Peer Revenue Play credits. Real papers.

Papers

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

Computer Science

cs Watch Computer Science

Friday 11 September

Robotics

Comfort by Construction: Adaptive, Comfort-Bounded Action Spaces for Learned Driving Policies

Anna Rothenhäusler, Daniel Jost, Raghu Rajan et al. (+4 more)

Data-driven driving simulators command accelerations and steering rates from a fixed grid without constraining the realized accelerations and jerks. As a result, reinforcement-learning policies inflate safety metrics through abrupt, last-second maneuvers that lie far outside the range of human driving and would be unacceptable to occupants of a real vehicle, so the metrics measure simulator permissiveness rather than policy quality. Enforcing comfort bounds naively is not enough: lateral limits shrink quadratically with speed, so clamping a static grid saturates it and destroys fine-grained control ("grid collapse"). We propose an adaptive action parameterization that rediscretizes the grid at every step to span exactly the per-step feasible control set, via closed-form inversion of the lateral-jerk constraint. We further present PufferDrive-Editor, a browser-based tool to audit realized kinematics and author kinematically challenging scenes. On the Waymo Open Motion Dataset and a hand-authored slalom, our adaptive model holds comfort violations below 1% while outperforming clipped-grid and direct-jerk baselines in navigability.
Read the full abstract

All authors Anna Rothenhäusler, Daniel Jost, Raghu Rajan, Faris Janjos, Oliver Scheel, Andreas Look, Joschka Boedecker

Machine Learning

Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions

Wenzhou Xia, Qiaoqiao Ding, Jingwei Liang et al. (+1 more)

Optimal transport (OT) compares distributions and aligns datasets in machine learning, yet unregularized discrete OT requires a linear program with quadratically many transport variables. We propose HELLO, a hierarchical solver that casts large-scale discrete OT as edge localization and uses dual potentials to guide both coarse-to-fine initialization and within-level refinement. Initialization propagates coarse dual potentials across a recursive subsampling hierarchy to assign candidate edges. Refinement then iteratively inserts the largest dual violators in each row and column until the relative KKT residual meets a prescribed tolerance, while budgeted pruning ensures linear memory complexity. For exact-arithmetic refinement, we prove finite termination at a global optimum under a symbolic lexicographic rule. At the million-point scale, HELLO attains lower transport objectives with order-of-magnitude runtime improvements over strong baselines across feature dimensions from single digits to thousands. It further scales to 1.28 million samples per marginal in 8192 dimensions on a single H100, using 41.6 GiB peak GPU memory while satisfying a full relative KKT residual below $10^{-6}$. Beyond standard discrete OT, the framework supports general pairwise costs and serves as a scalable balanced-OT oracle for semi-discrete OT, Gromov–Wasserstein, unbalanced OT, and OT-based Flow Matching.
Read the full abstract

All authors Wenzhou Xia, Qiaoqiao Ding, Jingwei Liang, Xiaoqun Zhang

Artificial Intelligence

How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks

Ali Ansari, Haoran Sun, Andy Zeyi Liu et al. (+48 more)

Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still struggle with advanced physics, a demanding test of their scientific reasoning and quantitative problem-solving abilities. Yet this impression does not always align with domain experts' experiences using these models in their work. We revisit these reported findings by evaluating frontier models on six widely used physics benchmarks and auditing them with experts, focusing on text-only problems with verifiable final answers. For each subfield of physics, faculty and graduate researchers with relevant expertise carefully review problem statements, reference solutions, and model responses to distinguish genuine model errors from grader errors, incorrect reference solutions, and ambiguous or underspecified questions. Most audited cases initially evaluated as incorrect reflect these benchmarking issues rather than errors in the models' physics reasoning. We then ask experts to address these benchmarking issues by correcting erroneous reference solutions and repairing or excluding flawed questions. We find that GPT-5.6-Sol's measured mean@4 rises from 47.3% to 78.7% on HLE-Physics and from 61.0% to 87.2% on CMT-Benchmark, while its corrected pass@4 reaches 94.4% on the 54 retained CritPt challenges. Corrected scores are computed on the retained evaluation subsets following expert review. Scores on the audited subsets of UGPhysics, PRISM-Physics, and PHYBench also rise substantially after correction. These findings suggest that current benchmarks substantially understate frontier models' ability to solve well-posed physics problems. Near-saturation on these closed-ended tasks highlights the need for more demanding, expert-validated evaluations.
Read the full abstract

All authors Ali Ansari, Haoran Sun, Andy Zeyi Liu, Mark Jabbour, Yongshan Ding, Steven Girvin, Yu He, Sohrab Ismail-Beigi, Aleksander Kubica, Owen D. Miller, Corey O'Hern, Vidvuds Ozolins, David Poland, A. Douglas Stone, Frank C. van den Bosch, Logan Wright, Navid Akbari, Santanu Antu, Kangle Cai, Andrew Calabrese-Day, Mateo Cárdenes Wuttig, Meng Cheng, Barry T. Chiang, Ali Ghorashi, Shouzhen Gu, Haoyang Huang, Zhibo Kang, Lukas Kienesberger, Hantian Liu, Charles Lomba, Zhongling Lu, Wenchao Ma, Rohin E. McIntosh, Evan McKinney, Ivan Rojkov, Xulei Sun, Yarone Meir Tokayer, Naveen Balaji Umasankar, Mira Varma, Leda Wang, Qimin Wang, Tyler Wang, Haoyu Wei, Jinming Yang, Jinchen Zhao, Sherlock Tingrui Zhao, Qinyuan Zheng, Jay S. Zou, Lucas Baker, Arman Cohan, John Sous

Computation and Language

Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models

Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie et al. (+2 more)

Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop reasoning. However, these benchmarks are typically short-horizon, requiring only a small number of retrieval or inference steps, and provide limited evidence of reliability on real-world tasks that involve following manuals spanning hundreds of pages with complex, interdependent guidelines. In this paper, we introduce Tasks over Application Manuals (TAM), a benchmark for evaluating long-horizon procedural reasoning. We construct TAM by curating real-world tasks from two domains: ICD-10-CM clinical coding (mapping medical conditions to diagnostic codes) and U.S. federal sentencing (computing crime sentencing guideline outcomes, specifically offense levels), with human-validated labels. Each task requires following an authoritative manual with tens of thousands of rules and executing a sequence of interdependent steps across different sections to produce an exact answer. We evaluate general-purpose prompting approaches, including retrieval-augmented generation, ReAct-style prompting, and an agent-harness baseline on GPT-5, and find that the best exact-match performance remains extremely low: 1% on ICD-10-CM coding and 15.5% on sentencing tasks. These results show that current benchmarks may overestimate LLM reasoning ability and miss a key challenge: reliably following long, rule-based procedures. The complete TAM data and code are publicly available.
Read the full abstract

All authors Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie, Sachin Chandrasekhar, Eugene Wen

Cryptography and Security

IntentFuzz: A Protocol-Aware Fuzzer for Automated Invariant Violation Detection in Intent-Based Cross-Chain Bridges

André Augusto, Christof Ferreira Torres, André Vasconcelos et al. (+1 more)

Cross-chain bridges move value between blockchains. Intent-based bridges are a variant where a solver fulfills a user's declared outcome and an off-chain settlement layer later reconciles the fill against the deposit. Existing smart-contract fuzzers and static analyzers only flag known-bad code patterns or require protocol-specific hand-written assertions. This work formalizes a taxonomy separating invariant violations, safety properties a contract must enforce locally, from settlement exposures legitimately delegated to the off-chain settlement layer, and proposes IntentFuzz: a protocol-aware fuzzer that recovers a bridge's intent structure and deposit/fill function roles directly from unannotated Solidity source, then synthesizes multi-step fuzz sequences using an LLM-based fallback to help build call arguments. IntentFuzz recovers the correct intent structure in 9/9 benchmark protocols and classifies deposit and fill functions with 100% recall and 82% combined precision; across a corpus of 77 manually labeled contracts, it reaches 79.5% bridge-classification precision and 97.2% recall, and among confirmed bridges, struct selection reaches 88.6% precision and recall while deposit and fill classification each reach 100% recall. On 23 planted-bug mutants, IntentFuzz attains 100% recall and 100% precision, executing 273 templates (507 transactions in a median of 14ms per template). Across 24 real-world deployments, it confirms 17 genuine invariant violations under heuristic-only input generation, rising to 22 with its LLM-assisted tier enabled, spanning eight vulnerable GitHub repositories, each finding reproducible against public, deployed bytecode.
Read the full abstract

All authors André Augusto, Christof Ferreira Torres, André Vasconcelos, Miguel Correia

Computation and Language

Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage

Foad Namjoo, Remy Ogasawara, Amirali Abdullah et al. (+3 more)

Binary-choice truth benchmarks ask models to choose between a correct and an incorrect answer, but if the two answers differ systematically in surface-level features, models can exceed chance without performing the intended reasoning. We show that this failure mode is detectable and can be exploited by downstream classifiers. In TruthfulQA, a simple six-feature logistic classifier achieves substantial accuracy in separating correct from incorrect answers. We further show that similar surface-level artifacts are present in additional benchmarks. To counteract this, we developed a general mechanism to clean them by removing the most leakage-reinforcing pairs. We release a version of TruthfulQA with surface-feature leakage reduced close to chance and provide a mechanism, Audit-Prune, so that the datasets can be cleaned before release.
Read the full abstract

All authors Foad Namjoo, Remy Ogasawara, Amirali Abdullah, Cullen Anderson, Narmeen Fatimah Oozeer, Jeff M. Phillips

Computer Vision

SV-Cine: Diagnosis-Conditioned Segmentation of Single Ventricle Physiology via Generative Data Augmentation

Lila Cunge

Single Ventricle Physiology (SVP) is a rare subtype of congenital heart disease characterized by the presence of a single functional cardiac ventricle with atypical anatomic configurations that challenge conventional image segmentation approaches. The scarcity of clinical data and the morphological diversity across SVP subtypes make the development of robust segmentation methods particularly difficult. To address these limitations, we propose a cardiac MRI segmentation framework focused on ventricular chambers and myocardium segmentation tailored for SVP. First, we introduce a data augmentation pipeline that generates synthetic 3D cardiac meshes using SDF4CHD and corresponding synthetic cardiac MRI through generative modeling. Second, we introduce SV-Cine, a diagnosis-conditioned adaptation of the foundation model CineMA that incorporates patient-level diagnostic information through Feature-wise Linear Modulation layers, enabling diagnosis-aware feature adaptation during segmentation. We evaluated the framework on an internal cohort with varying SVP subtypes. SV-Cine achieved median Dice scores of 0.89 (IQR: 0.80–0.91) for the left ventricle and 0.72 (IQR: 0.54–0.84) for the right ventricle, outperforming the strongest baseline, nnU-Net, by 0.39 Dice points on right ventricle segmentation. It also yields a median ejection fraction error of 5.55 percentage points (IQR: 3.41–7.69) for the dominant ventricle. Compared with the internal cohort, LV and myocardium segmentation performance was lower for the external cohort; whereas RV Dice scores were comparable for both cohorts. Our findings suggest that a pretrained foundation model can be adapted for highly specialized downstream tasks through usage of diagnosis priors while leveraging anatomic knowledge learned from large-scale MRI datasets during pretraining.
Read the full abstract

Computer Vision

Investigating Temporal Motion Features for Pose-to-Text Indian Sign Language Translation

Manav Dhamecha, Praveen Kumar Chandaliya and Pruthwik Mishra

We investigate the effect of pretrained T5 model scale and explicit motion features on pose-to-text Indian Sign Language Translation (SLT) for the WSLP 2026 Shared Task. Pose sequences are projected into the embedding space of T5 through a lightweight pose encoder, with the complete model fine-tuned to generate English text. The shared task data used for this work consists of a test set with 5,334 examples and a validation set with 5,257 examples. We compare T5-small, T5-base, and T5-large, and additionally introduce a motion-augmented variant, T5-small + Motion, that adds explicit frame-to-frame pose differences to the input representation. T5-small achieves the best BLEU and ROUGE scores among the spatial-only models, while T5-large obtains the highest chrF score. Augmenting T5-small with motion features yields the largest single improvement observed in our study, substantially improving BLEU over the spatial-only baseline and making it the strongest model overall on this metric. Our submitted system ranked 5th on the official WSLP 2026 SLT testing leaderboard. The source code and trained models are publicly available on GitHub and HuggingFace.
Read the full abstract

Systems and Control

An Adaptive Multi-Parameter ADMM Algorithm for Embedded MPC

Alberto Zaupa and Mikael Johansson

We introduce an adaptive multi-parameter variant of ADMM and prove that it exhibits local superlinear convergence once the set of active constraints has been identified. In simulations, the proposed algorithm consistently outperforms OSQP, a standard ADMM solver, in terms of iteration count. We then implement an MPC solver based on our method and compare its runtime against a broader selection of state-of-the-art algorithms. Evaluations on challenging benchmark problems reveal that our approach delivers competitive performance both in terms of average and worst-case solve times, without being limited to coarse tolerances, as is typically the case for standard ADMM implementations and first-order methods.
Read the full abstract

Systems and Control

Safe Stabilising Full-Order Affine Control Barrier Functions for Linear Systems (Extended)

Faisal Lawan, Joaquin Carrasco and Lanlan Su

Control barrier function safety filters enforce constraints by modifying a nominal input, but the resulting switching can destabilise the closed loop even when the nominal and filtered modes are individually stable. This paper presents a design framework for safe and globally exponentially stabilising controllers for linear systems with a single full-relative-degree affine constraint. We show that the filtered-mode spectrum is fixed by the barrier tuning and is independent of the plant, nominal controller, and quadratic-program weighting. This structure yields an explicit nominal controller for which the safety filter remains inactive everywhere. For a prescribed nominal controller, we prove that the nominal and filtered modes admit a strong common quadratic Lyapunov function if and only if the ratio of the nominal characteristic polynomial to the barrier polynomial is strongly strictly positive real. This equivalence characterises the existence of a common quadratic Lyapunov and provides a scalar frequency-domain test, along with an explicit interval of admissible gains. Building on these results, the extended analysis derives an explicit common storage function and reduces an existing LMI synthesis condition to a feasibility test in a single matrix variable. A flexible two-mass example explains a known instability mechanism and demonstrates how the proposed design restores safety and global exponential stability.
Read the full abstract

Performance · Cross-listed from quant-ph

Transpilation-Aware Runtime Prediction for Noisy Quantum Circuit Simulation

Davud Azizov, Javier Vela-Tambo and Tian Guo

Predicting the runtime of noisy quantum circuit simulations is important for scheduling, resource allocation, and performance optimization. However, accurate prediction is challenging because backend-aware transpilation can substantially alter the original circuit structure, while the backend-derived noise model and simulator execution behavior can introduce additional runtime variation. We study the effectiveness of graph neural networks (GNNs) and conventional regression methods in predicting Qiskit Aer simulation runtime measured after transpilation. We construct a dataset from a benchmark pool of 1,402 unique circuits spanning 22 circuit families, two Qiskit fake-backend configurations, and four transpiler optimization levels. Specifically, we compare a source GNN using original circuit information, hybrid GNN combining source-level graph with post-transpilation features, and transpiled GNN using only transpiled circuit information, along with five regression models. In the overall-model setting, the transpiled GNN achieves the strongest performance among the graph-based representations at all four optimization levels, obtaining $R^2$ values of 0.974, 0.713, 0.745, and 0.605 for optimization levels 0 through 3, respectively. However, under backend-specific evaluation, the advantage of GNN decreases, with conventional regression models matching or outperforming the GNNs in several settings. These results indicate that post-transpilation information is useful, while the value of explicit graph modeling depends on the backend and optimization level.
Read the full abstract

Operating Systems

SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading

Zihan Wang, Yuqi Wang, Lei Gong et al. (+5 more)

Mixture-of-Experts (MoE) creates a structural advantage for offloading: only a small fraction of activated experts need to reside in device memory, and if they can be loaded in time for computation, offloading can in principle approach full-load performance, where all model weights reside in device memory. Yet translating MoE's structural advantage into practical offloading gains remains challenging. We propose SeqMoE to bridge this gap. To maximize expert hits, we build predictive memory management: (i) Sequence-to-sequence prediction. We are the first to recast expert activation prediction as sequence modeling, enabling accurate multi-step, multi-layer forecasts that provide a long and reliable window for downstream decisions. (ii) Joint prefetch scheduling. We formulate prefetch scheduling as Job Sequencing with Deadlines to maximize expected expert hits and improve bandwidth efficiency. (iii) Forecast-driven caching. Leveraging the recursive nature of sequence modeling, we introduce a probabilistic Belady policy for future-aware eviction. To eliminate execution bottleneck, we develop (iv) Graph-compatible offloading runtime. We derive general runtime principles encompassing compute-transparent expert placement and synchronization-free orchestration disciplines for end-to-end graph capture. With 45% expert residency, SeqMoE averages a 96.97% hit rate and 80.22% of full-load performance, advancing the state of the art in MoE offloading.
Read the full abstract

All authors Zihan Wang, Yuqi Wang, Lei Gong, Cheng Tang, Wenqi Lou, Teng Wang, Chao Wang, Xuehai Zhou

Distributed Computing

A Dynamic Vertical Scaling Strategy for Distributed Stream Processing Applications in Edge Computing

Guilherme Hiago Costa dos Santos, Carlos Henrique Kayser and Tiago Coelho Ferreto

Distributed Stream Processing applications at the edge must reconcile low latency and high throughput with limited and heterogeneous resources. This paper presents a dynamic vertical scaling strategy based on Proximal Policy Optimization, formulated as a Partially Observable Markov Decision Process. The policy jointly adjusts task allocations and prioritizes compliance with a p95 end-to-end latency Service Level Objective. In EdgeStreamPy simulation experiments with two application profiles, two workloads, and ten paired placements per combination, the selected policies preserved throughput, obtained mean violation rates from 0.03% to 0.30%, below VRebalance in every scenario, and used less CPU in three of four combinations. The comparison covers complete controller configurations with different decision frequencies.
Read the full abstract

Networking

Virtualized 5G Tesbed using OpenAirInterface: Tutorial and Benchmarking Tests

M. Dória, V. Sousa, A. Campos et al. (+9 more)

The development of 5G and its evolutionary path to 6G brings virtualization as close as possible to the antennas. Native 3GPP systems are now software running at servers boosted by accelerator cards to cope with computationally intense signal processing. Meanwhile, the Radio Frequency (RF) front-end is still proprietary hardware, sheltering specific PHY-layer procedures like passband amplification/modulation. This approach takes advantage of the software's flexibility while keeping the complex microsecond signal processing performance from modern telecommunication systems. This paper provides tutorial material on the Core Network and Radio Access Network of OpenAirInterface (OAI) 5G stack on top of Universal Software Radio Peripheral (USRP) platforms. A set of blueprints showcases OAI's ability to provide a virtualized 5G network with different transmission capabilities and the possibility to use it with commercial mobile phones. Configuration discussions and throughput benchmark analyses follow installation and deployment instructions. Our results show that 5G prototyping using OAI and USRP frontends can lead to good reproducibility and consistent throughput.
Read the full abstract

All authors M. Dória, V. Sousa, A. Campos, N. Oliveira, P. Eduardo, P. Filho, C. Lima, J. Guilherme, D. Luna, I. Rego, M. Fernandes, A. Neto

Robotics

Tuning ROS 2 for Energy-Efficient Navigation: Empirical Insights from Costmap 2D Configurations

Michel Albonico, Andreas Wortmann and Ivano Malavolta

Robots are increasingly used in diverse application areas, where autonomous navigation plays a central role. As these systems become more widespread, improving their energy efficiency is critical to extending operational time and reducing environmental impact. The Robot Operating System (ROS) is a widely adopted middleware for robotics, offering a rich set of configurable packages. However, this flexibility can result in suboptimal software configurations in dynamic environments, negatively affecting both performance and energy consumption. This paper investigates the impact of ROS 2 package reconfigurations on the energy efficiency of mobile robot navigation. We conduct a controlled experiment in two warehouse-like scenarios (small and large) with varying obstacle layouts and Costmap 2D configurations (essential to the Nav2 stack). Through repeated trials, we measure energy usage, power profile, CPU load, memory consumption, and navigation performance. Results show that configurations must be carefully chosen for the specific robotic environment, and we were able to identify critical settings that lead to good and poor performance and energy consumption.
Read the full abstract

Systems and Control

End-to-End Battery Dispatch with Exact Rainflow Degradation via Mixed-Integer Differentiable Predictive Control

Eshagh Safarzadeh Ravajiri, Jan Drgona, Mahdi Mehrtash et al. (+1 more)

Optimal dispatch of battery energy storage systems requires balancing energy arbitrage against cycle-induced degradation, which is accurately quantified through rainflow cycle counting. However, rainflow's combinatorial, nondifferentiable algorithm is incompatible with both convex optimization and gradient-based neural network training. We present a self-supervised mixed-integer differentiable predictive control framework that trains neural policies directly on exact rainflow degradation through a novel differentiable rainflow layer combining exact gradients at state-of-charge extrema with dense proxy gradients on incremental changes, enabling stable end-to-end training while preserving true degradation physics. A mixed-integer differentiable architecture enforces power balance, dynamics, and mode exclusivity, with a safety filter guaranteeing constraint satisfaction. We evaluate the framework on 3,650 real battery-day scenarios (a 10-battery fleet over 365 days) spanning three utility regions (SDG&E California, Xcel Energy Colorado, APS Arizona) with diverse time-of-use pricing structures. A single-battery trained policy achieves a 0.35% performance gap on its training distribution with over 200x speedup, while fleet-wide training generalizes across all households and utility regions, achieving a 3.33% performance gap with 564x computational speedup (62 seconds vs. 9.7 hours) and 100% feasibility. The millisecond-scale inference reduces computation by over two orders of magnitude compared to mixed-integer solvers, enabling practical deployment at scale.
Read the full abstract

All authors Eshagh Safarzadeh Ravajiri, Jan Drgona, Mahdi Mehrtash, Benjamin F. Hobbs

Computer Vision

Generative Retrieval for Unsupervised Text-Based Person Search

Mang Ye, Yucheng Ji, Yang Bai et al. (+4 more)

Text-based person search (TBPS) aims to retrieve images of a target person from a large image gallery based on a given natural language description. Most existing methods rely on supervised learning with manually annotated image-text pairs. In this paper, we explore unsupervised TBPS, with only unlabeled images. We propose GTR+, a two-stage generation-then-retrieval framework. In the generation stage, we introduce a tiered description generation framework designed to produce fine-grained and stylistically diverse textual descriptions through a three-tier sequential process. The base tier leverages an automated question-and-answer mechanism to generate basic visual attribute descriptions; the intermediate tier enhances fine-grained detail using an inter-sample contrastive mechanism; the advanced tier further enriches textual diversity via a stylized expansion mechanism. In the retrieval stage, to mitigate the impact of noisy pseudo texts, we develop an adaptive confidence-weighted retrieval learning framework. We model image-text pairs as clean or noisy using a Gaussian Mixture Model, calibrated by real-time image-text similarity and static text generation probability from the prior stage, yielding adaptive sample weights during training. Beyond that, we also contribute LargeFine-Person, a large-scale TBPS dataset with high-quality, fine-grained, and diverse textual annotations, enabling a practical and generalizable TBPS pre-training benchmark under unsupervised setting. Experiments on multiple TBPS benchmarks demonstrate the effectiveness and generalization of both GTR+ and LargeFine-Person. Code is available at: https://github.com/Flame-Chasers/GTR.
Read the full abstract

All authors Mang Ye, Yucheng Ji, Yang Bai, Min Cao, Siyuan Chai, Bo Du, Min Zhang

Computation and Language

Fewer Words, Not Fewer Tokens: Measuring the Sanskrit Tokenization Penalty per Proposition

Devansh Sharma

Sanskrit fuses case, number, person and tense into word endings and chains clauses into compounds, so it is information-dense per word. Whether that density survives subword tokenization is a separate question, to be asked per unit of meaning rather than per word. On identical FLORES-200 devtest content, Sanskrit costs 1.774-2.187 times the English tokens under deployed tokenizers with vocabularies of 200,019 ids or more, but only 1.325-1.353 times the Hindi tokens. Against a deployed English tokenizer, Sanskrit-trained BPE arms then look cheaper per proposition than English on contemporary prose (0.887). Against a matched English control, the same algorithm and vocabulary trained on the English side of the same corpus, that flip disappears: at 32,000 and 64,000 pieces all 8 matched pairs, each size-matched arm against both a pair-matched and a byte-matched control, sit above 1.0 on prose with 95% intervals excluding it. The gap closes as the vocabulary grows: at 128,000 pieces the BPE pair reads 0.983 in domain while staying above parity out of domain (1.025) and on FLORES (1.116). The ratio factorises into a character-length ratio and a tokens-per-character ratio, the second near 1 throughout: what survives matched tokenization is character-level length, which Sanskrit prose lacks over English in SLP1 (1.028) and Sanskrit verse has (0.596). The robust statement is about deployed practice: on contemporary prose and on FLORES, with the Sanskrit side in SLP1 against the deployed o200k English pivot, Sanskrit costs 1.831-2.899 English tokens per proposition under the tokenizers people actually ship. Code, the results snapshot and every table here are public.
Read the full abstract

Robotics

Distributed Stochastic Optimal Control for Pattern-Oriented Swarms

Qingrui Zhang, Chenghao Yu, Feng Xue et al. (+1 more)

While offering significant promise for diverse applications, pattern-oriented swarms encounter multifaceted challenges in geometric control, self-organization, and safe navigation through dynamic environments. In this paper, we present a GRF-based stochastic optimal control framework to address these challenges within a unified probabilistic architecture. By extending the GRF into the temporal domain, the proposed framework casts collective coordination as a Bayesian inference task, enabling swarms to accommodate environmental uncertainty, satisfy non-convex constraints, and reconcile heterogeneous dynamics across diverse platforms. We develop an uncertainty- and safety-aware collision avoidance module for navigation in the presence of stochastic obstacle motion. The unscented transform is employed to propagate state uncertainty for both dynamic obstacles and neighboring agents, yielding principled confidence bounds for collision avoidance. In addition, density-guided pattern control is introduced, which encodes geometric patterns as implicit density fields. This representation decouples pattern specification from explicit agent-to-target assignments, thereby facilitating intrinsic self-healing and elastic reconfiguration in a distributed manner. The proposed framework is extensively evaluated through Monte Carlo simulations across diverse scenarios. Its model-agnostic nature is demonstrated on both quadrotor and fixed-wing UAV swarms, highlighting its generalizability across platforms with heterogeneous dynamics. Finally, the efficacy and robustness of the proposed method are validated through indoor experiments with a 15-quadrotor swarm and outdoor deployments involving 4 custom-built autonomous quadrotors. These experiments substantiate the proposed framework's capacity to maintain reliable geometric pattern transitions and safety-aware navigation within real-world environments.
Read the full abstract

All authors Qingrui Zhang, Chenghao Yu, Feng Xue, Xintong Wang

Human-Computer Interaction

Middleware for Feed Recommendation in Practice: How Feed Creators Build, Maintain, and Sustain Custom Feeds on Bluesky

Tony Zhou, Leijie Wang and Amy X. Zhang

Scholars have long proposed third-party middleware as an alternative to centralized algorithmic feeds: feeds built and distributed by independent feed creators. This vision saw no large-scale instantiation until Bluesky, a decentralized microblogging platform, introduced custom feeds in 2023. Although central to the middleware ecosystem, we know little about how feed creators understand their role, build feeds, and sustain them. Through interviews with n = 26 feed creators and third-party developers of feed-building tools, and analysis of n = 88,302 custom feeds, we identify two creator orientations—utility-providing and community-building. Additionally, creators struggle to maintain feeds that fully realize middleware ideals: they lack granular interaction data, receive little feedback, and lack technical expertise to act on either. Finally, creators sustain their feeds as unpaid hobbyists with little platform support and are divided on whether to monetize beyond covering costs. We conclude with design and policy implications for strengthening the middleware feed ecosystem.
Read the full abstract

Computer Vision

FIRM: Flow-based Imaging via Regularized Minimization

Shirin Shoushtari, Edward P. Chandler, Xiao Shi et al. (+1 more)

Flow matching methods for imaging inverse problems typically incorporate measurements through network conditioning or guidance during sampling. Neither approach explicitly applies the forward operator within the learned conditional velocity field. We develop a principled measurement-conditional velocity parameterization that does. For a linear interpolation path, we express the optimal velocity through the posterior mean $E[x_1|x_t, y]$ and show that this mean is the unique minimizer of a variational objective with an explicit data-consistency term. The velocity defined by this minimizer provably transports the source distribution to the measurement-conditioned posterior. This result leads to a forward operator-aware velocity field that is trained end-to-end and requires no separate guidance during sampling. Across five imaging tasks, our method achieves leading reconstruction quality with up to $50\times$ fewer network evaluations than competitive flow-based methods. Varying the number of sampling steps also controls the distortion-perception trade-off without retraining.
Read the full abstract

All authors Shirin Shoushtari, Edward P. Chandler, Xiao Shi, Ulugbek S. Kamilov

Artificial Intelligence

EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics

Jiaxu Zhao, Bahar Radmehr, Fares Fawzi et al. (+2 more)

Large language models (LLMs) are increasingly deployed as tutors, but it is unclear whether they support all students equally well. We introduce EduFair-Bench, a benchmark for auditing the pedagogical fairness of LLM tutors—whether tutoring quality varies systematically with student demographics. EduFair-Bench pairs a multi-domain question bank (mathematics, physics, chemistry) with a controlled simulation in which a fixed LLM student interacts with each tutor across nine demographic levels spanning four dimensions: gender, immigration background, first language, and socioeconomic status (SES). Tutoring quality is scored on five turn-level pedagogical metrics and four conversation-level dimensions, using an LLM judge validated against three-annotator consensus on 180 tutor turns. Bias is measured via paired Wilcoxon signed-rank tests and bootstrap effect-size confidence intervals. Two ablations (demographic cues conveyed through names; conflicting demographic information between tutor and student) disentangle tutor-driven from student-driven bias. Across five tutors, we find that model capability and demographic fairness are largely orthogonal: the smallest model is the most consistent while the four more capable tutors all exhibit wide demographic gaps with no clear capability-to-fairness ordering, pedagogy-specific RL training redistributes rather than removes bias, and language- and immigration-related cues produce larger gaps than gender- and SES-related cues.
Read the full abstract

All authors Jiaxu Zhao, Bahar Radmehr, Fares Fawzi, Tanya Nazaretsky, Tanja Käser

Game Theory

The possibility of solving a 3x3 Rubik's Cube under 2 seconds - Optimizing block building

Chung To Kong

Block building is an essential skill in speedcubing competitions. However, there is currently no systematic method to understand or analyze block-building techniques. Rewatching gameplay reveals only the outcome, not the underlying mechanism. This paper presents a systematic approach, the "AK-cubie method" (or "cubie method" for short), for constructing near-optimal block-building move sequences within a short computation time. Speedcubers can use the accompanying software to train their look-ahead and block-building skills. We hope this work will contribute to breaking the 2-second world record in the near future.
Read the full abstract

Sound

StepAudio 3 Gen Technical Report

Bin Lin, Bo Zhao, Boyang Wang et al. (+68 more)

We introduce StepAudio 3 Gen, a general-purpose audio generation model that supports zero-shot text-to-speech (TTS), voice design, vocal generation, sound effects, music, vibe speech, and mixtures of multiple audio types within a unified framework. At its core, StepAudio 3 Gen is a discrete autoregressive generator that models audio directly over residual vector quantization (RVQ) tokens, departing from the diffusion Transformer-based continuous generation paradigm prevalent in recent general audio models. Its StepAudio Tokenizer represents general audio at 12.5 Hz in a shared $16 \times 2048$ residual code space, jointly quantizing semantic and waveform-level acoustic features so that each code layer preserves both types of information. For generation, the backbone predicts the first codebook along the time axis using autoregressive modeling, while a lightweight causal Transformer completes the remaining fifteen codebooks along the codebook axis. Our study further identifies three key design principles: (1) interference-aware progressive pretraining for acquiring audio capabilities while preserving the textual abilities of the large language model, (2) RVQ Adaptor for effectively incorporating multi-codebook acoustic representations, and (3) discrete autoregressive modeling over a shared representation across general audio domains. With progressive pretraining, multi-task instruction training, and supervised fine-tuning, StepAudio 3 Gen achieves state-of-the-art performance on both TTS and voice design, while retaining strong generation capabilities across speech, vocals, sound effects, and music. Audio samples are available at https://stepaudiollm.github.io/step-audio-3-gen/.
Read the full abstract

All authors Bin Lin, Bo Zhao, Boyang Wang, Boyang Zhang, Boyong Wu, Chao Yan, Chen Geng, Chen Wu, Cheng Yi, Chengli Feng, Chenglin Zhu, DanNi Wan, Daxin Jiang, Dongqing Pang, Fei Tian, Feng Tian, Future Li, Gang Yu, Guanglong Yang, Jia Peng, Jiahao Song, Jiamin Fan, Jiangjie Zhen, Jianzheng Gao, Jun Chen, Li Xie, Lifang Zhang, Lingli Ji, Liying Shi, Lun Cai, Min Xu, Na Wang, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Ruijie Xiong, Runze Li, Shenghua Hu, Shi Qiu, Siqi Tu, Siyi Zhou, Tianjiao Deng, Wanying Lu, Weiming Niu, Wen Sun, WenWen Qu, Xiangyu Zhang, Xianwei Zhang, XiaoSu Su, Xing Chen, Xinyu Liu, Xuerui Yang, Yang Li, Yang Yang, Yechang Huang, Yibo Zhu, Yifan Zhang, Yiyang Xu, Yu Fu, Yu Luo, Yu Zhou, Yumang Wang, Yunzhou Ju, Yuxiang Yang, Zekai Liu, Zengwei Yao, Zhenwei Mou, Zheqi Dai, Zhiyue Wu, Zichao Zhou

Machine Learning

A Large-Scale AIS Dataset from Finnish Water

Debayan Bhattacharya, Ikram Ul Haq, Carlos Pichardo Vicencio et al. (+1 more)

This research paper contributes to the maritime research community by introducing a comprehensive AIS dataset from Finnish waters, specifically the Baltic Sea region. AIS data, initially designed for collision prevention, have evolved into a versatile tool with applications across diverse maritime domains. Our paper not only curates and categorises existing AIS datasets but also introduces a collected AIS dataset from the Baltic Sea area, renowned for its intercontinental cargo routes, military activities, and frozen water expanses. This dataset includes 229 millions data points and provides researchers with a resource for studying maritime activities and vessel behaviour in this dynamic region, notably distinguished by the inclusion of data from Finnish lakes. Our analysis includes a detailed listing of ship types and relevant features, empowering researchers to explore various maritime domains. To enhance comprehension and analysis, we provide visualisations of maritime traffic patterns. By publishing this AIS dataset, we aim to catalyse innovation and collaboration in maritime research, offering a gateway to deeper insights into maritime activities in the Baltic Sea and Finnish lakes.
Read the full abstract

All authors Debayan Bhattacharya, Ikram Ul Haq, Carlos Pichardo Vicencio, Sebastien Lafond

Robotics

A Robot Among People:From Social Imitation to the Social Becoming of Human Groups

Victor Tuan Vu Pham, Judith Dörrenbächer, Thomas H. Weisswange et al. (+1 more)

Robots designed to mediate human groups often fall into the solutionist trap: they are framed as sociable agents that fix problems such as conflict, disengagement, or lack of coordination. We suggest a different way of thinking. Rather than discrete agents, robots can be understood as situated elements of shared environments; catalysts and carriers of group experience whose meaning emerges through how people position, interpret, and interact with them. From this perspective, robots are not there to repair some ostensible dysfunctionality, but to enable group-level sense-making around care, norms, and identity. Our prior work on robotic street furniture suggests that this does not happen by imitating human sociality but by taking the shape of deliberately constrained, group-facing entities that happen and act for us without being socially entangled as one of us. We thus understand robots in public spaces not in terms of autonomy or intelligence, but as a relational capacity. This implies designing robots not in our image or for our utility, but grounded in our needs in being and becoming together.
Read the full abstract

All authors Victor Tuan Vu Pham, Judith Dörrenbächer, Thomas H. Weisswange, Marc Hassenzahl

Networking

Support-Aware Telemetry Compression for 5G Positioning via Conditional Conflict Graphs

Mohammad Reza Deylam Salehi and Hakima Chaouchi

Geographically separated transmission/reception points (TRPs) report quantized measurements to a Location Management Function (LMF), even when the application requires only a coarse location region. We formulate this task as a distributed zero-error function-computation problem, in which each TRP transmits an index sufficient for the LMF to reproduce the required service decision. Since positioning geometry induces a sparse and nonrectangular support, independently constructed per-terminal characteristic-graph colorings are not necessarily jointly decodable. We introduce a conditional conflict graph that exactly characterizes valid single-terminal updates and develop an alternating codebook construction that preserves global zero-error decodability. In a reproducible three-TRP study with range-equivalent timing measurements and $120$ native bins, all resulting codebooks satisfy an explicit decoder-conflict test. For service-cell sizes up to $100$ m, the achieved ideal rate is $5.38$–$5.44$ bits per epoch per TRP, compared with $6.91$ bits for raw reporting and $6.56$–$6.87$ bits for a globally valid interval-based baseline. A complementary measured six-base-station TDoA study shows that $83.77\%$ of the learned native support recurs on an independent trajectory. For these recurrent tuples, the codebooks preserve the service decision exactly and reduce the ideal rate by $22.8$–$35.6\%$ for $2$–$8$ m service grids. The feasible report-tuple set also provides a single-epoch geometric-consistency check under injected timing bias. Finally, we identify the NRPPa/OpenAirInterface integration points and safeguards required for experimental implementation.
Read the full abstract

Robotics

ARC: Autonomous Robotics Compliance A Three-Layer Governance Architecture for Deployed Autonomous Systems

Tord Eide and Einar Holt

Proposed governance framework for autonomous robotic systems, introducing a three-layer compliance architecture (ARC) instantiated through model safety validation, cognitive certification benchmarks, and operational authorization standards.

Computer Vision

DementiaCare-Bench: A Modality-Validated Video Benchmark

Afrouz Sheikholeslami, Yuankai Qi, Xuyun Zhang et al. (+4 more)

Dementia affects an estimated 57 million people worldwide, and for most families the hardest part of care is not memory loss but the behavioral and psychological symptoms of dementia (BPSD): agitation, wandering, resistance to care, sundowning. Understanding these symptoms requires more than recognizing the behavior itself; it also requires knowing what happened beforehand. The same behavior may call for a different response depending on its trigger. Video-language models (VLMs) could potentially support caregivers, yet no existing benchmark evaluates this capability. To fill this gap, we present DementiaCare-Bench: 56 professionally produced caregiver training videos segmented into 94 clips across nine BPSD categories, with 2023 questions generated by a multi-agent pipeline that grounds every clinical claim in a verbatim transcript span. Each question is then probed under four visual conditions and labelled by the least it requires, so its visual demand is measured rather than assumed. Measurement contradicts intent: we wrote 77.7% of the questions to require ordered frames, and 34.8% do. Across 12 current VLMs the pattern is uniform. The best reach 85% overall, but that average is carried by questions a language model can answer from clinical knowledge alone; accuracy falls by 17 points on average on questions that require the ordered clip, and a leading open model scores at chance on judging whether a caregiver's response was appropriate. A lightweight LoRA fine-tune, DemCare-VLM, moves video dependence from -3.3 to +4.5 points, so what the benchmark exposes can be repaired and not only measured.
Read the full abstract

All authors Afrouz Sheikholeslami, Yuankai Qi, Xuyun Zhang, Luping Zhou, Amin Beheshti, Quan Z. Sheng, Ming-Hsuan Yang

Robotics

Robust Underwater Grasping of Sloped Objects with a Waterproof Passive Adaptive Gripper

Jooyoung Hong, Daewon Hong and Joohyung Kim

Robust grasping of everyday objects remains challenging for parallel-jaw grippers, particularly when handling sloped or asymmetric items that induce torque-driven rolling and shear slip. These challenges become even more severe in domestic environments such as kitchens, where objects are often wet or submerged, drastically reducing friction between the gripper and the object. To address these issues, we present a waterproof passive adaptive gripper that combines local and global adaptability for high-performance grasping in the submerged environments. The proposed gripper features a fully waterproof design that integrates a passive rotational joint for global self-alignment on sloped surfaces and passive variable-stiffness pads for local surface adaptation. Experiments in both dry and underwater conditions on various cylindrical and conical objects demonstrate superior holding capability and grasp robustness compared to rigid-pad and fixed-joint baselines. The proposed design offers a practical and robust solution that successfully enables stable underwater manipulation of diverse everyday objects, effectively addressing a critical gap in current underwater robotic grasping for daily-life applications.
Read the full abstract