Machine Learning
A Comparative Study of Label-free Representation Quality Metrics in Deep Learning
Daniel Richards Arputharaj, Daniel Jönsson and Gabriel Eilertsen
We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliability under a wide variety of configurations. We group existing label-free metrics into three families based on their construction and analytically establish connections between metrics within the same family. We then characterise the sensitivity of spectral metrics through controlled synthetic experiments. Finally, all label-free metrics are evaluated against downstream task accuracy across a diverse set of 260
vision models on six
datasets spanning generic object classification, fine-grained object classification, scene recognition and geospatial task, stratifying results by architecture class and training objective. We find that intrinsic dimensionality (ID) is the most reliable predictor among the metrics considered. However, the reliability of all metrics, including ID, is moderated by architecture class and training objective. Our results provide a clearer understanding of what label-free representation quality metrics measure, when they are reliable, and how to interpret them in practice.
Read the full abstract ▾
Cryptography and Security
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo et al. (+10 more)
As large
language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research
attention, with closed-source LLMs (e.g., Mythos) delivering advanced cybersecurity capabilities. However, existing open-source efforts remain limited: frontier open-weight models do not provide reproducible cybersecurity training solutions, open-source training solutions focus on isolated tasks and lack scalable agentic data, and scaling agentic rollouts requires strong domain priors. In this work, we introduce CyberFactory, a unified open-source framework that connects data construction, trajectory synthesis, and model training across proof-of-concept (PoC) generation, vulnerability patching, and cybersecurity question answering (CyberQA). CyberFactory transforms public vulnerability artifacts, including CVEs from the wild, into executable and verifiable task instances. It further uses a reusable vulnerability-analysis skill to guide the teacher through source inspection, problem solving with domain prior, and evidence-based validation. The resulting supervision is agentic: the model interacts with tools and target environments and revises its solutions according to execution feedback. Using these trajectories, we train and release \modelname\footnote{Aegis is, in Greek mythology, the protective shield of Zeus and Athena; the name reflects the model's defensive, security-oriented purpose.}, which internalizes the skill-guided procedure without requiring the skill at inference time. On CyberGym, \modelname reaches 52.4% Pass@1 under a one-hour budget, improving over its Qwen~3.5 base model by +22.8 points and outperforming the evaluated general-purpose backbones under the same scaffold.
Read the full abstract ▾
All authors Jian Yang, Haau-Sing Li, Shawn Guo, Zixi Zhao, Yibo Tan, Jiajun Wu, Aishan Liu, Zhoujun Li, Xianglong Liu, Tianyu Zheng, Bryan Dai, Chengran Yang, Weifeng Lv
Networking
NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration
Chang Liu, Xiaohui Xie, Xinyi Chen et al. (+1 more)
Large
language model (LLM)
agents are increasingly attractive for automating network configuration, yet their reliability and failure patterns are poorly understood. An essential prerequisite is to assess such
agents in a realistic but risk-free environment. Existing
benchmarks, however, fall short: they often treat configuration as static command generation or rely on overly simplified settings. Such evaluations understate the core challenges of network configuration, where correctness requires
reasoning about protocol complexity and
topology dependence. We present NetConfArena, an executable
benchmark for evaluating LLM
agents in closed-loop network configuration. NetConfArena places
agents in emulated multi-device networks, provides a standardized and compact action interface for task execution, and evaluates the resulting network behavior with hidden task-specific executable test cases. The
benchmark relies on an LLM-assisted, emulation-grounded pipeline, which converts human-oriented network materials into reusable parameterized task templates. We evaluate representative LLM
agents on 480 task instances instantiated from 96 protocol-focused task templates, yielding 3840 execution trajectories, and show that failures are not limited to command errors. The failures also reveal gaps in task-specification adherence and robust planning and execution. These findings suggest two future directions: using validated trajectories as supervision signals to improve foundation models, and designing harness mechanisms that make
agent execution more reliable and accountable.
Read the full abstract ▾
All authors Chang Liu, Xiaohui Xie, Xinyi Chen, Yong Cui
Systems and Control · Cross-listed from math.OC
Zeroth-Order Nonsmooth Nonconvex Optimization with Convex Liftings and Its Application to State-Feedback $H_\infty$ Policy Optimization
Xuhao Wang and Yujie Tang
Direct policy optimization is widely used in reinforcement learning and control, but generally leads to nonconvex optimization problems. For state-feedback $H_\infty$ control, the policy objective is also nonsmooth, despite possessing a benign landscape whose hidden convexity can be revealed by the recently developed extended convex lifting framework. Motivated by recent advances in hidden convex optimization, we study zeroth-order optimization of nonsmooth, nonconvex problems admitting a convex lifting. We propose a zeroth-order proximal point
algorithm: An inexact proximal-point outer loop constructs strongly convex subproblems, while an inner loop approximately solves each subproblem using only function evaluations. With probability at least $1-\delta$, our proposed
algorithm returns an $\epsilon$-optimal solution using $\widetilde{O}\left(d\epsilon^{-3}\right)$ function evaluations, while all iterates remain feasible without explicit projection. Finally, we verify that the assumptions underlying our analysis hold for discrete-time state-feedback $H_\infty$ policy optimization, yielding an oracle complexity of $\widetilde{O}\left(n_u n_x\epsilon^{-3}\right)$ for attaining a prescribed objective value gap, where $n_u\times n_x$ is the dimension of the feedback gain to be optimized over.
Read the full abstract ▾
Information Retrieval
Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines
Emre Kuru and Mehmet Onur Keskin
Retrieval-augmented generation (RAG) systems have traditionally relied on text-based pipelines that extract and retrieve information from documents. While efficient and lightweight, these approaches often struggle with documents where meaning is conveyed through layout, tables, and visual elements. Recent advances in
multimodal pipelines, powered by
vision-
language models (VLMs), improve
retrieval quality by jointly encoding visual and textual signals, but at increased computational and
memory cost. We propose a quantitative, data-driven selection methodology that guides practitioners in choosing the most appropriate RAG pipeline for a given document corpus based on empirical effectiveness and resource constraints. We evaluate contemporary textual and
multimodal pipelines, including dense and late-interaction architectures, analyze their trade-offs, and provide actionable guidance for balancing
retrieval performance with system efficiency.
Read the full abstract ▾
Computer Vision
Neighbor-Aware View Synthesis for Restoring Missing Views in Light-Field Camera Arrays
Sakshi Goel, Ayush Goyal, K S Venkatesh et al. (+1 more)
In light-field (LF) imaging systems, dense spatial sampling from a camera array enables powerful post-capture capabilities such as refocusing and depth estimation. However, real-world LF capture is often affected by hardware malfunctions, where one or more cameras in the array fail, leading to missing sub-aperture images and degraded reconstruction quality. This paper addresses the problem of defective or missing view restoration in light-field camera arrays. We propose a novel generative framework that synthesizes the absent views by exploiting information from a carefully selected subset of neighboring cameras. These selected images, along with a positional encoding map indicating both their locations and the desired target view, are fed into a conditional Generative
Adversarial Network (cGAN) trained to generate the missing viewpoint in a geometrically consistent manner. Extensive experiments on synthetic and real-world LF
datasets demonstrate that our method produces visually plausible and photometrically accurate reconstructions, outperforming baselines for view interpolation both quantitatively and qualitatively. The proposed framework thus offers a robust and efficient solution for fault-tolerant light-field image acquisition.
Read the full abstract ▾
All authors Sakshi Goel, Ayush Goyal, K S Venkatesh, Koteswar Rao Jerripothula
Computer Vision
BenthicFlow: Generating Extensible Underwater Environments via Flow Matching
Joaquín Figueira, Camile Lendering, Manfred Gonzalez-Hernandez et al. (+3 more)
Computer
vision applications for 3D scene understanding in
underwater environments remain challenging due to the lack of high-quality 3D data and the inability of surface-trained models to generalize to
underwater scenes. To address this challenge, an emerging trend is to employ generative models to close the data domain gap. However, existing methods assemble large scenes by stitching independently generated tiles post hoc with separately trained models, while demonstrating heterogeneous landscapes only within individual survey sites. We introduce BenthicFlow, a unified framework based on a single conditional flow-matching model that jointly generates aligned textures and depth maps. A MultiDiffusion-inspired sampling procedure reconciles overlapping windows throughout the generative trajectory, enabling spatially extensible RGBD mosaics without a separate stitching model. The generated mosaics are subsequently lifted into explicit 3D benthic environments using surface-aligned Gaussian surfels. Experiments across geographically distinct survey sites demonstrate that BenthicFlow preserves site-specific appearance while generating coherent, large-scale 3D scenes that closely match the target distributions. Code and trained models are available at https://github.com/jacomof/BenthicFlow.
Read the full abstract ▾
All authors Joaquín Figueira, Camile Lendering, Manfred Gonzalez-Hernandez, Giacomo D'Amicantonio, Erkut Akdag, Egor Bondarev
Computation and Language
CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
Abhilash Nandy, Rahul Seetharaman, Aman Bansal et al. (+5 more)
Large-scale
vision-
language models (VLMs) have demonstrated remarkable versatility across a wide range of
multimodal tasks. However, understanding humor remains challenging because humorous content often depends on subtle interactions among entities, events, context, and implicit relationships across image and text modalities. These interactions can involve complex chains of
reasoning that are difficult to capture through conventional prompting or linear chain-of-thought
reasoning. In this work, we propose CaRGo-T (Causal
Reasoning Graph-of-Thought), a
reasoning framework that represents the causal and contextual relationships underlying
multimodal humor as a lightweight graph-based
reasoning structure. The graph is serialized into a code-based representation generated by a VLM, which can subsequently be interpreted by the same or a different VLM to produce the final prediction in zero-shot or in-context learning settings. We evaluate CaRGo-T on humor understanding and humor detection across four
datasets spanning diverse forms of comedic content, including satire, sarcasm, and memes. Experiments with state-of-the-art commercial and open-source VLMs show that CaRGo-T consistently improves performance over existing
reasoning-based baselines, achieving gains of approximately 1-20% on humor understanding and 1-3% on humor detection. Further analysis using mutual information indicates that the
reasoning representations produced by CaRGo-T contain more information relevant to the target output than those generated by baseline
reasoning approaches. Code is available at https://github.com/abhi1nandy2/CaRGo-T.
Read the full abstract ▾
All authors Abhilash Nandy, Rahul Seetharaman, Aman Bansal, Rounak Saha, Manav Nitin Kapadnis, Millon Madhur Das, Pawan Goyal, Niloy Ganguly
Networking
5 Shades of Cooperation: Spectrum Sharing in the Upper-Mid Band
Alberto Ceresoli, Marco Mezzavilla, Ilario Filippini et al. (+1 more)
Spectrum exclusively licensed to each mobile network operator (MNO) is scarce, and assigning it in fixed, frequency-orthogonal blocks leaves much of it idle under heterogeneous, time-varying traffic. Large
antenna arrays offer an alternative: an operator can spend part of its spatial degrees of freedom (DoF) serving its own users and part suppressing interference toward others' users (nullforming), letting competing networks reuse the same band. This raises two questions: does trading DoF for interference suppression beat orthogonal partitioning, and how much coordination is needed to realize the gain? We cast inter-operator sharing as a continuum of cooperation "shades" of a single null-forming MU-
MIMO precoding and interference-constrained scheduling primitive, spanning orthogonal partitioning, non-cooperative reuse, cooperative cross-operator protection, and a scheduling-aware bound exploiting foreign scheduling decisions. Evaluated on a ray-traced digital twin of a real multi-operator deployment with 27 base stations sharing a 7 GHz carrier, the cooperative shades deliver more than a 2.5$\times$ median per-user rate gain over both non-cooperative reuse and orthogonal splitting. Crucially, most of this gain requires only minimal inter-operator information exchange, indicating that a modest, standardizable metadata exchange, rather than tight joint processing, unlocks most of the value of shared-spectrum operation.
Read the full abstract ▾
All authors Alberto Ceresoli, Marco Mezzavilla, Ilario Filippini, Antonio Capone
Computation and Language
Accelerating Diffusion Language Models via Structured Suffix Modeling
Zifeng Cheng, Keda Li, Zhiwei Jiang et al. (+3 more)
Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple
tokens in a single generation step. However, this parallelism comes with substantial computational overhead, as each step requires interactions with all suffix
tokens. Existing methods typically reduce this cost by retaining only a local suffix window as a substitute for the full suffix. Despite their effectiveness, these methods overlook the structural heterogeneity across suffix regions and re-initialize suffix
tokens with identical representations at each timestep. To this end, we propose a structured suffix modeling method for efficient DLM inference. Specifically, we divide the suffix into three regions, i.e., the local, middle, and tail regions, and retain different numbers of suffix
tokens in each region according to their structural roles. Moreover, we incorporate the decoding results from the previous step into the suffix
token representations at the current step, allowing them to carry evolving denoising information across generation steps. Notably, our method is training-free and orthogonal to several existing acceleration techniques, such as parallel decoding strategies and KV cache. Empirical results across multiple
benchmarks on three DLMs demonstrate that our method can further accelerate DLM inference and improve performance in most cases. In particular, in long-sequence inference, our method achieves up to a \(72.81\times\) speedup when combined with other acceleration techniques. Our code is available at https://github.com/zifengcheng/SSM.
Read the full abstract ▾
All authors Zifeng Cheng, Keda Li, Zhiwei Jiang, Cong Wang, Fei Shen, Qing Gu
Systems and Control
Leveraging UAV Autonomy for Minimum 4D Flight Authorization Volumes
Christian Vitale, Yiannis Grigoriou, Panayiotis Kolios et al. (+1 more)
The increasing
UAV traffic in urban areas has prompted the creation of U-space, an EASA framework for safe and efficient unmanned aerial vehicle (
UAV) operations. Within this context, this work presents a flight authorization framework that leverages autonomous
UAVs, using their motion models and control characteristics to improve authorization efficiency. In the proposed framework, probabilistic spatial-temporal envelopes are generated to predict future
UAV locations within a desired confidence level, and this information is then used to determine the minimum 4D operational volumes that form a valid authorization request for the mission. By reserving only the necessary airspace, the approach enhances capacity and supports simultaneous
UAV operations. Simulations comparing the proposed method with a conventional rule-based strategy demonstrate consistently more compact and efficient airspace reservations across a range of mission types.
Read the full abstract ▾
All authors Christian Vitale, Yiannis Grigoriou, Panayiotis Kolios, Georgios Ellinas
Distributed Computing
Effects of Hybrid CPU and Cache Architectures on Parallel HPC and Cloud Applications
Nanda Velugoti, Joseph Manzano, Nathan Tallent et al. (+1 more)
Hybrid CPU architectures have entered the mainstream desktop computing with the announcement of Intel's Alderlake architecture. Such a transition to heterogeneous CPU architecture has various performance and power implications on existing parallel workloads. In this paper we study the effects and impact of hybrid core and cache architecture on the performance of highly parallel HPC workloads. We also illustrate interesting thread scaling behavior for parallel workloads and describes the reason for such behavior both qualitatively and quantitatively. We also explore the impact of hybrid cache architecture on parallel shared data HPC applications. Finally, we illustrate that 1) parallel applications with work imbalance (i.e., threads in application perform different amount of work) scale better across hybrid cores when thread affinity is disabled and 2) hybrid cache architecture has very little impact on parallel shared data applications except for some workloads with locks. This work lays the foundation for our future work which focuses on extending this work to model parallel workloads and hybrid CPU architectures to improve their performance in terms of execution time,
memory usage and power consumption.
Read the full abstract ▾
All authors Nanda Velugoti, Joseph Manzano, Nathan Tallent, Kyle Hale
Machine Learning
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
Syed Muhammad Hamza Zaidi, Szymon Bobek, Grzegorz J. Nalepa et al. (+1 more)
Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window's prediction? We argue that the more informative question for diagnostic interpretability is structural: how does the classifier connect its own classes to each other? We propose a counterfactual transition graph (CGT) in which each node is a class and each edge weight is the CF reliability of the transition from one prototype to another under a proximity aware
retrieval sweep. On a six-class hand-movement task, we induce a CGT that reveals a non-trivial
topology, which is not predicted by the binary confusion
matrix: it shows that counterfactual reachability does not align with classifier accuracy and even runs counter to it (Spearman $\rho=-0.37$ over the 15 pairs), i.e. the boundaries the classifier separates most confidently are among those an in-distribution edit can least often cross. Our framework is method agnostic, i.e. any CF-explainers can be used. Presently, we use it to juxtapose replacement-based CFs with gradient-based CFs; gradient-based methods reach almost any class by stepping off the data
manifold, while replacement-based methods stay on it and fail on precisely the rigid boundaries.
Read the full abstract ▾
All authors Syed Muhammad Hamza Zaidi, Szymon Bobek, Grzegorz J. Nalepa, Myra Spiliopoulou
Robotics
Spinning Quadrotor: Hover Thrust Augmentation with Passive Lifting Surfaces
Aniketh Parkala and Harikumar Kandath
Conventional multirotor aerial vehicles actively suppress yaw rotation during hover, expending power to maintain a fixed heading despite the fact that yaw regulation is not required for force balance or altitude control. This paper challenges that paradigm by proposing a spinning quadrotor architecture that intentionally operates at a sustained yaw rate, converting power traditionally spent on yaw regulation into useful aerodynamic effects. A dynamic model of the spinning quadrotor is developed, analysis for low Re range is conducted to choose an airfoil for lifting surfaces. Preliminary hardware tests show a 22% reduction in thrust required. These findings suggest that intentional yaw rotation, rather than being suppressed, can be exploited as a design mechanism for efficient and robust multirotor flight.
Read the full abstract ▾
Machine Learning
When More Modalities Hurt: Modality Dropout for Heavy-Duty Vehicle Engine Diagnostics
Adeel Zafar, Slawomir Nowaczyk, Hamid Sarmadi et al. (+1 more)
Heavy-duty vehicle diagnostics generate three disconnected data modalities: unstructured multi- lingual service complaints, high-dimensional sensor telemetry with over 80% missing values, and Diagnostic Trouble Codes (DTCs). We investigate whether fusing these modalities improves engine component classification on a proprietary
dataset from a major truck manufacturer. Through 5-fold cross-validation across multiple model configurations spanning three model families on five engine component classes (885 samples, the full cross-database matched population for this manufacturer), we find that naive fusion provides modest gains over text alone (65.3%). However, modality dropout during training, which randomly disables entire modalities per batch, forces the network to exploit weaker inputs and achieves 68.8% accuracy on text+DTC fusion (weighted F1: 0.67), a 3.5-point improvement over text-only (65.3%, weighted F1: 0.64) and the best result across all methods including logistic regression and gradient-boosted trees. Per-class analysis shows that the dominant modality varies by fault type: text describes symptoms, DTCs encode structured fault signals, and sensors measure physical state. On intake/exhaust faults, sensors alone reach 93% where text achieves 80%. On fuel system faults, fusion with modality dropout nearly triples accuracy from 15% to 38% over text alone. To our knowledge, this is the first application of three-way modality fusion combining text, sensors, and fault codes in industrial vehicle diagnostics.
Read the full abstract ▾
All authors Adeel Zafar, Slawomir Nowaczyk, Hamid Sarmadi, Saeed Gholami Shahbandi
Software Engineering
LLMCrater: Lifecycle-Aware FAIR Metadata Generation using Large Language Models
Dani Termaat, Nafiseh Soveizi, Zhiming Zhao et al. (+1 more)
FAIR (Findable, Accessible, Interoperable, and Reusable) metadata is essential for the discovery, interoperability, and reuse of scientific research assets. However, creating and maintaining FAIR metadata remains largely manual, making the process time-consuming for heterogeneous research artifacts generated throughout the research lifecycle. Existing approaches primarily generate metadata at publication time, missing opportunities to capture contextual information as it becomes available. To address this limitation, we present LLMCrater, a lifecycle-aware metadata generation framework that combines Large
Language Models (LLMs) with stage-specific RO-Crate metadata profiles. The framework progressively enriches metadata across four research lifecycle stages (Design, Development, Deployment, and Execution & Provenance) while remaining compatible with RO-Crate~1.1 and EOSC metadata recommendations. It automatically extracts metadata from heterogeneous artifacts, generates and validates machine-actionable RO-Crates, and supports publication to FAIR repositories and PID services (e.g., Zenodo). We demonstrate the approach using two representative use cases: a 5G experimentation environment within SLICES-RI and an experiment on GreenDIGIT's EcoJupyter platform. Results show that LLMCrater progressively enriches metadata throughout the research lifecycle and generates valid RO-Crates conforming to the RO-Crate~1.1 specification.
Read the full abstract ▾
All authors Dani Termaat, Nafiseh Soveizi, Zhiming Zhao, Marios Avgeris
Information Retrieval
The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness
Gustavo Penha, Juan Elenter, Claudia Hauff et al. (+3 more)
Recent work has focused on improving explicit natural-
language descriptive
reasoning traces for generative recommendation. This includes systems that augment semantic ID (SID) prediction with chain-of-thought
reasoning. However, because SIDs are opaque learned identifiers rather than natural
language, they require costly
alignment before an LLM can reason over them. This provides a controlled experimental setting in which both item representation (Title vs. SID) and semantic grounding (minimal vs. extensive SID
alignment) can be varied independently. We therefore present the first controlled comparison of descriptive
reasoning trace quality across semantic IDs and natural-
language titles in a 2 x 2 factorial study on three Amazon product domains using a shared Qwen3-1.7B backbone. We find that introducing explicit descriptive
reasoning traces reduces traditional offline recommendation effectiveness under standard SFT and RL training, even though natural
language titles produce substantially more grounded and interpretable traces. Extensive SID
alignment improves descriptive trace quality but not traditional offline recommendation effectiveness, while a richer reward signal partially recovers performance. Overall, our results show that improving descriptive
reasoning trace quality is not, by itself, sufficient to consistently improve traditional offline recommendation effectiveness under the training objectives and evaluation protocols studied here.
Read the full abstract ▾
All authors Gustavo Penha, Juan Elenter, Claudia Hauff, Hugues Bouchard, Paul Bennett, Mounia Lalmas
Machine Learning
Conformal Risk Minimization for Semi-Supervised Domain Adaptation via Optimal Transport
Manos Giannopoulos, Yi Shen and Michael M. Zavlanos
In high-stakes healthcare applications, machine learning models are frequently trained on data from one patient population and deployed on another, creating a distribution shift that degrades both accuracy and reliability. Semi-Supervised Domain Adaptation (SSDA) addresses this by leveraging labeled data from some source domain to improve model performance on a target domain where labels are scarce. However, existing SSDA methods optimize primarily for point-prediction accuracy and offer no principled uncertainty quantification — a prerequisite for clinical trust. Conformal Prediction (CP) can address this limitation by providing prediction sets with rigorous, distribution-free coverage guarantees. However, applying CP post-hoc to a pre-trained model can yield prohibitively large prediction sets, as SSDA pre-training methods do not account for the nonconformity score geometry that determines conformal set size. Conformal Risk Minimization (CRM) has been used to resolve this issue in the fully supervised setting by integrating the CP objective directly into model training, but it requires a large labeled
dataset to compute nonconformity thresholds during training, precisely the data that is scarce in the SSDA regime. We propose an end-to-end framework that integrates CRM into the SSDA training objective, enabling effective CRM in the limited-labeled-target-data regime. The key idea is to utilize Optimal Transport (OT) to generate pseudolabels for unlabeled target instances, providing the additional training signal needed by CRM to operate using only a small labeled target set. This results in a model jointly optimized for domain invariance and conformal efficiency, producing prediction sets that are compact, coverage-valid, and support domain-specific constraints such as excluding mutually contradictory diagnoses in skin lesion classification.
Read the full abstract ▾
Computation and Language
Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation
Sujoy Nath, Aswini Kumar and Tanmoy Chakraborty
Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes stylistic control while treating hate
speech as homogeneous, overlooking that distinct forms of abuse require fundamentally different counterspeech strategies. To address this gap, we introduce FIRE (Factuality Informed Multi-
Agent Reasoning Framework) that first decomposes hate
speech into one of the five distinct categories (misinformation, stereotype, conspiracy, dehumanizing, non-factual), and then maps it to a targeted counterspeech style. To facilitate FIRE, we curate FactualCS, a novel
dataset of $4,784$ instances that provides the annotations regarding hate categories,
reasoning traces, and evidence mappings, which are critical elements for grounded generation that are missing in prior work. A comprehensive evaluation across $28$ baseline configurations demonstrates that FIRE significantly surpasses existing methods, despite using compact
agents ($<$2B). FIRE achieves a $\sim$ $12 \%$ and $\sim$ $11 \%$ improvements in factual and category-specific accuracy respectively, while simultaneously reducing toxicity by $\sim$ $11 \%$ relative to the strongest baselines. Further human evaluation confirms that responses generated by FIRE are significantly preferred over the strongest baselines, underscoring its effectiveness for real-world deployment. These findings show that decomposing the underlying intent of hate
speech is essential for generating safe, effective, and contextually precise counterspeech.
Read the full abstract ▾
Computation and Language
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
Seungyoon Lee, Minhyuk Kim, Jungseob Lee et al. (+1 more)
The
alignment of Large
Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in other
languages. In this paper, we propose Cross-lingual Ranking Preference Optimization~(CRPO), a novel framework that leverages robust preference knowledge from English to facilitate preference
alignment in the target
language. We design a hierarchical structure within parallel preference pairs across the target
language and English to jointly optimize intra- and inter-lingual preferences, thereby enhancing
language adaptation and output quality. Building on the LambdaLoss framework, CRPO goes beyond the binary comparison based optimization by providing a relative ranking signal across multiple candidate responses. Our experiments across five
languages with varying resource scales demonstrate that CRPO consistently outperforms standard approaches in both instruction-following and knowledge utilization capability. Notably, the robust performance gains observed across various weighting schemes further validate the empirical effectiveness of our hierarchical design in a
multilingual setup. Furthermore, our findings highlight that CRPO significantly improves both reward margins and the log-probability of desirable responses, contributing to a more stable preference
manifold for cross-lingual
alignment. Our code is available at https://github.com/dltmddbs100/CRPO.
Read the full abstract ▾
All authors Seungyoon Lee, Minhyuk Kim, Jungseob Lee, Heuiseok Lim
Software Engineering
An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows
Nafiseh Soveizi, Sven Tesselaar, Hero Robinson Brouwer et al. (+1 more)
Legacy scientific applications remain valuable research assets but are often tightly coupled to project-specific execution environments, limiting their reuse, reproducibility, and deployment within modern scientific workflow systems and cloud-native Virtual Research Environments (VREs). Existing migration approaches primarily target individual artifacts, such as notebooks or containers, and provide limited support for systematically transforming heterogeneous legacy applications into reusable cloud-native workflows. This paper presents an AI-assisted migration framework that combines the Reference Model of Open Distributed Processing (RM-ODP)-guided architectural analysis, Large
Language Models (LLMs), and Design Structure
Matrix (DSM) analysis. The framework first uses RM-ODP to guide an LLM in identifying reusable workflow components, their interfaces, and execution dependencies from heterogeneous legacy applications. The resulting workflow structure is then iteratively evaluated and refined using DSM analysis. Finally, an LLM-based workflow generator implements the validated workflow components and produces containerized execution environments and executable workflow definitions for deployment in cloud-native workflow systems, including VREs. The framework was evaluated on two legacy scientific applications from different scientific domains. In both cases, the applications were successfully transformed into reusable cloud-native workflows while preserving their original functionality, demonstrating the feasibility of the proposed approach for modernizing legacy scientific software.
Read the full abstract ▾
All authors Nafiseh Soveizi, Sven Tesselaar, Hero Robinson Brouwer, Zhiming Zhao
Multiagent Systems
First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs
Jingyi Su, Yihao Zhang, Dianxuan Fu et al. (+15 more)
We present the first LLM-powered multi-
agent system for autonomous fault management across millions of optical links in production AIDCs. Refined via SFT and continuous
memory evolution, it achieves 97.7% F1 and over 60% fault-incident reduction, outperforming SOTA LLMs on a ten-week field data evaluation.
Read the full abstract ▾
All authors Jingyi Su, Yihao Zhang, Dianxuan Fu, Leiyan Fei, Juan Wang, Mengfan Dai, Qing Liu, Xiong Wu, Yufeng Jiang, Cheng Chen, Bowen Zhang, Peilong Wang, Xi Chen, Zonglong He, Hongchen Yu, Zhicheng Ye, Weisheng Hu, Qunbi Zhuge
Machine Learning
Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair
Zehao Liu, Chuangchuang Fang and Yang Ren
Low-bit weight quantization saves storage but leaves errors that degrade LLM quality. We introduce activation-weighted seeded residual coding (AWSRC), a compact repair codec for an existing quantization backbone. Given a reconstructed weight $W_0$, AWSRC encodes the residual $W-W_0$ using deterministic seed-generated bases. The sidecar stores seed selectors, low-bit coefficients, and scales rather than an explicit codebook. Two variants combine activation weighting with per-module byte quotas ($\mathrm{AWSRC\text{-}U}$), or blended activation/Fisher weighting with globally ranked progressive prefixes ($\mathrm{AWSRC\text{-}P}_{F}$) that support multiple byte budgets without refitting. On Qwen2.5-3B-Instruct, adding $0.162$ scope-bits/weight to an RTN-INT4 baseline closes $88.2\%$, $78.9\%$, and $71.3\%$ of the PPL, KL, and 11-task mean-accuracy gaps to BF16, respectively. AWSRC achieves the highest mean downstream accuracy in byte-matched residual-codec ablations and improves all metrics across model families with up to 32B parameters.
Read the full abstract ▾
Computer Vision
An end-to-end-trained vision-language model for native-language prostate pathology report generation
Christian Grashei, Fabian Gülhan, Maximilian Legnar et al. (+4 more)
Prostate cancer is among the most frequently diagnosed malignancies worldwide, and structured reporting of each biopsy core burdens pathologists. Existing tools frame this as classification, leaving pathologists to assemble coherent reports, while many slide-level
vision-
language models rely on English-centric encoders that transfer poorly to other clinical
languages. We present a slide-level framework generating prostate biopsy reports that is
language-independent by construction: tokenizer and model are trained from scratch, demonstrated here in German. To address paired-data scarcity, an automated pipeline uses a locally deployed large
language model to split composite reports into core-specific image-text pairs, yielding 17,344 pairs from 2,402 historical cases without manual annotation. Evaluated for clinical attributes rather than linguistic similarity, the model achieves 96.2% F1 for malignancy detection and 65.2% for Gleason grading, competitive with an FDA-cleared classifier. Grading is further validated on three external cohorts with latent-space augmentation. Institutions can thus train native-
language reporting models on their own archives.
Read the full abstract ▾
All authors Christian Grashei, Fabian Gülhan, Maximilian Legnar, Fabian Stögbauer, Cleo-Aron Weis, Carolin Mogler, Peter Schüffler
Computer Vision
How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?
Simon Ravé, Pejman Rasti and David Rousseau
Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and organ
segmentation. Plain
Vision Transformers (ViTs) provide a common architecture for these tasks, but quadratic
attention limits high-throughput and edge inference. Training-free
token merging is attractive because it can be inserted into trained models without retraining. We provide a systematic
benchmark of ToMe and Mutual Pair Merging across growth-stage classification, wheat-head detection, and wheat-organ
segmentation, measuring task quality, throughput,
token count, and peak GPU
memory, with additional Raspberry Pi 5 measurements. The
benchmark reveals a clear hierarchy: classification is highly merge-tolerant, while detection and
segmentation are constrained by repeated instances, thin organs, dense boundaries, reconstruction, and runtime overhead. Optimized
attention backends can erase apparent speedups, so deployment value must be profiled on the target runtime rather than inferred from
token count.
Read the full abstract ▾
Computer Vision
MIVIFI: Bridging Perspective and Fisheye Domains for Training Multi-View Fisheye Image Generation Models
Matthias Neuwirth-Trapp, Begüm Altunbas, Jiayi Wang et al. (+4 more)
Achieving 360{\deg} coverage is critical for the visual perception systems of autonomous vehicles. Fisheye cameras offer a cost-effective solution by enabling full surround coverage with as few as two sensors. However, existing multi-view fisheye
datasets are limited, and synthesizing rare corner cases typically requires computationally expensive 3D simulations, hindering the training. While generative models have achieved significant success in standard perspective imagery, their application to wide-angle distortion remains unexplored. In this work, we formally introduce the novel problem of multi-view fisheye image generation conditioned on volumetric semantic representations and present two distinct methods. We first propose SyntheOcc-FE, which adapts the SyntheOcc architecture to fisheye data. While effective, this method is constrained by the scarcity of fisheye
datasets, which limits its generalization. To overcome these limitations, we propose our second method, MIVIFI (multi-view fisheye), which leverages cross-domain learning with Equirectangular Projections. By bridging the gap between
dataset domains using KITTI-360 fisheye images alongside nuScenes multi-view standard images, our approach enables high-fidelity manipulation of scene content. This framework enables the structural modification of semantic occupancy inputs to introduce or eliminate specific actors and facilitates the rendering of diverse meteorological conditions and illumination scenarios absent in the limited fisheye
datasets. Quantitative and qualitative experiments demonstrate that our methods achieve robust photorealistic multi-view fisheye image generation and highlight the specific advantages of our cross-domain strategy for handling data scarcity.
Read the full abstract ▾
All authors Matthias Neuwirth-Trapp, Begüm Altunbas, Jiayi Wang, Yan Xia, Maarten Bieshaar, Xinyu Huang, Daniel Cremers
Numerical Analysis
The longest-edge bisection algorithm may produce degenerating tetrahedra
Sergey Korotov
An explicit sequence of tetrahedra generated by the longest-edge bisection
algorithm is shown to degenerate. The example violates shape regularity and both the minimum- and maximum-angle conditions, demonstrating that arbitrary tie-breaking among longest edges does not guarantee nondegeneration.
Read the full abstract ▾
Robotics
Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation
Xiwen Chen, Zelin Li, Zhiruo Zhou et al. (+3 more)
Vision-
language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action
tokens, creating brittle interfaces between
multimodal reasoning and
robot execution. We present Pointing-VLA, a typed hidden-state spatial readout built on
Embodied-R1. Geometry-specific heads predict normalized points, object-functional grounding (OFG) heatmaps, and visual trajectories without serializing geometry as text. For the evaluated Bridge/WidowX and physical pick-place deployments, an explicit execution contract assigns PICK to source-conditioned OFG and PLACE to Pointing, providing direct stage-aligned spatial targets. Pointing-VLA achieves SOTA performance on Bridge/WidowX, averaging 72.9% across the evaluated four-task set without Bridge-specific finetuning under collision-enabled CuRobo execution. Pointing and OFG show complementary strengths across native and cross-
dataset evaluations. The OFG/contact readout transfers to NORA-1.5, preserving or improving success while reducing recorded controller time by more than 20$\times$; typed heads are also 6.68–6.90$\times$ faster than
Embodied-R1 text decoding on a shared external suite. When integrated as spatial guidance for a $\pi_{0.5}$ action policy, Pointing-VLA raises autonomous real-
robot success from 52.7% to 80.7% across three visual contexts. These results establish typed spatial readouts as an efficient, inspectable interface between
embodied reasoning and
robot execution.
Read the full abstract ▾
All authors Xiwen Chen, Zelin Li, Zhiruo Zhou, Huiming Chen, Chenwei Wang, Xiaojun Zhu
Computer Vision
Simulate, record, verify: A language-portable framework for muscle-grounded articulatory QA (extended version)
Seungho Eum, Shantong Sun and Unsang Park
Articulatory data describe what the tongue looks like, but geometry alone does not explain the muscle-level why behind a configuration or how to move it toward a target posture. We present a simulator-based framework that constructs this supervision from controlled biomechanical inputs. Each simulated configuration is stored with its generating muscle state and
geometric properties in a structured fact record. Gold answers are derived before linguistic realization, and every naturalized output is checked against its source record, so the same records support new
languages and question types without re-simulation. We instantiate the framework as 3DTongueQA using the ArtiSynth Badin tongue model. From 295,115 meshes, we construct 891,156 record-checked QA instances per
language, and the checker detects over 96.9% of injected corruptions. Korean and Spanish realizations and a new question type are added from the same records, confirming portability. A SpiralNet++-Qwen3 probe reaches 62.9 Muscle EM, above 44.0 for nearest-neighbor transfer and 7.2 for a zero-shot commercial LLM given the same mesh, while mesh shuffling drops it to near zero. The supervision is learnable, useful beyond
retrieval, and grounded in paired geometry. It reflects simulator-defined states rather than measured physiology. Code, templates, and QA sets are available at https://github.com/esh0504/muscle-grounded-qa.
Read the full abstract ▾
Computer Vision
Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement
Hu Wang, Hongxu Pu, Zhiqi Hu et al. (+2 more)
Poor illumination obscures small, low-contrast defects in
UAV bridge imagery, reducing the reliability and operational flexibility of automated inspection. This paper investigates whether degradation-aware image restoration can improve bridge damage detection under low-light conditions and transfer from synthetic degradations to real inspection scenes. We propose DaL- MoE, a detector-agnostic restoration front end trained with an ISP-aware low-light synthesis pipeline and equipped with degradation-aware guidance estimation and complementary experts for noise suppression, color adjustment, and structural-detail recovery. On paired synthetic data, DaL-MoE achieves 23.12 dB PSNR and 0.8482 SSIM, increasing YOLOv11m box mAP50 from 0.3097 to 0.4923 and mask mAP50 from 0.2281 to 0.3529. On real low-light
UAV imagery without paired normal-light references, sim-to-real evaluation shows improved defect visibility and more complete detections than direct inference on raw low-light inputs. Future work will develop low-light-aware bridge damage detectors with stronger cross-scene generalization across bridge sites, imaging conditions, and illumination levels.
Read the full abstract ▾
All authors Hu Wang, Hongxu Pu, Zhiqi Hu, Fangzhou Lin, Wang Wang