Machine Learning
DART: Distributional Adversarial Recurrent Training for Algorithm Learning
Hieu Tran Bao, Phung Thanh Dang, Pham Quang Nhat Minh et al. (+1 more)
Recurrent
reasoning models (RRMs) can solve structured problems, achieving easy-to-hard generalization through iterative computation in hidden space. These models are typically trained with instance-level supervision, which becomes increasingly problematic as task difficulty grows: valid solutions occupy a tiny region of the solution space, while invalid solutions proliferate rapidly. We propose Distributional
Adversarial Recurrent Training (DART), a training framework that replaces single-point supervision with a local target distribution around the ground-truth solution and aligns model outputs with this distribution through an
adversarial objective. DART provides a richer learning signal and encourages more stable iterative trajectories toward valid solutions. When evaluated on Maze, Chess, and masked Sudoku with multiple RRMs, including Deep Thinking Systems and Tiny Recursive Models, DART improves solution quality, stability, and robustness under the evaluated distribution shifts. Comparisons with label smoothing, Gaussian softened targets, and progressive training show that DART is not explained by target softening alone and is complementary to training schemes that stabilize long-horizon recurrence. These results identify DART as a promising approach for improving robustness across the evaluated recurrent
reasoning models.
Read the full abstract ▾
All authors Hieu Tran Bao, Phung Thanh Dang, Pham Quang Nhat Minh, Hoang Thanh Tung
Numerical Analysis
Quasi-uniform designs from random candidates: optimal candidate complexity and farthest-point sampling
Takashi Goda and Hengjun Xu
We study randomized constructions of quasi-uniform designs on a compact metric-measure space satisfying two-sided
polynomial ball-growth conditions. Given integers $N\le M$, we first draw $M$ independent candidate points and then retain the first $N$ points of a farthest-point traversal of the candidate set. We prove probabilistic non-asymptotic bounds on the mesh ratio and show that $M=\Theta(N\log N)$ is the sharp order of the candidate-pool size required for bounded mesh ratio: a sufficiently large multiple of $N\log(N/\delta)$ suffices with probability at least $1-\delta$, whereas, if $M=o(N\log N)$, the mesh ratio diverges in probability for every procedure that selects $N$ points from the same independent candidate pool. If $M/(N\log M)\to\infty$, the upper bound on the mesh ratio for the exact farthest-point sampling (FPS) tends to $2$. We also quantify the effect of approximate FPS and analyze direct and fast implementations in spaces of bounded doubling dimension. Finally, using a single infinite stream of candidate points and increasing candidate budgets, we construct an almost surely quasi-uniform nested sequence; under supercritical oversampling and exact FPS, or more generally when the approximation factors tend to $1$, its mesh-ratio limit superior equals $2$ for compact positive-volume subsets of Euclidean space.
Read the full abstract ▾
Robotics
A Brain-inspired Hierarchical Framework for Zero-Shot Robot Task Reasoning and Execution
Guangming Wang, Pengfei Ye, Qizhen Ying et al. (+7 more)
Robots that follow open-ended
language instructions need to connect semantic intent to visual scene understanding,
geometric feasibility, object states, and physical interaction conditions. End-to-end
Vision-
Language-Action policies have improved cross-task generalization, but they typically map visual and
language inputs directly to
robot actions, leaving limited explicit structure for long-horizon decomposition, physical verification, and recovery. We present \method, a zero-shot hierarchical framework functionally inspired by the division of roles in the human
brain, comprising visual perception and state inference,
language grounding and action-sequence generation from a shared atomic action library, cost-based plan selection, and real-
robot execution and verification. The framework grounds commands in explicit object states, composes reusable atomic actions into task-conditioned sequences, ranks alternative sequences by execution cost, and verifies intermediate physical outcomes from refreshed observations. In the evaluation, \method{} completes 10/10 clean board trials, 10/10 pick-and-place trials, and 4/5 pyramid stacking trials for both the flat and irregular initial-layout conditions; the corresponding mean task progress is $99.03\%$, $100.00\%$, and $96.67\%$ respectively. Across all evaluated conditions, \method{} achieves higher success rates than ReKep, Dream2Flow, and $\pi_{0.5}$
benchmarks, demonstrating the effectiveness of combining explicit object-state
reasoning, compositional atomic actions, cost-based plan selection, and closed-loop execution verification.
Read the full abstract ▾
All authors Guangming Wang, Pengfei Ye, Qizhen Ying, Yixiong Jing, Yuxiang Ma, Haonan Chen, Haibing Wu, Olaf Wysocki, Molong Duan, Brian Sheil
Software Engineering
Replications, Revisions, and Reanalyses: Managing Empirical Evidence in Software Engineering
Julian Frattini, Jannik Fischbach, Davide Fucci et al. (+4 more)
One aspired outcome of empirical research on quantitative data is a variance theory, i.e., a quantification of the effect of an independent on a dependent variables. The validity of variance theories stems from the synthesis of multiple pieces of evidence, which increases its validity beyond the findings of a single study. However, research synthesis in SE is rare and if done mostly limited to purely narrative syntheses. At best, researchers perform meta-analyses to synthesize variance theories from several quantitative results. But even meta-analyses only produce reliable results when synthesizing exact replications yet fail to generalize from variations. We aim to extend the frontier of research synthesis beyond the state-of-the-art to systematically manage empirical evidence and its
evolution. We apply method engineering to construct a framework for research synthesis from proven, individual method fragments. The framework allows researchers to put new evidence in a clear relation to an existing body of evidence and systematically expand knowledge about a studied phenomenon. We demonstrate the application of this framework to two fields of research by explicitly modeling the relationship between existing pieces of evidence. The framework puts three types of
evolution of evidence into relation: (1) replications investigate the same hypothesis in a new context to improve external validity, (2) revisions challenge an existing hypothesis to improve internal validity, and (3) reanalyses replace analysis methods to improve conclusion validity. Through a systematic
evolution of evidence and clear assessment criteria for each dimension of validity, the proposed framework can determine the frontier of a field of research. The framework provides a perspective to systematically evolve empirical evidence in SE, supporting more constructive and productive advances in our field.
Read the full abstract ▾
All authors Julian Frattini, Jannik Fischbach, Davide Fucci, Michael Unterkalmsteiner, Daniel Mendez, Robert Feldt, Richard Torkar
Hardware Architecture
CMD: An Integrated CGRA Framework with Cluster-Based Distributed Memory Design
Shangkun Li, Cheng Tan, Zeyu Li et al. (+6 more)
Coarse-Grained Reconfigurable Arrays (CGRAs) are a promising solution for achieving high energy efficiency and reconfigurability across various application domains, but their performance is often crippled by rigid
memory architectures that limit the number and location of tiles that can access data
memory. This creates a significant bottleneck for kernels with intensive
memory accesses. To address this, we propose CMD, an integrated CGRA framework featuring cluster-based distributed
memory design with a co-designed compilation toolchain. The compiler includes a novel
memory-aware mapper and a design space exploration (DSE) mechanism that identifies the optimal
memory architecture design for specific kernels. Experimental results show that our post-DSE CMD CGRAs achieve an average speedup of $1.39\times$ over a conventional CGRA while simultaneously reducing the total area to an average of $0.912\times$ of the conventional CGRA.
Read the full abstract ▾
All authors Shangkun Li, Cheng Tan, Zeyu Li, Jinming Ge, Jiawei Liang, Hao Yang, Linfeng Du, Jiang Xu, Wei Zhang
Computer Vision
Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache
Zhirong Shen, Rui Huang, Chang Zou et al. (+10 more)
Diffusion Transformers have become the dominant paradigm in generative AI, but their high computational costs severely hinder real-time applications. Prediction-based feature caching is widely used to accelerate
diffusion transformers; however, as the number of steps increases, the deviation between its predictions and the reference full-compute trajectory gradually grows. An intuitive idea is to use an online regression model to dynamically correct this deviation, but it faces the issue of label data being unavailable during the acceleration process. This paper presents a statistical observation that the residuals between the features of full computation steps using caching methods and reference full-compute trajectory locally exhibit a zero-mean Gaussian distribution. By treating the features of full computation steps as noisy observations of reference features, the data acquisition problem is resolved. Based on this observation, a plug-and-play GP-Refiner correction framework is proposed. This method utilizes Gaussian Process Regression for correction and, leveraging the properties of GPR, introduces an uncertainty-adaptive computation strategy that triggers necessary full-computation calibration by monitoring the posterior variance in real time. Experiments demonstrate significant improvements across different models when combined with various state-of-the-art methods. Integrating the proposed framework with TaylorSeer reduces the computational load by 19.3% while improving PSNR by 0.9 dB and reducing LPIPS from 0.46 to 0.29. Code is available in https://github.com/Aredstone/GP-Refiner.
Read the full abstract ▾
All authors Zhirong Shen, Rui Huang, Chang Zou, Shikang Zheng, Jiacheng Liu, Peiliang Cai, Zhengyi Shi, Yaosong Du, Liang Feng, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Linfeng Zhang
Numerical Analysis
Robust high-dimensional integration using medians of coarsely scrambled Sobol' sequences
Ziyang Ye, Chaokun Zhu and Zexin Pan
We study the numerical approximation of high-dimensional integrals using randomized quasi-Monte Carlo (RQMC) methods, with a focus on scrambled Sobol' sequences. While asymptotically faster than Monte Carlo, classical RQMC suffers from error bounds that grow exponentially in the dimension $s$, and its root mean squared error (RMSE) convergence rate is generally no better than $O(N^{-3/2})$. To overcome these limitations, we combine two recent developments: Suzuki's coarse scrambling and the median trick. Coarse scrambling randomizes Sobol' sequences according to their generating base
polynomials and significantly reduces the maximal gain coefficient. By appropriately choosing the base
polynomials, we show that the coefficient can be made uniformly bounded in $s$, yielding an $O(N^{-1/2})$ RMSE for $L^2$ integrands with a dimension-independent constant. The median trick then enables near-optimal convergence for function classes beyond $L^2$: for $L^p$ integrands with $p\in(1,2)$, the median of independent coarsely scrambled estimates achieves an error of $O(N^{-1+1/p})$ with high probability; for integrands in the Haar wavelet space $\mathcal H_{\mathrm{wav},\alpha,s,p,q}$ with $\alpha_p:=\alpha-(1/p-1/2)_+>0$, we prove a high-probability error bound of $O(N^{-\alpha_p-1/2+\varepsilon})$ for any $\varepsilon>0$; the bound improves to $O(N^{-r-\alpha_p-1/2+\varepsilon})$ when the integrand has dominating mixed derivatives of order $r\ge1$ that belong to $\mathcal H_{\mathrm{wav},\alpha,s,p,q}$. The latter two bounds are uniform in $s$ under suitable conditions on the ANOVA components of the integrands. Numerical experiments confirm the predicted convergence rates and demonstrate the robustness of the proposed approach.
Read the full abstract ▾
Software Engineering
VibeCheck: Assessing the Quality of LLM-Generated Unit Tests: A Multi-agent Empirical Study across Heterogeneous Repositories
Anika Tabassum, Mushahid Intesum, Md. Fahim Arefin et al. (+1 more)
LLM-based IDE
agents are increasingly used to generate repository-grounded unit tests, yet common evaluations often rely on execution success or coverage. These metrics can miss deeper quality issues such as weak assertions, missing edge cases, poor isolation, and limited maintainability. This paper presents VibeCheck, an empirical study of unit test generation across 15 student-developed Python and JavaScript/TypeScript repositories. We evaluate Kiro, Antigravity, and Cursor with Claude Sonnet 4.5 as the underlying
agent, under repository-only, zero-shot conditions using a five-dimensional rubric covering runnability, assertion strength, logic and edge-case coverage, isolation/determinism, and maintainability. We also apply leave-one-out cross-
agent peer evaluation to compare tools and identify failure patterns. Results show a clear execution-adequacy gap: generated tests are often runnable but frequently lack strong assertions and meaningful behavioral coverage. Weak assertions and missing edge cases occur more often than blocking failures, showing that runnable tests can still be shallow. VibeCheck provides a reliability-oriented framework for evaluating LLM-generated tests beyond pass/fail outcomes.
Read the full abstract ▾
All authors Anika Tabassum, Mushahid Intesum, Md. Fahim Arefin, Tarannum Shaila Zaman
Computation and Language
Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning
Pengyang Shao, Chuanpeng Lu, Wei Qin et al. (+5 more)
Large
Language Model (LLM) unlearning aims to suppress target knowledge while preserving general capabilities. In
multilingual settings, unlearning must additionally propagate within its intended linguistic scope. However, existing evaluations mainly measure cross-lingual transfer and cannot distinguish insufficient from excessive propagation. We introduce CLLPU (Cross-Lingual and
Language-Bound Protocol for LLM Unlearning), a
multilingual benchmark that formulates this problem through two settings: common-goal forgetting, where target knowledge should be suppressed across all
languages, and
language-conditioned forgetting, where suppression should remain confined to a designated
language. CLLPU combines goal-guided topic pairing, schema-aware relation matching, and dual-anchor
multilingual translation to construct 800 matched knowledge-unit pairs and 72,000 QA instances across ten
languages. Experiments with six representative methods on Llama-3.1-8B-Instruct reveal opposite failure modes: forgetting remains incomplete when universal suppression is required, yet spreads beyond the intended boundary when
language-conditioned confinement is required. We further find that general
multilingual utility can conceal damage to neighbor knowledge. These findings establish propagation control as a central challenge for
multilingual LLM unlearning. We publicly release CLLPU together with its construction pipeline.
Read the full abstract ▾
All authors Pengyang Shao, Chuanpeng Lu, Wei Qin, Yanzheng Jin, Xiaohao Liu, Xi Ai, Kenji Kawaguchi, Richang Hong
Computers and Society
Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance
Ilia Voroshilov
We introduce Chain of Intent, a governance framework for agentic AI at small regulated firms, and validate it against a failure it was built to address. Existing agentic governance research assumes enterprise infrastructure that small firms do not have. In a simulated Hong Kong asset manager with 415 synthetic contact records, an
agent performing a routine client-communications task was subjected to ordinary managerial pressure to increase its reach. With its authorised constraints written into its configuration, the
agent held: it identified every ambiguity in the firm's records, cited
privacy legislation it had never been shown, and refused six successive requests, breaching in two of fifteen runs. With the same task, data, pressure and model, but its purpose left unstated as resource-constrained firms routinely leave it, it breached in thirteen of fifteen runs, contacting up to 220 individuals of whom 94 per cent had no demonstrable marketing consent - conduct carrying a maximum of three years' imprisonment under Hong Kong law. Chain of Intent applies four controls requiring no security engineering: a machine-readable purpose, constrained tool access, a scope ledger, and a pre-action check. It eliminated unlawful contact in every run while preserving task completion, and ablation shows each control independently sufficient by a different mechanism. We further show that drift must be measured at two stages -
agents widened their candidate sets in every pressured run while acting on them in roughly one in seven - and that governance applied at the point of intent costs roughly half as much as governance applied at the point of action.
Read the full abstract ▾
Computer Vision
Efficient and Robust Camera-independent Multiview 3D Geometric Reconstruction from Noisy Monocular Depth Estimation and Multiple Point Matching
Marius Leordeanu
We present an efficient and robust method for 3D
geometric reconstruction that is based solely on the camera-independent linear relationships among a given set of points, which are stable over time and robustly estimated using multiple point matches. We essentially learn, from correspondences between points across several frames, a linear
geometric auto-regression
matrix $\mathbf{W}$, which establishes how a point in 3D can be expressed as a linear combination of all the others. This
matrix is constant and does not depend on the world coordinate system or the camera pose—it is an intrinsic property of the point set. We also show that the principal eigenvectors of $\mathbf{W}$, which all have
eigenvalue $1$, provide a homogeneous representation of the 3D point configuration. The first version of our method takes advantage of noisy
monocular depth maps in order to obtain, from multiple frames, a robust
geometric auto-regression
matrix $\mathbf{W}$ of linear relationships between the 3D points. Thus, we build on recent advances in deep learning, which now provide
monocular depth estimation models that are fast but very often noisy. Our approach handles noise through robust linear estimation over several frames. The second version of our method does not need
monocular depth estimation maps. It applies in cases of weak-perspective projection, when the linear combinations between the 3D points can be robustly estimated from their 2D projections in the image. Note that the camera projection
matrix is never used in our derivations. Consequently, our method does not recover camera pose, but only 3D structure. This is a key difference between our method and the related literature on 3D
geometric reconstruction.
Read the full abstract ▾
Machine Learning
Machine Learning for Pre-Culture ESBL Risk Stratification to Guide Empiric Antibiotic Selection: A 12-Hospital Study of Enterobacteriaceae Cultures
Aravind V. Kuruvikkattil, Lalitha Pranathi Pulavarthy, Rashmita Kudamala et al. (+1 more)
Empiric antibiotic therapy for suspected ESBL-producing Enterobacteriaceae must be selected 48-72 hours before culture results, forcing clinicians to choose between undertreating resistant infections and overusing carbapenems that drive further resistance. We developed a cost-sensitive XGBoost model predicting an ESBL phenotype (resistance to ceftriaxone, ceftazidime, cefepime or piperacillin-tazobactam) at culture ordering using 45 pre-culture EHR features across 132,955 cultures from 72,217 patients at 12 hospitals (14.41% with the ESBL phenotype). Cultures were partitioned at the patient level. At 90% sensitivity, the model achieved 95.8% NPV, reducing post-test ESBL probability to 4.2%, a threshold that may support safe carbapenem-sparing in non-ICU settings, while sparing 307 of every 1,000 cultures an unnecessary broad-spectrum course at the cost of 14 missed ESBL cases per 1,000. SHAP analysis identified prior ESBL colonization as the dominant predictor, ahead of prior organism burden and neighborhood deprivation; removing deprivation features caused minimal performance loss ($\Delta\text{AUROC} = -0.020$), enabling equitable bedside deployment. Discrimination was unchanged under a strict IDSA ESBL-E definition (AUROC 0.766), with specimen type added as a predictor (0.764) and without any class-imbalance correction (0.762), and ranged from 0.71 to 0.78 across organism strata.
Read the full abstract ▾
All authors Aravind V. Kuruvikkattil, Lalitha Pranathi Pulavarthy, Rashmita Kudamala, Saptarshi Purkayastha
Computer Vision
Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models
Xin Xie, Fan Zhang and Dong Gong
Aligning a text-to-image generation flow model with a reward makes it follow objectives that the training data alone does not provide.
Alignment fine-tuning delivers this by reinforcement learning (RL) or preference optimization, but it must be repeated for every checkpoint and returns a model fixed at the reward and strength it was trained with. Test-time
alignment instead steers a frozen model during sampling, allowing task-specific and sample-specific guidance. Existing methods obtain this only by drawing the per-step signal from the reward function itself, through its gradient, or through a separately trained value function. We propose changing the supervision source: let a pair of weak models, not a reward function, supply the supervision. A source aligned model, kept together with its base as a source
alignment pair, stores its training reward as an implicit, step-wise, KL-anchored signal expressed in the sampler's own coordinates. We explore whether this model-form supervision can cross scale, and show that it does: our method, AlignGraft, aligns a larger, frozen, never-tuned model by adding the pair's velocity difference during sampling. The transport is exact under a shared noising kernel and needs neither the reward nor its gradient at test time. The method has no schedules, only a single scalar that controls the
alignment strength and can extrapolate it beyond that of the source
alignment pair. Across image and
video flow models (Stable
Diffusion 3.5, FLUX, and Wan), the transfer lifts the frozen large model on preference, compositional, and text-rendering rewards, can exceed the source aligned model itself, and preserves the large model's fidelity at a small constant sampling overhead. Extensive experiments show that one
alignment run on a weak model produces supervision that the whole model family can reuse at test time.
Read the full abstract ▾
Machine Learning
On-the-go Forgetting without Explicit Unlearning via ERASE
Kushal Chakrabarti and Mayank Baranwal
Existing unlearning approaches typically rely on post hoc weight adaptation or
distillation, leading to duplicated
memory costs, degraded generalization, and limited scalability. In this work, we introduce ERASE, Erasure via Reconstructive
Adversarial Signal Editing, a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights. ERASE leverages structured, class-conditioned input perturbations to induce selective forgetting during inference, eliminating the need for retraining, fine-tuning, or model copies. We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses while preserving predictions across other subclasses within the same superclass. This analysis offers a principled foundation for inference-time forgetting under mild regularity assumptions. Across diverse architectures and
benchmark datasets, ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods. By reimagining data removal as forgetting without unlearning, our work establishes a scalable, regulation-aligned pathway for continual,
privacy-conscious learning.
Read the full abstract ▾
Robotics
Observation Design for Certified Control Authority: Projection–Estimability Separation and Active-Face Equivalence
Guangxi Wan, Hualong Du, Yuqi Liu et al. (+4 more)
A sound runtime admission gate executes only actions it can certify, and certifies only what its observations support. This paper asks how observations should be designed to maximize the set of actions that can be safely admitted, and shows the question is not a re-vocabulary of classical design problems. First, a projection–estimability separation: decomposing a constraint normal as $c=c_{\mathrm{Range}}+c_{\ker}$ relative to an information
matrix, two-point discrimination along $c$ becomes arbitrarily reliable as the budget grows whenever $c_{\mathrm{Range}}\neq 0$, while robust admission of an action with normal $c$ is impossible at every budget whenever $c_{\ker}\neq 0$; such mixed directions are generic at any deficient rank, and at full rank the decoupling is bounded by the Kantorovich ratio and diverges with the condition number. Discrimination-optimal designs, being corner solutions of a linear criterion, land in exactly this regime. Second, an active-face equivalence
theorem: the permissiveness-optimal design is $L$-optimal for a target
matrix generated endogenously by the action faces that become certification bottlenecks, weighted inversely by their remaining slack; single-face collapse recovers $c$-optimal and goal-oriented design exactly, and a Caratheodory argument yields a bottleneck certificate of at most $r(r+1)/2+1$ faces. Around these we assemble exact certifiability per convex contract mode, for which $\kappa\approx 3.29$ is derived rather than calibrated, the $\sqrt{r}$ price of contract-agnostic design, an information-to-slack transfer
theorem with a
curvature-budget corollary, and a two-part audit in which a design meeting every margin requirement still leaves an action face at a certification cost above ten times its testing cost, in every probe library tested.
Read the full abstract ▾
All authors Guangxi Wan, Hualong Du, Yuqi Liu, Qingwei Dong, Qingxin Li, Hongfei Bai, Peng Zeng
Hardware Architecture
GPU-Accelerated Gate-Level Time-Based Power Analysis via Event-Density-Aware Partitioning and Kernel Fusion
Weihao Wang, Yikang Ouyang, Hongyuan Liu et al. (+1 more)
Power analysis is crucial in modern chip design flow. Particularly, time-based power analysis can provide fine-grained power consumption information to facilitate the diagnosis of power issues and guide power optimization accordingly. However, it may take tens of hours to conduct time-based power analysis on modern large-scale
circuits, which greatly slows down the power optimization flow. In this paper, we present the first GPU-accelerated gate-level time-based power analysis framework. We propose a novel data structure to enable efficient state-dependent power
retrieval. To accommodate the imbalanced event distribution across gates, we propose an event-density-aware partitioning strategy that allocates GPU threads based on gate event density. Finally, we fuse the power computation into a single kernel invocation to reduce redundant work in separate kernels. Experimental results show that our proposed framework achieves high accuracy while delivering up to 37.63x end-to-end speedup compared to multi-threaded Synopsys PrimeTime PX.
Read the full abstract ▾
All authors Weihao Wang, Yikang Ouyang, Hongyuan Liu, Yuzhe Ma
Computer Vision
FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection
Francesco Tonini, Lorenzo Vaquero, Mohammad Mahdi Derakhshani et al. (+3 more)
Human-Object Interaction (HOI) detection aims to localize humans and objects in images and classify their interactions. Zero-shot HOI focuses on recognizing interactions that are not observed during training, requiring models to generalize beyond seen verb-object compositions. Recent approaches leverage
Vision-
Language Models (VLMs), benefiting from rich semantic representations. However, they often rely on global or detector-centric features that compress interaction cues and hinder fine-grained spatial
reasoning. To overcome this limitation, we propose FineHOI, a zero-shot HOI framework that explicitly models interactions from dense patch-level features. Our approach is motivated by the observation that human-object interactions are defined by localized spatial relationships, which are not preserved by global and detector-centric representations. To this end, we introduce an Adaptive Part-Level
Attention module that decomposes humans and objects into semantically coherent parts via unsupervised clustering, and re-weights them based on their interaction relevance. These representations are then integrated through a Region-Aware Interaction
Transformer that integrates part-aware and global features and produces the final HOI
embedding. Extensive experiments demonstrate that FineHOI consistently outperforms existing zero-shot HOI methods, achieving particularly strong gains on unseen interactions. Code is available at https://github.com/francescotonini/fine-hoi.
Read the full abstract ▾
All authors Francesco Tonini, Lorenzo Vaquero, Mohammad Mahdi Derakhshani, Cees Snoek, Elisa Ricci, Cigdem Beyan
Computer Vision
STP-BENCH: A Unified Systematic Benchmark for Virtual Spatial Transcriptomics from Histopathology Images
Youngmin Chung, Ji Hun Ha, Andrew H. Song et al. (+8 more)
Spatial transcriptomics (ST) provides unprecedented insights into tumor heterogeneity by capturing spatially resolved gene expression, yet its high experimental cost hinders large-scale adoption. Consequently, computational approaches that predict spatial gene expression directly from hematoxylin and eosin slides, termed virtual ST, have rapidly emerged. Despite this progress, assessing advances in the field remains difficult due to insufficient benchmarking: prior studies rely on small, heterogeneous
datasets, inconsistent training and inference pipelines, and limited evaluation of biological interpretability and model robustness. To address these gaps, we present STP-BENCH, a standardized
benchmark for virtual ST models. STP-BENCH comprises six cancer types spanning two ST platforms (Visium and Xenium), with each training
dataset containing more than 30,000 spots and at least 15 slides to ensure statistical reliability. We evaluate 21 predictive approaches, re-implemented with a unified pathology foundation model as the morphological encoder when architecturally applicable. Beyond conventional
benchmarks that report average predictive accuracy on highly variable genes, we systematically examine which genes and gene sets are recoverable from histomorphology. We further evaluate the downstream biological utility of predicted profiles through
cell-type deconvolution and spatial domain identification, and assess model reliability under domain shifts and data scaling. Notably, unified morphological encoding substantially re-orders model rankings established in prior studies, indicating that architectural innovations and image encoding have been conflated in previous evaluations. We publicly release STP-BENCH to support reproducibility and serve as a community
benchmark at https://github.com/NEXGEM/STP-Bench.
Read the full abstract ▾
All authors Youngmin Chung, Ji Hun Ha, Andrew H. Song, Cristina Almagro-Pérez, Chaeyoung Seo, Won Jun Suh, Jeong Won Beom, Kyoung Bin Oh, Eytan Ruppin, Faisal Mahmood, Joo Sang Lee
Machine Learning
LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models
Mingqi Yang, Zidong Guo, Jihui Yang et al. (+1 more)
Tabular foundation models have become powerful graph learners. Systems such as G2T-FM and GraphPFN encode each node as a feature row and make predictions through in-context learning (ICL), with labeled rows serving as the
prompt. Current protocols employ the complete training table as context, causing
attention to scale quadratically with the labeled pool and introducing preprocessing and
memory bottlenecks. We investigate context construction for node-level graph ICL: which labeled nodes and auxiliary unlabeled nodes should constitute the
prompt for specified queries. We formulate this allocation in terms of two resources: a labeled-context budget for predictive evidence and an unlabeled-
halo budget for adapter message passing without using label capacity. We present LoGIC, which retrieves labeled nodes via structural, feature-based, and coverage channels, shares each context across the queries in a graph-local cluster, incorporates an unlabeled
halo for adapter backbones, and chooses the channel and context budget without test labels. Across three backbone configurations drawn from two model families on GraphLand, budgeted contexts maintain locally runnable full-context performance, stay competitive with published large-
dataset results, and markedly lower peak
memory requirements compared with full-context and whole-graph inference. They further permit frozen graph ICL on million-node graphs without retraining. Our analysis identifies when
retrieval channels work best and connects their behavior with graph properties.
Read the full abstract ▾
All authors Mingqi Yang, Zidong Guo, Jihui Yang, Wenming Zuo
Distributed Computing · Cross-listed from math.OC
Race, Exchange, Improve: Finding high-quality MIP solutions quickly
Gioni Mexi and Daniel Rehfeldt
Mixed-integer programming (MIP) is a cornerstone in applied optimization, both in industry and academia. Recently, there has been increased
attention to finding strong primal solutions quickly. This is reflected, for example, in the development of the NVIDIA cuOpt solver and, most recently, in the new MIPFEAS
benchmark, which has a tight time limit of 600 seconds and evaluates solvers based on how quickly they find high-quality primal solutions. This article introduces a MIP portfolio parallelization scheme, focusing on efficiently exchanging information between its workers. We present two implementations of this scheme: one built directly into the open-source MIP solver SCIP, and an external one, which we call ReXi. ReXi is currently the fastest non-commercial solver in the MIPFEAS
benchmark, followed by the SCIP-integrated implementation. Moreover, we present new versions of both implementations that considerably outperform their predecessors on the MIPFEAS
benchmark.
Read the full abstract ▾
Computer Vision
ProtoRAG: Prototype-Based Retrieval Augmentation for Few-Shot Fine-Grained Remote Sensing Object Detection
Jian Wang, Yuxiang Hong, Chufeng Zhou et al. (+2 more)
Few-shot fine-grained object detection (FGOD) in remote sensing imagery is challenging because limited annotations must support both object localization and discrimination among visually similar subcategories. Although
multimodal large
language models (MLLMs) provide strong coarse object localization, they lack explicit visual evidence for reliable fine-grained recognition. To address this limitation, we propose ProtoRAG, a prototype-based
retrieval-augmented framework that decouples coarse localization from fine-grained recognition by equipping MLLMs with an external object-level visual
memory. To construct a reliable visual
memory from limited support samples, we introduce Discriminative Prototype Space Learning (DPSL), which encourages discriminative and prototype-stable representations through supervised contrastive learning and prototype-consistency regularization. We further develop an uncertainty-guided candidate-constrained
reasoning strategy that augments MLLMs with retrieved candidate-specific visual references and invokes
multimodal reasoning only for ambiguous instances. Extensive experiments show that ProtoRAG consistently surpasses representative baselines in nine few-shot settings, outperforming the strongest baselines by 14.80, 2.27, and 4.04 mAP$_{50}$ on MAR20, HRSC2016, and FAIR1M-2.0, respectively.
Read the full abstract ▾
All authors Jian Wang, Yuxiang Hong, Chufeng Zhou, Chao Pang, Xiaokang Zhang
Machine Learning
QGB-W$k$NN: Quantum Granular-Ball Learning for Robust Classification
Suzhen Yuan, Dehang Chen, Lifeng Shen et al. (+2 more)
Nearest-neighbor classification is widely used in machine learning, yet existing methods often suffer from low computational efficiency and limited robustness in noisy environments. To jointly address these challenges, this paper proposes an efficient and reliable weighted $K$-nearest neighbor classification framework based on
quantum granular balls, termed QGB-W$k$NN. The proposed framework improves computational efficiency by integrating
quantum-enhanced granular-ball representation with hierarchical nearest-neighbor search, while enhancing classification reliability through a purity-aware weighted decision mechanism. Specifically,
quantum-kernel granular balls are constructed to reduce
retrieval redundancy and strengthen nonlinear feature representation under limited
quantum resources. A granular-ball purity-guided HNSW optimization strategy is developed to exploit structural reliability for hierarchical graph construction during neighbor
retrieval, alleviating the local optimality issue caused by conventional random layering. Finally, a weighted voting mechanism jointly incorporating granular-ball similarity and purity is introduced to produce more reliable classification decisions in noisy environments. Extensive experiments on
benchmark datasets demonstrate that QGB-W$k$NN achieves competitive classification accuracy while exhibiting favorable Pareto trade-offs between classification performance and computational cost. Moreover, the proposed framework consistently improves robustness under various noisy conditions, suggesting that reliability-aware
quantum granular-ball learning provides a promising paradigm for efficient and robust nearest-neighbor classification.
Read the full abstract ▾
All authors Suzhen Yuan, Dehang Chen, Lifeng Shen, Shuyin Xia, Jeremiah D.Deng
Computation and Language
The Blindness of Document-Level Translation Evaluation
Ahrii Kim, Vilém Zouhar, Chanjun Park et al. (+1 more)
Document-level machine translation (MT) evaluation extends segment-level protocols by presenting full documents to annotators, on the assumption that such presentation elicits document-level judgments. We test this assumption with a counterfactual condition (MIX) in which each document combines segments drawn from different systems, preserving document-level presentation while breaking cross-segment consistency. Across 18,420 expert Englis-to-Korean annotations and 14 automatic metrics, scores, system rankings, and error annotations are statistically equivalent between coherent and incoherent documents. Perception does not explain this: shown matched passages, raters identify the coherent one as the work of a single translator in 87.3% of trials. Document presentation does change how annotators work, but that change does not reach the recorded output. What is blind is the protocol, not the annotator. The concern is not that scores fall short, but that the resources invested in document-level systems, metrics, and annotation may not be measuring what they are intended to measure.
Read the full abstract ▾
All authors Ahrii Kim, Vilém Zouhar, Chanjun Park, Seong-heum Kim
Artificial Intelligence
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Review
Siming Yuan, Xueyi Zhang, Wangze Ni et al. (+7 more)
Peer review is central to quality control in science. However, existing evaluations of AI-assisted peer review mainly focus on the overall quality of generated reviews or the accuracy of final decisions. They therefore provide limited evidence about whether model decisions are supported by sufficient and reliable review evidence. We introduce a process-centric diagnostic
benchmark for AI-assisted peer review. It uses (x,$z_s$,$z_c$,$z_r$,y) to represent the paper content, summary, critique, suggestion, and decision. We convert heterogeneous review records from PeerRead, NLPeer ARR-22, and OpenReview-ICLR into process-aligned data. Our
benchmark uses direct decision prediction from the paper content (Direct) as its baseline. It compares the decision value of Gold-process variables and Predicted-process variables, and conducts stage-level evaluation, chain-consistency evaluation, and interventional sensitivity analysis. Experiments across three
datasets and six models show that Gold-process variables generally have higher decision value. For the main analysis model, the Gold–Predicted gap remains stable across
datasets and random seeds. This gap is also reproduced in most model–
dataset combinations. Although model-generated intermediate review texts show relatively high local consistency across adjacent stages, the final decisions are not consistently supported by the preceding review evidence. Our
benchmark targets AI systems designed to assist rather than replace human reviewers. It provides a transparent and auditable diagnostic tool for evaluating the reliability of their review processes.
Read the full abstract ▾
All authors Siming Yuan, Xueyi Zhang, Wangze Ni, Tianfang Xiao, Shimin Di, Jia Zhu, Zhuoren Jiang, Rong Tan, Lei Chen, Kui Ren
Machine Learning
Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning
Ziming Wang, Changwu Huang, Ke Tang et al. (+2 more)
Interpretability and
fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have been introduced to improve interpretability. This paper focuses on neural network (NN)-based generalized additive models (GAMs), a class of self-interpretable models. While most existing research has prioritized improving the accuracy of NN-based GAMs, their interpretability remains largely underexplored. To address this gap, this paper introduces explicit quantitative metrics for evaluating the interpretability of NN-based GAMs, empirically examines their effectiveness, and explores strategies for improving interpretability within these models. In addition, the simultaneous and explicit optimization of both interpretability and
fairness, along with their trade-offs and the underlying reasons, remains underexplored. To address this, we propose a multi-objective neural basis model (MONBM) framework based on multi-objective evolutionary learning to consider accuracy, interpretability, and
fairness simultaneously. A partial retraining strategy is further developed to facilitate the practical application of evolutionary multi-objective optimization to deep model architectures. Based on MONBM, this paper reveals the complex relationships between these dimensions and the reasons behind these intricate relationships. This analysis demonstrates how multi-objective optimization can be combined with self-interpretable models to reveal relationships among trustworthiness objectives. In addition, MONBM obtains a set of models with different trade-offs between dimensions, and the competitiveness of the approach is validated by comparing it with state-of-the-art methods.
Read the full abstract ▾
All authors Ziming Wang, Changwu Huang, Ke Tang, Yew-Soon Ong, Xin Yao
Databases
sheval: An RDF data shapes evaluation tool and test-suite for recursive shapes
Shqiponja Ahmetaj, Iovka Boneva, Jan Hidders et al. (+8 more)
Two different
languages have been developed to validate RDF data based on the concept of a shape: ShEx and SHACL. In each
language it is possible to define a shape that refers to itself, which is called a recursive shape. While in the case of ShEx, the semantics of recursive shapes is well defined and is part of the specification, in the case of SHACL, the semantics of recursive shapes is left to the implementation of the different SHACL engines. Consequently, the different SHACL engines show different behaviours when confronted with recursive shapes. In this paper we present sheval: an evaluation framework consisting of a tool and a test suite that can be used to compare the behaviour of different shapes technologies when confronted with recursive definitions. The tool has been used to evaluate and understand the differences in the implementation of recursive shapes in ShEx and SHACL. It provides a framework for testing and comparing the behaviour of different shape engines, helping to identify inconsistencies and potential issues, and providing a basis for further research and development in the field of shape-based validation of RDF data.
Read the full abstract ▾
All authors Shqiponja Ahmetaj, Iovka Boneva, Jan Hidders, Maxime Jakubowski, Jose-Emilio Labra-Gayo, Wim Martens, Filip Murlak, Cem Okulmus, Ognjen Savković, Mantas Šimkus, Dominik Tomaszuk
Robotics
Moment-Matching Probabilistic Data Association for Optimization-Based SLAM
Khoa Nguyen, Mitchell Turton and Florian Meyer
Optimization-based simultaneous localization and mapping (SLAM) makes it possible to reduce accumulated
navigation errors of sensing platforms by returning to known areas (loop closure). In this paper, we present an approach to combine probabilistic data association (PDA) with optimization-based SLAM. Instead of associating a single measurement with each landmark, we follow the PDA paradigm from the multiobject tracking community. In particular, in a processing stage performed in addition to the nonlinear least-squares solver of optimization-based SLAM, our method (i) assigns multiple measurements to landmarks probabilistically, (ii) computes the mean and covariance of landmark distributions via moment matching by taking multiple measurement-to-landmark associations into account, and (iii) establishes a virtual landmark measurement and a corresponding linear-Gaussian measurement model that leads to the mean and covariance
matrix as moment-matching PDA in (ii). By converting the PDA update step into an equivalent linear-Gaussian measurement update step, PDA can be performed effectively within any optimization-based SLAM method. Our preliminary numerical evaluation in a scenario with false negatives and false positives indicates that incremental smoothing and mapping 2 (iSAM2), combined with the proposed PDA approach, can improve
agent localization performance compared to conventional iSAM2.
Read the full abstract ▾
Numerical Analysis
A structure-preserving implicit-explicit method for a hyperbolic approximation of fourth-order PDEs
Rahul Barthwal and Rahuldev Ghorai
We introduce a novel structure-preserving numerical method for a first-order
hyperbolic approximation system, which approximates the solutions of general fourth-order partial differential equations. By employing an implicit-explicit (IMEX) splitting between the stiff and non-stiff terms, we rigorously prove that the proposed scheme is energy-consistent and positivity-preserving under a CFL-type condition. Furthermore, we show that the method remains robustly stable in asymptotic regimes, with a time-step restriction that is entirely independent of the relaxation parameters. Finally, we present a series of numerical examples for thin film equations to validate the theoretical properties and efficacy of the scheme.
Read the full abstract ▾
Computation and Language
SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation
Tong Bao, Mir Tafseer Nayeem, Yi Zhao et al. (+2 more)
Automatic scientific survey generation has become an important task in scientific document processing. The common approach of retrieving literature from a single source (e.g., arXiv) and generating surveys through a one-pass large
language model (LLM) call often leads to limited reference coverage and, more importantly, fails to replicate the expert-driven revision process that is crucial for writing high-quality surveys. In this paper, we introduce SurveyAgent-HKA, a multi-
agent framework that improves end-to-end scientific survey generation by incorporating knowledge derived from published surveys and peer-review comments. The framework decomposes survey generation into well-defined sub-tasks handled by LLM-powered
agent. It first retrieves relevant papers from multiple sources and identifies key topics through clustering to construct an initial outline, which is then refined using outlines from related human-written surveys. Based on the refined outline, topic-focused papers are retrieved and re-ranked to select for drafting a well-grounded survey. Then, we identify common issues raised by experts in peer-review comments from published surveys to guide the revisions and finalize the survey. Experiments on two domains show that our approach outperforms mainstream baselines in citation quality, structural consistency, and content quality. Furthermore, our framework is efficient in both time and cost, making it a practical solution for broader AI-assisted scientific writing applications.
Read the full abstract ▾
All authors Tong Bao, Mir Tafseer Nayeem, Yi Zhao, Davood Rafiei, Chengzhi Zhang
Computer Vision
Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics
Hexiang Bai, Hanyang Xu, Xiaoxue Li et al. (+4 more)
Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffers from spatial collapse, where models rely heavily on background shortcuts rather than localising critical foreground lesions. To overcome this limitation and align visual evidence with precise medical semantics, we systematically investigate alternative pre-training paradigms.Specifically, we evaluate three independent forms of structured supervision: topological priors via graph self-supervision, dense pixel-level constraints via
segmentation, and cross-modal semantic grounding via image-text pairs. Notably, our empirical analysis reveals that while all three forms of structured supervision successfully alleviate the global pooling bottleneck and steer visual
attention towards foreground regions, image-text
alignment achieves the most superior performance. By
embedding high-dimensional diagnostic logic, the cross-modal approach not only anchors
attention on precise visual evidence but also enables profound abstract
reasoning. Extensive experiments demonstrate that this semantically enriched pre-training fundamentally enhances the model's feature representation. Consequently, when fine-tuned for downstream clinical classification tasks, our models achieve superior accuracy and yield highly interpretable
attention maps focused on true pathological features, vastly outperforming vanilla classification baselines.
Read the full abstract ▾
All authors Hexiang Bai, Hanyang Xu, Xiaoxue Li, Xiaoliang Wu, Shangde Gao, Hongxia Xu, Ke Liu