Transformer
-
Neuron-Aware Data Selection In Instruction Tuning For Large Language Models
2026-03-13 17:39:03Xin Chen, Junchao Wu, Shu Yang, Runzhe Zhan, Zeyu Wu, Min Yang, Shujian Huang, Lidia S. Chao, Derek F. WongAbstract
Instruction Tuning (IT) has been proven to be an effective approach to unlock the powerful capabilities of large language models (LLMs). Recent studies indicate that excessive IT data can degrade LLMs performance, while carefully selecting a small subset of high-quality IT data can significantly enhance their capabilities. Therefore, identifying the most efficient subset data from the IT dataset to effectively develop either specific or general abilities in LLMs has become a critical challenge. To address this, we propose a novel and efficient framework called NAIT. NAIT evaluates the impact of IT data on LLMs performance by analyzing the similarity of neuron activation patterns between the IT dataset and the target domain capability. Specifically, NAIT captures neuron activation patterns from in-domain datasets of target domain capabilities to construct reusable and transferable neuron activation features. It then evaluates and selects optimal samples based on the similarity between candidate samples and the expected activation features of the target capabilities. Experimental results show that training on the 10\% Alpaca-GPT4 IT data subset selected by NAIT consistently outperforms methods that rely on external advanced models or uncertainty-based features across various tasks. Our findings also reveal the transferability of neuron activation features across different capabilities of LLMs. In particular, IT data with more logical reasoning and programmatic features possesses strong general transferability, enabling models to develop stronger capabilities across multiple tasks, while a stable core subset of data is sufficient to consistently activate fundamental model capabilities and universally improve performance across diverse tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13201
PDF
-
Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos
2026-03-13 17:18:03Rohith Peddi, Saurabh, Shravan Shanmugam, Likhitha Pallapothula, Yu Xiang, Parag Singla, Vibhav GogateAbstract
Spatio-temporal scene graphs provide a principled representation for modeling evolving object interactions, yet existing methods remain fundamentally frame-centric: they reason only about currently visible objects, discard entities upon occlusion, and operate in 2D. To address this, we first introduce ActionGenome4D, a dataset that upgrades Action Genome videos into 4D scenes via feed-forward 3D reconstruction, world-frame oriented bounding boxes for every object involved in actions, and dense relationship annotations including for objects that are temporarily unobserved due to occlusion or camera motion. Building on this data, we formalize World Scene Graph Generation (WSGG), the task of constructing a world scene graph at each timestamp that encompasses all interacting objects in the scene, both observed and unobserved. We then propose three complementary methods, each exploring a different inductive bias for reasoning about unobserved objects: PWG (Persistent World Graph), which implements object permanence via a zero-order feature buffer; MWAE (Masked World Auto-Encoder), which reframes unobserved-object reasoning as masked completion with cross-view associative retrieval; and 4DST (4D Scene Transformer), which replaces the static buffer with differentiable per-object temporal attention enriched by 3D motion and camera-pose features. We further design and evaluate the performance of strong open-source Vision-Language Models on the WSGG task via a suite of Graph RAG-based approaches, establishing baselines for unlocalized relationship prediction. WSGG thus advances video scene understanding toward world-centric, temporally persistent, and interpretable scene reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13185
PDF
-
MXNorm: Reusing MXFP block scales for efficient tensor normalisation
2026-03-13 17:14:06Callum McLean, Luke Y. Prince, Alexandre Payot, Paul Balan\c{c}a, Carlo LuschiAbstract
Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelerators that use increasingly low-precision number formats. However, improvements in matrix multiplication performance have far outstripped improvements in performance on reductions and elementwise computations, which are still being performed in higher precision. In this work, we propose MXNorm, a drop-in replacement for RMSNorm that estimates the RMS using only the block scales calculated as part of the MXFP8 cast and enables a 32x decrease in the size of reduction needed for normalization. We validate our approximation method on pre-training of Llama 3 models of 125M, 1B and 8B parameters, finding minimal loss of training accuracy compared to a baseline using RMSNorm with MXFP8 matmuls. We also show practical kernel speedups using only this http URL of up to 2.4x for MXNorm over RMSNorm, corresponding to a 1.3% speedup in Llama 3 8B transformer layers in MXFP8 and a 2.6% speedup in NVFP4.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13180
PDF
-
Semantic Invariance in Agentic AI
2026-03-13 17:08:44I. de Zarz\`a, J. de Curt\`o, Jordi Cabot, Pietro Manzoni, Carlos T. CalafateAbstract
Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordination systems. However, deploying LLM agents in consequential applications requires assurance that their reasoning remains stable under semantically equivalent input variations, a property we term semantic this http URL benchmark evaluations, which assess accuracy on fixed, canonical problem formulations, fail to capture this critical reliability dimension. To address this shortcoming, in this paper we present a metamorphic testing framework for systematically assessing the robustness of LLM reasoning agents, applying eight semantic-preserving transformations (identity, paraphrase, fact reordering, expansion, contraction, academic context, business context, and contrastive formulation) across seven foundation models spanning four distinct architectural families: Hermes (70B, 405B), Qwen3 (30B-A3B, 235B-A22B), DeepSeek-R1, and gpt-oss (20B, 120B). Our evaluation encompasses 19 multi-step reasoning problems across eight scientific domains. The results reveal that model scale does not predict robustness: the smaller Qwen3-30B-A3B achieves the highest stability (79.6% invariant responses, semantic similarity 0.91), while larger models exhibit greater fragility.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13173
PDF
-
Towards Faithful Multimodal Concept Bottleneck Models
2026-03-13 16:56:08Pierre Moreau, Emeline Pineau Ferrand, Yann Choho, Benjamin Wong, Annabelle Blangero, Milan BhanAbstract
Concept Bottleneck Models (CBMs) are interpretable models that route predictions through a layer of human-interpretable concepts. While widely studied in vision and, more recently, in NLP, CBMs remain largely unexplored in multimodal settings. For their explanations to be faithful, CBMs must satisfy two conditions: concepts must be properly detected, and concept representations must encode only their intended semantics, without smuggling extraneous task-relevant or inter-concept information into final predictions, a phenomenon known as leakage. Existing approaches treat concept detection and leakage mitigation as separate problems, and typically improve one at the expense of predictive accuracy. In this work, we introduce f-CBM, a faithful multimodal CBM framework built on a vision-language backbone that jointly targets both aspects through two complementary strategies: a differentiable leakage loss to mitigate leakage, and a Kolmogorov-Arnold Network prediction head that provides sufficient expressiveness to improve concept detection. Experiments demonstrate that f-CBM achieves the best trade-off between task accuracy, concept detection, and leakage reduction, while applying seamlessly to both image and text or text-only datasets, making it versatile across modalities.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13163
PDF
-
DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
2026-03-13 16:56:00Junqi Shi, Ming Lu, Xingchen Li, Anle Ke, Ruiqi Zhang, Zhan MaAbstract
Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where hierarchical downsampling forces diffusion to operate in shallow latent spaces (typically with only 8x spatial downscaling), resulting in excessive computation. In contrast, conventional VAE-based codecs work in much deeper latent domains (16x - 64x downscaled), motivating a key question: Can diffusion operate effectively in such compact latent spaces without compromising reconstruction quality? To address this, we introduce DiT-IC, an Aligned Diffusion Transformer for Image Compression, which replaces the U-Net with a Diffusion Transformer capable of performing diffusion in latent space entirely at 32x downscaled resolution. DiT-IC adapts a pretrained text-to-image multi-step DiT into a single-step reconstruction model through three key alignment mechanisms: (1) a variance-guided reconstruction flow that adapts denoising strength to latent uncertainty for efficient reconstruction; (2) a self-distillation alignment that enforces consistency with encoder-defined latent geometry to enable one-step diffusion; and (3) a latent-conditioned guidance that replaces text prompts with semantically aligned latent conditions, enabling text-free inference. With these designs, DiT-IC achieves state-of-the-art perceptual quality while offering up to 30x faster decoding and drastically lower memory usage than existing diffusion-based codecs. Remarkably, it can reconstruct 2048x2048 images on a 16 GB laptop GPU.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13162
PDF
-
Geometry-Guided Camera Motion Understanding in VideoLLMs
2026-03-13 16:13:09Haoan Feng, Sri Harsha Musunuri, Guan-Ming SuAbstract
Camera motion is a fundamental geometric signal that shapes visual perception and cinematic style, yet current video-capable vision-language models (VideoLLMs) rarely represent it explicitly and often fail on fine-grained motion primitives. We address this gap with a framework of $\textbf{benchmarking}$, $\textbf{diagnosis}$, and $\textbf{injection}$. We curate $\textbf{CameraMotionDataset}$, a large-scale synthetic dataset with explicit camera control, formulate camera motion as constraint-aware multi-label recognition, and construct a VQA benchmark--$\textbf{CameraMotionVQA}$. Across diverse off-the-shelf VideoLLMs, we observe substantial errors in recognizing camera motion primitives. Probing experiments on a Qwen2.5-VL vision encoder suggest that camera motion cues are weakly represented, especially in deeper ViT blocks, helping explain the observed failure modes. To bridge this gap without costly training or fine-tuning, we propose a lightweight, model-agnostic pipeline that extracts geometric camera cues from 3D foundation models (3DFMs), predicts constrained motion primitives with a temporal classifier, and injects them into downstream VideoLLM inference via structured prompting. Experiments demonstrate improved motion recognition and more camera-aware model responses, highlighting geometry-driven cue extraction and structured prompting as practical steps toward a camera-aware VideoLLM and VLA system. The dataset and benchmark is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13119
PDF
-
Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences
2026-03-13 15:53:42Wenxi Wu, Jingjing Zhang, Martim Brand\~aoAbstract
Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. While foundation models have been applied to task planning, it is still unclear the degree to which they have the capability of spatial reasoning required to enforce user preferences or constraints on motion, such as desired distances from objects, topological properties, or motion style preferences. In this paper, we evaluate the capability of four state-of-the-art VLMs at spatial reasoning over robot motion, using four different querying methods. Our results show that, with the highest-performing querying method, Qwen2.5-VL achieves 71.4% accuracy zero-shot and 75% on a smaller model after fine-tuning, and GPT-4o leads to lower performance. We evaluate two types of motion preferences (object-proximity and path-style), and we also analyze the trade-off between accuracy and computation cost in number of tokens. This work shows some promise in the potential of VLM integration with robot motion planning pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13100
PDF
-
MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts
2026-03-13 15:44:19Evandro S. Ortigossa, Guy Lutsker, Eran SegalAbstract
Real-world multivariate time series can exhibit intricate multi-scale structures, including global trends, local periodicities, and non-stationary regimes, which makes long-horizon forecasting challenging. Although sparse Mixture-of-Experts (MoE) approaches improve scalability and specialization, they typically rely on homogeneous MLP experts that poorly capture the diverse temporal dynamics of time series data. We address these limitations with MoHETS, an encoder-only Transformer that integrates sparse Mixture-of-Heterogeneous-Experts (MoHE) layers. MoHE routes temporal patches to a small subset of expert networks, combining a shared depthwise-convolution expert for sequence-level continuity with routed Fourier-based experts for patch-level periodic structures. MoHETS further improves robustness to non-stationary dynamics by incorporating exogenous information via cross-attention over covariate patch embeddings. Finally, we replace parameter-heavy linear projection heads with a lightweight convolutional patch decoder, improving parameter efficiency, reducing training instability, and allowing a single model to generalize across arbitrary forecast horizons. We validate across seven multivariate benchmarks and multiple horizons, with MoHETS consistently achieving state-of-the-art performance, reducing the average MSE by $12\%$ compared to strong recent baselines, demonstrating effective heterogeneous specialization for long-term forecasting.
Abstract (translated)
URL
https://arxiv.org/abs/2601.21866
PDF
-
Rooftop Wind Field Reconstruction Using Sparse Sensors: From Deterministic to Generative Learning Methods
2026-03-13 15:23:18Yihang Zhou, Chao Lin, Hideki Kikumoto, Ryozo Ooka, Sibo ChengAbstract
Real-time rooftop wind-speed distribution is important for the safe operation of drones and urban air mobility systems, wind control systems, and rooftop utilization. However, rooftop flows show strong nonlinearity, separation, and cross-direction variability, which make flow field reconstruction from sparse sensors difficult. This study develops a learning-from-observation framework using wind-tunnel experimental data obtained by Particle Image Velocimetry (PIV) and compares Kriging interpolation with three deep learning models: UNet, Vision Transformer Autoencoder (ViTAE), and Conditional Wasserstein GAN (CWGAN). We evaluate two training strategies, single wind-direction training (SDT) and mixed wind-direction training (MDT), across sensor densities from 5 to 30, test robustness under sensor position perturbations of plus or minus 1 grid, and optimize sensor placement via Proper Orthogonal Decomposition with QR decomposition. Results show that deep learning methods can reconstruct rooftop wind fields from sparse sensor data effectively. Compared with Kriging interpolation, the deep learning models improved SSIM by up to 32.7%, FAC2 by 24.2%, and NMSE by 27.8%. Mixed wind-direction training further improved performance, with gains of up to 173.7% in SSIM, 16.7% in FAC2, and 98.3% in MG compared with single-direction training. The results also show that sensor configuration, optimization, and training strategy should be considered jointly for reliable deployment. QR-based optimization improved robustness by up to 27.8% under sensor perturbations, although with metric-dependent trade-offs. Training on experimental rather than simulated data also provides practical guidance for method selection and sensor placement in different scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13077
PDF
-
Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
2026-03-13 15:16:27Yunzhuo Chen, Jordan Vice, Naveed Akhtar, Nur Al Hasan Haldar, Ajmal MianAbstract
State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random token insertion or embedding noise, may lower copying but often harm image-prompt alignment and overall fidelity. To address this, we introduce two complementary methods. First, Region-Aware Prompt Augmentation (RAPTA) uses an object detector to find salient regions and turn them into semantically grounded prompt variants, which are randomly sampled during training to increase diversity, while maintaining semantic alignment. Second, Attention-Driven Multimodal Copy Detection (ADMCD) aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation, and applies simple thresholded decision rules to detect copying without training with large annotated datasets. Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13070
PDF
-
GeoChemAD: Benchmarking Unsupervised Geochemical Anomaly Detection for Mineral Exploration
2026-03-13 15:14:57Yihao Ding, Yiran Zhang, Chris Gonzalez, Eun-Jung Holden, Wei LiuAbstract
Geochemical anomaly detection plays a critical role in mineral exploration as deviations from regional geochemical baselines may indicate mineralization. Existing studies suffer from two key limitations: (1) single region scenarios which limit model generalizability; (2) proprietary datasets, which makes result reproduction unattainable. In this work, we introduce \textbf{GeoChemAD}, an open-source benchmark dataset compiled from government-led geological surveys, covering multiple regions, sampling sources, and target elements. The dataset comprises eight subsets representing diverse spatial scales and sampling conditions. To establish strong baselines, we reproduce and benchmark a range of unsupervised anomaly detection methods, including statistical models, generative and transformer-based approaches. Furthermore, we propose \textbf{GeoChemFormer}, a transformer-based framework that leverages self-supervised pretraining to learn target-element-aware geochemical representations for spatial samples. Extensive experiments demonstrate that GeoChemFormer consistently achieves superior and robust performance across all eight subsets, outperforming existing unsupervised methods in both anomaly detection accuracy and generalization capability. The proposed dataset and framework provide a foundation for reproducible research and future development in this direction.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13068
PDF
-
Competition-Aware CPC Forecasting with Near-Market Coverage
2026-03-13 15:07:53Sebastian Frey, Edoardo Beccari, Maximilian Kranz, Nicol\`o Alberto Pellizzari, Ali Mete Karaman, Qiwei Han, Maximilian KaiserAbstract
Cost-per-click (CPC) in paid search is a volatile auction outcome generated by a competitive landscape that is only partially observable from any single advertiser's history. Using Google Ads auction logs from a concentrated car-rental market (2021--2023), we forecast weekly CPC for 1,811 keyword series and approximate latent competition through complementary signals derived from keyword text, CPC trajectories, and geographic market structure. We construct (i) semantic neighborhoods and a semantic keyword graph from pretrained transformer-based representations of keyword text, (ii) behavioral neighborhoods via Dynamic Time Warping (DTW) alignment of CPC trajectories, and (iii) geographic-intent covariates capturing localized demand and marketplace heterogeneity. We extensively evaluate these signals both as stand-alone covariates and as relational priors in spatiotemporal graph forecasters, benchmarking them against strong statistical, neural, and time-series foundation-model baselines. Across methods, competition-aware augmentation improves stability and error profiles at business-relevant medium and longer horizons, where competitive regimes shift and volatility is most consequential. The results show that broad market-outcome coverage, combined with keyword-derived semantic and geographic priors, provides a scalable way to approximate latent competition and improve CPC forecasting in auction-driven markets.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13059
PDF
-
Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback
2026-03-13 15:06:48Yuki Hirakawa, Takashi Wada, Ryotaro Shimizu, Takuya Furusawa, Yuki Saito, Ryosuke Araki, Tianwei Chen, Fan Mo, Yoshimitsu AokiAbstract
Given a person image and a garment image, image-based Virtual Try-ON (VTON) synthesizes a try-on image of the person wearing the target garment. As VTON systems become increasingly important in practical applications such as fashion e-commerce, reliable evaluation of their outputs has emerged as a critical challenge. In real-world scenarios, ground-truth images of the same person wearing the target garment are typically unavailable, making reference-based evaluation impractical. Moreover, widely used distribution-level metrics such as Fréchet Inception Distance and Kernel Inception Distance measure dataset-level similarity and fail to reflect the perceptual quality of individual generated images. To address these limitations, we propose Image Quality Assessment for Virtual Try-On (VTON-IQA), a reference-free framework for human-aligned, image-level quality assessment without requiring ground-truth images. To model human perceptual judgments, we construct VTON-QBench, a large-scale human-annotated benchmark comprising 62,688 try-on images generated by 14 representative VTON models and 431,800 quality annotations collected from 13,838 qualified annotators. To the best of our knowledge, this is the largest dataset to date for human subjective evaluation in virtual try-on. Evaluating virtual try-on quality requires verifying both garment fidelity and the preservation of person-specific details. To explicitly model such interactions, we introduce an Interleaved Cross-Attention module that extends standard transformer blocks by inserting a cross-attention layer between self-attention and MLP in the latter blocks. Extensive experiments show that VTON-IQA achieves reliable human-aligned image-level quality prediction. Moreover, we conduct a comprehensive benchmark evaluation of 14 representative VTON models using VTON-IQA.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13057
PDF
-
Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach
2026-03-13 15:06:14Elena Ryumina (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia), Maxim Markitantov (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia), Alexandr Axyonov (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia), Dmitry Ryumin (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia), Mikhail Dolgushin (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia), Denis Dresvyanskiy (ITMO University, St. Petersburg, Russia), Alexey Karpov (St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia, ITMO University, St. Petersburg, Russia)Abstract
Continuous emotion recognition in terms of valence and arousal under in-the-wild (ITW) conditions remains a challenging problem due to large variations in appearance, head pose, illumination, occlusions, and subject-specific patterns of affective expression. We present a multimodal method for valence-arousal estimation ITW. Our method combines three complementary modalities: face, behavior, and audio. The face modality relies on GRADA-based frame-level embeddings and Transformer-based temporal regression. We use Qwen3-VL-4B-Instruct to extract behavior-relevant information from video segments, while Mamba is used to model temporal dynamics across segments. The audio modality relies on WavLM-Large with attention-statistics pooling and includes a cross-modal filtering stage to reduce the influence of unreliable or non-speech segments. To fuse modalities, we explore two fusion strategies: a Directed Cross-Modal Mixture-of-Experts Fusion Strategy that learns interactions between modalities with adaptive weighting, and a Reliability-Aware Audio-Visual Fusion Strategy that combines visual features at the frame-level while using audio as complementary context. The results are reported on the Aff-Wild2 dataset following the 10th Affective Behavior Analysis in-the-Wild (ABAW) challenge protocol. Experiments demonstrate that the proposed multimodal fusion strategy achieves a Concordance Correlation Coefficient (CCC) of 0.658 on the Aff-Wild2 development set.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13056
PDF
-
Topo-R1: Detecting Topological Anomalies via Vision-Language Models
2026-03-13 15:05:04Meilong Xu, Qingqiao Hu, Xiaoling Hu, Shahira Abousamra, Xin Yu, Weimin Lyu, Kehan Qi, Dimitris Samaras, Chao ChenAbstract
Topological correctness is crucial for tubular structures such as blood vessels, nerve fibers, and road networks. Existing topology-preserving methods rely on domain-specific ground truth, which is costly and rarely transfers across domains. When deployed to a new domain without annotations, a key question arises: how can we detect topological anomalies without ground-truth supervision? We reframe this as topological anomaly detection, a structured visual reasoning task requiring a model to locate and classify topological errors in predicted segmentation masks. Vision-Language Models (VLMs) are natural candidates; however, we find that state-of-the-art VLMs perform nearly at random, lacking the fine-grained, topology-aware perception needed to identify sparse connectivity errors in dense structures. To bridge this gap, we develop an automated data-curation pipeline that synthesizes diverse topological anomalies with verifiable annotations across progressively difficult levels, thereby constructing the first large-scale, multi-domain benchmark for this task. We then introduce Topo-R1, a framework that endows VLMs with topology-aware perception via two-stage training: supervised fine-tuning followed by reinforcement learning with Group Relative Policy Optimization (GRPO). Central to our approach is a topology-aware composite reward that integrates type-aware Hungarian matching for structured error classification, spatial localization scoring, and a centerline Dice (clDice) reward that directly penalizes connectivity disruptions, thereby jointly incentivizing semantic precision and structural fidelity. Extensive experiments demonstrate that Topo-R1 establishes a new paradigm for annotation-free topological quality assessment, consistently outperforming general-purpose VLMs and supervised baselines across all evaluation protocols.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13054
PDF
-
ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
2026-03-13 14:43:00Yanpeng Zhao, Wentao Ding, Hongtao Li, Baoxiong Jia, Zilong ZhengAbstract
A recent trend in vision-language models (VLMs) has been to enhance their spatial cognition for embodied domains. Despite progress, existing evaluations have been limited both in paradigm and in coverage, hindering rapid, iterative model development. To address these limitations, we propose ESPIRE, a diagnostic benchmark for embodied spatial reasoning. ESPIRE offers a simulated world that physically grounds VLMs and evaluates them on spatial-reasoning-centric robotic tasks, thus narrowing the gap between evaluation and real-world deployment. To adapt VLMs to robotic tasks, we decompose each task into localization and execution, and frame both as generative problems, in stark contrast to predominant discriminative evaluations (e.g., via visual-question answering) that rely on distractors and discard execution. This decomposition further enables a fine-grained analysis beyond passive spatial reasoning toward reasoning to act. We systematically design ESPIRE both at the instruction level and at the environment level, ensuring broad coverage of spatial reasoning scenarios. We use ESPIRE to diagnose a range of frontier VLMs and provide in-depth analysis of their spatial reasoning behaviors.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13033
PDF
-
Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
2026-03-13 14:36:46Qichen Zhao, Shengfang Zhai, Xinjian Bai, Qingni Shen, Qiqi Lin, Yansong Gao, Zhonghai WuAbstract
Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation. To mitigate these risks, proactive image protection methods embed small, often imperceptible adversarial perturbations into images before sharing to disrupt downstream editing or fine-tuning. However, in realistic post-release scenarios, content owners cannot control downstream processing pipelines, and protections optimized for a surrogate model may fail when attackers use mismatched diffusion pipelines. Existing purification methods can weaken protections but often sacrifice image quality and rarely examine architectural mismatch. We introduce a unified post-release purification framework to evaluate protection survivability under model mismatch. We propose two practical purifiers: VAE-Trans, which corrects protected images via latent-space projection, and EditorClean, which performs instruction-guided reconstruction with a Diffusion Transformer to exploit architectural heterogeneity. Both operate without access to protected images or defense internals. Across 2,100 editing tasks and six representative protection methods, EditorClean consistently restores editability. Compared to protected inputs, it improves PSNR by 3-6 dB and reduces FID by 50-70 percent on downstream edits, while outperforming prior purification baselines by about 2 dB PSNR and 30 percent lower FID. Our results reveal a purify-once, edit-freely failure mode: once purification succeeds, the protective signal is largely removed, enabling unrestricted editing. This highlights the need to evaluate protections under model mismatch and design defenses robust to heterogeneous attackers.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13028
PDF
-
Accelerating Stroke MRI with Diffusion Probabilistic Models through Large-Scale Pre-training and Target-Specific Fine-Tuning
2026-03-13 14:13:53Yamin Arefeen, Sidharth Kumar, Steven Warach, Hamidreza Saber, Jonathan TamirAbstract
Purpose: To develop a data-efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables faster scan times in clinical stroke MRI when only limited fully-sampled data samples are available. Methods: Our simple training strategy, inspired by the foundation model paradigm, first trains a DPM on a large, diverse collection of publicly available brain MRI data in fastMRI and then fine-tunes on a small dataset from the target application using carefully selected learning rates and fine-tuning durations. The approach is evaluated on controlled fastMRI experiments and on clinical stroke MRI data with a blinded clinical reader study. Results: DPMs pre-trained on approximately 4000 subjects with non-FLAIR contrasts and fine-tuned on FLAIR data from only 20 target subjects achieve reconstruction performance comparable to models trained with substantially more target-domain FLAIR data across multiple acceleration factors. Experiments reveal that moderate fine-tuning with a reduced learning rate yields improved performance, while insufficient or excessive fine-tuning degrades reconstruction quality. When applied to clinical stroke MRI, a blinded reader study involving two neuroradiologists indicates that images reconstructed using the proposed approach from $2 \times$ accelerated data are non-inferior to standard-of-care in terms of image quality and structural delineation. Conclusion: Large-scale pre-training combined with targeted fine-tuning enables DPM-based MRI reconstruction in data-constrained, accelerated clinical stroke MRI. The proposed approach substantially reduces the need for large application-specific datasets while maintaining clinically acceptable image quality, supporting the use of foundation-inspired diffusion models for accelerated MRI in targeted applications.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13007
PDF
-
A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
2026-03-13 13:55:34Tangzheng Lian, Guanyu Hu, Yijing Ren, Dimitrios Kollias, Oya CeliktutanAbstract
While Vision-Language Models (VLMs) have achieved remarkable performance across diverse downstream tasks, recent studies have shown that they can inherit social biases from the training data and further propagate them into downstream applications. To address this issue, various debiasing approaches have been proposed, yet most of them aim to improve fairness without having a theoretical guarantee that the utility of the model is preserved. In this paper, we introduce a debiasing method that yields a \textbf{closed-form} solution in the cross-modal space, achieving Pareto-optimal fairness with \textbf{bounded utility losses}. Our method is \textbf{training-free}, requires \textbf{no annotated data}, and can jointly debias both visual and textual modalities across downstream tasks. Extensive experiments show that our method outperforms existing methods in debiasing VLMs across diverse fairness metrics and datasets for both group and \textbf{intersectional} fairness in downstream tasks such as zero-shot image classification, text-to-image retrieval, and text-to-image generation while preserving task performance.
Abstract (translated)
URL
https://arxiv.org/abs/2603.12998
PDF
