Peer Revenue Past citations are no guarantee of future returns

Papers

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

All of arXiv

Wednesday 30 September

Quantum Physics

Information Potential: A Variational Approach to Quantum Information Complexity

Penghui Yao and Yifan Zhou

Quantum information complexity (QIC), introduced by Touchette [Touchette, STOC 2015], has been shown to be one of the most powerful methods for proving quantum communication complexity and has also been shown to be equal to amortized quantum communication complexity. Unfortunately, QIC is generally hard to analyze because it is a sum of quantum conditional mutual information terms, which are difficult to estimate. In this work, we introduce a new variational approach, the information potential, for analyzing QIC and proving quantum communication lower bounds inspired by the resolvent representation for quantum relative entropy. This approach connects the QIC of individual messages to a quadratic form, making it more amenable and thus enables us to bound the cumulative positive increments of the potential throughout an interactive quantum protocol by its QIC. Lower bounds on the growth of the potential therefore translate into lower bounds on both QIC and quantum communication complexity. As an application, we give an optimal $\Omega(1/r)$ lower bound on the QIC of the two-bit $\mathsf{AND}$ function as well as an optimal $\Omega(n/r)$ lower bound on the quantum communication complexity of $r$-round Set-Disjointness, answering an open problem in~[Braverman, Garg, Ko, Mao, Touchette FOCS 2015]. Moreover, we further prove a direct-sum theorem for bounded-round quantum communication complexity of Set Disjointness. With the tight bound on the QIC of $\mathsf{AND}$ function, we further establish a nearly tight tradeoff for the asymmetric quantum communication complexity of $\mathsf{Set} \mathsf{Disjointness}$: $(q_A+1)(q_B+1)=\Omega(n)$, where $q_A$ and $q_B$ denote the total numbers of qubits sent by Alice and Bob, respectively.
Read the full abstract

Information Retrieval

Generative End-to-end Ad Retrieval at Douyin

Shaowen Zeng, Yanhua Huang, Jiacheng Sun et al. (+8 more)

Generative retrieval reformulates recommendation as the generation of discrete item tokens. However, scaling this paradigm to real-world recommender systems reveals two critical bottlenecks: 1) Representation collapse, where the item tokenizer converges to degenerate results under continuous distribution shifts, fundamentally hindering stable end-to-end adaptation. 2) Item collisions, where the massive candidate pool causes distinct items to share identical token sequences, compromising the final retrieval precision. Crucially, these bottlenecks are inherently coupled: expanding codebook capacity to mitigate collisions inevitably exacerbates collapse. To address them simultaneously, we propose GEAR, an end-to-end framework that jointly optimizes the tokenizer, generator, and reranker. To mitigate representation collapse, we introduce BasisVQ, which re-parameterizes the codebook via an orthogonal basis to enable global gradient sharing and rigid spatial rotation of the latent space, effectively stabilizing gradient dynamics without ad-hoc heuristics. We further extend it to prefix-aware BasisRQ, substantially enhancing the codebook's expressiveness with the same asymptotic time complexity. To resolve item collisions, GEAR integrates a context-conditioned reranking head into the generative process, efficiently disambiguating colliding items with minimal computational overhead. By unifying stable tokenization and joint reranking within an end-to-end generative framework, GEAR establishes a fully differentiable and scalable paradigm. It currently serves hundreds of millions of daily active users on Douyin Ads, yielding substantial empirical improvements in extensive online A/B tests.
Read the full abstract

All authors Shaowen Zeng, Yanhua Huang, Jiacheng Sun, Jiarui Liu, Qian Dai, Zhikai Yang, Hancheng Li, Boya Wu, Tuoyu Zhang, Yekui Chen, Xiang Sun

Machine Learning (Statistics)

Discrete Score Matching Enables Causal Discovery from Count Data

Euijong Song, Hyewon Park and Gunwoong Park

Count data pose a challenge for score-matching-based causal discovery: derivatives are unavailable, and simply replacing them with finite differences does not generally suffice for causal discovery. We generalize SCORE's constant-curvature criterion (Rolland et al., 2022) by conditioning on the node's value, yielding the conditional curvature score (CCS) for ordering. We also extend curvature-based parent recovery through the off-diagonal curvature score (OCS), enabling directed acyclic graph (DAG) recovery with both scores constructed from score functions for continuous data and concrete scores for counts. In the bivariate setting, zero CCS exactly characterizes a semiparametric generalized linear model (GLM) conditional form in which the conditional family need not be specified in advance, unlike in classical GLMs. For bivariate semiparametric GLM DAGs under our regularity condition, canonical-parameter nonlinearity is necessary and sufficient for identifiability. In multivariate DAGs, this nonlinearity enables DAG recovery through CCS and OCS. Our framework identifies a new class of semiparametric GLM DAGs that strictly contains the nonlinear Gaussian ANM class identified by SCORE. We introduce DISCO (DIscrete SCOre), a count-DAG recovery algorithm that estimates CCS and OCS using discrete diffusion. Experiments demonstrate accurate DAG recovery across Poisson, negative binomial, binomial, and mixed-family settings, as well as scalability to 1,000-node DAGs on a single GPU.
Read the full abstract

Artificial Intelligence

WorkGenesis: Building the Worlds That Teach Agents to Work

Xinyu Zhu, Fenyi Liu, Yuzhu Cai et al. (+4 more)

The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents requires realistic work scenarios. Expert-authored occupational work is costly and slow to produce, while unconstrained synthesis often yields tasks with weak factual grounding or internally inconsistent requirements. To bridge this gap, we introduce WorkGenesis, a framework that constructs executable occupational work from real-world artifacts through two core technical innovations: (1) Evidence-Based Work Construction, which grounds each unit of work in real-world evidence by retrieving public files guided by O*NET occupational knowledge and synthesizing the surrounding context, companion materials, work request, and itemwise rubric around them; and (2) Execution-Guided Consistency Verification, which renders a reference deliverable inside the constructed work, attributes every unsatisfied rubric item to the agent, the task, or the rubric, and uses task and rubric defects as feedback to iteratively repair the work until it passes the audit. Experimental results demonstrate that Fx-Work-35B, trained with simple supervised fine-tuning (SFT) on only 20K units of work synthesized by WorkGenesis, achieves the highest scores among all comparable-scale baselines on the five reported metrics across GDPvalAA-v2, APEX-Agents-AA, and JobBench (31.00 versus 24.79 average score), and even surpasses frontier models such as the 1.6T DeepSeek-V4-Pro-Preview. These results show that WorkGenesis provides scalable training data for working agents.
Read the full abstract

All authors Xinyu Zhu, Fenyi Liu, Yuzhu Cai, Shuo Tang, Rui Ye, Linfeng Zhang, Siheng Chen

Robotics

MotionWeave: Learning Motion-Centered Future Dynamics for Vision-Language-Action Policies

Jingqiu Wang and Yan Wang

Vision-Language-Action (VLA) models have recently incorporated world models to provide richer dynamic supervision beyond sparse action labels. However, explicitly predicting future images or videos may include control-irrelevant appearance, while guidance derived from holistic future visual representations and shared global action features may fail to establish timestep-specific correspondence between actions and local visual changes. To address this issue, we propose MotionWeave, a motion-centric future-dynamics framework for action-chunk prediction with two modules: the Action-Induced Motion Grounder (AIMG) and the Horizon Residual Composer (HRC). Specifically, AIMG conditions on action and proprioceptive representations to construct horizon-specific queries that localize interaction regions associated with each future action timestep from current visual tokens. HRC extracts differences between interaction representations at adjacent horizons, encodes them as temporal motion cues, and injects them into action tokens through a gated residual. During training, robot-arm masks rendered from future frames are used to construct KL-based motion-grounding supervision, while inference uses only the current observation. On six MetaWorld tasks, MotionWeave achieves a 75.3% average success rate, an absolute gain of 8.6% over {\pi}0 (66.7%), especially on sustained-interaction tasks. Our code is available at https://github.com/autu-mn/MotionWeave.
Read the full abstract

Robotics

HiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path Planning

Guoqing Ma, Mingqi Yuan, Chen Gao et al. (+2 more)

Robot demonstration generation requires a system to identify where an interaction should occur, plan a feasible motion, and execute the required contact. HiWE connects these decisions through a point-based interface between visual grounding and language-based planning. PointVLM is instruction-tuned to associate task-relevant objects with image coordinates using a mixture of point annotations, segmentation-derived samples, robot observations, and visual question answering data. Depth measurements lift these predictions into a semantic 3D representation. A language planner, 3DLLM, uses this representation to specify end-effector waypoints and gripper commands, while a hybrid grasping module resolves local grasp poses. The evaluation covers 14 simulated manipulation tasks and four physical-robot tasks, together with ablations of the visual training data, spatial inputs, and grasp selection. Here, zero-shot execution refers to deployment without task-specific demonstration training; the visual model uses existing robot data during fine-tuning. This paper describes the original point-based formulation of the framework; its relationship to the subsequent GeneralVLA extension is detailed in the introduction.
Read the full abstract

All authors Guoqing Ma, Mingqi Yuan, Chen Gao, Jiayu Chen, Shan Yu

Robotics

A Biophysically Detailed C. elegans Circuit as a Task-Agnostic Dynamical Core for Visually Robust Robot Manipulation

Linrui Qian, Jiajia Zhang, Gan He et al. (+7 more)

Robot policies are usually trained for one task, one body and one visual environment, and generalize poorly beyond these conditions. Whether a nervous system can instead supply the sensorimotor computation through its evolved wiring and biophysics remains unresolved. Here we embed a biophysically detailed Caenorhabditis elegans sensorimotor circuit - 136 multicompartment neurons with realistic morphologies and electrophysiological characteristics - as the dynamical core of a visuomotor policy. Only thin task-specific adapters are trained; the core's synaptic weights stay fixed while its membrane voltages evolve freely. Across different MetaWorld tasks the core matches or exceeds diffusion-policy, action-chunking-transformer and neural-circuit-policy baselines, and degrades less under visual perturbations. Replacing the core with generic network models such as MLP, LSTM, transformer or reservoir networks removes the advantage. Furthermore, on a real robotic arm the core withstands diverse visual perturbations that collapse the baselines. Our results suggest that visual robustness can be inherited from biophysically detailed circuit dynamics rather than learned by task-specific controllers.
Read the full abstract

All authors Linrui Qian, Jiajia Zhang, Gan He, Bohan Sun, Zhiwei Lin, Qianhao Wang, Zewu Cai, Nianyu Yi, Mengdi Zhao, Kai Du

Machine Learning

GRPO Training Dynamics for Small Language Models

Rajat Ghosh, Vaishnavi Bhargava, Henry Wong et al. (+2 more)

Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. How- ever, GRPO training dynamics on small language models (SLMs) remain poorly understood, limiting its reliable adoption and reproducibility in open and resource- constrained environments. In this work, we present a systematic study of GRPO fine-tuning for SLMs ranging from 1.5B to 7B parameters under a practical single- node 8xA100 compute budget. Our study spans multiple model families and reasoning domains, including mathematics, coding, and multiple-choice question answering (MCQ) in science. Across these settings, we analyze how group size affects policy convergence, training stability, and downstream benchmark per- formance. We further characterize tensor-level update dynamics during GRPO training and investigate whether the choice of LoRA target modules and layers can improve the performance of GRPO-tuned models. While our initial GRPO-tuned models outperform their base counterparts on approximately 80% of mathematical benchmark evaluations, they demonstrate limited capability on MCQ and code reasoning tasks. Guided by our mechanistic evaluations, we refined our LoRA and reward-shaping configurations to improve performance in latter domains. These findings provide practical guidance for GRPO training for SLMs.
Read the full abstract

All authors Rajat Ghosh, Vaishnavi Bhargava, Henry Wong, Aryan Singhal, Debojyoti Dutta

Classical Physics

Automated Sailboat Navigation using Controllabilty-Aware Nonlinear Model Predicitive Control under Stochastic Winds

Junzhuo Wu, Ya-Jun J Pan, Chao Shen et al. (+2 more)

This paper presents a systematic approach to plan and execute a time-efficient sailboat trajectory under the challenging stochastic wind conditions for automated sailboat. Unlike deterministic scenarios, stochastic wind disturbances introduce challenges such as gust unpredictability, directional shifts, and fluctuating apparent wind speeds. These characteristics render traditional planning methods, such as Line-of-Sight (LoS) and waypoint approaches, to be ineffective and not applicable, as they often rely on static or deterministic environmental models. This paper proposed a new path planner and controller based on nonlinear model predictive control method. It is compared with a baseline planner and controller. A Lie-algebraic analysis of the sailboat dynamics is carried out to identify the operating conditions under which the vessel loses first-order control authority in surge, and these conditions are embedded as constraints in the NMPC. Finally, simulation results are provided to validate the proposed framework.
Read the full abstract

All authors Junzhuo Wu, Ya-Jun J Pan, Chao Shen, Sean Smith, Emmanuel Witrant

Information Retrieval

Residual Trajectory Distillation for Generative Retrieval

Weihao Shen, Wei Chen, Fuwei Zhang et al. (+4 more)

Generative retrieval has emerged as a general retrieval paradigm, representing items with discrete Semantic IDs (SIDs) and retrieving them through autoregressive identifier generation. When SIDs are constructed with residual quantization (RQ), standard retrieval training supervises only the selected codes and discards the residual trajectories that produce them. The same hard code can nevertheless arise from different preferences over competing codewords, while the residual trajectory also contains information about subsequent quantization decisions. As a result, hard SID supervision collapses distinct quantization behaviors into identical targets and leaves information available during indexing unused in retrieval training. We introduce ResTD, a Residual Trajectory Distillation framework that transfers this discarded indexing information into retrieval training. Treating the frozen RQ indexer as a process teacher, it distills residual-induced codeword preferences into SID-decoding states. This supervision recovers distinctions hidden by hard assignments and allows earlier decoder states to capture information about subsequent quantization decisions before the corresponding SID suffix is generated. In this way, richer information from SID construction is incorporated into retrieval learning while preserving the original retrieval index and inference procedure. Experiments on multilingual e-commerce retrieval show consistent improvements over strong baselines and matched training controls. Controlled comparisons show that residual-derived targets outperform the tested codebook-only soft targets. Representation probes further show that future codebook preferences become more recoverable from earlier decoder states. ResTD can also be readily extended beyond retrieval to generative recommendation. Code is available at: https://github.com/Nevaeh7/iclr2027_ResTD.git.
Read the full abstract

All authors Weihao Shen, Wei Chen, Fuwei Zhang, Guojun Liu, Qingsong Hua, Wei Lin, Fuzhen Zhuang

Quantum Physics

A Dichotomy for MIP* in the Presence of Unital Noise

Yangjing Dong, Zhenyu Jiang, Minglong Qin et al. (+2 more)

We study two-prover one-round quantum interactive proofs in which the provers share arbitrarily many copies of a noisy EPR pair. Prior work showed that if the shared state $\psi$ has quantum maximal correlation $\rho_{\max}(\psi) < 1$, then $\mathrm{MIP}^{\psi}[\mathrm{poly}, O(1)] = \mathrm{MIP} = \mathrm{NEXP}$, while noiseless EPR pairs give $\mathrm{MIP}^{\mathrm{EPR}}[\mathrm{poly}, O(1)] = \mathrm{RE}$. That result leaves two cases open: answers of polynomial length, and noise that keeps $\rho_{\max}(\psi) = 1$, which unital noise can do. We settle both for unital noise. Equivalently, let $\psi$ be any two-qubit state with maximally mixed marginals. We show that $$\mathsf{MIP}^{\psi}[\mathrm{poly},\mathrm{poly}] =\mathsf{MIP} =\mathsf{NEXP},~\text{if $\psi$ is separable or $\rho_{\max}(\psi)<1$};$$ $$\mathsf{MIP}^{\psi}[\mathrm{poly},\mathrm{poly}] =\mathsf{RE}, \text{if $\psi$ is entangled and $\rho_{\max}(\psi)=1$.}$$ Beyond this complexity-theoretic dichotomy, our proof introduces two techniques of potential independent interest. The first technique approximates quantum measurements by positive low-degree operators. We prove that the square roots of the measurement elements, after applying the smoothing operation, can be approximated by low-degree operators, with error controlled in the Schatten 4-norm. This further gives a positive low-degree approximation with small normalization error. Second, we introduce Pauli folding, a randomized dimension-reduction method for low-degree quantum operators. For fixed accuracy, the number of qubits after folding is polynomial in the Pauli degree and the number of outcomes and does not depend on $n$. Moreover, Pauli folding preserves Hilbert-Schmidt inner products in expectation and is approximately multiplicative. This is an exponential improvement over the dimension reductions via invariance principles in all previous works.
Read the full abstract

All authors Yangjing Dong, Zhenyu Jiang, Minglong Qin, Penghui Yao, Haigang Zhou

Category Theory

Orthogonal Model Structures

Yang Gao, Yu-xiao Yang and Pu Zhang

This paper studies orthogonal model structures, i.e., model structures such that a lifting in the Lifting axiom is unique. Cofibrant (fibrant) objects are defined without initial (terminal) objects. For an orthogonal model structure on a category with enough cofibrant objects and fibrant objects, it is proved that the homotopy category is equivalent to the full subcategory of cofibrant-fibrant objects. TTF model structures, bi-reflective model structures, and torsion model structures, are introduced. They are all orthogonal. One to one correspondences between TTF model structures and TTF triples in an abelian category, bi-reflective model structures and bi-reflective pairs in any category, and torsion model structures and twin torsion pairs in an abelian category, are established in a constructive way. Torsion model structures on a poset, on the category of $G$-sets, and on the category of topological groups, are also constructed. The homotopy categories of all these model structures are computed. In particular, the homotopy category of a TTF model structure is an abelian category.
Read the full abstract

Digital Libraries

Augmenting Italian Cultural Heritage with Virtual and Digital Technologies: the final outcomes of Project CHANGES' Spoke 4

Silvio Peroni, Gianluca Genovese, Roberto Balzani et al. (+107 more)

CHANGES (Cultural Heritage Innovation for Next-Gen Sustainable Society) was a project coordinated by the CHANGES Foundation, bringing together complementary disciplines and expertise across the entire cultural heritage lifecycle. This article focuses on the project's research area dedicated to applying virtual technologies to museums and art collections. This research enabled us to experiment with different types of museums and art collections across Italy, designing case studies and best practices that institutions and similar contexts can adapt and reuse. The meta-analysis of the case studies showed that museum types play a decisive role in shaping not only technological choices but also organisational strategies, training models, and pathways to sustainability. This work also allowed us to identify technological and organisational gaps that go beyond single cases and reflect shared challenges across museum contexts. Finally, we documented the success of the engagement, exploitation, and dissemination strategy proposed in the project.
Read the full abstract

All authors Silvio Peroni, Gianluca Genovese, Roberto Balzani, Silvano Montaldo, Sofia Pescarin, Cristina Caterina Amitrano, Luisa Ammirati, Riccardo Antonino, Giorgio Bacci, Davide Bagnaresi, Sebastian Barzaghi, Giuliana Benvenuti, Marco Bertini, Luca Bevilacqua, Marco Biffi, Elisa Bonacini, Federica Bonifazi, Alice Bordignon, Davide Borra, Andrea Bottino, Ivana Bruno, Daniele Caccavale, Marcello Calogero, Giuseppe Capotorto, Andrea Carpentieri, Veronica Casadei, Cristina Casero, Maurizio Cattani, Roberto Cavallo Perin, Vito Leonardo Chiechi, Fabio Ciotti, Luca Cipriani, Simona Colitti, Federica Collina, Michela Contessi, Lorenzo Copelli, Michele Corriero, Marianna Cuomo, Francesca D'Angelo, Rossana Damiano, Marilena Daquino, Stefano De Martino, Kevin De Vecchis, Davide Domenici, Nicole Dore, Francesca Fabbri, Bruno Fanini, Filippo Fantini, Fabrizio Federici, Daniele Ferdani, Enrico Ferraris, Giulia Fiorini, Anna Forte, Rocco Furferi, Riccardo Gagliarducci, Vincenzo Gattulli, Manuel Gentile, Federica Giacomini, Valentina Alena Girelli, Martina Grinello, Bianca Gualandi, Jasmine Habsy, Stephan Hassam, Ivan Heibi, Alessandro Iannucci, Alessandra Inglese, Marco Lamorte, Laura Travaglini, Federica Maietti, Rachele Manganelli Del Fà, Gianluigi Mangiapane, Nicola Mariniello, Giulia Marsili, Arcangelo Massari, Marcello Massidda, Michele Mellara, Enrico Mensa, Mattia Modugno, Roberto Montanari, Antonio Monteleone, Arianna Moretti, Elena Musiani, Francesca Nicolais, Sara Obbiso, Carmelo Occhipinti, Francesca Paruzzo, Cecilia Pennacini, Davide Perinciolo, Mario Petrella, Margherita Elena Pomero, Roberta Presta, Maria Felicia Rega, Giulia Renda, Diego Ronchi, Alessandro Rossi, Nicola Santopuoli, Chiara Scardozzi, Nicolò Serafino, Ilaria Serati, Ulderico Sicilia, Stefano Sorrentino, Daniele Spedicati, Cristina Stalteri, Riccardo Stracuzzi, Mattia Sullini, Ursula Thun Hohenstein, Maria Alessandra Tini, Federica Veratelli, Riccardo Zanzi, Guido Nicolas Zingari

Computer Vision

Rethinking Generative Image Compression at Extremely Low Bitrates

Tianyu Zhang, Zhaoyang Jia, Houqiang Li et al. (+1 more)

Generative image compression produces visually plausible reconstructions at low bitrates, yet their behavior as the rate approaches zero remains largely unexplored. When pushed below normal operating rates, representative codecs undergo semantic collapse: rather than gracefully losing source-specific detail, they produce malformed or unrecognizable content. Our analysis identifies two factors. As the bitrate decreases, reconstruction losses increasingly conflict with semantic objectives on gradients and visual results, while pixel-space and reconstruction-oriented VAE diffusion models become less efficient on semantic preservation. Guided by these findings, we introduce RAE-CoD, a compression-oriented diffusion (CoD) built in a representation autoencoder (RAE) space with direct alignment between compressed and source representations, preserving recognizable, naturally structured content for a $256\times256$ image with as few as 16 bits. We evaluate this framework using five vision foundation models (VFM) and a blinded vision-language model protocol. On MSCOCO-30K, RAE-CoD stands out from all evaluation. At 0.001-0.008 bpp, it reduces relative VFM feature MSE and Fréchet Distance ratio by at least 25.7% and 69.1% over the best competitors. Meanwhile, semantic recognizability and quality of the reconstructions remain nearly constant while source consistency falls smoothly, replacing abrupt semantic collapse with a graceful transition toward unconditional generation. Code will be released at https://github.com/LuizScarlet/RAE-CoD.
Read the full abstract

All authors Tianyu Zhang, Zhaoyang Jia, Houqiang Li, Dong Liu

Number Theory

The cardinality of a set containing the pairwise sums of four positive integers

Wouter van Doorn and John Erlbacher

Choi, Erdős and Szemerédi showed that there exists an absolute constant $C$ such that for all subsets $A \subseteq \{1, 2, \ldots, 2n\}$ with at least $n+C$ elements, there exist four distinct positive integers whose pairwise sums are all contained in $A$. A proof that one can take $C = 3166$ was recently sketched by the first author, and here we show that we actually have $C = 4$ for all $n \ge 6$, which is optimal. The proof we present was originally conceived of by AI, with the final result proved and formalized by Aristotle, the formal reasoning agent developed by Harmonic.
Read the full abstract

Classical Analysis and ODEs

A Note on Capacity Muckenhoupt Weights with respect to the Hausdorff Content

Yangzhi Zhang and Ciqiang Zhuo

Let $p\in[1,\infty)$ and $\delta\in(0,n]$. Recently, to characterize the weighted boundedness of maximal operator on Choquet integrals based on Hausdorff content $\mathcal H_\infty^\delta$, a class of Capacity Muckenhoupt weights is introduced, denoted by $\mathcal A_{p,\delta}$, and, for any fixed $\delta\in(0,n]$, this new class of weights is proved to satisfy the self-improving property with respect to the index $p\in(1,\infty)$. In this note, we show that, for every fixed $p\in[1,\infty)$, the class of capacity Muckenhoupt weights $\mathcal A_{p,\delta}$ fails to satisfy the self-improving property with respect to the index $\delta\in(0,n]$.
Read the full abstract

Information Retrieval

Learning Multiresolution Relevance for Hierarchical Generative Retrieval

Weihao Shen, Wei Chen, Fuwei Zhang et al. (+4 more)

Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes and diverge at finer depths, with branching patterns varying across queries. These paths reveal how relevance is distributed across successive refinements, yet standard full-SID supervision treats them as separate training targets. To make this allocation explicit, we formulate multiresolution relevance as consistent conditional distributions induced by a single document-level relevance measure across the SID hierarchy. We introduce RARS, Resolution-Aligned Relevance Supervision, which uses the resulting refinement-level distributions to supervise a shared query representation. RARS aggregates document relevance over prefixes and trains a prefix-conditioned predictor to allocate relevance among sibling branches. All relevance-bearing children participate in local competition, and each local loss is weighted by the relevance mass reaching its parent. This objective trains the query encoder to capture both the coarse structure shared by relevant documents and their finer branch allocations. The predictor is discarded after training, preserving standard autoregressive retrieval at inference. Experiments on three multilingual ESCI locales show consistent improvements over matched full-SID training under autoregressive decoding. RARS also outperforms grouped soft-target, decoder soft-target, and sampled-tree supervision under a common retrieval rule. The gains persist across alternative identifier structures and relevance definitions. Code is available at: https://github.com/Nevaeh7/RARS
Read the full abstract

All authors Weihao Shen, Wei Chen, Fuwei Zhang, Guojun Liu, Qingsong Hua, Wei Lin, Fuzhen Zhuang

Human-Computer Interaction

When Data Becomes Judgment: Misaligned Interpretations and Accountability in Food Delivery Platforms

Yibo Meng, Shuoning Shi, Bingyi Liu et al. (+1 more)

Food delivery platforms mediate service encounters through real-time tracking data. While presented as objective, such data often obscures the situational constraints shaping delivery work, producing systematic misalignments between user perception and courier experience. This study presents a socio-technical analysis of real-time mobile tracking systems in the wild. Through semi-structured interviews with 23 users and 17 couriers on Chinese food delivery platforms, we identify two interrelated dynamics. First, users operate within a data-as-behavior interpretive framework, translating spatial and temporal anomalies into moralized judgments of courier negligence. Second, couriers engage in anticipatory data management, a form of hidden digital labor in which they reshape their physical behavior to produce interface-legible trajectories rather than physically optimal ones. Together, these findings expose a burden-shifting mechanism—characterizing the systemic outcomes of decontextualized interface design rather than explicit designer intent—in current tracking architectures, demonstrating how current tracking architectures leave gig workers bearing much of the explanatory burden. We propose design directions toward contextual transparency, redistributing this explanatory burden from individual workers to the platforms that possess the logistical context to bear it.
Read the full abstract

All authors Yibo Meng, Shuoning Shi, Bingyi Liu, Hongkai Chen

Cryptography and Security

XIM: The XDC Interledger Messaging Protocol

Atul Khekade, Ritesh Kakkad, Wanwiset Peerapatanapokin et al. (+1 more)

Distributed ledgers, privacy-preserving institutional networks, and conventional payment systems increasingly need to exchange authenticated messages and settle assets across heterogeneous trust domains. Existing interoperability systems typically optimize for one of three concerns: application-level abstraction, cross-chain message transport, or synchronized execution within a related ledger family. This paper proposes XIM, the XDC Interledger Messaging Protocol, a chain-agnostic protocol for transporting canonical messages across heterogeneous networks while allowing each communication lane to select an explicit verification policy. XIM separates message semantics from transport, verification, execution, routing, asset identity, and compliance metadata. Its cryptographic state is represented by deterministic message identifiers and commitment roots, while an append-only transition log provides auditability and replay protection. XIM introduces a Universal Asset Identifier (UAID), a pluggable adapter interface, lane-scoped security policies, and an optional policy-aware route graph for multi-hop settlement. XDC Network can serve as a coordination and settlement domain without requiring every XIM message or route to transact through XDC. We specify the protocol model, state machine, message encoding, commitment structure, verification modes, failure semantics, security assumptions, threat model, implementation architecture, and an incremental deployment plan. The design targets public blockchains, permissioned ledgers, institutional networks, and authenticated financial-system gateways, with particular attention to stablecoins, tokenized assets, trade finance, and ISO 20022-compatible payment workflows.
Read the full abstract

All authors Atul Khekade, Ritesh Kakkad, Wanwiset Peerapatanapokin, Behnam Mohammadkhani

Algebraic Geometry

Normal Bundle Splitting Strata of Rational Curves in Toric Varieties

Hikari Iwasaki

We study stratification by normal-bundle splitting type in families of unramified rational curves of fixed class in a smooth projective toric variety over an algebraically closed field {of arbitrary characteristic}. Using the Cox construction, we construct an explicit two-term resolution of the relative normal bundle by direct sums of line bundles on the universal curve over the fixed-source parameter space. Then we construct morphisms of vector bundles on the parameter space, which we call relative cohomology morphisms, from which we can investigate generic splitting type and jumping loci of the family. In particular, we obtain sufficient numerical criteria for unbalancedness of the normal bundle. We apply this method to blowups of projective space along linear subspaces, and show that the numerical criteria for unbalancedness are equivalent to those of Cela–Lian \cite{CelaLian2026}. We also obtain explicit formulas for the expected Chow classes of the jump loci.
Read the full abstract

Numerical Analysis

On bounds for rank growth of iterands in conjugate gradients for Lyapunov equation

Jana Lungová and Martin Plešinger

We focus on solving the Lyapunov equation $AX + XA^T = F$, where $A$, $X$ and $F$ are square matrices, $A$ is symmetric positive definite (SPD) and sparse, and $F$ is symmetric and of a low-rank. The solution $X$ is then also symmetric and in general dense, but it can be approximated by a low-rank matrix. If $n$ is large, $X$ cannot be computed directly, but it is accessible by using the so-called low-rank arithmetics (LRA). The equation is solved by matrix reformulation of the method of conjugate gradients (MCG). We are interested in the behavior of ranks of the solution approximations $X_\ell$, residuals $R_\ell$, and direction vectors $P_\ell$ during iterations.
Read the full abstract

Probability

Convergence of the free energy of vector spin glasses with non-convex interactions

Fu-Hsuan Ho

We prove that the enriched free energy of vector spin glasses converges as the number of sites tends to infinity. The interaction is not assumed to be convex. This is the convergence assumed by Chen and Mourrat (Probab. Math. Phys., 2025) in their representation of the limit as a critical point representation, so that representation holds without further assumptions.
Read the full abstract

Machine Learning

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Shengjie Jin, Hengbo Xu, Zelong Sun et al. (+2 more)

Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with existing methods reveal a collapse in deployment performance across cycles, while task performance with privileged information (PI) also declines. We address this collapse by prioritizing informative interaction steps for distillation and preserving PI-conditioned behavior as the student becomes the next teacher. We introduce Retentive and Selective Augmentation for Iterative Self-Distillation (ReSAIL), a plug-in augmentation for iterative PI-based self-distillation. ReSAIL selects interaction steps where PI most strongly changes the teacher's predictions and balances the resulting distillation losses across trajectories. It also regularizes the student's PI-conditioned output distributions toward those of the frozen teacher at selected and unselected steps to preserve PI-conditioned behavior for supervision in the next cycle. On ALFWorld and TextCraft, ReSAIL sustains substantial gains across model scales over three cycles, with an average absolute gain of 22.5% in final-cycle success rates when added to self-distillation baselines. Sensitivity-guided selection of offline data also improves action prediction accuracy for multimodal GUI agents on AITZ. These findings provide the first evidence that a more robust learning mechanism can effectively mitigate performance collapse in iterative agent self-distillation over deployment trajectories.
Read the full abstract

All authors Shengjie Jin, Hengbo Xu, Zelong Sun, YuJie Guo, Zhiwu Lu

Robotics

FORTE: Forecasting Occupancy for Spatiotemporal Risk-Aware Planning in Dynamic Environments

Hahjin Lee and Young J. Kim

Safe navigation in dynamic environments requires anticipating future environmental states to account for spatiotemporal risks, specifically when and where collisions may occur. To this end, occupancy grid map (OGM) prediction has been widely adopted as an effective approach. However, existing OGM-based navigation methods often struggle to achieve accurate and efficient forecasting and fail to fully exploit the temporal information in predicted OGMs during planning. To address these challenges, we propose FORTE, a navigation framework that directly exploits the spatiotemporal evolution of predicted occupancy from the perspectives of spatiotemporal occupancy overlap and occupancy directivity. Based on these properties, FORTE evaluates multiple topology-distinct paths and selects the suitable one without explicit object detection or tracking. To support online planning, we formulate a latent diffusion model-based OGM predictor that generates the entire forecast horizon in a non-autoregressive manner while maintaining temporal consistency through temporal shift modules. Extensive evaluations demonstrate that FORTE outperforms state-of-the-art baselines. For prediction, FORTE achieves up to 215.3% higher IoU and 5.24x faster inference; for navigation, it yields up to a 3.5x higher success rate.
Read the full abstract

Robotics

Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents

Zhijie Wei, Ferris Tan, Jinghui Wang et al. (+1 more)

When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posing a virtual target gripper through a few tools, the agent's harness, its prompts, tools, and control rules, largely determines success, and until now it has been written by hand. We show that this harness can be improved automatically by another coding agent, the optimizer agent, and report two findings about what makes it work. First, the number of rollouts the optimizer agent sees per round governs whether the evolved harness generalizes: with rounds fixed, held-out success rises as the training batch grows from 5 to 100 rollouts, while small batches overfit the training tasks. Second, the optimizer agent must not be given free rein. Accepting every revision it proposes degrades the harness within a few rounds; a simple Champion-Challenger rule that promotes a revision only if it beats the incumbent on the same fixed cases turns the same loop into one that raises held-out success on LIBERO tasks from 51% to 67% over 30 rounds. The evolved harness is also a natural place to attach a pretrained policy, through one tool that hands it control. Distilling the rollouts of that combination back into the policy with multi-teacher on-policy distillation yields a standalone policy at 62.2% on RoboCasa365 under the official protocol, 4.8 points above its starting point with no harness at inference; the evolved harness on top of the distilled policy reaches 71.2% on the RoboCasa365 leaderboard benchmark, 13.1 points above the best published entry, and the loop closes when harness evolution resumes on the stronger policy. Automatic harness evolution for visual-interface robot agents is thus feasible, but its gains hinge on the rollout scale behind each decision and on how the optimizer agent's revisions are selected.
Read the full abstract

All authors Zhijie Wei, Ferris Tan, Jinghui Wang, Hao Zhou

Strongly Correlated Electrons

Varying A-site radius and size disorder to tune magnetic ordering in compositionally complex perovskite oxides

Madeleine Geers, Ravi Kiran Dokala, Roland Mathieu et al. (+1 more)

A long standing goal of magnetochemists is to be able to control ordering temperatures through compositional engineering. Here we report the synthesis of a perovskite oxide with twelve cations accommodated within a single phase solid solution, AM7O$_3$, A = La$_{\frac{1}{5}}$Sm$_{\frac{1}{5}}$Gd$_{\frac{1}{5}}$Nd$_{\frac{1}{5}}$Dy$_{\frac{1}{5}}$ (A5), and M7 = Ti$_{\frac{1}{7}}$Cr$_{\frac{1}{7}}$Mn$_{\frac{1}{7}}$Fe$_{\frac{1}{7}}$Co$_{\frac{1}{7}}$Ni$_{\frac{1}{7}}$Cu$_{\frac{1}{7}}$. Bulk magnetometry measurements for A5M7O$_3$, as well as for A = La, Gd and La$_{\frac{1}{2}}$Gd$_{\frac{1}{2}}$, show that all these compounds magnetically order as ferrimagnets between 89 and 115 K. We find that the magnetic properties are influenced by considering a combination of the size disorder parameter alongside the A-site cationic radii and valence electrons.
Read the full abstract

All authors Madeleine Geers, Ravi Kiran Dokala, Roland Mathieu, Rebecca Clulow

Quantum Physics

SQD-Agent: LLM-driven agentic framework for Quantum Chemistry workflows

Kislaya Tiwari and Anupama Ray

Quantum algorithms and quantum hardware are advancing towards a promising paradigm for scientific applications. However, translating domain-specific problems into executable hybrid quantum-classical workflows remains a significant barrier for application researchers due to the required expertise in quantum algorithms, nuances in quantum programming, and hardware-aware system integration. At the same time, AI and primarily LLM based agents are increasingly capable of interpreting natural-language intent, reasoning over complex workflows, and translating high-level objectives into executable code and building computational pipelines. In this work, we introduce SQD Agent, an LLM-based agentic framework that translates natural-language user intent into executable workflows for Quantum Chemistry applications where algorithms from the Sample-Based Quantum Diagonalization (SQD) family are used. By automating this translation, SQD Agent reduces the level of human expertise and configuration overhead required, thereby simplifying experimentation in hybrid quantum-classical settings for application researchers new to quantum. SQD Agent adopts a modular and extensible architecture that supports seamless integration of heterogeneous quantum backends, classical solvers, and workflow components, ensuring adaptability to rapidly evolving quantum ecosystems. The framework further incorporates interactive capabilities for on-demand profiling, bottleneck analysis, resource optimization, intelligent result caching, and convergence visualization. Key features include quantum chemistry experiments, error mitigation on real quantum hardware, together with analysis of candidate mitigation schemes in terms of their potential error-recovery behavior and computational budget, helping users understand their practical trade-offs and decide which strategies to explore in subsequent experiments.
Read the full abstract

Optimization and Control

Generalized Geometry Block Proximal Linearized Method for Multiblock Nonconvex and Nonsmooth Optimization

Weifeng Yang

This paper considers a class of multiblock nonconvex and nonsmooth optimization problems arising in many applications. Existing methods construct proximal linearized operators or their variants within standard Euclidean geometry to solve this class of problems, forcing their block variable updates to rely on the standard inner product and its induced norm. Nevertheless, this construction fails to capture the geometric structure of the target problem, leading to low numerical efficiency. To overcome these drawbacks, we propose a generalized geometry proximal linearized operator for updating block variables, and develop the Generalized Geometry Block Proximal Linearized (GGBPL) method based on this operator. Compared with existing proximal linearized operators, the proposed operator allows the block surrogate functions to be constructed using arbitrary inner products and general admissible metrics, thereby enabling the GGBPL method to adapt its updates to the geometric structure of various problems. We also introduce the inertial version of GGBPL, named the inertial GGBPL (iGGBPL) method. We further establish a new unified convergence framework under this generalized geometry, within which we prove that our methods guarantee convergence of the objective function values, establish global convergence of the generated sequence to a critical point, and derive the convergence rate of our methods. We also establish an $\mathcal{O}(\varepsilon^{-2})$ iteration complexity bound for obtaining an $\varepsilon$-stationary point. We apply our methods to two nonconvex and nonsmooth problems: sparse nonnegative matrix factorization with $\ell_0$-constraints and sparse nonnegative CP decomposition with $\ell_0$-constraints. Numerical results demonstrate the superior numerical performance of our proposed methods over several state-of-the-art methods.
Read the full abstract

Computer Vision

BMASH: Ball-Motion-Aware Soccer Header Spotting

Ahmed Endris Hasen, Muhammad Shahzad Khan, Nikolaos Passalis et al. (+1 more)

Recent advances in computer vision have made broadcast sports videos increasingly useful for event analysis, performance assessment, and player-safety applications. In soccer, however, header spotting remains a challenging problem due to the subtle and short-lived nature of header events. This paper focuses on soccer header spotting: identifying moments in broadcast videos where the ball contacts a player's head. We first adapt and evaluate Video Swin as a strong action-recognition baseline for this task, and then introduce BMASH, a ball-motion-aware fusion framework that integrates detector-derived ball features. BMASH combines Video Swin action representations with ball-presence and motion features from frame-level soccer-ball detection, integrating player-action context with ball dynamics to distinguish headers from visually similar events. We evaluate BMASH using game-level splits with separate test matches and rotating validation folds, considering both centered-window classification and continuous full-video spotting. Results show that Video Swin provides a strong baseline for header spotting, while BMASH improves clip-level AP and ROC-AUC over the corresponding Video Swin baseline. In continuous full-video spotting, BMASH achieves a comparable event-level F1-performance with a different precision–recall trade-off.
Read the full abstract

All authors Ahmed Endris Hasen, Muhammad Shahzad Khan, Nikolaos Passalis, Jenni Raitoharju

Statistical Mechanics

Phase Separation in Fractonic Fluids: Coarsening, Interfaces, Nucleation, and Hyperuniformity in and out of Equilibrium

Raphael Maire

We develop a theory of phase separation in fluids conserving higher-order multipole moments of a scalar density, and investigate the resulting coarsening dynamics, nucleation, and interfacial fluctuations. We find that higher-order conservation laws slow the relaxation of all phenomena investigated, whereas nonequilibrium violations of the fluctuation–dissipation theorem suppress density and interfacial fluctuations while hindering nucleation. Simulations support these predictions.
Read the full abstract