Computer Vision
Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR
Bilal Sidiqi, Yipei Wang, Wen Yan et al. (+3 more)
Boundary delineation of anatomical structures in prostate MRI is often compromised by regional ambiguity. Automated segmentation methods relying on global overlap loss functions tend to be insensitive to surface deviations, leading to significant errors in ambiguous regions. Most existing uncertainty-aware methods treat uncertainty as a post-hoc quality indicator or prediction filter. We propose Contrastive Uncertainty Learning (CUL), a supervised framework that uses predictive uncertainty to directly guide representation learning. Using Monte Carlo Dropout, CUL identifies voxel-wise uncertainty and structures the
embedding geometry accordingly: low-uncertainty, correctly predicted features form stable voxels while high-uncertainty or misclassified features are actively repelled, preventing feature collapse at difficult boundaries. We evaluate CUL on a 589-scan 3D prostate MRI multi-structure segmentation task (8 anatomical structures) using a ViT with UperNet decoder architecture. Average Dice ($83.38\%$) remains comparable to the baseline ($83.35\%$), while surface distance decreases significantly ($p<0.001$) across 6 of 8 anatomical structures. A hard-case analysis reveals a $22{\times}$ asymmetry between significantly improved and degraded cases ($18.8\%$ vs $0.9\%$). Ablation studies show that removing uncertainty-guided sample selection eliminates improvements for the transition zone, while replacing the contrastive objective with a boundary loss additionally removes bladder improvements, demonstrating that both uncertainty-guided sampling and the contrastive objective are essential for the observed gains. These findings demonstrate that the proposed uncertainty-guided representation learning is a useful mechanism for reducing the risk of extreme errors in safety-critical medical segmentation
Read the full abstract ▾
All authors Bilal Sidiqi, Yipei Wang, Wen Yan, Shaheer U. Saeed, Daniel C. Alexander, Yipeng Hu
Data Structures and Algorithms
Subexponential Parameterized Approximation for Group-Fair Euclidean $k$-Center
Rudranarayan Kar, Diya Roy and Abhishek Sahu
Clustering is a basic tool for grouping data into meaningful classes, but in many applications the resulting clusters must also respect the
fairness conditions among different groups. We study this direction for the group-fair Euclidean $k$-center problem in fixed dimension, where the input points are partitioned into disjoint color classes, and every cluster must satisfy given lower and upper bounds on the fraction of each color. We give a separator-based recursive approximation
algorithm for the continuous-center setting. The main idea is to first reduce the continuous search space to a finite candidate center set and then use the
geometric sphere separators to break the instance into smaller subproblems. Our
algorithm gives a bicriteria approximation: the clustering radius is within a factor of $(1+\epsilon)$ of the optimum exactly fair solution, while the
fairness bounds are relaxed only by a multiplicative factor. For fixed dimension, number of colors, and approximation parameters, the running time is
polynomial in input size and subexponential in $k$. A recent IJCAI-ECAI2026 result gives a $(1+\epsilon)$-approximation for group-fair $k$-center in bounded doubling metrics with running time $(k/\epsilon)^{\mathcal{O}(k)}n^{\mathcal{O}(1)}$. In the fixed-dimensional Euclidean setting considered here, we improve the dependence on $k$ to subexponential, while allowing continuous centers. The
fairness guarantees of the two results are different: the previous work allows an additive
fairness violation, whereas our
algorithm uses a controlled multiplicative relaxation.
Read the full abstract ▾
Superconductivity
Bulk superconductivity in quintuple-layer square-planar nickelate La6Ni5O12
Mengzhu Shi, Mei Du, Hongyu Li et al. (+5 more)
Nickelate
superconductors, sharing a similar electronic environment with cuprate
superconductors, offer a promising platform for unraveling the mechanism of high-temperature superconductivity. However, the realization of superconductivity in these systems has so far been restricted to thin films or bulk samples under high-pressure. This limits the applicability of various experimental probes to study the mechanism of superconductivity, and hinders the potential application of the nickelate
superconductors. Exploring bulk superconductivity at ambient pressure is therefore essential to understand its origin and enable broader experimental research. Here, we report the realization of bulk superconductivity at ambient-pressure in quintuple-layer square-planar (SP) nickelate La6Ni5O12. The SP phase is obtained by performing topotactic reaction on the quintuple-layer Ruddlesden-Popper (RP) compound La6Ni5O16. Optimized reduction condition endows La6Ni5O12 with a superconducting state that exhibits onset transition temperature of ~ 18 K, as verified by both zero resistance and diamagnetic shielding effect. Pronounced hysteresis loops revealed by magnetization and torque magnetometry demonstrate the occurrence of
vortex pinning. Specific heat measurements on a polycrystalline pellet of La6Ni5O12 reveal a clear superconducting transition at ~18 K and a superconducting volume fraction of ~ 25%, which strongly supports the presence of bulk superconductivity. Our results establish an unprecedented bulk sample platform for investigating superconductivity in nickelates at ambient pressure, which paves the way for further experimental studies into the superconducting mechanism.
Read the full abstract ▾
All authors Mengzhu Shi, Mei Du, Hongyu Li, Zhiwei Wang, Zhengjie Wang, Ziji Xiang, Tao Wu, Xianhui Chen
Systems and Control
Robust Data-Driven Controller Synthesis from Sampled and Uncertain Frequency Response Estimates using Integral Quadratic Constraints
Luuk Marceau Spin, Maurice W. P. M. H. Heemels, Nathan van de Wouw et al. (+1 more)
In this paper, we develop a novel
MIMO controller synthesis method that relies solely on frequency-domain data of discrete-time systems. The approach is based on an iterative design procedure using integral quadratic constraints (IQCs). It generalizes existing data-driven methods that approximate semi-infinite IQC conditions by enforcing them on a finite set of measured frequency points. Such approximations do not provide guarantees on the continuous frequency axis and may fail to capture inter-frequency behavior. We address this limitation by formulating a convex optimization problem that preserves robustness guarantees over the entire frequency range. In particular, the proposed method explicitly accounts for inter-frequency behavior of both plant and controller, leading to certified robust stability and performance. The effectiveness and computational efficiency of the approach are demonstrated using experimentally obtained frequency response data from industrial-grade
semiconductor equipment. The synthesized controller is implemented on the physical setup, and its performance is validated in real-time experiments.
Read the full abstract ▾
All authors Luuk Marceau Spin, Maurice W. P. M. H. Heemels, Nathan van de Wouw, Roland Toth
Computation and Language
Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation
Joel Dag, Nikit Srivastava, Hamada M. Zahera et al. (+1 more)
Multilingual models share capacity across
languages, so adding
languages can hurt performance on existing ones. Mixture-of-experts models expand this capacity with little additional per-
token computation. Given this extra capacity, does adding experts reduce what each additional
language costs? To answer this question, we propose a repetition-aware joint scaling law relating number of active parameters, training
tokens per
language, number of experts, and
language coverage. Fitted on 26,300 per-
language loss observations from 64 pretrained configurations, our law reduces prediction error on held-out configurations by 28% relative to the strongest evaluated baseline. At matched number of active parameters and training
tokens per
language, 32 experts reduce the loss penalty of expanding from 12 to 200
languages by 83% compared with a dense model. Our law further shows that broader
language coverage favors more experts across a wider range of compute budgets, guiding capacity allocation as multilingual models scale.
Read the full abstract ▾
All authors Joel Dag, Nikit Srivastava, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo
Sound
Evaluating perceptual transparency of lossy music audio compression with Opus codec
Benjamin Martin and Romain Hennequin
Although the open-source Opus audio codec is widely used for digital audio streaming, its perceptual transparency threshold for high-bitrate music compression remains insufficiently evaluated. To establish this threshold, this study evaluates Opus across a two-phase ITU-R BS.1116-3 double-blind framework, analyzing Difference Grades using a Linear Mixed-Effects Model (LMM) and Two One-Sided Tests (TOST) for statistical equivalence. In a first phase with 21 qualified listeners and 23 music excerpts, 128 kbps achieves statistical in-distinguishability ($p = 0.456$) but narrowly fails strict equivalence to the uncompressed reference ($p = 0.064$). In Phase 2, Best Linear Unbiased Predictors (BLUPs) isolate the 10 most critical listeners and 8 most challenging samples for a stress-test. Under these worst-case conditions, 128 kbps is conclusively detected as degraded ($p = 0.030$), whereas 160 kbps successfully reaches perceptual transparency ($p = 0.747$) and strict statistical equivalence ($p = 0.024$). The study concludes that 160 kbps demonstrates perceptual transparency to uncompressed CD quality in critical listening environments. For reproducibility, we publicly release results for both phases, anonymized subject background info and sample characteristics.
Read the full abstract ▾
Cryptography and Security
P2Patch: Exploit-Guided Vulnerability Repair
Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat et al. (+7 more)
Large
language models are increasingly deployed as autonomous
agents for automated program repair, patching software vulnerabilities through multi-step
reasoning and tool use. Yet these systems typically validate a patch against the same evidence used to construct it – a static alert, sanitizer trace, published exploit, or test suite. A patch that blocks that one piece of evidence can therefore look successful while remaining vulnerable to the same vulnerability with some variation. We present P2Patch, a generative
adversarial repair system that treats each patch as a new attack target. Starting from a normalized vulnerability finding, an exploitation
agent constructs a reproducing proof of vulnerability (PoV), a patching
agent repairs the program, and the exploitation
agent then attacks the patched program for a distinct same-vulnerability exploit. Every successful exploit becomes a permanent repair requirement, and the final patch must block all PoVs accumulated during the patching process, with construction-time PoVs kept strictly separate from held-out evaluation oracles. Across 101 C/C++ and Java CVE subjects, this
adversarial loop surfaces a distinct confirmed exploit in 41% of runs after the patch has already blocked its original construction-time PoV. Against single-pass repair from the same finding using Claude Code, P2Patch raises held-out fix-closed coverage from 78.1% to 84.7% and beyond-upstream coverage from 42.1% to 62.5%. Under the same held-out oracles, it also certifies more attack paths as blocked than recent state-of-the-art agentic repair systems on overlapping subjects. These results show that
adversarial testing and independent security oracles expose repair gaps that one-shot validation misses.
Read the full abstract ▾
All authors Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat, Ali Javidi Ghasr, Maxime Newman Nereyabagabo, Kousha Amouzesh, Jaivir Malhi, Vinci Velasco, Alex Chung, Mohammad A. Tayebi
Computational Geometry
FPTAS for Polygonal Multi-Robot Motion Planning
Sayan Bandyapadhyay, William Lochet, Saket Saurabh et al. (+1 more)
We study multi-
robot motion planning in a polygonal environment with polygonal
robots. The setting of the problem consists of a polygonal domain $\mathcal{W}$ with $n$ vertices and $k$
robots $R_1,\dots,R_k$ translating in $\mathcal{W}$ each of which is represented by a polygon of constant complexity. Given a source configuration $\mathbf{s}$ and a target configuration $\mathbf{t}$ of the
robots in $\mathcal{W}$, the goal of the problem is to find a collision-free motion plan from $\mathbf{s}$ to $\mathbf{t}$ that is shortest with respect to some cost function. We present the first fully
polynomial-time approximation schemes (FPTAS) for motion planning with any fixed number $k$ of
robots, under the min-sum objective, the min-max objective, and the min-makespan objective. Here, the min-sum variant aims to minimize the total traveling distance of all
robots, the min-max variant aims to minimize the maximum traveling distance of a single
robot, and the min-makespan variant aims to minimize the total time cost under the assumption that all
robots move with a maximum speed $1$. The
algorithm directly generalizes to the problem in any fixed dimension $d$, with a polytope environment and polytope
robots. Our result settles an open question of Agarwal, Halperin, Sharir, Steiger [SODA'24] and Agarwal, Holmgren, Steiger [SODA'26], who gave an FPTAS for $k=2$ unit-square
robots and a bicriteria-approximation
algorithm for a fixed number $k$ of unit-square or unit-disk
robots, respectively. Compared to the previous results, our
algorithm is substantially simpler.
Read the full abstract ▾
All authors Sayan Bandyapadhyay, William Lochet, Saket Saurabh, Jie Xue
Machine Learning
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
Christos Panourgias, Roberto Stanzione, Adrien Petralia et al. (+2 more)
Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent
benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a
retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as
embedding-based representations. Our results show that RAMSAD outperforms existing baselines in In-Distribution (ID) settings and is the most robust selector in OOD, where, when selecting a small subset of detectors, it matches or exceeds ensembles that run the entire detector pool, at a fraction of their cost. Overall, we demonstrate that similarity-based
retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.
Read the full abstract ▾
All authors Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol
Number Theory
On the Hardy–Littlewood–Chowla conjecture
Guangshi Lü, Zhiwei Wang and Jie Wu
An old
conjecture dating back at least to Hildebrand's work in 1989, asserts that the Möbius function exhibits cancellation on shifted
primes; that is, $$\sum_{p\le x}\mu(p+2)=o(\pi(x)),\quad \text{or equivalently}\quad \sum_{n\le x}\Lambda(n)\mu(n+2)=o(x).$$ This is also a well-known model case for the parity problem in sieve theory. In this paper, we prove this
conjecture. As an application, we show that each of the two sets $\{p:\, \mu(p+2)=1\}$ and $\{p:\, \mu(p+2)=-1\}$ has asymptotic density $1/2$ among the
primes $p$ with $\mu^2(p+2)=1$: \begin{equation*} \lim_{x\to\infty} \frac{\#\{p\le x:\ \mu(p+2)=\kappa\}} {\#\{p\le x:\ \mu^2(p+2)=1\}} =\frac12, \quad \kappa\in\{-1,\,1\}. \end{equation*}
Read the full abstract ▾
Robotics
Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes
Chengyang Peng, Zhihao Zhang, Upama Pant et al. (+3 more)
Offline navigation demonstrations are
multimodal, because one observation often allows several valid actions, such as passing an obstacle on either side. Behavior cloning averages these actions, potentially leading to unsafe routes.
Multimodal policies must discover the alternatives from the data, but similar states can lead to different routes whose current actions overlap. In navigation, the alternatives have a
geometric cause and can be computed from one observation. We propose a hierarchical neural-network policy that computes candidate modes from local geometry and learns from demonstrations which mode to follow and how. A high-level policy selects a mode using the goal and its previous choice among a set of candidate modes, and a low-level policy turns it into an action. In simulation, the policy succeeds in over 95% of seen and unseen test cases, compared with at most 43% and 20% for four offline learning baselines and 79% and 67% for a heuristic that uses the same modes without learning. The simulation-trained policy also transfers to a LimX Tron 1 bipedal
robot.
Read the full abstract ▾
All authors Chengyang Peng, Zhihao Zhang, Upama Pant, Yiming Wang, Keith A. Redmill, Ayonga Hereid
Computer Vision
PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
Siqi Yang, Yimu Wang, Ziqi Cai et al. (+6 more)
A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's current field of view. A point-of-view (POV)
video captures such changes only after they enter its field of view, whereas panoramic
video records the surroundings in every viewing direction and has served as an intermediate representation of the world state in recent world models. Learning this task therefore requires synchronized POV and panoramic
videos of interacting players together with their actions, yet no existing
dataset provides this combination in Minecraft, an established testbed in which players act independently in a shared, modifiable 3D world. We present PAWA, a
dataset and framework for action-conditioned panoramic multiplayer world modeling. The
dataset pairs each player's POV
video with world-stabilized panoramic
video and aligned actions. Its distributed pipeline decouples CPU gameplay capture from GPU rendering, scales beyond 64 simultaneous players, and re-renders each recorded session under new observation configurations without replaying the gameplay. On this
dataset, we develop a dual-tower model that jointly predicts POV and panoramic
video and couples the two streams through cross-
attention that aligns
tokens observing the same direction in a shared world frame. We further introduce a quadratic-phase player encoding that provides many more player codes than existing rotary codes at the same
embedding dimension. Experiments show that PAWA outperforms state-of-the-art multiplayer world models in POV prediction quality while also producing high-fidelity panoramic predictions. The
dataset and collection pipeline are open source to support further research on multiplayer world models.
Read the full abstract ▾
All authors Siqi Yang, Yimu Wang, Ziqi Cai, Chengxuan Zhu, Shuchen Weng, Erwin Wu, Zhaofei Yu, Kaipeng Zhang, Boxin Shi
Algebraic Geometry
Chow groups of symmetric products of projective space
Youming Chen and Wenchuan Hu
We prove that the integral cycle class map for $\SP^d(\PP^n)$ is split injective, with finite cokernel annihilated by $d!$,and we determine the ranks of Chow groups for $\mathrm{SP}^d(\mathbb{P}^n)$. Compatible integral transfer retractions show that $\CH_q(\SP^d(\PP^n))$ stabilizes for $d\geq q$. An explicit nonalgebraic order two class persists under addition of points, producing a split cokernel summand even in the range $q\leq d$ and in the infinite symmetric product. For the smooth configuration open set, we identify the codimension two cokernel with third unramified cohomology and detect its ramification on a rational resolution. In contrast to addition, even multiplicities annihilate a nonzero Chow class.
Read the full abstract ▾
Machine Learning
MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
Junlin Chen, Wenhao Wang, Junchao Xu et al. (+5 more)
Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental graph learning, predictions are often dominated by recently learned classes, causing severe recency bias. Dynamic expansion can isolate knowledge across sessions, but many methods assume task-incremental settings and require task identities at test time to select branches or heads—information unavailable in class-incremental learning. Learnable routers offer an alternative, yet continual fine-tuning the router on new data can bias routing toward recent components. We propose MAEM, a replay-free, capacity-controlled dynamic mixture-of-experts framework for class-incremental graph learning. MAEM builds representations with Simplified Graph Convolution (SGC) and trains a dedicated expert for each new session, then freezes it to protect prior knowledge. For routing without task IDs or a shared trainable router, each expert uses a masked autoencoder (MAE); test nodes are assigned to the expert with the lowest reconstruction error, reducing routing-level recency bias. When the expert pool reaches a fixed capacity, MAEM merges the least-used experts via Git Re-Basin
alignment and further distills them into a fused expert using
topology-aware pseudo data synthesized from MAE distributions (DeepInversion-style), without storing or revisiting historical graph data. On four class-incremental graph
benchmarks, MAEM mitigates recency bias, outperforms strong continual graph learning baselines, and keeps model capacity bounded under strict replay-free learning.
Read the full abstract ▾
All authors Junlin Chen, Wenhao Wang, Junchao Xu, Qingsong Yao, Fei Xue, Li Sun, Xiao Wang, Ruijie Wang
Optics
Photoacoustic-guided reflection-mode wavefront shaping through dynamic biological tissue
Xuan Liu, Sacha Noimark, Wenfeng Xia et al. (+2 more)
Strong optical scattering limits the depth at which light can be focused and used for imaging in biological tissue. Photoacoustic (PA)-guided wavefront shaping enables non-invasive light focusing in scattering media, but most existing implementations require optical and acoustic access from opposite sides of the sample and a rigidly aligned free-space optical path, which have confined these demonstrations to thin or static samples. Here, we combine a real-valued intensity transmission
matrix (RVITM)
algorithm with a photoacoustic guidestar (PA-RVITM) in a reflection-mode configuration. Modulated light is delivered through a flexible multimode fiber passing through the central aperture of a focused ultrasound transducer, enabling optical illumination and acoustic detection from the same side of the sample without a free-space combiner. Fiber integration preserved the wavefront shaping performance, and the reflection-mode PA-RVITM system achieved sub-second wavefront optimization with a ~14-fold PA signal enhancement through a diffuser. In ex vivo chicken breast tissue, the enhancement decreased with tissue thickness, reaching ~3.5 through a 2-mm chicken breast layer, with a speckle decorrelation time of ~450 ms. By performing an independent RVITM optimization at each scan position, our system enabled photoacoustic microscopy of a black nylon wire through the same layer, reducing the imaged line width from ~141 {\mu}m to ~102 {\mu}m, close to the nominal diameter of ~100 {\mu}m. This work advances PA-guided wavefront shaping toward a compact, same-side implementation for future biomedical therapeutic and imaging applications.
Read the full abstract ▾
All authors Xuan Liu, Sacha Noimark, Wenfeng Xia, Sebastien Ourselin, Tianrui Zhao
Nuclear Experiment
Physics with Radioactive Ion Beams at the Nuclear Science Laboratory
W.S. Porter, D.W. Bardayan, M. Brodeur et al. (+13 more)
The University of Notre Dame is home to a rich history of nuclear science efforts, including some of the earliest developments in the production and creation of radioactive ion beams (RIBs). The resulting TwinSol facility stands as the longest continuously-operating RIB facility in the United States, and has enabled a wide range of experimental efforts in nuclear structure, astrophysics and fundamental
symmetries through in-flight RIBs one to two nucleons from stability. A recent upgrade to TwinSol via a third solenoid constituted the founding of the TriSol facility, which provides cleaner, better-focused RIBs to downstream experiments. In this paper, we present a summary of RIB science at the Nuclear Science Laboratory (NSL) with both TwinSol and TriSol and discuss recent upgrades and future experimental plans at the facilities.
Read the full abstract ▾
All authors W.S. Porter, D.W. Bardayan, M. Brodeur, C. Dembski, P.D. O'Malley, F. Rivero, W.W. von Seeger, C. Boomershine, O. Bruce, S.R. Carmichael, S. Coil, A.M. Houff, J.J. Kolata, D. Schroeder, A.A. Valverde, R. Zite
Nuclear Experiment
$^{16}$O(p,$\gamma$)$^{17}$F Reaction and the C and O Isotopic Ratios in Red Giant Branch Stars
D. Robb, P. McGlynn, M. Aliotta et al. (+55 more)
The $^{16}$O/$^{17}$O isotopic ratio is a widely used tracer of nucleosynthesis and mixing processes in red giant
stars. Its value depends on the rates of the
proton-capture reactions responsible for the production and destruction of $^{16}$O and $^{17}$O among which the $^{16}$O(p,$\gamma$)$^{17}$F reaction plays a central role, as it involves both isotopes. This work reports on a new measurement of the $^{16}$O(p,$\gamma$)$^{17}$F cross section carried out at the Laboratory for Underground Nuclear Astrophysics (LUNA) over a center-of-mass energy range of 200 - 380 keV, a region previously unexplored by experimental studies. Two complementary techniques were employed:
prompt gamma-ray detection and activation. The results obtained with the two techniques are consistent within experimental uncertainties. From the measured cross sections and existing literature data, we evaluate a new thermonuclear reaction rate, which is then used to demonstrate how simultaneous measurements of stellar carbon and oxygen isotopic ratios constrain the initial mass and the extent of the mixing events in red giant branch
stars. In particular, we demonstrate how the $^{12}$C/$^{13}$C abundance ratio is primarily sensitive to the temperature T$_{\textrm{max}}$ attained during mixing, whereas the $^{16}$O/$^{17}$O abundance ratio is highly sensitive to the initial stellar mass M$_i$. Therefore, simultaneous measurements of these isotopic ratios can disentangle and place stringent constraints on M$_i$ and T$_{\textrm{max}}$, and the remaining uncertainty is now dominated by stellar abundance measurements rather than nuclear-physics inputs.
Read the full abstract ▾
All authors D. Robb, P. McGlynn, M. Aliotta, C. Ananna, F. Barile, L. Barbieri, D. Bemmerer, A. Best, R. Biasissi, A. Boeltzig, R. Bonnell, C. Broggini, C.G. Bruno, A. Caciolli, M. Campostrini, F. Casaburo, F. Cavanna, G.F. Ciani, T. Chillery, P. Colombetti, A. Compagnucci, P. Corvisiero, L. Csedreki, T. Davinson, R. Depalo, A. Di Leva, Z. Elekes, F. Ferraro, A. Formicola, Zs. Fülöp, G. Gervino, R. M. Gesuè, G. Gosta, Gy. Gyürky, A. Guglielmetti, C. Gustavino, C. Hebborn, G. Imbriani, M. Junker, M. Lugaro, J. Marsh, E. Masha, R. Menegazzo, D. Mercogliano, V. Paticchio, D. Piatti, P. Prati, D. Rapagnani, V. Rigato, M. Rossi, R. Sariyal, R.S. Sidhu, J. Skowronski, O. Straniero, T. Szücs, S. Turkat, M. Vagnoni, S. Zavatarelli
Combinatorics
The parity module of a matroid
Tom Braden, June Huh, Jacob P. Matherne et al. (+2 more)
We introduce the parity module of a matroid with coefficients in a field $\mathbb{k}$. When $\mathbb{k}$ has characteristic zero, we show that the parity module of a matroid is isomorphic to its intersection cohomology module, yielding a new intrinsic characterization of the latter. The structure and dimension of the parity module can vary depending on the characteristic, giving rise to characteristic-dependent generalizations of the Kazhdan-Lusztig and Z-
polynomials of matroids. When the matroid is realizable over the complex numbers, the parity module is isomorphic to the hypercohomology of the parity sheaf supported on the arrangement Schubert variety of any such realization. We also introduce the notion of pure modules over any field $\mathbb{k}$ and show that they satisfy a matroid analogue of the Beilinson-Bernstein-Deligne-Gabber decomposition
theorem: Every pure module over the graded Möbius
algebra decomposes as a direct sum of shifts of the parity modules of matroids obtained by restricting to flats.
Read the full abstract ▾
All authors Tom Braden, June Huh, Jacob P. Matherne, Nicholas Proudfoot, Botong Wang
Information Theory
Exact Cap Response and Aperture Selection for Molecular Communication under Aligned Drift
Yen-Chi Lee, Chun-An Yang and Nan Yang
Spatial reception under directed molecule transport requires balancing useful molecule capture against intersymbol interference (ISI). To characterize this balance, we study a fully absorbing spherical receiver that counts absorption events only within a prescribed cap. Using the known joint first-hitting law under aligned drift, we derive exact cap impulse, cumulative, and eventual responses. We perform stable cumulative evaluation. We then assess the derived responses through particle simulations and time-step comparisons, and demonstrate that our conditional-timing analysis explains when opposite drifts of equal magnitude can favor the same wider aperture. We also show that for the studied geometry and a symbol duration of $0.15$ s, the aperture that maximizes the signal-to-interference difference (SID) increases from $29.13^\circ$ at zero drift to $61.86^\circ$ at a drift magnitude of $40$ $\mu$m/s. These results (i) connect joint arrival-time and location statistics to spatial reception design, (ii) characterize the tradeoff between useful molecule capture and ISI, (iii) support SID-based aperture selection for a given drift and symbol duration, and (iv) quantify the SID loss incurred by retaining the zero-drift optimal aperture for the same symbol duration.
Read the full abstract ▾
Differential Geometry
Invariant complex structures on the Euclidean motion group as deformations of Calabi-Eckmann structures
Neda Bokan and Srdjan Vukmirovic
We classify, up to equivalence, all left-invariant complex structures on the three-dimensional Euclidean rigid motion group $SE(3).$ Our approach is based on the correspondence between complex structures on a real Lie
algebra $\mathfrak{e}(3)$ of the motion group and complex Lie subalgebras of the complexification of $\mathfrak{e}(3).$ The resulting structures form a one-parameter family $J_\phi.$ We further establish a connection with the classical Calabi-Eckmann complex structures on $S^3\times S^3.$ More precisely, we construct a one-parameter deformation of Lie brackets connecting $\mathfrak{so}(3)\oplus \mathfrak{so}(3)$ to $\mathfrak{e}(3),$ for which each endomorphism $J_\phi$ remains integrable. Consequently, every left-invariant complex structure on $SE(3)$ arises as a contraction limit of Calabi-Eckmann structures. The same family of endomorphisms also defines complex structures on $\mathfrak{so}(3,1).$
Read the full abstract ▾
Cosmology and Nongalactic Astrophysics
Exact map-space beam convolution via spin-mapmaking
Camille Demay, Magdy Morshed, Martina Gerbino et al. (+1 more)
Forthcoming
cosmic microwave background (CMB) experiments are targeting ambitious science goals, including the exploration of the particle content of the Universe across
cosmic times and the search for the faint signal from primordial gravitational waves. To pursue these goals, CMB experiments will house an unprecedented high number of detectors that will dramatically enhance their sensitivity. This will in turn require a tight control of instrumental systematics, demanding efficient and precise simulation of systematic effects. Leveraging
spin-mapmaking, we present a map-based method to propagate beam convolution systematics to the map-level, especially well-suited for main-beam studies. From the scanning strategy information compressed into precomputed h-maps and the beam and sky harmonic coefficients, our method directly outputs beam convolved maps. We validate against pixel-centered TOD-level 4{\pi} convolution for circular, elliptical, and Planck HFI scanning beams, demonstrating that our method retains agreement to numerical precision, while operating in map space. This formalism enables efficient simulation of beam convolution systematics across the full focal plane of upcoming experiments. As a first practical application, we demonstrate the ability to efficiently produce beam-convolved simulated Planck maps, showing excellent agreement with the QuickPol pipeline at the power-spectrum level. We release a public code, Smarties4Planck, to easily generate such maps for broader use.
Read the full abstract ▾
All authors Camille Demay, Magdy Morshed, Martina Gerbino, Luca Pagano
Networking
Multi-Cell LTE-U/Wi-Fi Coexistence Evaluation Using a Reinforcement Learning Framework
José M. de C. Neto, Sildolfo F. G. Neto, Pedro M. de Santana et al. (+1 more)
Cellular broadband Internet of Things (IoT) applications are expected to keep growing year-by-year, generating demands from high throughput services. Since some of these applications are deployed over licensed mobile networks, as long term
evolution (LTE), one already common problem is faced: the scarcity of licensed spectrum to cope with the increasing demand for data rate. The LTE-Unlicensed (LTE-U) forum, aiming to tackle this problem, proposed LTE-U to operate in the 5 GHz unlicensed spectrum. However, Wi-Fi is already the consolidated technology operating in this portion of the spectrum, besides the fact that new technologies for unlicensed band need mechanisms to promote fair coexistence with the legacy ones. In this work, we extend the literature by analyzing a multi-
cell LTE-U/Wi-Fi coexistence scenario, with a high interference profile and data rates targeting a cellular broadband IoT deployment. Then, we propose a centralized, coordinated reinforcement learning framework to improve LTE-U/Wi-Fi aggregate data rates. The added value of the proposed solution is assessed by a ns-3 simulator, showing improvements not only in the overall system data rate but also in average user data rate, even with the high interference of a multi-
cell environment.
Read the full abstract ▾
All authors José M. de C. Neto, Sildolfo F. G. Neto, Pedro M. de Santana, Vicente A. de Sousa Jr
Machine Learning (Statistics)
The minimal width of neural networks and immersions of real projective space
BaoZhi Chu and Ben Weinkove
We investigate the minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the
topology of uniform convergence on compact subsets. We show that whenever the real projective space $\mathbb{RP}^{n-1}$ admits a smooth immersion into $\mathbb{R}^n$, the minimal width is at least $n+\min\{n,m\}$, assuming that the activation function is continuous and monotone. As a consequence, the minimal width of ReLU networks is $n+m$ whenever $n$ is equal to 2, 3, 4, 7 or 8 and $1\le m \le n$, extending results of Hanin-Sellke and Hwang. This suggests an intriguing connection between the approximation theory of neural networks and differential
topology.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Spin and 3D structure: theoretical advances
Markus Diehl
Theoretical studies of
hadron structure have made important progress since the previous DIS workshop in 2025. This talk reviews selected new results and developments, with a focus on
spin dependent parton distributions, on transverse-momentum distributions and their rapidity dependence, on generalised parton distributions, and on the evaluation of power corrections.
Read the full abstract ▾
Human-Computer Interaction
Let Me Clarify: Interactive Modeling of Soft Attributes
Steffen Holter, Rita Sevastjanova, Michaela Benk et al. (+1 more)
People commonly express preferences through soft attributes such as is interesting,” which are difficult to operationalize for computational preference modeling. Latent representations can obscure how such attributes are interpreted, limiting transparency and user control. We formalize softness as the diversity of valid interpretations a description permits and provide empirical support for this characterization. Our proposed measure estimates softness to guide clarification and determine when to generate computational approximations. This is instantiated in AttriFy, a mixed-initiative system that translates descriptions into executable Python functions over text corpora. An interactive dashboard connects the dialogue to proposed functions and computed values, enabling users to inspect, accept, reject, and refine interpretations. An exploratory within-subjects study with 32 participants compares our softness-guided clarification approach with an LLM baseline in supporting interpretable attribute construction. This work positions softness as a basis for constructing explicit, user-steerable attribute dimensions for downstream preference elicitation and decision-making.
Read the full abstract ▾
All authors Steffen Holter, Rita Sevastjanova, Michaela Benk, Mennatallah El-Assady
Robotics
Smart Fusion for Adaptive Visual-IMU Weighting in cuVSLAM Sparse Bundle Adjustment
Wonju Lee, Dara Molloy, Abhilash Nand Kumar et al. (+5 more)
In cuVSLAM, visual and inertial measurement unit (IMU) residuals are fused in sparse bundle adjustment (SBA) with a weighting fixed by pre-calibrated noise covariances, leaving no mechanism to adapt the visual-inertial balance at runtime. We introduce a scalar $\alpha\geq1$ that upscales the visual information
matrix relative to the IMU preintegration constraint. Across the candidate set $\{1.0,2.0,5.0,10.0,20.0\}$, the resulting trajectories form two empirical performance regimes. The IMU-TRUST regime contains $\alpha\in\{1,2\}$ near the calibrated baseline, while the
VISION-TRUST regime contains $\alpha\in\{10,20\}$. The intermediate value $\alpha=5$ is treated as a transition case. Differences within each regime are small relative to those observed between the regimes. This structure motivates reducing $\alpha$-selection to a binary decision. We train a lightweight Visual Quality
Estimator (VQE), implemented as a multilayer perceptron with 914 trainable parameters. It maps a 10-dimensional visual quality feature vector assembled from statistics already maintained by the tracker to a per-SBA regime prediction. The proposed method reduces mean RMSE APE by $27.7\%$ and by $14.9\%$ under leave-one-out cross-validation (LOOCV) on EuRoC MAV and TUM-VI Room, respectively.
Read the full abstract ▾
All authors Wonju Lee, Dara Molloy, Abhilash Nand Kumar, Onias Castelo, Petar Trslic, David Adley, Conor Ferguson, Hesam Rabeti
Probability
Asymptotic Error Distributions for Euler-Maruyama Schemes with Additive Semimartingale Noise
Mikio Hirokane
We establish a joint stable limit
theorem for integrated discretization errors of finite-dimensional càdlàg semimartingales whose predictable characteristics are absolutely continuous in time and satisfy a pathwise integrability condition. The normalized integrated error, evaluated on the discretization grid, converges stably jointly with the discretized semimartingale in the vector-valued Skorokhod $J_1$-
topology. No martingale representation property is assumed. We apply this
theorem to the Euler-Maruyama scheme for
stochastic differential equations with additive semimartingale noise. For a $C^1$ drift with locally Lipschitz derivative and a nonexplosive solution, the grid-point error normalized by $n$ converges stably jointly with the discretized driver. The limiting error solves a linear integral equation with an explicit inhomogeneous term involving the driver, an auxiliary Brownian motion, and independent uniform marks attached to the jumps. We also obtain the same limit under two alternative drift regularity conditions based on small-jump integrability or Lévy semigroup smoothing. For continuous drivers, the continuous-time error converges stably in the uniform
topology.
Read the full abstract ▾
Artificial Intelligence
Design Space Exploration of Reinforcement Learning Configurations for Post-Legalization Placement
Foteini Oikonomou, Maria Pantazi-Kypraiou, George Goudroumanis et al. (+5 more)
Graph Neural Networks (GNNs) and Reinforcement Learning (RL) have recently been explored for VLSI placement optimization, but their effectiveness for post-legalization placement refinement remains unclear. This paper presents a systematic design space exploration of a GNN-Proximal Policy Optimization (GNN-PPO) framework across three ISPD2015
benchmarks. We evaluate 18 configurations covering reward functions, GNN architectures, action spaces, candidate-set sizes, and training strategies. We analyse the results we obtain to identify pitfalls and to assess the prospects and opportunities of the RL methods for post-legalization placement. On top of that we propose a design classification approach to guide the design decisions of RL models.
Read the full abstract ▾
All authors Foteini Oikonomou, Maria Pantazi-Kypraiou, George Goudroumanis, Pavlos Stoikos, Athanasios Tziouvaras, Christos Anagnostopoulos, Georgios Karakonstantis, George Floros
Robotics
ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction
Huailiang Ma, Yuxuan Li, Ziyi Zhao et al. (+7 more)
Vision-
language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling
robots to generate actions from visual observations and
language instructions. However, most existing VLA models still operate on image-level visual representations inherited from pretrained
vision-
language backbones, while lacking fine-grained object understanding for manipulation. As a result, their robustness can degrade under out-of-distribution object layouts, clutter, and background variations. To address these limitations, we introduce ObjDream, an object-centric VLA framework centered on object-level understanding and future object state prediction. ObjDream uses a spatio-temporal object encoder to organize visual observations into temporal object slots, where persistent object identity and dynamic object state are represented through separate channels. These structured object representations are inserted into the
token sequence of the
vision-
language model (VLM), where identity-guided routing modulates VLM
attention to the corresponding object
tokens. In addition, an action-conditioned object dynamics module predicts compact future object states relevant to manipulation during training, explicitly supervising object state
evolution under
robot actions without requiring future prediction at inference. Experiments on LIBERO, LIBERO-Plus, and RoboTwin 2.0 show that ObjDream improves generalization under diverse distribution shifts and scene perturbations. Real-world
robot experiments further demonstrate that ObjDream transfers to physical manipulation settings with novel object arrangements and background changes.
Read the full abstract ▾
All authors Huailiang Ma, Yuxuan Li, Ziyi Zhao, Xinkai Wang, Mingyu Li, Xinyu Guo, Lifeng Zhu, Aiguo Song, Cewu Lu, Jianhua Sun
Networking
A Multiarmed Bandit Approach for LTE-U/Wi-Fi Coexistence in a Multicell Scenario
Iago Diógenes do Rego, José M. de Castro Neto, Sildolfo F. G. Neto et al. (+4 more)
Recent studies and literature reviews have shown promising results for 3GPP system solutions in unlicensed bands when coexisting with Wi-Fi, either by using the duty cycle (DC) approach or licensed-assisted access (LAA). However, it is widely known that general performance in these coexistence scenarios is dependent on traffic and how the duty cycle is adjusted. Most DC solutions configure their parameters statically, which can result in performance losses when the scenario experiences changes on the offered data. In our previous works, we demonstrated that reinforcement learning (RL) techniques can be used to adjust DC parameters. We showed that a Q-learning (QL) solution that adapts the LTE DC ratio to the transmitted data rate can maximize the Wi-Fi/LTE-Unlicensed (LTE-U) aggregated throughput. In this paper, we extend our previous solution by implementing a simpler and more efficient
algorithm based on multiarmed bandit (MAB) theory. We evaluate its performance and compare it with the previous one in different traffic scenarios. The results demonstrate that our new solution offers improved balance in throughput, providing similar results for LTE and Wi-Fi, while still showing a substantial system gain. Moreover, in one of the scenarios, our solution outperforms the previous approach by 6% in system throughput. In terms of user throughput, it achieves more than 100% gain for the users at the 10th percentile of performance, while the old solution only achieves a 10% gain.
Read the full abstract ▾
All authors Iago Diógenes do Rego, José M. de Castro Neto, Sildolfo F. G. Neto, Pedro M. de Santana, Vicente A. de Sousa Jr., Dario Vieira, Augusto Venâncio Neto