arXiv:2508.06904v3 Announce Type: replace 
Abstract: Training-free Camouflaged Object Segmentation (COS) seeks to segment camouflaged objects without task-specific training, by automatically generating visual prompts to guide the Segment Anything Model (SAM). However, existing pipelines mostly yield semantic-level prompts, which drive SAM to coarse semantic masks and struggle to handle multiple discrete camouflaged instances effectively. To address this critical limitation, we propose an \textbf{I}nstance-\textbf{A}ware \textbf{P}rompting \textbf{F}ramework (IAPF) tailored for the first training-free COS that upgrades prompt granularity from semantic to instance-level while keeping all components frozen. The centerpiece is an Instance Mask Generator that (i) leverages a detector-agnostic enumerator to produce precise instance-level box prompts for the foreground tag, and (ii) introduces the Single-Foreground Multi-Background Prompting (SFMBP) strategy to sample region-constrained point prompts within each box prompt, enabling SAM to output instance masks. The pipeline is supported by a simple text prompt generator that produces image-specific tags and a self-consistency vote across synonymous task-generic prompts to stabilize inference. Extensive evaluations on three COS benchmarks, two CIS benchmarks, and two downstream datasets demonstrate state-of-the-art performance among training-free methods. Code will be released upon acceptance.

تم تقديم إطار جديد لتجزئة الكائنات المتخفية بدون تدريب، مما يحسن من تجزئة الكائنات المتخفية دون الحاجة إلى تدريب مسبق. يعمل إطار التحفيز الواعي بالنسخ (IAPF) على تحسين دقة التحفيز من المستوى الدلالي إلى مستوى النسخ، مما يسمح لنموذج Segment Anything (SAM) بإنتاج أقنعة نسخ أكثر دقة. تعتبر هذه الخطوة مهمة لأنها تعالج القيود في الأساليب الحالية وتظهر أداءً متفوقًا في مهام التجزئة.

Se ha introducido un nuevo marco para la Segmentación de Objetos Camuflados (COS) sin entrenamiento, mejorando la segmentación de objetos camuflados sin formación previa. El Marco de Promoción Consciente de Instancias (IAPF) mejora la granularidad de los prompts de nivel semántico a nivel de instancia, permitiendo que el Modelo Segment Anything (SAM) produzca máscaras de instancia más precisas. Este avance es significativo ya que aborda las limitaciones de los métodos existentes y demuestra un rendimiento de vanguardia en las tareas de COS.

Un nouveau cadre pour la segmentation d'objets camouflés sans entraînement a été introduit, améliorant la segmentation d'objets camouflés sans formation préalable. Le cadre de prompting conscient des instances (IAPF) améliore la granularité des prompts, passant du sémantique au niveau des instances, permettant au modèle Segment Anything (SAM) de produire des masques d'instances plus précis. Cette avancée est significative car elle répond aux limitations des méthodes existantes et démontre des performances de pointe dans les tâches de COS.

A new framework for Training-free Camouflaged Object Segmentation (COS) has been introduced, enhancing the segmentation of camouflaged objects without prior training. The Instance-Aware Prompting Framework (IAPF) improves prompt granularity from semantic to instance-level, allowing the Segment Anything Model (SAM) to produce more accurate instance masks. This advancement is significant as it addresses limitations in existing methods and demonstrates state-of-the-art performance in COS tasks.

An Instance-Aware Prompting Framework for Training-free Camouflaged Object Segmentation

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

arXiv:2505.10769v2 Announce Type: replace 
Abstract: Accurate segmentation of regions of interest in biomedical images holds substantial value in image analysis. Although several foundation models for biomedical segmentation have currently achieved excellent performance on certain datasets, they typically demonstrate sub-optimal performance on unseen domain data. We owe the deficiency to lack of vision-language knowledge before segmentation. Multimodal Large Language Models (MLLMs) bring outstanding understanding and reasoning capabilities to multimodal tasks, which inspires us to leverage MLLMs to inject Vision-Language Knowledge (VLK), thereby enabling vision models to demonstrate superior generalization capabilities on cross-domain datasets. In this paper, we propose a novel framework that seamlessly uses MLLMs to guide SAM in learning microscopy cross-domain data, unifying Segment Anything in Microscopy, named uLLSAM. Specifically, we propose the Vision-Language Semantic Alignment (VLSA) module, which injects VLK into Segment Anything Model (SAM). We find that after SAM receives global VLK prompts, its performance improves significantly, but there are deficiencies in boundary contour perception. Therefore, we further propose Semantic Boundary Regularization (SBR) to regularize SAM. Our method achieves performance improvements of 11.8% in SA across 9 in-domain microscopy datasets, achieving state-of-the-art performance. Our method also demonstrates improvements of 9.2% in SA across 10 out-of-domain datasets, exhibiting strong generalization capabilities. Code is available at https://github.com/ieellee/uLLSAM.

تناقش الورقة المعنونة 'توحيد نموذج تقسيم أي شيء في المجهر باستخدام المعرفة بين الرؤية واللغة' أهمية التقسيم الدقيق في الصور الطبية الحيوية. تبرز الورقة قيود النماذج الحالية في التعامل مع بيانات المجالات غير المرئية بسبب نقص المعرفة بين الرؤية واللغة. يقترح المؤلفون إطارًا جديدًا، uLLSAM، الذي يستخدم نماذج اللغة متعددة الوسائط (MLLMs) لتعزيز أداء التقسيم. تهدف هذه الطريقة إلى تحسين قدرات التعميم عبر مجموعات البيانات بين المجالات.

El artículo titulado 'Unifying Segment Anything in Microscopy with Vision-Language Knowledge' discute la importancia de la segmentación precisa en imágenes biomédicas. Destaca las limitaciones de los modelos existentes para manejar datos de dominio no vistos debido a la falta de conocimiento visión-lenguaje. Los autores proponen un nuevo marco, uLLSAM, que utiliza Modelos de Lenguaje Multimodal (MLLMs) para mejorar el rendimiento de la segmentación. Este enfoque busca mejorar las capacidades de generalización en conjuntos de datos inter-dominio.

L'article intitulé 'Unifying Segment Anything in Microscopy with Vision-Language Knowledge' aborde l'importance de la segmentation précise dans les images biomédicales. Il met en lumière les limites des modèles existants pour traiter des données de domaine non vues en raison d'un manque de connaissance vision-langage. Les auteurs proposent un nouveau cadre, uLLSAM, qui utilise des modèles de langage multimodaux (MLLMs) pour améliorer la performance de segmentation. Cette approche vise à améliorer les capacités de généralisation sur des ensembles de données inter-domaines.

The paper titled 'Unifying Segment Anything in Microscopy with Vision-Language Knowledge' discusses the importance of accurate segmentation in biomedical images. It highlights the limitations of existing models in handling unseen domain data due to a lack of vision-language knowledge. The authors propose a new framework, uLLSAM, which utilizes Multimodal Large Language Models (MLLMs) to enhance segmentation performance. This approach aims to improve generalization capabilities across cross-domain datasets, achieving notable performance improvements.

An Instance-Aware Prompting Framework for Training-free Camouflaged Object Segmentation

Was this article worth reading? Share it