Artificial Intelligence · Cross-listed from cs.LG
Multi-Label Node Classification with Label Influence Propagation
Yifei Sun, Zemin Liu, Bryan Hooi et al. (+4 more)
Graphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include
proteins in PPI networks with multiple functions and users in social or e-commerce networks exhibiting diverse interests. Tackling multi-label node classification (MLNC) on graphs has led to the development of various approaches. Some methods leverage graph neural networks (GNNs) to exploit label co-occurrence correlations, while others incorporate label
embeddings to capture label proximity. However, these approaches fail to account for the intricate influences between labels in non-Euclidean graph data. To address this issue, we decompose the message passing process in GNNs into two operations: propagation and transformation. We then conduct a comprehensive analysis and quantification of the influence correlations between labels in each operation. Building on these insights, we propose a novel model, Label Influence Propagation (LIP). Specifically, we construct a label influence graph based on the integrated label correlations. Then, we propagate high-order influences through this graph, dynamically adjusting the learning process by amplifying labels with positive contributions and mitigating those with negative influence. Finally, our framework is evaluated on comprehensive
benchmark datasets, consistently outperforming SOTA methods across various settings, demonstrating its effectiveness on MLNC tasks.
Read the full abstract ▾
All authors Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony, Jia Chen, Bingsheng He
Artificial Intelligence · Cross-listed from cs.CL
Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications
Frank Xing and Erik Cambria
Explanations for
emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label. We present an explication interface for event-based
emotion analysis. A parser maps the input text to an explication, a short script in the closed vocabulary of Natural Semantic Metalanguage organized into twelve typed slots, and a fixed decision list of rules transcribed from published semantic definitions computes the label from the explication alone. The faithfulness guarantee is therefore causal and definitional, while all empirical risk lives in the learned parser, which the per-line entailment interface makes auditable against the input. On crowd-sourced event descriptions, our fine-tuned parser reaches 0.33 accuracy and 0.48 selective accuracy on a small held-out set, suggesting that the interface trades insignificant accuracy difference to a black-box model for a verifiable, inspectable decision basis for first-person event-based
emotion analysis. We also release EmoExpl-1200 with per-line verification metadata and the full rule set.
Read the full abstract ▾
Artificial Intelligence
Coachable Agents for Interactive Gameplay
Roberto Capobianco, Harm van Seijen, Nolan D. Bard et al. (+38 more)
Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing (Silver et al., 2016; 2017; Wurman et al., 2022) to robotics (Levine et al., 2016; Andrychowicz et al., 2020; Luo et al., 2025; Dürr et al., 2026) to foundation models (Ouyang et al., 2022; Noukhovitch et al., 2024; Sun et al., 2024; Guo et al., 2025). Through trial and error, these AI systems typically learn a single, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, after training is completed, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning
algorithms, and data augmentation to create a framework for coaching
agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA
video games Horizon Forbidden West and Gran Turismo, and in an open-source
humanoid test domain. Despite the different nature of the domains–car racing, stylized game combat, and
humanoid walking–each
agent shows strong coherence to the style requests while still satisfying the main task in its domain. Importantly, the techniques outlined in this paper allow an end user to choose the final behavior at run time, giving them flexible control over the final executed performance.
Read the full abstract ▾
All authors Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du, Ishan Durugkar, Siddhant Gangapurwala, Daniel Hernandez, G. Zacharias Holland, Sahil Jain, Kenta Kawamoto, Raksha Kumaraswamy, Patrick MacAlpine, Dustin R. Morrill, Declan Oller, Francesco Riccio, Akanksha Saran, Craig Sherstan, Kaushik Subramanian, Thomas J. Walsh, Samuel Barrett, Kizza N. Frisbee, Mady Govil, Johannes Günther, Varun R. Kompella, James A. MacGlashan, Maxwell Svetlik, Michael D. Thomure, Jaden B. Travnik, Kevin Waugh, Elahe Aghapour, Florian Fuchs, Andreanne Lemay, Shruti Mishra, Takuma Seno, Peter Stone, Michael Spranger, Peter R. Wurman
Artificial Intelligence · Cross-listed from cs.LG
Loss Smoothing for Stable Adaptation Under Distribution Shift
Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu et al. (+1 more)
In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift. Standard adaptation methods typically optimize the target objective directly, inducing an abrupt change from the source training objective. This abrupt transition can distort learned representations, including features that may still be useful for the new task. We investigate whether a more gradual transition can improve adaptation. We propose loss smoothing, a simple approach that interpolates between the source and target training objectives at the start of adaptation. This smooth transition helps to preserve useful features from the source distribution while still enabling the model to specialize to the target distribution. Across controlled supervised shifts, pretrained
vision adaptation, offline-to-online and online reinforcement learning, and
language model fine-tuning, we find that loss smoothing consistently improves performance, suggesting that smoother objective transitions are a broadly useful tool for model adaptation.
Read the full abstract ▾
All authors Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu, Sarath Chandar
Artificial Intelligence
AGI Maze as a Benchmark Framework for World-Modeling Agents
Alexey Potapov
Large
language models (LLMs) are powerful pattern-completion systems, but their default operating mode - predicting the next
token from a static context - does not reliably produce persistent, manipulable representations of an external world. Many tasks that look like "
reasoning" in text become substantially harder once the environment is partially observable, stateful, and requires
memory and structured hypotheses about hidden state. AGI Maze is a lightweight framework for building such environments without requiring high-dimensional sensory inputs. It provides a family of grid-based maze tasks with a clean API and multiple difficulty regimes. The goal is to create
benchmarks where
agents must learn and use world state representations, not just infer a local rule over readily provided observations. We provide an initial evaluation of several vanilla LLMs on simple mazes showing that they fail to represent mazes internally at LLM inference time. We also introduce a baseline
agent, which is allowed to use its message history as a working
memory to construct descriptions of observations at agentic runtime. Although this can improve performance, it is still insufficient for an LLM
agent to reliably solve even small mazes within a step budget that is more than enough for humans.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Identifying Latent Concepts and Structures for Generalized Category Discovery
Boyang Dai, Chaoqi Chen and Yizhou Yu
Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, current approaches primarily focus on designing clustering objectives, often overlooking a critical bottleneck: standard
vision backbones yield high-rank, entangled
token representations that are ill-suited for unsupervised discovery of latent concepts and structures. In this paper, we propose Compositional Primitive Fields (CPF-GCD), a novel representation learning framework that reshapes the feature space to make such latent structure identifiable by enforcing a low-rank compositional organization. Our core hypothesis is that all categories, whether known or novel, can be expressed as compositions and spatial arrangements of a finite set of learnable visual primitives that capture reusable concepts. CPF instantiates this
geometric constraint via a spatial field mechanism. Inserted between the backbone and the head, it rewrites noisy patch
tokens through low-rank primitive mixtures, effectively decomposing images into reusable atomic parts and their spatial layouts. By explicitly modeling the spatial distribution of primitives, CPF enables novel categories to emerge naturally as new activation patterns over a shared vocabulary. This shifts the focus of representation from merely partitioning global
embeddings to constructing a structured and separable primitive field. Extensive experiments demonstrate that CPF serves as a generic, plug-and-play module that consistently boosts performance across diverse GCD baselines, validating that identifying and leveraging low-rank compositional structure is a crucial inductive bias for open-world recognition.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Arya Raeesi and Hanna Roed
Limited
Memory Language Models (LMLMs) externalize factual knowledge to a database to enable deletion-based unlearning without retraining. Existing evaluations measure post-deletion correctness in aggregate and cannot tell whether a deleted fact persists through residual parametric
memory, alternative
retrieval paths, or near-neighbor
retrieval artifacts. We propose a causal
auditing framework that holds the model fixed and varies the database state at inference time across three interventions: FULL, DEL-ON, and DEL-OFF. The framework decomposes post-deletion behavior into parametric leakage L(f),
retrieval-mediated correctness R(f), and a
retrieval artifact rate grounded in the inference-time
retrieval trace. We apply it to 12,228 alias-closure deletions across thirteen databases, including four
adversarial topologies (Base, Alias, Noise, Collision) we construct in three domains, and six
prompt formulations. Parametric leakage is near zero in every variant and every
prompt style: the model rarely returns the deleted answer in the absence of
retrieval. The residual that does survive lives in the
retrieval graph:
retrieval-mediated correctness and the
retrieval artifact rate match within rounding everywhere, so post-deletion correctness is, in our audit, predominantly reconstituted from near-neighbor
retrieval. This residual ranges from 0.7% on the released LMLM database to 13.6% on the most
adversarial variant, and
prompt formulation does not independently control how much of a deleted fact survives. These results suggest that, for this class of LMLM and deletion procedure, the unlearning boundary is drawn primarily by the database administrator rather than by the model.
Read the full abstract ▾
Artificial Intelligence
HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
Shei Pern Chua, Hao Wu, Qianli Ma et al. (+1 more)
Understanding how aligned LLMs internally represent safety is critical for diagnosing
alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust
alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separable directions in the residual stream at
prompt-side
token positions. We show that jailbreaks succeed at
prompt encoding by suppressing either the refusal or harmfulness direction before any
token is generated, with distinct attack classes occupying separable regions of the harmfulness-refusal plane. Extending the analysis to response-
token positions, we find that the model recognizes harmful content while it is generating that content, even when it failed to recognize the input as harmful at the
prompt side. Motivated by our findings, we introduce HARC (Harmfulness-And-Refusal Coupling), a fine-tuning method that pairs the two directions across both
prompt and response positions. Since the intervention is confined to the harmfulness-refusal subspace, it leaves the rest of the residual stream intact and does not degrade general capability or inflate over-refusal. Across extensive experiments, HARC achieves the strongest robustness-capability-usability trade-off among six baselines spanning the major training-time and inference-time safety methods. The harmfulness and refusal directions at
prompt and response positions transfer across the five model families and two scales we tested without architecture-specific tuning.
Read the full abstract ▾
All authors Shei Pern Chua, Hao Wu, Qianli Ma, Fangzhao Wu
Artificial Intelligence · Cross-listed from cs.SE
A Methodology for Investigating AI Patterns Prevalence in Software Repositories
Srinath Perera, Hasinthaka Piyumal, Frank Leymann et al. (+1 more)
As Artificial Intelligence(AI)-based applications take off, a clear understanding of AI patterns can uplift the quality of AI applications. Many AI patterns have been proposed in the literature; however, their prevalence in real-life code has not yet been validated. Understanding the actual use of those patterns in practice can clarify our understanding both of the significance of these patterns and their utility. In this paper, we present a methodology to a) identify relevant patterns by mining the literature and then to b) validate their presence and prevalence in actual code repositories using active learning. To that end, we identify 14 AI pattern classes by mining 44 published AI pattern-related sources. Then we use an active learning approach to determine the prevalence of the most common pattern class across 100 GitHub open AI repositories. Using prevalence estimation, we propose bounds on the accuracy of the occurrences. The model achieves 56% accuracy and 55% recall in an 8-way classification task, significantly outperforming the 11% random-chance baseline. Furthermore, the prevalence estimation offers usable bounds for analyzing pattern applications. This methodology provides a robust foundation to start understanding how AI patterns are used in practice, a field that currently lacks empirical data.
Read the full abstract ▾
All authors Srinath Perera, Hasinthaka Piyumal, Frank Leymann, Rania Khalaf
Artificial Intelligence · Cross-listed from cs.LG
Group-Equivariant Poincaré Convolutional Networks
Aiden Durrant, Rahul Baburajan and Georgios Leontidis
While recent methods like that of the Poincaré ResNet have demonstrated the ability to learning visual representations directly in
hyperbolic space, their optimisation remains a challenge, primarily due to the parameter redundancy of learning distinct orientation filters. In addition,
hyperbolic learning exhibits distinct computational overheads that limit their wide use, where efforts to improve their efficiency via optimisation have seen good success, there has been limited exploration into structural priors that enable stronger sample efficiency at training. To address this, we propose Equivariant Poincaré ResNets, combining
hyperbolic geometry with discrete
symmetry groups ($C_4$ and $D_4$). We identify critical roadblocks in applying Euclidean equivariance to
hyperbolic space and propose geometrically safe tensor reshaping, left-regular permutations for
hyperbolic group convolutions, and joint-orientation Poincaré Midpoint Batch normalisation. Empirical evaluations show that
embedding equivariance significantly improves the sample efficiency during training which in-turn accelerates convergence while respecting the boundary constraints of the Poincaré ball and retaining spatial group equivariance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
MD Azizul Hakim, Md Shihab Uddin and Talha Ibne Anis
Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their suitability for resource-constrained edge deployment. Most reported results evaluate these models only within their training network, leaving behavior on unseen networks unverified. This study trains four lightweight architectures on one IIoT
dataset and evaluates them, without retraining, on two structurally distinct IIoT
datasets using a feature representation restricted to attributes available across all three sources. Explainability analysis across two top-performing models shows both rely overwhelmingly on coarse port-category features; the most influential category occurs in source-domain attack traffic at 96 to 435 times the rate in the two target domains, indicating that coarsening port resolution relocates rather than removes a documented shortcut. Evaluation under naturally imbalanced class distributions reveals a further effect: the evaluation protocol used can reverse which target network appears to pose the greater generalization challenge.
Adversarial robustness and recovery through limited target-domain exposure are also assessed; robustness to
adversarial perturbation is unrelated to cross-network generalization, and recovery through adaptation varies considerably by architecture. These findings suggest deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes
Jihyeok Jung, Jeewu Lee, Sanghyeop Kim et al. (+2 more)
Existing
egocentric benchmarks have primarily constructed the
egocentric setting from first-person-view data, which makes it difficult to evaluate
egocentric perspective itself in isolation. However, understanding first-person-view input and taking an
egocentric perspective are separable abilities, especially when first-person body cues are absent or when other
agents are present. To isolate
egocentric perspective understanding, we introduce EgoGapBench, a diagnostic
benchmark for measuring action selection in multi-
agent egocentric scenes. We define the ability measured by this
benchmark as
Egocentric Action Selection (EAS): selecting an appropriate action from the
agent's perspective in the presence of other
agents. On EgoGapBench, humans answer reliably, whereas both open-source and proprietary MLLMs perform substantially worse and systematically select actions performed by other visible
agents. Fine-tuning on existing
egocentric data fails to close this gap and can even be detrimental. In contrast, fine-tuning on EgoGapBench training data improves accuracy but does not reach human performance. These results show that EAS is difficult to acquire from first-person-view data alone, and that MLLMs should be evaluated and trained not only for scene understanding but also for
egocentric action selection.
Read the full abstract ▾
All authors Jihyeok Jung, Jeewu Lee, Sanghyeop Kim, Chanhee Han, Seong Joon Oh
Artificial Intelligence · Cross-listed from cs.LG
Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
Zhiqi Li, Wen Zhang and Bo Zhu
Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by learning long-range transport maps between noise and data. However, their deterministic transitions do not directly provide the
stochastic trajectories and tractable likelihood ratios required by reinforcement learning (RL) post-training. Existing SDE-based stochasticization techniques target velocity-based samplers and do not directly extend to long-range flow-map transitions. We propose Flow-Map GRPO, an online RL post-training framework for deterministic few-step flow-map generators. Its key component, Anchored
Stochastic Flow Map Composition (ASFMC), combines deterministic transport with anchor-based conditional resampling. We establish the conditions under which this construction preserves the marginal probability path and develop tractable local- and endpoint-anchor policies for two-time and single-time flow maps. These policies enable a unified GRPO training procedure. Experiments on FLUX-based MeanFlow and sCM generators demonstrate substantial improvements in OCR, PickScore, and GenEval at different numbers of inference steps, including joint OCR–PickScore gains with mixed rewards. Controlled ablations show that the
stochastic transition design is essential for translating training rewards into generation quality. Flow-Map GRPO enables effective RL
alignment of pretrained deterministic flow-map generators while retaining their original parameterization, without retraining them as native
stochastic models.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Xuefeng Liu, Mingxuan Cao, Qinan Huang et al. (+3 more)
Scientific
reasoning is an increasingly important capability of large
language models, yet improving the robustness and efficiency of training such
reasoning remains a key open challenge. We study this problem in instruction-based molecular optimization, where answer-only supervised fine-tuning (SFT) collapses multi-step
reasoning and reinforcement learning with verifiable rewards (RLVR) suffers from sparse feedback. Reference-guided Policy Optimization mitigates both by anchoring policy updates to
dataset-provided references, but its effectiveness is tightly coupled to reference quality: weak or misaligned references impose a performance ceiling. To overcome this ceiling, we propose active
reasoning, a paradigm in which the policy actively decides, on a per-instance basis, when to imitate a reference and when to reinforce its own discoveries, while continuously upgrading what it imitates. We instantiate this paradigm as Active Group Relative Policy Optimization (Active-GRPO), realized through two coupled mechanisms: active imitate-reinforce and active referencing. The former performs imitation learning when the reference still outperforms the policy's own candidates, and shifts to self-improvement via reinforcement learning once the policy has generated molecules that surpass the reference. The latter continuously upgrades the reference itself by replacing it with the best policy-generated candidate discovered so far, progressively raising the imitation target and ensuring that reference guidance remains informative-rather than restrictive-throughout training. Across TOMG-Bench MOLOPT, Active-GRPO improves average SRxSim from 0.0959 for GRPO and 0.1665 for RePO to 0.1773 under matched three-seed evaluation, with statistically significant gains on LogP, MR, and QED.
Read the full abstract ▾
All authors Xuefeng Liu, Mingxuan Cao, Qinan Huang, Thomas Brettin, Rick Stevens, Le Cong
Artificial Intelligence · Cross-listed from cs.RO
From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping
Jian Song, Tian Zi and Shen Guanting
Improvements in the technical performance of human–
robot interaction (HRI) systems do not automatically translate into differences that human users can detect during live interaction. This paper investigates whether a 15 percentage point gain in end-to-end task success (from 75% in a
multimodal baseline system to 90% in an improved configuration identified through a prior ablation study) is sufficient to produce consistent and measurable differences in user perception. The baseline system combines Whisper for
speech recognition, Florence-2 for open-vocabulary object detection, LLaMA 3.1 for action extraction, and an interval Type-2 fuzzy logic controller for motion execution. The improved configuration replaces the perception and
language modules with Grounding DINO + SAM and Qwen 3.5 9B, respectively, while retaining the same controller. A within-subject user study with 24 participants compared both systems on the same tabletop object-grasping task. After interacting with each configuration, participants rated perceived speed, reliability, and overall competence and fluency on a 7-point Likert scale. Results show that 17 out of 24 participants (70.83%) preferred the improved system (exact binomial test, p = 0.043, h = 0.43), and all three perceptual constructs were rated significantly higher for the improved configuration after Holm correction, with large to very large effect sizes (p < 0.001). These findings confirm that the identified technical improvements are perceptible to users in direct interaction and underscore the importance of complementing
benchmark evaluation with user-centred evidence when assessing robotic manipulation pipelines.
Read the full abstract ▾
Artificial Intelligence
AI Native Games: A Survey and Roadmap
Zhiyue Xu, Fandi Meng, Kaijie Xu et al. (+3 more)
Generative AI now enables games to produce dialogue, quests, characters, images, and worlds at runtime. Yet generation alone does not make a game AI-native, nor does it guarantee playability. This paper defines AI-native games by whether runtime generative AI is constitutive of the core loop: if the AI component were removed or trivially replaced, the central form of play would collapse or become fundamentally different. This counterfactual criterion separates AI-native games from AI-augmented games and adjacent boundary artifacts. Using this definition, we screen candidate artifacts and analyze 53 publicly available AI-native games and prototypes. We introduce a dual-axis G/N taxonomy: the G-axis captures player-facing game type, while the N-axis captures the dominant AI mechanic that makes generative AI indispensable to play. The corpus is concentrated around
language-forward designs, especially narrative adventure, epistemic interaction, and generative narrative, while categories such as semantic adjudication, multi-
agent simulation, generative construction, and relationship/companion play remain less represented. We argue that the central design problem is organizing semantic openness into stable gameplay. AI-native design depends on mechanical invariants: goals, rules, state, feedback, pacing, and player agency that make open-ended AI outputs interpretable and consequential. We conclude with a roadmap for controllable generation, AI-as-mechanic design,
multimodal and multi-
agent systems, inference economics, evaluation, safety, and regulation.
Read the full abstract ▾
All authors Zhiyue Xu, Fandi Meng, Kaijie Xu, Clark Verbrugge, Simon Lucas, Jian Zhao
Artificial Intelligence · Cross-listed from cs.HC
AI, Trust, and Teaming: The Humans-as-Handlers Approach for Autonomous and Opaque AI Systems
Nathan G. Wood
Artificial intelligence (AI) is becoming ubiquitous, and across domains, increasingly autonomous systems are carrying out tasks which raise significant ethical and legal challenges which demonstrate a need for strong human-machine teams rooted in trust. In this article, I argue that within highly impactful areas (such as medicine or warfighting) there are grounds for us initially treating autonomous and opaque systems as relevantly analogous to dogs (or other animals with which we have close relationships). Under this analogy, humans making use of these systems are not to be viewed as "users" or "deployers" of these systems, but instead take the role of "handlers". This recasting of roles shifts the way we view humans, AI-enabled and autonomous systems, and the relations between them, and moreover clarifies the clear and traceable lines of responsibility humans have for the outcomes brought about when using these systems. In developing this point, I clarify that the machine-animal analogy does admit disanalogous elements, but that its touch-points ground it as a starting point. I then explore how we can divest the humans-as-handlers approach of those aspects of our relationships with animals which are unfitting for how we engage with and make use of autonomous and AI-enabled systems. I conclude by arguing that the trajectory of human-machine teamings for autonomous and AI-enabled systems should be a state where we authentically view these not as artifacts which we simply make use of, but as collaborators with which we pursue complex goals and carry out complex tasks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning
Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo et al. (+2 more)
Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and
LiDAR, is central to robotics and
embodied perception. Yet annotating them densely is expensive, making self-supervised pretraining the natural route to transferable representations. Existing pretext tasks, however, are almost entirely intra-modal, and the few methods that transfer knowledge from 2D foundation models rely on a single global
embedding per clip, discarding the rich per-patch semantics that these models compute. To address this gap, we propose Cross4D-JEPA, a teacher-student method that distills a frozen 2D foundation model, an image model DINOv2, or a
video model V-JEPA 2, into a 4D point encoder. The proposed method combines (1) a dense cross-modal correspondence that maps every 3D point to the teacher patch feature it projects to, and (2) a per-point objective that trains the student to match these features in latent space with no masking, negatives, or decoder. We evaluate Cross4D-JEPA on four
benchmarks, MSR-Action3D, DeformingThings4D, NTU-RGB+D 60, and HOI4D, against intra-modal and global cross-modal baselines. Experimental results show that, under a matched protocol, the proposed method consistently outperforms intra-modal and global cross-modal baselines across the four
benchmarks and is competitive with heavier published 4D methods; further analysis attributes this gain primarily to the granularity of the correspondence rather than the teacher modality. Beyond recognition accuracy, the dense representation learned by Cross4D-JEPA transfers across domains, improves label efficiency, and improves full-label fine-tuning under the same training budget, while a 13x smaller encoder matches a heavyweight pooling backbone.
Read the full abstract ▾
All authors Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo, Hoang M. Truong, Tuan-Anh Vu
Artificial Intelligence · Cross-listed from cs.CL
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
Prabod Rathnayaka, Fabian Waschkowski and Lukas Wesemann
We present BaseRT, a native Metal inference runtime for large
language models (LLMs) on Apple Silicon, and report the highest inference throughput on this hardware to date. Existing runtimes, including llama.cpp and MLX-based frameworks, incur overhead from abstractions not designed for Metal's execution model or Apple Silicon's unified
memory topology. By building natively on Metal with chip-specific kernel fusion, unified
memory-aware optimisation, and custom dispatch logic, BaseRT recovers performance that framework-based approaches leave on the table. BaseRT supports a wide range of model families across eight quantisation formats (Q2 to FP16) on all Apple M-series devices. In this paper, we evaluate the Qwen3, Llama 3.2, and Gemma 4 families at Q4 and Q8 quantisation on M3 and M4 Pro devices. BaseRT achieves up to 1.56x higher decode throughput than llama.cpp and up to 1.35x higher than MLX, with substantially larger margins on prefill for mixture-of-experts models, delivering consistent best-in-class throughput from sub-1B to 30B parameter models. These results establish Apple Silicon as a more capable inference platform than previously reported, with direct implications for the emerging edge inference paradigm: as
privacy requirements, latency constraints, and cloud cost pressures drive inference toward on-device deployment, performance-optimised local runtimes are a critical enabling layer for this transition. BaseRT is publicly available at https://github.com/basecompute/baseRT
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
Leyuan Yu, Xiao Tang, Minghao Liu et al. (+6 more)
Benchmarks for
vision-
language models (VLMs) mostly test observational spatial
reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene fixed. Can VLMs instead predict the consequences of hypothetically moving or rotating an object? We introduce MindEdit-Bench, a
benchmark of six spatial
reasoning tasks built from three-photo smartphone triplets of newly captured indoor scenes via an automatic in-the-wild 3D scene-graph extraction pipeline. Four tasks probe perception and perspective transformation over observed structure; two new tasks, L4 (spatial editing) and L5 (cross-view visibility editing), probe object-level counterfactual
reasoning, where correct answers are absent from all input images. Each question provides 8-24 structured answer choices, enabling answer-letter-level diagnosis of spatial and fallback errors. The
benchmark covers 120 private indoor scenes not drawn from public
datasets, reducing public-data pretraining-overlap risk. Across 15 VLMs on 1,003 human-verified questions, task-wise mean VLM accuracy is only 8%-31%, versus 81%-97% human majority-vote accuracy. The pooled human–best-VLM gap is 53 pp, with at least 39 pp on every task. The structured answer space further reveals non-uniform failures, including weaker camera-depth-axis inference and fallback behavior on difficult visibility-editing cases.
Read the full abstract ▾
All authors Leyuan Yu, Xiao Tang, Minghao Liu, Xinyuan Li, Xiaokai Bai, Sheng Zhou, Qunshu Lin, Weihao Xuan, Naoto Yokoya
Artificial Intelligence · Cross-listed from cs.LG
PAPA: Online Personalized Active Preference Alignment
Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas et al. (+2 more)
Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific regions of the distribution that maximize user preferences-initially unknown but gradually uncovered through interactive feedback. This can naturally be framed as a reinforcement learning problem, where the goal is to fine-tune a
diffusion model to maximize a reward function based on preferences. However, the main challenge lies in learning a parameterized reward model, which typically requires large-scale preference data-something that is often not feasible in practice. In this work, we introduce Personalized Active Preference
Alignment PAPA, a novel method that bypasses the requirement for a parametrized reward model by directly optimizing the
diffusion model using real-time user feedback. PAPA enables feedback-efficient preference
alignment, drawing inspiration from the variational inference framework. We demonstrate PAPA's effectiveness through extensive experiments and ablation studies across diverse class-conditioned and fine-grained
alignment tasks. Additionally, based on theoretical insights, we propose an enhanced fine-tuning strategy, referred to as EPAPA, that requires less computational budget and accelerates the fine-tuning process, further boosting PAPA's suitability for real-world deployment. Our code is made publicly available at https://github.com/NasikNafi/papa.
Read the full abstract ▾
All authors Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, Yevgeniy Vorobeychik
Artificial Intelligence · Cross-listed from cs.CR
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
Junlong Liu, Haobo Wang, Weiqi Luo et al. (+1 more)
Jailbreak attacks remain a critical threat to the safe deployment of large
language models (LLMs). While prior work has primarily studied attacks and defenses at the
prompt level, we show that this
prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments. In such applications, developer-defined schemas, structured arguments, and untrusted tool outputs are interleaved into a single shared model context. This architecture expands the attack surface by blurring the boundary between trusted control logic and untrusted data, allowing
adversarial intent to be distributed across a multi-turn execution path. We exploit this architectural flaw through SMT, a black-box attack framework based on Simulated Moderation Traces. Departing from purely
prompt-based interactions, SMT constructs a multi-turn trajectory that simulates a legitimate moderation-
auditing workflow. Within this trajectory, a fabricated moderation frame leverages red-team testing as a pretext to elicit harmful generations. The subsequent validation feedback treats safety refusals as execution failures, prompting refinements that gradually weaken the model's safety constraints and ultimately trigger harmful outputs. Extensive empirical evaluations on prominent commercial LLMs from five different providers across two standardized safety
benchmarks show that SMT consistently achieves the highest average attack success rate and HarmScore while requiring a near-minimal number of queries, substantially outperforming existing baselines. These findings demonstrate that
prompt-level sanitization alone is fundamentally insufficient for defending tool-enabled LLM systems and highlight the urgent need for context-aware validation across schemas, arguments, tool outputs, and accumulated conversation state. The code is available at https://github.com/liujlong27/SMT.
Read the full abstract ▾
All authors Junlong Liu, Haobo Wang, Weiqi Luo, Xiaojun Jia
Artificial Intelligence · Cross-listed from cs.CE
A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction
Xin-Yang Liu, Xiantao Fan and Jian-Xun Wang
Predicting complex spatiotemporal dynamics in physical processes often demands computationally expensive numerical methods or data-driven neural networks that suffer from high training costs, error accumulation, and limited generalizability to unseen parameters. An effective approach to address these challenges is leveraging physics priors in training neural networks, known as physics-informed deep learning (PiDL). In this work, we introduce the Multi-Resolution Finite-Volume-inspired network, MuRFiV, designed to capitalize on the conservative property of finite volume on the global scale and the expressive power of deep learning on the local scale. We demonstrate the effectiveness of MuRFiV on several spatio-temporal systems governed by partial differential equations (PDEs), including Burgers' equation, shallow water equations, and incompressible Navier-Stokes equations. By
embedding PDE information into the deep learning architecture, MuRFiV achieves strong long-term prediction accuracy and remains stable over very long autoregressive rollouts, significantly outperforming data-driven neural network baselines. This result highlights the promise of combining multiresolution learning with finite-volume-inspired inductive bias for accurate and robust long-term prediction of complex dynamics.
Read the full abstract ▾
Artificial Intelligence
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
Jinwoo Jang, Daniel J. Rho, Sihyung Yoon et al. (+2 more)
Embodied agents operating in the real world require multi-scale
reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (MoE) to this setting: routing lacks an explicit notion of scale, preventing targeted updates at specific scales, and a uniform update policy cannot accommodate the different rates at which knowledge at each scale becomes outdated. We present MuSix, a framework that addresses both challenges through scale-aware world model mixture and
evolution. A two-stage routing mechanism grounds scale selection in experiential distance, a measure of situational novelty inspired by Construal Level Theory: a meta-router first maps this quantity to a weight over continuous scale space, then per-scale base routers select world models within the identified scale. For adaptation, scale-dependent forgetting rates allow low-scale knowledge to refresh rapidly while high-scale abstractions persist, and gated inter-scale transfer maintains coherence across the hierarchy. Experiments on EmbodiedBench and HAZARD show that MuSix improves over state-of-the-art baselines on multi-scale
reasoning and dynamic adaptation.
Read the full abstract ▾
All authors Jinwoo Jang, Daniel J. Rho, Sihyung Yoon, Hyunsuk Cho, Honguk Woo
Artificial Intelligence
Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation
Vedant Balasubramaniam, Geetha Charan, Manojkumar Patil et al. (+4 more)
Agricultural advisory systems face a fundamental tension: static agronomic guidelines offer consistent, evidence-based recommendations, yet remain blind to in-season variability and dynamic uncertainties. Recent advisory systems powered by LLMs are liable for a different risk of generating recommendations that are agronomically credible but physiologically unconvincing. Agri-SAGE is a closed-loop framework designed to resolve the above two limitations by integrating
retrieval-grounded multi-
agent LLM
reasoning with APSIM-based biophysical simulation, to generate and validate agronomic advisories. To assess this framework, we evaluate three
reasoning approaches, namely Plan-and-Solve, Tree of Thoughts, and Reflexion, over a 10-year retrospective analysis. All three significantly outperform static PoP (Package-of-Practice) baselines, with Tree of Thoughts achieving impressive peak yields. At the same time, Reflexion achieves comparable agronomic outcomes at substantially lower computational cost by leveraging cross-seasonal episodic
memory.
Read the full abstract ▾
All authors Vedant Balasubramaniam, Geetha Charan, Manojkumar Patil, Rohit P Suresh, V Priyanka, Kodur Sai Vinay Sathvik, Y. Narahari
Artificial Intelligence · Cross-listed from cs.LG
Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning
Konstantin Garbers
Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or value loss. Critic complexity is introduced as an additional diagnostic and intervention dimension for actor-critic reinforcement learning. The analysis uses spectral effective-rank
entropy, a rank-like summary of the singular-value distributions of critic weight
matrices, to assess critic model complexity. Across TD3 and PPO experiments, critic complexity is tracked together with return and Monte Carlo value-estimation bias. The results show that critic complexity is measurable throughout training and is systematically associated with training behavior, while also making clear that the relationship is heterogeneous across
algorithms, tasks, and hyperparameters. A direct complexity-control intervention is then evaluated by adding a spectral-
entropy penalty to the critic loss. This intervention reliably changes the targeted spectral quantity, demonstrating that critic complexity can be controlled rather than only observed. Return effects are treated as task-dependent evidence rather than as a general performance claim, because overall complexity-control results vary.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval
Ivan Ji, Liuyi Hu, Harrison Zhao et al. (+4 more)
The two-tower model is widely used in the
retrieval stage of large-scale recommendation systems, where training typically relies on in-batch and/or out-of-batch negative sampling. These methods, however, tend to produce easy negatives that the model learns quickly and that provide little training signal. This paper proposes a self-supervised, cluster-based hard negative sampling technique that draws negatives from the same semantic cluster as the positive item; in our production deployment the clusters are derived from large
language model (LLM) based
multimodal content representations, so that intra-cluster items are genuinely similar and yield informative negatives. To make this deployable at industrial scale, we realize the technique in a real-time, end-to-end framework that maintains a live in-
memory item pool and draws cluster-based negatives from it on the fly via global out-of-batch sampling (GOOBS). The framework integrates directly into production two-tower training and serving and scales to billions of training examples with minimal computational overhead. Experiments on four public
datasets and a 14-day online A/B test in a large-scale production system show that the proposed technique outperforms widely used industry methods, while also helping to break recommendation feedback loops and substantially reducing popularity bias.
Read the full abstract ▾
All authors Ivan Ji, Liuyi Hu, Harrison Zhao, Lei Huang, Qunshu Zhang, Max Fan, Aameek Singh
Artificial Intelligence · Cross-listed from cs.CV
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
Seohyun Lee, Seoung Choi, Dohwan Ko et al. (+2 more)
As
video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant
videos from large-scale corpora (inter-
video reasoning) and subsequently perform fine-grained, query-conditioned tasks (intra-
video reasoning) within the retrieved content, such as temporal grounding. However, existing approaches typically treat
retrieval as a preprocessing step, and consequently, when the initial
retrieval fails, there is no mechanism to refine the search, leading to the failure of subsequent fine-grained intra-
video reasoning. Moreover, while recent agentic frameworks have advanced
video understanding, they typically assume that the query-relevant
video is already given, focusing exclusively on intra-
video reasoning tasks. To address these limitations, we propose VideoSearch-R1, an agentic framework for iterative
video retrieval and
reasoning through multi-turn interaction with a
video search engine. Specifically, we introduce Soft Query Refinement (SQR) to refine search query
tokens in a continuous latent space rather than rewriting queries in the discrete text space, enabling more efficient and fine-grained adjustments. SQR and its
reasoning process are trained using Group Relative Policy Optimization (GRPO), guided by task-level reward signals derived from
retrieval and downstream tasks. Building upon this, VideoSearch-R1 achieves state-of-the-art performance across three
datasets on
Video Corpus Moment
Retrieval (VCMR), iteratively retrieving
videos from large-scale corpora, refining search queries, and performing precise query-conditioned temporal grounding within the retrieved content. Our analyses show that SQR effectively refines the original query, requiring significantly fewer generated
tokens than explicit text-level query refinement. Code and model checkpoints are publicly available at mlvlab.github.io/VideoSearch-R1.
Read the full abstract ▾
All authors Seohyun Lee, Seoung Choi, Dohwan Ko, Jongha Kim, Hyunwoo J. Kim
Artificial Intelligence · Cross-listed from cs.RO
Search-Based Spatiotemporal and Multi-Robot Motion Planning on Graphs of Space-Time Convex Sets
Jingtao Tang, Zining Mao, Lufan Yang et al. (+1 more)
Spatiotemporal motion planning, especially in multi-
robot settings, requires
robots to reason about collision-free regions that change over time, which is challenging in continuous spaces when feasible regions are transient and geometrically constrained. We present an algorithmic framework based on graphs of space-time convex sets (ST-GCSs), where collision-free regions are represented as convex sets in space-time and trajectories correspond to paths on the graph together with continuous motions within the selected sets. We formulate time-optimal planning on ST-GCSs as a graph-search problem over path-indexed states and develop a best-first search solver that evaluates partial paths via continuous trajectory optimization, guided by admissible heuristics and dominance checks. We further present an Exact Convex Decomposition (ECD) scheme to reserve trajectory occupancies in space-time, enabling unified handling of dynamic obstacles and multi-
robot interactions. For multi-
robot motion planning, we integrate ST-GCS planning and ECD into prioritized planning methods and introduce a windowed coordination scheme to improve efficiency. Extensive experiments on single-
robot and multi-
robot problems demonstrate substantial speedups over various planners while maintaining high solution quality, particularly in environments with narrow and transient feasible regions. Large-scale demonstrations further show that the proposed multi-
robot motion planner can solve instances with up to $100$
robots within only a few minutes. Project homepage: https://sites.google.com/view/stgcs
Read the full abstract ▾
All authors Jingtao Tang, Zining Mao, Lufan Yang, Hang Ma
Artificial Intelligence · Cross-listed from cs.RO
Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications
Merve Atasever, Keyan Azbijari, Cagan Bakirci et al. (+3 more)
Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that may limit interpretability of learned policies and may lack explicit control over gait behaviors. We introduce a framework where distinct gaits are specified using parameterized constraints expressed in Signal Temporal Logic (STL). These include safety bounds, gait synchronization constraints, command tracking, and actuation bounds. From these specifications, we develop a reward shaping mechanism that provides learning
agents a dense, continuous reward landscape that encodes desired behavior. We define parametric STL templates for three speed regimes (walking-trot, trot, bound), calibrate their parameters from reference rollouts, and compute rewards from using smooth approximations of STL robustness over the rollouts. The generated rewards can be used to provide shaped gradients compatible with Proximal Policy Optimization (PPO). We instantiate the approach on Google's Barkour quadruped
robot in MuJoCo XLA (MJX). We use parallelization within the simulator to improve training speeds and use domain randomization to robustify learned policies. Compared with hand-crafted rewards, an expert-switching oracle, and Text2Reward, Human-STL maintains high command-tracking success across the evaluated speed range while exhibiting substantially higher consistency with the intended speed-dependent gait structures.
Videos can be found on our project website: https://stl-locomotion.github.io/.
Read the full abstract ▾
All authors Merve Atasever, Keyan Azbijari, Cagan Bakirci, Alfredo Reina Corona, Tolga Izdas, Jyotirmoy V. Deshmukh