Machine Learning
Learning Pareto Stationary Fronts via Single-Pass Backpropagation
Elina Rojin Celik, Marcos Medeiros Raimundo and Isabel Valera
We propose MOSEL (Multi-Objective Stackelberg Efficient Learning), a framework for a posteriori multi-objective optimization (MOO) in deep neural networks that recovers a full front of Pareto stationary solutions at the computational cost of standard single-objective training. MOSEL reformulates the problem as a bilevel optimization problem that leverages network modularity to decouple representation learning from objective-preference
alignment. Casting the bilevel optimization problem as a Stackelberg game enables solving the original a posteriori MOO problem in a single forward-backward pass. As a result, MOSEL matches the time and
memory efficiency of standard single-objective training while enabling scalable Pareto stationary front learning. Empirically, MOSEL uncovers diverse and optimal Pareto frontiers in strongly conflicting settings (e.g.,
fairness-accuracy). Remarkably, even in weakly conflicting regimes such as multi-task learning, it consistently converges to solutions closer to the utopia point, outperforming both standard single-objective training and specialized multi-task learning methods. These results highlight the broader potential of a posteriori MOO learning as a pathway to efficiently learn more diverse and robust representations, ultimately improving generalization.
Read the full abstract ▾
Computer Vision
Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection
Zhaolin Cai, Huiyu Duan, Liu Yang et al. (+5 more)
Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform strongly but rely on task-specific training. Recent
multimodal large
language models (MLLMs) offer a promising route to training-free HOI detection through their broad visual-semantic knowledge and versatile perceptual and
reasoning capabilities. However, existing approaches largely invoke these capabilities through loosely coordinated inference stages. This fragmented execution restricts the role of interaction hypotheses in guiding visual exploration, leaving key participants overlooked and local ambiguities unresolved. Furthermore, propagating early semantic assumptions through subsequent visual grounding and relation prediction induces self-reinforcing semantic circularity. To resolve these challenges, we propose HarnessHOI, a training-free framework that transforms passive MLLM inference into an active interaction-centric harness. Specifically, we introduce an interaction-guided perception mechanism that projects emerging interaction hypotheses back into the visual space to discover missing participants and refine ambiguous evidence through targeted observation. Furthermore, a relation-agnostic
geometric adjudication module reconciles multi-source evidence to establish a unified spatial basis for grounded interaction
reasoning across multiple actions and semantic roles. Extensive experiments on HICO-DET and V-COCO demonstrate that HarnessHOI achieves state-of-the-art performance among training-free methods, confirming the effectiveness of the proposed harness for complex interaction understanding. Code will be released upon publication.
Read the full abstract ▾
All authors Zhaolin Cai, Huiyu Duan, Liu Yang, Yanjun Qin, Bo Ai, Wei Chen, Xiongkuo Min, Guangtao Zhai
Computer Vision
Multi-Task Partially Supervised Learning for Super-Resolution and Semantic Segmentation on Earth Observation data
Hoàng-Ân Lê, Minh-Tan Pham, Solange Lemai-Chenevier et al. (+1 more)
Super-resolution and semantic
segmentation are known to benefit one another, especially in the Earth observation context. However, learning both tasks in a joint model often requires both task annotations, which is impractical and expensive. In this paper, we study the multi-task partially supervised learning paradigm for both tasks, where each example is assumed to have only a single-task annotation. To that end, we examine two multi-task architectural variations, the sequential and shared variants, and then propose a hybrid variant and a re-projection loss to benefit from the shared representation and enforce image quality of super-resolution when training with semantic
segmentation. Experiments show favorable results compared to the SOTA sequential variant. Source code will be published at https://github.com/lhoangan/munera.
Read the full abstract ▾
All authors Hoàng-Ân Lê, Minh-Tan Pham, Solange Lemai-Chenevier, Daniel Greslou
Machine Learning
Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models
Joe Dwyer
Large
language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. However, traditional scaling approaches produce diminishing returns, rising financial and environmental costs, and barriers to participation for researchers operating outside large industrial laboratories. This review examines the
evolution of LLM scaling theory from empirical scaling laws to compute-optimal training, with particular emphasis on parameter efficiency,
token utilization, data efficiency, and resource-constrained environments. Foundational work on scaling laws is synthesized alongside later research on compute-optimal training, data
pruning, efficient architectures, quantization, low-rank adaptation, and edge-oriented optimization. The literature indicates a shift from scale maximization toward more deliberate allocation of parameters,
tokens, compute, and hardware resources. At the same time, important empirical, theoretical, and methodological gaps remain regarding whether scaling principles established on enterprise-grade infrastructure generalize to smaller models and constrained computing environments. This review organizes these developments into a unified framework for resource-efficient LLM training and argues that future progress should evaluate efficiency not solely through model performance, but through the relationship among performance, parameter count, computational cost,
token allocation, and hardware constraints.
Read the full abstract ▾
Machine Learning
Steering by Influence: Curvature Aware Data Weighting for Activation Steering
James A. E. Dixon, Stephen J. Roberts and Francesco Quinzan
Inference-time steering offers cheap, fine-grained control over a
language model's outputs by estimating a concept's representation in activation space and shifting activations towards it. Existing methods build these representations from activation averages over contrastive
datasets. These averages incorporate unrelated concepts and noise, and are dominated by a few
tokens, meaning the activation transport encodes
token-level rather than thematic concepts. In this work, we steer towards examples that most express a concept thematically, rather than towards an expectation over all. We identify these examples using influence functions, which estimate how much each data point contributes to a model's representation of a concept. Unlike simple model activation similarity, they incorporate the
curvature of the model's loss landscape, allowing them to capture concept-relevant relationships beyond superficial
token-level similarity. We then propose influence-weighted activation transport, which uses optimal transport to steer activations of non-concept text towards those of concept text, weighting concept examples by their influence scores. We evaluate on toxicity suppression (Jigsaw), object-based concept induction (OneSec) and truthfulness induction (TruthfulQA), outperforming existing activation-transport baselines. We track capability after steering using perplexity and MMLU accuracy, finding that our method improves steering while largely preserving model quality. We further show that influence functions capture concept-relevant information that activation-based methods miss with the two approaches ranking data points significantly differently. Together, these results demonstrate the value of
curvature-aware influence information for activation steering.
Read the full abstract ▾
Computational Engineering
AeroMig: Multi-modal Inverse-Gamma modeling for aerosol particle number size distributions
Abdur Rahman, Juha Kangasluoma, Santtu Mikkonen et al. (+4 more)
Aerosol particles play a critical role in air quality, human health, and
climate processes, making their accurate characterization essential. One common way to represent aerosol populations is through particle number size distributions (PNSDs), which describe the concentration of particles across different mobility diameters. However, these distributions are often highly skewed, heavy-tailed, and multi-modal, posing significant challenges for conventional fitting approaches. In this study, we propose a robust parametric framework (AeroMiG) for modeling PNSDs using Inverse-Gamma mixture distributions. The method represents observed size distributions as a superposition of multiple Inverse-Gamma components, enabling flexible modeling of asymmetric and heavy-tailed structures that are not well captured by widely-used Log-Gaussian based approaches. The performance of the proposed method is evaluated using real-world data from three measurement stations. Results are assessed using multiple criteria, including predictive accuracies, computational efficiency, and a composite score summarizing overall model quality. Comparative analysis against a widely used Aerosol Multi-mode Log-Gaussian (AeroMG) demonstrates that the AeroMiG framework consistently achieves improved fitting accuracy, lower error, and faster computation. The proposed approach provides a reliable and computationally efficient solution for modeling complex aerosol size distributions, with potential applications in real-time air quality monitoring and data-driven environmental analysis.
Read the full abstract ▾
All authors Abdur Rahman, Juha Kangasluoma, Santtu Mikkonen, Tareq Hussein, Tuukka Petäjä, Sasu Tarkoma, Martha Arbayani Zaidan
Computer Vision
MTOR: Generalizable AI-Generated Video Detection with Multimodal Semantics and Temporal Over-Regularity
Hang Wang, Chao Shen, Lei Zhang et al. (+1 more)
The rapid
evolution of
video generation has narrowed the perceptual gap between authentic and synthetic
videos, making generalizable AI-generated
video detection increasingly challenging. Existing detectors predominantly rely on visual representations, leaving caption-derived textual semantics underexplored. Meanwhile, temporal regularity in fine-grained visual representations has received limited
attention. We find that caption-derived textual representations provide complementary discriminative cues to global visual representations. Our analysis further reveals that AI-generated
videos exhibit stronger temporal persistence and lower temporal variability, a pattern we term temporal over-regularity (TOR). Based on these findings, we propose MTOR with a
multimodal branch and a TOR component. The
multimodal branch integrates global visual and caption-derived textual representations, while the TOR component models temporal over-regularity at three levels: coarse inter-frame continuity, fine-grained
token correspondence, and frame-to-
video stability. Extensive evaluations on five
benchmarks covering 46 generator variants demonstrate state-of-the-art overall performance against 16 representative baselines, while robustness experiments confirm strong resilience to twelve real-world
video perturbations. Code and models will be released at https://github.com/hwang-cs-ime/MTOR.
Read the full abstract ▾
All authors Hang Wang, Chao Shen, Lei Zhang, Zhi-Qi Cheng
Robotics
Towards Robust Prehensile Manipulation in Open-Ended Environments
Mathilde Kappel, Mahdi Khoramshahi, Louis Annabi et al. (+2 more)
We propose to use Quality-Diversity (QD)
algorithms to solve robotic prehensile manipulation tasks in open-ended environments. Our approach enables the efficient discovery of a wide range robust grasp configurations, which serve as reliable starting points for generating diverse prehensile manipulation trajectories on articulated objects. The resulting diversity in manipulation behaviors enhances generalization and adaptability, enabling effective deployment continuously evolving open-world settings.
Read the full abstract ▾
All authors Mathilde Kappel, Mahdi Khoramshahi, Louis Annabi, Faïz Ben Amar, Stéphane Doncieux
Game Theory
A Decremental Algorithm for Checking the Possibility of Braess Paradox in Dynamic Nets
Dario Fiorenza, Daniele Gorla and Ivano Salvo
Braess paradox originates when latency at Wardrop
equilibrium in traffic networks decreases because of removing edges. The graph-theoretic property of networks suffering from the Braess paradox was called vulnerability by Roughgarden in 2006; it was then characterized and algorithmically checked both for undirected and for directed nets. In this paper, we provide a decremental
algorithm of linear amortized complexity to check vulnerability for dynamically evolving networks. The basic idea of our dynamic
algorithm is to use a static
algorithm that marks some edges as irrelevant for the vulnerability of the graph and ignore those edges for all subsequent runs of the decremental procedure. To get a linear amortized cost for every edge remotion, we also provide a new version of such a static
algorithm that improves its complexity from O(n m^2) to O(m^2), that is in turn aligned with the cost of the best state-of-the-art static
algorithm for vulnerability.
Read the full abstract ▾
Computer Vision
Environmental sensor readings in two crop disease image datasets identify the session in which each image was taken
Sungwoo Kang
Integrating environmental sensor data with leaf imagery is widely reported to boost crop disease classification accuracy. In this work, we reveal that these reported gains are often artifacts of
dataset construction: because a single sensor reading is shared across many images collected in a single session (one farm on one date),
multimodal networks can predict disease simply by memorizing session identities. Analyzing two widely used Korean
datasets, the Crop Disease Diagnosis (CDD)
benchmark and an AI Hub pest/disease
dataset, we demonstrate that nearly all images share sensor values, with 91.9% of CDD test images having exact sensor duplicates in the training set. Remarkably, an image-free classifier given only timestamps matches or exceeds sensor-driven predictions across all seven evaluated crops, and matches the published macro-F1 of a state-of-the-art CDD fusion model. These results indicate that performance gains on standard random splits cannot be disentangled from session leakage. We propose that
multimodal crop studies must evaluate on session-held-out splits and report performance against sensor-free date-time baselines to ensure genuine generalization.
Read the full abstract ▾
Logic in Computer Science
Decreasing Diagrams are Complete for Confluence
Jörg Endrullis, Ievgen Ivanov and Femke van Raamsdonk
Confluence is a fundamental property of nondeterministic computations, arising from parallelism, concurrency, or freedom in the evaluation order. It guarantees that such a computation always yields the same result, regardless of the order in which steps are taken. The decreasing diagrams technique of van Oostrom is one of the most versatile methods for establishing confluence of transition systems (abstract rewriting systems). It reduces global confluence to local confluence: a system is confluent whenever its transitions admit a locally decreasing labeling. Essentially all classical confluence criteria arise as corollaries. A central question, posed by van Oostrom in 1993, asks whether the decreasing diagrams technique is complete: Does every confluent transition system admit a locally decreasing labeling? This is Problem 56 of the RTA List of Open Problems. A positive answer was known only for countable systems, and recently up to the first uncountable cardinal $\aleph_1$. The general case remained open. We settle this thirty-three-year-old problem in full. We prove that every confluent transition system admits a locally decreasing labeling using only three labels. This bound is optimal, as two labels do not suffice even at the first uncountable cardinality. It follows that this single criterion can, in principle, certify the confluence of every confluent system, and hence of every confluent program. The entire development is machine-checked in the Isabelle/HOL and Lean proof assistants and relies only on classical logic and the axiom of choice.
Read the full abstract ▾
Cryptography and Security
Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning
Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni et al. (+1 more)
Large
Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; practitioners need explanations to triage bugs and engineer patches. Standard practice relies on Chain-of-Thought (CoT) prompting, but free-form
reasoning allows models to obscure logical leaps, hallucinated execution steps, and internal inconsistencies behind plausible prose. Our manual audit reveals that approximately 60% of correct vulnerability verdicts are accompanied by fabricated or unverifiable claims, and free-form explanations allow
reasoning errors to evade LLM-as-a-judge evaluation. We present Vulnerability Explanation
Reasoning Auditor (VERA), an automated framework for
auditing LLM vulnerability
reasoning. Rather than accepting free-form text, VERA asks models to output a Structured
Reasoning Record (SRR) encoding tracked pointers,
memory operations, and state transitions in machine-readable fields. A multi-stage judge audits each SRR against eight
reasoning failure modes using deterministic checks, with LLM calls reserved for semantic interpretation. The standardized SRR schema also enables automated mutation testing to
benchmark judges at scale without human annotation. Our evaluation shows
reasoning flaws occur in correct verdicts just as frequently as incorrect ones, and VERA exposes 87% of
reasoning errors that free-form LLM-as-judge systematically miss.
Read the full abstract ▾
All authors Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni, Limin Jia
Machine Learning
Multimodal Deep Survival Analysis for Sinkhole Susceptibility
Lucas Yuan, Minhee Kim, Zihan Li et al. (+4 more)
Sinkholes are a widespread geohazard in karst terrain. In Florida, soluble carbonate bedrock, shallow groundwater, and intense rainfall combine to make subsidence both common and spatially heterogeneous. Predicting where and when sinkholes will occur is difficult for two reasons. First, locations without reported sinkholes cannot be directly labeled or sampled as true negative locations. Second, the potential factors governing sinkhole risk span heterogeneous data modalities and therefore require careful integration within a unified modeling framework. We address both problems with our proposed model, a
multimodal Cox proportional hazards framework for sinkhole susceptibility. Our contributions are threefold. First, we extend the proportional-hazards formulation to heterogeneous
multimodal input through modality-specific encoders and a cross-modal fusion layer. Second, we treat unreported locations as right-censored rather than negative, avoiding hard-negative labeling and yielding continuous, time-aware susceptibility from the predicted survival function. Third, a statewide Florida case study with spatially blocked validation and ablation studies quantifies the benefit of
multimodal integration. A Florida case study demonstrates that the proposed method effectively ranks sinkhole risk and produces a statewide susceptibility map that captures spatial variations in sinkhole occurrence.
Read the full abstract ▾
All authors Lucas Yuan, Minhee Kim, Zihan Li, Chunli Dai, Sanduni S. Disanayaka Mudiyanselage, Ming Ye, Kani Fu
Cryptography and Security
Explicit Nonlinear Functions beyond the Fourier bound
Swastik Kopparty, Rishabh Kothary and Shanthanu S. Rai
We study the problem of constructing highly nonlinear vectorial maps $F: \mathbb F_2^n \to \mathbb F_2^m$. Concretely, we want an $F$ and an $A = A(m,n)> 0$ as small as possible, so that for every affine map $L: \mathbb F_2^n \to \mathbb F_2^m$ (of the form $L(x) = M x + b $) we have: $$\mathrm{agree}(F, L) := |\{ x \in \mathbb F_2^n \mid F(x) = L(x) \}| \leq A.$$ Such questions have been studied by Nyberg (1991,1993), Carlet and Ding (2004,2007), Liu, Mesnager and Chen (2017), Nagy (2025), and Biryukov, Turecek, and Udovenko (2026). There is a classical method of constructing such functions from bent-functions and
Fourier analytic ideas; the best bound achievable by this method is: $$ A(m,n) = \Theta(2^{n-m} + 2^{n/2}),$$ and in particular, is never smaller than $2^{n/2}$. In this work, we show how to construct highly nonlinear functions beyond this
Fourier bound. Concretely, we show how to construct for every $\gamma>0$, a function $F: \mathbb F_2^n \to \mathbb F_2^m$ with $m = O_{\gamma}(n)$, achieving $$ A(m,n) \leq (1 + \gamma)^n.$$ Surprisingly, we even achieve the same quantitative behavior for the much harder question of having low agreement with $m$-tuples of degree $d$
polynomials $Q: \mathbb F_2^n \to \mathbb F_2^m$, with $m = O_{\gamma, d}(n)$. Here the previously best bounds were of the form $A(m,n) = O( 2^{-\frac{n}{2^{d+1}}} \cdot 2^n )$ of Ben-Sasson and Kopparty (2010), based on Gowers-norm-type arguments. All our results generalize to all finite fields $\mathbb F_q$ in place of $\mathbb F_2$. Our methods are based on a new connection to classical results on counting solutions to systems of
polynomial equations via algebraic methods. This connection brings us to basic questions in combinatorics, about graphs and hypergraphs with simultaneously a small number of edges and independent sets.
Read the full abstract ▾
Artificial Intelligence
Yaoqi Chen, Yuru Feng, Qianxi Zhang et al. (+8 more)
Memory self-
evolution uses task feedback to iteratively improve executable
memory programs that store and retrieve information from past interactions. Existing approaches typically adopt holistic
evolution, deriving revision directions from mixed feedback and judging progress by overall performance. This can obscure optimization directions and hide capability-specific gains offset by regressions elsewhere, leaving promising directions underexplored. We introduce capability-driven
evolution, which extends search guidance from overall performance to individual capability dimensions, preserving promising revisions and expanding exploration beyond the boundaries of holistic
evolution. We propose PrisMem, which uses dependency-aware capability selection to prioritize targets with potential cross-capability benefits and history-guided diagnosis to refine capability specialists. Trace-guided integration compares evaluated programs on paired differential cases, using their behavioral differences to consolidate complementary gains into a unified
memory program. Experiments show that PrisMem outperforms the strongest baselines by 10.54 and 7.83 percentage points on BEAM-1M and LongMemEval-M, respectively, demonstrating its effectiveness on million-
token histories.
Read the full abstract ▾
All authors Yaoqi Chen, Yuru Feng, Qianxi Zhang, Baotong Lu, Jianan Lu, Zhirui Wang, Shusen Xu, Zewen Jin, Zengzhong Li, Cheng Li, Qi Chen
Computation and Language
Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Aditya Tanna and Abhishek Jindal
Reinforcement learning post-training for
language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clinical question answering fits neither. Near-correct answers differ by a single substituted entity, and no executable check decides clinical correctness. We instantiate a soft verifier from a maintained controlled vocabulary: UMLS Concept Unique Identifier overlap (via scispaCy, set-level F1) gives a graded, externally specified reward computed without a model in the loop. We combine it inside GRPO with an
entropy-normalised LLM judge, which covers the safety and evidence axes overlap cannot see, and a small consistency penalty on padding and repetition that keeps early-training samples scorable. This three-term composite improves over SFT on Phi-3-mini (3.8B) over MedQA by 2.9% on EM (0.700 vs 0.680) and 39% on
Token-F1 (0.202 vs 0.145); on Llama-3.2-3B the corresponding gains are 14% on EM and 35% on
Token-F1. We report
Token-F1 as the primary metric because it credits partially-correct clinical content that EM discards at this open-generation scale. Main-table results are means over 3 seeds with standard deviations below 0.005. The method transfers to PubMedQA, where training on the PubMedQA train set with the same composite reward improves
Token-F1 over SFT by 22% on Phi-3-mini and 17% on Llama-3.2-3B without retuning. A reward ablation on Phi-3, varying the judge-ontology split at a fixed consistency weight, attributes 3 EM points to the ontology term, the contribution that catches entity substitutions the judge cannot. Three negative findings constrain the design: DPO under random negatives underperforms SFT for strong-prior models but helps the weakest-prior one; PPO under a sparse neural reward diverges; GRPO with KL-in-loss collapses at 7B.
Read the full abstract ▾
Neural and Evolutionary Computing
A Flexible and Generic Approach for Explainable Landscape Analysis and the pyXla Toolbox
Tony Ombaso, Anna S. Bosman, Arnaud Liefooghe et al. (+2 more)
Landscape analysis has been successfully applied to understand complex optimisation problems, gain insights into
algorithm behaviour, and automate
algorithm selection and configuration. Although many landscape analysis techniques have been developed over the last decades, it remains difficult for researchers and practitioners to decide which approaches are appropriate and to implement them in practice. Some tools are available, but these are either restricted to particular problem domains (e.g., unconstrained black-box continuous optimisation), or are limited in what they model and measure. In addition, output from landscape analysis is often not easily interpretable, especially when computed landscape features do not correspond with aspects of problems that practitioners are familiar with. In this paper, we introduce a principled approach for explainable landscape analysis (XLA) with an associated Python package called pyXla. The approach is generic in that it applies to problems with different representations (continuous or combinatorial), with single or multiple objectives, with or without constraints. The extent of analysis provided by the XLA framework depends on the data available, with richer analysis offered as additional information is provided by the user. We demonstrate the explainable output produced by pyXla on a selection of hand-crafted problems with diverse landscape characteristics.
Read the full abstract ▾
All authors Tony Ombaso, Anna S. Bosman, Arnaud Liefooghe, Katherine M. Malan, Sébastien Verel
Distributed Computing
DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics
Dongyoon Ryu, Sungho Jeon, Xinyue Ma et al. (+4 more)
Edge
video analytics with lightweight models is prone to accuracy degradation due to persistent distributional shifts in live
video streams. While continuous learning (CL) addresses such data drift, it heavily strains the limited compute resources of edge servers originally provisioned for inference. Our empirical study reveals that emerging
vision foundation models (VFMs) offer a practical, retraining-free alternative that delivers high average accuracy with remarkable compute savings. However, VFMs frequently misclassify specific rare classes, which often represent critical objects, as visually similar common classes. We design DIALER, a system that exploits the spare compute cycles freed by retraining-free VFM inference to mitigate rare-class misclassifications. Specifically, DIALER pre-builds multi-stage correction pipelines for dominant rare-to-common confusion pairs offline. At runtime, it routes correction candidates to the corresponding pipelines and executes as many stages as idle GPU headroom permits. Evaluation on four real-world driving
datasets shows that DIALER improves rare-class accuracy by up to 14.0% without interfering with real-time VFM inference for multi-stream analytics.
Read the full abstract ▾
All authors Dongyoon Ryu, Sungho Jeon, Xinyue Ma, Di Wang, Jonghyun Choi, Minjia Zhang, Myeongjae Jeon
Machine Learning · Cross-listed from stat.ML
Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support
Yaniv Yacoby, Weiwei Pan, Hope Neveux et al. (+4 more)
Forecasting suicide risk is difficult due to the high heterogeneity of patients and the low base rate of suicide-related events (SREs). We present Latent Similarity Gaussian Processes (LSGPs), which embed patients in a continuous latent space to jointly model similarity and forecast risk. By selectively drawing information from latent peers, LSGPs better capture individualized risk trajectories, generalizing nomothetic (pooled), idiographic (per-patient), and hierarchical frameworks. Our contributions are: (1) an identifiable two-channel Similarity Kernel; (2) proof that the standard model-fitting
algorithm, mean-field variational inference, collapses LSGPs to nomothetic models, along with a fix; and (3) empirical results on intensive longitudinal suicide data showing LSGPs outperform nomothetic, idiographic, and hierarchical models for next-week risk
forecasting, with the largest gains in
forecasting first-occurrence SREs.
Read the full abstract ▾
All authors Yaniv Yacoby, Weiwei Pan, Hope Neveux, Taylor C. McGuire, Franchesca Castro-Ramirez, Anushka R. Patel, Matthew K. Nock
Artificial Intelligence
GraphDecisionBench: Benchmarking System One Models on Graph Tasks
Xianliang Yang, Yapu Zhang and Li Zhao
Large
language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select directly from supplied options. However, the capabilities of System One models on graph-related tasks remain unclear. We introduce GraphDecisionBench, a model-independent
benchmark that combines structural task profiles, matched graph-text input contrasts and heuristic-proposal controls to diagnose graph decision performance. We evaluate Jev and related choice-based models alongside
language-model baselines, covering fourteen model-interface configurations. Jev's results illustrate the
benchmark's central distinctions: accurate adjacency recognition does not guarantee broader structural correctness, joint graph-text input does not consistently improve prediction, and feasible construction does not establish high solution quality. Its task contracts, candidate interfaces and scoring rules support comparison across native selectors and
language-model adapters. Code and aggregate results are available at https://github.com/VictorYXL/GraphDecisionBench.
Read the full abstract ▾
Distributed Computing
From a Last-Week Add-On to First-Day Practice: Three Years of Integrating MPI Performance Analysis into HPC Education with EduMPI Suite
Anna-Lena Roth and Jonas Posner
Performance analysis is essential for scalable MPI programs, yet tool and workflow complexity often relegates it to the end of Parallel Programming courses. EduMPI Suite lowers this entry barrier by automating cluster execution, measurement, and near-real-time analysis while visualizing MPI communication from the first program. This paper presents a three-year experience report on its integration into HPC education. We trace the transition of performance analysis from a last-week add-on to a recurring element of MPI development, using unpublished historical survey evidence and individual 2025 questionnaire data. Earlier cohorts perceived performance analysis as unnecessary, difficult, or unintuitive. In the final study, all students recommended introducing EduMPI Suite early in the course. Of 33 students, 29-33 rated it higher than conventional tools for understanding program behavior, interpreting communication, identifying bottlenecks, obtaining visual feedback, and navigating the tool. These findings support
embedding performance analysis throughout MPI education before transitioning learners to professional environments.
Read the full abstract ▾
Computer Vision
KineWorld: Action-Induced Transport Fields for Embodied World Modeling
Ziying Song, Yuchen Liu, Zhuoran Xu et al. (+6 more)
Embodied world models predict the visual consequences of candidate actions before execution. However, existing action-conditioned world models often adopt uniformly weighted visual generation objectives that can be misaligned with
embodied prediction needs. Even with explicit motion conditioning, these objectives can underemphasize spatially sparse changes that are critical to interaction. We propose KineWorld, a transport-aware world-modeling framework that extends
robot kinematics from motion conditioning to the spatial allocation of generative supervision. Kinematic Transport Lifting (KTL) constructs renderer-derived, camera-aligned transport fields from commanded
robot motion. Transport-Aware World
Diffusion (TAWD) calibrates their motion support on the
video-latent grid and reweights future-RGB flow matching through a normalized mixture of uniform and transport-focused distributions. We train KineWorld using ALOHA-AgileX bimanual manipulation data from RoboTwin 2.0. KineWorld achieves an EWMScore-P of 68.95 in single-view evaluation and a TWB-Score of 54.82 in multi-view evaluation. These results support a shift from appearance fitting toward action-consequence modeling for
embodied decision-making.
Read the full abstract ▾
All authors Ziying Song, Yuchen Liu, Zhuoran Xu, Ziyang Liu, Jian Jin, Jiangtao Su, Haibao Yu, Lei Yang, Yuanpei Chen
Numerical Analysis
IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs
Sima Naraghi, Kourosh Parand, Amirhossein Sadr et al. (+1 more)
Isogeometric analysis (IGA) solves partial differential equations accurately on exact NURBS geometry, whereas neural solvers are mesh-free but often orders of magnitude less accurate and typically trained by non-convex optimization without error control. We propose IGA-KAN, which uses local Kolmogorov-Arnold networks, fitted in closed form, to improve the IGA solution instead of replacing it. An IGA Galerkin solve produces u_h; on every
knot-vertex patch a Kolmogorov-Arnold ridge model is fitted to the strong form of the equation, the exact boundary data and u_h, and the models are blended by IGA hat functions. With fixed inner functions the fit is one batched linear least-squares problem, without optimizer, learning rate or initialization. An a posteriori safeguard, motivated by a maximum-principle bound, decides where local models are used, keeping the IGA solution elsewhere. On eight
benchmarks with exact solutions, five from the literature and one also posed on a domain fitted to a
brain slice from MRI, the method reduces the error of IGA, at an unchanged number of Galerkin unknowns, by factors of 4.2 to 90 in L^2 and 4.1 to 220 in H^1 on the reference meshes, and its L^2 error is 6 to 6x10^4 times smaller than that of the best Kolmogorov-Arnold network trained from scratch on the same equations with a fixed budget. In an inverse problem it recovers an unknown constant source from one noise-free observation 167 times more accurately than IGA. The gain is attributed to the superconvergence of local averages of the Galerkin solution.
Read the full abstract ▾
All authors Sima Naraghi, Kourosh Parand, Amirhossein Sadr, Dara Rahmati
Artificial Intelligence
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
Xingbo Yao, Xiaoman Wang, Zhengwu Lei et al. (+11 more)
Adapting general-purpose large
language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially challenging because model updates change the error distribution, requiring strategies to be continually refined. We introduce ImproveAnyTask, an autonomous post-training harness that improves task performance under a limited compute budget. Drawing inspiration from gradient-based parameter optimization, the harness organizes adaptation into error attribution, update-direction selection, and executable model updates. It combines metric-level and case-level analysis to identify a focal problem, then investigates research-backed strategies and compares their reported gains and reproduction difficulty. The selected strategy is translated into training data and a training configuration, with small-scale execution checks preceding full post-training. Subsequent evaluation guides model selection and further adaptation, while validated strategies and scripts are retained for reuse. Across 11 tasks, ImproveAnyTask achieves mean gains of 18.29 and 11.97 percentage points on the Base and Instruct models, respectively, with a maximum gain of 41.96 points, under a 24-hour budget with resources equivalent to eight H20 GPUs.
Read the full abstract ▾
All authors Xingbo Yao, Xiaoman Wang, Zhengwu Lei, Tinghui Luo, YiLin Zhang, Yuefeng Wu, Yijie Xu, Tianfu Wang, Qingyuan Zhan, Ye Guo, Daoxin Zhang, Zhe Xu, Jian Liu, Hui Xiong
Computation and Language
Breaking Bureaucracy: Evaluating open-source LLMs for legal document review
Farrukh Baratov, Niki van Stein and Suzan Verberne
In this paper, we evaluate open-source generative LLMs on legal Natural
Language Inference (NLI). Legal inspectorial processes take place in specific domains and often deal with confidential data. This creates a need for working with local models that do not require labeled training data. We evaluate our models on the ContractNLI
benchmark and two NLI4Wills
datasets. We successfully reproduce the baseline for the task (Span NLI BERT) and we evaluate multiple open-source LLMs on the same task. We analyze the invalid rate of the models, and their stability across temperature settings and domains. Among the generative models, Gemma-4 26B performs the best, reaching an accuracy of 81.2%, even outperforming the supervised model on one metric. On accuracy, it is not possible to beat the supervised model with zero-shot approaches. Qwen-3.6 35B performs well on both ContractNLI and additional
datasets in the legal wills domain. Our findings indicate that zero-shot, open-source, generative LLMs are a viable alternative for real-world legal NLI when no supervised data is available. Our code is available at https://github.com/fbaratov/contractnli-llms.
Read the full abstract ▾
Machine Learning
Stability-Shaped Deep Graph Learning
Junyou Zhu, Langzhou He, Fenying Cai et al. (+7 more)
In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align. We develop a unified, mode-wise stability framework for deep GNN propagation that provides a principled characterization of over-smoothing. By interpreting layer depth as time and layer updates as graph-coupled dynamics, over-smoothing can be understood as an undesirable dynamical synchronization of features, for which the master stability curve provides a theoretical tool to assess the stability of synchrony. Guided by this theory, we further propose Stability-Shaped Deep Graph Learning (SDGL) to mitigate over-smoothing in deep GNNs. SDGL has two complementary instantiations: one induces controlled Turing instability to replace synchronization with spatial pattern formation, and the other maintains stable near-critical propagation. Experiments on diverse node- and graph-level
benchmarks demonstrate the improved depth scaling and consistent accuracy gains over strong baselines, including graphs exhibiting long-range dependencies.
Read the full abstract ▾
All authors Junyou Zhu, Langzhou He, Fenying Cai, Christian Nauck, Ping Xiong, Chao Gao, Philip S. Yu, Klaus-Robert Müller, Jürgen Kurths, Frank Hellmann
Computer Vision
MeSD: Multi-Evidence Self-Distillation for VideoLLM
Weijie Zhu, Han Fang, Hanyu Fu et al. (+13 more)
While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited
token-level guidance. On-policy self-
distillation addresses this limitation by conditioning a self-teacher on privileged information to provide dense
token-level supervision. However, aggregating heterogeneous evidence within a single teacher context obscures cross-evidence agreement and conflict. A further challenge lies in determining whether teacher guidance should refine reward-based updates or provide corrective supervision for failed trajectories. To address these issues, we propose MeSD, a multi-evidence self-
distillation framework for VideoLLMs. MeSD constructs three evidence-conditioned teachers with shared parameters, using the ground-truth answer as a common semantic context while separately incorporating temporal and spatial evidence. Given the same student-generated prefixes, MeSD evaluates evidence-specific preferences relative to the Answer Teacher and fuses teacher-common preferences with gated teacher-specific residuals. Furthermore, MeSD introduces Verification-Guided Optimization to classify trajectories as Success, Failure, or Indeterminate. For Success and Indeterminate trajectories, MeSD refines
token-level advantage magnitudes while preserving reward-derived signs. For verified failure trajectories that contain the required evidence, MeSD applies failure-conditioned
distillation, using reverse-KL correction toward the fused distribution. Experiments on multiple
video benchmarks demonstrate consistent gains over reinforcement learning and self-
distillation baselines.
Read the full abstract ▾
All authors Weijie Zhu, Han Fang, Hanyu Fu, Yuzhe Zhang, Xin Wei, Zhaoyan Pan, Feiran Liu, Xunjie Jin, Hongbo Sun, Zhiyu Lin, Tianyi Gao, Tianyi Ding, Ye Yuan, Zhongjiang He, Hao Sun, Zhiheng Wu
Computer Vision
Carlotta Segna, Joel Tschesche and Anna Rohrbach
Reliable and practical audio-visual DeepFake detection requires
benchmarks that reflect diverse linguistic contexts and modern data synthesis pipelines for visual as well as audio manipulations. However, existing
datasets predominantly contain footage of English-speakers, often include outdated manipulation types, or overlook the audio modality. Further, many
datasets feature individuals who did not consent to be used in DeepFake creation. We introduce BabelFake, a
multilingual audio-visual DeepFake
benchmark recorded with consenting participants. BabelFake contains 399k clips (1,323 hours) from 496 individuals spanning five
languages (English, German, Italian, French, Spanish). Our modular data generation pipeline pairs 11 modern
video manipulation methods with 4 voice cloning engines, distinguishing visual-only (face swapping) and joint audio-visual manipulations (lip synchronization and portrait animation). By benchmarking state-of-the-art detectors, we show that detection difficulty depends on the audio-visual generation pairing, with substantial performance degradation when authentic audio is preserved. Cross-
language/demographic evaluation reveals sensitivity varying across detector architectures and training data, while human evaluation reveals that perceived realism and machine-detection difficulty do not necessarily align.
Read the full abstract ▾
Game Theory
Computing Stable Matchings under Complementarities and Preference Misalignment
Tatsuya Iwase, Baharak Rastegari, Sebastian Stein et al. (+1 more)
We study many-to-one, two-sided stable matching problems in which preferences are complementary and firms and workers may rank the same allocation differently. Here a coalition is a group of workers that can be jointly matched with a firm. With complementary preferences, a stable matching need not exist. We show that a stable matching exists for every instance when two conditions hold. The first requires each firm to have an anchor worker who is included in every feasible coalition that can be matched with that firm. The second is Transitive
Alignment, which means there must be an overall ranking across different coalitions that is consistent with the workers' preferences. We propose CDAR (Combinatorial Deferred Acceptance with Reproposals), a Deferred Acceptance-style
algorithm that permits reproposals, and prove its finite-time convergence and its output of a stable matching by constructing an $N$-digit potential function. Moreover, we show that, under strict preferences, the output of CDAR is Pareto optimal among stable matchings. The proposed framework naturally captures applications such as vehicle-route assignment for traffic safety and the misaligned interests of labor and management in wage negotiation.
Read the full abstract ▾
All authors Tatsuya Iwase, Baharak Rastegari, Sebastian Stein, Enrico H. Gerding
Computer Vision
SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic Neighborhoods
Fengming Gu, Jie Zhang, Zhongqi Wang et al. (+3 more)
Diffusion models have greatly advanced instruction-guided image editing, while also raising concerns about unauthorized image manipulation. Image immunization addresses this risk by adding imperceptible perturbations to an input image to disrupt subsequent edits. Since editing requests are unknown at image release, protection should remain effective beyond the instruction used to construct the perturbation. Existing immunization methods either require costly full-trajectory backpropagation or use intermediate objectives whose effects may be weakened by subsequent denoising. Meanwhile, a single inference path provides limited feedback about alternative denoising continuations. To address these challenges, we propose
SPIN, a framework for image immunization via one-step projection over local
stochastic trajectory neighborhoods. Starting from an early denoising state,
SPIN generates
stochastic neighboring states under the same instruction and predicts their clean latents through one-step projection without full unrolling. We then optimize a bounded input perturbation to maximize the average deviation of these predictions from a clean-edit reference, encouraging the perturbation to disrupt multiple possible editing outcomes. Experiments on two image editors demonstrate substantial gains in protection performance, with
SPIN outperforming compared methods across all six metrics under seen instructions and in the more challenging unseen instruction setting.
Read the full abstract ▾
All authors Fengming Gu, Jie Zhang, Zhongqi Wang, Qiankun Li, Shiguang Shan, Xilin Chen