Artificial Intelligence · Cross-listed from cs.LG
NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
Xinwei Liu, Junyuan Liang, Zicong Hong et al. (+2 more)
Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and performance, with minor modifications and limited additional computation. However, this approach still struggles in challenging tasks with low-dimensional observations. In this paper, we identify a key factor behind this problem: unbalanced reconstruction losses across observation dimensions, where dimensions with larger value ranges dominate the loss. This encourages the
agent to neglect dimensions with relatively small ranges, leading to degraded performance. To address this issue, we propose a novel normalization method tailored to online RL, which normalizes low-dimensional observations and balances the resulting losses and gradients. Beyond balancing reconstruction losses, observation normalization enables dynamics prediction to be performed in a normalized observation space, thereby providing a unified treatment of low- and high-dimensional inputs (e.g., physical states and images). Building on this idea, we further introduce Normalized Observation Space Dynamics-Augmented Q-learning (NASDAQ), a framework for observation-predictive RL applicable across diverse domains. NASDAQ learns state-action representations by coupling value learning with two auxiliary tasks: short-term value prediction and next normalized observation prediction. Extensive experiments demonstrate that NASDAQ achieves competitive or superior performance compared with state-of-the-art model-based and self-predictive RL methods, while requiring significantly less training wall-time.
Read the full abstract ▾
All authors Xinwei Liu, Junyuan Liang, Zicong Hong, Jianting Zhang, Wuhui Chen
Artificial Intelligence · Cross-listed from cs.LG
Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling
Borui Cai and Yao Zhao
Existing sequence models, including RNNs, LSTMs, continuous-time networks, and
Transformers, share a common structural principle: layer-wise dynamics, where all
neurons in the same layer co-evolve through a shared parameterized operator, leaving individual
neurons no freedom to evolve independently. Yet in many complex dynamical systems, rich global behavior emerges precisely from locally evolving units interacting through structured connectivity. Inspired by this principle, we introduce Topological Neural Dynamics (TND), a sequence modeling framework that shifts computation from layer-wise to
neuron-wise dynamics. TND represents a neural system as a directed
neuron graph, an interaction operator, and a local dynamics function, where each
neuron evolves independently and collective computation emerges from interactions through the explicit graph
topology. We instantiate TND as a discrete-time graph-coupled dynamical system and evaluate it as a case study on a behavior cloning task in single-player Pong. Compared with Vanilla RNN, Sparse RNN, LSTM, Closed-form continuous-time neural network (CfC), and
Transformer baselines, TND achieves the best catch rate and a mean of 17.47 consecutive catches per round, more than three times that of the strongest baseline. These results suggest that shifting from layer-wise to
neuron-wise dynamics provides an effective inductive bias for sequence modeling.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Few-Shot Hyperspectral Aphid Detection via FastGAN Synthetic Data Generation, Transformer-Based Classification and Explainable AI
Ali Saeidan
Early detection of aphid infestation in crops is essential for preventing yield loss and reducing unnecessary pesticide use. Hyperspectral imaging combined with Spectral Information Divergence (SID) analysis offers a non-destructive approach for monitoring plant health; however, deep learning methods applied to hyperspectral data are often limited by small
dataset sizes. In this study, a data-efficient generative
adversarial network (FastGAN) was employed to augment a hyperspectral SID
dataset of faba bean leaves containing healthy and aphid-infested samples. The trained generator produced 10,000 synthetic images preserving structural and spectral characteristics of real samples. Image quality was evaluated using Frechet Inception Distance (FID), demonstrating stable convergence and realistic reconstruction of leaf morphology and infestation patterns. The augmented
dataset was used to train four classification architectures: VGG16, ResNet-50, EfficientNet, and
Vision Transformer (ViT). Results showed that
dataset augmentation significantly improved classification robustness, with performance progressively increasing from classical convolutional networks to
transformer-based models. The ViT model achieved the highest accuracy and F1-scores, while EfficientNet provided strong balanced performance and ResNet-50 showed moderate improvements over VGG16. Confusion
matrix analysis confirmed reduced false negatives and improved disease detection when using advanced architectures. The findings demonstrate that FastGAN-based augmentation effectively enhances hyperspectral plant disease classification and that
transformer-based models provide the most reliable discrimination between healthy and infested leaves.
Read the full abstract ▾
Artificial Intelligence
ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents
Zihang Tian, Jingsen Zhang, Rui Li et al. (+3 more)
Reinforcement learning for multi-step LLM
agents often relies on scalar rewards that indicate success but cannot explain why a trajectory is good or bad. Rubric-based rewards improve interpretability through natural-
language criteria, but existing methods share two limitations: they score at the trajectory level, offering no guidance for individual steps; and their scorer is closed-source and static, so it cannot adapt as the
agent evolves during training. We propose ARCO (Adaptive Rubric CO-
evolution), which generates a per-step rubric and predicts a rubric-conditioned step-level reward for each action, and continually updates this rubric model on on-policy rollouts so that its criteria and scores co-evolve with the
agent's improving behavior. Across HotpotQA, 2WikiMultiHopQA, and MuSiQue with two open-source backbones, ARCO achieves the highest EM in all settings over outcome-, rubric-, and process-reward baselines, and analyses show its rubrics are step-specific, robust to design choices, and useful for diagnosing
agent behavior. Code and data are available at https://github.com/zihangtian/ARCO.
Read the full abstract ▾
All authors Zihang Tian, Jingsen Zhang, Rui Li, Xiaohe Bo, Yuanzi Li, Xu Chen
Artificial Intelligence · Cross-listed from cs.LG
An Empirical Study of openPangu Quantization on Ascend NPUs
Tong Shi, Jiacheng Wang, Hui Xie et al. (+4 more)
openPangu models are attractive targets for private and domestic large-
language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs has not been systematically characterized. This paper conducts a controlled empirical study of openPangu 1B and 7B models on Huawei Ascend 910B1 NPUs. We evaluate representative weight-only and weight-activation post-training quantization methods, including RTN, GPTQ, AWQ, SmoothQuant, GPTAQ, BiLLM, and SliM-LLM, under a unified calibration and evaluation protocol. Across 18 evaluation tasks, we find that 8-bit weight-only quantization is effectively lossless for both models, while 4-bit quantization remains practical for the 7B model but is visibly more harmful for the 1B model on
reasoning, math, and code tasks. Ultra-low precision remains challenging: most 2-bit and binary settings collapse to near-random behavior, and W4A4 SmoothQuant produces non-finite perplexity in our evaluation. These results provide an NPU-oriented accuracy map for selecting openPangu quantization settings and highlight the persistent difficulty of extreme low-bit compression.
Read the full abstract ▾
All authors Tong Shi, Jiacheng Wang, Hui Xie, Ying Li, Aishan Liu, Jinyang Guo, Xianglong Liu
Artificial Intelligence · Cross-listed from cs.CV
ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting
Jijian Zhao
3D Gaussian Splatting achieves exceptional real-time rendering, but its substantial computational and storage demands hinder widespread deployment. Existing accelerated paradigms often aggressively prune primitives for rapid convergence, causing severe loss of high-frequency details. To address this, we tackle the fundamental problem of achieving both exceptional rendering quality and ultra-fast reconstruction speed. In this paper, we propose ACE-GS, a progressive optimization framework tailored for accurate, compressed, and efficient scene representation. We realize that precise primitive management is the key to breaking this trade-off. Therefore, we first design a momentum consistency-guided densification strategy, strictly constraining primitive growth onto authentic
geometric manifolds to avoid computational waste while significantly accelerating convergence. Building upon this efficient initialization, we deploy a statistical sensitivity-driven sparsification mechanism to precisely prune redundant primitives, yielding a further compressed footprint. Finally, to thoroughly compensate for the risk of micro-structure loss caused by the aforementioned strict primitive control, we introduce a cross-dimensional residual frequency compensation scheme that explicitly back-injects high-frequency error energy into primitive attributes, perfectly restoring sharp
geometric details. Extensive experiments validate our superiority. While maintaining a highly compact scene representation, our system achieves up to 3.7 times training acceleration against the rapid framework Speedy-Splat. Requiring only 3 to 5 minutes to converge, ACE-GS secures the highest structural similarity and achieves a peak PSNR improvement of up to 0.89 dB over the original 3DGS, establishing a new
benchmark for ultra-fast and high-fidelity novel view synthesis.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.DC
Recency/Frequency Adaptive KV Caching for Large Language Model Serving
Yang Shen, Meghana Madhyastha, Robert Underwood et al. (+2 more)
Key-value (KV) caching is a powerful technique for accelerating large
language model inference and generation. Inference workloads are large and diverse, which makes them difficult to cache effectively. Existing cache management strategies adopt the least-recently-used policy for evicting cache blocks. However, LRU leads to multiple unrelated workloads flushing each other's caches. To address this, we integrate adaptive caching that dynamically allocates cache space between recently and frequently occurring KV blocks. Evaluations show that it improves the KV cache hit rate by up to 10.8% and reduces time to first
token by up to 12.6% over naive vLLM on synthetic document question answering workloads, and 2.1% and 2.0% respectively on real-world conversation workloads. The method generalizes well to batch inference and demonstrates clear interpretability while effectively accommodating diverse workloads.
Read the full abstract ▾
All authors Yang Shen, Meghana Madhyastha, Robert Underwood, Bogdan Nicolae, Randal Burns
Artificial Intelligence · Cross-listed from cs.RO
FleetAgent: Teleoperation Assistant for Autonomous Fleets via Vectorized V2N Messages
Juntong Peng, Qi Chen, Deyuan Qu et al. (+3 more)
Large-scale autonomous fleets rely on teleoperation to resolve rare failures, yet streaming raw sensor data from many vehicles is costly, and remote operators can only monitor a limited number of vehicles at a time. We introduce FleetAgent, a cloud-hosted
multimodal large
language model (MLLM) assistant that consumes compact vectorized vehicle-to-network (V2N) messages, such as map elements, detected objects, and the ego planned path. It provides a structured natural-
language response (including narration, explanation, and evaluation of the plan and scene), along with an intervention urgency score for operator prioritization. To make structured messages compatible with
token-based MLLMs, we propose VecFormer, a vector-to-
embedding interface with differentiable top-K context selection that bounds context length and GPU KV-cache growth, enabling more efficient batch processing, which is important under the context of cloud-hosted large-scale fleet management. We also construct VecEval, a nuScenes-derived
dataset with paired human and synthetic imperfect plans and human-verified
language labels, to facilitate the training and evaluation of our proposed system. Our proposed system can reduce uplink payload by up to 625 times compared with raw images and reduce KV-cache
memory by 16.54 times compared with original text descriptions. On VecEval, FleetAgent improves Lingo-Judge score by 16.8% and reduces intervention failure rate by 19.9%, compared with Qwen2.5-VL-7B using
language descriptions. These results demonstrate that FleetAgent can utilize compact structured V2N messaging to enable efficient, explainable teleoperation monitoring for autonomous fleets.
Read the full abstract ▾
All authors Juntong Peng, Qi Chen, Deyuan Qu, Takayuki Shimizu, Yaobin Chen, Ziran Wang
Artificial Intelligence · Cross-listed from eess.AS
Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach
Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou et al. (+4 more)
As expressive text-to-
speech (TTS) and voice conversion (VC) systems increasingly generate non-verbal vocalizations (NVVs) to enhance naturalness, reliable speaker verification (SV) becomes essential to objectively assess identity consistency across both verbal and non-verbal segments. Yet current SV systems generalize poorly to NVVs, and fine-tuning on NVV data causes catastrophic forgetting of
speech performance. We present the first systematic study across 10 NVV types and propose a framework combining frozen Data2Vec self-supervised features with ECAPA-TDNN, enhanced by a Mixture of Experts (MoE) module with learned domain-aware routing. A conditional
distillation loss on
speech inputs via a pretrained teacher retains
speech-to-
speech accuracy, while a contrastive loss bridges the
speech-NVV domain gap. Our method reduces
speech-NVV EER from 38.93% to 22.66% over a pretrained baseline, and improves
speech EER from 13.17% to 9.24% via
distillation.
Read the full abstract ▾
All authors Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou, Kuan-Yu Chen, Hsin-Yen Sung, Shrikanth Narayanan, Hung-yi Lee
Artificial Intelligence · Cross-listed from physics.chem-ph
QBioFusion-QSAR: Morgan-Anchored Quantum Multiple Kernel Learning for Small-Data Ligand Classification
Azadeh Alavi, Fatemeh Kouchmeshki, Muhammad Usman et al. (+1 more)
Small quantitative structure-activity relationship (QSAR) studies are difficult when close molecular analogues have different activity labels. This paper asks whether a
quantum kernel can add similarity information to a Morgan/Tanimoto fingerprint model, and which molecules account for the change. QBioFusion-QSAR uses
quantum multiple kernel learning (QMKL): a support vector machine combines a Morgan/Tanimoto kernel with a
quantum fidelity kernel constructed from fold-local components derived from RDKit and Mordred descriptors and Deep-PK features. Linear and radial basis function descriptor kernels are included as classical controls. On the 54-molecule PsychLight-A
benchmark, Morgan/Tanimoto was the strongest single representation. In the primary stratified five-fold evaluation, QMKL increased accuracy from 0.815 to 0.833 and Matthews correlation coefficient (MCC) from 0.613 to 0.645. Matched-regularization
auditing attributed the change to N-Me-5-HT and N-Me-tryptamine changing from false-negative to true-positive predictions; activity-cliff subset MCC increased from 0.07 to 0.22. Repeating the five-fold protocol over ten random partitionings showed that learned QMKL did not exceed Morgan/Tanimoto on mean MCC; paired held-out bootstrap intervals for the matched comparison also span zero. These results support QBioFusion-QSAR as an auditable QMKL framework for identifying localized residual
quantum-kernel contributions in small-data, activity-cliff-aware ligand classification.
Read the full abstract ▾
All authors Azadeh Alavi, Fatemeh Kouchmeshki, Muhammad Usman, Jessica Holien
Artificial Intelligence · Cross-listed from cs.CL
When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs
Ece Takmaz, Nitin Kumar, Li Kloostra et al. (+1 more)
Psycholinguistics studies show that human readers fall for coherence illusions: an incoherent discourse can seem coherent simply because a distractor matches what comes next. We investigate whether Dutch
language models (6 monolingual and 4
multilingual) show the same behavior on texts that link back to earlier context with words such as 'again' and 'too'. First, we find that surprisal at the critical word tracks human acceptability judgments and eye-tracking data. Models are more surprised by incoherent continuations, but a matching distractor in the prior context reduces this surprisal. Second,
attention entropy identifies heads that behave differently under coherence vs. incoherence. We find that ablating these heads shows transfer effects across experiments, suggesting a shared mechanism. Third, we introduce energy from the associative-
memory literature as a metric to quantify discourse coherence. Taken together, our results show that coherence illusions arise in Dutch LLMs, with
entropy and energy exposing mechanisms that operate across settings.
Read the full abstract ▾
All authors Ece Takmaz, Nitin Kumar, Li Kloostra, Jakub Dotlacil
Artificial Intelligence · Cross-listed from cond-mat.dis-nn
Communication Heterogeneity and Collective Consensus in Neural Cellular Automata
Nishit Singh
Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that all
agents share a single communication protocol. We ask what happens when they do not. Using a Neural Cellular Automaton in which a population of
cells must solve the density classification task, agreeing on a global majority that no individual can observe, we introduce “
languages” as sub-populations that read one another's messages through a translation with a tunable “linguistic distance”. We find that linguistic distance slows consensus, that it produces mild divergence between groups rather than full fragmentation, and that a collective whose shared rule was trained under diverse protocols is robust to mismatch; a homogeneously trained one is not. The findings hold on both a ring and a two-dimensional grid, and admit a natural reading as Ising relaxation, in which a foreign-
language region acts as a boundary defect that leaves the system in a higher-energy, partially ordered state. These patterns are qualitatively consistent with effects reported in human group studies, suggesting that distance between communication protocols is a minimal mechanism sufficient to produce them, without anything
language-specific.
Read the full abstract ▾
Artificial Intelligence
Whistleblowing and the machine – towards a considered position
Marija Slavkovik, Liuwen Yu, Leon van der Torre et al. (+1 more)
Artificial intelligent
agents and autonomous systems are embedded in our environments. They are both a commercial product and a personal tool that generates a lot of data and can draw conclusions from it: machines generate and keep secrets. But should machines protect all secrets? It has been shown that artificial
agents are able to whistleblow and it has been argued that digital multi-
agent environments should allow for
agents in them to whistleblow. We argue that machine whistleblowing must be normative and principled and routed in the existing understanding of whistleblowing as an important rule-breaking mechanism in society. We also argue that there is a need for government regulators to formulate an informed stance on both what machines should be allowed to whistleblow on and how to legally protect those who develop whistleblowing machines
Read the full abstract ▾
All authors Marija Slavkovik, Liuwen Yu, Leon van der Torre, Reka Markovich
Artificial Intelligence · Cross-listed from cs.CV
Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders
Sergio Lanza, Jae Hee Lee and Stefan Wermter
Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answering (VQA), but our understanding of their internal processes remains limited. Recently, Sparse Autoencoders (SAEs) have emerged as a promising tool to support the interpretation of concepts encoded in VLMs. However, most SAE-based approaches focus only on textual or visual concepts separately, ignoring
multimodal concepts. This limitation hinders a comprehensive understanding of VLMs, since concepts that integrate both modalities can be misclassified. Moreover, previous visual approaches often produce low-quality visual concept descriptions that are vague or incomplete, limiting their usefulness for understanding model
reasoning. We propose a framework based on SAEs to extract and analyze visual, textual, and
multimodal concepts from VLMs. For each
neuron, we propose a candidate human-interpretable concept and compute the
alignment between the concept and the
dataset samples using cosine similarity scores. Experiments on a VQA
dataset (LLaVA-NeXT) demonstrate that our framework improves visual concept quality by up to 45% compared to existing SAE-based methods, while maintaining high textual concept quality and enabling systematic identification of
multimodal concepts. This work contributes new insights into the conceptual space of VLMs, providing a structured approach to distinguish between visual, textual, and
multimodal concepts. The code is available at https://github.com/PHDLanza/Multidata_SAE
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding
Joo Yull Rhee
This paper revisits the grounding problem for large
language models in light of recent vector-grounding accounts. I accept the shift from classical symbol grounding to vector grounding, but argue that the current debate remains incomplete in two respects. First, reference is often treated too thinly, as if it were a fixed link between an isolated expression and an object. I argue instead that reference is profile-based, context-sensitive, discourse-level, affectively shaped, and norm-governed. Even in the human case, reference is publicly stabilized through patterns of use, correction, distinction, inference, and continuation rather than through identical private representations. Second, vector grounding requires an account of numerical realization. LLMs do not acquire reference through human perception,
memory, intention, embodiment, or understanding. Rather, through optimization, they parameterize linguistic traces of human world-directed practice. In a finite vector system, referential profiles must be distributed, may be superposed, and are recovered through context-sensitive computation. Weights, activations,
attention-mediated hidden states, softmax-trained contrasts, and inner-product
alignments are the mathematical sites at which inherited linguistic relations become stable and causally active. Mechanistic interpretability findings, including entity-like features, knowledge
neurons, and
emotion-related activation directions, provide indirect support for this view. They do not show that LLMs possess human reference. They support a more limited thesis: LLMs may possess derivative,
language-mediated, profile-based, and numerically structured forms of reference.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models
Han Jang, Junhyeok Lee, Songsoo Kim et al. (+4 more)
Medical
Vision-
Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale
multimodal benchmark and evaluation framework for Medical Lay
Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source
datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical
Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing
hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay
alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible
language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication.
Read the full abstract ▾
All authors Han Jang, Junhyeok Lee, Songsoo Kim, Chae Young Lim, Hyeonjin Goh, Heeseong Eum, Kyu Sung Choi
Artificial Intelligence · Cross-listed from cs.LG
TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations
Yitian Zhou, Chaoning Zhang, Zhenzhen Huang et al. (+8 more)
Non-stationary partial differential equations (PDEs) arise throughout scientific computing, where the dominant frequency content and energy distribution can drift over time. While efficient in PDE solving, many spectral neural operators apply a shared spectral response across rollout stages, leading to mismatch with time-varying spectra in non-stationary systems. To address this issue, we propose Time-Frequency Gated Spectral Neural Operator (TF-SNO), a state-adaptive framework with learnable time-frequency gating inside spectral blocks. TF-SNO extracts compact frequency-domain and physical-space statistics from the current state to generate modulation coefficients, enabling the spectral response to evolve with the dynamics. TF-SNO learns temporal variation implicitly from the evolving state without introducing an explicit time dimension or time
embedding, keeping the modeling complexity low. We further embed the adaptive operator blocks to accurately capture the multi-scale features, thereby improving long-horizon stability. Experiments on six non-stationary PDE
benchmarks in 1D and 2D demonstrate that TF-SNO significantly reduces prediction errors and improves robustness compared to strong baselines, with particularly clear gains in long rollout, suggesting the effectiveness of state-dependent spectral adaptation in modeling non-stationary physical systems.
Read the full abstract ▾
All authors Yitian Zhou, Chaoning Zhang, Zhenzhen Huang, Haoxuan Yu, Jiaquan Zhang, Yiran Li, Fan Mo, Kuien Liu, Jie Zou, Caiyan Qin, Yang Yang
Artificial Intelligence · Cross-listed from eess.IV
Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors
Dayun Ju, Chanyoung Kim, Sunyoung Jung et al. (+4 more)
Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in practice due to its small size, low contrast, and morphological variability. Existing methods, primarily adapted from general
segmentation architectures, often produce fragmented or anatomically inconsistent masks, leading to unstable measurements of disc position and shape for downstream diagnosis. To address these challenges, we propose TISC, a TMJ disc
segmentation framework that integrates semantic anchoring with clinical metadata-guided boundary refinement. The framework first establishes robust disc localization in the foundation model feature space via a Prototypical Semantic Anchoring (PSA) module that aggregates adjacent-slice MedDINOv3 features and derives a prototype-driven similarity map. It then performs targeted boundary refinement through a Clinical-Metadata Point Refinement (C-MPR) module, with point-wise predictions modulated by Mouth Open Limitation (MOL), a clinical indicator associated with disc displacement without reduction. On a large-scale cohort of 2,488 PD MRI volumes from 1,300 patients, our method achieves up to a 4.96 Dice improvement over strong baselines across diverse architectures, delivering more anatomically coherent and clinically reliable TMJ disc
segmentation.
Read the full abstract ▾
All authors Dayun Ju, Chanyoung Kim, Sunyoung Jung, Hyo-Jung Jung, Chena Lee, Younjung Park, Seong Jae Hwang
Artificial Intelligence · Cross-listed from cs.LG
Inverting the Bellman Equation: From $Q$-Values to World Models
Alistair Letcher, Mattie Fellows, Alexander D. Goldie et al. (+3 more)
Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: instead of learning a model of the transition kernel $P$, model-free
agents typically estimate value functions tied to a specific policy and reward. In this paper, we challenge this dichotomy by proving that value-based
agents trained on a sufficiently rich set of reward functions, e.g. using goal-conditioned RL, implicitly encode a unique and accurate world model. To extract this model in practice, we introduce \textit{$P$-learning}, an inverse analogue to $Q$-learning that samples from an
agent's $Q$-values, policies and rewards to decode its internal model of the environment. We then provide sufficient conditions on the type and number of goals for which
agents encode the true kernel $P$, covering both
stochastic and deterministic MDPs over finite or continuous state spaces. Even when our assumptions are violated, we empirically demonstrate that
agents trained on a handful of reward functions encode accurate dynamics in $\texttt{Reacher}$, $\texttt{MountainCar}$ and
stochastic variants of $\texttt{FourRooms}$. Surprisingly, we find that policies trained exclusively on a Reacher
agent's implicit world model are quasi-optimal on out-of-distribution, velocity-based goals despite position-only training – suggesting that
agents contain hidden generalisation capabilities and providing a new lens into the connection between model-based, model-free, and goal-conditioned RL.
Read the full abstract ▾
All authors Alistair Letcher, Mattie Fellows, Alexander D. Goldie, Jonathan Richens, Jakob N. Foerster, Oliver Richardson
Artificial Intelligence · Cross-listed from cs.SE
An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game
Jan Wunderlich, Markus Kleffmann and Sebastian Lempert
Large
language models (LLMs) are increasingly used to support software development, but their practical usefulness in applied game-development settings remains underexplored, especially when generated code must be integrated into an existing game software system. This paper presents an exploratory empirical case study of GPT-4o in a custom Python/Pygame endless runner. The study examines six selected development tasks: three localized refactoring tasks and three tasks involving gameplay feature generation. The resulting implementations were evaluated using software metrics, unit tests, and manual gameplay assessments. In this case study, all three selected refactoring tasks were completed successfully in functional terms, whereas only one of the three selected gameplay feature generation tasks resulted in a correctly integrated feature. The findings suggest that, in this setting, GPT-4o handled localized transformations more reliably than tasks requiring new gameplay interactions across multiple existing systems. Given the exploratory single-case design, these results are best interpreted as indicative observations rather than as generalizable evidence of category-level model performance. Overall, the paper contributes a transparent case-based account of the opportunities and limitations of LLM-assisted refactoring and gameplay feature generation in an existing game software system.
Read the full abstract ▾
Artificial Intelligence
Trip+: Benchmarking Agents in Personalized Interactive Travel Planning
Junle Chen, Wei Chen, Yehong Xu et al. (+6 more)
Interactive travel planning has become a popular use case for
language models.
Agents are deployed to manage evolving preferences and unexpected disruptions over multiple turns. Such settings require models to make complex, profile-conditioned planning decisions. However, existing
benchmarks often evaluate feasibility, personalization, or interaction in relatively isolated settings. We therefore introduce Trip+ to measure the ability of
agents to plan travel holistically. In Trip+, given traveler profiles and dynamic interactions,
agents must generate and revise minute-level itineraries. End-to-end traveler experiences are evaluated via an LLM-based simulator, enabling the assessment of subjective metrics like fatigue. Our scenarios range from simple request resolutions to complex environment-driven replanning. We evaluate 18 LMs and find a consistent gap in experiential quality. Models favor technically feasible but exhausting itineraries that diverge sharply from profiled traveler preferences.
Read the full abstract ▾
All authors Junle Chen, Wei Chen, Yehong Xu, Zhengjun Huang, Yuqian Wu, Zhoujin Tian, Kai Wang, Lei Wang, Xiaofang Zhou
Artificial Intelligence · Cross-listed from cs.RO
OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving
Juntong Peng, Juanwu Lu, Yupeng Zhou et al. (+3 more)
We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-modal and multi-
agent observations. The new design mitigates the computational cost of dense 3D perception, the vulnerability to data scarcity in cooperative scenarios, and the poor compliance with standardized messaging in existing methods that fuse multi-modal inputs into a shared representation. For training, we present an end-to-end supervised pipeline using a downstream trajectory generation loss, in which a high-capacity generative sequence planner implicitly learns to steer the model and leverage multi-modal inputs via cross-
attention injection. As a foundation model, we demonstrate that OmniV2X pre-trained on large-scale single-
agent planning
datasets can efficiently adapt to cooperative environments by integrating the conditioning context with lightweight, standard-compliant V2X
tokens. Evaluated on the DAIR-V2X-Seq
dataset, OmniV2X outperforms existing end-to-end cooperative driving baselines, achieving state-of-the-art performance with less than 10% of the fine-tune V2X
dataset and less than 1% of the communication bandwidth. We conduct comprehensive evaluations to demonstrate its computational efficiency and robustness under real-world constraints.
Read the full abstract ▾
All authors Juntong Peng, Juanwu Lu, Yupeng Zhou, Can Cui, Yaobin Chen, Ziran Wang
Artificial Intelligence · Cross-listed from cs.CV
Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
Joohyeok Kim, Taejin Jeong, Jinyeong Kim et al. (+1 more)
The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However, this prediction task faces an inherent limitation, as tissue morphology alone provides insufficient information to fully resolve underlying gene expression. To address this limitation, a recent study leverages partial gene expression to guide the prediction process alongside histology images. Building on this paradigm, we approach the prediction task as a spatial imputation problem, employing a Masked Autoencoder (MAE) to utilize a small fraction of gene expression as genetic anchors for inferring whole-slide gene expression profiles. Specifically, we propose a bio-saliency score and a learning-to-rank strategy to adaptively identify the most informative spots within the tissue. Based on these identified spots, our framework selects contiguous regions as genetic anchors to ensure suitability for real-world ST profiling hardware. To effectively leverage these anchors, we design a cross-modal joint encoder that integrates visual and genetic modalities. By aligning the selected anchors with their corresponding visual features via contrastive learning, the encoder generates robust joint representations to accurately predict gene expression across the whole slide. Notably, our framework consistently surpasses existing methods in both histology-only prediction and spatial imputation, achieving superior accuracy even without genetic anchors and further excelling with as little as 10% transcriptomic coverage. Our code is available at https://github.com/Kyyle2114/CAMMST.
Read the full abstract ▾
All authors Joohyeok Kim, Taejin Jeong, Jinyeong Kim, Seong Jae Hwang
Artificial Intelligence · Cross-listed from cs.SE
Context-Aware Generative AI for Automated Telecom Test Script Generation
Gautam Prasad, Chandramohan T. N. and Joy Bose
Automated test generation for telecom software systems and networks has advanced significantly with the adoption of machine learning and rule-based approaches. However, most existing solutions generate static test suites against a snapshot of the system; as code, configurations,
topologies, and key performance indicators (KPIs) evolve, these tests quickly become outdated or misaligned with the live system. There is currently no widely adopted solution that continuously detects fine-grained changes and selectively adapts only the affected tests without regenerating entire test suites. This paper presents a context-aware generative AI framework for automated telecom test script generation that treats testing as a continuously adapting process driven by the current state of the system rather than a static artifact. The central contribution is delta-conditioned test generation over a live knowledge graph: our approach employs a continuously updated knowledge graph (KG) as a single source of truth, a delta engine for fine-grained change detection, and a KG-guided generative AI
agent, operating via the Model Context Protocol (MCP), to create, update, or retire test cases automatically. We further integrate
Retrieval-Augmented Generation (RAG) to enrich
reasoning with telecom-domain knowledge and historical artifacts. We demonstrate applicability across software-system and telecom-network use cases, including a Python-based KPI monitoring application managed in GitLab, and show how the framework reduces manual effort, improves test relevance, and accelerates test cycles.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
Jiaxi Yang, Chaewan Chun, Jason Lucas et al. (+2 more)
Large Audio
Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety
alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to over-refusal, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because
speech that appears harmful in isolation may become benign when interpreted together with the surrounding acoustic context, such as background sounds. To study this problem, we introduce AOR-Bench (Audio Over-Refusal
Benchmark), the first
benchmark for over-refusal specifically designed for LALMs. AOR-Bench contains 3,000 pseudo-harmful audio samples across six scenario categories. Evaluating 12 representative LALMs from six major model families, we find that over-refusal is widespread (Figure 1) and uncover several important patterns in their safety judgments. As a preliminary effort to mitigate this issue, we further explore two lightweight strategies (e.g., Chain-of-Thought and activation steering) to reduce over-refusal.
Read the full abstract ▾
All authors Jiaxi Yang, Chaewan Chun, Jason Lucas, Yuchen Yang, Dongwon Lee
Artificial Intelligence · Cross-listed from cs.CL
AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents
Xingyu Chen, Rui Wang, Zhaopeng Tu et al. (+1 more)
Long-term
memory systems allow LLM
agents to preserve information beyond a single context window, but most systems focus on storing and retrieving facts after extraction, leaving the write decision under-specified. What deserves
memory can depend on the user's current task, topic, activity, or interaction partner, while uniform extraction applies one notion of importance across these different situations. We formulate this challenge as preference-conditioned write control and introduce AdaMem, which uses adaptive natural-
language Memory Policies to personalize what an
agent writes to
memory. Each policy represents the user's
memory preference for a particular interaction context, is updated from periodic feedback, and controls subsequent
memory writing. We evaluate this loop in AdaMem-Bench, which assigns different
memory preferences to six concurrent interaction personas across five ten-week stories. Across two extraction models and two feedback modes, AdaMem improves average QA accuracy over Mem0 from 80.0% to 84.35% while reducing persistent
memory by 9.27%. Our analyses show that explicit feedback helps models learn better
memory policies, but current models still struggle to translate those policies into reliably selective writing behavior. AdaMem thus demonstrates the promise of adaptive write control while exposing policy execution as a central limitation of current
memory agents. Our code is publicly available: https://github.com/galaxyChen/AdaMem
Read the full abstract ▾
All authors Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo
Artificial Intelligence · Cross-listed from cs.SE
Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
Han Chi, Jiaxin Qi, Yan Cui et al. (+2 more)
Rapid advances in large
language models have improved the task-solving capabilities of command-line-interface (CLI)-based
agents, whose CLIs determine how models invoke tools, maintain interaction history, and recover from failures. Consequently, effective matching between CLIs and LLMs has become essential. However, existing
agent benchmarks largely emphasize success rate while overlooking practical objectives such as cost and efficiency, as well as the selection of LM-CLI combinations, all of which are critical in real-world deployment. We therefore introduce AgentMeter, a quality-efficiency
benchmark with a new metric, the AgentMeter Score (AMS), that jointly characterizes task quality, budget sensitivity, and resource-intensive zero-reward execution, enabling a more complete assessment of deployed LM-CLI pairs. Furthermore, collected task descriptions may inadvertently favor LM-CLI pairs that are particularly compatible with their wording and structure, causing evaluation results to reflect description-specific advantages rather than general task-solving capability. We therefore propose AgentMeter-Opt, a trajectory-grounded optimization framework that constructs pair-adapted, task-preserving description variants to build a fairer evaluation set across LM-CLI pairs. Extensive experiments show that no CLI is universally optimal across
language models and that task success, execution cost, and AMS identify different competitive configurations. Results on AgentMeter-Opt further reveal that task-preserving description changes affect LM-CLI pairs unevenly and can alter their relative ordering across valid description conditions. Together, AgentMeter and AgentMeter-Opt provide a practical foundation for fair and deployment-relevant evaluation of command-line
agents.
Read the full abstract ▾
All authors Han Chi, Jiaxin Qi, Yan Cui, Baisheng Lai, Jianqiang Huang
Artificial Intelligence · Cross-listed from cs.RO
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Youngjoon Jeong, Jihwan Yu, Minsoo Jo et al. (+2 more)
Robot actions vary in both extent and mode: how much change they produce and what kind of change they produce. A latent action space that reflects this structure may make it easier for downstream policies to map latent actions to
robot actions. However, existing latent action methods typically rely on visual reconstruction from observation pairs without explicitly encouraging such structure. We introduce Polar Latent Actions with Radial structure (PoLAR), which imposes a radial-direction structure on latent actions, encouraging radius to encode transition extent and direction to retain transition mode. PoLAR uses temporal offsets between observations as a weak proxy for transition extent, encouraging transitions with larger offsets to occupy larger radii. We instantiate this structure in
hyperbolic space, whose expanding volume with radius offers a natural fit for more diverse transition modes at larger extents. Across in-task and large-scale pretraining settings, PoLAR improves downstream policy performance in simulation and real-world
robot experiments, outperforming latent action baselines and strong pretrained VLAs. These results suggest that structuring latent actions by extent and mode helps transfer visual pretraining to
robot policy learning.
Read the full abstract ▾
All authors Youngjoon Jeong, Jihwan Yu, Minsoo Jo, Junha Chun, Taesup Kim
Artificial Intelligence
Learning Burst-Aware Early Warning Models for Capacity Stress under AI Workload Surges in Hyperscale Data Centers
Zihan Yu, Xianling Zeng, Zhiming Xue et al. (+2 more)
The rapid growth of large-scale AI workloads, particularly Large
Language Model (LLM) training and inference, is fundamentally reshaping the operational dynamics of hyperscale data centers. Unlike traditional cloud workloads, AI-driven jobs exhibit bursty, high-intensity, and rapidly shifting resource demands, often leading to sudden capacity stress that cannot be effectively handled by reactive threshold-based mechanisms. In this paper, we propose a deployment-oriented, burst-aware early warning framework for proactive capacity stress prediction under AI workload surges. We formulate the problem as a high-recall
forecasting task over multivariate telemetry windows, with the explicit goal of enabling operational intervention before system degradation occurs. The proposed framework integrates workload intensity, temporal variation, and system pressure signals, and employs a lightweight tree-based learning model to capture nonlinear interactions in highly imbalanced environments. To evaluate the system under realistic conditions, we introduce an AI workload surge injection methodology that simulates burst-driven demand patterns observed in large-scale AI systems. Our XGBoost-based model achieves an ROC AUC of 0.697 and an AP of 0.670, significantly outperforming baseline methods. Under deployment-oriented threshold selection, the framework achieves a Recall of 0.914, enabling the detection of the majority of stress-prone periods with acceptable false-alarm cost. Beyond predictive performance, we show how the proposed framework can be integrated into operational control loops to support proactive actions such as workload throttling and resource scaling. Our results highlight the practical value of high-recall, learning-based early warning systems in enabling resilient and adaptive data center operations in the era of AI-driven workloads.
Read the full abstract ▾
All authors Zihan Yu, Xianling Zeng, Zhiming Xue, Yalun Qi, Sichen Zhao
Artificial Intelligence
PulseCX: Breaking the Closed-World Assumption in Real-Time CX
Rajat Agarwal, Suvidha Tripathi and Shubham Sharma
Conversational AI
agents in Customer Experience (CX) typically suffer from a Closed-World Constraint, ignoring high-velocity external shifts like viral trends or outages. Ad-hoc web search attempts to bridge this gap but often introduce prohibitive latency and context poisoning. We introduce PulseCX, a framework that decouples knowledge acquisition from consumption. Adopting a structure-first paradigm, PulseCX employs an asynchronous
agent to linearize signals into a Decay-Aware Temporal Knowledge Graph (DA-TKG) governed by reinforcement–decay dynamics to actively manage information lifecycles. By coupling this self-evolving
memory with hierarchical intent gating, PulseCX removes synchronous search bottlenecks (<10ms overhead) and drives significant gains in Intent Resolution (IRR) and Customer Satisfaction (s-CSAT) in dynamic environments.
Read the full abstract ▾