Research
Papers and datasets worth knowing, ranked by significance and community attention.
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved.
Beyond the Snowflakes: Disentangling Weather Effects from Confounding Meta-Factors in LiDAR Object Detection
Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather.
PaperNormalizing Trajectory Models
We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training.
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank.
PaperLearning Representations to Guide Pixel Diffusion Transformers
Motivated by these insights, we introduce Representation Guidance (RG), which directly forms and exploits internal representations while retaining a plain Transformer architecture.
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint.
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
To establish identity-preserving correspondence across such transformations, we introduce FreeMatching, a generalizable framework combining generative and semantic foundation representations with heterogeneous supervision from classical datasets, tracked videos, and synthetic scenes.
Pumpire: Unified Benchmark for Metric Distance Estimation
We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation models, with or without depth priors.
PaperMixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement
We introduce MixTok, a hybrid visual tokenizer that combines a compact 1D global representation with sparse 2D tokens for local refinement.
CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation.
Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers
In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Head Attention (MHA) through the lens of metric learning.
GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models
We present GLIMPSE, a global-local memory interface with band-wise multi-precision coordinates and geometry-conditioned spectral attenuation to reduce sensitivity to inaccurate projected addresses.
Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters.
Why DiT Models Underperform as Representation Learners without Long Skip Connections
Diffusion feature, i.e., intermediate activations extracted from diffusion model backbones, has emerged as a promising approach for unifying generation and vision understanding (discrimination).
State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement
Vision Mamba has recently emerged as an efficient alternative to convolutional and Transformer-based architectures by modeling long-range spatial dependencies through recurrent state evolution.
Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding
Open-set visual grounding in remote sensing requires models to determine not only where a queried object is located, but also whether the image provides sufficient evidence for the query at all.
QCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action Recognition
In this work, we propose a plug-in robustification module via quantization for contrastive learning in self-supervised skeleton-based human action recognition (QCLR), which enhances the robustness of representations against adversarial attacks while preserving their representational capability.
Predicting Cable Dynamics with Physical Attention Bias
Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts.
CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope
Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry.
CV-OPD: Contrastive Vision On-policy Distillation
To address the issue, we introduce Contrastive Vision On-policy Distillation (CV-OPD), which compares teacher distributions induced by positive and negative crops while conditioning on the same student prefix and augments optimization with a margin-based contrastive constraint, which is modulated with discrepancy gating across token and sample level.
PlacePulse: Learning Transferable Place Representations from Structural Geographic Data
We introduce PlacePulse, a structural geospatial foundation model that compresses 572 attributes, expanded to 2,288 inputs through H3 neighborhood aggregates, into 256-dimensional unit-norm embeddings for 1,055,537 H3 resolution-7 cells in the United States.
MOSAIC: Multi-Scale Object-Centric Slot Adaptation with Image-Guided Prototype Conditioning for Remote Sensing Image Super-Resolution
Pretrained diffusion Transformers provide powerful generative priors for image restoration, yet adapting them to structure-sensitive tasks remains challenging.
MCL: Meta Convolution Layer
Dynamic convolution enhances convolutional neural networks (CNNs) by adapting kernels to input content, but it expresses the effective kernel as a linear mixture of a small number of basis kernels, which limits expressivity and complicates optimization as the mixture size grows.
Selective Spatio-Temporal Fruit Inspector (S$^2$FI): A Mamba-based Framework for Rotational Fruit Quality Assessment
We propose the Selective Spatio-Temporal Fruit Inspector (S$^2$FI) architecture, which combines a 3D convolutional encoder with a Mamba-based backbone.It efficiently extracts spatiotemporal features, adaptively weighs informative frames during fruit rotation, and models long-range dependencies with linear complexity, reducing motion blur and occlusion.
OccludeBench: Can VLMs Find What's Missing?
How well can vision-language models (VLMs) reason about what is missing from an image?
Decoding Register Tokens Preserves Global Scene Details
Pretrained vision transformers learn structured image representations spanning spatial patch tokens and non-spatial tokens.
Deep Learning Approach for RealTime Contraction Detection in Laboring Dairy Cattle
This paper presents a computer vision-based approach for the automatic recognition of labor contractions in cows.
Neurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual Interpretability
In this work, we propose Neurons++, a visual-stream fMRI reconstruction framework for both static image and dynamic video reconstruction.
Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
We conduct a systematic explainability evaluation across Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba (ViM).
Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging
Natural-image-pretrained foundation models are increasingly adapted to medical imaging, yet transfer remains unreliable under domain shift, modality heterogeneity, and label scarcity.
ECGWmark: Deep Watermarking for Electrocardiogram Signals
To bridge this gap, we propose ECGWmark, a fully convolutional and quantization-free deep watermarking framework for medical time-series.
PPG-Bench: A Unified Benchmark for PPG Foundation Models
We present PPG-Bench, a unifying open-source benchmark evaluating five public PPG FMs across nine open-access datasets and 26 tasks spanning cardiovascular state estimation, activity, sleep, screening, and identification.
Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation
To this end, we propose a self-evolving framework, named Rubric-CEPR, that verifies the editor's own samples with its internal representations through a rubric-augmented Contrastive Edit-Preservation Reward (CEPR).
Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
Representation structure is crucial for understanding Vision Transformer (ViT) architectures and their generalization behavior.
AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image Fusion
To address this challenge, we propose an attack-defense semantic reinforcement framework for multi-modal image fusion, termed AD-SRF.
Complexity-Calibrated Reconstruction Discrepancy for No-Reference Point Cloud Quality Assessment
The discrepancy induced by surface reconstruction in a distorted point cloud is jointly influenced by its intrinsic structural complexity and signal degradation.
GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
We propose GLIO2, a tightly-coupled LiDAR-Inertial-GNSS system whose GPU-parallel front-end jointly optimizes scan-to-multiscan LiDAR, IMU pre-integration, and raw GNSS measurements in a single sliding-window factor graph, sustaining real-time operation on edge hardware.
UniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object Tracking
In this work, we present UniMergeTrack, a new model merging paradigm that preserves task-specific optimization while enabling effective cross-task knowledge integration.
From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction
We present a comparative study of eight open-source lightweight VLMs (up to 7B parameters) for Optical Character Recognition (OCR)-to-structure across three university heritage collections.
NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection
We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection.
Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study
Purpose: To compare dual- and single-suggestion AI support for radiographic interpretation by residents, particularly when the shared AI suggestion was incorrect.
EchoDiST: Self-distillation-based joint learning for diffusion-conditioned echocardiographic myocardial motion estimation
We propose EchoDiST, a framework for unsupervised echocardiographic myocardial motion estimation that integrates self-distillation-based joint learning with a diffusion-conditioned motion estimation network.
GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQA
We present CoVeR-VQA, a training-free multi-stage verification and correction framework for grounded multi-view VQA.
Domain Adaptation of SAM 2.1 for Building-Component Segmentation in Image-Based 3D Reconstruction
3D reconstruction of building components using image-based scanning requires appropriate segmentation of the objects in the 2D building images.
On the Necessity of Attention-FFN Split in Vision Transformers
In this work, we investigate the necessity of the Attention-FFN dichotomy in Vision Transformers (ViTs).
The Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute
We present BEVPIPE, a framework for deploying multimodal BEV perception pipelines using portable GPU compute APIs and integrating them with production inference runtimes.
Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction
We present Zebra3D, a layerwise sparse-linear hybrid attention framework that improves the efficiency of pretrained 3D foundation models without training from scratch.
CARE: Constrained Attention Refinement for Fine-Grained Visual Classification via Teacher-Student Distillation
To address this problem, we propose CARE, a constrained attention refinement framework for interpretable fine-grained recognition via teacher-student distillation.