CVPR 2026

3,659 papers

Top Research Directions

Research directions most represented by CVPR 2026 papers.

Generalizing from Synthetic Data to the Real World 54
Overcoming the Static Scene Assumption 47
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 39
Scaling Visual Attention Beyond Quadratic Complexity 37
Mitigating Multi View Inconsistency in Generative 3D Modeling 35
The Spatial Reasoning Bottleneck in Multimodal Models 35
Aligning Global Semantics with Local Spatial Precision 33
The Decoupling of Visual Perception and Logical Reasoning 31
Aligning Video Generation Models with Physical Laws 29
Spatial Attention Masking in Generative Diffusion Models 29
Overcoming the Iterative Inference Latency of Diffusion Models 28
Physics Constrained Generative Human Motion Synthesis 26
Fusing 2D Semantic Features with 3D Geometric Representations 26
Group Relative Policy Optimization for Large Reasoning Models 25
Exploiting Temporal Redundancy in Video Neural Networks 24

Top Authors

AuthorPapers
Honglu Zhou4
Caiming Xiong3
Juan Carlos Niebles3
Junhao Chen3
Ramesh Raskar3
Siddharth Somasundaram3
silvio savarese3
Yanwei Fu3
Akshat Dave2
Andrew Zisserman2
Botong Wu2
Dahua Lin2
Di Wu2
Fangneng Zhan2
Gaowen Liu2
Gim Hee Lee2
Hanming Deng2
Hanspeter Pfister2
Hui Shan2
Jian Zhang2

Papers

Title
M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
M^3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
M⁴-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
M4V: Multimodal Mamba for Efficient Text-to-Video Generation
MA-Bench: Towards Fine-grained Micro-Action Understanding
Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
MacTok: Robust Continuous Tokenization for Image Generation
MAD: Motion Appearance Decoupling for efficient Driving World Models
MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues
MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts
MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
Make it SING: Analyzing Semantic Invariants in Classifiers
Making the Classification Explanation Faithful to the Confidence Score
Making Training-Free Diffusion Segmentors Scale with the Generative Power
Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding
MambaSIC: Mamba-based Stereo Image Compression with Bi-directional Multi-reference Entropy Model
MAMMA: Markerless Accurate Multi-person Motion Acquisition
MangoBench: A Benchmark for Multi-Agent Goal-Conditioned Offline Reinforcement Learning
ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
MAPo: Motion-Aware Partitioning of Deformable 3D Gaussian Splatting for High-Fidelity Dynamic Scene Reconstruction
MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
MARCO: Navigating the Unseen Space of Semantic Correspondence
Mario: Multimodal Graph Reasoning with Large Language Models
MARIS: Marine Open-Vocabulary Instance Segmentation
Mark4D: Temporally-Consistent Watermarking for 4D Gaussian Splatting
Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures
MARSS: Radar Semantic Segmentation via Modular Attention and State Space Models
Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
Masked-Diffusion Autoencoders for 3D Medical Vision Representation Learning
Masked Region Transformer for Layered Image Generation and Editing at Scale
MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
Mask to Align, Weight to Disambiguate: Reliable Unsupervised Cross-Modal Hashing with Masked-Weight Contrast
MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models
MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator
Match-and-Fuse: Consistent Generation from Unstructured Image Sets
MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision
Matching Every Pair to Track Every Point: PairFormer for All-Pairs Tracking and Video Trajectory Fields
MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation
MatE: Material Extraction from Single-Image via Geometric Prior
Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes

« prev Page 37/74 next »