Computation and Language
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Shengfang Zhai, Leo Marchyok, Yuling Shi et al. (+4 more)
Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the
privacy risks of DLMs remain underexplored. We identify a phenomenon termed
token-level memorization asymmetry through theoretical analysis of
diffusion training dynamics. Building on this finding, we propose Q-Skew, a
quantile-weighted skewness-based indicator for membership inference on finetuned DLMs. Experiments across multiple fine-tuning
datasets and models show that our method outperforms existing baselines. Moreover, we show that Q-Skew can also facilitate other
privacy violations, such as PII extraction. Our findings reveal a previously underexplored
privacy attack surface and highlight the need for systematic
privacy evaluation of DLMs.
Read the full abstract ▾
All authors Shengfang Zhai, Leo Marchyok, Yuling Shi, Huanran Chen, Yinpeng Dong, Jiaheng Zhang, Sanghyun Hong
Machine Learning · Cross-listed from math.AP
Sharp Mixed Spectral Barron Regularity of Coulombic Many-Electron Wave Functions
Pingbing Ming and Hao Yu
We establish sharp mixed spectral Barron regularity for eigenfunctions of molecular Coulomb
Hamiltonians. The mixed norm is a
Fourier $L^1$ norm with one isotropic weight and coordinate-product weights, and therefore detects regularity invisible to the isotropic Barron scale. For a nonempty set $I$ of electron indices on which the wave function is antisymmetric, we derive an explicit admissible region for the isotropic order $s$ and the coordinate orders $\alpha,\beta$. This region is optimal as a uniform statement over the class of clamped-
nuclei Coulomb
Hamiltonians. For fixed-
spin components with two occupied
spin blocks, it reduces to $s+\alpha+\beta<1$; in the fully
spin-polarized class it reduces to $s+\alpha<1$. In particular, if $\mathcal I_\sigma$ denotes the family of occupied same-
spin blocks determined by $\sigma$, then every fixed-
spin spatial component $\psi_\sigma$ satisfies, for every $0\leq\alpha<1$, \[ \left(\sum_{I\in\mathcal I_\sigma}\prod_{i\in I}\langle\xi_i\rangle^\alpha\right)\widehat{\psi_\sigma}\in L^1(\mathbb{R}^{3N}). \] For a fully
spin-polarized state, $\mathcal I_\sigma=\{\{1,\ldots,N\}\}$.
Read the full abstract ▾
Formal Languages and Automata
Construction of a DFA for Computing Grundy Numbers in the Successful Derivation Games on Right-Linear Grammars
Yoshiaki Takata, Yusuke Inoue and Hiroyuki Seki
Inoue et al. have introduced the successful derivation game (SDG) on context-free grammars (CFGs), which is a generalization of classic heap-based games including subtraction games and Keyles, and shown that the least upper bound of the Grundy numbers in the SDG on a given CFG G is undecidable in general even when we restrict G to be a linear CFG. This paper shows that for the SDG on a right-linear grammar (RLG), we can construct a DFA for computing the Grundy number of a given position. In other words, for the SDG on an RLG, the set of positions with a given Grundy number c is regular. As a corollary, the least upper bound of the Grundy numbers in the SDG on a given RLG is decidable. We also investigate the complexity of computing the least upper bound of the Grundy numbers in the SDG on a given RLG, and it is shown to be PSPACE-complete.
Read the full abstract ▾
Computer Vision · Cross-listed from math.OC
Stochastic Optimization of Tree Tensor Networks
Marius Willner, Maximilian Scharf, André Uschmajew et al. (+2 more)
Tensor networks, originally developed for
quantum many-body physics, are promising models for machine learning. We derive
stochastic Riemannian optimizers for tree tensor networks (TTNs) on both their parameter and quotient
manifolds, including adaptive and learning-rate-free schemes suitable for minibatch training. Using a hybrid CNN-TTN architecture, we evaluate the methods on Fashion-MNIST, CIFAR10, and Imagenette. The proposed optimizers achieve predictive performance comparable to unconstrained optimization while enabling numerically stable downstream compression.
Read the full abstract ▾
All authors Marius Willner, Maximilian Scharf, André Uschmajew, Timo Felser, Marco Trenti
Computer Vision
The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence
Genpei Zhang
Vision-
language models are evaluated by aggregate accuracy on
multimodal benchmarks, a practice that implicitly assumes the model uses its visual input. We show this assumption fails on 40%–97% of samples across six VLMs and three perceptual
benchmarks: blurring the question-relevant visual region leaves the next-
token distribution nearly unchanged. We name this phenomenon the Visual Insensitivity Gap and quantify it with a per-sample Visual Sensitivity Index (VSI). The gap is a property of samples, not of models: VSI ranks correlate across models (grand-mean Spearman rho=+0.40, permutation p<10^-3), so the same samples are flagged insensitive by VLMs sharing no architectural detail beyond a contrastively pretrained
vision tower. The mechanism is concrete: on the insensitive samples, a linear probe on each model's own
vision tower distinguishes perturbed from clean images at 0.72–0.79 accuracy, yet the model's argmax
token changes on only 2%–11% of the same samples, an encoder–LLM gap above 0.65 on every model. Mapping VSI's diagnostic utility
cell by
cell surfaces a strong regime (multi-choice
reasoning on capable VLMs: AUROC=0.85–0.87) and a weak regime (well-calibrated factuality, where softmax confidence already leads). VSI is not a universal best abstention signal; it is a sample-intrinsic indicator of
vision-ignoring failure, best used as a conditional ensemble component.
Read the full abstract ▾
Computer Vision
Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation
Yumi Lee, Harim Oh, Hyoryung Kim et al. (+52 more)
The rapid advancement of
vision-
language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pathology report generation remains limited by the scarcity of large-scale WSI–report
datasets and the complexity of mapping spatially distributed visual patterns to structured clinical text. To address this, we introduce a clinically curated Pan-Asia WSI–report
dataset of approximately 10,500 pairs from five institutions and establish the REG 2025
benchmark through a MICCAI challenge for systematic evaluation of
multimodal models. We analyze submitted methods spanning pretrained VLMs, multiple-instance learning frameworks, hierarchical expert models,
retrieval-augmented generation, and cross-modal
Transformers. Rather than indicating that VLM use alone was sufficient for superior performance, the results suggest that top-performing methods benefited from structured report representations, hierarchical diagnostic decomposition, and effective
multimodal grounding. We identify key limitations, including instability in quantitative attribute estimation (e.g., numeric
hallucination) and a tendency toward diagnostic overspecification, with some errors resembling known diagnostic pitfalls in routine pathology. These findings establish REG 2025 as a
benchmark for evaluating WSI-based structured report generation and
vision-
language understanding in computational pathology, providing insights for the design of clinically grounded
multimodal pathology models.
Read the full abstract ▾
All authors Yumi Lee, Harim Oh, Hyoryung Kim, Minji Kim, Eunsu Kim, Hyeseong Lee, Junya Fukuoka, Andrey Bychkov, Jijgee Munkhdelger, Rajiv Kumar Kaushal, Ayushi Sahay, Rajni Yadav, Bharathi Prabakaran, Sulen Sarioglu, Serdar Balc{\i}, Ilknur Turkmen, Yuri Tolkach, Christian Harder, Julian Westerdorf, Reinhard Buettner, Audun Ljone Henriksen, Sepp De Raedt, Byung Hyun Lee, Sungjin Lim, Joohoon Lee, Gwanghyun Kim, Se Young Chun, Suryakant Singh, Saarthak Kapse, Prateek Prasanna, Kyung A Kim, Yousun Kang, Sehwan Yoo, Sungman Hong, Shubham Innani, Michael Feldman, Spyridon Bakas, Ujjwal Baid, Prasad Dutande, Suhas Gajare, Bhakti Baheti, Serkan Sökmen, Ece Tuğba Cebeci, Ahmet Hal{\i}c{\i}, Musa Balc{\i}, Kardelen Peçenek, Srividhya Sainath, Kyongseok Jang, Messi H.J. Lee, Noorul Wahab, Bodong Du, Jiaming Zhang, Qixiang Zhang, Jang-Hwan Choi, Sangjeong Ahn
Machine Learning
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Zinco J, Xunjie Zhu, Shen Huang et al. (+3 more)
Production
agent harnesses such as Claude Code and Qwen-
Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain the rightmost path, causing time-travel leakage, or replay a depth-first traversal, causing train-inference mismatch. We introduce two exact, gradient-equivalent corrections: LogitTree, a segmented K-forward traversal, and a packed 4D
attention mask. LogitTree requires K+1 backward passes; the 4D mask requires a custom kernel and white-box eviction records. We also propose SDCC (Self-
Distillation for Conditioning Consistency), a single-backward-pass variational relaxation. At each eviction, it minimizes forward KL between the compressed student and a stop-gradient teacher on the reconstructed pre-eviction prefix. A residual per-junction KL of epsilon_KL gives an O(sqrt(epsilon_KL)) bound on the train-deployment total-variation gap. SDCC also applies to black-box harnesses. On seven web-search
benchmarks with TC-RAG, AgentFold, MemexRL, Claude Code, and OpenCode, naive training inflates the train-rollout log-probability gap, especially on eviction-heavy batches. The exact methods stay at the no-compression floor, and SDCC substantially closes the gap, with lower logit drift and higher rollout rewards.
Read the full abstract ▾
All authors Zinco J, Xunjie Zhu, Shen Huang, Zhenyi Wang, Pengjun Xie, Jieping Ye
Machine Learning
Conditional Flow Matching for ML-Based Inverse Design Problems
Juliana Felder, Milad Habibi, Soheyl Massoudi et al. (+1 more)
Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generative models can produce candidate designs without rerunning the simulator at inference time. Generative
adversarial networks (GANs) sample in one forward pass, whereas
diffusion models require iterative reverse-time integration. In this work, we add conditional flow matching (CFM) to EngiOpt and compare it with a conditional
diffusion model and a conditional generative
adversarial network (cGAN) on structural (beams2d) and thermal (heatconduction2d)
benchmarks from EngiBench using the same downstream optimization protocol. We use cumulative optimality gap (COG) and final optimality gap (FOG) as the primary metrics for evaluating the generated designs as warm starts for gradient-based refinement. On the evaluated EngiOpt implementations and two EngiBench tasks, CFM achieves the lowest measured COG, FOG, maximum mean discrepancy (MMD), and volume-fraction deviation on both tasks. CFM has mean volume-fraction deviations of 0.4% and 1.0% on beams2d and heatconduction2d, respectively, compared with 3.8% and 11.2% for
diffusion. At Euler s = 16, CFM achieves 53.2 samples/s on beams2d, about 66 times the measured throughput of the evaluated
diffusion baseline using 1000 network evaluations under the same timing protocol, with COG 1.182 +/- 3.126, compared with 1.173 +/- 3.100 for Euler s = 32. Across the two tasks, CFM produces warm starts with lower measured COG than both baselines and uses fewer network evaluations than
diffusion.
Read the full abstract ▾
All authors Juliana Felder, Milad Habibi, Soheyl Massoudi, Mark Fuge
Computer Vision
Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model
Zhenhuan Wang and Fengyi Yuan
We show that a frozen generic text-to-image
diffusion model can perform conditional inpainting across three evaluated natural-image domains with one fixed controller configuration, without inpainting-specific weight training,
dataset-specific weight adaptation, or learned inpainting-specific conditioning channels. Step-PI augments known-region projection with boundary-interior latent feedback, persistent PI state, and a predefined four-field release schedule that modulates controller signals along the reverse trajectory. Developed only on Main35-disjoint CelebA-HQ pilots, the controller transfers unchanged to AFHQ and Places2. Across two field-identical comparisons on the same 3,500 cases, adding persistent state and replacing uniform release with the predefined schedule each improve all 15
dataset-metric
cells; 95% bootstrap intervals exclude zero for all five metrics in both comparisons. In descriptive native-route comparisons, Step-PI leads LanPaint and PILOT (the closest evaluated training-free baselines using vanilla SD1.5) on all five equal-
dataset macro metrics. Inpainting-trained systems retain the absolute metric leads but rely on substantial inpainting-specific offline optimization. Our method provides a complementary approach for repurposing a frozen generic text-to-image model for cross-domain inpainting through test-time latent control.
Read the full abstract ▾
Artificial Intelligence
Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems
Yi Chen, Zikang Yu, Jiahai Wang et al. (+3 more)
Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced optimization solvers can effectively solve such problems. However, modeling complex VRP variants for solvers often requires substantial domain expertise, which limits the accessibility of advanced optimization technologies. In this paper, we propose Reinforcement Learning Enhanced LLMAgents(RLEA), a multi-
agent framework designed to automate the modeling of complex VRPs. RLEA introduces a lightweight neural Planner trained with Soft Q-learning to efficiently orchestrate the actions of LLM-based
agents. In addition, we equip the system with an evolutionary
memory module and
retrieval-augmented generation, enabling the
agent to leverage both accumulated experience and external solver knowledge during program generation and refinement for solving VRPs. We evaluated 48 distinct VRP variants across various solvers. The experimental results demonstrate that RLEA outperforms the previous state-of-the-ar method, achieving a 16.67% higher success rate while significantly reducing runtime errors. These results validate that integrating reinforcement learning with LLM-based
reasoning is highly effective for automated optimization modeling. The appendix is available at: https://doi.org/10.5281/zenodo.19134435.
Read the full abstract ▾
All authors Yi Chen, Zikang Yu, Jiahai Wang, Jinbiao Chen, Jianpeng Zhou, Zizhen Zhang
Artificial Intelligence
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
Ivan Decostanzi, Michele Ronco, Sergio Consoli et al. (+8 more)
Effective humanitarian response depends on the rapid synthesis of heterogeneous, high-volume information sources - a task that routinely exceeds human analytical capacity in the critical early hours of a crisis. We present a pipeline that combines structured disaster records from EM-DAT with unstructured documents from ReliefWeb and the European Media Monitor (EMM) to produce source-grounded disaster storylines and causal knowledge graphs supporting situational awareness for responders and analysts. Using
Retrieval-Augmented Generation, the pipeline extracts structured storylines - tabular event profiles covering 17 fields, from severity and key drivers to child-sensitive impact indicators - and constructs causal knowledge graphs where each node and edge is enriched with citation-grounded explanatory narratives, enabling full traceability back to primary sources. We evaluate the system on three diverse crisis use cases through a human evaluation involving 9 domain expert and 9 non-expert evaluators. Results confirm high
retrieval precision, strong faithfulness of extracted causal relations, and a clear expert preference for citation-grounded components over ungrounded alternatives. The pipeline is designed to scale to the full EM-DAT catalogue, with the goal of publicly releasing a new collection of disaster stories complementing the EM-DAT database.
Read the full abstract ▾
All authors Ivan Decostanzi, Michele Ronco, Sergio Consoli, Christina Corbane, Lorenzo Bertolini, Indaco Biazzo, Daria Mihaila, Manuel Garcia-Herranz, Felix Schwebel, Yelena Mejova, Kyriaki Kalimeri
Hardware Architecture
LLM Inference on IMC-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism
Yimin Wang, Yue Jiet Chong and Xuanyao Fong
LLM inference has become an essential service, yet it imposes unprecedented demands on
memory bandwidth, computational density, and communication efficiency. While IMC is a promising solution to the
memory wall issue, the heterogeneous data dynamicity of LLM requires complementary resources to handle intermediate data generated during run-time. Furthermore, the massive number of parameters in LLM necessitates scale-up architectures where on-chip data movement is often the primary performance bottleneck. This article presents a hardware-software co-design framework that unifies distributed compute,
memory, and communication into a seamless processing-communication fabric. On the hardware side, we propose a scalable architecture, named LEAP, that integrates IMC PE, NMC PE, and INC. This allows each hardware layer to execute specialized tasks: IMC for static weights, NMC for dynamic data, and INC for partial result reduction. On the software side, we introduce a partitioning, mapping, and scheduling framework optimized for key metrics in LLM serving, including throughput and latency. To address the distinct computational intensities of the prefill and decode phases, we present a prefill-decode disaggregation approach that dynamically reconfigures PE organizations to maximize resource utilization. Compared to commercial GPU platforms, the proposed architecture provides a throughput and an energy efficiency improvement of $\geq{}1.52\times$ and $24.91\times$, respectively.
Read the full abstract ▾
Software Engineering
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
Anik Jha
Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is small, and a second model call may succeed without using the failure at all. We separate these explanations with three arms applied to the same failed candidate: blind whole-solution resampling, spectrum-based localization followed by suspect-span infilling, and same-length infilling at a disjoint random code span. Across three frozen 26-32B models, three
benchmarks and 488 failing candidates, plus a separately declared 24B fourth model from a third family, three results follow. First, localization is rarely available: only 9.0% of failing candidates expose a failing public test with a usable spectrum. Second, among the 177 candidates localizable from a strong suite, localized infilling loses decisively to blind resampling at a matched attempt count (3:40, p = 3.0 x 10^-9), opposite to our hypothesis; the loss replicates in a third family at -11.3 points (95% CI [-16.6, -6.8]), and widening the edit does not rescue it. Third, against the random-span placebo localized infilling leads pooled (11:1, Holm-adjusted p = .019), but that lead resolves in no individual model under the analysis our shipped plan designates primary (best Holm p = .087), so we report the location effect as suggestive rather than established. Re-pricing attempts as
tokens narrows but does not overturn this: a span attempt spends 21.7 generated
tokens against 371.1, yet 16 localized attempts reach 6.8% while one blind attempt already reaches 10.1%. Infilling reproduces the removed span verbatim in 48.9% of attempts, which is why more budget does not help. We restrict every localization conclusion to the 24-32B models tested.
Read the full abstract ▾
Computer Vision
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
Tongtong Wang, Mingzhu Xu, Chenglong Yu et al. (+3 more)
InfRared Small Target Detection (IRSTD) is a challenging task. Relying solely on pixel-level information,
vision-only methods struggle to distinguish targets from clutter. Current
multimodal methods typically describe both targets and backgrounds with a single textual
prompt. Such an approach lacks dedicated regional guidance and ignores infrared semantic asymmetry. Consequently, it provides insufficient background suppression information and introduces severe feature optimization conflicts, overwhelming small targets with noise. To address these issues, we propose a novel Asymmetric Dual-text Guided Network (ADGNet). Specifically, accounting for the infrared semantic asymmetry, we first design the Asymmetric Dual-text
Prompt (ADP), comprising an image-agnostic abstract target
prompt and an image-specific detailed background
prompt. To leverage these
prompts, we introduce an Asymmetric Dual-Branch Interaction (ADBI) module to separately guide visual features with their respective text priors, protecting targets from noise while suppressing background clutter. Subsequently, we introduce an Adaptive Feature Aggregation (AFA) module to dynamically fuse features from the two branches. Furthermore, we construct a
multimodal Asymmetric Image-Text Infrared (AITIR)
dataset by providing asymmetric text annotations for three public
datasets (IRSTD-1K, NUDT-SIRST, and SIRST). Extensive experiments demonstrate that ADGNet outperforms 21 state-of-the-art (SOTA) methods. Code is available at https://github.com/iLearn-Lab/MM26-ADGNet.
Read the full abstract ▾
All authors Tongtong Wang, Mingzhu Xu, Chenglong Yu, Jing Wang, Xiaohui Lin, Weili Guan
Numerical Analysis · Cross-listed from physics.flu-dyn
Assessment of Numerical Lift Coefficient Data for a Circular Cylinder with Application to Bladeless Turbines
L. Ridgway Scott and Henry von Wahl
We assess computed lift coefficient data for flow past a circular cylinder to evaluate their suitability for practical applications. Specifically, we consider lift coefficient data for a circular cylinder over Reynolds numbers from 120 to 8000. The results are obtained from two-dimensional finite element simulations of the incompressible Navier-Stokes equations using pressure robust discretizations. We compare the computed lift coefficients with published experimental and numerical results, finding good agreement in some cases but significant disagreement in others. Because lift fluctuations are central to
vortex-induced vibration concepts, these data therefore provide input for the analysis and preliminary design of bladeless turbines.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.ao-ph
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño et al. (+5 more)
As machine learning and artificial intelligence find their way into nearly every aspect of
climate, weather, and Earth system modeling, it is worth pausing to consider what our design decisions imply for the science and for the computational resources we consume. A growing body of literature addresses the ethical and sustainable development of ML/AI, yet translating these principles into day-to-day research practice remains a challenge as most of best practices are dispersed across multiple studies and commentaries. Here, we distill these discussions into a practical checklist that ML/AI and Earth system science practitioners can use to assess and reduce the environmental footprint of their own applications, organised around the successive stages of the model development pipeline. We complement the checklist with a selection of metrics drawn from the literature for estimating the energy consumption and carbon footprint of a project. For each question, we point to concrete examples and actionable suggestions from recent literature, aiming to bridge the gap between aspirational principles and the decisions researchers face at every stage of the development cycle.
Read the full abstract ▾
All authors Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño, Aina Gaya i Àvila, Lluís Palma Garcia, Alessio Melli, Oscar Dimdore Miles, Amanda Duarte
Computer Vision
An Intelligent Decision Support System for Emotion Monitoring using Microscopic Fixational Dynamics
Xiangyu Shen, Feiyang Deng, Zijian Dai et al. (+4 more)
The rising prevalence of psychological disorders necessitates effective
emotion monitoring, yet current methods relying on facial or physiological signals often suffer from intrusiveness and
privacy issues. This paper proposes an intelligent decision support system and pervasive edge-computing framework that leverages smart glasses and a companion smartphone to infer emotional states from microscopic visual fixation patterns. Moving beyond traditional macroscopic gaze metrics, the proposed system extracts and decomposes three distinct neurophysiological micro-movements: microsaccades, ocular drifts, and ocular microtremors. We introduce an interpretable hybrid artificial intelligence pipeline combining a multi-head
attention mechanism, extreme gradient boosting, and a support vector machine to extract deep temporal features, quantify their physiological importance, and perform efficient on-device classification. Through an extensive evaluation involving 60 volunteers, we rigorously validate the framework under a strict leave-one-subject-out cross-validation protocol across both controlled and naturalistic mobile scenarios. Ablation studies unequivocally demonstrate that these fixational micro-movements are substantially more discriminative for
emotion inference than traditional macroscopic features. Furthermore, aligned with contemporary affective science, the system incorporates a few-shot personalization mechanism to bridge universal physiological baselines with individual emotional heterogeneity, achieving a highly robust personalized F1-score of 83.6%. This work establishes a physiologically interpretable, unobtrusive, and deployable paradigm for continuous real-time
emotion monitoring.
Read the full abstract ▾
All authors Xiangyu Shen, Feiyang Deng, Zijian Dai, Aibin Chen, Jizheng Yi, Jie Li, Hongbo Jiang
Artificial Intelligence
Towards Generalizable Visually Grounded Exploration of Household Devices
Linhao Zheng, Zeming Liu, Wangke Chen et al. (+4 more)
Recent advancements in
Vision-
Language Models (VLMs) have demonstrated impressive capabilities in static visual recognition and high-level semantic
reasoning. However, current
embodied exploration paradigms still heavily rely on imitation learning from human-annotated trajectories, which severely limits
agents' generalization ability. The key bottleneck of realizing general autonomous
embodied agents lies in Generalizable Visually Grounded Exploration: the ability to operate novel devices without manuals or specific training by actively grounding abstract world knowledge into fine-grained visual affordances. Yet, existing
benchmarks fail to evaluate this capability: they generally rely on explicit documents and annotated trajectories, neglecting the dynamic Hypothesis-Interaction-Refinement process essential for functional device operation. To bridge this gap, we introduce VGEBench, a comprehensive
benchmark designed to evaluate the generalizable visually grounded exploration capabilities of VLMs. Unlike static
datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling
agents to achieve goals by active visual perception and feedback-driven correction. Experimental results demonstrate that existing VLMs face significant challenges in translating semantic knowledge into physical execution and maintaining long-horizon state tracking.
Read the full abstract ▾
All authors Linhao Zheng, Zeming Liu, Wangke Chen, Li Zeng, Wanxiang Che, Heyan Huang, Yuhang Guo
Computation and Language
Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
Hyeonseop Yoon and Jeong-Eun Park
Customer-service QA in an AI contact center (AICC) runs under deployment constraints that
benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed set of verified QA units: it returns a retrieved unit verbatim, or routes to clarify, abstain, or handoff. The index is enriched offline by staged linguistic seeding (SLS): a human authors a per-unit world-grounded slot recipe, gpt-4.1-mini renders it into variants, and a light human gate filters them. One methodology is reused across both domains, so inference stays a single
retrieval pass with no query-time generation. On held-out query variants from two industrial domains, SLS lifts hybrid R@1 to 0.881/0.930 (+0.27/+0.34), with gains across all five retrievers tested. At the same gpt-4.1-mini generation budget, SLS beats doc2query by +0.20/+0.32, while cross-provenance evaluation provides additional evidence of transfer across generated-query distributions. Verified-unit answering also removes free-form generation's unsupported-content surface (7-13% versus approximately 0%). We report this as an application study, including negative results.
Read the full abstract ▾
Distributed Computing
Shared-Memory Range-Tiled CDF Sort for Small-Range Integer Keys on GPUs
Kento Ando, Kaito Takase, Noriyuki Fujimoto et al. (+1 more)
We study unstable integer sorting on GPUs for arrays whose elements lie in a known integer range. Focusing on counting-sort-based methods that determine the output interval of each value from its frequency and the prefix sums of the frequencies, we propose and evaluate Range-Tiled CDF sort (RT-CDF), which partitions the possible value range into small intervals, called tiles, that fit in shared
memory. For each tile, RT-CDF constructs a histogram, computes its prefix sum as a local CDF, and directly generates the output array from the local CDF. We compare RT-CDF against three baselines: CUB DeviceRadixSort, whose processed bit range is restricted to $[0,\lceil\log_2 R\rceil)$ to exploit the known range size $R$; Ref-H-P sort; and an implementation based on the
algorithm of Kolonias et al. Experiments on an NVIDIA GeForce RTX 4090 with range sizes from $R=2^7$ to $2^{18}$, input sizes from $n=10^6$ to $10^9$, and uniformly distributed, normally distributed, and all-equal inputs show that RT-CDF outperforms the baselines over a broad set of conditions for small to medium ranges, achieving a maximum speedup of 4.39 over the fastest baseline. For $R=2^{18}$, however, at least one baseline outperforms RT-CDF for every evaluated input size and input distribution, showing that the cost of histogram construction limits the applicability of RT-CDF to larger ranges.
Read the full abstract ▾
All authors Kento Ando, Kaito Takase, Noriyuki Fujimoto, Koichi Wada
Computer Vision
Residual Kalman Dynamics for Event-Based UAV Forecasting
Per Nyblom, Hannes Ovrén and David Gustafsson
We study short- and mid-horizon
UAV bounding-box
forecasting on the FRED event-camera
dataset. We use a constant-velocity Kalman filter over a full center-size box state as a strong physical baseline, and train a residual model to predict acceleration-like corrections from recent box history, filtered state features, and local event representations. This simple residual formulation consistently improves over the Kalman baseline, with event-conditioned models giving the strongest results among the evaluated methods. We further show that part of the residual target is predictable from anchor position and velocity alone, indicating that canonical FRED results can reflect both visual evidence and
dataset-specific motion priors. To analyze this effect, we introduce decorrelated subsets as a diagnostic stress test, showing that event-conditioned residual models retain useful predictive signal even when measured position- and velocity-based shortcuts are weakened.
Read the full abstract ▾
Software Engineering
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross and Arnaud Gotlieb
Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under test (SUT) places on constraint-violating alternatives that are reachable under sampling and what fraction of the input population satisfies a domain requirement. We answer both with probabilistic model checking. The pipeline extracts a discrete-time Markov chain (DTMC) from the SUT's
token-by-
token generation, verifies formal PCTL specifications with the PRISM model checker, and aggregates the per-input verdicts into a coverage curve over the input space. A soundness
theorem establishes the DTMC as an under-approximation, so every verdict yields a certified interval on the SUT's true reachability probability. The coverage built from those verdicts is, therefore, conservative by construction. A counterexample-guided abstraction refinement (CEGAR) loop adaptively tightens the interval, and a maximum-likelihood
algorithm extracts the most probable falsifying trace. Two case studies exercise the pipeline. On a GPT-2 computer-aided process-planning (CAPP) model with 100% test accuracy, the pipeline quantifies the probability mass greedy decoding hides, but that is reachable with sampling; and identifies the smallest training fraction at which an ordering requirement holds population-wide, neither of which test accuracy can report. We then verify the SMILES molecular generator with a 50x larger vocabulary. The only change is an external chemical-validity oracle, and the pipeline identifies the gap between structural completeness and chemical validity.
Read the full abstract ▾
Distributed Computing
Breaking Cycles for Scalable Fair Ordering in Blockchain Systems
Jinchun He, Wangjie Qiu, Yizhong Liu et al. (+2 more)
In blockchain systems, transaction order directly determines financial outcomes: unfair ordering enables front-running and sandwich attacks that have extracted over \$686M from Ethereum users. Current fair-ordering protocols aggregate pairwise receive-order evidence from replicas. Under contention or adversarial manipulation, however, Condorcet cycles force them into global strongly connected component (SCC) condensation, causing delays, coarse batches, and scaling failures. We present FlashOrder, a deterministic fair-ordering engine that localizes cyclic ambiguity before it propagates across the batch. FlashOrder embeds pairwise preferences into one-dimensional canonical positions, clusters nearby transactions with a partition hypergraph, and performs hierarchical inter- and intra-cluster serialization, replacing batch-wide SCC condensation with localized sorting and aggregation. Evaluated against Themis (CCS '23) and Rashnu (VLDB '24) on a libhotstuff-based prototype, FlashOrder achieves up to 10.5$\times$ higher throughput than Themis and 4.8$\times$ higher than Rashnu, with the latency gap widening as network scales. In controlled adversarial simulation, it reduces maximum rank displacement by 88.7\%, and under Condorcet attacks it sustains 12.0$\times$ and 9.7$\times$ higher throughput than Themis and Rashnu on average. These results show that localizing cyclic ambiguity yields stronger
fairness at substantially higher throughput.
Read the full abstract ▾
All authors Jinchun He, Wangjie Qiu, Yizhong Liu, Shengda Zhuo, Kwok-Yan Lam
Software Engineering
Replacing Training with Memory: Listwise Selection for Text-to-SQL
Yeonseok Jeong, Soyoung Yoon, Seongjun Lee et al. (+1 more)
Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tuning-free listwise selector. We replace two major fine-tuning objectives with inference-time strategies: (1) learning selection criteria as ordering and (2) mitigating positional bias. First, we build reusable structured
memories instead of learning selection behavior as model parameters. Given a question, MaP-SQL retrieves
memories distilled from training data that encode how natural
language maps to schema elements, SQL operations, and expected outputs. These
memories serve as explicit decision criteria for evaluating candidates in a listwise manner. Second, to mitigate ordering bias of listwise selectors, we aggregate rankings across multiple input permutations, with inference cost optimized by execution results and pointwise scoring. Our approach improves selection accuracy while maintaining efficiency and compatibility with existing large
language models. Across Text-to-SQL
benchmarks, it produces more stable selection without fine-tuning and fewer unnecessary comparisons than existing methods. On BIRD-dev, it outperforms the previous state-of-the-art selector-based method R^3-SQL by 2.02 execution accuracy points on average using the same candidate sets, with 2.92x fewer
tokens.
Read the full abstract ▾
All authors Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang
Computation and Language
Dense Process Supervision for Search Agents via Fact Utility Estimation
Rongzhi Zhu, Xiangyu Liu, Yi Liu et al. (+7 more)
Reinforcement learning (RL) for search
agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the
reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using
Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA
benchmarks show that our method consistently outperforms existing baselines. Ablation studies validate clear relative improvements on multi-hop QA compared to outcome reward-only training.
Read the full abstract ▾
All authors Rongzhi Zhu, Xiangyu Liu, Yi Liu, Shuo Zhang, Ruirui Zhang, Rui Wu, Tao Jiang, Zequn Sun, Wenhao Xu, Wei Hu
Computation and Language
TWIX: a Two-Stage Approach for End-To-End Named Entity Recognition and Relation Extraction
Marco Martinelli and Laura Menotti
The exponential growth of scientific publications calls for automatic Information Extraction (IE) systems to support knowledge discovery. In this context, the GutBrainIE
benchmark evaluates Named Entity Recognition (NER), Named Entity Recognition and Disambiguation (NERD), and Relation Extraction (RE) systems in the gut-
brain axis domain. We propose Two-stage Workflow for Information eXtraction (TWIX), an end-to-end IE pipeline featuring three interconnected modules, each leveraging a two-stage framework to solve all four GutBrainIE subtasks. Evaluation on the development and test sets shows that our method substantially outperforms the baseline by a wide margin, while also ranking first among all participant submissions across all subtasks. These results indicate that the proposed two-stage pipeline effectively improves both precision and recall in practical settings.
Read the full abstract ▾
Artificial Intelligence
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
Kewei Li, Rongying Zhang, Xueli Wang et al. (+6 more)
Token aggregation converts
token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original
token space. We introduce Frequency-Domain Latent-
attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the
Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral
tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated
token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based
language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven
language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-
attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across
protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.
Read the full abstract ▾
All authors Kewei Li, Rongying Zhang, Xueli Wang, Xiwen Gong, Zhongjian Wang, Qiuchen Zhao, Lan Huang, Ruochi Zhang, Fengfeng Zhou
Computer Vision
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
Xurui Song, Weishi Wang, Zhongqi Yue et al. (+5 more)
Whether
attention weights faithfully reflect model
reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in
Vision-
Language Models (VLMs). We address this gap through causal perturbation analysis on current VLMs, evaluating both the comprehensiveness and sufficiency gap of
attention-ranked visual
tokens. Our analysis reveals that visual
attention faithfulness is heterogeneous, manifesting in three distinct processing modes: Faithful-Sufficient, where top-$k$
attention tokens are both necessary and sufficient for prediction; Faithful-Distributed, where they are necessary but broader visual context remains required; and Non-Focal, where no localized
attention region is individually necessary while visual information remains an essential trigger for prediction. Furthermore, human-annotated ground-truth regions satisfy comprehensiveness in only $\sim 60$% of cases compared with model
attention rankings, revealing systematic divergence between model visual reliance and human intuition. We demonstrate these patterns across both general VQA on VQAv2 and document tasks on VRDU and ChartQA, showing that visual
attention faithfulness varies systematically with processing demands and model architectures rather than being uniformly faithful or unfaithful.
Read the full abstract ▾
All authors Xurui Song, Weishi Wang, Zhongqi Yue, Kuluhan Binici, Tao Bai, Hongxin Shao, Daniel Dahlmeier, Jun Luo
Machine Learning
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian et al. (+6 more)
Self-evolving
agents advance toward autonomy by optimizing their harness—
prompts, skills, tools, and execution logic—based on environmental feedback. This paradigm, however, is hampered by three challenges: credit assignment failure, where terminal success/failure feedback makes it ambiguous which step caused the error; shortcut learning, where
agents memorize task-specific patterns rather than acquire generalizable capabilities; and catastrophic forgetting, where unguarded updates degrade previously acquired competence. In this paper, we introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable
agent self-
evolution. HarnessEvolve decouples the execution
agent from the evolutionary pipeline, assigning execution, evaluation, optimization, and gating to independent
agent modules, enabling generalizable and stable harness improvements. Specifically, HarnessEvolve overcomes credit assignment failure by generating reference trajectories (execution paths produced when given the ground-truth answers) and aligning failed executions against them to extract error signals, which are clustered to reveal systematic failure patterns. To prevent shortcut learning and catastrophic forgetting, candidate harness updates must pass two gates: a quality gate that filters data leakage and
prompt bloat, and a performance gate that accepts each update if it improves on the current batch without degrading recent batches, with epoch-end validation on a held-out set selecting the best-performing accepted
agent snapshot. We conduct extensive experiments on several
benchmarks spanning open-domain and enterprise scenarios, using different models and
agent frameworks. Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all
benchmarks and settings, confirming reliability across task domains.
Read the full abstract ▾
All authors Wen Jiang, Mingmin Chu, Yimeng Tian, Qianxin Zhang, Haofei Yang, Rui Yang, Yang Liu, Tao Lv, Fangming Li
Systems and Control
Low-Complexity Control Under Input Saturation and Performance Constraints: A Bidirectional Modification Scheme
Jinyu Ni, Xiucai Huang, George A. Rovithakis et al. (+1 more)
This article addresses the output tracking control problem for a class of high-order uncertain highly-coupled
MIMO nonlinear systems subject to input saturation and performance constraints. To resolve the problem, a bidirectional modification mechanism is constructed, which is able to not only relax the constraints when saturation occurs to alleviate potential conflict, but also accelerate the recovery of original constraints after saturation ceases, and further tighten the constraints to enhance control performance if saturation remains inactive at the steadystate phase. Based on the mechanism, a model-, approximationand complexity-explosion-free control scheme is proposed. To bypass the obstacle in Lyapunov analysis, a novel stability analysis framework is developed, which, given that two parameter selection conditions are met, ensures satisfaction of modified constraints and boundedness of all closed-loop signals. Simulation results validate the effectiveness and superiority of the methodology.
Read the full abstract ▾
All authors Jinyu Ni, Xiucai Huang, George A. Rovithakis, Yamin Yan