Robotics
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Friday 14 August
This paper presents THRIVE (Therapeutic Humanoid Robot In Virtual Environment), an at-home rehabilitation platform that integrates a suite of virtual-reality upper-body rehabilitation games, a real-time camera-based motion-tracking system, and a socially interactive robot therapist. The system is designed for therapy and intervention in children with upper-limb motor impairments, which can be improved through consistent, task-specific practice. THRIVE features a set of newly designed, engaging games that target functional reaching, grasping, and object-manipulation movements through customizable popping, hitting, catching, and grabbing tasks, while the camera-based tracking system captures the child's kinematic performance during play. A robot therapist - deployable either as a physical robotic coach or as a remote-presence virtual agent - delivers adaptive, dynamic feedback to motivate the child and guide their movements toward therapeutic goals. THRIVE decouples the therapeutic games from the robot embodiment, extending the platform to support various embodiments and different robots within one modular system. This robot-agnostic design makes THRIVE affordable, scalable, and readily adaptable for sustained use in the home, offering a practical pathway to more consistent and engaging upper-limb therapy for children with motor function impairments.
Game Theory
Individual Rationality in Constrained Hedonic Games: Friends, Enemies, and Neutrals
We study constrained coalition formation in games induced by friends, enemies, and neutrals, under the two standard refinements of additively separable preferences: friend-oriented and enemy-oriented. We ask for partitions that are individually rational (IR), while additionally requiring exactly $k$ non-empty coalitions, each satisfying a prescribed lower and upper bound on its size. Although IR alone is trivial to satisfy for any hedonic game, the size constraints make it computationally intractable to decide whether a feasible partition exists. The two models tell strikingly different stories. Under enemy-oriented preferences, the problem collapses to size-constrained graph coloring, and its complexity follows accordingly. Under friend-oriented preferences, however, the picture is far more intricate, and is governed by the enmity structure rather than the friendships. The complexity is further shaped by two factors: how strict the imposed size requirements are, and whether relationships are symmetric or asymmetric, with several cases turning out tractable in the symmetric setting but intractable once asymmetry is allowed. Charting this boundary in terms of both classical and parameterized complexity, we provide a complete understanding of which properties of the friend/enemy structure are responsible for hardness.
Read the full abstract
Computation and Language
Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation
The majority of work on summarization evaluation focuses on general summary quality (e.g., ROUGE, BERTScore) or specific desired properties (e.g., readability, factuality). However, these metrics fail to measure the utility of a summary to an individual user. For example, a biomedical researcher learning about the latest vaccine research will have different informational needs from a family doctor. Query-focused summarization captures part of this need, but in practice, users rarely state everything relevant in a query: a single short query is likely inadequate to distinguish the needs of a researcher from those of a physician. By contrast, a reader's background or persona (their role and expertise) is comparatively stable across queries and recovers much of this missing context, which makes it a practical signal for assessing whether a summary satisfies that reader's needs. In this work, we assess how sensitive popular summarization metrics are to both informational and persona differences, and find that many popular metrics, including strong LLM-as-judge metrics, fail basic perturbation tests of informational content. We additionally conduct an expert human evaluation, measuring summary preferences based on information satisfaction given a specific person's background and use case. We find that both traditional and LLM-based metrics are insufficient measures of information satisfaction and agree poorly with human judgment.
Read the full abstract
Artificial Intelligence
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the target domain are limited and the statistical properties of the source and target domains differ. In these settings, models trained only on local data may not capture complex temporal dynamics, while direct transfer learning can result in negative transfer. This study develops a shift-aware dual-encoder transfer framework that combines source-domain knowledge with target-specific representation learning. The source encoder was pretrained using hourly observations from 10 U.S. monitoring locations. The framework was then adapted and evaluated using two years of hourly observations from 77 stations in Taiwan under a chronological train-validation-test protocol. Among the four principal baselines, the frozen-source dual-encoder model achieved the best performance, with MSE = 21.8960, MAE = 3.1597, and R^2 = 0.8725. This corresponds to an MSE reduction of approximately 7.1% relative to TL-v1 and 4.1% relative to TL-v2. The ablation analysis showed that removing the Taiwan-specific branch caused the largest decline in performance. Allowing the source encoder to adapt produced the best overall result, with MSE = 21.6575, MAE = 3.1383, and R^2 = 0.8739. SHAP analysis indicated that predictions were driven mainly by recent PM2.5 observations and meteorological variables related to pollutant transport and dispersion. These results suggest that source-domain knowledge is most effective when target-specific information is preserved and the transferred representation is allowed to adapt under target supervision.
Read the full abstract
Artificial Intelligence
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatial layouts. Existing methods typically flatten these multidimensional structures into sequential strings, losing important intra-sheet boundaries and inter-sheet semantics. Consequently, LLMs cannot exploit the global spatial context that human experts naturally use when inspecting spreadsheets. We propose SheetCompass, a graph-guided and memory-driven agentic framework for spreadsheet reasoning and automation. SheetCompass explicitly models structural relationships within and across worksheets while maintaining task-relevant information in memory, enabling agents to reason more effectively over complex workbooks.
Read the full abstract
Information Theory · Cross-listed from math.ST
Converse bounds for multiple graph alignment and correlation detection based on last matching
The paper focuses on information theoretic converse bounds for the alignment of $m$ correlated graphs and for the detection of correlation among $m$ graphs. A simple idea for $m\geq 3$ is that if the alignment of $m-1$ of the graphs is revealed as extra information (by a genie for example) then it is still necessary to produce the alignment between the one remaining graph and the others, i.e. the last matching must be accomplished. For both Gaussian and Erdos-Renyi models, the last-matching problem is equivalent to one with two observed graphs, providing a path to extend converse bounds for $m=2$ to larger $m$. While the method is rather obvious for alignment, we show that the method can also be used to derive converse bounds for weak detection of correlation.
Read the full abstract
Robotics
Control-Informed Constraint Adaptation in Minimum-Time Trajectory Planning for Autonomous Racing
Autonomous racecars operate at the limits of vehicle dynamics, where small control errors translate into safety-critical behavior and lost performance. Trajectory planners assume perfect tracking and remain blind to execution errors. To guarantee safety, trajectory planners therefore restrict themselves to conservative spatial margins, leaving usable track space untapped. To overcome these issues, we introduce a control-informed online trajectory planning framework that learns from its own execution errors. By measuring systematic tracking deviations during runtime, we dynamically adapt spatial track constraints and iteratively expand the free-space planning area. The planner remains time-optimal while compensating for accumulated execution errors. This method was analyzed in a high-fidelity closed-loop simulation environment with autonomous racecars. The results demonstrate that our approach reduces lap time by 1.8\,s without increasing computational burden, maintaining a median runtime of 25 ms. Our finding indicates that feeding control-induced deviations back into the planning layer unlocks performance previously inaccessible to modular architectures and enables autonomous vehicles to exploit track limits systematically.
Read the full abstract
Artificial Intelligence
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly used to synthesize content, they often lack in information grounding. To address these peculiarities of our time, we propose Wyvern, a multi-agent framework for the automated generation of grounded, multimodal technical reports. Wyvern allows for the generation of multimodal outputs, integrating images, tables, and text with supporting references in a unified report. Additionally, a particular focus is placed on the grounding of the content, with the implementation of a claims auto-revision stage. We conduct a human evaluation study to assess the quality of our proposed framework. The results show that the figures' informativeness is perceived as superior to that of a recent baseline in 87% of cases. Furthermore, Wyvern's reports are rated as more useful than those produced by three alternative methods in 63% to 100% of instances. We also carry out automatic evaluations showing that Wyvern gains up to 2.3$\times$ in citation recall and 1.6$\times$ in citation precision with respect to the baselines.
Read the full abstract
Machine Learning
Designing Compact Neural Architectures via Neuron Gating and Mixed Activation
Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with strong predictive performance. We propose three scalable formulations that replace discrete neuron- and activation-level decisions with continuous relaxations, enabling differentiable optimization over otherwise combinatorial architecture spaces. These formulations give rise to three NAS methods: NAS based on Neuron Gating (NAS-NG), NAS based on Mixed Activation (NAS-MA), and NAS based on Neuron Gating and Mixed Activation (NAS-NGMA). Experiments on MLPs and CNNs using MNIST and CIFAR-10 show that the proposed methods consistently identify compact architectures with competitive or improved predictive performance. On MNIST, NAS-NGMA achieves 98.68% test accuracy with 7.69M MLP parameters, while NAS-NG achieves 99.63% accuracy with only 0.26M CNN parameters. On CIFAR-10, the proposed methods consistently outperform vanilla DARTS. Further experiments demonstrate that NAS-NG can optimize substantially over-parameterized and literature-optimal architectures, improving accuracy while reducing parameters. These results establish relaxed bilevel optimization as a scalable alternative to discrete NAS and provide a general framework for efficient neuron- and activation-level architecture optimization.
Read the full abstract
Artificial Intelligence
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery after those conditions change. To address this gap, we introduce PACE-Bench (Physics Adaptation via Code Evolution), a simulator-grounded benchmark of 144 source-to-target adaptation pairs across six physics domains. Each pair links a source environment to a mutated target environment with the same goal and interface. A code-driven design that succeeds in the source fails in the target, where agents must iteratively adapt it into a working target design using diagnostic sandbox feedback within a limited attempt budget. We compare ten self-evolving methods from four paradigms. The benchmark remains far from saturated: Reflexion + Qwen3-14B succeeds on only 35.9% of full-benchmark pairs, while GPT-5.5 solves 66.7% of the Statics subset under the full budget. Together, these results show that simulator-grounded reflection is more reliable than unverified self-revision, while memory anchors agents to early designs and broad tree search explores without converging. Even revealing exact physical changes does not raise the performance ceiling, pointing to mechanism redesign rather than parameter inference as the central bottleneck. Data and code are available at https://github.com/thunlp/PACE-Bench.
Read the full abstract
Systems and Control
Reduced Arc-Weight Heterogeneity for Master Stability Analysis of Directed Networks
Master stability analysis can be applied to directed networks even when their Laplacian matrices are not diagonalizable. Nevertheless, a diagonalizable Laplacian is easier to analyse because the perturbations governing synchronization separate into independent modes. This paper asks how many different positive coupling strengths are needed to obtain this simplification without adding or removing any directed connections. We first give an elementary construction showing that suitable positive weights exist for every weakly connected directed network and explain its relationship to stronger genericity results in the literature. We then introduce a measure of the smallest number of distinct coupling strengths required for diagonalizability. If a common coupling strength already produces a diagonalizable Laplacian, only one value is needed. For directed acyclic networks, we give a constructive upper bound based on the length of the longest directed path from a source. This bound is exact for rooted outward directed trees. Consequently, an outward star requires only one coupling value, whereas a directed path requires a different value on every arc. These results reduce coupling heterogeneity while retaining the simpler modal form of master stability analysis. Diagonalizability is treated as an analytical convenience, not as a sufficient condition for synchronization.
Read the full abstract
Computer Vision
Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings
Frozen image embeddings from models such as CLIP are increasingly used to classify paintings by art-historical style, with high reported accuracy. We ask whether this accuracy reflects an understanding of style or the recognition of individual artists. Standard evaluation uses random splits in which works by the same artist appear on both sides, so a classifier can succeed by recognising the painter rather than the movement. We re-evaluate style classification under an artist-disjoint protocol, holding out every artist in turn so that no work is ever classified using other works by its own painter. On a balanced dataset of 320 paintings across four twentieth-century movements, 5-NN style accuracy falls from 0.87 to 0.77 under this protocol, and the drop is sharply uneven. Impressionism and Cubism barely move, while Surrealism falls twenty points. The pattern holds across four image encoders, including a vision-only self-supervised model, which places the effect in visual structure rather than language. Where an encoder captures genuine shared form, individual artists are barely recognisable yet style is robust, while Surrealism shows the opposite. We argue that artist-disjoint evaluation is necessary to measure stylistic understanding in frozen embeddings.
Read the full abstract
Machine Learning
Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising versions of the rollout samples. This paper shows that these seemingly different losses arise from a single path-space principle. Starting from the regularized diffusion-RL objective, we use importance sampling between sampling SDEs to obtain an explicit policy-gradient estimator on trajectory space. The estimator contains the stochastic Itô integral underlying Flow-GRPO-type updates; we derive an equivalent variance-reduced value-gradient form that recovers the forward-matching structure of AWM and DiffusionNFT. This identifies the empirical gap between these method families as a variance-reduction effect rather than a difference in RL principle. The derivation yields a unified design space organized by value-gradient estimation, weight functions, and sampling choices. Within this space, we propose a multi-sample KDE value-gradient estimator that reuses rollout groups, together with scale-bounded weight families that retain stable existing recipes while excluding singular ones. Experiments on SD3.5-M and Qwen-Image models validate the variance-reduction explanation and show that the resulting recipe improves over prior diffusion-RL baselines.
Read the full abstract
Information Retrieval
PriCoRec: A Privacy-Aware Cloud-Device Collaborative Framework for Ad Recommendation under Feature Constraints
Privacy regulations increasingly restrict cloud processing of sensitive user data (e.g., age, gender), hindering traditional cloud-only recommendation models. To mitigate this challenge, we propose a Privacy-aware Collaborative cloud-device ads Recommendation framework (PriCoRec) which personalizes recommendations while keeping sensitive features on-device. While separating recommendation into cloud-based and on-device stages enables privacy-aware deployment, naive splitting suffers from degraded shortlist quality and inefficient on-device inference due to limited private features. We therefore design a collaborative framework that comprises a cloud-based pre-ranking stage using cloud-accessible features, and an on-device ranking stage that locally incorporates highly personalized features. We introduce a diversity regularizer to pre-ranking to improve candidate quality. Moreover, to control device power consumption and computational cost, we incorporate a cloud-guided training mechanism that enhances device model performance while keeping the model lightweight. Experiments demonstrate that the proposed framework maintains strong recommendation performance while keeping sensitive features on-device.
Read the full abstract
Computer Vision
GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure
3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers well to per-point tasks such as semantic and panoptic segmentation, but transfer to 3D detection remains weaker. We analyze recent SSL methods and find that most objectives are defined only on measured LiDAR returns from visible surfaces, leaving occluded and unobserved regions unconstrained. This visible-surface bias can be sufficient for point-wise prediction, but 3D detection requires robustness to missing structure. To address this gap, we propose GhostPoint, an SSL framework that hallucinates latent features in local neighborhoods around discovered instances, generated via a novel instance voxel dilation. In GhostPoint, an encoder processes observed returns, and an additional predictor infers neighborhood representations from observed context. In addition to standard encoder-level supervision, we introduce a predictor-level supervision scheme on sampled voxels from generated neighborhoods. Specifically, observed (visible/masked) voxels match teacher-encoder targets, while unobserved voxels match teacher-predictor hallucinations. This design encourages the learned representation to explicitly model structure beyond observed returns. Extensive evaluations on nuScenes and Waymo demonstrate that our method achieves state-of-the-art performance, consistently improving downstream 3D detection, especially under sparse scans and limited labels.
Read the full abstract
Distributed Computing
Large-scale workflow placement in serverless computing using integer nonlinear programming
Serverless edge computing has become a powerful cloud framework that enables the execution of large workflows without the need for the user to manage the underlying servers and edge devices. In this work, we address the challenge of deploying these workflows on a large number of different existing servers and edge devices such that monetary costs for the users and workflow evaluation times are minimized. To this end, the workflow and cloud node attributes are modeled in a mathematical framework. As a result, we present a novel model of the optimal placement problem as a nonlinear integer program. To solve both the issues of scaling towards a larger number of cloud/edge nodes as well as decomposed knowledge of node attributes, we propose a novel decomposition strategy. In a case study, we show the beneficial scaling properties of the decomposition approach and a mean improvement of 10% against a simple deployment heuristic.
Read the full abstract
Artificial Intelligence
The Dynamics of Intelligence Explosions
AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loop might be able to produce an intelligence explosion, with rapidly escalating AI capabilities. I explore the mathematics of the most explosive possibilities, with an eye to understanding what drives the dynamics. I show that singular growth (towards a vertical asymptote) is harder to achieve than would be expected from recent economics-inspired modelling, and that there is an important but neglected class of growth rates that are faster than exponential but don't lead to a vertical asymptote. I draw out the generation time (the time to go around the feedback loop) as a neglected parameter that plays a pivotal role in determining the behaviour of any intelligence explosion — one cannot have singular growth unless the generation time rapidly approaches zero.
Read the full abstract
Artificial Intelligence
Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after estimates are precise. We introduce optstop, a precision-based adaptive stopping framework that treats evaluation as a sequential measurement problem: keep sampling where uncertainty remains high, and stop where estimates are precise or stable enough. The framework builds on hierarchical Bayesian inference, supports binary, ordinal, and continuous outcomes, and keeps every benchmark item eligible for sampling, without requiring a calibrated item bank. It runs live or retrospectively, and includes a safeguard that samples more cautiously as measured performance approaches zero, where rare successes matter most. In an illustrative 200-item, 10-epoch evaluation, it removes 57%-97% of planned trials across nine validation settings, with overall conclusions equivalent to the full run. These results show that LLM evaluation compute can be allocated by uncertainty rather than by fixed repetition counts, with the magnitude of savings depending on evaluation design.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
UMPIRE-Net: Unrolled Magnitude-Phase Regularization Network for Accelerated MRI
MRI reconstruction from undersampled k-space measurements is an ill-posed inverse problem. Physics-driven deep learning (PD-DL) methods have shown strong performance for this task by combining the MRI forward model with learned image regularization within algorithm-unrolling frameworks. However, most existing PD-DL methods reconstruct complex-valued images directly, thereby implicitly coupling magnitude and phase within a single learned representation. This coupled regularization may be suboptimal in reconstruction settings where accurate phase modeling plays an important role, such as partial Fourier (PF) imaging, where recovery of the omitted asymmetric k-space measurements depends on the underlying image phase. In such scenarios, explicit modeling of magnitude and phase as separate components may reduce the reliance on externally estimated or predefined phase information. To this end, we propose UMPIRE-Net (Unrolled Magnitude-Phase In REgularization Network), a PD-DL method that introduces separate learned regularizers for magnitude and phase components, together with a novel data-fidelity formulation that enforces measurements consistency. We evaluate UMPIRE-Net for accelerated MRI with PF across different datasets and acceleration factors. Experimental results demonstrate that our proposed method improves reconstruction quality compared with a conventional complex-valued PD-DL baseline, yielding sharper images and reduced artifacts. Code available at: https://github.com/MahdiSaberii/UMPIRE-Net
Read the full abstract
Computers and Society
Estimating the growth in emissions from AI data centres
The advent of agentic AI is driving an unprecedented growth in data centre expansion. Using state-of-the-art life cycle assessment models for operational and embodied emissions from AI servers, we estimate the ensuing growth in overall CO2 emissions of AI data centres. The main contribution of this work is a rigorous quantification of emissions arising from projected AI data centre expansion using scenarios by the IEA and McKinsey. We show that the scenarios promoted by the AI industry would result in a dramatic rise in overall emissions and that the embodied carbon component is considerable.
Read the full abstract
Machine Learning
More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It
Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time. It also has the potential to serve as a general-purpose front end for a broad range of downstream sampling methods. However, we uncover a striking paradox: Power Sampling can drive more probability mass toward correct trajectories while degrading the downstream inference it is intended to enhance. Using self-consistency as a representative case, we observe accuracy drops of up to 18.5 percentage points across models and reasoning benchmarks. We trace this paradox to two mismatches. Dose mismatch arises because a fixed exponent induces drastically different amounts of distributional change across problems. Coverage mismatch arises because global sharpening concentrates mass on a narrow set of dominant paths: high pass@k, often interpreted as evidence of preserved diversity, can therefore coexist with the loss of broad reasoning-path support required for downstream aggregation, search, and selection. Guided by this diagnosis, we replace uniform trajectory exponentiation with a deformation-controlled, support-preserving Power target that calibrates sharpening across problems while limiting the suppression of moderate-probability paths. In a same-budget instantiation with weighted self-consistency, the repaired sampler reverses the losses caused by global Power and outperforms standard multi-sample inference across reasoning benchmarks.
Read the full abstract
Cryptography and Security
STINER: Automated Extraction of Strategic Cyber Threat Intelligence from X
Strategic Cyber Threat Intelligence (CTI) focuses on high-level insights, such as identifying targeted industries, attributing attacks to specific ransomware groups, and assessing the scale of data loss. Today, X (formerly Twitter) has become the fastest source for this intelligence, often hosting real-time breach announcements days before formal vendor reports. Converting this raw chatter into actionable intelligence requires navigating a complex linguistic landscape. Conventional Named Entity Recognition (NER) models struggle to parse the informal and highly irregular dialect of social media, creating a blind spot for automated defense systems. To address this challenge, we introduce STINER, a taxonomy and expert-annotated corpus for extracting strategic intelligence from social media streams. We construct a high-quality, expert-annotated dataset of 2,100 real-world alerts and propose a granular taxonomy of eight entity types centered on strategic pivots such as Threat Actor, Sector, and Location. We benchmark nine models across 12 evaluated configurations, spanning general-purpose and domain-adapted encoders, open-schema extraction, and generative LLMs in both zero-shot and fine-tuned settings. Domain-adapted encoders such as DarkBERT reach a strict F1-score of 89.33%, outperforming both general-purpose baselines and fine-tuned Large Language Models, which additionally incur substantially higher inference latency. Leveraging STINER-DarkBERT, we conduct a European threat landscape analysis for H1 2025. Our results align with official reporting on major targets while highlighting the distinct visibility profile of attacks in Spain, and illustrate how social-media-driven extraction can surface early signals of the SafePay ransomware campaign prior to its retrospective characterization in vendor threat landscape reports.
Read the full abstract
Machine Learning
CytoBERT: A Foundation Model for Cytometry Data
Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.
Read the full abstract
Graphics
Uncertainty-Aware Jacobi Set Computation
We present an uncertainty-aware Jacobi set computation method. In general, Jacobi sets are topological descriptors that capture the gradient alignments of two scalar fields, as, e.g., used for multi-field visualization. We adopt and reformulate an existing computational approach that relies on an edge-based identification of Jacobi set edges on a given triangulation. Our extension to uncertainty visualization builds upon a versatile, spatially coherent uncertainty model for pairs of scalar fields based on multivariate normal distributions. We propagate the uncertainty analytically, thereby lifting the original Jacobi set computation to uncertain inputs. Furthermore, we present an overlay of visual mappings specifically designed to show the Jacobi sets along with different facets of uncertainty information. Both the uncertainty model and uncertainty-aware method are validated against a Monte Carlo approach on an analytic dataset and applied to two use cases from fluid dynamics and weather ensembles.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Online Inference in Distributional Temporal-Difference Learning
We study online statistical inference for functionals of the return distribution under a fixed policy. The return distribution is estimated by nonparametric distributional temporal-difference learning from a single Markov trajectory. For the Polyak–Ruppert averaged estimator, we prove that its root-$T$ error converges weakly to a centered Gaussian random element in Cramér space. We also prove that, conditionally on the observed trajectory, the root-$T$ difference between the bootstrap and original averages converges weakly to the same Gaussian limit. These results justify bootstrap inference for smooth statistical functionals, including variance, CVaR, expected shortfall, and expectiles. For nonsmooth statistical functionals, we develop a local asymptotic theory for the estimated return CDF over $T^{-1/2}$-neighborhoods of finitely many thresholds, together with its bootstrap analogue. This theory allows us to conduct inference for nonsmooth statistical functionals characterized by CDF equations, including return quantiles.
Read the full abstract
Artificial Intelligence
The Past and Future of AI Scientists
We present a survey of the past and future of AI Scientists: machines capable of automating science. AI Scientists can originate hypotheses, deduce their consequences, design and execute experiments, interpret their results, and revise their beliefs. Such systems are integrated scientific agents, connected to the literature, formal knowledge, mathematical models, simulations, data-analysis systems and physical laboratories. Adam was the first machine to make novel scientific discoveries through cycles of hypothesis formation and physical experimentation. Eve established the architecture of the modern self-driving laboratory. Foundation models, autonomous agents and laboratory robotics now make it possible to build systems far more general than either Adam or Eve. The central problem is no longer whether individual components of science can be automated. They can. The problem is integration. AI Scientists must combine neural learning with logic, probability, mathematics, causal reasoning, simulation, experimental design, robotics and formal scientific records. AI Scientists have the potential to transform science: to make science faster, cheaper, more systematic and more reproducible. AI Scientists could investigate systems too complicated for unaided human science, and enable thousands of AI scientists to work together on single problems. The Nobel Turing Challenge sets the goal of developing by 2050 AI systems capable of automating Nobel-quality discoveries. Progress is ahead of schedule. When we succeed it will create a new form of science and transform the world.
Read the full abstract
Robotics
Effect of Twisted-Yarn Architecture on Pressure and Proximity Sensing Characteristics of Textile Capacitive Sensors for Robotic Skin
Textile-integrated capacitive sensors offer flexible and conformable tactile sensing for wearable electronics and human-robot interaction; however, the influence of yarn-level architecture on capacitive transduction characteristics remains insufficiently quantified. This work presents a textile capacitive sensing platform based on silver-coated yarns coated with polydimethylsiloxane and assembled into one-, two-, and four-layer twisted configurations. The influence of effective electrode overlap area and inter-fiber separation on the capacitive response is systematically investigated, enabling architecture-dependent tuning of pressure and proximity sensing characteristics. Pressure was calculated using the localized single-fiber contact area, corresponding to stresses of 0.4-3.9 MPa. Increasing the layer number improved mechanical strength and sensing performance: elongation at break increased from 37.5% to 62.5% and 85.0%, while the maximum load increased from 23.3 to 42.7 and 89.7 N. Sensitivity increased with layer number and frequency, reaching 0.1331 MPa$^{-1}$ for the four-layer sensor at 100 kHz. The four-layer configuration also exhibited low hysteresis, minimal thermal drift from 25 to 90 $^\circ$C, and stable operation over 15,000 cycles. Proximity detection ranges of 60, 50, and 40 mm were obtained for the one-, two-, and four-layer sensors, respectively, revealing an architecture-dependent sensitivity-range trade-off. A 4$\times$4 textile sensing array enabled spatial contact mapping, while robotic-arm integration demonstrated real-time touch and proximity detection with an end-to-end robotic system latency (from detection to robot reaction) of 403 ms. The results establish yarn architecture as a tunable design parameter governing the measurement characteristics of textile-integrated capacitive sensing systems.
Read the full abstract
Human-Computer Interaction
From Style Replication to Style Exploration: Enabling Art Style Exploration with Analyze-Experiment-Resituate Framework
Art style is a signature of professional digital artists that develops through repeated experimentation, reflection, and adaptation. While generative AI (GenAI) can reproduce styles with high fidelity, current tools provide limited support for exploring new stylistic directions and may encourage style replication over exploration. To address this gap, we propose Analyze-Experiment-Resituate (AER), a framework for AI-assisted style exploration derived from interviews with 10 professional digital artists. Rather than prioritizing visually appealing outputs alone, AER supports three core practices of style exploration, including interpreting references, trying out stylistic possibilities, and reflecting on how emerging styles may be received. Specifically, AER enabled artists to (1) analyze artworks into interpretable stylistic elements, (2) have controllable experimentation guided by their own choices, and (3) resituate emerging styles through simulated social perspectives. We implemented AER in a prototype system and evaluated it in a controlled study with 16 artists. Compared with a direct style-transfer workflow, AER increased artists' agency and reflection as they pursued new stylistic directions. A two-week field study with four artists revealed how the AER framework influenced daily style exploration, such as reflection, experimentation, and stylistic decision-making at each stage. We discuss opportunities and challenges in designing AI-assisted style-exploration workflows, and outline implications for future artistic support tools.
Read the full abstract
Computer Vision
CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
Subject-driven image personalization—generating new images that preserve the identity of one or several reference subjects in novel scenes—is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired (reference, composed-target) examples, where each composed target is a synthesized image of the subject in a novel scene. Producing such targets demands a costly multi-stage curation pipeline—LLM-based prompt generation, T2I-based composed-target synthesis, reference-subject extraction, VLM-based quality filtering, and correspondence labeling—and tightly couples each method to a particular target synthesizer and curation choice. We introduce CRAFT (Constrained Reward via Attention Fine-Tuning), a single-step ReFL framework that fine-tunes a pre-trained reference-aware MMDiT via LoRA adapters using a compact reference-only data construction—$10$K reference images and subject masks, with no composed-target supervision. CRAFT realizes a Where to look principle: attention-level rewards align noise- and phrase-token attention with the correct reference subject, and the resulting per-subject attention masks gate a pixel-level identity reward to keep image-space supervision consistent with the learned attention routing. Applied to FLUX.2-klein-9B, CRAFT achieves state-of-the-art performance on XVerseBench \rev{while using no composed-target supervision—only $10$K reference-only samples, whereas prior generalized methods require $150$K to over $2$M composed-target pairs}. The same recipe transfers to other reference-aware backbones, consistently improving performance. Project page: https://jihun999.github.io/projects/CRAFT/.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Offline Deep Q* Estimation with Diffusion Models
In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental challenge is that the reward function and transition kernel are unknown, so the optimal Bellman operator is not directly observable from data. To address this issue, we propose a novel framework that decouples operator estimation from value function learning. In this approach, we first formulate conditional diffusion models to estimate the reward law and transition kernel, which induces a data-driven approximation of the optimal Bellman operator. We then plug these estimators into the Bellman equation and obtain a deep estimator of $Q^*$ by minimizing the empirical Bellman residual over a neural network function class. Theoretically, we first establish sharp nonasymptotic convergence rates for learning the optimal Bellman operator. We establish the smoothness of $Q^*$ through the Bellman equation using the the Hölder assumptions on the conditional reward and transition densities. With suitable sample sizes, we obtain the oracle value-stage rate $\widetilde{\mathcal O}\bigl(n^{-\frac{2\alpha}{d_x+d_a+2\alpha}}\bigr)$ for the excess Bellman residual risk. We then translate this risk bound into an expected $L^2$ estimation error of order $\widetilde{\mathcal O}\bigl(n^{-\frac{\alpha}{d_x+d_a+2\alpha}}\bigr)$ under a concentrability condition. For the total offline budget $\widetilde n=n+n_r+n_x$, we obtain a value estimation rate of $\widetilde{\mathcal O}\bigl(\widetilde n^{-\frac{\alpha}{2d_x+d_a+2\alpha}}\bigr)$ and establish an information-theoretic lower bound of order $\widetilde n^{-\frac{\alpha}{d_x+d_a+2\alpha}}$. Importantly, our theoretical analysis does not rely on Bellman completeness assumptions commonly used in deep RL theory.