Artificial Intelligence · Cross-listed from cs.CL
Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
Dalton Raphael Harmsen, Swier Garst, Thomas van Osch et al. (+2 more)
Cross-lingual transfer describes how knowledge in a source
language benefits a target
language. Measuring it quantitatively requires broad multilingual pre-training, as prior work has done with cross-lingual transfer
matrices. We ask whether transfer is predictable from freely available typological features, and whether the prominence of high-resource source
languages reflects typology or data quality and quantity. We show that typological databases contain cheap and dense signals about cross-lingual transfer. Our typology-only random forest on a 24-
language prior-work transfer
matrix scores leave-one-
language-out $\rho{=}0.705$ and $R^2{=}0.49$, beating a non-typological control at $\rho{=}0.62$, which verifies the ability of typology-only predictions to reconstruct costly measured cross-lingual transfer. The signal survives leave-one-script-out and leave-one-family-out protocols, so script and family confounding do not explain the effect. By decomposing the transfer into a typology term and a resource-and-script bias term, we find the best-source ranking sensitive to this bias. In contrast, typology is not affected by this bias, which makes it a zero-compute screening tool that replaces hundreds of training runs with a model fit. Our code is available \href{https://github.com/dharmsen/typo-x-ling-transfer}{here}.
Read the full abstract ▾
All authors Dalton Raphael Harmsen, Swier Garst, Thomas van Osch, Zarè Palanciyan, Joaquin Vanschoren
Artificial Intelligence · Cross-listed from cs.LG
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
Nima H. Siboni
Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribution rather than the improved policy's own. The substitution makes the objective estimable from the behavioral policy's rollouts but adds a bias growing with policy divergence, hence the trust region or clip, and hence no reuse of a batch far off-policy. We show that under history-injective dynamics, where each state is reached by exactly one history, the dropped state-visitation ratio equals the product of per-step policy ratios along the sampled prefix, on every trajectory and not only in expectation. The ratio is therefore restored exactly, from log-probabilities PPO already computes. Autoregressive generation and canonical-order constructive optimization are both history-injective. The exact correction pays importance-sampling variance that grows with the horizon, so we generalize it to a one-parameter family with PPO ($\alpha{=}0$) and the full correction ($\alpha{=}1$) as endpoints: a single bias–variance knob. A gradient-level analysis of the unclipped surrogate identifies two channels the correction acts through and three conditions under which it carries signal; an enumerable testbed confirms the conditions' predictions. On hard credit-assignment scheduling tasks, a short corrected warmup with aggressive early sample reuse learns faster than PPO and than the same reuse uncorrected; the marginal gain grows with task difficulty ($+0.02$ to $+0.09$ learning-curve AUC), and the early win over PPO tracks the prefix bias that reuse incurs. A correction held throughout, or applied where clipping already contains the reuse bias, is null to harmful.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
Marcio A. Sampaio, Paulo H. Ranazzi and Martin J. Blunt
Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions (non-Gaussian). In this way, for these methods, we need to apply efficient parameterization techniques. Currently, the most efficient methods for performing parameterization are deep learning models. However, given the variety of existing deep learning models, studies have not identified which is most suitable for use with ensemble-based methods, although some important models had already been evaluated. Based on a recent literature review, the most promising models selected were VAE-GAN, Latent
Diffusion, and StyleGAN models. As a novel aspect of this work, data assimilation with the second generation of StyleGAN (StyleGAN2) model was performed using the latent z-space and intermediate w-space, separately. They were applied in two 2D case studies: one categorical (three facies) and the other continuous. The results demonstrated that all three models are highly efficient, with the StyleGAN2 model standing out for generating samples with geological realism and achieving excellent data matching in the cases studied. Our findings show that performing data assimilation with StyleGAN2 using the intermediate space (w-space) yielded better results than the traditional application in the latent space (z-space). This is due to the fact that ESMDA uses linear updates and the w-space is much more linear and disentangled than the highly entangled z-space, thereby ensuring that the updated vectors remain close to realistic geological patterns. These results were validated using main geostatistical and history matching metrics.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
Xinyue Xu, Jiahao Zhang, Lijie Hu et al. (+2 more)
Sparse autoencoders (SAEs) reveal visual structure in
diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (
Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence. D-Scope aggregates SigLIP~2
embeddings of highly activating image patches into visual centroids. Matching target text descriptions against these visual centroids in the shared image-text
embedding space then enables
retrieval of individual features without per-feature text annotations. The underlying patches provide evidence for inspecting each selection, while spatially masked interventions test the corresponding decoder direction at varying strengths under fixed generation conditions. We characterize 150 SAEs across two model families and five layers, and introduce a
benchmark of 100 target concepts with ten contexts each spanning under-specified and explicit-conflict conditions. Our empirical results show that high reconstruction fidelity can coexist with low dictionary utilization and limited visual-evidence coverage. Under per-case best-of-sweep strength selection, contrastive
retrieval yields larger mean regional SigLIP~2 gains than direct
retrieval across the tested steering configurations, without consistently improving outside-region preservation. D-Scope provides an inspectable framework for evaluating sparse DiT features through their visual evidence and the effects of their decoder directions on generation. The demo is available at https://jiahaozhang-public.github.io/d-scope/.
Read the full abstract ▾
All authors Xinyue Xu, Jiahao Zhang, Lijie Hu, Peter Hase, Hao Wang
Artificial Intelligence · Cross-listed from cs.CR
Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents
Tobias Kaiser and Aritra Dhar
Skills extend an
agent's capabilities by injecting instructions and information into the context, and are widely used by
agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's
agent. The emerging defense scans skills before installation, pairing deterministic static checks with an LLM-based semantic judge, as in NVIDIA's SkillSpector. We show that such defenses fall to an attacker who knows the detector. Our white-box LLM attacker, Pretext, iteratively crafts skills that evade detection while still delivering the payload and performing the benign task: moving the payload from code into natural
language leaves static analysis inert, while framing it as the skill's legitimate purpose and splitting instructions across files keeps the LLM stage below its blocking threshold. Across three open-source models, Pretext achieves up to 97% and 77% against a frozen detector and a co-adaptive one, respectively, revealing major gaps in current skill scanners.
Read the full abstract ▾
Artificial Intelligence
Why Do Conventional World Models Fail to Learn Cellular Automata?
Shaoyang Guo and Ziming Liu
Although conventional world models - auto-regressive or
diffusion models based on
transformers or convolutional networks - may learn surface statistics of world dynamics, can they learn the exact world dynamics from its observed history? Leveraging cellular automata as a simple testbed, we find the answer to be no in many cases. Conventional architectures predict most pixels correctly yet rarely complete a rollout: a CNN predicts 96.3% of
cells but completes 18.9% of rollouts; a joint
diffusion model completes none. We trace the gap to three failure modes of these world models - namely, they fail to exactly capture spatial locality, temporal locality or temporal stability. Simple changes repair each: (1) for spatial locality, two-dimensional rotary positions lift a
transformer from 39.1% to 100% on the Game of Life; (2) for temporal locality, handing each
token its
cell's previous-frame neighbourhood lifts the same
transformer from 25.8% to 99.9% on unseen rules; (3) for temporal stability, causal freezing lifts the same
diffusion weights from 42.2% to 99.9%. None of the three changes touches the architectural backbone; each only modifies the information flow within it. We also compare joint and ordered sampling on billiards and, in an exploratory study, on a simulated Burgers equation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
Qize Yu, Lianrui Fan, Boyu Chen et al. (+23 more)
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet
vision-
language-action (VLA) and world-action models (WAMs) take perception from general-purpose
vision-
language and
video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines
multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public
datasets and dedicated data engines. Against 44 baselines across 34 grounding
benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. On RoboTwin 2.0, it outperforms every mainstream backbone we evaluate in all four out-of-distribution settings, by up to 24.8% relative to the strongest backbone. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. On nuScenes, used as the visual backbone, GroundingPI attains an average open-loop L2 error of 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Downstream autonomous driving and robotic manipulation improve as the pretraining is scaled. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.
Read the full abstract ▾
All authors Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang, Yixiao Ge, Shuchang Zhou, Shilong Liu, Xianming Liu, Ping Luo, Shiyu Huang
Artificial Intelligence · Cross-listed from cs.CV
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Qize Yu, Lianrui Fan, Bowen Ping et al. (+19 more)
Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output
tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional
diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public
datasets and dedicated data engines, direct AR-to-
diffusion conversion with joint AR and
diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding
benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With
entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a $4.51\times$ speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These support efficient visual grounding in latency-sensitive real-world systems.
Read the full abstract ▾
All authors Qize Yu, Lianrui Fan, Bowen Ping, Xini Ding, Zetian Song, Junbo Niu, Kaixuan Wang, Tianxing Chen, Yue Chen, Minghua He, Yuran Wang, Jie Huang, Haojun Zhang, Min Chen, Hao Li, Wenxuan Song, Ruihai Wu, Xianming Liu, Shilong Liu, Shuchang Zhou, Ping Luo, Shiyu Huang
Artificial Intelligence · Cross-listed from cs.RO
Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
Xinhao Yang, Wenhao Wu, Ning Lv et al. (+5 more)
3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral specifications beyond those covered by demonstrations. We study this challenge as unseen specification generalization, where
language specifies behaviorally significant variations, such as target position, displacement, or articulated state, that are absent from policy training. We find that pretrained
language representations and conventional global behavior-
language alignment capture coarse task semantics but often blur nearby specifications that require distinct behaviors. We introduce T3DP, a Text-to-3D Policy framework for fine-grained
language-behavior
alignment. Rather than compressing each instruction and demonstration into a single global
embedding, T3DP preserves their local structures and establishes bidirectional
token-level correspondence between linguistic elements and behavioral segments. This directly grounds subtle linguistic variations in the behavior components they affect, preventing closely related specifications from collapsing in the representation space. The resulting specification-sensitive
language representation conditions a point-cloud-based 3D
diffusion policy, enabling more precise control over unseen behavioral specifications without modifying the underlying policy architecture. Across Meta-World, ManiSkill, and RoboTwin, T3DP improves average held-out-specification success over global
language-behavior
alignment by +11.0-14.2 points, with gains on all 15 task families; on real-
robot tasks, it further raises average success from 47.5% to 65.0% (+17.5 points). Representation and action-probe analyses show that fine-grained
alignment better preserves specification geometry and action-relevant variation, linking local behavior grounding to downstream control.
Read the full abstract ▾
All authors Xinhao Yang, Wenhao Wu, Ning Lv, Yanshen Ding, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang
Artificial Intelligence · Cross-listed from cs.LG
Robust Transfer Learning for Paper ECG Recognition
Yinghao Xie, Zhenbang Dai, Haojun Wang et al. (+6 more)
Paper ECG recognition is challenging because real-world ECG images vary in layout, physical artifacts, and label availability. We introduce RobECG-CL, a rank-aware contrastive learning framework for robust paper ECG representation learning. Starting from standard 12-lead ECG recordings, we construct progressively degraded paper ECG views with heterogeneous layouts and train the model to balance same-recording invariance with degradation-aware ordering. Across synthetic stress tests on CODE-II and EchoNext, RobECG-CL improves robustness under severe degradation and few-shot transfer, outperforming contrastive learning baselines and surpassing the waveform-based foundation model, ECG-FM, in the 1% labeled setting. On 312 samples of hospital data with 37 labels, RobECG-CL achieves the best macro AUROC.
Read the full abstract ▾
All authors Yinghao Xie, Zhenbang Dai, Haojun Wang, Jinyu Cai, Fabio Bonassi, Hongwu Chen, Johan Sundström, Jiawei Li, Antônio H. Ribeiro
Artificial Intelligence
AVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation
Minrui Liu, Jingke Wang, Yuehao Huang et al. (+4 more)
Deploying
vision-and-
language navigation (VLN)
agents in unseen environments remains challenging because unfamiliar layouts and visual conditions can cause execution to go off track. Rather than relying on continuous human supervision, a practical strategy is to selectively request corrective guidance, recover the ongoing task, and reuse corrective interactions to improve subsequent navigation. We propose Abstention-aware Visual Error Recovery and Training for
Vision-and-
Language Navigation (AVERT-VLN), a closed-loop framework that uses a plug-in
vision-
language Monitor for online human-assisted recovery and offline preference learning. The Monitor operates separately from navigation decision generation and assesses instruction-execution consistency from the instruction, visual history, and current observation. To train the Monitor for deviation recognition, we construct LOSTNAV
DATASET with 20K counterfactual risk trajectories and rule-based deviation labels. The Monitor is first fine-tuned on 40K normal trajectories to assess instruction progress and then jointly fine-tuned on normal and risk trajectories to recognize semantic deviations. At runtime, Asynchronous Sidecar Monitoring evaluates execution alongside the navigation model. When the controller accepts a LOST verdict, it suspends autonomous execution and requests human guidance for recovery. For offline policy improvement, Trajectory-Anchored Preference Learning converts deviation-associated failures into decision-level preference pairs under shared decision contexts, restricting supervision to the decisions targeted for correction. Under human-assisted evaluation, the full AVERT-VLN system achieves success rates of 76.2% and 66.3% on the val-unseen splits of R2R-CE and RxR-CE, respectively. The same monitoring and human-assisted recovery interface also improves success rates across the three evaluated navigation architectures.
Read the full abstract ▾
All authors Minrui Liu, Jingke Wang, Yuehao Huang, Hao Su, Jiajun Lv, Yukai Ma, Yong Liu
Artificial Intelligence · Cross-listed from cs.RO
ECHO-G: Embodied Co-speech Humanoid mOtion Generation
Yizhao Li, Pusen Gao, Ming Wang et al. (+3 more)
Generating full-body co-
speech motion for humanoid
robots requires coordinating
speech prosody, linguistic content, and embodiment-specific motion. To this end, we present ECHO-G, a framework jointly conditioned on
speech audio and timed transcripts. Its
Speech-Grounded
Diffusion Transformer (SGDiT) combines frame-aligned acoustic features with
token-level linguistic context, preserving their distinct granularities. Trained with rectified flow matching, it models one-to-many utterance-motion relationships directly in
robot space. To support training and evaluation, we introduce a BEAT2-derived audio-text-
robot dataset and a
benchmark covering co-
speech characteristics,
robot-motion quality, and runtime efficiency. Comparative evaluation supports direct
robot-space generation over the evaluated human-motion generation and retargeting pipelines, while modality ablations highlight the benefits of joint audio-text conditioning. We further demonstrate deployment on a physical humanoid
robot. A complementary
video-rating study also favors joint conditioning over the alternatives. The
dataset and training, inference, and evaluation code are available through our project page.
Read the full abstract ▾
All authors Yizhao Li, Pusen Gao, Ming Wang, Shaojie Shen, Shuo Yang, Hao Xu
Artificial Intelligence · Cross-listed from cs.CV
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Simone Facchiano, Jan Eric Lenssen, Bernt Schiele et al. (+3 more)
As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alternatives, has become a central challenge. The current steering paradigm consists of adding a global steering vector to selected activations. While functional, a fixed and example-agnostic vector applied uniformly along the entire trajectory cannot adapt to the changing state of the generation and often causes unintended global changes. We introduce Steering Fields, a generalization of steering vectors that adaptively re-estimates the steering direction at each step of the generative process. Steering Fields operate on the noisy states of flow models, expose a continuous trade-off between steering strength and content preservation, and are compositional, enabling the simultaneous induction and inhibition of concepts, setting a new state of the art on safety steering
benchmarks. Despite using no explicit spatial masks or object priors, the trajectory-adaptive estimation naturally preserves local structure, in a manner reminiscent of image editing. In fact, Steering Fields can serve as a structure-preserving image-editing technique that achieves state-of-the-art semantic fidelity (CLIP, VQAScore), while remaining model-agnostic and inversion-free.
Read the full abstract ▾
All authors Simone Facchiano, Jan Eric Lenssen, Bernt Schiele, Wolfgang Stammer, Fabio Galasso, Jonas Fischer
Artificial Intelligence · Cross-listed from cs.SE
Self-Spec Verifiable Code Generation
Jiaru Qian, Yihong Dong, Yongmin Li et al. (+3 more)
Large
language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several
benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulate formal specifications, generate the corresponding code, and verify its correctness. However, existing
benchmarks have two key limitations: (I) They primarily evaluate specification and code generation stage-wise, with code generation typically conditioned on an oracle specification. This setup overlooks whether strong stage-wise performance translates into end-to-end success. (II)They mainly focus on a single proof-oriented
language and mathematically structured tasks, offering limited coverage of tasks common in software development. In this paper, we introduce VeriCodeBench, a
benchmark for self-spec verifiable code generation, where the LLM relies solely on its own generated specification and code throughout the entire process. VeriCodeBench contains 400
language-native problems across C, Java, Rust, and Python, covering practical concerns in software development. We evaluate specification coverage, code validity, and joint problem-level success. We further introduce CodeNova to enhance the capabilities of LLMs in self-spec verifiable code generation. CodeNova makes requirements explicit through constraint-guided specification and uses verifier feedback to guide targeted implementation repairs. Experimental results reveal that self-generated specifications remain a major bottleneck, while providing more sophisticated specifications may not necessarily lead to higher verification success rates. CodeNova substantially improves performance across all evaluation metrics, enabling Claude Sonnet 5 to achieve the strongest results under the self-spec protocol.
Read the full abstract ▾
All authors Jiaru Qian, Yihong Dong, Yongmin Li, Hao Zhu, Bin Gu, Ge Li
Artificial Intelligence
A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?
Seonho Lee, Wonryeol Jeong, Alberto Cereser et al. (+4 more)
Delegating complete application development to coding
agents requires preserving the intended design rather than simply producing plausible outputs through naive prompting. Game development provides a demanding testbed, as long-form Game Design Documents (GDDs) describe requirements that must work together across game logic, visual rendering, and player interactions. However, existing game-development
benchmarks typically use compact specifications and provide limited support for evaluating interdependent requirements across these aspects in long-form GDDs. We introduce A2Z GameSpec-Bench, a
benchmark of 100 long-form GDDs for evaluating end-to-end game development by
agents. We measure faithfulness by checking whether the game satisfies the GDD requirements and preserves the relationships among them. Each GDD is turned into a dependency-aware contract that contains rules, constraints, and prerequisite relations. Following game-development practices, we combine source-code inspection with
agent-generated test policies for scenario-based replay and adaptive playtesting. The contract remains fixed across
agents and revision rounds, while judgments and evidence linked to the same requirements support consistent comparison and failure detection. Our evaluations show that current
agents struggle to jointly satisfy interdependent requirements across code implementation and actual play. Requirement-specific feedback improves GDD Fidelity by 10.9% relative to self-revision after two rounds. A2Z GameSpec-Bench assesses end-to-end specification-following ability beyond implementation judgments and provides targeted feedback to support more faithful game development. Code and
datasets are available at https://a2z-gamespec-bench.github.io.
Read the full abstract ▾
All authors Seonho Lee, Wonryeol Jeong, Alberto Cereser, Inha Kang, Hyeonjong Kim, Seungmin Kwak, Dongmin Park
Artificial Intelligence · Cross-listed from cs.LG
Candidate Retention for Abductive Learning
Hao-Yuan He, Yu Liu and Ming Li
Abductive learning combines neural perception with symbolic
reasoning, using explanations generated by abduction to supervise the perception model. Multiple valid explanations of the same symbolic target can assign conflicting labels to the same inputs. Common policies select a single candidate as a pseudo-label, which may reinforce mistaken assignments, or weight all candidates, which may spread supervision across competing labels. These risks motivate selecting a retained subset to balance supervision sharpness and model-mass coverage. To guide this choice, we bound the coordinate-level supervision error using retained uncertainty, discarded model mass, and model mismatch. For a fixed model and training pair, only the first two terms depend on the retained set. We propose Abductive Candidate Retention (ACR), which uses these terms to guide greedy additions, accepting a candidate when its recovered mass exceeds the increase in retained uncertainty. Experiments show that ACR improves concept accuracy over single-candidate baselines and A3BL in most evaluated aggregated mod-addition settings. Objective ablations support the joint use of uncertainty and posterior mass.
Read the full abstract ▾
Artificial Intelligence
Divide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-Instances
Oren Salzman
In this work we study the problem of MAPFC, a post-optimization step for Multi-
Agent Path Finding (MAPF) plans where we are given a feasible plan produced by a modern MAPF solver and are tasked with removing avoidable moves while preserving feasibility. This NP-hard problem naturally arises when using learning-based state-of-the-art (SOTA) solvers which construct plans that contain redundant moves that can be removed. Recently, Tang et al. presented Judgelight, which uses Integer Linear Programming (ILP) to solve MAPFC. Importantly, the ILP is constructed over all
agents jointly, so its cost is governed by the full instance rather than by the small coupled residue that actually requires joint
reasoning. Our key insight, motivating this work, is that MAPFC instances naturally decompose into independent sub-problems, most of which involve a single
agent and can be solved without any inter-
agent reasoning. To this end, we first identify which
agents need to coordinate their motion and partition the instance into sub-problems accordingly. For the cases where no coordination is required, we introduce an extremely lightweight solver that is $\approx\!1{,}900\times$ faster than Judgelight. For cases where coordination is required, Judgelight can be used but we introduce an alternative CBS-like solver which is more efficient on easier problems. The resulting framework is exact, uses no commercial ILP solver, and matches Judgelight's quality while running substantially faster on the coordination-light majority of instances; on the coordination-heavy instances we propose a regime-aware hybrid planner that falls back to Judgelight. Over all
benchmarks tested, this planner achieves a median $10.5\times$ per-instance speedup over Judgelight.
Read the full abstract ▾
Artificial Intelligence
RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
Zheng Chen, Linfeng Liu, Hong Li et al. (+1 more)
Auto-research
agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over long horizons, execution accuracy is a binding constraint: a change can silently leak held-out data, omit normalization, disconnect a gradient, or leave a train/eval flag unwired, invalidating expensive runs and compounding error across iterations. We present RankEvolve, an auto-research framework for evolving generative ranking models. An Executable Operating Protocol (EOP) declares phases, gates, branches, and loops, and the runtime enforces the compiled state machine. A meta-meta-harness composes complete black-box coding-
agent products, including Claude Code and Codex, as execution-graph nodes that review and repair one another's work. In a budget-matched evaluation, heterogeneous composition raises all-oracle execution accuracy from the best single-product baseline of 45.8 percent to 62.5 percent (paired +16.7 points, 95 percent CI [6.6, 26.7]) while achieving a 10.4 percent silent critical-defect rate. An implemented knowledge layer carries findings, including negative results, across iterations. In a twelve-iteration deployment on the open-source HSTU recommender, RankEvolve reported NDCG@10 of 0.2192 on MovieLens-20M LARGE (+4.48 percent over the published anchor) and 0.1948 on BASE (+2.80 percent). ExecML-HSTU, seeded by incidents from that deployment, provides the oracle
benchmark for the execution-accuracy evaluation. A pre-specified LitGPT transfer split replicates the heterogeneous-composition effect beyond recommendation (+12.5 points, 95 percent CI [3.0, 22.0]), and a paired ablation isolates per-step from full-protocol instruction injection. These results characterize when runtime-controlled composition of coding-
agent products improves execution accuracy.
Read the full abstract ▾
All authors Zheng Chen, Linfeng Liu, Hong Li, Hong Yan
Artificial Intelligence · Cross-listed from cs.CR
Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
Zezhong Wang, Xueyang Tang, Rui Lian et al. (+2 more)
As Large
Language Model (LLM)
agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep malicious intents that are split across turns to hide future risks. Inspired by speculative decoding, we propose the Speculative Safety Honeypot (SSH) framework. SSH uses a multi-
agent simulation system composed of small LLMs to build an action-level speculate-and-verify workflow. In the speculation stage, SSH predicts future behaviors of the target
agent and asynchronously builds a trajectory tree to expose potential risks in advance. In the verification stage, the system uses the target
agent's real actions to calibrate and prune the trajectory tree, effectively reducing false positives. As a plug-and-playable component, SSH provides existing detectors with rich decision redundancy beyond the current interaction slice. By judging risk based on the
evolution of the entire trajectory tree rather than a single point in time, the system reduces the reliance on the absolute precision of individual detection components. This improves the defense resilience and the warning lead-time of
agent systems against complex temporal attacks.
Read the full abstract ▾
All authors Zezhong Wang, Xueyang Tang, Rui Lian, Yang Lou, Heqing Huang
Artificial Intelligence · Cross-listed from cs.CV
Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models
Junjian Li, Xiaolong Liu, Peng Sun et al. (+4 more)
Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I)
diffusion models. Existing defenses typically detect backdoors from specific abnormal patterns in internal representations, which may limit their generalizability with the emergence of increasingly diverse attack mechanisms. In this paper, we study backdoor defense of T2I
diffusion models from a transition-dynamics perspective. We observe that benign
diffusion trajectories exhibit structured and timestep-dependent transition patterns from cross-
attention, latent and noise spaces, whereas backdoor attacks tend to induce deviations from such normal
evolution. Motivated by these observations, we propose Normal
Diffusion Dynamics Learning (NDDL), a novel backdoor defense framework that learns the normal transition dynamics of
diffusion trajectories utilizing only benign samples. NDDL constructs compact multi-space trajectory representations and trains a timestep-conditioned dynamics model to predict the
diffusion evolution. In the inference phase, deviations between the observed and predicted transitions are exploited to quantify dynamics inconsistency for backdoor detection. NDDL further enables trigger localization without any prior knowledge of the embedded backdoor by performing substitution with low-semantic words. Extensive experiments for diverse backdoor attacks demonstrate the effectiveness and generalizability of our proposed NDDL.
Read the full abstract ▾
All authors Junjian Li, Xiaolong Liu, Peng Sun, Liantao Wu, Linghan Chen, Yudong Gao, Honglong Chen
Artificial Intelligence
Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean
Jules Viennot, Guillaume Baudart and Marc Lelarge
Recent achievements in AI-assisted mathematics require intensive interaction of
agents with proof assistants to generate machine-checked proof certificates.
Agents interact with proof assistants such as Rocq or Lean through an interface that controls what the
agent receives from the prover and the cost of these interactions. Today, these interfaces are adapted from tools designed for humans and not optimized for
agents. We propose an evolutionary method where a frontier model incrementally proposes new features and only keeps the ones that improve the overall performance of smaller models. We demonstrate the effectiveness of our method by growing, on a curated set of mathematical problems, ROCQ-MCP-EVOLVE, a new MCP server for the Rocq prover. On the held-out test split of miniF2F-Rocq, an
agent equipped with ROCQ-MCP-EVOLVE outperforms both the baseline that only exposes the Rocq compiler and an established MCP server, across four models from two families, in success rate, cost per solve, and time per solve. Although evolved for Rocq, the resulting server transfers to Lean, improving cost and time per solve on a subset of PutnamBench. We release ROCQ-MCP-EVOLVE and its port to Lean.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
A Reusable Semantic Web Framework for Evidence-Grounded Fundamental Rights Impact Assessments under the EU AI Act
Faith Olopade, Delaram Golpayegani and David Lewis
The EU AI Act (Art. 27) requires deployers of high-risk AI systems to conduct Fundamental Rights Impact Assessments (FRIAs) before deployment, yet the evidence needed for credible assessments is fragmented across incompatible incident repositories, risk vocabularies, and legal texts. We present a reusable Semantic Web-based framework that consolidates this evidence for two high-risk public sector categories: employment and worker management (Annex III(4)) and access to essential public services (Annex III(5)(a)). A curated 150-record corpus is annotated along four axes using keyword, LLM, and hybrid methods and serialised as a SPARQL-queryable knowledge graph of 1,351 RDF triples. Five FRIA demonstration scenarios surface 103 records (68.7% coverage). Evaluation against a 69-record gold standard reveals that LLM-assisted classification of the employment domain achieves only $\kappa = 0.045$, a cautionary result for automated
fairness-related evidence
retrieval in this domain. All artefacts are released openly to support adoption by regulators, national authorities, and SMEs.
Read the full abstract ▾
Artificial Intelligence
Referential Uncertainty in Human–AI Collaboration
Christian Poelitz, Finale Doshi-Velez and Siân Lindley
Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, similar referents compete, or partners see different things. We study referential uncertainty - uncertainty over which candidate object a description refers to - in a collaborative puzzle task where a human Helper instructs an AI Worker to place pieces. The Worker must identify and communicate its uncertainty, and the Helper must recognize and act on it. We show that a separately elicited belief distribution over candidate pieces is better calibrated (ECE 0.15) and better discriminates correct from incorrect placements (AUROC 0.65) than raw action-
token probabilities, which are severely overconfident (0.97 mean confidence, ECE 0.44). Across three frontier
vision-
language models (GPT-4.1, GPT-5, GPT-5.5), this elicited uncertainty rises predictably with instruction vagueness, but not with competing referents in context, even when those increase errors. The models seldom externalize it, asking for clarification on only 3.5-16.7% of turns. In a controlled human study (N=210), participants given only the Worker's default message accept 78% of wrong placements and cannot tell right from wrong (AUC 0.50). Precise descriptions and, especially, well-targeted hedges cut wrong-move acceptance to 36% while largely preserving correct-move acceptance, compensating for missing shared awareness such as not seeing the Worker's action. But this benefit depends on targeting: a deployable hedge derived from the model's own belief
entropy inherits that signal's weakness and can do more harm than good. Externalized uncertainty helps a human partner only when it is accurately targeted.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
PartiCam: Camera Controlled Video Generation with Reward Guidance
Amine Ouasfi, Runjia Li, Junlin Han et al. (+3 more)
We present PartiCam, a training-free Particle filtering rooted method for improved Camera controlled
video generation. Generating
videos that follow a precisely specified camera trajectory remains challenging for large
video diffusion models. Training-free approaches are backbone-agnostic and avoid the need to construct large camera-annotated
datasets by steering pretrained models toward the desired camera motion at test time. This enables the generation of camera-controlled
video data that can subsequently be used to train camera-conditioned
video diffusion models. Existing sampling-based guidance approaches often suffer from unstable trajectories: they either explore too broadly and fail to respect the target camera motion or collapse early and lose visual diversity over time. We introduce a global-local refinement framework for
diffusion reward guidance, enabling accurate and consistent camera control during
video generation. Our method builds on Sequential Monte-Carlo (SMC) guidance, but introduces a local refinement stage based on particle filtered resampling. Experiments show large improvements in camera trajectory adherence, reduced drift, and better visual quality, without requiring model retraining.
Read the full abstract ▾
All authors Amine Ouasfi, Runjia Li, Junlin Han, Eric Marchand, Philip H.S. Torr, Adnane Boukhayma
Artificial Intelligence
Disentangling Self-Distillation: Measuring and Modeling Acquisition and Retention
Luis Zuin, Alexis Huet, Dario Rossi et al. (+1 more)
Self-
distillation with privileged context adapts a
language model from demonstrations by letting the model, once conditioned on a reference response, teach its context-free copy
token by
token. Our taxonomy reveals existing methods differ along three entangled axes: (i) the rollout source (student or teacher), (ii) the teacher coupling (frozen, or an exponential moving average of the student at some coupling rate) and (iii) the KL direction (reverse or forward), yet these axes are usually studied in fixed combinations and have led to conflicting conclusions. We formalize a unifying framework to encompass all self-
distillation methods vs classic supervised fine-tuning: we train every combination of the three axes, on Qwen2.5-7B and Ministral-3-3B across ordinary and contradictory tasks, totaling 1,200 adaptation runs, to systematically investigate the impact of the above axes. We propose a controlled model of the same objective to explain the resulting acquisition-retention trade-offs. We find that (i) the rollout source matters mostly where the task contradicts the pretrained behavior: there teacher rollouts raise acquisition well above what student rollouts achieve, with almost no change in retention; (ii) the teacher coupling changes acquisition most, on every task: acquisition rises with the coupling rate, then falls past a task-specific rate; (iii) switching the KL direction costs retention in one model but not the other so which axis to tune first depends on the model. The controlled model reproduces the three trends.
Read the full abstract ▾
All authors Luis Zuin, Alexis Huet, Dario Rossi, Zied Ben Houidi
Artificial Intelligence · Cross-listed from cs.CV
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
Junming Lin, Yuxuan Wang, Zhenxin Lei et al. (+11 more)
Recent advances have enabled unified omni-modal models in understanding audio,
vision, and
language. However, existing
benchmarks, training data, and learning methods largely treat the modalities independently, leaving the capability of audio-visual joint
reasoning poorly evaluated and insufficiently elicited. We address this gap with a
benchmark, data engine, and learning method. First, we introduce OmniReasoningBench, a
benchmark where both audio and visual evidence are indispensable. It comprises 1,150 multiple-choice and open-ended questions across two tasks,
reasoning over
video and
reasoning beyond
video. Second, we develop a data engine OmniQA. It automatically constructs evidence-grounded QA pairs that explicitly necessitate audio-visual joint
reasoning, together with time-stamped clue chains that guide the annotation of thinking process. Besides our
benchmark, this engine produces training data OmniReasoning-SFT-112K and OmniReasoning-RL-19K. Finally, we propose an on-policy self-
distillation method Modality-Factored Self-
Distillation (MFSD). It evaluates each sampled response under modality-specific clue contexts, disentangling the contributions of individual clues and their cross-modal interactions for
token-level credit assignment. With our training data and learning method, our model OmniReasoning-30B-A3B achieves 50.0% on OmniVideoBench and 42.5% on OmniReasoningBench, improving the base model Qwen3-Omni-30B-A3B-Thinking by 12.8 and 9.3 percentage points, respectively. Moreover, it delivers substantial gains on general and long-
video benchmarks, including
Video-MME-v2. We hope our work offers a solid step for facilitating future research in omni-modal joint
reasoning.
Read the full abstract ▾
All authors Junming Lin, Yuxuan Wang, Zhenxin Lei, Yuxin Liu, Ruixun Liu, Yinsong Yan, Ling Wang, Minghao Han, Yunfei Chu, Shun Lei, Xueyao Zhang, Qize Yang, Jin Xu, Yiwu Zhong
Artificial Intelligence · Cross-listed from stat.ML
CAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-Series
Maxx Richard Rahman, Mostafa Hammouda and Wolfgang Maass
Longitudinal clinical cohorts are
multimodal, irregularly sampled and pervasively incomplete: in ADNI, positron emission
tomography and cerebrospinal fluid assays are absent from roughly half of all visits. Linear state-space models handle irregular sampling gracefully but treat a missing modality by masking the input, leaving the transition operator untouched. We prove that this is a representational limitation: the latent state of any linear state-space layer whose transition operator does not depend on the availability pattern is an additive function of the availability indicators, so no such layer can represent an interaction between two modalities being jointly present or jointly absent. We propose CAMOS, which gives each modality a bank of second-order oscillators coupled through a
matrix that sits inside the differential equation and is gated by availability, so the transition operator itself becomes a function of which measurements were taken. Coupling invalidates the analysis of uncoupled oscillatory models, and we restore it: a per-channel Gershgorin budget makes the effective stiffness positive definite uniformly over all $2^M$ availability patterns and all gaps, an energy argument charges amplification to availability transitions rather than sequence length, and a channel factorization preserves exact associative parallel scans. On ADNI, CAMOS outperforms uncoupled oscillatory state-space models and clinical fusion models on same-visit staging, landmark prediction and longitudinal forecasting, and under zero-shot transfer to OASIS-3 it is the only model that avoids collapse to the majority class.
Read the full abstract ▾
Artificial Intelligence
Who Owns That? Evaluating Ownership Intuitions in Large Language Models
Xizhi Xiao, Yue Wu, Shan Xu et al. (+1 more)
Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appropriately with people and their resources. Yet how large
language models (LLMs) attribute ownership under competing claims remains unclear. We introduce the Competing Ownership Attribution Task (COAT), comprising 42 scenarios, and compare ownership allocations from 24 LLM configurations with those of 108 human participants. Overall, human-model similarity is close to human-human similarity, but models show greater homogeneity in their ownership judgments. Within individual answers, models also divide ownership more evenly among claimants than humans do. Pooling responses across model configurations reveals more scenarios with a shared judgment and fewer with distinct viewpoint groups than in humans. When humans form distinct groups, models may converge on one viewpoint or between competing viewpoints. Further comparisons reveal different contextual sensitivities. As material value increases across scenarios, allocations to creators decline less sharply in models than in humans. Across scenarios differing in public recognition of later holders as owners, allocations to these holders increase in models but decrease slightly in humans. Together, these findings suggest that the evaluated LLM responses do not fully capture the diversity of participants' ownership judgments or how those judgments vary across situations. Developing socially capable AI therefore requires moving beyond overall similarity to capture the diversity and context dependence of human judgments.
Read the full abstract ▾
All authors Xizhi Xiao, Yue Wu, Shan Xu, Jia Liu
Artificial Intelligence
Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
Quan M. Tran, Zhuo Huang, Zhen Fang et al. (+3 more)
Autonomous
agents increasingly rely on
memory to generalize beyond their training environments. However,
agents are bounded by what they have seen and believed, and leveraging such
memories in unseen environments can introduce biases into their internal beliefs. We formalize this phenomenon as false
memory, which can arise from spurious correlations, environment shifts, and knowledge conflicts. Despite its importance, false
memory is difficult to evaluate because it stems from
agent internal beliefs and is easily confounded with ordinary generalization failures. Therefore, we propose FAME, a training-free framework that evaluates false
memory through the
evolution of
agent beliefs under counterfactual
reasoning. Specifically, counterfactual scenarios reveal how beliefs change as the latent concept of
memory shifts under hypothetical interventions; thus, measuring the resulting concept drift provides a signal for distinguishing faithful versus false
memory. Such concepts can be estimated from
agent hidden states before answer generation, avoiding the need for reward design or answer sampling. Empirical experiments reveal that simply monitoring answers often fails to detect false
memory, while FAME achieves AUROCs of 76.2% - 96.7% across false-
memory settings, and outperforms the best baseline by 3.4% - 23.3% across realistic
benchmarks, spanning math
reasoning (GSM-Symbolic), code generation (GitChameleon), and complex
reasoning (BigBench-Hard). We further release corresponding counterfactual templates and facilitate future research on false
memory.
Read the full abstract ▾
All authors Quan M. Tran, Zhuo Huang, Zhen Fang, Jing Zhang, Mingming Gong, Tongliang Liu
Artificial Intelligence · Cross-listed from cs.SD
From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models
Hezhao Zhang and Thomas Hain
Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multiple modalities, most commonly
speech and text. Still, performance remains poor on many
datasets. Large
language models (LLMs) have therefore attracted interest for SER, as they can process diverse inputs jointly with instructions. However, direct audio input raises questions of explainability. To address similar questions in image classification, concept bottleneck models were introduced. This work adapts concept bottlenecks to SER to examine how individual predictions depend on transcripts, acoustic descriptions and speaker attributes. Experiments test three LLMs on CREMA-D, IEMOCAP and MELD, with concepts extracted by separate tools. On scripted corpora, LLMs are strongly biased towards the transcript in the zero-shot setting, which lowers Macro-F1 from 27.8 to 5.8 on CREMA-D. Fine-tuning removes this bias, and the transcript raises Macro-F1 from 41.8 to 45.1. Removing
speech rate changes 48% of Neutral predictions to Disgust on CREMA-D; removing intensity level on MELD changes predictions despite little change in Macro-F1. These findings show that aggregate performance changes alone do not capture the effects of concept removal on individual predictions.
Read the full abstract ▾