Peer Revenue Now accepting positions

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Saturday 7 November

Robotics

LSRP*: Scalable and Anytime Planning for Multi-Agent Path Finding with Asynchronous Actions

Multi-Agent Path Finding (MAPF) seeks collision-free paths for multiple agents from their respective starting locations to their respective goal locations while minimizing path costs. Although many MAPF algorithms were developed, most of them rely on a common assumption on synchronized actions, where the actions of all agents start at the same time and always take a time unit. This assumption may limit the use of MAPF planners in practice. To get rid of this assumption, recently, an algorithm called Loosely Synchronized Rule-based Planning (LSRP) was proposed, which can find sub-optimal solutions for many agents. However, LSRP often finds poor quality solutions due to its unbounded sub-optimality. This paper develops a new anytime planner called LSRP* that can keep improving solution quality after the initial solution is obtained until the runtime budget depletes. We analyze the properties of LSRP* and test it against several baselines with up to 1000 agents on various maps. LSRP* can handle up to 25% more agents than LSRP and can reduce up to 40% of the solution cost found by LSRP.
Read the full abstract

All authors Dachuan Liu, Shuai Zhou, Shizhe Zhao, Zhongqiang Ren

Machine Learning (Statistics)

Information-Theoretic Generalization for Set-Input Optimization-Valued Objectives

Modern machine learning is increasingly evaluated using criteria such as multicalibration, CVaR, and Cressie-Read DRO, which target subgroup reliability, tail risk, and distributional robustness rather than averages of fixed per-example losses. Existing information-theoretic generalization bounds for pointwise losses do not directly apply, because these empirical criteria depend on the entire batch and involve a post-hoc auxiliary optimization over witnesses, thresholds, or reweightings. We formalize this structure as set-input optimization-valued objectives. In the balanced supersample setting, we bound the expected optimized validation-training gap in terms of an objective-dependent sub-Gaussian parameter and the square root of the prediction-based conditional mutual information (fCMI) between the learned supersample prediction table and the selector vector. Combining this with fixed-predictor population-validation comparisons yields unified algorithm-dependent generalization bounds. We verify sub-Gaussianity of the selector gap using stability and convex L2-Lipschitz certificates, obtaining concrete bounds for multicalibration, CVaR, and Cressie-Read DRO, with a stability-based single-index refinement.
Read the full abstract

Systems and Control

Simulating Nonlinear Resistive Networks using a Behavioral Splitting

An operator splitting method is developed for computing operating points of nonlinear resistive networks. Our behavioral formulation separates the device laws from Kirchhoff's laws and casts simulation as a zero-finding problem. Branch port resistances then provide a diagonal preconditioner for the relaxed Peaceman-Rachford iteration in scattering variables. Each iteration requires solving independent scalar equations and a linear system with a fixed weighted Laplacian matrix. Convergence is established for maximal monotone device laws when an operating point exists. Contractive branch reflections also yield a linear convergence bound independent of network topology. Numerical experiments on crossbar arrays illustrate the computational advantages.
Read the full abstract

All authors Ryan Alizadeh, Thomas Chaffey, Dominic Liao-McPherson, Alberto Padoan

Artificial Intelligence

MambaLoc: Lightweight Indoor Localization Using Cross-Modal Knowledge Distillation

Accurate indoor localization on resource-constrained edge devices remains challenging due to the tension between modeling fidelity and computational efficiency. Wi-Fi Channel State Information (CSI) enables low-cost deployment using existing Wi-Fi infrastructure but is heavily distorted by multipath propagation. Transformer-based solutions mitigate these effects but their quadratic complexity limits real-time edge deployment. Ultra-Wideband (UWB) provides geometrically precise ranging yet requires dedicated infrastructure. We present MambaLoc, a cross-modal distillation framework that improves the accuracy-efficiency balance in CSI-based localization. MambaLoc uses a linear-time Selective State Space Model (Mamba) as a lightweight CSI student, guided during training by a UWB-Transformer teacher. A Feature Alignment Module bridges the representational gap between heterogeneous RF modalities, allowing the CSI model to inherit UWB-derived geometric structure without UWB hardware at inference. A probabilistic Gaussian Mixture regression head models multi-modal spatial ambiguity from multipath effects, avoiding the physically implausible averaging of deterministic regression. Evaluations on a real-world dataset show MambaLoc achieves a median localization error of 0.230 m, reducing error by 22.2% over a standalone Mamba baseline, while requiring 65.1% fewer FLOPs and 58% lower inference latency than Transformer-based approaches.
Read the full abstract

All authors Mohab Bahnassy, Omar Saqr, Hamada Rizk, Moustafa Youssef

Machine Learning (Statistics)

Spiking Sensory Networks

Effective sensory reception is critical for survival, yet the computational mechanisms behind how peripheral sensory neurons (SNs) transduce external signals into spiking representations for downstream brain circuits remain to be fully understood. Numerous theoretical frameworks have been proposed to model sensory processing, with Bayesian approaches among the most prominent. However, existing machine learning attempts to apply Bayesian theory to spiking neurons remain largely phenomenological, disconnected from empirical biology, and poorly validated on non-stationary temporal data. Conversely, neuroscientific models often rely on strong inductive experimental biases or explicit kinetic dynamics fit post hoc to match spiking data. Here, we introduce a class of recurrent Poisson VAE models, termed Spiking Sensory Networks (SSNs), that bridge these paradigms by reconciling variational inference with biologically inspired spike transduction for time-varying stimuli. Evaluated on real-world odor plume recordings from locust olfactory receptor neurons (ORNs), SSNs match or exceed the reconstruction fidelity of Spiking Neural Network (SNN) and GLM baselines while exhibiting superior representational characteristics. Furthermore, SSNs are well-suited for neuroscientific investigation, learning empirical in vivo ORN response motifs and exhibiting emergent spike-frequency adaptation under unsupervised reconstruction without manual tuning. Moreover, we theoretically link the recurrent decoding objective to mutual information maximization, and derive a formal thermodynamic lower bound connecting the Poisson Kullback-Leibler regularizer to the excess non-equilibrium metabolic power of biophysical homeostasis. Ultimately, our work synthesizes principles from machine learning theory and empirical neuroscience, providing a viable bridge that concretizes Bayesian models with biological mechanisms.
Read the full abstract

Statistics Theory

Divide-and-Conquer is Tail- and Anomaly-Robust: Factor Model Estimation Without Moment Constraints

We study robust estimation of elliptical factor models with abnormal observations and without requiring the existence of any positive moments. In particular, a divide-and-conquer (DC) estimator averages orthogonal projectors onto the full column spaces of small data blocks, and we rigorously establish its probability bound that allows weak and heterogeneous factors. The derived convergence rate is comparable to that of classical principal component estimators, up to the proportion of anomalies. Building on our DC estimator, we propose a split-sample tail- and anomaly-robust (STAR) estimator for the factor number using sample medians of successive projected coordinate ratios, which is shown consistent under mild conditions. Subsequent factor and common component estimation is also discussed, with the rates of convergence spelled out. Remarkably, given an upper bound on the true factor number, our suite of procedures are free from tuning, require no tail-dependent truncation threshold nor solving an optimization problem, admit parallel block computations, and hence has the same computational complexity as the classical principal component methods. Extensive experiments corroborate our theoretical findings, where DC and STAR are comparable and often outperform state-of-the-art competitors. We also illustrate our methods on a portfolio return dataset.
Read the full abstract

Information Retrieval

LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages

A generative recommender names each candidate with a short token sequence, a Semantic ID, and recommends by generating those tokens. Some generative recommenders, including the Uber Eats search engine we are building, write a whole results page, stores with their menu items, in one decoding pass. Every Semantic ID on such a page must name a real store or item that is eligible for the search, such as a store that delivers to the user's location, and that is not already on the page. Each item must also belong to the store above it. A trie over the catalog keeps identifiers real, but eligibility and repetition change with every request and token, and the grammar-constrained decoder we tried could not enforce these changing rules exactly and quickly. We call this constraint LEGIT, for live eligibility gating over identifier tries. Numbering trie leaves depth first turns each rule into a range lookup over one store trie and one item trie, and every generated page passes an independent catalog check. On one NVIDIA B200 GPU with one or two requests per decode step, a direct implementation that walks the trie on the GPU makes each token about 5 times as slow as unconstrained decoding. Across 36 implementations, hardware counters and ablations are consistent with kernel launches and CPU-GPU waits as the source of this slowdown. Our fastest implementation walks the trie on the CPU while the GPU runs the model, needs no custom kernel, and cuts time per output token by 65.9 percent against the direct GPU implementation, to about 1.7 times the unconstrained cost. This implementation is also the fastest on a page layout that puts each item before its store.
Read the full abstract

Information Retrieval

SepLRM: A Foundation Model Paradigm for Recommendation

Large recommendation models (LRMs) improve recommendation performance by scaling behavior sequence length, model capacity, and training compute. However, the return on investment (ROI) of continued scaling deteriorates as marginal gains diminish and long-sequence encoding costs rise, especially when this computation is repeatedly executed by distinct models for diverse recommendation stages and business scenarios. To address this issue, we propose SepLRM, a recommendation foundation model (RFM) paradigm that identifies reusable sequence encoding and reorganizes multiple end-to-end (E2E) LRMs into one RFM and multiple independently optimized vertical models (VMs). The RFM adopts an encoder-decoder architecture and exports its final-layer encoder state as the shared key-value (KV) cache that is independent of downstream task-offered candidates. Unlike candidate-specific logits or aggregated user embeddings, the KV cache preserves fine-grained behavioral information. Separation at this native KV interface also allows each VM to construct candidate-conditioned queries while retaining the same query-KV interaction as its E2E counterpart, enabling high-fidelity capability transfer. To ensure both transfer effectiveness and system efficiency, we co-design cache compression, the training and serving workflows, and LG-Store, a distributed storage system for KV caches. Experiments on three large-scale datasets show that SepLRM achieves state-of-the-art offline performance with a transfer rate of approximately 100%. It also demonstrates strong transferability across model iterations, recommendation stages, and business scenarios. Deployment in two large-scale industrial scenarios substantially improves the ROI of sequence scaling and delivers consistent gains in online A/B tests at ByteDance.
Read the full abstract

All authors Di Chen, Xijun Xiao, Qin Ren, Weijiang Lai, Zhijian Pan, Zhentao Pan, Pengfei Nie, Cheng Yuan, Zixuan Tan, Xuyang Liu, Tao Wang, Yunwen Huang, Hao Fang, Yichao Wang, Hao Zhang, Siyuan Wu, Hao Chen, Han Diao, Mingyu Yang, Yongkang Feng, Beihong Jin, Jinfeng Yang, Deping Xie, Peng Xu, Zheng Chai, Yuchao Zheng

Networking

From Radio Measurements to Sensing Services: A 3GPP Perspective on Multi-UAV Tracking with Networked ISAC

Integrated sensing and communication (ISAC) can turn radio measurements into networked sensing services, but accurate position estimates alone do not ensure useful tracking. Missed targets, late acquisition, track interruptions and aging observations also shape the information available to an application. This article examines tracking of noncooperative unmanned aerial vehicles (UAVs) from a Third Generation Partnership Project (3GPP) perspective. It connects sensing-service requirements and network architecture to three information interfaces: receiver search regions, measurement context and track validity. A five-UAV case study in a 3GPP urban scenario and a ray-traced San Francisco scene illustrates the tradeoff between target coverage and extra outputs, the distinction between acquisition and ongoing continuity, and the value of testing a static mission envelope before adding adaptation. An observation-age example explains how a state predicted to the present can still rely on old evidence. The resulting lessons are to align receiver search with requested coverage, preserve measurement time and uncertainty, and assess coverage, ambiguity and timeliness together. We conclude by pointing out fruitful avenues for further work in sensing design, calibration and service validation.
Read the full abstract

Materials Science

Fabrication and Characterization of Flexible In2O3 Thin-Film Transistors on Mica Substrates

Flexible oxide-semiconductor thin-film transistors (TFTs) with high field-effect mobility (uFE > 70 cm^2/Vs) are required for next-generation flexible displays. Polycrystalline In2O3-based TFTs are promising candidates; however, conventional flexible substrates such as plastics are not suitable because their fabrication typically requires relatively high temperatures (~350 deg.C). In this study, we used mica as a flexible substrate to fabricate polycrystalline In2O3-based TFTs, motivated by previous demonstrations of crystalline oxide growth on mica. The resulting TFTs exhibited a uFE of approximately 75 cm^2/Vs. The devices maintained gate-modulated operation after 10^3 flex-out bending cycles at a 5 mm radius, whereas flex-in cycling caused early electrical failure, likely due to In2O3 film degradation. The TFTs also operated normally after exposure to 85 deg.C and 40% relative humidity for one day. These results demonstrate that mica substrates enable high-mobility, flex-out-compatible In2O3-based TFTs.
Read the full abstract

All authors Hyeonjun Kong, Ping-Hsein Wu, Xian-Ye Jiang, Yasutaka Matsuo, Ying-Hao Chu, Hiromichi Ohta

Computer Vision

DAPointRWKV: Domain Adaptive Vision RWKV for Point Cloud Completion

Domain adaptive point cloud completion (DA PCC) aims to bridge the geometric discrepancy between labeled source domains and unlabeled target domains for accurate 3D shape completion. Existing methods based on CNNs, Transformers, and Mamba-like sequence models still face challenges from limited receptive fields, high computational complexity, insufficient geometric bias, and serialization sensitivity. Recently, Receptance Weighted Key Value (RWKV) provides a linear-complexity alternative for long-range sequence modeling. However, adapting RWKV to DA PCC remains challenging due to the lack of explicit geometric priors, the mismatch between recurrent modeling and coarse-to-fine generation, and unstable target-domain adaptation. To address these challenges, we propose DAPointRWKV, a novel RWKV-based framework for DA PCC. DAPointRWKV consists of three components: Geometry-Aware RWKV (GA-RWKV) Backbone, RWKV-Oriented Progressive Decoder (RWKV-PD), and Dual Structural Regularization (DSR). Specifically, GA-RWKV introduces geometry-aware recurrent representation learning, RWKV-PD bridges RWKV token representations with coarse-to-fine reconstruction through local token-guided refinement, and DSR stabilizes target-domain transfer through visible-structure anchoring and complete-shape hypothesis stabilization. Extensive experiments on synthetic and real-world benchmarks demonstrate that DAPointRWKV consistently outperforms state-of-the-art methods.
Read the full abstract

All authors Yinghui Li, Qianyu Zhou, Hao Yang, Richard Dazeley, Ye Zhu, Xuequan Lu

Machine Learning

TripletAD: Weakly Supervised Anomaly Detection in Embedding Space with Rare Anomalies and Scarce Labels

Many practical anomaly detection problems come with only a handful of confirmed anomalies, and the unreviewed remainder of the data cannot be trusted to be normal. We study this setting under a curated-label protocol, in which unconfirmed anomalies are removed from training rather than relabelled as normal, and propose TripletAD, a weakly supervised detector that learns a triplet-margin embedding and calibrates a linear scoring head with two soft penalties: a partial cross-entropy on labelled anomalies and a relative-contrast hinge that separates the mean scores of anomalous and normal samples. Because every mined triplet contains a labelled anomaly, the few labels are reused across the entire training set instead of being diluted by it. On 24 ADBench datasets whose inputs are pre-trained embeddings (text, image and speech vectors), TripletAD outperforms established state-of-the-art weakly supervised detectors (DevNet, PReNet and DeepSAD) and gradient-boosted trees when anomalies are rare. At a 1% anomaly rate it has the highest mean AUCPR of six methods, 20% above DevNet; on the naturally rare Speech dataset it doubles the best baseline (0.394 vs. 0.196 AUCPR); and on MVTec-AD it is best when only a quarter or half of the anomalies are labelled. Pooled over 70 rare- or sparse-label settings, it has the best average rank (2.21 of 6) and outperforms each baseline under Wilcoxon signed-rank tests with Holm correction. When anomalies are more frequent it performs on par with these methods. The method needs no per-dataset tuning and is insensitive to its loss weights and training length; on raw tabular features, gradient-boosted trees remain the stronger choice.
Read the full abstract

Quantum Physics

Realizing Unstructured PDE Forecasting on Superconducting Quantum Processors

Simulating high dimensional unstructured Partial Differential Equations (PDEs) with quantum processors is a major challenge with significant potential benefit. Existing methods have been demonstrated at small qubit counts, on simplifications of realistic problems. We implement a quantum reservoir network (QRN) for forecasting high-dimensional unstructured PDEs using up to 52 qubits on IBM superconducting hardware. Our method is gradient-free and does not suffer from the challenges of variational quantum algorithms. Instead, the QRN provides a large kernel space, up to 2^52 dimensions and beyond the reach of exact classical simulation, that remains useful under current hardware noise levels. Furthermore, a partial measure-and-reset mechanism enables total circuit runtime for ~24 times the qubit coherence time, so qubit lifetimes do not limit the forecast horizon. Thus, our method enables forecasting realistic unstructured nonlinear PDEs on quantum hardware. Typical difficulties associated with predicting large scale PDEs, such as transpilation, exponential shot requirements, hardware noise, and short qubit lifetimes are mitigated through careful design considerations and a dynamic observable reconstruction method. We validate our approach using a ~34k cell unstructured 2D cylinder flow at Reynolds number 1000 and a challenging nonlinear Gray–Scott reaction–diffusion problem, demonstrating high fidelity prediction on CUDA-Q simulation and on 26 and 52-qubit superconducting quantum processors. Specifically, we show that adding QRN features to an autoencoder linear prediction pipeline reduces prediction error by 21%-43%. Finally, we demonstrate closed-loop autoregressive PDE forecasting on these problems. This work demonstrates, for the first time, quantum circuits with depth beyond qubit lifetimes achieving accurate unstructured mesh forecasting on highly nonlinear PDEs.
Read the full abstract

All authors Erik Connerty, Jonathan Eastridge, Taylor Patti, Gerasimos Angelatos, Ethan N. Evans

Dynamical Systems

Quenched large deviation estimates for skew product systems with the almost-sure fiber specification property

We establish quenched level-2 large deviation estimates for empirical measures of measurable skew products with compact metric fibers over an invertible ergodic measure-preserving transformation on a Polish space. Our hypotheses are formulated through lower and upper energy functions, which describe the exponential decay of conditional measures of fiber Bowen balls. Under almost-sure fiber specification, we prove lower bounds for open sets. Upper bounds for closed convex sets require only the upper energy condition, and upper semicontinuity of fiber entropy removes the convexity restriction. When these hypotheses hold with a common energy function \(T\), we obtain a quenched level-2 large deviation principle with a good rate function \(I_T(\rho)=\int T\,d\rho-h_\rho(F)\) on invariant measures with the prescribed base marginal, and \(+\infty\) otherwise. We also derive quenched level-1 large deviation principles for bounded continuous observables and a quenched Laplace principle. As an application, we consider skew products that are Anosov and topologically mixing on fibers. For Gibbs equilibrium states associated with random potentials $f$ having integrable two-sided Bowen variation, we construct bounded strictly positive common energy functions by coboundary corrections. This construction identifies the large deviation rate on invariant measures as \(\pi_F(f)-h_\rho(F)-\int f\,d\rho\), where \(\pi_F(f)\) denotes the fiber topological pressure.
Read the full abstract

Artificial Intelligence

SituRecBench: Evaluating Frontier Models as Situated Recommendation Assistants in 3D Environments

Recommender systems are transitioning from static retrieval engines into interactive assistants grounded in physical environments. However, current studies largely neglect the combined complexities of spatial navigation, visual grounding, and multi-turn social interaction. To bridge this gap, we introduce SituRecBench, an interactive benchmark for evaluating frontier vision-language models (VLMs) as situated recommendation assistants within high-fidelity 3D environments. We reformulate recommendation as a situated assistance process in which an assistant interacts with a user while sharing the user's egocentric view. Our benchmark simulates real-world shopping environments (e.g., supermarkets and home furnishings stores), requiring assistants to elicit preferences, ground recommendations in the environment, and guide the user to relevant locations through dialogue. The benchmark evaluates dialogue quality, recommendation utility, and navigation effectiveness through a unified interactive protocol. Extensive experiments reveal persistent challenges in spatial grounding and preference elicitation, highlighting limitations in their ability to integrate global contextual information with local observations. SituRecBench provides a rigorous foundation for advancing the development of situated assistants in the real world.
Read the full abstract

All authors Jingtong Yang, Dongding Lin, Jian Wang, Wenjie Li

Computer Vision

Guided Co-Attention with Adaptive Gating for Multimodal Medical Data Fusion

Multimodal fusion requires not only exchanging information across modalities but also determining which representations should participate in the interaction and how complementary cross-modal views should be combined. We introduce Guided Co-Attention with Adaptive Gating, a fusion framework that integrates token-wise guidance, bidirectional cross-attention, and sample-specific fusion. The proposed method constructs two directional representations: an image-conditioned text representation, obtained by allowing textual tokens to query visual features, and a text-conditioned image representation formed in the reverse direction. Token-wise guidance modulates the representations before cross-attention, while an adaptive gate learns the relative contribution of the two resulting directional representations for each sample. We evaluate the approach using paired chest radiographs and radiology reports as an image-text test bed for binary (normal vs. abnormal) classification. The two cross-attention directions exhibit distinct performance characteristics, demonstrating that reversing the query and source modalities does not produce interchangeable representations. Ablation experiments further show that bidirectional interaction, adaptive gating, and token guidance provide complementary benefits. The proposed model achieves 96.05% accuracy, 96.10% F1-score, 98.37% AUC, 95.60% Sens@95Spec, and 96.51% Spec@95Sens, yielding the highest mean performance across all evaluated metrics. These findings support explicitly modeling interaction direction, token relevance, and sample-dependent integration when constructing multimodal representations.
Read the full abstract

All authors Muntaqim Ahmed Raju, Priyanka Siddappa, Md Shifat Haider Al Amin, Ruizhe Ma, Md Ripon Ahammed

Computer Vision

PoseBench: Probing Pose Awareness in Visual Foundation Models

Pose awareness characterizes the extent to which a learned feature space aligns with the underlying object-pose manifold, such that observations with similar poses exhibit greater feature similarity than those with increasingly different poses. While such structure is desirable for pose-sensitive 3D vision tasks, visual foundation models pre-trained on individual 2D images typically lack explicit 3D or pose supervision. This raises a fundamental question: Do 2D visual foundation models exhibit pose awareness after large-scale pretraining? To answer this question, we introduce PoseBench, a systematic benchmark to probe pose awareness in pretrained visual features. Our evaluation follows a progressive design: held-out rendered views probe intrinsic pose-aware structure under controlled conditions, while real-image queries evaluate how robustly this structure remains accessible under real-world variations. We further introduce pose-graph-based refinement as a complementary probe of compatibility between feature neighborhoods and the underlying pose manifold. Across 31 publicly available checkpoints from 10 pretraining families, PoseBench reveals that pose awareness is an implicit but non-uniform property of 2D visual foundation models, and consistent gains from pose-graph refinement suggest that feature spaces retain structure compatible with the underlying pose manifold. PoseBench therefore provides a systematic basis for understanding and selecting pretrained features for pose-sensitive 3D vision tasks.
Read the full abstract

Populations and Evolution

Quasispecies relocate rather than drift: hierarchical genotype networks track viral adaptation

Viral populations are ensembles of mutationally related genotypes that explore sequence space locally. Their genotype networks are hierarchical: abundance decays with mutational distance from the most abundant genotype (the root) and degree distributions are heavy-tailed. How this architecture responds to selective challenges remains unclear. We combine simulations of sequence populations on NK fitness landscapes with longitudinal hepatitis B virus (HBV) deep-sequencing data from chronically infected patients under treatment. Quasispecies structure is rapidly rebuilt around the current root, while root replacement is occasional, when a fitter variant is found. Adaptation unfolds on two timescales: fast, local reorganisation and slow, stochastic relocation. HBV populations of patients not responding to therapy show stasis. Meanwhile, responders show either near-complete replacement by a new root, or transient excursions followed by return to the original root. These patterns resemble the stasis and relocation regimes found in simulations. Our results suggest that genotype network organization and dynamics under selective pressure present generic features of molecular adaptation, with a potentially informative clinical readout.
Read the full abstract

All authors Iker Atienza-Diez, Samuel Martínez-Alcalá, Luis F. Seoane, Susanna Manrubia

Game Theory

The Power of Two Choices in Dynamic Pricing: As Good As Full Feedback, Instance-Wise

We study the dynamic pricing problem, where a firm sells a product to $T$ myopic customers and their values are independent samples from an unknown value distribution $F$. With posted prices, the firm only sees whether each customer buys, and the minimax regret is $\widetilde \Theta(T^{2/3})$ [KL03]. A menu instead offers several options, each selling the product with some probability at some expected payment. Infinitely many menu options allow the seller to fully reveal customer values, reducing the regret to $\Theta(\sqrt T)$. How many options are needed? Perhaps surprisingly, a second menu option suffices, achieving the same regret as infinite menus (up to $\log$ factors). This holds broadly: without knowing any property of $F$, our algorithm with two menu options attains $\tilde O(\sqrt T)$ regret in general, $\tilde O(T^{1/3})$ regret for monotone-hazard-rate distributions, and $\tilde O(T^{d/(d+1)})$ instance-dependent regret when $d\in(0,1)$ is a suitable notion of "dimension". All are optimal even with infinite menus. Moreover, we argue, via a novel lower-bound construction, that our algorithm is near-optimal for each problem instance. Along the way, we study the query complexity of revenue maximization, where an algorithm issues a query to each customer to learn the property of interest (either the best price or the CDF) up to some precision. We show that interval queries suffice to achieve the same query complexity as value queries (up to $\log$ factors) for both properties and across several classes of value distributions. We provide a new interval-query algorithm for each property. The best-price-estimation algorithm is the key ingredient in our main dynamic pricing algorithm, and the CDF-estimation algorithm underpins a simpler algorithm attaining $\tilde O(\sqrt T)$ regret with three menu options.
Read the full abstract

Computer Vision

MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs

Multimodal Large Language Models (MLLMs) show strong visual perception capabilities, but existing evaluations largely focus on single-view or multi-view settings with shared camera parameters, leaving the challenge of multi-agent collaborative scenarios underexplored. In such settings, multiple agents observe a shared environment from independent viewpoints, and reliable decisions require reasoning across these independent observations of the same environment. To study this problem, we introduce MaRiO, a benchmark for evaluating multi-agent collaborative reasoning, and evaluate 23 state-of-the-art MLLMs on it. Our analysis reveals three key findings: (1) tasks governed by static perception are generally easier than tasks that require transformational event sequences; (2) most models struggle to resolve cross-agent correspondences, with errors increasing with scene complexity; and (3) models show limited ability to leverage geometric cues present in the scene. As an initial step toward addressing these challenges, we explore geometry-guided synthetic view augmentation that generates intermediate transition frames between agent observations, providing auxiliary spatial context that improves performance in certain categories. Overall, our results highlight that multi-agent collaborative reasoning remains an open challenge and an important direction for multimodal embodied systems. The code is available on the project page: https://omarftt.github.io/MaRiO-page/.
Read the full abstract

All authors Nathaniel Redmond, Fidel Omar Tito Cruz, Devansh Sharma, Shehreen Azad, Sirshapan Mitra, Shruti Vyas, Yogesh S. Rawat

Robotics

GUARD: Anomaly-Informed Q-Steering for Generative Robot Policies in Dexterous Manipulation

Generative robot policies based on diffusion and flow matching can model complex, multimodal behaviors, but remain susceptible to covariate shift during closed-loop execution. Existing approaches mitigate such failures through additional demonstrations, policy fine-tuning, or test-time guidance, but often require human intervention, engineered rewards, or other task-specific signals. We introduce GUARD, an anomaly-informed Q-steering framework that leverages the policy's training distribution to construct a dense, failure-anticipatory steering signal. GUARD pairs sparse task rewards with dense anomaly scores learned from policy training data and propagates both through a learned Q-function. Its gradients then steer the denoising process toward actions that improve task return while preventing trajectories from entering poorly supported regions, without directly modifying the pretrained policy. Across four Adroit dexterous manipulation tasks, GUARD achieves average success rates of $96.0\%$ and $80.0\%$ under nominal and perturbed dynamics, outperforming the strongest baseline by $21.0$ and $20.0$ percentage points while maintaining the lowest anomaly score. GUARD further demonstrates direct sim-to-real transfer on in-hand screwdriver rotation and reorientation tasks, achieving $40$ and $25$ percentage-point gains in success rate. These results demonstrate that anomaly signals can serve not only for failure monitoring but also to complement sparse task rewards as effective supervision for robust policy steering.
Read the full abstract

All authors Aryaman Gupta, Xiaoyue Wu, Rana Soltani Zarrin, Mark Van der Merwe

Earth and Planetary Astrophysics

From Exo-Earth Detection to Atmospheric Characterization: Enabling Phase-Dependent Molecular Detection SNR in EXOSIMS

Detection and characterization of Earth-like worlds is a primary science goal for the upcoming NASA flagship Habitable Worlds Observatory (HWO). The HWO mission will be the first of its kind to specifically search for Earth-like worlds around Sun-like stars and characterize their atmospheres to identify potential biosignatures. A mission with such ambitious science goals thus requires equally robust and physically realistic simulation tools. In this work, we extend the realism of the EXOSIMS framework by incorporating phase-dependent biosignature detectability. We use the spectral retrieval tool rfast to determine the signal-to-noise ratio (SNR) required to detect atmospheric O2 and H2O as a function of planetary phase and incorporate these requirements directly into EXOSIMS characterization integration-time calculations. Although the required molecular detection SNR decreases toward increasingly crescent phases, successful molecular detections are concentrated at intermediate phase angles, demonstrating the competing effects of molecular information content and direct-imaging observability. Relative to fixed characterization thresholds of SNR = 5 for H2O and SNR = 8.5 for O2, the phase-dependent treatment increases mean molecular detection yield by 76.8 percent for H2O and 29.7 percent for O2. Ultimately, we provide a framework that improves simulation fidelity, increases the realism of EXOSIMS as we expand to assess additional biosignatures in future work, and marries detection and characterization in yield modeling as we look to the future with HWO.
Read the full abstract

All authors Searra Foote, Tyler D. Robinson, Rhonda Morgan, Dmitry Savransky, Mario Damiano, Armen Tokadjian

Social and Information Networks

Collaboration Signatures: Tracking Long-Horizon Dynamics of Cross-Meeting Collaboration Networks

Enterprise platforms have received increasing attention as a core component of social networks and the Web. However, existing work mostly relies on fragmented logs of small units of work, like emails and chats, and focuses on who connects with whom without sufficient account of collaboration content and dynamics. This work systematically explores tracking collaborations across sequences of meetings as a new approach to interpreting their long-horizon dynamics. Linking 45,426 meetings in a large multinational technology company based on full transcripts and 1.6 million extracted agenda items, we establish a cross-meeting collaboration network of 6,065 collaborations. The network recovers the natural shapes of workplace collaborations: meetings, as snapshots of ongoing collaboration, link into largely tree-shaped structures, while the work content forms nested directed acyclic graphs (DAGs). Further, we explore how these networks evolve over time, examining three established perspectives: task division, team composition, and temporal continuity. Each explains part of the dynamics but does not capture the distinctness of long-horizon workplace collaboration: e.g., work flows in a consistent direction between a few pairs of subjects, yet a collaboration's subject explains little of how its meetings are conducted. Instead, accumulating the agenda, interaction, and language of meetings along each tree yields a signature of the collaboration, a distinctive profile that picks out the collaboration of a held-out meeting at 4.5 times chance. The signature models collaboration better than team or task views, individually or combined, in next-meeting prediction and tree-level fitting. We discuss the implications of these cross-meeting dynamics for designing office applications and support tools, and call for next-generation Web systems that represent collaborations over their long horizon.
Read the full abstract

Artificial Intelligence

IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories

Feature caching accelerates Diffusion Transformers by reusing intermediate computations across denoising timesteps, yet existing methods share a fundamental blind spot: they treat the standard reference denoising trajectory as the optimisation target, approximating its per-step states and thus inheriting its output as an implicit quality ceiling. We argue that this target is arbitrary – what truly matters is the ideal result, not the intermediate path taken to reach it. We propose IdealCache, a training-free framework that abandons step-wise imitation of the reference trajectory. Instead, it anchors caching on a per-input ensemble of ideal trajectories constructed from candidate target results, aggregates their geometry into a single graph, and discovers optimal non-uniform schedules via a constrained shortest path on this graph. By decoupling from the reference process, IdealCache breaks the performance bottleneck of trajectory-approximation; our schedules can attain near-lossless fidelity in generation and even surpass on task-specific metrics (e.g., maintaining higher semantic consistency in image editing). Without retraining, IdealCache achieves 6.35x speedup on Qwen-Image, 5.84x on Qwen-Image-Edit, and 4.32x on HunyuanVideo, with competitive or superior quality across tasks.
Read the full abstract

Probability

Critical Branching Systems with General Lifetimes: Hunt Motions and Applications to Semilinear Equations

We consider a critical monotype Bellman-Harris branching particle system on $E=R^d$ or $E=[0,\infty)^d$, started from a homogeneous Poisson field with Lebesgue intensity. Particles follow a conservative Hunt process with transition semigroup $(P_t)_{t\ge 0}$, have independent lifetimes with distribution $\Gamma$, and reproduce at death with generating function $f(s)=s+c(1-s)^{1+\beta}$. We assume Lebesgue invariance and uniform bounds $P_t1_K=O(t^{-q})$ for compact $K$. We also impose a localization condition: the expected number of particles in a fixed compact set at time $t$ descended from ancestors initially outside suitable regions of volume $O(t^q)$ can be made arbitrarily small, uniformly for $t\ge 1$. For spread-out lifetimes of finite mean, the system converges to a nontrivial limit of Lebesgue intensity when $q\beta>1$ and becomes locally extinct when $q\beta\le 1$. For nonarithmetic lifetimes satisfying $\bar{\Gamma}(t)\sim c_1t^{-\gamma}$, $0<\gamma\le 1$, the threshold is $q\beta=\gamma$: the limit is Poisson above it, local extinction holds below it, and a nontrivial subsequential limit exists at equality. We verify the hypotheses and determine recurrence-transience regimes for symmetric and anisotropic stable processes, symmetric uniformly elliptic diffusions, generalized squared-Bessel products on $[0,\infty)^d$, and symmetric bilateral Bessel-type diffusions on $R^d$ and their nonsingular linear images. Finally, we derive quantitative sufficient conditions for survival of total mass in semilinear equations with absorption, including time-dependent diffusion rates. Here survival means that the limiting total mass is strictly positive. For a hyperbolic diffusion, this holds for every $\beta>0$ in the absorption term $-v^{1+\beta}$.
Read the full abstract

Machine Learning

On the universal structure in deterministic generative diffusion

Diffusion-based generative modeling has emerged as a general computational framework for simulating high-dimensional, structured data across various domains. Understanding its generative mechanisms is paramount for advancing model training and inference in a principled way. Here, we demonstrate that deterministic sampling trajectories share a universal geometric structure invariant to data modalities and diffusion model implementations. This structure can be largely explained by an exactly solvable model based on the optimal linear denoiser.
Read the full abstract

All authors Defang Chen, Zhenyu Zhou, Can Wang, Zeyu Zheng, Siwei Lyu

Computer Vision

TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding

Streaming video understanding (SVU) requires models to answer user queries over continuously evolving video streams. Unlike offline video QA, SVU must handle queries whose evidence may lie in the past, appear in the current scene, or emerge only after future observations. Existing streaming video systems often rely on compact visual memories or fixed evidence-access schemes, which can lose fine-grained details and fail to adapt the answering process to the temporal intent of each query. In this paper, we propose TimeTraveler, a streaming VQA framework that performs temporal strategy planning with a Time Dictionary. Inspired by the need to search across different temporal regions of a stream, TimeTraveler stores each observed moment as a timestamp-indexed structured caption and uses this dictionary as an explicit source of queryable evidence. Given a query, TimeTraveler determines whether to recall past evidence, read the present context, or wait for future observations, and then applies a strategy-specific evidence acquisition process. Comparative experiments on streaming video QA benchmarks show that TimeTraveler improves streaming question answering by preserving fine-grained temporal evidence and selecting the appropriate temporal strategy for each query. The project page is available at https://geppa.github.io/TimeTraveler.
Read the full abstract

Analysis of PDEs

Vázquez Strong Maximum Principle and Compact Support Principle for singular and degenerate elliptical operators

In this paper, we present adaptations of the classical strong maximum principle and the compact support principle for a certain class of equations, with particular emphasis on the degeneracy of fully nonlinear operators and a new Vázquez-type condition on the nonhomogeneous term. The novelty of our approach lies in the framework of the problem: the coefficients of the operators are bounded, but we introduce a degeneracy depending on the power of the gradient of the solution. Moreover, the source term $f$ on the right-hand side of the equation is treated under a adapted and optimal integrability assumptions.
Read the full abstract

Machine Learning

Two-Sided Conformal Evidence Sets for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) can surface passages that support a claim, contradict it, or fail to address it, yet existing calibrated grounding methods are typically one-sided and model only supporting evidence. We introduce Conformal Evidence Sets (CES), a two-sided framework that returns separate support and refutation sets with finite-sample inclusion coverage of at least $1-\alpha$ on each side under exchangeability; a Bonferroni union yields joint coverage of at least $1-2\alpha$. On labeled candidate pools from the contrastive VitaminC benchmark, CES closely tracks nominal coverage across $\alpha\!\in\!\{0.05,0.10,0.15,0.20,0.30\}$, with maximum deviations of $3.0$ percentage points for support and $5.4$ for refutation, and reaches essentially the same empirical coverage–size frontier as a test-tuned fixed-threshold heuristic without any test exposure. Stress tests mark the boundary of that guarantee: under FEVER distribution shift both sides under-cover, by up to $12.7$ percentage points, and support-side group-stratified recalibration substantially reduces the support gap. Scorer swaps, hard-negative retrieval, cross-dataset transfer, and a live end-to-end pilot expose a clear separation: when exchangeability holds and relevant evidence is retrieved, evidence inclusion remains calibrated even with an imperfect scorer, whereas the support/refute verdict tracks scorer quality directly. Calibrated evidence coverage and reliable verdicts are therefore distinct properties and should be reported separately.
Read the full abstract

Machine Learning

Reproducible LoRA Inference Through Deterministic Split-K Reduction

Reproducibility is important for LoRA-adapted language models used in repeated evaluation, auditing, and decision-making. However, Split-K kernels used to introduce parallelism in low-rank LoRA multiplications can have the unintended consequence of numerical nondeterminism when partial results are combined using floating-point atomic additions. We investigate this non-determinism in vLLM across GSM8K mathematical reasoning, MBPP code generation, and Jev-style structured toxicity decisions on Civil Comments and introduce a deterministic Triton Split-K implementation. Under identical-input replay, Atomic Split-K=8 produces different FP32 shrink outputs in 97.61% of comparisons, while our Deterministic Split-K=8 shows no observed variation. Repeated atomic inference changes generated outputs in 17.30% of GSM8K and 14.96% of MBPP comparisons, sometimes altering task correctness. Structured-decision probabilities vary in 81.47% of atomic comparisons, with decision flips. Controlled tracing demonstrates how shrink-output differences propagate into the KV cache and how accumulated cache differences can change token decisions and final answers. Our deterministic Triton Split-K=8 implementation preserves parallelism, achieving 16.8-21.1% latency-based speedup over unsplit reduction with only 1.02-2.62% additional latency relative to Atomic Split-K=8.
Read the full abstract