Distributed Computing · Cross-listed from astro-ph.IM
GPUPHOT: A Python Framework for High-Performance GPU-Accelerated Photometry and Distributed Astronomical Data Reduction
Samuel Lemes-Perera, Miguel R. Alarcon, Miquel Serra-Ricart et al. (+1 more)
We present GPUPHOT, an open-source Python framework for GPU-accelerated real-time photometry and astrometry of astronomical CCD and scientific CMOS images. Four of its seven stages run entirely on the GPU through CuPy (background estimation, source detection, PSF modeling and aperture photometry); the catalog crossmatch selects a CPU or GPU backend by problem size, and the zero-point and astrometric calibrations run on the CPU, within a containerized distributed system. Checkpoint-based GPU
memory monitoring and an opt-in spatial-binning fallback let a single container image run on GPUs from a 4 GB laptop card to 80 GB datacenter accelerators. We
benchmark the framework on nineteen observations from two robotic facilities, the Two-meter Twin
Telescope and the Transient Survey
Telescope, spanning 4.2 to 151.2 megapixels and 228 to 134,206 cataloged sources, on eight NVIDIA GPU platforms with one process per image. The H100 completes the densest 151.2-megapixel field end-to-end in 31.9 s, and GPU source detection on the A100 is 6-15x faster than the CPU library sep on the same frames. Once three sources of non-determinism are pinned, catalogs and zero points agree to the fourth decimal across GPU models and host CPUs. In this one-process-per-image regime the CuPy 14 / cuML stack showed a 7% lower peak
memory and a median 38% higher per-image latency than CuPy 12, both due to the RAPIDS allocator displacing the CuPy
memory pool at import; restoring the pool removes the
memory difference and cuts the median overhead on datacenter GPUs to 11%, with identical output. Long-lived workers, the production mode, run the two stacks near parity. We recommend the CuPy 14 stack for its reproducibility and maintained libraries, not for
memory or speed. GPUPHOT and its
benchmark scripts are released for autonomous facilities that require end-to-end photometric reduction at survey cadence.
Read the full abstract ▾
All authors Samuel Lemes-Perera, Miguel R. Alarcon, Miquel Serra-Ricart, Pino Caballero-Gil
Numerical Analysis
Active Subspace-Guided Free-Form Deformation with Sinkhorn Autoencoders for Reduced-Order Modelling of Parametrised Shape Problems
G. Padula, C. Giovannini, G. Rozza et al. (+1 more)
Geometrically parametrised PDEs arise in shape optimisation, where solving a PDE over many deformed domains at manageable cost is a central challenge. Free-form Deformation (FFD) parametrises shape variations through a
lattice of control points, but the resulting parameter space is typically high-dimensional, with most directions barely affecting the quantity of interest (QoI). We address this with a two-stage reduction pipeline. An Active Subspace (AS)-guided structured control-point selection identifies the low-dimensional subspace of FFD weights driving the QoI. A Sinkhorn Autoencoder (SAE) is then trained on the reduced weights, learning their distribution in a compact latent space by minimising the Wasserstein distance between aggregated posterior and prior. We compare three non-intrusive Reduced-order Models (ROMs), mapping full FFD weights, AS-reduced weights, or SAE latent codes to the QoI, each using Random Forests, Gaussian Processes, and K-Nearest Neighbours. We test the methodology on a non-linear heat equation with Gaussian random Robin boundary data on a deformed Stanford Bunny, and on drag prediction for the DTC Hull bulb under FFD deformations. In both cases, the generative model captures the bulk of the QoI distribution over a comparable support, thinning the shoulder opposite the design objective, while its extremes in the design-relevant direction match the FFD sample within numerical and sampling uncertainty. ROMs learned in the SAE latent space yield smaller test errors than those on full FFD weights in most regressor-metric combinations, whereas AS-reduced weights give no comparable gain. Only the latent representation attains a positive predictive coefficient $Q^2$.
Read the full abstract ▾
All authors G. Padula, C. Giovannini, G. Rozza, A. Dashtimanesh
Machine Learning
STRIDE: State-Transition Representation via Increment Dynamics and Evolution
Yuchen Xiong, Siming Huang and Jianfeng Sun
We introduce STRIDE (State-Transition Representation via Increment Dynamics and
Evolution), which defines states through derivative fingerprints and learns local functions for state transitions (qpairs), recasting continuous
forecasting as transition prediction. Trailing convolution windows estimate local joint-transition frequencies, whose lagged differences form a high-dimensional increment trajectory. Proper orthogonal decomposition (POD) gives coordinate paths, jointly forecast by sparse dynamics with
memory. Recombining their forecasts and applying history-anchored inversion recovers future transition distributions; sampled state paths select local functions to generate continuous forecasts. Three-seed experiments compare STRIDE against fourteen baselines across nine
benchmark families. Five independent Markov and hidden-state baselines cover all 230 evaluated tasks, with 220 complete whole-horizon pairs. Against these comparators, system-weighted late-Energy win fractions range from 73.6% to 78.5% on 190 multi-step pairs; against DLinear, the fraction is 77.3% on 72 paired multi-step tasks. Matched controls examine the intermediate representation. On 64 independently initialized Aizawa trajectories, late-Energy reductions against four matched controls range from approximately 24% to 56%, with all four prespecified contrasts passing Holm correction. These results connect transition-statistic prediction to continuous probabilistic
forecasting, with substantial long-horizon gains in the matched Aizawa study.
Read the full abstract ▾
Machine Learning
Graph Memory: Spectral Associative Memory via Dirichlet Energy
Zhaoyang Shi
Dense associative
memories have traditionally focused on storing and retrieving vector-valued patterns. Many modern machine learning problems, however, are naturally graph-structured, requiring
memory mechanisms for relational patterns, graph
diffusion geometries, community structures, and graph-based inductive biases. We propose a spectral dense associative
memory for storage and
retrieval of graph data, extending the classical vector-valued
memories.
Retrieval is performed through a log-sum-exp energy induced by Dirichlet energy with spectral norm distances, producing a softmax-weighted average of the stored
Laplacians that remains a valid graph
Laplacian. We prove exponential storage capacity and exponentially decaying
retrieval error. Beyond graph
retrieval, we establish theoretical guarantees for spectral quantities central to graph learning, including
eigenvalues, eigenspaces, and
diffusion operators. Experiments on synthetic graph data, real-world airline network,
protein conformation data and wearable sensor data demonstrate robust graph
retrieval while preserving the graph geometry of the data. Our framework provides a new associative
memory paradigm for graph-structured data and bridges dense associative
memory with modern graph learning and generative AI.
Read the full abstract ▾
Machine Learning
DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
Weiwei Ye, Dongyuan Li, Hangchen Liu et al. (+3 more)
Probabilistic time series
forecasting requires modeling and predicting complex and time-varying distributions. Recently, Denoising
Diffusion Probabilistic Model (DDPM)-based approaches have shown promise by equipping the dif- fusion process with pretrained mean and variance
estimators to accommodate distributional shift. However, these methods typically follow the standard DDPM framework and consider only partial components of the evidence lower bound (ELBO), treating the training of
estimators as designed regression tasks separate from the variational inference framework. To address this, we rethink the ELBO under the Location-Scale Noise Model (LSNM) and find that it naturally induces a Gaussian negative log likelihood objective for the
estimators and inherently defines a joint training objective that unifies recent
diffusion paradigms for probabilistic
forecasting. Building on this principled ELBO reformulation, we propose Diff- PTS, a general framework that enables end-to-end optimization of all components within the ELBO. Across multiple
benchmarks, DiffPTS consistently outperforms recent models, achieving state-of-the-art performance with an average CRPS/MSE reduction of over 14.53%/16.55% compared to existing
diffusion-based methods. The code is available at https://github.com/wwy155/DiffPTS.
Read the full abstract ▾
All authors Weiwei Ye, Dongyuan Li, Hangchen Liu, Haotong Jiang, Yoshihide Sekimoto, Renhe Jiang
Computer Vision
StegGNN: Learning Graphical Representation for Image Steganography
Abhinav Kumar, Shorya Singhal, Agam Pandey et al. (+2 more)
Image steganography refers to
embedding secret messages within cover images while maintaining imperceptibility. Recent advances in deep learning - primarily driven by Convolutional Neural Networks (CNNs) and architectures such as inverse neural networks, autoencoders, and generative
adversarial networks - have led to notable progress. However, these frameworks are primarily built on CNN architectures, which treat images as regular grids and are limited by their receptive field size and a bias toward spatial locality. In parallel, Graph Neural Networks (GNNs) have recently demonstrated strong adaptability in several computer
vision tasks, achieving state-of-the-art performance with architectures such as
Vision GNN (ViG). This work moves in that direction and introduces StegGNN - a novel autoencoder-based, cover-agnostic image steganography framework based on GNNs. By modeling images as graph structures, our approach leverages the representational flexibility of GNNs over the grid-based
rigidity of conventional CNNs. We conduct extensive experiments on standard
benchmark datasets to evaluate visual quality and imperceptibility. Our results show that our GNN-based method performs comparably to existing CNN
benchmarks. These findings suggest that GNNs provide a promising alternative representation for steganographic
embedding and open the field of deep learning-based steganography to further exploration of GNN-based architectures.
Read the full abstract ▾
All authors Abhinav Kumar, Shorya Singhal, Agam Pandey, Tushar Kumar, Sukrit Jindal
Machine Learning
Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Derui Wang, Zewei Shi, Rayne Holland et al. (+4 more)
Debate
distillation adapts weaker verifiers using multi-
agent debate transcripts to improve their judgement in subsequent debates, but gains on monitored tasks do not establish reliability on related unmonitored tasks. We study epistemic reliability degradation, in which adaptation preserves monitored performance while reducing support for correct responses on hidden tasks. We consider an
adversarial debater that manipulates debate arguments while defending the correct monitored response, and ask whether the resulting degradation merely reflects catastrophic forgetting and whether standard evaluation can detect it. To address these questions, we propose ER-Audit, a two-stage black-box
auditing framework that compares frozen verifier checkpoints before and after adaptation, and introduce two evaluation
benchmarks pairing monitored and hidden task
prompts grounded in shared contexts. ER-Audit searches for counterexamples to non-degradation by evaluating semantically valid paraphrases and, if none is found, uses independent paraphrases for sequential hypothesis testing. We derive anytime-valid lower confidence bounds on the non-degradation probability, allowing data-dependent stopping within a finite budget. We further establish a common lower bound across fixed paraphrase distributions and extend it to distributions within a bounded total variation distance of their mixtures. Our experiments show that higher hidden-task accuracy can coexist with more counterexamples to non-degradation and lower non-degradation bounds. This divergence challenges explanations based solely on broad catastrophic forgetting and shows that
auditing can uncover selective hidden-task degradation concealed by aggregate performance gains. Our code and
benchmarks are available at https://github.com/CSIRO-CQS-AI-
alignment-Team/Epistemic-Reliability-Auditor.
Read the full abstract ▾
All authors Derui Wang, Zewei Shi, Rayne Holland, Ruoxi Sun, Xingliang Yuan, Jason Xue, Liming Zhu
Machine Learning
Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation
Takayuki Mizuno, Shouji Fujimoto, Mikito Hiruki et al. (+1 more)
Geospatial simulation of infrastructure interventions requires mobility generators that respond directly to edited maps, yet many data-driven generators do not expose the map as an editable condition. We formulate this task as map-conditioned autoregressive generation of human mobility: a road raster conditions a decoder that emits nominal 31.25 m mesh-
cell tokens at one-minute intervals. The mesh-local vocabulary supports held-out and locally edited maps without retraining or vocabulary changes. We instantiate a ResNet-50 visual-prefix configuration and a
Vision Transformer (ViT) cross-
attention configuration, trained from scratch on 87,400 smartphone-derived trajectories from 874 meshes in Ishikawa Prefecture, Japan; 219 meshes are held out. We evaluate map sensitivity by comparing correct-map and within-split shuffled-map generations with held-out real trajectories. On the 110-mesh test split, for the ResNet-50 configuration, correct-map generations are closer than shuffled-map generations on 60% of meshes under Hausdorff-based energy distance (p = 0.021), while DTW is directional but inconclusive (57%, p = 0.074); correlation with real density is 0.38 with the correct map versus 0.01 with shuffled maps. The ViT configuration shows weaker trajectory-level sensitivity and smaller density gains. An illustrative bridge-removal edit changes generated continuations without retraining. Together, these results support the feasibility of editable-map human-mobility simulation.
Read the full abstract ▾
All authors Takayuki Mizuno, Shouji Fujimoto, Mikito Hiruki, Atushi Ishikawa
Numerical Analysis
Application of Machine Learning to the Computation of Parameters in the SUPG Method for Unstructured and Anisotropic Meshes
Petr Knobloch and Manoj Prakash
Solution of convection-dominated problems using stabilized methods often requires to specify stabilization parameters whose optimal choice is not known but which considerably influence the quality of the approximate solution. In a recent work of the authors, an approach for computing these parameters by machine learning was proposed and applied to the streamline upwind/Petrov-Galerkin (SUPG) method for convection-
diffusion equations. In the present paper, this approach is studied numerically for unstructured meshes and extended to meshes obtained by anisotropic mesh adaptation.
Read the full abstract ▾
Data Structures and Algorithms
Stability Dichotomies for Boolean Constraint Satisfaction Problems
Chunyang Wang and Yuichi Yoshida
We study the stability of Boolean constraint satisfaction problems (CSPs) through the notion of average sensitivity (Varma and Yoshida, SODA 2021; SICOMP 2023). It measures the expected $1$-Wasserstein distance between an
algorithm's output distributions before and after the deletion of a uniformly chosen constraint, using the unnormalized Hamming metric. We establish two dichotomies for every finite Boolean constraint
language $\Gamma$, where $n\geq 2$ denotes the number of variables in an instance. For stable solvability, exactly one of the following holds: $\bullet$ either there is an
algorithm that solves $\mathrm{CSP}(\Gamma)$ and has average sensitivity $O_{\Gamma}(1)$ for all satisfiable instances; $\bullet$ or every
algorithm that solves $\mathrm{CSP}(\Gamma)$ has average sensitivity $\Omega_{\Gamma}(n)$ on satisfiable instances of arbitrarily large $n$. The first alternative holds if and only if $\Gamma$ has finite duality: unsatisfiability can be witnessed on a bounded number of variables. For stable approximability, where a $(1-\varepsilon)$-approximation violates at most an $\varepsilon$-fraction of the constraints in expectation, exactly one of the following holds: $\bullet$ either for every $\varepsilon\in(0,1]$, there is an
algorithm that $(1-\varepsilon)$-approximates $\mathrm{CSP}(\Gamma)$ with average sensitivity $O_{\Gamma}(\varepsilon^{-1}\log n)$ for all satisfiable instances; $\bullet$ or there exists $\varepsilon_{\Gamma}\in(0,1]$ such that every
algorithm that $(1-\varepsilon_{\Gamma})$-approximates $\mathrm{CSP}(\Gamma)$ has average sensitivity $\Omega_{\Gamma}(n)$ on satisfiable instances of arbitrarily large $n$. The first alternative holds if and only if $\Gamma$ has bounded width: local consistency checks on bounded sets of variables detect unsatisfiability.
Read the full abstract ▾
Computation and Language
Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models
Jonathan Drechsel and Steffen Herbold
Model-internal features can be studied through both their ability to identify a specified concept and their causal effect when manipulated, e.g., through steering or weight editing. A prominent approach to feature learning is Sparse Autoencoders (SAEs), which learn broad feature dictionaries whose relation to particular concepts is typically identified post hoc. However, many interpretability questions are instead hypothesis-driven and concern a concept specified in advance. We study this setting as targeted feature learning, where a single feature is constructed for such a predefined concept. We present a controlled comparison across three model signals (activation values, activation gradients, and parameter gradients) and two
estimators (contrastive mean and a learned one-dimensional encoder-decoder), yielding six targeted methods, with CAA and GRADIEND as existing instances and four new methods covering the remaining combinations. We compare these methods against pretrained SAEs across 15 tasks and three
language models, evaluating both detection and causal intervention. Across models, the strongest detection performance is achieved by contrastive activation value methods, whereas the strongest intervention performance is achieved by gradient-based methods. Overall, our results show that targeted feature quality depends jointly on the model signal and
estimator, with detection and intervention capturing complementary properties.
Read the full abstract ▾
Robotics
Proactive Motion Planning for Human-Robot Cooperation
Elena Basei, Edoardo Lamon, Matteo Saveriano et al. (+2 more)
This abstract addresses the incorporation of human motion prediction into proactive and dynamic human-aware motion planning, with the goal of enabling safe collaboration between humans and
robots. A deep learning, graph-based model is used to forecast human motion and is integrated into a planning framework. This framework employs a static roadmap along with a time-variant A*
algorithm to modify the trajectory of a UR5e manipulator. This method greatly improves human-
robot interaction and enables proactive collision avoidance by combining precise motion forecasts with adaptive trajectory planning.
Read the full abstract ▾
All authors Elena Basei, Edoardo Lamon, Matteo Saveriano, Daniele Fontanelli, Luigi Palopoli
Computer Vision
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Junxian Li, Ruixuan Yang, Tianao Zhang et al. (+3 more)
Visual
token reduction is an effective way to accelerate
multimodal large
language models (MLLMs), but performance deteriorates rapidly under extremely low
token budgets. Existing work has explored both visual-
token selection and training-based adaptation to reduced visual inputs. We take a step further by asking how a heavily compressed MLLM should learn from the states induced by its own generations. This setting naturally calls for on-policy self-
distillation: a heavily compressed model is supervised on the states induced by its own generations, while its full-
token counterpart serves as an information-rich teacher. Based on this insight, we propose LT-OPD, a training framework for extreme visual-
token reduction. The student rolls out responses with only a small fraction of visual
tokens, and a frozen full-
token copy of the same MLLM provides distributional supervision along these student-generated trajectories. To stabilize on-policy learning when visual evidence is severely limited, we further introduce a budget-level curriculum that progressively decreases the
token budget during training. Across nine
benchmarks on Qwen3.5-4B, LT-OPD raises average retained performance under 5% visual-
token retention from 68.6% to 82.3%, outperforming training-free, training-based, and reinforcement-learning baselines at the same budget. The gains transfer consistently to Qwen3.5-9B, GLM-4.6V-9B, and LLaVA-OV-1.5-4B. LT-OPD also reduces KV-cache usage by 85.2% and prefill FLOPs by 85.4% without additional inference overhead, demonstrating that on-policy learning can substantially recover capabilities lost to extreme visual-
token reduction.
Read the full abstract ▾
All authors Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu, Weisheng Dong, Yulun Zhang
Computer Vision
EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding
Gujie Shao, Zixun Xie, Xuechun Xing et al. (+7 more)
Vision-
language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging remain insufficiently characterized. Existing ophthalmic
datasets are typically designed for individual diseases or specialized tasks, making it difficult to systematically evaluate whether VLMs can move beyond disease recognition toward comparative
reasoning and fine-grained spatial grounding. We introduce EyeVQA, a unified visual question answering
benchmark for comprehensive evaluation of ophthalmic VLMs. EyeVQA is constructed from 21 available ophthalmic
datasets and contains 20,000 question-answer pairs spanning six disease groups and seven question types: Single-Choice, Multi-Select, Variable-Select, True-False, Ranking, Point Location, and Bounding Box. Gold answers are deterministically derived from source-provided diagnoses, severity grades, clinical findings,
segmentation masks, bounding boxes, and anatomical landmarks, enabling reproducible evaluation without relying on model-generated annotations. Notably, 44.5% of the questions require
reasoning across multiple images, extending evaluation beyond conventional single-image medical VQA. We
benchmark fourteen representative general-purpose, scientific, and medically specialized VLMs under a unified zero-shot protocol. The best-performing model only achieves an overall score of 62.8, while substantial gaps remain in spatial grounding and cross-task generalization. These results highlight the limitations of current VLMs in comprehensive ophthalmic visual understanding and establish EyeVQA as a diagnostic
benchmark for developing more reliable and spatially grounded ophthalmic
multimodal models. The project page is available at https://github.com/PKUTHM/EyeVQA.
Read the full abstract ▾
All authors Gujie Shao, Zixun Xie, Xuechun Xing, Ruixiang Wang, Ziyun Lan, Yanlin Qi, Gangyi Zhang, Yuxin Yang, Dawei Li, Haiming Tang
Artificial Intelligence
From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs
Yangzhe Peng, Xiaoyang Wang, Yiyang Zhao et al. (+2 more)
Comparative Process Reward Models (PRMs) provide critical step-level guidance for autonomous web
agents by evaluating state-conditioned preferences between candidate actions. However, existing preference training data synthesized via multi-policy sampling suffers from a severe scarcity of Grounded Minimal Contrastive Pairs (GMCPs)-where competing candidates target genuine on-page elements with identical action types. In representative baselines preference data (namely, WebArbiter), GMCPs account for merely 24.19%, biasing PRMs during training to rely on shallow shortcuts (such as element
hallucinations and action type mismatches) rather than acquiring genuine contextual decision semantics. To address these challenges, we propose SURFPRM, a graph-guided process preference synthesis framework for comparative Web PRMs. SURFPRM structures web demonstrations into a persistent Interaction Element Graph that acts as an environment-grounded negative action proposal mechanism, systematically synthesizing contrastive negative actions across spatial, temporal, and spatiotemporal confusion axes. This elevates the GMCP proportion from 24.19% to 74.60%, producing the curated SURFPRM-DATA
dataset. Across six open-source backbones (3B to 9B parameters), PRMs trained on SURFPRM-DATA outperform baseline-trained models on average on WEBPRMBENCH and rival leading proprietary LLMs. In downstream reward-guided trajectory search on WEBARENA-LITE, SURFPRM provides step-level guidance for both GPT-4o (+14.21%) and GPT-4o-mini (+12.83%) policies, yielding substantial improvements in complex web task success rates.
Read the full abstract ▾
All authors Yangzhe Peng, Xiaoyang Wang, Yiyang Zhao, Lijun Wu, Kun He
Machine Learning
Analog-Friendly Predictive Coding without Activation Derivatives
Francesco Innocenti
Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementation on analog hardware. However, standard nonlinear PC requires evaluating the derivative of the activation function during both inference and learning, which can be difficult to realise physically. Here, we introduce activation-matched Bregman PC, replacing standard squared-error energies with Bregman divergences matched to the activation function. This formulation eliminates activation derivatives and, when combined with inference via mirror descent, yields local inference and learning rules requiring only weighted sums, local prediction errors, state integration, and the activation function. In digital experiments, Bregman PC performs comparably to standard PC and BP on classification and generative tasks, while preserving characteristic learning dynamics of PC and its convergence to BP under stable large-model parameterisations. These results provide a more analog-friendly formulation of nonlinear PC while retaining its key computational properties.
Read the full abstract ▾
Robotics
Human Motion Prediction for Human-Robot Collaboration
Placido Falqueto, Elena Basei, Edoardo Lamon et al. (+4 more)
This paper compares three human motion prediction methods - GMM-based clustering, TransFusion, and Graph-Mixer - evaluating their effectiveness in human-
robot collaboration. These predictions are valuable for improving
robot motion planning by anticipating human movements and enhancing safety and efficiency in dynamic environments.
Read the full abstract ▾
All authors Placido Falqueto, Elena Basei, Edoardo Lamon, Giovanni Perantoni, Matteo Saveriano, Daniele Fontanelli, Luigi Palopoli
Game Theory · Cross-listed from math.PR
Equilibrium Joining Strategies for Queues in Two-Phase Random Environment
Konstantin Avrachenkov and Uri Yechiali
We study
equilibrium joining strategies in an M/M/1-type queueing system with strategic customers operating in a two-phase random environment described as a continuous-time Markov process. Strategic customers, upon arrival, choose whether to join or to balk based on available information and anticipated utility, considering the trade-off between reward from service and waiting cost. Four observation scenarios are analysed: fully observable (both queue length and environment phase are disclosed to a customer upon arrival), queue-only observable, environment-only observable, and fully unobservable. In each case,
equilibrium joining strategies are analysed. In the environment-only observable and fully unobservable cases, explicit solutions and
equilibrium conditions are derived under rapid oscillations and under very slow transitions between environment phases.
Read the full abstract ▾
Artificial Intelligence
ALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs
Shanfeng Huang, Zhou Fang, Song Xiao et al. (+1 more)
For large
language models (LLMs), parametric adaptation is costly when
retrieval already suffices. We introduce ALLOT, a hybrid-
memory routing framework that separates learned write priority from a hard parametric budget. A
memory-aware router combines frozen text representations,
retrieval confidence, and relation metadata; a single ranking supports multiple write budgets while preserving all facts in external
memory. On CounterFact with Qwen3-4B, ALLOT reaches 0.760 accuracy at a 20% parametric-write budget and recovers 78.4% of the budget-matched oracle gain, with 80% fewer parametric writes than dual-writing every fact. At this budget, jointly adding
retrieval and relation features to text improves normalized oracle gain by 6.2 percentage points. Complementary Qwen3-0.6B shared-store results achieve dual-write-level accuracy with 6-14.5% parametric writes, and cross-
benchmark transfer retains approximately 88% of in-domain gain. These results support allocating adaptation capacity according to its incremental value rather than treating every factual update as an equally valuable training target.
Read the full abstract ▾
All authors Shanfeng Huang, Zhou Fang, Song Xiao, Hai Du
Computer Vision
OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI
Zhengyi Lu, Ming Lu, Chongyu Qu et al. (+11 more)
Metal implants corrupt MRI measurements throughout $k$-space, yet existing accelerated MRI methods assume clean data and most metal artifact reduction approaches assume fully sampled acquisitions. No public
dataset provides paired $k$-space and images with and without metal for the same anatomy, and no framework jointly addresses artifact-aware acquisition and reconstruction across sampling trajectories. We present OpenMASC, an open-source pipeline covering the full workflow from data generation to deployment. A physics-based data generation module converts public CT volumes into paired clean and metal-corrupted MRI data in both Cartesian and radial formats. MA-VarNet, an unrolled reconstruction network with a per-cascade DC Rectifier, corrects artifacts that data-consistency steps reintroduce from corrupted measurements. A reinforcement learning
agent actively selects $k$-space readouts and co-trains with the reconstruction network through a decoupled three-stage procedure. The framework is trajectory-agnostic except for the data-consistency operator, supporting both Cartesian and radial acquisition without architectural changes. Experiments on two
datasets at $4\times$ and $8\times$ acceleration demonstrate consistent improvements over conventional and learned baselines on both trajectories.
Read the full abstract ▾
All authors Zhengyi Lu, Ming Lu, Chongyu Qu, Junchao Zhu, Junlin Guo, Marilyn Lionts, Yanfan Zhu, Yuechen Yang, Tianyuan Yao, Jayasai Rajagopal, Bennett Allan Landman, Xiao Wang, Xinqiang Yan, Yuankai Huo
Machine Learning
A Comparative Analysis of Attention versus State-Space Models for In-Context Learning
Enes Arda, Semih Cayci and Atilla Eryilmaz
Transformers and state-space models (SSMs) are two prominent sequential learning architectures, yet their comparison remains largely empirical and existing theoretical analyses are typically task-specific or architecturally restricted. In this paper, we develop belief geometry, a unified analytical framework for comparing the representational capabilities of broad classes of
attention and SSMs. Starting from a generalized formulation of in-context linear regression and using cumulative Bayes regret as our measure, we abstract three capabilities required by many sequential learning problems in our belief geometry: evidence assembly, belief maintenance, and addressing. We then study three cases of our formulation that isolate these capabilities and yield sharp architectural lessons: For belief maintenance, SSMs attain the optimal regret over stationary aggregation kernels; for positional assembly, SSMs have a
memory advantage; and for content addressing, softmax
attention has an exponential width advantage over sigmoid-selective SSMs. Experiments with LLaMA-type
Transformers and Mamba-2 show that these architectural insights extend beyond our analytically tractable classes and linear-regression testbed.
Read the full abstract ▾
Computer Vision
SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO
Yunkai Yang, Yudong Zhang, Xinying Chen et al. (+5 more)
Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an efficient critic-free paradigm by calculating advantages over sampled candidate trajectories. However, standard Flow-GRPO applies a uniform scalar advantage across both temporal denoising steps and spatial latent dimensions, without explicitly accounting for the spatial structure of generated images, which may lead to sub-optimal policy updates. To address this, we propose a novel gradient-guided spatial credit assignment framework tailored for
Diffusion Transformers (DiTs). We first reformulate the transition-level log-likelihood in Flow-GRPO into a
token-wise representation natively aligned with DiT patch architectures, constructing spatially fine-grained importance sampling ratios. To allocate localized credit without rigid, boundary-sensitive
segmentation heuristics, we introduce a continuous spatial credit map derived from reward gradients. Crucially, we employ an outlier-robust normalization scheme based on Median Absolute Deviation (MAD) coupled with temperature scaling, effectively eliminating gradient noise while highlighting functional
prompt-aligned regions. Extensive evaluations on GenEval show that our approach delivers SOTA
alignment quality, achieving a convergence rate comparable to top-tier methods like DiffusionNFT while substantially improving upon Flow-GRPO-based methods in
alignment performance.
Read the full abstract ▾
All authors Yunkai Yang, Yudong Zhang, Xinying Chen, Bin Luo, Jienan Lyu, Kunquan Zhang, Weitao Wan, Runmin Dong
Artificial Intelligence
Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context
Feng Liang, Yupeng Li, Runhao Zeng et al. (+2 more)
Reusable skills help LLM-based
agents solve complex tasks, but the
agent must receive guidance before it commits to an ineffective approach. Existing skill mechanisms often expose only metadata and load full content on demand, leaving useful guidance unavailable until the
agent decides to retrieve it. General
memory methods can incur substantial maintenance overhead, while keeping guidance in conversation context risks repeatedly exposing the
agent to irrelevant or harmful advice. We propose TipsWarm, a mechanism that complements existing skill mechanisms by maintaining a budgeted pool of skill-derived keypoints, or warm tips, for selective injection into the context of every message turn. By separating event-triggered LLM assessment from inexpensive per-turn screening, it makes transferable skill guidance readily available while controlling maintenance costs. In three coding and iterative task-execution
benchmarks, TipsWarm achieves the highest task success rate while remaining time-efficient, compared to recent skill and general
memory baselines.
Read the full abstract ▾
All authors Feng Liang, Yupeng Li, Runhao Zeng, Francis C. M. Lau, Xiping Hu
Game Theory
Top Trading Cycles with Indifferences under Matroid Constraints
Yasushi Kawase
We study the reallocation of indivisible objects among
agents who may hold initial endowments and may be indifferent between objects. Each
agent has her own set of admissible objects, and a matroid constraint specifies which combinations of assigned objects are feasible. The model contains the housing
market, house allocation with newcomers who hold no endowment, and the assignment of students to schools under matroidal constraints at each school. For this model, we introduce the top-class trading cycles mechanism (TCTC), which extends the top trading cycles mechanism (TTC) to matroid constraints and weak preferences. When a trading cycle is selected, TCTC fixes each
agent's top indifference class rather than a specific object and postpones the choice within the class to the end. TCTC is individually rational, Pareto efficient, and weakly group-strategy-proof on the full domain of weak preferences, and it runs in
polynomial time. When preferences and reports are strict, TCTC is strongly group-strategy-proof. Together with a known impossibility result, our
theorem establishes a maximal domain of school-by-school constraints for individual rationality, Pareto efficiency, and strategy-proofness.
Read the full abstract ▾
Robotics
WSM-Aware HRI: An IoT-Enhanced Framework for Early Detection and Norm-Guided Repair of Failures with LLM Guidance
Hanlin Zhang, Yuquan Wang, Tianwei Zhang et al. (+1 more)
Human-
robot interaction (HRI) failures remain a major barrier to deploying
robots in real-world environments. Prior work often treats failures as isolated technical faults or focuses on post-hoc recovery behaviors. In practice, many breakdowns arise because humans and
robots operate under inconsistent assumptions about the current world state. We propose WSM-Aware HRI, an IoT-enhanced modular framework that unifies diverse HRI breakdowns as World-State Mismatches (WSMs) between a human's instruction-implied assumptions and a
robot's grounded world model built from
multimodal perception and digital augmentation. A Large
Language Model (LLM) is used to make implicit assumptions explicit, map them to a small set of mismatch types, and specify the evidence needed for verification against the
robot's world state. WSM-Aware HRI shifts failure handling from execution-time recovery to proactive mismatch detection during intention formation, enabling interventions guided by safety, norm compliance, and multi-user coordination with transparent explanations. We evaluate mismatch identification in ten everyday cases spanning both visual and latent-state mismatches. The system can accurately produce the expected output results, and ablations show that reliable identification depends on appropriate grounding representations and verification-oriented refinement. These results indicate that treating interaction breakdowns as explicit world-state mismatches enables earlier detection of impending failures and offers a principled mechanism for integrating external evidence and social constraints into human-
robot interaction.
Read the full abstract ▾
All authors Hanlin Zhang, Yuquan Wang, Tianwei Zhang, Zhenglong Sun
Computer Vision
Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs
Shanfeng Huang, Zhou Fang, Song Xiao et al. (+1 more)
Regional-to-global
distillation uses crop-conditioned guidance to improve full-image understanding. The challenge is to effectively transfer the teacher's crop-based advantage to the student's full-image inference. We propose progressive-view on-policy
distillation (PVD), which shifts the student's view distribution from the crop toward the full image through an intermediate aspect-preserving padded crop. The padded crop preserves regional content while matching the full image's visual-
token grid. Across stages, the view mixture assigns increasing probability to the full image. A lightweight regional-advantage weighting reallocates
token-level supervision using the crop-conditioned teacher-student log-probability gap. Evaluated under each sampled input, it applies mild reweighting when the gap is small and emphasizes higher-gap
tokens when the gap widens. A Jensen-Shannon metric decomposition interprets this schedule as a shift from matched-input imitation toward the deployment objective. Across
benchmarks spanning perception, visual mathematics and general
multimodal question answering, PVD-full reaches an average accuracy of 77.51 over three seeds, improving on the reward-free
distillation baseline by 2.01 points and on its reward-matched variant by 1.00 point. In the reward-free setting, PVD-distill still gains 1.16 points.
Read the full abstract ▾
All authors Shanfeng Huang, Zhou Fang, Song Xiao, Hai Du
Machine Learning
When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
Yixuan Liu, Yuhao Sun, Sen Song et al. (+1 more)
Rehearsal-free continual learning with parameter-efficient adapters can be cast as a sequence of task-vector write-in operations: for each new task, a low-rank adapter is learned and merged into a running model. We propose Proximity Regularized Merging (PRM), a minimal modification to sequential LoRA merging that adds a proximal penalty during task-vector training without changing the subsequent write-in rule. PRM acts as a robust task-vector regularizer: in the reported Base->+Prox diagnostics, it improves AAA across multiple write-in rules, backbones, and class-incremental settings, while its fixed-coefficient variant remains competitive with strong coefficient-based baselines. Mechanistically, matched-prefix norm controls and proximal-strength sweeps show that proximal training shrinks the task-vector radius, lowers Fisher-weighted interference, broadens the coefficient plateau, and exposes a stability-plasticity trade-off. Together, these results suggest that the effectiveness of sequential LoRA merging depends not only on how much of a task vector is written in, but also on whether the task vector itself has been trained to be mergeable.
Read the full abstract ▾
All authors Yixuan Liu, Yuhao Sun, Sen Song, Jin Li
Computation and Language
Language Distances are Practical for Equitable Cross-Lingual Transfer
York Hay Ng, Razan Ahsan Rifandi, Aditya Khan et al. (+1 more)
Cross-lingual transfer is strongly conditional on how the source
language is chosen, but it is impractical to determine the best candidate source for every target
language, especially for low-resource target
languages.
Language distances are widely used to rank candidate sources due to their correlation with transfer efficacy and applicability in resource-sparse settings. However, the reliability of distance-based rankers across tasks and resource levels remains underexplored. We therefore present the first equity-focused evaluation of paradigms for ranking source
languages, studying resource-level inequality and task inequality across ten cross-lingual tasks and two
multilingual models. While both inequalities are most pronounced for individual
language distances and an English-always baseline, they are substantially reduced by training-free composite distances, and nearly eliminated by trained rankers. We further demonstrate the reliability of rankers using
language distances compared to rankers using
language model internals. Overall, we find that
language distances provide a practical basis for equitable and performant transfer
language selection. We recommend using trained rankers when task-specific transfer evaluations are available, and composite distances otherwise.
Read the full abstract ▾
All authors York Hay Ng, Razan Ahsan Rifandi, Aditya Khan, En-Shiun Annie Lee
Machine Learning
Continual Data Unlearning in Diffusion Models via Transition-based Regularization
Sunbeom Jeong, Sehwan Kim, Sangwoo Hong et al. (+1 more)
Data unlearning in
diffusion models aims to remove the influence of specific training examples without suppressing the broader concepts they represent. However, when deletion requests arrive sequentially, updates for new requests can degrade generative utility and undermine earlier deletions. We propose a continual data unlearning framework that uses completed deletion transitions as directional references to regularize future updates. For each request, we record changes in denoiser responses on the same fixed noisy inputs before and after unlearning. Rather than matching full post-deletion responses, we apply a one-sided penalty that discourages reversal along the recorded directions relative to the post-deletion references, while leaving orthogonal response changes and progress beyond these references unpenalized. To keep storage independent of the number of requests, we maintain a fixed-capacity bank of representative transition records. Records are selected based on the local sensitivity of progress along their recorded directions to parameter updates, allowing them to be retained even when their penalties are inactive. Empirical evaluations show that the proposed framework achieves a better balance between deletion persistence and generative utility than existing unlearning baselines as requests accumulate, using only a small transition
memory.
Read the full abstract ▾
All authors Sunbeom Jeong, Sehwan Kim, Sangwoo Hong, Jungwoo Lee
Artificial Intelligence
HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning
Zicheng Zhao, Linhao Luo, Junnan Dong et al. (+4 more)
Large
language models (LLMs) have shown strong capabilities, with
retrieval-augmented generation (RAG) supporting complex multi-hop
reasoning by retrieving evidence distributed across documents. Graph-based approaches exploit connections among evidence, and hypergraph-based
retrieval further preserves higher-order entity associations within documents and connects documents through shared entities. However, existing hypergraph retrievers often rely on predefined structural expansion or
diffusion, which may miss query-dependent interactions needed to identify relevant evidence. They also leave connections among retrieved evidence implicit, requiring LLMs to reconstruct these connections before
reasoning. Therefore, we propose HyperReCo, a framework for retrieving and connecting evidence with a hypergraph neural network (HyperGNN). We represent each document as a hyperedge over its extracted entities, with shared entities connecting the hyperedges. Through hypergraph message passing with joint supervision over documents and entities, the HyperGNN learns query-dependent interactions to retrieve complementary evidence. We further introduce Gradient-Guided Hyper-Path Decoding (GGHD), which uses gradient attribution to interpret the learned interactions and translate them into explicit hyper-paths that help LLMs combine complementary facts for multi-hop
reasoning. Experiments on six
benchmarks show that HyperReCo achieves the best
retrieval performance among the compared methods on all three multi-hop QA
datasets, together with strong downstream QA performance. Case studies and further analyses demonstrate the utility of decoded hyper-paths for connecting retrieved evidence.
Read the full abstract ▾
All authors Zicheng Zhao, Linhao Luo, Junnan Dong, Haoran Luo, Xiaoli Li, Shirui Pan, Chen Gong