Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photometrically inconsistent results across different views of the same scene. Such inconsistencies are particularly problematic for editing of 3D representations such as NeRFs or Gaussian splat models. We propose a training-free guidance framework that enforces multi-view consistency during the image editing process. The key idea is that corresponding points should look similar after editing. To achieve this, we introduce a consistency loss that guides the denoising process toward coherent edits. The framework is flexible and can be combined with widely varying image editing methods, supporting both dense and sparse multi-view editing setups. Experimental results show that our approach significantly improves 3D consistency compared to existing multi-view editing methods. We also show that this increased consistency enables high-quality Gaussian splat editing with sharp details and strong fidelity to user-specified text prompts. Please refer to our project page for video results: https://3d-consistent-editing.github.io/

Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data is a complex problem in human activity recognition, as many styles share similar poses, gestures, and temporal motion patterns. This work presents a lightweight framework for classifying dance styles that determines motion characteristics based on pose estimates extracted from videos. We propose temporal-spatial descriptors inspired by Laban Movement Analysis. These features capture local joint dynamics such as velocity, acceleration, and angular movement of the upper body, enabling a structured representation of spatial coordination. To further encode rhythmic and periodic aspects of movement, we integrate Fast Fourier Transform features that characterize movement patterns in the frequency domain. The proposed approach achieves robust classification of different dance styles with low computational effort, as complex model architectures are not required, and shows that interpretable motion representations can effectively capture stylistic nuances.

Recently, Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs), but Vision-Language Models (VLMs) still struggle with multi-step reasoning tasks due to limited multimodal reasoning data. To bridge this gap, researchers have explored methods to transfer CoT reasoning from LLMs to VLMs. However, existing approaches either need high training costs or require architectural alignment. In this paper, we use Linear Artificial Tomography (LAT) to empirically show that LLMs and VLMs share similar low-frequency latent representations of CoT reasoning despite architectural differences. Based on this insight, we propose L2V-CoT, a novel training-free latent intervention approach that transfers CoT reasoning from LLMs to VLMs. L2V-CoT extracts and resamples low-frequency CoT representations from LLMs in the frequency domain, enabling dimension matching and latent injection into VLMs during inference to enhance reasoning capabilities. Extensive experiments demonstrate that our approach consistently outperforms training-free baselines and even surpasses supervised methods.

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to ease computational/memory burdens while preserving performance, enabling MLLM deployment in resource-constrained or latency-sensitive scenarios. Current visual token pruning methods mainly rely on attention-based redundancy analysis and are tailored to dense architectures. We propose Fast Multimodal Mixture-of-Experts (FastMMoE), a training-free acceleration framework for mixture-of-experts (MoE) based MLLMs, developed from a routing analysis perspective. FastMMoE combines two complementary strategies: (i) expert activation reduction for visual tokens to minimize unnecessary expert computation; and (ii) routing-aware token pruning that leverages similarity in routing probability distributions to identify and remove highly redundant visual tokens. Experiments on large-scale MoE-MLLMs such as DeepSeek-VL2 and InternVL3.5 demonstrate that FastMMoE can reduce FLOPs by up to 55.0% while retaining approximately 95.5% of the original performance, consistently outperforming dense-model pruning baselines including FastV and SparseVLM across multiple retention rates.

We present FORWARD, a high-resolution multimodal dataset of a cut-to-length forwarder operating in rough terrain on two harvest sites in the middle part of Sweden. The forwarder is a large Komatsu model equipped with vehicle telematics sensors, including global positioning via satellite navigation, movement sensors, accelerometers, and engine sensors. The forwarder was additionally equipped with cameras, operator vibration sensors, and multiple IMUs. The data includes event time logs recorded at 5 Hz of driving speed, fuel consumption, machine position with centimeter accuracy, and crane use while the forwarder operates in forest areas, aerially laser-scanned with a resolution of around 1500 points per square meter. Production log files (Stanford standard) with time-stamped machine events, extensive video material, and terrain data in various formats are included as well. About 18 hours of regular wood extraction work during three days is annotated from 360-video material into individual work elements and included in the dataset. We also include scenario specifications of conducted experiments on forest roads and in terrain. Scenarios include repeatedly driving the same routes with and without steel tracks, different load weights, and different target driving speeds. The dataset is intended for developing models and algorithms for trafficability, perception, and autonomous control of forest machines using artificial intelligence, simulation, and experiments on physical testbeds. In part, we focus on forwarders traversing terrain, avoiding or handling obstacles, and loading or unloading logs, with consideration for efficiency, fuel consumption, safety, and environmental impact. Other benefits of the open dataset include the ability to explore auto-generation and calibration of forestry machine simulators and automation scenario descriptions using the data recorded in the field.

The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement Learning (RL), encounters critical efficiency bottlenecks: response generation during RL training exhibits a persistent long-tail distribution, where a few very long responses dominate execution time, wasting resources and inflating costs. To address this, we propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding. Applying speculative decoding in RL is challenging due to the dynamic workloads, evolving target model, and draft model training overhead. TLT overcomes these obstacles with two synergistic components: (1) Adaptive Drafter, a lightweight draft model trained continuously on idle GPUs during long-tail generation to maintain alignment with the target model at no extra cost; and (2) Adaptive Rollout Engine, which maintains a memory-efficient pool of pre-captured CUDAGraphs and adaptively select suitable SD strategies for each input batch. Evaluations demonstrate that TLT achieves over 1.7x end-to-end RL training speedup over state-of-the-art systems, preserves the model accuracy, and yields a high-quality draft model as a free byproduct suitable for efficient deployment. Code is released at https://github.com/mit-han-lab/fastrl.

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge of catastrophic forgetting, where learning new tasks leads to performance degradation on previous ones. In this paper, we introduce a novel insight into catastrophic forgetting by conceptualizing it as a problem of missing gradients from old tasks during new task learning. Our approach approximates these missing gradients by leveraging the geometric properties of the parameter space, specifically using the directional vector between current parameters and previously optimal parameters as gradient guidance. This approximated gradient can be further integrated with real gradients from a limited replay buffer and regulated by a Bernoulli sampling strategy that dynamically balances model stability and plasticity. Extensive experiments on multimodal continual instruction tuning datasets demonstrate that our method achieves state-of-the-art performance without model expansion, effectively mitigating catastrophic forgetting while maintaining a compact architecture.

Supervised learning relies on high-quality labeled data, but obtaining such data through human annotation is both expensive and time-consuming. Recent work explores using large language models (LLMs) for annotation, but LLM-generated labels still fall short of human-level quality. To address this problem, we propose the Annotation with Critical Thinking (ACT) data pipeline, where LLMs serve not only as annotators but also as judges to critically identify potential errors. Human effort is then directed towards reviewing only the most "suspicious" cases, significantly improving the human annotation efficiency. Our major contributions are as follows: (1) ACT is applicable to a wide range of domains, including natural language processing (NLP), computer vision (CV), and multimodal understanding, by leveraging multimodal-LLMs (MLLMs). (2) Through empirical studies, we derive 7 insights on how to enhance annotation quality while efficiently reducing the human cost, and then translate these findings into user-friendly guidelines. (3) We theoretically analyze how to modify the loss function so that models trained on ACT data achieve similar performance to those trained on fully human-annotated data. Our experiments show that the performance gap can be reduced to less than 2% on most benchmark datasets while saving up to 90% of human costs.

Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we introduce HalluClean, a lightweight and task-agnostic framework for detecting and correcting hallucinations in LLM-generated text. HalluClean adopts a reasoning-enhanced paradigm, explicitly decomposing the process into planning, execution, and revision stages to identify and refine unsupported claims. It employs minimal task-routing prompts to enable zero-shot generalization across diverse domains, without relying on external knowledge sources or supervised detectors. We conduct extensive evaluations on five representative tasks-question answering, dialogue, summarization, math word problems, and contradiction detection. Experimental results show that HalluClean significantly improves factual consistency and outperforms competitive baselines, demonstrating its potential to enhance the trustworthiness of LLM outputs in real-world applications.

Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation.

Chronic pain is a global health challenge affecting millions of individuals, making it essential for physicians to have reliable and objective methods to measure the functional impact of clinical treatments. Traditionally used methods, like the numeric rating scale, while personalized and easy to use, are subjective due to their self-reported nature. Thus, this paper proposes DETECT (Data-Driven Evaluation of Treatments Enabled by Classification Transformers), a data-driven framework that assesses treatment success by comparing patient activities of daily life before and after treatment. We use DETECT on public benchmark datasets and simulated patient data from smartphone sensors. Our results demonstrate that DETECT is objective yet lightweight, making it a significant and novel contribution to clinical decision-making. By using DETECT, independently or together with other self-reported metrics, physicians can improve their understanding of their treatment impacts, ultimately leading to more personalized and responsive patient care.

We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while self-supervised methods allow incomplete ground truth but typically rely on random sampling that, in expectation, covers the entire image. In contrast, we consider fixed, deterministic sampling patterns with inherently incomplete coverage, even in expectation. To overcome this limitation, we exploit multiple invariances of the underlying image distribution, which theoretically allows us to achieve the same reconstruction performance as fully supervised approaches. We validate our method on optical-resolution image upsampling in photoacoustic microscopy (PAM), demonstrating competitive or superior results while requiring substantially less ground truth data.

Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods often rely on task-specific deep learning models trained on manually labeled datasets, which are costly to build and limited in generalizability. While recent Multimodal Large Language Models (MLLMs) offer broad real-world knowledge and policy understanding, they struggle to reason over fine-grained visual details and apply structured compliance rules effectively on their own. In this paper, we propose CompAgent, the first agentic framework for visual compliance verification. CompAgent augments MLLMs with a suite of visual tools-such as object detectors, face analyzers, NSFW detectors, and captioning models-and introduces a planning agent that dynamically selects appropriate tools based on the compliance policy. A compliance verification agent then integrates image, tool outputs, and policy context to perform multimodal reasoning. Experiments on public benchmarks show that CompAgent outperforms specialized classifiers, direct MLLM prompting, and curated routing baselines, achieving up to 76% F1 score and a 10% improvement over the state-of-the-art on the UnsafeBench dataset. Our results demonstrate the effectiveness of agentic planning and robust tool-augmented reasoning for scalable, accurate, and adaptable visual compliance verification.

The pursuit of efficient Large Language Models (LLMs) has led to increasingly complex techniques like extreme quantization and dynamic routing. While individual benefits of these methods are well-documented, their compositional effects remain poorly understood. This paper introduces BitSkip, a hybrid architectural framework for systematically exploring these interactions. Counter-intuitively, our findings reveal that a simple 8-bit quantized model without Hadamard transform (BitSkip-V1) not only outperforms its more complex 4-bit and Hadamard-enhanced counterparts but also competes the full-precision baseline in quality (perplexity of 1.13 vs 1.19) . The introduction of Hadamard transforms, even at 8-bit precision, catastrophically degraded performance by over 37,000%, tracing fundamental training instability. Our BitSkip-V1 recipe demonstrates superior early-exit characteristics, with layer 18 providing optimal 32.5% speed gain for minimal 4% quality loss.

Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectively approximated as linear directions in the latent space. Existing bias evaluation methods rely on predefined attribute labels, synthetic counterfactuals, or proximity-based clustering, all of which fail to capture intersectional subpopulations that emerge along latent directions. We introduce LatentAlign, an attribute-free algorithm that discovers semantically coherent and interpretable subpopulations by iteratively aligning embeddings along dominant latent directions. Unlike distance-based clustering, LatentAlign exploits the geometry of hyperspherical embeddings to isolate directional structures shared across identities, allowing for the interpretable discovery of attributes. Across four state-of-the-art recognition backbones (ArcFace, CosFace, ElasticFace, PartialFC) and two benchmarks (RFW, CelebA), LatentAlign consistently yields more semantically coherent groups than $k$-means, spherical $k$-means, nearest-neighbor search, and DBSCAN. Crucially, the discovered subpopulations expose severe intersectional vulnerabilities, with False Match Rates up to 4x higher than groups defined by explicit annotations. Our results show that by treating semantic attributes as directional features rather than spatial clusters, we can effectively isolate intersectional subpopulations and expose hidden biases that standard audits miss.

Axioms are a feature of the Planning Domain Definition Language PDDL that can be considered as a generalization of database query languages such as Datalog. The PDDL standard restricts negative occurrences of predicates in axiom bodies to predicates that are directly set by actions and not derived by axioms. In the literature, authors often deviate from this limitation and only require that the set of axioms is stratifiable. We show that both variants can express exactly the same queries as least fixed point logic. They are thus strictly more expressive than stratified Datalog, which aligns with another restriction on axioms occasionally considered in the planning literature. Complementing this theoretical analysis, we also present a compilation that eliminates negative occurrences of derived predicates from PDDL axioms.

We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation backlogs in financial services, where millions of customer utterances require accurate categorization, MAFA combines specialized agents with structured reasoning and a judge-based consensus mechanism. Our framework uniquely supports dynamic task adaptation, allowing organizations to define custom annotation types (FAQs, intents, entities, or domain-specific categories) through configuration rather than code changes. Deployed at JP Morgan Chase, MAFA has eliminated a 1 million utterance backlog while achieving, on average, 86% agreement with human annotators, annually saving over 5,000 hours of manual annotation work. The system processes utterances with annotation confidence classifications, which are typically 85% high, 10% medium, and 5% low across all datasets we tested. This enables human annotators to focus exclusively on ambiguous and low-coverage cases. We demonstrate MAFA's effectiveness across multiple datasets and languages, showing consistent improvements over traditional and single-agent annotation baselines: 13.8% higher Top-1 accuracy, 15.1% improvement in Top-5 accuracy, and 16.9% better F1 in our internal intent classification dataset and similar gains on public benchmarks. This work bridges the gap between theoretical multi-agent systems and practical enterprise deployment, providing a blueprint for organizations facing similar annotation challenges.

Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores a fundamentally different, neuro-inspired paradigm for 6-DoF grasp detection. We introduce SpikeGrasp, a framework that mimics the biological visuomotor pathway, processing raw, asynchronous events from stereo spike cameras, similarly to retinas, to directly infer grasp poses. Our model fuses these stereo spike streams and uses a recurrent spiking neural network, analogous to high-level visual processing, to iteratively refine grasp hypotheses without ever reconstructing a point cloud. To validate this approach, we built a large-scale synthetic benchmark dataset. Experiments show that SpikeGrasp surpasses traditional point-cloud-based baselines, especially in cluttered and textureless scenes, and demonstrates remarkable data efficiency. By establishing the viability of this end-to-end, neuro-inspired approach, SpikeGrasp paves the way for future systems capable of the fluid and efficient manipulation seen in nature, particularly for dynamic objects.

Accurate face parsing under extreme viewing angles remains a significant challenge due to limited labeled data in such poses. Manual annotation is costly and often impractical at scale. We propose a novel label refinement pipeline that leverages 3D Gaussian Splatting (3DGS) to generate accurate segmentation masks from noisy multiview predictions. By jointly fitting two 3DGS models, one to RGB images and one to their initial segmentation maps, our method enforces multiview consistency through shared geometry, enabling the synthesis of pose-diverse training data with only minimal post-processing. Fine-tuning a face parsing model on this refined dataset significantly improves accuracy on challenging head poses, while maintaining strong performance on standard views. Extensive experiments, including human evaluations, demonstrate that our approach achieves superior results compared to state-of-the-art methods, despite requiring no ground-truth 3D annotations and using only a small set of initial images. Our method offers a scalable and effective solution for improving face parsing robustness in real-world settings.

The rapid growth of scientific publications has made it increasingly difficult to keep literature reviews comprehensive and up-to-date. Though prior work has focused on automating retrieval and screening, the writing phase of systematic reviews remains largely under-explored, especially with regard to readability and factual accuracy. To address this, we present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process. LiRA utilizes specialized agents for content outlining, subsection writing, editing, and reviewing, producing cohesive and comprehensive review articles. Evaluated on SciReviewGen and a proprietary ScienceDirect dataset, LiRA outperforms current baselines such as AutoSurvey and MASS-Survey in writing and citation quality, while maintaining competitive similarity to human-written reviews. We further evaluate LiRA in real-world scenarios using document retrieval and assess its robustness to reviewer model variation. Our findings highlight the potential of agentic LLM workflows, even without domain-specific tuning, to improve the reliability and usability of automated scientific writing.

Improved prediction of personalized health outcomes -- such as sleep quality and stress -- from multimodal lifelog data could have meaningful clinical and practical implications. However, state-of-the-art models, primarily deep neural networks and gradient-boosted ensembles, sacrifice interpretability and fail to adequately address the significant inter-individual variability inherent in lifelog data. To overcome these challenges, we propose the Subject-Adaptive Sparse Linear (SASL) framework, an interpretable modeling approach explicitly designed for personalized health prediction. SASL integrates ordinary least squares regression with subject-specific interactions, systematically distinguishing global from individual-level effects. We employ an iterative backward feature elimination method based on nested $F$-tests to construct a sparse and statistically robust model. Additionally, recognizing that health outcomes often represent discretized versions of continuous processes, we develop a regression-then-thresholding approach specifically designed to maximize macro-averaged F1 scores for ordinal targets. For intrinsically challenging predictions, SASL selectively incorporates outputs from compact LightGBM models through confidence-based gating, enhancing accuracy without compromising interpretability. Evaluations conducted on the CH-2025 dataset -- which comprises roughly 450 daily observations from ten subjects -- demonstrate that the hybrid SASL-LightGBM framework achieves predictive performance comparable to that of sophisticated black-box methods, but with significantly fewer parameters and substantially greater transparency, thus providing clear and actionable insights for clinicians and practitioners.

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.

Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates this issue, yet existing approaches face limitations. Attention-based methods rely on raw attention scores, which are often unstable across layers and heads and can lead to redundant selections. Diversity-based methods improve robustness by selecting tokens far apart in feature space, but risk dropping regions needed for accurate prediction. We propose ZOO-Prune, a training-free framework built on the intuition that highly sensitive tokens have a stronger influence on the model's output and capture complementary visual cues rather than redundant ones. To achieve this, we estimate token sensitivity using zeroth-order perturbations at the lightweight projection layer. This measures how small random perturbations affect the projected features and enables efficient approximation of each token's influence without backpropagation. Extensive experiments across multiple VLMs and benchmarks show that ZOO-Prune consistently outperforms prior methods while pruning up to 94.4% of tokens without sacrificing accuracy. Our method also improves efficiency, reaching up to 2.30x faster end-to-end inference compared to the baseline.

Policy evaluation is a core component of many reinforcement learning (RL) algorithms and a critical tool for ensuring safe deployment of RL policies. However, existing policy evaluation methods often suffer from high variance or bias. To address these issues, we introduce Evaluation-Aware Reinforcement Learning (EvA-RL), a general policy learning framework that considers evaluation accuracy at train-time, as opposed to standard post-hoc policy evaluation methods. Specifically, EvA-RL directly optimizes policies for efficient and accurate evaluation, in addition to being performant. We provide an instantiation of EvA-RL and demonstrate through a combination of theoretical analysis and empirical results that EvA-RL effectively trades off between evaluation accuracy and expected return. Finally, we show that the evaluation-aware policy and the evaluation mechanism itself can be co-learned to mitigate this tradeoff, providing the evaluation benefits without significantly sacrificing policy performance. This work opens a new line of research that elevates reliable evaluation to a first-class principle in reinforcement learning.

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables efficient problem solving in complex environments. In robotics, abstractions and hierarchical reasoning have long been central to planning, yet they are typically hand-engineered, demanding significant human effort and limiting scalability. Automating the discovery of useful abstractions directly from visual data would make planning frameworks more scalable and more applicable to real-world robotic domains. In this work, we focus on rearrangement tasks where the state is represented with raw images, and propose a method to induce discrete, graph-structured abstractions by combining structural constraints with an attention-guided visual distance. Our approach leverages the inherent bipartite structure of rearrangement problems, integrating structural constraints and visual embeddings into a unified framework. This enables the autonomous discovery of abstractions from vision alone, which can subsequently support high-level planning. We evaluate our method on two rearrangement tasks in simulation and show that it consistently identifies meaningful abstractions that facilitate effective planning and outperform existing approaches.

The silhouette coefficient quantifies, for each observation, the balance between within-cluster cohesion and between-cluster separation, taking values in the range [-1,1]. The average silhouette width (ASW) is a widely used internal measure of clustering quality, with higher values indicating more cohesive and well-separated clusters. However, the dataset-specific maximum of ASW is typically unknown, and the standard upper limit of 1 is rarely attainable. In this work, we derive for each data point a sharp upper bound on its silhouette width and aggregate these to obtain a canonical upper bound for the ASW. This bound-often substantially below 1-enhances the interpretability of empirical ASW values by providing guidance on how close a given clustering result is to the best possible outcome for that dataset. We evaluate the usefulness of the upper bound on a variety of datasets and conclude that it can meaningfully enrich cluster quality evaluation; however, its practical relevance depends on the specific dataset. Finally, we extend the framework to establish an upper bound for the macro-averaged silhouette.

The effectiveness of Large Language Models (LLMs) diminishes for extremely low-resource languages, such as indigenous languages, primarily due to the lack of labeled data. Despite growing interest, the availability of high-quality natural language processing (NLP) datasets for these languages remains limited, making it difficult to develop robust language technologies. This paper addresses such gap by focusing on Ladin, an endangered Romance language, specifically targeting the Val Badia variant. Leveraging a small set of parallel Ladin-Italian sentence pairs, we create synthetic datasets for sentiment analysis and multiple-choice question answering (MCQA) by translating monolingual Italian data. To ensure linguistic quality and reliability, we apply rigorous filtering and back-translation procedures in our method. We further demonstrate that incorporating these synthetic datasets into machine translation training leads to substantial improvements over existing Italian-Ladin translation baselines. Our contributions include the first publicly available sentiment analysis and MCQA datasets for Ladin, establishing foundational resources that can support broader NLP research and downstream applications for this underrepresented language.

Subgraph Federated Learning (FL) aims to train Graph Neural Networks (GNNs) across distributed private subgraphs, but it suffers from severe data heterogeneity. To mitigate data heterogeneity, weighted model aggregation personalizes each local GNN by assigning larger weights to parameters from clients with similar subgraph characteristics inferred from their current model states. However, the sparse and biased subgraphs often trigger rapid overfitting, causing the estimated client similarity matrix to stagnate or even collapse. As a result, aggregation loses effectiveness as clients reinforce their own biases instead of exploiting diverse knowledge otherwise available. To this end, we propose a novel personalized subgraph FL framework called Curriculum guided personalized sUbgraph Federated Learning (CUFL). On the client side, CUFL adopts Curriculum Learning (CL) that adaptively selects edges for training according to their reconstruction scores, exposing each GNN first to easier, generic cross-client substructures and only later to harder, client-specific ones. This paced exposure prevents early overfitting to biased patterns and enables gradual personalization. By regulating personalization, the curriculum also reshapes server aggregation from exchanging generic knowledge to propagating client-specific knowledge. Further, CUFL improves weighted aggregation by estimating client similarity using fine-grained structural indicators reconstructed on a random reference graph. Extensive experiments on six benchmark datasets confirm that CUFL achieves superior performance compared to relevant baselines. Code is available at https://github.com/Kang-Min-Ku/CUFL.git.

Discrete Element Method (DEM) simulations of granular media are computationally intensive, particularly during initialization phases dominated by large displacements and kinetic energy. This paper presents a novel generative pipeline based on 3D diffusion models that directly synthesizes arbitrarily large granular assemblies in mechanically realistic configurations. The approach employs a two-stage pipeline. First, an unconditional diffusion model generates independent 3D voxel grids representing granular media; second, a 3D inpainting model, adapted from 2D techniques using masked inputs and repainting strategies, seamlessly stitches these grids together. The inpainting model uses the outputs of the unconditional diffusion model to learn from the context of adjacent generations and creates new regions that blend smoothly into the context region. Both models are trained on binarized 3D occupancy grids derived from a database of small-scale DEM simulations, scaling linearly with the number of output voxels. Simulations that spanned over days can now run in hours, practically enabling simulations containing more than 200k ballast particles. The pipeline remains fully compatible with existing DEM workflows as it post-processes the diffusion generated voxel grids into DEM compatible particle meshes. Being mechanically consistent on key granulometry metrics with the original DEM simulations, the pipeline is also compatible with many other applications in the field of granular media, with capability of generating both convex and non-convex particles. Showcased on two examples (railway ballast and lunar regolith), the pipeline reimagines the way initialization of granular media simulations is performed, enabling scales of generation previously unattainable with traditional DEM simulations.

LLMs have recently been used to generate Python programs representing generalized plans in PDDL planning, i.e., plans that generalize across the tasks of a given PDDL domain. Previous work proposed a framework consisting of three steps: the LLM first generates a summary and then a strategy for the domain, both in natural language, and then implements that strategy as a Python program, that gets debugged on example planning tasks. In that work, only one strategy is generated and passed directly to the program generation. If the strategy is incorrect, its implementation will therefore result in an incorrect generalized plan. Here, we introduce an approach that generates the strategy in the form of pseudocode and enables automatic debugging of the pseudocode, hence allowing us to identify and fix errors prior to the generation of the generalized plan itself. Additionally, we extend the Python debugging phase with a reflection step prompting the LLM to pinpoint the reason for the observed plan failure. Finally, we take inspiration from LLM code generation to produce several program variants and pick the best one. Running experiments on 17 benchmark domains with two reasoning and two non-reasoning LLMs, we show that these extensions substantially improve the quality of the generalized plans. Our best performing configuration achieves an average coverage of 82% across the domains.