Peer Revenue Equity in science

Papers

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

Computer Science

cs Watch Computer Science

Wednesday 30 September

Human-Computer Interaction

NarrativeSteward: Coordinating Delegation, Guidance, and Verification in Agent-Assisted Interactive Narrative Authoring

Wenjin Wang, Jiazhen Lei, Yuxin Sha et al. (+6 more)

Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As agents generate and revise extensive content, authors struggle to grasp its overall structure, local details, and relationships, complicating continued guidance. We present NarrativeSteward, an authoring environment that organizes outlines, worldbuilding, and narrative graphs as linked artifacts for agent implementation and author guidance. Agent dialogue and project-wide structural review help authors understand the evolving work and guide local and cross-layer revisions, while change records and execution verification help authors assess the resulting work. Technical tests validated the system's change records, recovery mechanisms, and execution diagnostics. In a 12-participant within-subject study, NarrativeSteward supported easier formulation of revision requests and inspection of changes, and greater perceived understanding of changes and story structure, than general-purpose agents. Qualitative findings show how reviewing the work and feedback helps authors develop requirements and guide subsequent delegation. We open-source NarrativeSteward at https://github.com/Tencent/NarrativeSteward.
Read the full abstract

All authors Wenjin Wang, Jiazhen Lei, Yuxin Sha, Nuwa Xi, Meng Zhao, Xingxi Yin, Qi Liu, Yuliang Shen, Zixun Sun

Machine Learning

PatchKV: Weight-Space Compensation of KV Cache

Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi et al. (+2 more)

Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compression methods reduce the cache through token eviction or approximation, but degrade sharply at aggressive compression budgets. We propose PatchKV, a training-free framework that compensates KV cache compression methods by carrying part of the context in the model's weights. PatchKV pairs an off-the-shelf compressed KV cache with a context-specific weight patch, which is computed once at context-loading time and served for downstream queries for the context. The weight patch is derived in closed form via ridge regression, by aligning the block-wise activations of context-derived reference query tokens under the full cache and the compressed cache. Once merged into the model, the patch leaves the forward graph and per-query inference cost unchanged in the single-context, multi-query setting. Across long-context QA (SCBench with up to 170K tokens, SQuAD, NIAH) and math (GSM8K) benchmarks on three model architectures, PatchKV consistently improves cache compression methods, suggesting an alternative direction to compensate them at aggressive budgets.
Read the full abstract

All authors Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi, Donggyun Kim, Seunghoon Hong

Computational Complexity · Cross-listed from quant-ph

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 · Cross-listed from stat.ML

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

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

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

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

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

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

Multiagent Systems · Cross-listed from quant-ph

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

Machine Learning · Cross-listed from math.OC

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

Artificial Intelligence

MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate

Jiaming Zhang, Yuwan Liu, Yue Huang et al. (+1 more)

Autonomous agents powered by large language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, industry initiatives increasingly assess agent reputation from past behavior and provide performance leaderboards. However, reputation derived from past performance may not reliably predict an agent's behavior on new tasks, particularly when malicious agents can adapt their behavior and influence other agents during collaboration. We study reputation in multi-agent debate (MAD), where multiple agents answer the same query, debate to improve their answers, and aggregate them into a final output. We present MiniRep, a reputation-based aggregation system for MAD under malicious agents. To ground our threat model in established research, we construct an attack taxonomy drawing on reputation-system attacks and software-testing mutation operators, covering strategic exploitation of reputation and subtle corruption of agent proposals. Guided by this taxonomy, MiniRep evaluates agents based on both their behavior on the current task and their reputation over time, while preventing groups of agents with highly similar responses from dominating the final decision. We assess MiniRep across diverse tasks, LLM-agent compositions, corruption placements, and attack types drawn from our taxonomy. Our experimental results show that, MiniRep outperforms both conventional MAD aggregation and conventional reputation-based approaches on MATH no matter being attacked or not. Also, under a heterogeneous 10-agent setting on MATH, MiniRep outperforms all baselines in all 28 attack conditions.
Read the full abstract

All authors Jiaming Zhang, Yuwan Liu, Yue Huang, Sisi Duan

Machine Learning

Semantic-Aware Joint Source-Channel Optimization for Encoder-Agnostic Digital Video Communication

Xiangben Zhu, Caili Guo, Yang Yang et al. (+2 more)

Video semantic communication has attracted increasing attention as a promising approach to improving video transmission efficiency. However, most existing approaches rely on computationally intensive deep learning-based video encoders and decoders, which hinders their deployment in resource-constrained scenarios. To address this issue, we propose a lightweight semantic-aware joint source-channel optimization (SAJSCO) scheme that can be integrated into existing digital video communication systems as a plug-in module. Specifically, we develop a video communication system model in which the transmitter jointly optimizes source and channel coding parameters based on the inter-frame semantic importance of the input video and estimated channel state information. On this basis, we formulate an optimization problem that maximizes semantic importance weighted video reconstruction quality under a maximum bitrate constraint. To solve it, we first quantify inter-frame semantic importance using a cosine similarity-based metric with a shifted window mechanism. We then develop a multi-actor proximal policy optimization (MPPO) algorithm to solve the formulated problem by jointly adapting the source compression rate and channel coding rate. The learned policy can be directly applied to different video encoders without encoder-specific retraining or fine-tuning. SAJSCO achieves Bjøntegaard Delta rate reductions of 34.86% and 18.01% when integrated with H.265, a conventional video encoder, and DCVC-RT, a deep learning-based video encoder. Over-the-air experiments on a hardware testbed further demonstrate a PSNR gain of up to 1.448 dB with H.265 and an LPIPS reduction of up to 0.033 with DCVC-RT compared with the respective best-performing fixed-parameter baselines.
Read the full abstract

All authors Xiangben Zhu, Caili Guo, Yang Yang, Chuanhong Liu, Meiyi Zhu

Artificial Intelligence

ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning

Jinsung Jeon and Seung-won Hwang

Precise numerical reasoning with Large Language Models (LLMs) is essential for expanding their applicability to complex real-world tasks. However, text-based tokenization often fragments numbers, significantly hindering precise arithmetic reasoning. Meanwhile, numerical embeddings, despite arithmetic precision, rely on context-agnostic substitution that disregards the semantic role of numbers as identifiers. To combine the complementary strengths, we propose ANI (Adaptive Numerical Injection), a hybrid framework that governs the selective injection of numerical features based on the semantic context. By employing a context-aware gating mechanism, we selectively inject numerical embeddings (specifically FoNE) into the latent space, explicitly preserving nominal identifiers while enhancing quantitative operands. Through extensive evaluations across various LLMs, we demonstrate that ANI enhances MATH performance by 9.5 points over the official reference model, while maintaining robust performance on general linguistic benchmarks.
Read the full abstract

Computational Geometry

Polynomial-time algorithm for exact $(1,2)$-center problem under continuous Fréchet distance

Soumya Bhattacharya, Serene Rasheed and Sasanka Roy

In this paper, we explore the $(1,2)$-center problem for polygonal curves under continuous Fréchet distance. The $(k,\ell)$-center problem, in general, is known to be NP-hard. Aronov, Filtser, Horton, Katz, and Sheikhan (WADS'19) gave a polynomial-time algorithm for the $(1,2)$-center of curves in the plane under the discrete Fréchet distance. To the best of our knowledge, the $(1,2)$-center under continuous Fréchet distance has not been studied yet. We present a polynomial time algorithm to solve the problem exactly under both $\mathbb{L}_2$ and $\mathbb{L}_\infty$ norm, running in $O\bigr((n^2r+nr^2)^{2+\epsilon}\bigl)$ time for curves in the plane where $r$ is the number of input curves and $n$ is the maximum complexity of any curve. Further, for curves in any dimension $d$, the expected time to compute the center using the algorithm is $O\bigr((n^2r+nr^2)^{2(d-1)+\epsilon}\bigl)$. We have also shown that an $(1+\widetilde{\epsilon})-$factor approximation of $(1,2)$-center can be computed in $O(n^2r+nr^2+1/\epsilon^s)$ time for any $\epsilon>\widetilde{\epsilon}>0$ and some constant $s$ for curves in the plane. For curves in the plane, we have shown that, with the center restricted to be horizontal, we can compute the exact center in $O(n^2r+nr^2)$ time. An algorithm has been introduced to find a $3$-factor approximation of the $(1,2)$-center in time linear in the number of curves. A formulation was introduced by de Berg, Mehrabi, and Ophelders (CCCG'17) to measure Fréchet distance between a curve and a query segment under $\mathbb{L}_2$ norm for curves in the plane. We have shown the formulation is valid under both $\mathbb{L}_2$ and $\mathbb{L}_\infty$ norm for curves in $\mathbb{R}^d$.
Read the full abstract

Machine Learning

Physics-Informed Method of Group Data Handling: Adaptive Construction of Functional Representations with an Application to the Navier-Stokes Equations

Mykhailo Minin

Physics-informed computational methods usually optimize parameters within a functional representation whose structure is fixed in advance. This work proposes a Physics-Informed Method of Group Data Handling (PI-GMDH), in which representations of coupled physical fields are progressively constructed during solution. Candidate functional directions are evaluated through the first variation of the complete physical and observational objective, introduced in packages, and followed by block-coordinate damped Gauss-Newton coefficient optimization. The framework is demonstrated with tensor-product Chebyshev functions on the incompressible Navier-Stokes equations using a two-dimensional time-dependent Taylor-Green benchmark. Under the tested configuration, adaptive PI-GMDH reached validation and held-out test losses of 5.299e-19 and 5.296e-19 with 204, 201, and 175 active functions for u, v, and p. Complete degree-by-degree and all-terms PI-GMDH variants, together with selected PINN and KAN reference configurations, are used to examine the effect of structural construction policy. The results show that, for this controlled synthetic benchmark, selective progressive construction can provide a favorable combination of accuracy, representation size, and wall-clock time. The comparison is illustrative rather than a claim of universal superiority over alternative physics-informed approaches.
Read the full abstract

Human-Computer Interaction

Present After Presence: Subtraction, Givenness, and the Structure of Being-There

Koichi Toida

Presence research has often proceeded by addition, treating immersion, embodiment, agency, ownership, co-presence, reciprocity, and temporal simultaneity as conditions that stabilise the sense of being there. Yet immersive video suggests that several of these conditions can be weakened without eliminating Presence. Building on Bodyless Presence and Bodyless Presentness, this paper asks what is disclosed when such conditions are progressively subtracted. I distinguish three levels that should not be conflated: stabilising conditions that strengthen or support Presence; empirically resilient articulation-forms through which Presence is lived as here and now; and a transcendental limit-condition concerning the first-personal givenness of experience. Subtraction provides evidence for the resilience of here and now, but empirical resilience does not by itself establish constitutivity or transcendental necessity. I argue, on phenomenological rather than experimental grounds, that for-me-ness names the limit-condition within which any such spatial or temporal articulation can be experienced at all. The paper bridges operational Presence research with Husserlian givenness, Leibhaftigkeit, and image consciousness; rereads Bodyless Presence as exposing the resilience of here; rereads Bodyless Presentness as exposing the resilience of now; and develops a stratified account of Presence through Zahavi's pre-reflective self-awareness while taking Derrida's critique of self-presence seriously. It concludes by proposing immersive media as dissociation apparatuses for loosening conditions ordinarily coupled within experiential there-ness.
Read the full abstract

Computers and Society

The Concentration of Artificial Intelligence in Big Tech and Its Implications for Human Rights in the European Union

Marcin Marciniak

The development of advanced artificial intelligence is increasingly concentrated in a small group of vertically integrated technology companies. These firms control combinations of computing infrastructure, cloud services, data, foundation models, software ecosystems, and channels of distribution. This article argues that such concentration transforms market power into a form of private governance over the conditions in which fundamental rights are exercised. Drawing on an interdisciplinary narrative review, it examines how concentration affects equality of access, privacy, freedom of science, working conditions, access to essential resources, environmental protection, and the availability of effective remedies. Evidence from data-centre expansion in Ireland, the United Kingdom, the United States, and Chile, together with studies of automation and collective bargaining, shows that benefits may be widely distributed while decision-making power and economic returns remain concentrated. Concentration does not itself establish a rights violation, but it increases dependency, opacity, switching costs, and the risk that social and environmental costs are externalised. The article concludes that competition policy must be combined with rights-based impact assessment, interoperability, public research capacity, worker participation, and enforceable access to review and remedy.
Read the full abstract