Artificial Intelligence · Cross-listed from eess.AS
Orantqing, Shengpeng Ji, Junlong Tong et al. (+19 more)
In this work, we present Gander, a native
multimodal duplex interaction model that builds on MiniCPM-o 4.5 and is further adapted for realtime interaction with an asynchronous
agent loop. In contrast to conventional turn based systems, Gander continuously processes streaming user inputs, enabling full-duplex interaction in both everyday conversations and complex workflow
agent scenarios. Users can interrupt an ongoing response, while the model can proactively provide intermediate feedback or ask follow up questions. To natively support these capabilities, Gander adopts two key architectural designs: 1) a Cerebellum-
Brain collaborative framework, Cerebellum is responsible for realtime interaction while the
Brain handles complex
reasoning and higher level agentic tasks. The two components interact continuously through tool calling and the
agent orchestration runtime. 2) The Cerebellum is built upon a streaming Thinker-Talker architecture, where user inputs and model outputs are flattened into an ordered
token stream at the chunk level. We evaluate Gander across conversational ability, interactive capability, understanding, and tool assisted task execution. Internal human evaluations show that Gander maintains natural and expressive spoken dialogue, while
benchmark results demonstrate effective turn taking capability and encouraging results on spoken question answering and related understanding tasks. Gander also supports a range of challenging interaction settings, including background noise interference, multi-party interactions, and backchannel communication. While our current evaluation focuses on tool assisted settings, broader long horizon
agent tasks and more diverse deployment conditions remain promising directions for further study. We release Gander together with its models, code, and data to facilitate further research and development in the community.
Read the full abstract ▾
All authors Orantqing, Shengpeng Ji, Junlong Tong, Jialong Zuo, Dongjie Fu, Di Cao, Yangzhuo Li, Shangda Wu, Franz, Evan, Theron Veyra, Changhao Pan, Jingyu Lu, Dongchao Yang, Zhifei Xie, Yang Tan, Xiaoyu Shen, Xiaoda Yang, Wenfu Wang, Teddy Sun, Steve Yves, Zhou Zhao
Cryptography and Security
NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces
Zahra Tarkhani, Georgios Akkogiounoglou, Lorena Qendro et al. (+2 more)
The rapid integration of AI into human-centred systems such as
Brain-Computer Interfaces (BCIs) has created a poorly understood attack surface linking neural signals to physical systems. Exploits in this domain threaten cognitive autonomy, mental
privacy, and physical safety, from neural data exfiltration to malicious control of BCI-tethered devices. We introduce the NERVE Attacks class, a systematic characterisation of five orthogonal attack dimensions that together span the complete BCI stack: Neuro-mimetic Forgery (N), Evasion via Desynchronization (E), Replay-based Hijacking (R), Vein Tapping (V), and Embedded
Backdoors (E). To evaluate this class, we present EEGle, an AI-assisted extensible framework for systematic BCI security analysis. Our evaluation uncovers 17 novel neuro-specific attack instances and reveals a stealth-effectiveness spectrum unique to BCI
backdoor design. We also show that generative AI lowers the barrier to entry for non-expert attackers and provide EEGle to the community for building and verifying the security of these deeply personal devices.
Read the full abstract ▾
All authors Zahra Tarkhani, Georgios Akkogiounoglou, Lorena Qendro, Isabel Tscherniak, Anil Madhavapeddy
Machine Learning
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
Yice Luo, Yun Zhu, Xi Chen et al. (+7 more)
Industrial fraud detection often relies on costly expert-crafted features that overlook graph-structured relational signals, while GNNs often do not meet the interpretability and deployment requirements of financial risk control. We propose GraphFAS (Graph Feature Automated Selection), a distributed feature selection procedure based on Boruta that bridges this gap through: (1) a non-parametric graph feature generation module that constructs explicit, interpretable structural features via multi-hop subgraph extraction and multi-scale aggregation without learned parameters; and (2) an automated distributed feature selection
algorithm extending Boruta with median-based aggregation across partitions to robustly identify informative features at scale with minimal domain expertise. Compared with end-to-end GNN pipelines, GraphFAS decouples feature aggregation from model training, enabling direct integration with tabular models and direct compatibility with TreeSHAPbased explanations. Deployed in Alipay, GraphFAS delivers orderof-magnitude improvements in engineering efficiency while showing strong performance against expert-driven and graph-learning baselines on large-scale graphs.
Read the full abstract ▾
All authors Yice Luo, Yun Zhu, Xi Chen, Yongchao Liu, Xintan Zeng, Chengying Huan, Kai Zhang, Jinrui Zhang, Juelu Zhang, Jiajun Zheng
Cryptography and Security
On APN Functions with Boomerang Uniformity One over $\mathbb F_{3^n}$: Differential and Boomerang Spectra and CCZ-Inequivalence
Namhun Koo, Soonhak Kwon, Minwoo Ko et al. (+1 more)
Let $q=3^n$, where $n>1$ is odd, and let $g:\Fq\to\Fq$ be a perfect nonlinear (PN) function represented by a Dembowski–Ostrom (DO)
polynomial. Put $\tau=g(1)$, let $\epsilon$ be the indicator of $\Fthree^*$, and, for $c\in\Fq$, define $\widetilde G_c(x):=g(x+c)+\tau\epsilon(x)$. We prove that every $\widetilde G_c$ is APN and has boomerang uniformity either one or two. More precisely, \[ \beta_{\widetilde G_c}=1 \quad\Longleftrightarrow\quad c\in\mathcal C_g :=\{c\in\Fq\setminus\Fthree:g(c)+\tau\notin g(\Fq)\}, \qquad |\mathcal C_g|=\frac{q-3}{2}, \] whereas $\beta_{\widetilde G_c}=2$ for the remaining $(q+3)/2$ parameters. We determine the common differential spectrum and complete boomerang spectra of all the functions $\widetilde G_c$. Since boomerang uniformity one is the least possible for an APN function over a finite field of odd characteristic, this gives, to the best of our knowledge, the first general construction yielding infinite families of APN functions attaining this optimum. This common differential spectrum rules out CCZ equivalence with every power function and every Ness–Helleseth-type binomial. We also prove that CCZ equivalence between sign-switches of DO PN functions forces EA equivalence between the original PN functions. Using the orders of the
nuclei of the associated presemifields, we exhibit, for infinitely many odd $n$, three pairwise CCZ-inequivalent PN functions over $\F_{3^n}$, one from each of the Gold $f_1$, Ding–Yuan $f_3$, and Bierbrauer $f_5$ families. Consequently, over each such field, our construction produces three pairwise CCZ-inequivalent APN functions with boomerang uniformity one. The smallest extension degree obtained in this way is $n=45$.
Read the full abstract ▾
All authors Namhun Koo, Soonhak Kwon, Minwoo Ko, Byunguk Kim
Artificial Intelligence
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Sohir Maskey, Philipp Scholl, Jonas Knupp et al. (+2 more)
Language-model checkpoints are commonly selected by pretraining loss or
benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoints that perform better after the full downstream training stack also have higher solution density, i.e., retain downstream performance under local weight perturbations.
Read the full abstract ▾
All authors Sohir Maskey, Philipp Scholl, Jonas Knupp, Pit Neitemeier, Sascha Wirges
Artificial Intelligence
PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving
Yuan Gao, Sebastian Müller, Mattia Piccinini et al. (+5 more)
Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation,
retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large
Language Model (LLM)
agents have shown promise across ADS sub-systems such as perception, planning, and control. However, no prior work covers the whole scenario-based testing pipeline for ADSs with a unified LLM-
agent framework. We present PlannerForge, an LLM-
agent framework that extends all scenario-based testing stages (from Scenario Generation to ADS Assessment) and adds two further LLM-enhanced stages: ADS Enhancement and ADS Benchmarking. We evaluate PlannerForge with 10 off-the-shelf LLMs across all tasks (Generation, Selection, Modification, Module Routing, Planner Testing, and Enhancement) under 5
prompt conditions. Best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends match commercial APIs on most tasks. Open-source models such as Qwen3.6:35B match commercial APIs on three of the five tasks. Chaining the modules end-to-end retains 83% / 78% of seed queries (commercial / open). It outperforms Scenario Factory 2.0 (Finkeldei et al., 2025) on natural-
language generation (193 vs. 144 executable of 200) and realises 92-96% of requested city, road and vehicle attributes. It outperforms BM25 (Robertson and Zaragoza, 2009) at rank 1 selection (92.0% vs. 67.5%) and From-Words-to-Collisions (Gao et al., 2025) on physically valid edits (>=94% vs. 31%). At N=400, cost-tuning lifts planner success from 50.4% to 70.2% and cuts collisions from 19.0% to 8.4%, without domain-specific fine-tuning.
Read the full abstract ▾
All authors Yuan Gao, Sebastian Müller, Mattia Piccinini, Marc Kaufeld, Yuchen Zhang, Finn Rasmus Schäfer, Qunying Song, Johannes Betz
Logic in Computer Science
Fitting and Learning Basis-Restricted Propositional Formulas
Balder ten Cate
For a finite set $O$ of Boolean functions, we consider the class of propositional formulas built using the functions in $O$ as connectives. We determine, for each possible choice of $O$, the complexity of various fitting and learning problems. These include: finding a formula that fits a given labeled sample, finding a small one (an Occam
algorithm), minimizing the number of misclassified examples when the sample is not realizable (empirical risk minimization), and several forms of PAC learning. Our results apply both to formulas (represented as trees) and to
circuits. We also briefly discuss the status of the same questions for other kinds of propositional fragments.
Read the full abstract ▾
Robotics
Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model
Nelson Chen, Patrick Meng, Charles Tang et al. (+5 more)
Tensegrity
robots offer lightweight, compliant mobility over challenging terrain but remain difficult to model and control due to complex contact-rich dynamics and partial observability. This work presents a model predictive path integral (MPPI) controller for a three-bar tensegrity
robot driven by a learned graph neural network (GNN) dynamics model. This work first extends prior GNN-based models with a differentiable contact detection module. The extension allows the dynamics model to reason over non-horizontal planar terrains, obstacles, as well as self-collisions. Then, the learned dynamics model and the MPPI controller operate in a closed data-collection loop, iteratively improving model accuracy and control performance. This work further introduces a hybrid MPPI strategy that combines MPPI with turning motion primitives to improve maneuverability. Experiments are performed in MuJoCo across five
navigation tasks, which include, wall obstacles, inclines, narrow corridors, low-clearance structures, and a composite 3D obstacle course. The experiments demonstrate that the hybrid MPPI controller operating over the learned GNN dynamics model improves predictive accuracy over a flat-ground baseline model and achieves superior
navigation performance compared to $A^*$-based re-planning and MPPI-only variants. Results show that the contact-aware learned dynamics combined with the sampling-based model predictive control enable robust tensegrity
navigation in complex, contact-rich environments.
Read the full abstract ▾
All authors Nelson Chen, Patrick Meng, Charles Tang, Angelina Degay, Zachary Brei, Rebecca Kramer-Bottiglio, Kostas E. Bekris, Mridul Aanjaneya
Sound
TASTE2: Text-Aligned Speech Modeling and Deployment toward Full-Duplex Voice Interaction
Yi-Chang Chen, Chun Wei Chen, Dien-Ruei Wu et al. (+7 more)
Full-duplex voice interaction requires more than utterance-level conversion. It must process streaming
speech, manage turn-taking and interruptions, while preserving pretrained linguistic competence and acoustic paralinguistic cues. We ask whether TASTE (Text-Aligned
Speech Tokenization and
Embedding) provides a viable path toward this goal. We present TASTE2, which transforms utterance-level TASTE into an incremental dialogue stack. A shared text-
token vocabulary removes word-level averaging, while modality-aligned dialogue training predicts one continuous audio latent per text
token without interleaving heterogeneous
token streams. An incremental
Speech Detokenizer enables streaming synthesis through CosyVoice2. After
speech and dialogue training, TASTE2 (Merge) reaches 56.3% on LLaMA-Questions against a 57.3% Qwen2.5-7B Instruct text-only reference (98.2% accuracy retention), and TASTE2 (Direct) reaches 53.0% (92.4% retention). We build TASTE2 VoiceBot, which processes user
speech incrementally, streams synthesized audio, and stops generation on barge-in. On Full-Duplex-Bench v1.0, TASTE2 and TASTE2 VoiceBot handle interruptions well while maintaining high conversational coherence. Natural conversation remains challenging, and deployed mean time to first audio is 2.701 s on two NVIDIA RTX A6000 after TensorRT acceleration. Finally, to our knowledge, we provide the first systematic characterization of explicit paralinguistic control in a TASTE based model. Fast speaking rate serves as a cross-strategy proof of concept after dialogue SFT, while
emotion control is strategy dependent and the remaining attributes stay weak. Together, these results establish TASTE based modeling as a practical route toward full-duplex systems while identifying natural conversation robustness,
speech generation latency, and feature general paralinguistic control as open challenges. Explore TASTE2 online.
Read the full abstract ▾
All authors Yi-Chang Chen, Chun Wei Chen, Dien-Ruei Wu, Jie Lin, Yu-Kuan Fu, Yang-Hsien Lin, Eddie TC Huang, Simon See, Hung-yi Lee, Da-Shan Shiu
Game Theory
PMMS Allocations Need Not Exist for 3 Agents with Additive Valuations
Paul Gölz
This note gives an instance demonstrating that the pairwise maximin share (PMMS) property cannot be satisfied by any allocation in certain fair division problems with indivisible goods and additive valuations. The instance requires only $n=3$
agents and $m=9$ goods, and is accompanied by a proof that no PMMS allocation exists. A separate instance shows (certified by exhaustive enumeration with a computer) that PMMS cannot be approximated within a ratio above $78/79 \approx 0.987$.
Read the full abstract ▾
Software Engineering
DJPlus: Generating minimal test suites for strong coverage criteria in graph models
Yavuz Köroğlu, Mutlu Beyaz{\i}t, Onur K{\i}l{\i}nççeker et al. (+2 more)
Automated test generation from graph models is essential to model-based testing. In this type of testing, graph coverage ensures test suite strength but also results in long test cases that take time to execute on the system under test. We propose a novel optimization-driven method, DJPlus, which generates reduced test suites while satisfying given graph-based test requirements. We implement DJPlus and show the feasibility of edge-pair criterion, a stronger coverage criterion than vertex or edge criteria, on four realistic systems, while
prime path criterion poses scalability issues. Our evaluation reveals that the alternative methods generate 2 to 26 times more redundant test steps than DJPlus and DJPlus decreases test execution times by reducing the number of test steps. These results show that DJPlus is a positive step towards tackling the challenges of model-based testing at an industrial scale.
Read the full abstract ▾
All authors Yavuz Köroğlu, Mutlu Beyaz{\i}t, Onur K{\i}l{\i}nççeker, Serge Demeyer, Franz Wotawa
Databases
SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation
Mohammadhossein Malekpour, Mohamed Riahi, Maxime Lamothe et al. (+1 more)
Text-to-SQL systems translate natural
language queries into executable SQL, democratizing access to structured data. Despite recent advances driven by large
language models (LLMs), evaluation remains a major bottleneck: public
benchmarks fail to capture the complexity of enterprise schema, while building private evaluation sets is costly and nondeterministic, making evaluation results difficult to reproduce. To address this issue, we present SQLMorph, a framework for Text-to-SQL evaluation via query mutation. SQLMorph introduces two techniques to automatically generate and expand evaluation sets: Join Query Expansion (JQE), which systematically increases structural complexity through valid join additions, and Textual Query Augmentation (TQA), which generates controlled natural
language perturbations to assess robustness to linguistic variation. JQE and TQA create targeted choke points to challenge specific system components. When applied to state-of-the-art systems, JQE increases query coverage and reveals accuracy degradation as the number of joins grows. Meanwhile, TQA shows that linguistic brittleness induced by heavy abbreviation can reduce accuracy by up to 17%. Beyond evaluation sets, SQLMorph introduces a family of execution-level metrics that address the limitations of current binary measures, such as Execution Accuracy. We define Execution Precision (EXP) and Execution Recall (EXR) to quantify the fraction of correct and recovered results, respectively, and combine them via F1 for unified scoring. Our experiments show that these relaxed metrics enable fine-grained analysis of over- and under-prediction, revealing differences across systems that binary metrics obscure. Together, SQLMorph's query mutation and fine-grained metrics support debugging and better align Text-to-SQL evaluation practices with real-world deployments.
Read the full abstract ▾
All authors Mohammadhossein Malekpour, Mohamed Riahi, Maxime Lamothe, Amine Mhedhbi
Computer Vision
Prior-free relative 6D pose estimation of multiple object instances
Behdad Khodabandehloo, Andrea Caraffa, Davide Boscaini et al. (+1 more)
Object 6D pose estimation formulations have progressively reduced reliance on object-specific priors, evolving from explicit 3D models to multi-view object captures to single reference images. We take this progression to its extreme by introducing prior-free relative 6D pose estimation, which lifts the assumption of knowing which object is to be posed within the scene. This novel setting aims to estimate the relative poses of multiple instances of an unknown object within the same image, without requiring CAD models, templates, or reference images. We solve this by formulating a novel method (PROSE) that finds coarse correspondences between object instances using
multimodal foundation features, thus requiring no training. We refine these correspondences by imposing cycle consistency across tuples of instances, and leverage the resulting globally consistent correspondences to estimate the relative 6D pose between any pair of instances. To enable systematic evaluation, we design a novel
benchmark (PRENCH) built from three multi-instance BOP
datasets and enriched with task-specific metadata. PROSE consistently outperforms baselines obtained by adapting state-of-the-art single-image methods to the proposed setting, while requiring neither task-specific supervision nor additional learned components. Project website: https://tev-fbk.github.io/PROSE/
Read the full abstract ▾
All authors Behdad Khodabandehloo, Andrea Caraffa, Davide Boscaini, Fabio Poiesi
Sound
Disentangled Global-Local Feature Learning with E-Branchformer for Audio Deepfake Detection
Phuong Tuan Dat, Ho Bao Thu, Nguyen Tran Trung et al. (+2 more)
The rapid advancement of voice synthesis technologies such as text-to-
speech and voice conversion poses significant threats to
speech-based authentication systems, necessitating robust deepfake detection methods. In this work, we propose a novel E-Branchformer-based architecture that effectively leverages self-supervised
speech representations for audio deepfake detection. Our model employs parallel branches to simultaneously capture global contextual dependencies through multi-head self-
attention and local temporal patterns through convolutional processing. To enhance discriminative capability, we integrate depthwise convolution and Squeeze-and-Excitation modules that enrich the classification
token with refined patch
token information after feature merging. Extensive experiments on ASVspoof 2021 LA, DF, and In-the-Wild
datasets demonstrate state-of-the-art performance with equal error rates of 0.88%, 1.85%, and 6.30% respectively, substantially outperforming existing methods. Comprehensive ablation studies validate that the dual-branch architecture provides complementary discriminative information, Squeeze-and-Excitation Aggregation significantly improves SSL feature integration, and the combination of DWConv and SE modules is critical for effective class
token enhancement. The superior performance on real-world scenarios demonstrates strong generalization capability to diverse acoustic conditions and unseen spoofing attacks.
Read the full abstract ▾
All authors Phuong Tuan Dat, Ho Bao Thu, Nguyen Tran Trung, Pham Viet Hoang, Nguyen Thi Thu Trang
Machine Learning · Cross-listed from physics.flu-dyn
ONE CYLinder: A Benchmark for Graph-Based Surrogate Modeling of Unsteady Bluff-Body Flows
Théodore Michel, Antoine Campos, Alban Dujardin et al. (+3 more)
Graph-based surrogate models offer a promising route to accelerate computational fluid dynamics (CFD) simulations on unstructured meshes. However, their development is limited by the scarcity of
benchmark datasets spanning multiple flow regimes and standardized protocols for long-horizon autoregressive prediction. We introduce ONECYL (ONE CYLinder), a new
benchmark for unsteady flow past a circular cylinder across laminar, transitional, and high-Reynolds-number regimes. The
benchmark comprises 450 high-fidelity Variational Multiscale finite-element simulations (270,000 flow snapshots) with randomized cylinder geometries, providing time-resolved velocity and pressure fields together with mesh connectivity,
geometric descriptors, Reynolds numbers, and integrated aerodynamic quantities. Beyond the
dataset, ONECYL establishes a unified evaluation framework combining full-field rollout errors, virtual probes, and drag and lift predictions to assess numerical accuracy and physical fidelity. To accompany the
benchmark, we develop a Graph
Transformer as a reference baseline predicting velocity and pressure fields autoregressively on unstructured meshes. Using ONECYL, we investigate
geometric representations and physics-based regularization across the three Reynolds-number regimes. The results show that explicitly encoding the cylinder geometry through a level-set representation consistently improves long-horizon prediction accuracy and generalization to unseen geometries, while divergence-based regularization becomes increasingly beneficial as flow complexity increases. The ONECYL
benchmark and its Graph
Transformer baseline provide a reproducible framework for evaluating graph-based surrogate models and establish a foundation for future research on long-horizon prediction of unsteady bluff-body flows.
Read the full abstract ▾
All authors Théodore Michel, Antoine Campos, Alban Dujardin, Henry Areiza, Philippe Meliga, Elie Hachem
Distributed Computing
ContinuumBench: Benchmarking Joint Autoscaling and Placement Across Evaluation Regimes in the Cloud-Edge Continuum
Lanpei Li, Antonino Vaccarella, Vincenzo Lomonaco et al. (+1 more)
Cloud-edge controllers coordinate service placement, replica scaling, and resource pre-warming to keep end-to-end latency within application deadlines. But evaluations often obscure the source of a reported gain: placement and scaling are studied separately; workload, connectivity, and calibration assumptions remain implicit; and metrics over completed tasks hide unfinished work. We present ContinuumBench, a
benchmark that controls these factors. Its completion-aware accounting treats late, unfinished, and discarded tasks as deadline misses. A common protocol compares placement-only and scale-capable controllers under declared regimes and stressors. Built on the ECLYPSE simulator, ContinuumBench adds arrivals, worker elasticity, intermittent transport, buffering, and failures to close the control loop. We evaluate nine controllers across four scenarios and two regimes. The studied regimes are capacity-bound: elastic capacity, not placement sophistication, drives completion, and once capacity suffices, the choice of autoscaling policy decides how much of that work arrives on time. Placement re-planning has no measurable effect without relocation, while cost-free migration defines the observed exception. Consequently, scale-capable controllers approach an over-provisioned reference while placement-only controllers degrade with load; and placement quality separates controllers only once capacity is exhausted. Finally, the accounting choice itself changes the reported result: completion-only and completion-aware scoring can rank controllers differently.
Read the full abstract ▾
All authors Lanpei Li, Antonino Vaccarella, Vincenzo Lomonaco, Massimo Coppola
Numerical Analysis
Sharp Computational Bounds for Spectral Types of Schrödinger Operators
Matthew J. Colbrook and George Coote
We prove sharp bounds for determining the spectral-type decomposition of Schrödinger operators in the spirit of Smale's program on the foundations of computation. For explicit one-dimensional self-adjoint Schrödinger operators $H=-{\mathrm d^2}/{\mathrm dx^2}+V$ on $L^2(\mathbb R)$, where $V\in C^\infty(\mathbb R;\mathbb R)$ is given by a finite description of all derivatives and derivative bounds, the pure point and absolutely continuous spectral sets cannot, in general, be recovered by any single limiting procedure. The singular continuous spectral set is strictly harder: it cannot, in general, be recovered by two nested limiting procedures. Analytic constructions of dichotomies realize the lower bounds: Gordon-type repetitions for pure point spectrum, high barriers for absolutely continuous spectrum, and an inverse spectral construction for singular continuous spectrum based on Riesz products, moment-killing perturbations, and a computational Gelfand–Levitan scheme. The finite-description framework also implies corresponding limitations on what can be certified in fixed formal systems (e.g., when used in computer-assisted proofs). Conversely, using wavelet-based certified computation, we prove matching upper bounds for broad classes of self-adjoint differential operators on $\mathbb R^d$ with coefficients of locally bounded variation and quantitative local variation control: two limits suffice for the pure point and absolutely continuous parts, and three for the singular continuous part. This provides a sharp hierarchy for spectral types.
Read the full abstract ▾
Artificial Intelligence
SkillAdam: Stable and Efficient Skill Evolution for Agents
Gaoyuan Li, Meihao Fan, Yizhe Liu et al. (+7 more)
Agent skills provide a lightweight way to equip frozen
language-model
agents with domain knowledge and procedural guidance, yet obtaining high-quality skills remains costly and difficult to scale. Expert-written skills require substantial human effort. Recent skill self-
evolution methods automate an iterative loop that uses execution feedback to revise skills, but their heuristic update strategies often yield unstable optimization and low iteration efficiency. We identify two challenges in realizing stable and efficient skill self-
evolution. Direction Stability requires effective corrections to accumulate rather than be overwritten by iteration-local feedback. Update Adaptivity requires the scope of each revision to reflect the consistency of recent case-level improvements. We introduce SkillAdam, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents. As a functional analogue of Adam's first moment, an optimization
memory records identified problems and the outcomes of prior solution attempts to stabilize the update direction. As a functional analogue of Adam's second moment, a
volatility-driven edit budget tracks the history-weighted variation of recent case-level improvements and adaptively controls the update magnitude. Across seven
benchmarks that span short- and long-horizon tasks, SkillAdam achieves state-of-the-art performance with more stable optimization dynamics. It also obtains stronger skills with substantially fewer optimization iterations and lower cost than prior methods. Code repository: https://github.com/ruc-datalab/SkillAdam
Read the full abstract ▾
All authors Gaoyuan Li, Meihao Fan, Yizhe Liu, Shaolei Zhang, Ju Fan, Siyi Wang, Jiaheng Hou, Xudong Weng, Honghan Tian, Zang Li
Computation and Language
Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation
Xingyu Deng, Mingzi Cao, Nikolaos Aletras et al. (+2 more)
Automatic fact-checking systems assess the veracity of claims given evidence from relevant documents. Large
Language Models (LLMs) have demonstrated strong performance in fact-checking due to their general
reasoning capabilities. However, it remains unclear whether they faithfully make use of the evidence provided to reach veracity judgments or rely on parametric knowledge. To investigate this, we introduce Fact-Ablated Evaluation (FAE), a new evaluation framework that iteratively ablates the cited evidence to assess whether LLMs revise their predictions accordingly. Our empirical results show that current off-the-shelf LLMs as fact-checking systems rely more on their parametric knowledge than on the evidence provided. To bridge this gap between prediction accuracy and evidence grounding, we propose REAL (Rigorous Evidence Ablation Learning), a training framework that promotes evidence-dependent verification through counterfactual evidence supervision for the LLM-as-verifier models. Experiments on four fact-checking
datasets across different domains demonstrate that models trained with REAL obtain superior evidence-dependent capabilities compared to standard fine-tuned models. Our findings highlight that strong fact-checking performance can still coexist with weak evidence dependency, while REAL encourages veracity predictions to remain more closely tied to the availability of supporting evidence.
Read the full abstract ▾
All authors Xingyu Deng, Mingzi Cao, Nikolaos Aletras, Xi Wang, Mark Stevenson
Information Retrieval
FINALLY: A Dataset Recommender System for Recommender-Systems Research
Louis Owie
Dataset selection shapes the empirical conditions under which recommender-system
algorithms are evaluated, yet existing tools provide limited support for constructing complete
dataset sets that jointly satisfy experimental constraints and set-level selection objectives. To address this problem, I developed FINALLY, a web-based
dataset recommender for constructing configurable
dataset sets for offline recommender-systems evaluations. FINALLY combines required
datasets, candidate-pool restrictions, metadata filters, configurable target-set sizes, Random selection, and diverse and non-diverse strategies based on adapted Effective Covariance and Convex Hull objectives. I evaluated FINALLY through 420 recommendation runs across ten systematically varied configurations. All evaluated
dataset sets satisfied the applicable target-size, duplicate-avoidance, snapshot-membership, required-
dataset, and metadata-filter requirements. All 40 deterministic strategy–configuration combinations were reproducible. Both the Effective-Covariance-based and Convex-Hull-based strategies produced the expected diverse-versus-non-diverse score ordering in all ten configurations. Under their corresponding objectives, the diverse strategies produced scores above all 30 configuration-specific Random results, whereas the non-diverse strategies produced scores below all 30 Random results. These results establish technical consistency for the evaluated FINALLY workflow and show that the implemented strategies follow their intended optimization directions within the investigated configuration space. They do not establish the scientific suitability, global optimality, or practical superiority of the generated selections.
Read the full abstract ▾
Numerical Analysis
On the sample complexity of the active subspace method
Fabio Nobile, Matteo Raviola and Raúl Tempone
Active subspaces identify low-dimensional linear structure in high-dimensional parameter-to-output maps by estimating the dominant eigenspace of a gradient covariance operator. In practice this covariance is replaced by a Monte Carlo
estimator built from a limited number of gradient evaluations. Classical analyses based on controlling the covariance error in operator norm lead to sample-complexity estimates that can be substantially more pessimistic than the sampling rules commonly used in computations. This paper studies the empirical active subspace method directly in the projection-error metric relevant for ridge approximation. We derive non-asymptotic quasi-optimality bounds governed by a regularized inverse Christoffel function associated with the gradient field. Under a bounded-gradient assumption, the resulting estimates already improve the sample-complexity estimates obtained from operator-norm covariance bounds. We then show that additional smoothness of the gradient map, expressed through membership in a reproducing kernel
Hilbert space, yields sharper coherence estimates and motivates tractable importance sampling from kernel diagonal measures. Furthermore, the same smoothness assumption yields a priori decay bounds for the population active subspace tail energy, which can be combined with our finite-sample estimate to prescribe rank, regularization scale, and sample size, allowing to fully characterize the a priori sample complexity. The abstract assumptions are verified for lognormal Gaussian and affine uniform parametric
elliptic PDEs using weighted summability of Hermite and Legendre series expansions.
Read the full abstract ▾
Computer Vision
EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning
Jingpu Yang, Fengxian Ji, Mingxuan Cui et al. (+4 more)
UAV video question answering requires separating camera motion from changes in the scene, but RGB-only
multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages. Factorized Visual Ego-Transitions (FVET) fits a robust image-plane transition and exposes motion, residual-support, and reliability factors. Reliability-Gated Ego-Transition
Memory (ReTEM) uses reliability-weighted updates for a bounded history and re-anchors it at cuts or sustained uncertainty. Ego-Aligned Spatial Evidence (EASE) warps supported visual features into each segment's local anchor and injects four spatial evidence
tokens per visual slice through zero-initialized residuals, without changing Qwen's visual-
token count. On SIS-Bench, EgoSIS-8B obtains 89.9% perception, 82.5% perception-plus-
memory, and 76.2% overall accuracy, with the largest gains concentrated in self-awareness perception and
memory. The adapter thus provides an interpretable interface between optical flow and spatial
reasoning.
Read the full abstract ▾
All authors Jingpu Yang, Fengxian Ji, Mingxuan Cui, Yilin Sun, Hang Zhang, Jianhua Zhu, Yufeng Wang
Discrete Mathematics · Cross-listed from math.CO
Abelian Cayley High-Dimensional Expanders with Polylogarithmic Degree
Songtao Mao
We construct an explicit infinite family of simple two-dimensional Cayley complexes over $\mathbb{F}_2^n$ whose degree is
polynomial in $n$ and whose nontrivial vertex-link
eigenvalues lie in $[-\lambda,\lambda]$ for every fixed $\lambda>0$. For every fixed $d\ge2$, we also obtain an explicit infinite family of weighted $d$-dimensional Cayley complexes over $\mathbb{F}_2^n$ with codimension-two local spectral norm at most $1/d$ and Cayley degree $\Theta_d(n)$. Our two-dimensional construction uses evaluation at rational points of algebraic curves to produce projective direction sets and many functions affine along these directions, which may be useful for further constructions and improvements.
Read the full abstract ▾
Sound
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
Ziyang Ma, Zhikang Niu, Wenming Tu et al. (+30 more)
We introduce AuK, an open-source foundational model that unifies
speech generation and editing through a common interface of natural-
language instructions and audio context. To support this broad capability set, we construct approximately 3.03 billion instruction–audio instances and 1.95 million hours of effective supervision across five task families:
speech generation, content editing, enhancement and separation, paralinguistic editing, and acoustic editing. AuK combines a
multimodal large
language model for semantic conditioning, an VAE jointly trained on
speech, general audio, and music for acoustic conditioning, and a hybrid rectified-flow
Transformer that performs dual-stream MMDiT blocks followed by unified single-stream DiT blocks for generation. Training begins with generation-only warm-up and proceeds to joint generation–editing pre-training. We then apply complementary post-training strategies: human-feedback preference optimization for open-ended editing and reward-based reinforcement learning for
speech generation. To reduce inference cost, we further distill the model with consistency initialization and task-routed Decoupled DMD. The resulting AuK-Flash performs 4-step inference without classifier-free guidance and achieves a 4.5 wall-clock speedup over the full model under matched conditions. Experiments demonstrate leading performance on zero-shot and instruction-controlled
speech generation and general instruction-guided editing, while remaining competitive on signal-level restoration tasks. We release both the source code and model weights to support reproducibility and further research.
Read the full abstract ▾
All authors Ziyang Ma, Zhikang Niu, Wenming Tu, Tianrui Wang, Ruiqi Yan, Junxi Liu, Yanru Huo, Nickk Huang, Yang Liu, Qicong Xie, Zeyu Xie, Hui Wang, Haitao Li, Zixuan Jiang, Yalin Li, Jie Fang, Yifan Duan, Zeyue Tian, Guangzheng Li, Haina Zhu, Shuyi Wang, Jinwen Wang, Mingyu Cui, Tian Tan, Auden, Sen Liang, Steve Yves, Shan Yang, Liefeng Bo, Zilong Zheng, Kai Yu, Eng-Siong Chng, Xie Chen
Computation and Language
When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA
Manikandan Ravikiran and Siddharth Vohra
Language models often receive a question together with a claim about what another source answered. We audit whether such claims destabilize answers in multiple-choice question answering. For each item, we hold one wrong option fixed across misleading conditions and vary the cue template attached to it. We introduce neutral-conditioned misleading cue adoption rate (NC-MCAR), which measures switches to that option only on valid cued trials where the same model first selected the gold answer under a neutral
prompt. This is a measure of answer instability, not proof that the model knew the answer or that all deference is irrational. We evaluate four instruction-following models on MMLU-Pro and IndicMMLU-Pro in English, Hindi, Bengali, Tamil, and Telugu. Across 220{,}000 outputs, the expert template yields 41.1% aggregate NC-MCAR, compared with 12.5% for the majority template. These two conditions use the same wrong option and final instruction. Filler accuracy remains well above expert-wrong accuracy, while correct-cue
prompts have high valid-response accuracy. The audit documents answer instability relevant to grounding under the tested forced-choice
prompts: a bare, unverified source claim can outweigh an answer that was previously consistent with the task evidence.
Read the full abstract ▾
Systems and Control
Unifying Power Flow and Electromagnetic Transient Modeling
Tina Gao, Aayushya Agarwala, Timothy McNamara et al. (+1 more)
Grid tools are separated by timescales: steady-state analysis is performed by power flow (PF), whereas the fastest dynamics are captured by electromagnetic transient (EMT) simulation. Although operating at varying timescales, different tools should produce consistent results when analyzing the same grid conditions. However, the PF steady-state solution does not match the time-to-infinity EMT response. This mismatch exists because simplified device models in PF are inconsistent with the "ground truth" EMT models derived from first principles. As inverter-based resources (IBRs) and data centers strip away inertia and operating reserves, approximations used in PF risk grid security by missing violations. To address this, we introduce a steady-state framework that uses full-physics EMT models for high-fidelity steady-state grid analysis. The challenge lies in systematically formulating algebraic frequency-domain representations of dynamic power devices that are naturally described in state-space form. Our tool, SALT (Steady-state After Last Transients), constructs steady-state representations that exactly capture grid device physics when embedded into transmission networks. The approach exploits the structural properties of power device models and the single-harmonic, balanced nature of the transmission system. Results demonstrate SALT achieves EMT steady-state accuracy while delivering a 1x10^6 times speedup. We demonstrate that SALT can capture security threats in contingency scenarios without exception — whereas PF-based analyses reported 75% fewer rated line violations, 18% fewer Q-limit violations, and 7% fewer voltage violations.
Read the full abstract ▾
All authors Tina Gao, Aayushya Agarwala, Timothy McNamara, Lawrence Pileggi
Systems and Control
The consequences of high SMR operating costs in electricity markets
Pradyumna Rao, Daniel T. Kaffine and Bri-Mathias Hodge
As US power
markets contend with growing demand for firm generation, the
nuclear industry has offered Small Modular Reactors (SMRs). However, how these concepts would fare in a rapidly evolving power grid is unclear, given the paucity of operational examples. Current literature, informed by substantial cost escalations for traditional
nuclear plants, focuses on the investment costs SMRs need to achieve for private investment feasibility. However, this work finds that the operating and marginal costs of SMRs are more critical to economic feasibility in
market environments. This work dispatches SMRs using a flexible operations model, considering revenue from two main electric
markets, capacity and wholesale energy
markets, with and without policy support. Manufacturer advertised costs for investment and operating costs are used, with fuel costs calculated from manufacturer provided design parameters. Results indicate that SMRs are uneconomical primarily because investment cost reductions are offset by increased marginal costs. As such, an environment of prices and subsidies beyond historic norms are necessary to attract private investment at manufacturer advertised cost
benchmarks. Current SMRs are as profitable as advanced estimates of the AP1000 traditional
nuclear reactor, and if investment costs escalate at the average rate for
nuclear projects, they are similar to Vogtle 3 & 4. In projected future power
markets, reductions in marginal cost may be more beneficial than those in investment costs.
Read the full abstract ▾
Robotics
Robot Motion as a Keyed Communication Channel
Benjamin Chang, Michael Amir, Manon Flageat et al. (+1 more)
Messages from electronic devices are conventionally received as text, audio, or
radio signals. But
robots move with rich, articulate motion in the real world, opening up the possibility of transmitting messages through motion itself. In this paper, we consider the problem of motion-based communication, where we seek to modify a
robot's movements so as to transmit messages detectable from remote sensing (e.g.,
video or motion capture), without degrading policy performance. We introduce a method for messaging through motion capable of encoding arbitrary message content over short payloads - such as an
agent's current intent - as noise in any pre-trained policy's actions. This brings a new kind of robustness to
robot communication: this 'physical' channel complements standard wireless communications channels but does not depend on them, requiring no extra hardware nor the establishment of a direct link to the
robot. We systematically characterize the space of encoding schemes and derive design heuristics, then validate them across simulated environments and real-
robot deployment; on real
robots running at 50 Hz, four
robots jointly recover an 8-bit message at an aggregate 0.8 bits/s.
Read the full abstract ▾
All authors Benjamin Chang, Michael Amir, Manon Flageat, Amanda Prorok
Computation and Language
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents
Wenbo Gao, Zhaomou Song, Zhiyuan Ji et al. (+7 more)
Autonomous
agents powered by large
language models (LLMs) continuously accumulate experience through interaction, creating an opportunity to improve future behavior through self-
evolution. A fundamental challenge is how to transform abundant, task-specific interaction experience into reusable model competence without sacrificing the ability to adapt rapidly to newly observed evidence. Explicit textual states, such as skills and
agent harnesses, provide fast, human-readable and editable adaptation, but incur persistent dependence on external context; parametric policies provide compact and reusable competence, but are substantially slower to update. We present Experience Funnel, a self-evolving framework that couples fast state adaptation with slow policy consolidation in an alternating loop. Interaction trajectories are first distilled into an explicit textual state, where newly acquired experience can be rapidly incorporated and validated. The framework then selectively identifies state-enabled behavior that remains useful across state revisions and consolidates it into the policy through transition-aware
distillation. The updated state–policy pair subsequently generates new rollouts, providing fresh evidence for the next round of state adaptation and policy consolidation. Experiments across diverse
agent benchmarks show that Experience Funnel consistently improves
agent capability over state-only
evolution and policy-internalization approaches, while progressively converting useful explicit experience into autonomous policy competence.
Read the full abstract ▾
All authors Wenbo Gao, Zhaomou Song, Zhiyuan Ji, Renxi Liu, Xing Li, Xianzhi Yu, Xiaoguang Li, James Chung-wai Cheung, Weizhe Lin, Yaoyuan Wang
Computer Vision
Data-Efficient Crosswalk Segmentation from Overhead CCTV via Confidence- and Geometry-Guided Pseudo-Labeling
Abdirashid Omar and Jonghyuk Park
Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabeled CCTV frames. A source-domain experiment trains a 31.0M-parameter custom U-Net on 3,300 first-person-view (FPV) images and obtains 93.05% IoU on its 330-image FPV test split. This result is a source baseline, not transferred performance: the released CCTV notebook instantiates a 42.0M-parameter DeepLabV3-ResNet50 from torchvision weights, and no compatible mapping from the U-Net checkpoint is implemented. Training on 201 manual CCTV images and selecting on 40 held-out manual masks yields 88.91% IoU. The model then predicts all unlabeled frames; image-level certainty and a largest-component area prior rank the candidates, and the top 1,000 attain mean certainty 0.976 and mean combined score 0.988. A repository audit shows that the reported second-stage 98.52% IoU was measured on a 150-image split containing only teacher-generated pseudo-masks. Because of a directory-layout mismatch, the executed combined-data loader found zero manual samples and split 1,000 pseudo-labeled samples into 850 training and 150 evaluation samples. We therefore report 98.52% as internal pseudo-label agreement rather than human-ground-truth accuracy. The defensible target-domain result is 88.91% IoU on the 40 manual validation images. Batch-one FP32 inference at 512 x 512 requires 12.98 ms, corresponding to 77.03 FPS, on an NVIDIA RTX A6000 48 GB GPU. These findings support the practicality of confidence-and-geometry filtering while also showing why pseudo-label evaluation must remain isolated from the labels used for self-training.
Read the full abstract ▾