversations. Across 5 misaligned behaviors, our probes match a strong LLM judge with 0.935 AUROC on out-of-distribution
benchmarks while keeping a low false positive rate on benign traffic. We further perform in-depth analysis to understand the probes and the model's internal representations of misalignment indicators.
Read the full abstract ▾
All authors Kaiwen Zhou, Constantin Venhoff, Jonathan Michala, Xin Eric Wang, William Saunders
Artificial Intelligence · Cross-listed from cs.SE
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Pingchuan Ma, Zhaoyu Wang, Zimo Ji et al. (+5 more)
Large
language model (LLM)
agents increasingly automate complex tasks by integrating
language models with external tools and environments. However, their autonomy poses significant safety risks:
agents may execute destructive commands, leak sensitive data, or violate domain constraints. Existing safety approaches face a fundamental tradeoff: hand-crafted rules are interpretable but brittle, with overly conservative rules blocking safe operations (high false positives) while permissive rules miss unsafe behaviors (high false negatives). Neural classifiers lack the interpretability required for safety-critical deployments. We present AutoSpec, a framework that automatically evolves deployed expert-designed safety rules from user safe/unsafe annotations through counterexample-guided inductive synthesis (CEGIS) guided by inductive logic programming (ILP). Starting from the expert rules and a stream of annotated traces, AutoSpec iteratively evaluates rules, mines false-positive and false-negative counterexamples, uses ILP to learn which predicates discriminate them, generates candidate rule edits, and verifies candidates to select the best revision. The key insight is that ILP efficiently identifies predicates that appear frequently in false negatives but rarely in false positives (or vice versa), dramatically
pruning the exponential search space of rule edits. This continues until convergence, producing interpretable rules that balance precision and recall. We evaluate AutoSpec on 291 execution traces spanning code execution and
embodied agent domains. AutoSpec raises rule F1 to 0.98 and 0.93 across the two domains, achieving up to 94% false positive reduction while maintaining high recall, and converges within 4-5 iterations. The ILP-guided approach achieves up to 4.8x higher F1 than heuristic CEGIS. The learned rules are human-readable, auditable, and generalize to unseen scenarios.
Read the full abstract ▾
All authors Pingchuan Ma, Zhaoyu Wang, Zimo Ji, Yuguang Zhou, Zhantong Xue, Zongjie Li, Shuai Wang, Xiaoqin Zhang
Artificial Intelligence
Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
Lianshuai Guo, Zhongzheng Yuan, Xunkai Li et al. (+2 more)
Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data
privacy. However, real-world data categories frequently exhibit long-tailed distributions. Such statistical scarcity severely degrades performance in two ways: it biases the global model toward majority classes, and it structurally isolates minority nodes by submerging them in heterophilic, head-dominated neighborhoods. While existing methods attempt
topology-agnostic statistical compensations, they often fail under data scarcity. Instead of recovering tail nodes, they overfit the structural noise from adjacent dominant classes, leading to representation degradation. To address these limitations, we propose FedEPD, a framework built on a dual decoupling paradigm that separates topological purification from semantic recalibration. Specifically, FedEPD utilizes distribution-aware Dirichlet energy
pruning to filter spatial heterophilic edges. It then overcomes Non-IID distribution shifts by extracting robust global prototypes from topologically central nodes, which are incorporated into local representations via a spatial low-pass prototype injection. Furthermore, a two stage alternating optimization strategy strictly protects majority decision boundaries while improving minority accuracy. Extensive experiments demonstrate that FedEPD achieves state-of-the-art performance across diverse long-tailed
benchmarks, yielding absolute improvements of up to 4.97% in Accuracy and 5.48% in Macro-F1.
Read the full abstract ▾
All authors Lianshuai Guo, Zhongzheng Yuan, Xunkai Li, Meixia Qu, Wenyu Wang
Artificial Intelligence
SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
Yucheng Yuan, Yuanfeng Ji, Zhongxiao Li et al. (+1 more)
Spatial proteomics enables single-
cell-resolution characterization of
protein expression within tissue architecture, playing a critical role in understanding tumor microenvironments and guiding precision medicine. However, current analysis workflows remain fragmented, requiring expert manual orchestration of heterogeneous tools and limiting research scalability and reproducibility. We present SP-Mind, the first autonomous AI
agent designed to unify the spatial proteomics analysis pipeline, from raw multiplexed tissue imaging to downstream phenotype discovery. Equipped with expert-curated biological analysis skills and specialized computational tools, SP-Mind converts natural-
language queries into end-to-end analytical workflows without task-specific fine-tuning. To rigorously evaluate its capabilities, we introduce SP-Bench, a comprehensive
benchmark spanning diverse tissue types, comprising 102 tasks across 18 distinct categories. Through extensive evaluation on SP-Bench and established downstream tasks, SP-Mind achieves state-of-the-art performance compared to existing open-source biomedical
agent baselines. Code is publicly available at https://github.com/tomtommyyuan/spmind.
Read the full abstract ▾
All authors Yucheng Yuan, Yuanfeng Ji, Zhongxiao Li, Ruijiang Li
Artificial Intelligence
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Xirui Li, Zhe Liu, Xiaoqing Ye et al. (+4 more)
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching decoder, FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model, forcing the model to internalize the correlation between an action and its outcomes in safety, progress, comfort, and rule compliance. To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation. The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals. FlowR2A achieves state-of-the-art results on the NAVSIM v1 and v2
benchmarks, with
multimodal proposals of substantially higher quality than prior methods.
Read the full abstract ▾
All authors Xirui Li, Zhe Liu, Xiaoqing Ye, Wenhua Han, Yifeng Pan, Junyu Han, Hengshuang Zhao
Artificial Intelligence
Exploring the relationship between human-centric AI and firm idiosyncratic risks
Zhen-Yuan Ralph Liu, Yu-Ting Wang, Jia-Jia Yan et al. (+2 more)
Despite the extensive discussions of human-centric AI (HCAI) in Industry 5.0, its effects on firms' idiosyncratic risks (IR) remains underexplored. This is an imperative issue for firms navigate financial risks during the current technological revolution, as IR reflects investor reactions to corporate heterogeneous AI strategies and implementations by isolating firm-level stock
volatility from systematic factors. Integrating situated AI theory with social-technical systems theory, we conceptualise HCAI as a situated AI strategy that reduces AI-related ethical risks and fosters AI-Human synergies in firms' business operations, ultimately reducing IR by aligning with stakeholders' diverse expectations. Moreover, socio-technical factors, namely digitalisation, operational efficiency, executive shareholding, and CEOs with IT background, may moderate the HCAI-IR relationship. Using a multi-source panel
dataset of Chinese listed firms from 2015 to 2023, we find that HCAI is associated with lower firm IR. Furthermore, digitalisation and executive shareholding strengthen this risk-reducing effect, whereas operational efficiency and CEOs with IT background surprisingly attenuate it. Our findings offer theoretical contributions and practical insights for both ethical AI governance and firm financial risk management in the AI era.
Read the full abstract ▾
All authors Zhen-Yuan Ralph Liu, Yu-Ting Wang, Jia-Jia Yan, Shivam Gupta, Mihalis Giannakis
Artificial Intelligence · Cross-listed from cs.CV
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
Chang Liu, Mingwen Shao, Xiang Lv et al. (+5 more)
Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image
diffusion model. However, existing methods remain two practical challenges: (1) They primarily generate single 3D object, but struggle to generate multi-object compositional 3D assets due to the lack of the modeling for Gaussian primitives in reasonable interactions. (2) They often suffer from cross-view inconsistency during 3D optimization, as Score
Distillation Sampling inherently performs on each single view, inevitably resulting in cross-view
hallucinations. To solve above issues, we propose I2C-3D, a novel optimization-based method to generate multi-view consistent compositional 3D assets with reasonable interactions. Specifically, we propose an Inclusive Interactive Collisions strategy to guide Gaussian primitives appearing in reasonable interaction regions naturally, thereby ensuring objects in the compositional scene interact in a physically plausible and visually coherent way. Additionally, to enhance multi-view consistency, Multi-View Adaptive Score
Distillation Sampling is devised to distill multi-view consistency prior and layout prior from pre-trained
diffusion model by modulating
attention map of instance
token and spatial
token across viewpoints. Benefiting from above elaborate designs, I2C-3D not only generates high-fidelity multi-view consistent compositional 3D assets but also supports 3D editing flexibly, facilitating complex scene generation. Extensive experiments demonstrate our I2C-3D outperforms existing methods in generation quality and multi-view consistency.
Read the full abstract ▾
All authors Chang Liu, Mingwen Shao, Xiang Lv, Xinyuan Chen, Lingzhuang Meng, Qiao Zhang, Zhengyi Gong, Jinghao Hu
Artificial Intelligence · Cross-listed from cs.CL
Junhyeok Lee, Han Jang, Hyeonjin Goh et al. (+1 more)
Retrieval-augmented generation (RAG) in clinical settings increasingly requires
multilingual retrieval against predominantly English evidence corpora.
Multilingual medical
retrieval demands three capabilities: cross-lingual
alignment, concept discrimination, and evidence
retrieval. However, existing
benchmarks evaluate these only in isolation, leaving the interaction between biomedical expertise and
multilingual coverage unmeasured. We introduce MMed-Bench-IR, a
benchmark designed to disentangle these axes across 6
languages and three structurally heterogeneous tasks: (1) cross-lingual medical QA
retrieval with 6,127 queries grounded in the Unified Medical
Language System (UMLS), (2) concept discrimination over 4,975 confusion sets at three difficulty tiers, and (3)
multilingual evidence
retrieval for RAG with 2,040 quality-assured queries. The three tasks share zero concept and query overlap by design, ensuring that aggregate scores reflect genuine capability breadth. Evaluation of ten systems across six paradigm families reveals severe cross-lingual failure: biomedical encoders that score 0.818 nDCG@10 in English drop to 0.056 in Japanese, a gap that English-only
benchmarks cannot detect.
Read the full abstract ▾
All authors Junhyeok Lee, Han Jang, Hyeonjin Goh, Kyu Sung Choi
Artificial Intelligence
Navigating User Behavior toward Personalized Multimodal Generation
Hengji Zhou, Yufeng Liu, Ye Liu et al. (+3 more)
Modern AIGC pipelines deliver high-fidelity images and
videos but presuppose a well-formed creation instruction, while end users rarely articulate visual details, leaving generators misaligned with user demand. We study personalized content generation, which turns a user's interaction history into an executable instruction for downstream synthesis, and identify two obstacles: behavior must be encoded in a form legible to
language reasoning, and the model must acquire instruction-writing skill absent from both pretraining and behavior data. We propose NaviGen, which represents each item with a dual identifier coupling a collaborative code and a textual code as a behavioral substrate and a semantic bridge in one
token stream. On this representation, a two-stage SFT+RL pipeline first distills preference
reasoning and instruction writing from evolutionarily searched supervision, then aligns generation with user intent through hierarchical and self-consistent rewards. Experiments across product, game, and short-
video domains show that NaviGen improves personalized image and
video generation, strengthens next-item prediction, and yields more specific, relevant, and visually generatable instructions. Our code is released at: https://github.com/iLearn-Lab/NaviGen.
Read the full abstract ▾
All authors Hengji Zhou, Yufeng Liu, Ye Liu, Yong Xu, Lianghao Xia, Liqiang Nie
Artificial Intelligence · Cross-listed from cs.CV
Co-occurring Associated REtained concepts in Diffusion Unlearning
Miso Kim, Georu Lee, Yunji Kim et al. (+3 more)
Unlearning has emerged as a key technique to mitigate harmful content generation in
diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig.1, unlearning nudity can unintentionally suppress the concept of person, preventing a model from generating images with person. We define these undesirably suppressed co-occurring concepts that must be preserved CARE (Co-occurring Associated REtained concepts). Then, we introduce the CARE score, a general metric that directly quantifies their preservation across unlearning tasks. With this foundation, we propose ReCARE (Robust erasure for CARE), a framework that explicitly safeguards CARE while erasing only the target concept. ReCARE automatically constructs the CARE-set, a curated vocabulary of benign co-occurring
tokens extracted from target images, and leverages this vocabulary during training for stable unlearning. Extensive experiments across various target concepts (Nudity, Van Gogh style, and Tench object) demonstrate that ReCARE achieves overall state-of-the-art performance in balancing robust concept erasure, overall utility, and CARE preservation.
Read the full abstract ▾
All authors Miso Kim, Georu Lee, Yunji Kim, Hoki Kim, Jinseong Park, Woojin Lee
Artificial Intelligence · Cross-listed from cs.CV
Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms
Afifa Khaled, Said Jadid Abdulkadir and Majdy Mohamed Eltayeb Eltahir
Three-dimensional scene completion has evolved as a major problem in computer
vision and robotics, and its applications are diverse, including autonomous
navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten years, i.e., 2016 to 2026, which has revolutionized the field from the voxel semantic completion paradigm represented by SSCNet to the latest paradigm that combines generative
diffusion priors with real-time rendering using a Gaussian splatting technique. The
evolution in representation paradigms, such as voxel grids, point learning, implicit neural fields,
transformer networks,
diffusion networks, and the latest paradigm based on rendering-aware 3D Gaussian primitives, has been discussed in this study. A comprehensive analysis has been carried out on the contributions made in the last ten years, and a taxonomy has been developed to provide a clear idea about the contributions made in the field. The study has also discussed the research contributions made in the field, along with the challenges that still need to be addressed. Finally, the study has presented a research agenda that will provide a clear idea about the directions that can be followed in the development of the next-generation system
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring
Dominik Lindner, Johann Schmidt, Tom Siegl et al. (+2 more)
Pretrained
vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usually restored either by building equivariance into the architecture or by retraining with augmentation, both of which require changing or retraining the model. Test-time canonicalization instead leaves the classifier untouched. It undoes the transformation of each input, mapping it to a canonical form near the training distribution before classification. Existing canonicalizers, however, rely on a narrow set of logit-based energy scores and bespoke search procedures, leaving the design space of scoring functions and optimizers unexplored. We reframe canonicalization as out-of-distribution (OOD) detection, which lets any OOD score serve as the energy minimized over transformations. Across
benchmarks ranging from handwritten characters and sketches to natural images and 3D point clouds, we systematically evaluate around twenty OOD scores and nine search
algorithms, finding that distance-based scores paired with random search and local refinement perform best overall. Because canonicalizing an already-aligned input can hurt accuracy, we add a gated mechanism that transforms an input only when its OOD score indicates this is needed, preserving most in-distribution accuracy while retaining the robustness gains on transformed inputs. Code is available at github.com/johschm/its.
Read the full abstract ▾
All authors Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker, Sebastian Stober
Artificial Intelligence · Cross-listed from cs.SE
Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy
Youran Sun, Xingyu Ren, Chugang Yi et al. (+4 more)
Large
language models are making research production scalable, shifting the bottleneck from producing artifacts to judging claims. We present Agon, a research orchestrator that validates what can be checked inside the workflow and leaves the remaining judgments to human scientists. Agon is built on six design principles:
Prompt Economy, Future-Facing, Minimal
Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. We ran Agon across domains for 444 iterations of
Prompt Economy loops, using only small starting topics and no human-written experimental code. These deployments demonstrate scalability while exposing new classes of failure. We organize these failures into a taxonomy along severity, fixability, visibility, and capability locus. The taxonomy separates failures the loops can see and fix from those that require human judgment. Together, these results show that Agon is pushing research toward a new paradigm: machine scales, human steers.
Read the full abstract ▾
All authors Youran Sun, Xingyu Ren, Chugang Yi, Jiaxuan Guo, Kejia Zhang, Jianda Du, Haizhao Yang