Information Retrieval
Improving disruptive research in the EU: why strengthening European Research Council grants alone is not enough
Alonso Rodríguez-Navarro
Disruptive innovation in the EU is not sufficiently competitive; this weakness puts at risk the social benefits that its citizens take for granted. This report argues that, in addition to addressing structural and economic deficiencies, the EU must improve disruptive research to strengthen its disruptive innovation capacity. Currently, the level of disruptive research is too low. Using
graphene research as an example, for which the EU has a specific programme, this report shows that Germany, France, Italy, and Spain cannot compete with Singapore. Even more concerning, the research funded by the European Research Council on
graphene fails to compete with research conducted in Singapore. Similarly, the EU is far from competing with the USA or China. A few examples in this report and cited references evidence that the situation is similar in other technologies. To overcome this situation, the EU must adopt drastic changes in research policy. However, such changes face a vanity culture among policymakers and, perhaps, scientists who have been proclaiming an inexistent research excellence for decades. Without drastic changes, the prospect of the EU becoming a technological leader at the level of the USA and China cannot be considered realistic.
Read the full abstract ▾
Audio and Speech Processing
Speech Language Models for Full-Meeting Speaker Diarization: Capabilities and Limitations
Jialu Li, Jinchuan Tian and Shinji Watanabe
Recent advances in
Speech Language Models (SpeechLMs), which integrate large
language models with
speech foundation models, have enabled unified sequence modeling of
speech processing tasks. However, many SpeechLM-based approaches to speaker diarization (SD) are tightly coupled with automatic
speech recognition (ASR) and evaluated using word-level metrics, making it difficult to assess SD performance independent of ASR accuracy. In this work, we investigate ESPnet-SpeechLM as a
token-based backbone for generating SD hypotheses, formulating SD as autoregressive generation of structured
tokens conditioned on acoustic input. We systematically compare two output representations: an event-based representation that explicitly models speaker turn onset and offset timestamps, and a frame-based representation that predicts frame-level speaker activity. To provide structured conversational cues, we further incorporate auxiliary tasks including
speech activity detection, overlapped
speech detection, and speaker turn counting within the output sequence. Across multiple meeting
datasets, we find that event-based representations produce more stable and consistent SD outputs than frame-based representations. Our analysis shows that outputs generated by SpeechLMs encode useful temporal SD structure, but full-meeting SD remains limited by recording-level speaker tracking and overlap-related misses. Explicit speaker-linking post-processing substantially reduces speaker confusion, suggesting that robust SpeechLM-based SD requires persistent speaker tracking and overlap-aware generation.
Read the full abstract ▾
Robotics
Search, Ground, Plan: Functional Sufficiency for Task and Motion Planning under Incomplete Scene Knowledge
Narendhiran Vijayakumar, Nav Singhal, Girish Varma et al. (+1 more)
Foundation models (FMs) have expanded task and motion planning (TAMP) to manipulation problems specified through
language and visual observations. However, incomplete scene knowledge leaves a critical gap between understanding what the task requires and knowing whether the physical scene can actually realize it. We introduce GRAB-TAMP, an FM-based TAMP framework that searches for scene entities required for task completion, grounds functional roles to valid physical objects, and plans only after a complete joint assignment establishes functional sufficiency. We represent the task through functional roles, relations, and assignment constraints, and incrementally inspect the scene while requirements remain unresolved, verifying candidate objects through semantic,
geometric, and relational checks. We evaluate GRAB-TAMP across 32 scene variants spanning Kitchen, Living Room, and Workshop domains. Across 200 feasible trials, our approach achieves 54.0% end-to-end success with 67.3% plan goal coverage. Compared with three FM-based TAMP frameworks under the same execution setting, GRAB-TAMP improves end-to-end success by 25.7 percentage points over the mean baseline. Implementation and evaluation code: https://github.com/Narendhiranv04/GRAB-TAMP
Read the full abstract ▾
All authors Narendhiran Vijayakumar, Nav Singhal, Girish Varma, Antony Thomas
Information Theory
Black-Box Attack for IRS-Aided Communications with BER-Only Feedback
Zhengkai Tu, Xinyue Xiang and Jimmy Huang
Intelligent reflecting surface (IRS) has emerged as a promising wireless technology for enhancing legitimate communications. In this paper, we investigate an IRS-assisted multiuser MISO downlink network in which an attacker reconfigures the IRS to degrade legitimate data transmission. Specifically, we consider a black-box attack setting in which the attacker has access to neither channel information nor symbol-level observations and can observe only the BER reported by each user. The objective of the attacker is to identify an IRS configuration that maximizes the minimum BER among all users under a limited budget of non-repeated tests. To address this BER-only black-box attack problem, we propose PRIS, an online search method that learns effective phase transitions from previous trials and progressively narrows the search from large-block modifications to single-element refinement. Specifically, an annealed user-balancing reward and prioritized replay are incorporated to exploit noisy BER feedback. Numerical results demonstrate that PRIS achieves a higher minimum BER than existing
benchmarks.
Read the full abstract ▾
Information Retrieval
Inherit4Rec: Parameter Inheritance for Efficient Scaling of Recommendation Models
Ruihao Zhang, Bo Chen, Xiao Wang et al. (+8 more)
Scaling model capacity has emerged as an effective approach to overcoming performance bottlenecks in industrial recommender systems. However, repeatedly training new models from scratch requires large amounts of data and substantial training resources. Parameter inheritance provides a promising route for both dense model growth and sparse conversion, yet existing methods for LLMs are primarily designed for static corpora and can suffer sharp performance drops under dynamically evolving recommendation data. To address these challenges, we propose Inherit4Rec, a parameter-inheritance framework that supports both Dense-to-Dense (D2D) growth and Dense-to-Sparse (D2S) conversion. Inherit4Rec-D2D combines hybrid growth with asymmetric training to preserve the forward function at expansion and maintain update continuity. Inherit4Rec-D2S constructs SMoE networks through co-activation-aware partitioning with a load-balancing loss, preserving dense-model capabilities while promoting balanced expert activation. Experiments on KuaiRand-1K and an industrial short-
video recommendation
dataset show that both transformations consistently outperform the SOTA inheritance baselines across all prediction objectives. These results demonstrate the effectiveness of Inherit4Rec for continual capacity expansion and computation-efficient sparse conversion in industrial recommender systems.
Read the full abstract ▾
All authors Ruihao Zhang, Bo Chen, Xiao Wang, Jinlong Jiao, Tijian Hu, Qinglin Jia, Xiuqiang He, Xiangyu Zhao, Chaoyi Ma, Ruiming Tang, Wenwu Ou
Instrumentation and Detectors
Single-electron detection in a high-purity Ge device
Antoine Armatol, Corinne Augier, Laurent Bergé et al. (+69 more)
High-purity germanium (HPGe) detectors are among the most powerful instruments for gamma ray spectroscopy, combining exceptional energy resolution with large active volumes. Although they operate close to the fundamental resolution limit at high energies, their performance at very low energies has long been limited by electronic noise, restricting detection thresholds to above approximately 30 electron-hole pairs ($\sim$100 eV). Here we introduce a cryogenic HPGe detector architecture that achieves single electron-hole pair sensitivity by calorimetrically measuring ionization at temperatures near 20 mK. The device integrates a NbSi transition-edge sensor into a point-contact-inspired geometry, concentrating athermal
phonon energy generated during charge drift and enabling eV-scale sensitivity ultimately set by the
semiconductor band gap. Beyond single-charge detection, the device rejects the low-energy excess background that limits existing cryogenic low-threshold technologies, establishing a pathway towards discrimination between electron- and
nuclear-
recoil events below 100 eV. These advances open a route towards next-generation detectors for direct dark matter searches, coherent elastic
neutrino-
nucleus scattering, and
nuclear reactor monitoring for non-proliferation applications.
Read the full abstract ▾
All authors Antoine Armatol, Corinne Augier, Laurent Bergé, Julien Billard, Harvey Birch, Juliette Blé, Clarence Chang, Yen-Yung Chang, Luke Chaplinsky, Gordon Cline, Alec Cochard, Ion Cojocari, Jules Colas, Simon Connolly, Maryvonne De Jesus, Pierre de Marcillac, Kamil Dwinger, Romain Faure, Simon Fiorucci, Maurice Garcia-Sciveres, Jules Gascon, Ryan Gibbons, Gil Gilchriese, Cloé Girard-Carillo, Wei Guo, Leila Haegel, Scott Haselschwardt, Scott Hertel, Tyler Horoho, Keith Hunter, Leslie Juigne, Alexandre Juillard, Alex Kavner, Jacob Lamblin, Tatiana Le-Bellec, Junsong Lin, Rupak Mahapatra, Stefanos Marnieros, Claire Marrache-Kikuchi, Nicolas Martini, Will Matava, Daniel McKinsey, Connor McLaughlin, Johann Menu, Knut Moraa, Valentina Novati, Emiliano Olivieri, Björn Penning, Mark Platt, Denys Poda, Matt Pyle, Yinghe Qi, Rafsan Rabbi, Ivar Rydstrom, Bernard Sadoulet, Silvia Scorza, Bruno Serfass, Peter Sorensen, Gabrielle Soum-Sidikov, Samara Steinfeld, Henry Su, Toki Suzuki, Ronald Vaughn II, Charlie Veihmeyer, Paul Vittaz, Gensheng Wang, Yue Wang, Michael R. Williams, Joanna Wuko, Volodymyr Yefremenko, Alexandre Broniatowski, Louis Dumoulin
Group Theory
Octonions, Albert vectors and the group ${}^2 \mathrm{E}_6(F)$
John N. Bray, Yegor Stepanov and Robert A. Wilson
We extend the explicit octonionic approach to groups of type $\mathrm{E}_6$ to the twisted groups ${}^2\mathrm{SE}_{6,K}(F)$ associated with a quadratic Galois extension $K/F$. These groups act on the Albert space over $K$, preserving the Dickson–Freudenthal determinant and a Hermitean form. When the field norm $K^{\times}\to F^{\times}$ is surjective, we give explicit generators and coördinate proofs of the three-orbit
theorem on white points and of the stabilisers of representative white vectors. Under this hypothesis we also prove simplicity of the central quotient. Over finite fields we recover the classical orbit lengths and group orders from the stabiliser orders and the total number of white points. Finally, without assuming norm surjectivity, we show that the two isotropic white-point orbits remain unchanged, while the non-isotropic orbits are parametrised by $F^{\times}/\mathrm{N}_{K/F}(K^{\times})$.
Read the full abstract ▾
Fluid Dynamics
Channel confinement mollifies roll wave instabilities
Jake Langham, Cyril Gadal, Jamie P. Webb et al. (+2 more)
Under certain conditions,
gravity currents spontaneously develop large-amplitude streamwise undulations on their free surfaces ('roll waves'). The effect of channel geometry on this instability is investigated herein. Via a section-averaged stability analysis conducted independently of the rheology of the flowing material, convex open channels are found to be stabilising, relative to unconfined flows. This is shown to agree with experimental observations of laterally shallow currents of water and dry granular material in trapezoidal channels. For such flows, the influence of the geometry can be characterised by a single dimensionless parameter, which predicts stabilisation as the channel width narrows. Including the cross-stream velocity profile in the analysis further stabilises predictions and can render steady flows in triangular channels unconditionally stable - a finding borne out by our experiments. Consequently, laterally tilting a trapezoidal channel can also stabilise flows by adjusting the wetted region towards a triangular one. Implications for observations in natural channels are considered by adapting an existing model of roll waves in the Illgraben, Switzerland, to incorporate channel geometry. The resulting simulations produce suitable waves for a realistic cross-section, but are stabilised by a modest narrowing of the channel. Complementary nonlinear wave solutions are then constructed and used to show that channel confinement also diminishes amplitudes of observed waves. Finally, exceptions to the analysis are discussed, including the possibility for static material to shield waves from the effects of geometry. We demonstrate this using observations of undamped granular avalanches travelling through an arrested deposit in a triangular chute.
Read the full abstract ▾
All authors Jake Langham, Cyril Gadal, Jamie P. Webb, Chris G. Johnson, J. M. N. T. Gray
Combinatorics
Degree sequence condition for pancyclicity in tough graphs
Songling Shan and Zachary Warren
Let $t \ge 1$ be an integer, and let $G$ be a $t$-tough $n$-vertex graph with degree sequence $d_1, d_2, \ldots, d_n$ in non-decreasing order. In 1995, Hoàng conjectured that if $G$ is
Hamiltonian and, for every integer $i$ satisfying $t\le i<n/2$, $d_i\le i$, and $d_{n-i+t}<n-i$, one has $d_j + d_{n-j+t} \ge n$ for all $j$ with $i < j < \frac{n}{2}$, then $G$ is pancyclic or bipartite. In this paper, we disprove the
conjecture for $t = 1$ and confirm it for all $t \ge 7$.
Read the full abstract ▾
Combinatorics
Improved upper bound on the number of distinct k-decks for any k and alphabet size by counting the independent parameters
Arman Nilforoushan and Farzad Parvaresh
Data stored in synthetic DNA is retrieved by shotgun sequencing, which returns short subsequences rather than the stored word itself. A natural abstraction of this readout is the $k$-deck of a word: the vector recording how often each word of length $k$ occurs as a subsequence. Two stored words are distinguishable from their readouts exactly when their $k$-decks differ, so the number $D_{q,k}(n)$ of distinct $k$-decks of words of length $n$ over an alphabet of size $q$ measures what a length-$k$ readout retains. We analyse the degrees of freedom remaining in a $k$-deck once all shorter decks are fixed. Within each class of words having prescribed letter multiplicities, the length-$k$ entries are confined to an affine subspace whose dimension is exactly the number of Lyndon words with the same multiplicities, which we give in closed form as a Möbius sum. Writing $L_q(j)$ for the number of Lyndon words of length $j$ over an alphabet of size $q$, we deduce the improved upper bound \[ D_{q,k}(n)=O\!\left(n^{E_q(k)}\right),\qquad E_q(k)=\sum_{j=1}^{k}j\,L_q(j)-1 . \] In the case of a binary alphabet this bound satisfies $D_{2,k}(n)=O\!\left(n^{4\cdot 2^{k-1}}\right)$. We then prove matching lower bounds in the first two nontrivial cases: $D_{q,2}(n)=\Theta\!\left(n^{q^2-1}\right)$ for every alphabet size $q$, and $D_{2,3}(n)=\Theta(n^{9})$ for the binary alphabet. The latter confirms, for $q=2$ and $k=3$, our
conjecture that the upper bound has the correct degree for every $q$ and $k$.
Read the full abstract ▾
Fluid Dynamics
Equivariant Neural Prediction of the Stokes Resistance Tensors for Arbitrary Microparticle Shapes
Sanjay Pradeep, David Dandy, Candace S.J. Tsai et al. (+1 more)
The Stokes-flow hydrodynamics of an irregular microparticle is encoded by its grand resistance
matrix, a 6x6 tensor whose translational and rotational blocks (A and C) govern settling,
diffusion, and orientational transport. Empirical drag correlations compress these tensors to a single scalar, discarding drag's orientation dependence and the rotational response. We present an SO(3)-equivariant neural network that predicts the full symmetric positive-definite A and C blocks from a particle's spherical-harmonic surface representation, equivariant by construction to floating-point precision. Trained on 1.1x10^5 random shapes from near-spherical to very rough, with a sealed test set of 18,000, it achieves 1.4% and 2.7% mean relative error on the two blocks while evaluating each shape 4-5 orders of magnitude faster than the regularised-Stokeslet solver that generated its labels. A spectral-convergence study confirms the representation is faithful: truncating a shape at spherical-harmonic degree 15 changes its resistance by a median of 0.14% (translation) and 0.38% (rotation), while the training shapes, generated band-limited at degree 15, carry no truncation error. Across 1.16x10^6 orientation-sampled settling, rotation and
diffusion events, the surrogate reveals lateral drift up to 11 deg, rotational misalignment up to 46 deg, and shape-induced
diffusion spreads of 30% (translational) and 2.4x (rotational), all identically zero under any scalar or spheroid reduction. Even the orientation-averaged scalar friction the correlations target, accurate to 1.7-2.8% (median; 2.2-3.2% mean), carries no tensor orientation, whereas the surrogate reproduces that scalar to ~1% while supplying the full anisotropic tensors. A fast, equivariant tensor surrogate can replace both solver and scalar approximation in atmospheric
dust transport, microplastic fate and colloidal Brownian dynamics.
Read the full abstract ▾
All authors Sanjay Pradeep, David Dandy, Candace S.J. Tsai, Jeff D. Eldredge
Human-Computer Interaction
Deciphering the Babel of Play: A Human-AI Collaborative Approach for Large-Scale Cross-Language Analysis of Game Reviews
Zixiaofan Yang and Chang Xiao
We present a large-scale cross-
language analysis of game reviews using a human-AI collaborative framework that combines quantitative screening with
multilingual large
language models (LLMs). Starting from 17 million Steam reviews across 30
languages and 2,000 top-selling titles, we select 28 games with notable cross-
language rating patterns. We then apply LLM-assisted content analysis to 442,162 reviews spanning 17
languages, with human researchers guiding codebook development and interpreting the results. Our findings reveal differences in both the aspects
language communities prioritize and how they evaluate them, highlighting the roles of narrative expectations, game mechanics and stability, localization quality, cultural proximity, and perceptions of developers and publishers. We also identify rare cases of cross-
language consensus. This work offers empirical insights into cross-cultural game evaluation and a scalable methodological approach to
multilingual content analysis that preserves human interpretation.
Read the full abstract ▾
Robotics
DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation
Guanxiong Chen, Yiduo Qu, Qianjun Xia et al. (+12 more)
While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility after generation, leaving an object's simulated response unused as feedback for repairing upstream errors. We present DiagGen, an agentic framework that turns a single in-the-wild image into a simulation-ready deformable asset through a generate–simulate–diagnose–refine loop. DiagGen constructs part-aware geometry and material parameters, then uses a VLM (
vision-
language model)-based
agent to select semantically informative regions, probe them in a physics simulator, observe material responses, and route evidence-backed repair cues to the responsible generation stage. Experiments on 40 assets show that diagnostics provides useful repair cues and can moderately improve the quality of generated deformable assets. Finally, we show that unlike assets generated from visual foundation models which may not be simulatable, DiagGen-generated deformables can be directly dropped into a high-fidelity physical simulator for the planning and simulation of contact-rich pick-and-place tasks. The project's website is https://diaggen.github.io/.
Read the full abstract ▾
All authors Guanxiong Chen, Yiduo Qu, Qianjun Xia, Pengyu Jing, Yixian Cheng, Bole Ma, Pengzhi Yang, Bingyang Zhou, Ziming Li, Shashwat Suri, Gongbo Sun, Chao Liu, Peter Yichen Chen, Ziqiu Zeng, Fan Shi
Machine Learning
When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation
Yufeng He
Diffusion models and
transformers have supplanted GANs for multivariate time series imputation, largely on grounds of GAN training instability. R3GAN (NeurIPS 2024) removes that instability via regularized relativistic losses with provable convergence, raising a natural question: do stable, modern GANs revive
adversarial imputation? We adapt R3GAN to 1D temporal data with a coarse-to-fine refinement framework and a frequency-domain discriminator, and audit 14 saved configurations across 3
datasets. Because these are heterogeneous single runs, the evidence is descriptive rather than a matched causal ablation. We report a negative result. All five saved mean/zero-start configurations improve by 48.4-70.2%. Among eight eligible non-legacy linear-start configurations, the mean change is -0.7% (range -3.0% to +1.1%); a separate -21.9% legacy logging anomaly is retained for provenance but excluded from that aggregate. In a saved Weather comparison, standalone R3GAN-1D underperforms BRITS by 5.8x. Crucially, we argue the common explanation (that GANs optimize distributional rather than point-wise objectives) cannot be the whole story, since
diffusion models also optimize distributional objectives yet achieve state-of-the-art imputation. Our saved reconstruction-weight sweep is consistent with the
adversarial signal being inert or harmful, but cannot identify its causal contribution; a matched discriminator-removed ablation is the key next experiment. We frame the precise reason a learned discriminator fails to provide useful refinement gradients (where a learned
diffusion denoiser succeeds) as an open problem, and offer practical guidance on when
adversarial refinement is worthwhile.
Read the full abstract ▾
Human-Computer Interaction
Measuring Smartphone User Experience through a Hierarchical Metric Framework via Social Media Reviews
Xiaoteng Pan, Mingang Lan, Chenrui Zhang et al. (+5 more)
Smartphone user experience (UX) is widely expressed in user-generated online discourse across platforms, creating opportunities for in-the-wild measurement at scale. However, existing UX instruments and review-mining approaches do not provide a smartphone-oriented, theory-grounded hierarchical measurement specification that supports consistent aggregation and comparison across heterogeneous platforms. In this research, we propose a hierarchical smartphone UX measurement framework and an interpretable computational pipeline that translates cross-platform reviews into structured UX metrics. The pipeline extracts localized experience evidence units, maps them to the hierarchy via coarse-to-fine classification, and quantifies evaluations with a unified five-level satisfaction sentiment model. We apply the approach to a stratified subset of approximately 20,000 Chinese social media reviews covering four major smartphone brands across three platforms. The resulting metrics separate what users discuss, captured by normalized mention frequency, from how they evaluate it, captured by mean five-level sentiment scores. This work provides a scalable and interpretable evidence base for cross-brand comparison and metric-level interpretation beyond raw review volume or single-platform observations.
Read the full abstract ▾
All authors Xiaoteng Pan, Mingang Lan, Chenrui Zhang, Yu Su, Weijie Liu, Yue Gao, Nan Gao, Haining Zhang
Robotics
Splat-CBF: Safe Next-Best-View Control in 3D Gaussian-Splat Maps
Amirhossein Mollaei Khass, Athanasios Cosse and Nader Motee
Where to look and how to move? A
robot navigating an unmapped environment must do both at once, and the two goals pull against each other. The regions most worth observing are the ones the map knows least about, and those are exactly where the
robot cannot trust its collision margins. We resolve this tension by introducing Splat-CBF, an active perception control barrier function that steers the camera toward the next best view while collision avoidance is enforced as a hard constraint. Safety is enforced by a risk-aware control barrier function that turns the Average Value-at-Risk of the Gaussian field into a single smooth hard constraint. Perception is enforced by a second barrier that rewards camera orientations with high expected Fisher information gain near the
robot's planned path. The two meet in a quadratic program where safety is hard and perception is soft, with a slack penalty that adapts to how often perception has already been relaxed and how close the
robot is to an uncertain region. We verify the method in indoor simulations, a Isaac Kinova manipulator and in experiments on an Ackermann-drive
robot. Our results assert that
robot navigates faster, gathers more information, and runs faster online than safety-only and perception-only baselines, giving up informative motion only when safety requires it.
Read the full abstract ▾
Mesoscale and Nanoscale Physics
Non-Hermitian Topology from Edge Transport in Hermitian Quantum Anomalous Hall Systems
Humian Zhou, Ming Lu, Chui-Zhen Chen et al. (+1 more)
Non-Hermitian physics, known for exotic phenomena like exceptional points and the skin effect, has been most prominently realized in engineered systems relying on controlled gain and loss. Here we show that it can also arise naturally as an intrinsic transport response of a globally Hermitian
quantum anomalous
Hall system, without the need for external non-Hermitian engineering. We show that the interplay between unidirectional
chiral edge modes and diffusive normal edge modes induces intrinsic non-reciprocal transport described by a continuum Hatano-Nelson model. Consequently, the non-Hermitian skin effect is encoded directly in experimentally accessible
Hall-bar observables: the electrochemical potential and local heat dissipation acquire chirality-dependent exponential spatial profiles, while the longitudinal conductance decays exponentially with system size and the
Hall conductance remains quantized. Using Landauer–B{"u}ttiker simulations, we confirm these transport signatures and identify
magnetic topological
insulators as a realistic platform for an intrinsic non-Hermitian transport response. Our results bridge non-Hermitian
topology with mesoscopic transport, opening a pathway toward non-Hermitian topological devices in solid-state systems.
Read the full abstract ▾
All authors Humian Zhou, Ming Lu, Chui-Zhen Chen, X. C. Xie
Probability
A short operator proof of Hoeffding inequalities for Markov chains
Oleksii Kachaiev
We give a short operator-theoretic proof of the sharp Hoeffding inequality for additive functionals of a Markov chain on a general state space with an $L^2(\pi)$ spectral gap, recovering the bound of Fan et al. (2021). We further show that the same argument yields the Hoeffding inequality of Neeman et al. (2024) for Markov-dependent random
matrices. The proof rests on two key observations. First, the transition operator factors as $P=Q_\lambda^{1/2} K Q_\lambda^{1/2}$ through the León-Perron operator $Q_\lambda$, with $\|K\|=1$. This bounds the moment generating function by a product of one-step operator norms. Second, each one-step operator is a rank-one perturbation of a multiplication operator, so bounding its norm reduces to verifying a scalar resolvent condition. Scalar convexity and the classical Hoeffding lemma then give the desired estimate. This bypasses the asymptotic cumulant generating function, essential-spectrum analysis, and extremal two-state comparison used in existing proofs. In the
matrix setting, the multi-
matrix Golden-Thompson inequality first reduces the moment generating function to an operator problem on a lifted
Hilbert space. The same two steps then apply: the projection onto constants becomes finite-rank, and a Schur-complement argument yields the same scalar estimate. The
matrix Hoeffding inequality of Neeman et al. (2024) follows. For complex Hermitian summands, working directly on the complex
Hilbert space improves the bound by a factor of $2$.
Read the full abstract ▾
Cryptography and Security
An LLM-Assisted AutoML Framework for Intrusion Detection in IoT Networks
Li Yang
Internet of Things (IoT) systems are increasingly deployed in smart homes, transportation, energy systems, and critical infrastructure. This broad connectivity improves service intelligence, but also enlarges the attack surface of IoT networks. Machine Learning (ML)-based Intrusion Detection Systems (IDSs) are widely used to identify malicious network threats and protect IoT systems, but developing effective ML-based IDS models often requires human expertise and repeated manual decisions on many procedures, including data pre-processing, feature selection, model selection, and hyperparameter tuning. Automated Machine Learning (AutoML) reduces this burden by automating steps of the ML pipeline using optimization techniques, but conventional AutoML methods can consume substantial optimization time because they explore broad candidate model families and large hyperparameter spaces. This paper proposes a Large
Language Model (LLM)-assisted AutoML framework for IoT intrusion detection. The proposed framework uses an LLM as a policy generator that converts
dataset profiles into bounded and validated AutoML policies for automated data balancing, automated feature engineering, and Combined
Algorithm Selection and Hyperparameter Optimization (CASH). Under an equal 10-trial budget, the proposed LLM-assisted policy achieves higher weighted test F1-score than traditional AutoML using the Tree-structured Parzen
Estimator (TPE) on both
datasets, reaching 99.680% on CICIDS2017 and 99.186% on IoTID20. Relative to the broader 30-trial Traditional AutoML-TPE baseline, the 10-trial proposed method reduces optimizer time by 63.7% and 49.9%, respectively, while achieving slightly higher F1-score. These results show that a bounded LLM policy can improve the quality of a low-budget AutoML search while retaining a clear efficiency advantage relative to a larger conventional search budget.
Read the full abstract ▾
High Energy Physics (Phenomenology)
The 248 keV LZ Recoil: A Possible Hint of Non-SM-Like Quark Yukawa Couplings with a Scalar-Portal Dark Matter
Bibhabasu De
The recent observation of an isolated
nuclear recoil event at an energy of $248\pm 23 (stat)\pm 23 (sys)$ keV, as reported by the LUX-ZEPLIN (LZ) collaboration, can be an intriguing signature for Beyond the Standard Model (BSM) possibilities, particularly for dark matter (DM). This paper explores a scenario in which the observed
recoil could simultaneously signal inelastic DM and a
flavor-specific New Physics (NP) interaction in the
quark sector. Considering a minimal extension of the Standard Model (SM) with two closely degenerate $Z_2$-odd vector-like
fermions (VLFs), interacting with the SM via a scalar portal, the analysis shows that a perfect agreement with the observed 248 keV
nuclear recoil can be achieved if the
quark Yukawa couplings are allowed to deviate from their SM values. The underlying quarkophilic NP can originate from a dimension-6 effective operator at a NP scale $\Lambda\leq \mathcal{O}(10)$ TeV. Future
collider searches can be crucial to test/falsify the proposal.
Read the full abstract ▾
Analysis of PDEs
Wave propagation of a non-conservative compressible two-fluid model with different pressures
Zhigang Wu and Yinghui Zhang
This paper investigates the wave propagation for a non-conservative compressible two-fluid model with unequal pressures in R3. This model is novel and fundamentally distinct from the classical single-phase compressible Navier-Stokes equations proposed by Liu-Wang [28]. This work fills a significant gap, as prior results largely apply only to conservative or partially conservative systems with specific Green's function cancellations. The non-conservative nature and the coexistence of two distinct-speed Huygens waves demand dedicated nonlinear coupling analysis and add further complexity. Our study reveals fundamentally different physical behaviors of this non-conservative two-phase model under equal and unequal interfacial pressures. For equal pressure, the model admits a stationary
diffusion wave comprising a single Huygens wave, analogous to classical Navier-Stokes equations. In sharp contrast, under unequal pressure, the stationary
diffusion wave consists of two Huygens waves propagating at different speeds–a novel phenomenon absent in the classical Navier-Stokes context.
Read the full abstract ▾
Discrete Mathematics
Counting and Covering in Nearest-Neighbour Representations of Boolean Functions
Martin Anthony
We study the number of prototypes needed to represent Boolean functions by nearest-neighbour classification. There are two distinct settings: the prototypes may be arbitrary points of Euclidean space, or they may themselves be required to lie in the Boolean cube. For unrestricted prototypes, we strengthen a known lower bound for almost all Boolean functions. The bound applies simultaneously to nearest-neighbour voting rules with any number of voting neighbours, and substantially narrows the gap with the known general upper bound. We obtain a VC-dimension bound for classes with a bounded number of prototypes, and show that it is sharp in order in dimensions at least four. We then study Boolean prototypes, beginning with symmetric threshold functions. A connection with covering designs expresses the minimum number of prototypes at every threshold level exactly in terms of a covering number, and leads to further exact results for related monotone functions, including disjunctive extensions and a characterisation of when a representation with a single negative prototype is possible. For a uniformly random Boolean function, the Boolean nearest-neighbour complexity, as a proportion of the cube, is asymptotically close either to one half or to one, with explicit limiting probabilities. In particular, almost every Boolean function requires at least approximately half as many prototypes as there are points in the cube, and one half is the largest proportion for which such a lower bound holds. Finally, we consider arbitrary symmetric Boolean functions. Their Boolean nearest-neighbour complexity is closely approximated by a weighted vertex-cover problem on paths. As a consequence, a uniformly random symmetric function typically requires prototypes amounting to $11/20$ of the cube. This is much larger than the upper bounds known when the prototypes are allowed to lie anywhere in Euclidean space.
Read the full abstract ▾
Number Theory
Counting number fields with symplectic Galois group
Anwesh Ray
Let $n\geq 1$ and let $\ell$ be an odd
prime. Let $G=\mathrm{PGSp}_{2n}(\mathbb{F}_\ell)$ or $\mathrm{GSp}_{2n}(\mathbb{F}_\ell)$, and fix a faithful transitive permutation representation $\pi:G\longrightarrow S_d$. We study degree-$d$ number fields whose Galois closures have Galois group $G$ and whose associated permutation representation is $\pi$. For $\sigma\in S_d$, write $\operatorname{ind}(\sigma)$ for its permutation index, namely $\operatorname{ind}(\sigma) = d-\#\{\text{orbits of $\sigma$ on $\{1,\ldots,d\}$}\}$. If $\tau$ denotes a
symplectic transvection, or its image in the projective
symplectic group, we prove that the number of such fields with absolute discriminant at most $X$ is bounded below by a constant multiple of $X^{1/(2n\,\operatorname{ind}(\pi(\tau)))}$. For the natural vector and projective actions, the exponents we obtain are asymptotically $1/(4n)$ of those predicted by the weak form of Malle's
conjecture as $\ell\to\infty$. The fields are constructed from the mod-$\ell$ Galois representations attached to the Jacobians of a one-parameter family of hyperelliptic curves. The proof combines large
symplectic monodromy for this family with a squarefree sieve.
Read the full abstract ▾
Machine Learning
The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits
Changkun Guan and Mengfan Xu
Adversarial multi-objective bandits hold the potential to help us optimize choices (arms) whose reward is a multidimensional vector chosen by an adversary and whose performance is measured by Pareto regret. We define loss as one minus reward and measure the easiness of a coordinate by the smallest cumulative loss of the arms on it, and call the coordinate easier when this quantity is smaller. Existing work suggests that in theory an easier coordinate may reduce Pareto regret. However, in practice, one may not know which coordinate is easier. On the negative side, we show that this lack of information eliminates the possibility: a smaller cumulative loss does not improve the worst-case order of Pareto regret. Precisely, let \(L_d\) be the smallest cumulative loss along coordinate $d$ over $T$ rounds. For \(K\ge4\) arms, \(T\ge6\) rounds, and at least 2 coordinates, we prove that the minimax expected Pareto regret is \(\Omega(\min\{T-L_0,\sqrt{K(T-L_0)}\})\). It is monotonically decreasing in \(L_0\), even when \(L_0=\min_d L_d\) itself is known. On the positive side, this result motivates the possibility that other coordinates, not just the easy one, may suffice to attain the optimal rate of Pareto regret. When $L_0$ is known, we apply Poly-INF to a fixed coordinate and obtain an upper bound on Pareto regret that exhibits the same order and thus matches the lower bound. Without such knowledge, we develop a reward-doubling version of Poly-INF that adapts to this unknown quantity while still attaining the matching minimax rate. Another implication is that it has no extra \(\log T\) factor and is independent of the number of coordinates.
Read the full abstract ▾
Earth and Planetary Astrophysics
Super-Earth Interiors Shrink by About 10% as They Crystallise
Tim Lichtenberg, Mara Attia, Harrison Nicholls et al. (+26 more)
Super-Earth
exoplanets are among the most abundant
planets known, yet their bulk densities leave the interior state degenerate. The static structure models used to interpret them, and the interior
retrievals built on them, typically describe the cold, solidified end state of an
evolution that begins hot and molten. During this magma ocean stage the interior, the outgassed atmosphere, and the surface co-evolve and set the long-term
climate and geophysics of super-Earths. We develop and validate a fully coupled model for the structural and thermal
evolution of super-Earth
exoplanets within the PROTEUS framework, including new and upgraded models of the interior structure, mantle energetics, and volatile outgassing. In volatile-poor super-Earths of 1 to 10 Earth masses, the silicate interior contracts by about 10 % of its molten radius through cooling and crystallisation, nearly independent of
planet mass and driven by the thinning silicate shell alone. The solidified radius is set by planetary mass and core fraction, insensitive to the host
star, irradiation, and initial thermal state. In contrast, volatile-rich super-Earths at and above about 5 Earth masses may not solidify: their thick outgassed atmospheres throttle the surface heat loss until the interior settles into a deep magma ocean, keeping the
planet inflated and limiting the contraction to about half its volatile-poor value. Mantle contraction alone thus shapes the low-mass
exoplanet transit population, motivating joint interpretation of atmospheric and geophysical signatures in upcoming
exoplanet surveys.
Read the full abstract ▾
All authors Tim Lichtenberg, Mara Attia, Harrison Nicholls, Mariana Sastre, Dan J. Bower, Karen Stuitje, Flavia C. Pascal, Laurent Soucasse, Daniel Apai, Patrick Bos, Robb Calder, Lorenzo Cesario, Lisa Dang, Emeline Decocq, Marijn van Dijk, Mohammad Farhat, Kaustubh Hakim, Tadahiro Kimura, Imre Kisvárdai, Sebastiaan Krijt, Yamila Miguel, Ioannis Panagiotou, Emma Postolec, Martin Schlecker, Sara Seager, Anat Shahar, Oliver Shorttle, Paolo A. Sossi, Wim van Westrenen
Human-Computer Interaction
How Did Writing Change At CHI? Analyzing 44 Years of CHI Writing Before and After the Introduction of Large Language Models
Thomas Kosch, Robin Welsch, Michael Hedderich et al. (+1 more)
The availability of Large
Language Models (LLMs) reshaped scientific discourse at a linguistic level. LLMs are assumed to homogenize academic writing, flattening it into a single generic lexical register. To understand how CHI writing has changed since the public release of LLMs, we analyzed full texts of 14,262 archival papers across all 44 CHI proceedings from 1982 to 2026, measuring readability, register, lexical diversity, and marker words typically produced by LLMs. We find that prose did not homogenize, while vocabulary grew more varied, and sentence rhythm remained irregular. CHI prose changed more between 2016 and 2026 than in other decades toward greater density, and reading ease has declined since 2022. The word-level shift began before any author used LLMs, so LLMs did not start the change but accelerated it. Reflecting on the history of CHI papers, we discuss what may have caused changes in prose and how LLMs accelerated them.
Read the full abstract ▾
All authors Thomas Kosch, Robin Welsch, Michael Hedderich, Christopher Katins
Statistical Methodology
Calibration of Time-Varying SEIR Models
Yisa Abolade, Yichuan Zhao and Gerardo Chowell
Mechanistic epidemic calibration can be sensitive to short-lived reporting anomalies that give a few observations high leverage under least squares (LSQ). We develop direct forward-solver least absolute deviations (LAD) calibration for time-varying susceptible-exposed-infectious-removed models fitted to reporting-interval incidence, with finite-horizon regularity and large-sample results. A phase-aware Monte Carlo study compares LAD and LSQ across three transmission drivers, four epidemic phases, five reporting mechanisms, and four forecast horizons. All 120,000 primary fits converged. LAD was favored in 56.7% of mean-absolute-error comparisons and 57.9% of weighted-interval-score comparisons overall; under isolated spikes, backlog release, or temporary underreporting, these proportions rose to 73.6% and 72.2%, with strong gains near the epidemic peak. Rolling-origin validation on four synthetic RAPIDD Ebola scenarios also identifies settings where LSQ is preferred, demonstrating the framework's ability to distinguish robustness gains from sustained-trend behavior. Multiple uncertainty and identifiability diagnostics, complete code and data, and an interactive application provide a reproducible computational workflow.
Read the full abstract ▾
Computation and Language
OmniEdu: Open Foundation Models for Learning and Teaching
Hao Liang, Qihan Lin, Meiyi Qiang et al. (+5 more)
Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional support. Existing educational
language models often focus on either problem solving or tutoring, with training mixtures organized by source or task rather than capability. We present OmniEdu, an open family of foundation models for K-12 learning and teaching. Its instruction-tuning corpus combines over 100 educational resources and general instruction sources, organized around four capabilities: subject competence, curriculum grounding, diagnostic
reasoning, and pedagogical action and scaffolding. Our pipeline integrates deterministic cleaning, semantic
auditing and rewriting, task-specific quality scoring,
token-budgeted diversity selection, and pedagogical instruction assignment. It yields 69,999 examples and 15.96M supervised response
tokens, including 60,951 education-specific examples. We fine-tune 4B, 9B, and 27B models and evaluate curriculum grounding, K-12 problem solving, and pedagogical tutoring, alongside general capability. Education-oriented tuning consistently improves all three educational
benchmark groups across model scales. OmniEdu-27B achieves 63.12% EM and 76.69% F1 on K12-Bench, 85.89% on MathFish, 86.95% on EDUMATH, and 78.74% in MathTutorBench's Scaffold setting. It also achieves the highest Teaching average on LongTutor among the evaluated models, at 3.02. These results demonstrate the value of curated, capability-balanced supervision for adapting general
language models to educational tasks spanning problem solving, curriculum understanding, and instructional support.
Read the full abstract ▾
All authors Hao Liang, Qihan Lin, Meiyi Qiang, Linzhuang Sun, Hengyi Feng, Mingrui Chen, Sizhe Qiu, Wentao Zhang
Machine Learning
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Chenyu Zhu, Ruoyu Zhao and Zhichao Lu
Modern
Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size and compute but not architectural structure: two architectures with identical parameter budgets but different depth-width, head, or FFN allocations receive identical scores yet behave differently. We propose Neural Spectral Capacity (NSC), a closed-form scalar grounded in the singular-value spectrum of each weight
matrix. Under standard random initialization, the Marchenko-Pastur law renders NSC computable from the architectural specification alone, with no model instantiation, data, or gradients. Its layer-wise additive structure admits NSC-DP, an exact dynamic-programming solver returning the architecture globally maximizing NSC under resource constraints in seconds on a CPU – a guarantee that black-box search over existing training-free proxies cannot provide. Empirically, NSC outperforms #Params, #FLOPs, and representative training-free proxies in ranking across seven
Transformer and CNN families (on FlexiBERT, $\tau = 0.505$ on pairs differing in #Params by less than 10%, where #Params collapses to 0.082); NSC-DP discovers a
Transformer-XL architecture on WikiText-103 that beats the human-designed baseline in 2 seconds; and prunes LLaMA-7B to the best 5.7B model across eight commonsense
reasoning tasks without any calibration data, about 5900x faster than the strongest training-free proxy baseline.
Read the full abstract ▾
Numerical Analysis
A fast spectral particle method for the Landau equation
Giacomo Borghi and Lorenzo Pareschi
We propose a fast deterministic particle method for the spatially homogeneous Landau equation. The method combines a particle representation of the solution with a
Fourier approximation of the nonlinear collision flux. Nonuniform fast
Fourier transforms are used to reconstruct the density from the particles and to evaluate the flux and density at the particle locations, while the convolutional structure of the flux enables its efficient computation by FFTs. For a fixed transform tolerance, the cost per time step is $\mathcal{O}(N+M^d\log M)$, where $N$ is the number of particles and $M$ the number of
Fourier modes per velocity dimension. We establish a consistency estimate for the reconstructed velocity field on regions where the reference density is bounded away from zero. The estimate separates the spectral truncation error from the particle-density reconstruction error, showing how the latter can dominate for sufficiently smooth densities. Two-dimensional numerical experiments with Maxwellian interactions illustrate the accuracy and efficiency of the method, its sensitivity to particle and spectral resolution, and the effects of filtering. Comparisons with a direct blob implementation demonstrate improved accuracy at a strongly reduced computational cost.
Read the full abstract ▾