Measure by measure, studying society accurately
Naoki Egami has become a standout in political methodology, helping refine tools that give scholars durable results.
Read at sourceMechReason: Benchmarking Multi-Image Multi-Hop Reasoning in Mechanical Engineering
arXiv:2609.16012v1 Announce Type: new Abstract: Despite significant progress in general visual question answering and cross-modal understanding, multimodal large language models still face a pronounced gap in evaluation for complex reasoning within the mechanical engineering domain. Existing benchmarks predominantly f…
Read at sourceDenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching
arXiv:2609.16149v1 Announce Type: new Abstract: Despite steady progress in face recognition, current face recognition models still suffer from significant demographic biases. While approaches for bias mitigation have been proposed, existing methods often impose constraints on the training procedure and result in the d…
Read at sourceHyperbolic Contrastive Learning with Entailment for Spatial Transcriptomics
arXiv:2609.16207v1 Announce Type: new Abstract: Spatial Transcriptomics (ST) has transformed biomedical research by enabling the spatial mapping of gene expression across tissue sections. However, high operational costs, specialized equipment requirements, and sensitivity to experimental noise limit the accessibility…
Read at sourceSceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes
arXiv:2609.16233v1 Announce Type: new Abstract: Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current benchmarks. First, 3D datasets often rely on point clouds that capture geometry but discard rich visual features like texture…
Read at sourceProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement
arXiv:2609.16284v1 Announce Type: new Abstract: Query-conditioned vision--language models enable fine-grained interpretation by revealing how visual evidence changes with textual queries. However, evidence conditioned on complete descriptions does not necessarily resolve into object-specific evidence, nor does an expo…
Read at sourceSequence Recognition in Bharatnatyam dance
arXiv:2609.16306v1 Announce Type: new Abstract: Bharatanatyam is the oldest Indian Classical Dance (ICD) which is learned and practiced across India and the world. Adavu is the core of this dance form. There exist 15 Adavus and 58 variations. Each Adavu variation comprises a well-defined set of motions and postures (c…
Read at sourceRacing in Volume with Flow Ensembles
arXiv:2609.16310v1 Announce Type: new Abstract: Streaming 4D reconstruction has been demonstrated only indoors, on dense camera rigs surrounding subjects that move at human pace. Outdoor 4D reconstruction exists but relies either on cameras mounted on the moving vehicle itself, or on limited-coverage arrays observing…
Read at sourceReasoning with Image Generation
arXiv:2609.16409v1 Announce Type: new Abstract: Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual domain presents limitations for tasks requiring direc…
Read at sourceDecentralized Gossip Learning and Federated Averaging for Histopathology Image Classification
arXiv:2609.16448v1 Announce Type: new Abstract: Breast histopathology analysis increasingly relies on distributed learning because direct data pooling across institutions is often restricted by privacy, governance, and communication constraints. This study compares server-based Federated Averaging (FedAvg), fully dece…
Read at sourceA multimodal large language model for evidence-based autism spectrum disorder screening
arXiv:2609.16464v1 Announce Type: new Abstract: The clinical management of autism spectrum disorder (ASD) faces a bottleneck in early screening, mainly because trained specialists are scarce and conventional assessment tools are subjective. Here, we introduce ASDchat, a multimodal large language model designed for evi…
Read at sourceMDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing
arXiv:2609.16475v1 Announce Type: new Abstract: Multi subject video editing modifies designated subjects while preserving non target content, but faces cross subject attribute leakage, and occlusion ambiguity. Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent gener…
Read at sourceVPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation
arXiv:2609.16486v1 Announce Type: new Abstract: Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe performance degradation under a coupled dual-drift paradigm: visual domain…
Read at sourceWhich Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound
arXiv:2609.16551v1 Announce Type: new Abstract: Self-supervised learning (SSL) can reduce the need for labelled medical images, but the choice of pretext objective remains unclear for lung ultrasound (LUS). Contrastive learning, masked reconstruction, and joint-embedding predictive architectures (JEPA) differ in the s…
Read at sourceVision And Text Transformer For Predicting Answerability On Visual Question Answering
arXiv:2609.16565v1 Announce Type: new Abstract: Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utilize a binary mapping from visual question answering systems into Answerability. It does not r…
Read at sourceCounterfactual Reasoning for Robust Visual Question Answering
arXiv:2609.16567v1 Announce Type: new Abstract: Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to language bias. Although counterfactual learning has shown promise, existing methods can be improved to bett…
Read at sourceEfficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
arXiv:2609.16572v1 Announce Type: new Abstract: Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity of the input text prompt. We propose an adaptive diffusion controller that dynamically adjus…
Read at sourceGraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
arXiv:2609.16578v1 Announce Type: new Abstract: The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or attention, leaving the r…
Read at source