DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
super hub Mixed citations
DINOv2: Learning Robust Visual Features without Supervision
Mixed citation behavior. Most common role is background (44%).
753
Pith papers citing it
Background
44% of classified citations
abstract
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model (Dosovitskiy et al., 2020) with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP (Ilharco et al., 2021) on most of the benchmarks at image and pixel levels.
hub tools
citation-role summary
method 59
background 57
baseline 9
dataset 3
other 1
citation-polarity summary
claims ledger
- abstract The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques
authors
co-cited works
representative citing papers
X-Palm supplies the first paired multispectral-to-smartphone palmprint dataset with broad real-world variability to support cross-domain biometric authentication.
Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
A multi-view transformer predicts dense perspective fields that feed a geometric optimizer to estimate camera intrinsics and gravity from arbitrary numbers of real-world views.
Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.
Image-to-3D models successfully generate harmful geometries in most cases with under 0.3% caught by commercial filters; existing safeguards are weak but a stacked defense cuts harmful outputs to under 1% at 11% false-positive cost.
neuralCAD-Edit benchmark shows even the best foundation model (GPT 5.2) scores 53% lower than human CAD experts in acceptance trials for multimodal-instructed 3D model edits.
The work creates the first dataset and baseline for generating emission textures on 3D objects to reproduce glowing materials from input images.
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
A training-free prototype memory-guided framework for multi-class prenatal ultrasound anomaly classification and localization using few reference images per class, validated on a 9-category multi-center dataset.
EPO is a trackless, edge-map-alignment framework that refines pose estimates from 3D foundation models and matches or exceeds bundle-adjustment performance with substantially lower runtime and memory use.
GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
WarpHammer densifies scene warps with 3D object priors from generative models and fuses pose-unknown auxiliary views via multi-view geometry to enable stable extreme novel view synthesis.
AnyMatch synthesizes large-scale geometrically consistent multi-modal image pairs from single-view images, enabling fine-tuned matching networks to achieve substantial gains on benchmarks.
A new dataset of 220k+ cross-view pairs and a single-stage geometry-aware model GAGeo based on the π³ 3D foundation model outperforms prior methods on object geo-localization with strong generalization and zero-shot ground-to-drone capability.
First complete digital unwrapping and reading of a Herculaneum papyrus scroll (PHerc. 1667) via synchrotron X-ray CT, virtual unrolling, and machine learning.
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
Constructs G-equivariant ViTs for arbitrary discrete G ≤ O(2), proves H ≤ G implies G-models embed into H-models and single-head equivariant attention realizes all ordinary G-equivariant maps, introduces D6 hexagonal model, and reports preliminary accuracy gains on PatternNet in low-data regimes.
BiLoc is the first binary neural network framework for 6-DoF LiDAR pose estimation that uses an auxiliary objective to adaptively regulate information retention and achieve SOTA among BNNs on large outdoor datasets.
SHOW is a mask-promptable framework coupling feed-forward scene reconstruction with human mesh recovery in a unified metric space to resolve scale ambiguity and improve human-scene alignment from monocular video.
MIRAGE immunizes images by crafting perturbations that align them with policy-violating concepts in open-source moderation models, triggering refusals in closed-source commercial image editors at over 88% success rate.
Introduces TSMa using text-visual channel interaction and SHARe using ViT layer-aligned autoregressive regression to improve prototype-based few-shot object detection, reporting +10.1 nAP on COCO.
citing papers explorer
-
A foundation model of vision, audition, and language for in-silico neuroscience
TRIBE v2 is a multimodal AI model that predicts human brain activity more accurately than linear encoding models and recovers established neuroscientific findings through in-silico testing.
-
ReLeaf: Benchmarking Leaf Segmentation across Domains and Species
A YOLO26 model trained on four leaf segmentation datasets reaches 83.9% mean mAP50-95 on their test sets but only 40.2% on a new 23-species benchmark, revealing substantial cross-domain generalization gaps.
-
Automated In-the-Wild Data Collection for Continual AI Generated Image Detection
An automated fact-check-based pipeline for in-the-wild AI image data, when mixed with generator data in continual learning, lets detectors adapt to new generators while avoiding forgetting and delivers 8-9% accuracy gains on two existing models.
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features from diffusion intermediates and aligns them to complementary expert foundation models via a multi-modal alignment loss and modality-specific decoupling regularization for improved multimodal video generation.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
Towards Visual Query Localization in the 3D World
The authors release the 3DVQL benchmark for 3D multimodal visual query localization and show that a lift-and-attention fusion module outperforms prior fusion baselines on it.
-
Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion
Action Agent pairs LLM-driven video generation with a flow-constrained diffusion transformer to produce velocity commands, raising video success to 86% and delivering 64.7% real-world navigation on a Unitree G1 humanoid.
-
Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
Gromov-Wasserstein distance between modalities provides a stronger, inference-only predictor of final VLM performance than conventional encoder metrics, backed by theory linking it to cross-modal learnability and verified across 60+ training runs.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
Rethink MAE with Linear Time-Invariant Dynamics
Token order in frozen visual representations is exploitable via SSM-based LTI probes, revealing pre-training-dependent heterogeneity that fixed pooling misses.
-
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
AirZoo is a new dataset covering 378 regions across 22 countries with pixel-level metric depth and 6-DoF poses, shown via benchmarks to improve SoTA models on aerial image retrieval, cross-view matching, and multi-view 3D reconstruction.
-
Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.
-
LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
LearnPruner prunes vision tokens to 5.5% of the original count while retaining about 95% of VLM performance and delivering 3.2 times faster inference by fixing attention sink in encoders and using unbiased middle-layer attention in LLMs.
-
VitaminP: cross-modal learning enables whole-cell segmentation from routine histology
VitaminP uses paired H&E-mIF data to train a model that transfers molecular boundary information, enabling accurate whole-cell segmentation directly from routine H&E histology across 34 cancer types.
-
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation
MuSS is a new movie-sourced dataset and benchmark that enables AI models to generate multi-shot videos with improved narrative coherence and subject identity preservation.
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain generalized object detection.
-
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
WildSplatter jointly learns 3D Gaussians and appearance embeddings from unconstrained photo collections to enable fast feed-forward reconstruction and flexible lighting control in 3D Gaussian Splatting.
-
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
Render-in-the-Loop reformulates SVG generation as a step-wise visual-context-aware process using self-feedback from rendered intermediate states, VSF training, and RaV inference to outperform baselines on MMSVGBench for Text-to-SVG and Image-to-SVG.
-
Evaluating Remote Sensing Image Captions Beyond Metric Biases
Unfine-tuned MLLMs outperform fine-tuned models on remote sensing image captioning when captions are scored by their ability to reconstruct the source image, and a training-free self-correction method achieves SOTA performance.
-
Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance
Frequency-Forcing guides pixel flow-matching with a data-derived low-frequency auxiliary stream to softly enforce scale-ordered generation, improving FID on ImageNet-256 over baselines.
-
TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editing
TransSplat uses unbalanced semantic transport to match edited 2D evidence with 3D Gaussians and recover a shared 3D edit field, yielding better local accuracy and structural consistency than prior view-consistency methods.
-
Generative Texture Filtering
A two-stage fine-tuning strategy on pre-trained generative models enables effective texture filtering that outperforms prior methods on challenging cases.
-
Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
Distillation from visual foundation models to lidar enables frame-wise indoor semantic segmentation without manual annotations, achieving up to 56% mIoU on pseudo labels and 36% on real labels.
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
-
CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement
CFSR reframes shadow removal as a physics-constrained process using geometric and semantic priors from depth, DINO, CLIP, and frequency decoupling to achieve claimed state-of-the-art results.
-
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
MU-GeNeRF combines source-view and target-view uncertainties via a heteroscedastic loss to enable distractor-aware generalizable NeRF reconstruction that matches scene-specific methods.
-
DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection
DifFoundMAD improves differential morphing attack detection by replacing traditional embeddings with those from vision foundation models and applying class-balanced lightweight fine-tuning, cutting high-security error rates from 6.16% to 2.17%.
-
Coevolving Representations in Joint Image-Feature Diffusion
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample quality than fixed-representation baselines.
-
Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
-
Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation
Flow of Truth is the first proactive temporal forensics framework for image-to-video generation that uses a learnable forensic template following pixel motion and a template-guided flow module to decouple motion from content.
-
Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
Text-to-3D models lose prompt sensitivity for out-of-distribution shapes due to sink traps but retain geometric diversity via unconditional priors, enabling a decoupled inversion method for robust editing.
-
OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism
OmniGCD trains a Transformer once on synthetic data to enable zero-shot generalized category discovery across 16 datasets in four modalities without any dataset-specific fine-tuning.
-
OneHOI: Unifying Human-Object Interaction Generation and Editing
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
-
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
-
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
VideoFlexTok introduces coarse-to-fine variable-length video tokenization that enables 5x smaller models to match grid-based generation quality and supports 10-second videos with 8x fewer tokens.
-
IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
IAD-Unify unifies industrial anomaly segmentation, region-grounded language understanding, and mask-guided generation in one framework using DINOv2 token injection into Qwen3.5, supported by the new Anomaly-56K dataset of 59,916 images.
-
VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale
VidTAG achieves fine-grained global video-to-GPS geolocalization via temporal frame alignment and denoising sequence refinement, reporting 20% gains at 1 km over GeoCLIP and 25% on CityGuessr68k.
-
Scene Change Detection with Vision-Language Representation Learning
LangSCD fuses VLM-generated text descriptions with visual features and adds geometric-semantic matching to improve scene change detection, while releasing the NYC-CD dataset of 8122 New York City image pairs with multiclass annotations.
-
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
-
Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding
MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
-
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
-
SIMPLER: H&E-Informed Representation Learning for Structured Illumination Microscopy
SIMPLER learns biologically grounded SIM representations by progressively aligning them with H&E images through multiple self-supervised objectives, outperforming scratch-trained or H&E-only models on downstream tasks like multiple instance learning and clustering.
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
-
WildDet3D: Scaling Promptable 3D Detection in the Wild
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
-
DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather
DinoRADE reports a radar-centered multi-class detection pipeline that fuses dense radar tensors with DINOv3 features via deformable attention and outperforms prior radar-camera methods by 12.1% on the K-Radar dataset across weather conditions.
-
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
-
VDPP: Video Depth Post-Processing for Speed and Scalability
VDPP is an RGB-free video depth post-processor that achieves over 43 FPS on Jetson Orin Nano by refining geometry at low resolution rather than reconstructing full scenes.