Cvpr 2026 Findings 2026

761 papers

Top Research Directions

Research directions most represented by Cvpr 2026 Findings 2026 papers.

The Decoupling of Visual Perception and Logical Reasoning 10
The Spatial Reasoning Bottleneck in Multimodal Models 9
Generalizing from Synthetic Data to the Real World 9
Scaling Visual Attention Beyond Quadratic Complexity 9
The Cross Modal Safety Gap in Multimodal Models 7
Scaling Spatiotemporal Attention Beyond Quadratic Complexity 7
Group Relative Policy Optimization for Large Reasoning Models 6
Spatial Attention Masking in Generative Diffusion Models 6
Modality Imbalance in Multimodal Large Language Models 6
Managing Visual Token Redundancy in Multimodal Models 6
The Representational Bottleneck of Frozen Foundation Models 5
Overcoming Low Frequency Bias with Spectral Losses 5
Closed Loop Visual Feedback for Multimodal Generation 5
Aligning Video Generation Models with Physical Laws 5
Zero-Shot Generalization through Diverse Synthetic Supervision 5

Top Authors

AuthorPapers
Andrew Feng1
Peter Anthony Beerel1
Zhenglong Sun1

Papers

Title
Latent-Compressed Variational Autoencoder for Video Diffusion Models
Latent Domain Modeling Improves Robustness to Geographic Shifts
Layer Embedding Deep Fusion Graph Neural Network
Learning by Neighbor-Aware Semantics, Deciding by Open-Form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
Learning from Label Proportion with Dual-Proportion Constraints
Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM
Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection
Learning Multi-Task Robot Trajectory Segmentation from Visual and Kinematic Streams
Learning Predictive Visuomotor Coordination
Learning Spatial-Preserving Hierarchical Representations for Digital Pathology
Learning Through Creation: A Hash-Free Framework for On-the-Fly Category Discovery
Learning to Propose Pose for Category-Agnostic Objects via Joint Refinement with Co-Matching Supervision
Learning to Translate Noise for Robust Image Denoising
Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning
Learning Vision-Language-Action World Models for Autonomous Driving
Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning
Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection
LED: LLM Enhanced Open-Vocabulary Object Detection Without Human Curated Data Generation
Less is More: Multimodal Human Pose Estimation with Selective Fusion
Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization
Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection
LiDAR-to-4D Radar Synthesis for Building Large-Scale Tensor Datasets
Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution
LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation
LiteEmbed: Adapting CLIP to Rare Classes
LLM Guided Multi Style Typography and Layout Generation via Dynamic Direct Preference Optimization
Logical Consistency Optimization for Few-Shot Weakly Supervised Video Anomaly Detection
Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
Loom: Diffusion-Transformer for Interleaved Generation
LoViC: Efficient Long Video Generation with Context Compression
Low-Bitrate Video Compression Through Semantic-Conditioned Diffusion
LP3: LLM-Based Potential Prediction Policy for Object Navigation using a Scene-Object Semantic Map
LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
LUMINA: Learning and Understanding of Multimodal Information for Narrative and Affect-Based Virality Prediction
LWTformer: A Detail-Aware, Learnable Wavelet-Transformer for Ancient Chinese Character Image Restoration
M^3A Policy: Mutable Material Manipulation Augmentation Policy Through Photometric Re-Rendering
M^3D-BFS: a Multi-Stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis
Machine Vision-Oriented Appearance Design: Generate Natural And Robust Textures For 3D Meshes
MADrive: Memory-Augmented Driving Scene Modeling
MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps
MARIO: Motion-Augmented Real-Time Multi-Sensor Inertial Odometry
Masked Next-Scale Prediction For Self-Supervised Scene Text Recognition
MASS: Motion-Aware Spatial–temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Materialistic RIR: Material Conditioned Realistic RIR Generation
MathAll: A Real-World Benchmark for Mathematical Reasoning and Cross-Modal Understanding Evaluation in Omni-MLLMs
MDG: Masked Denoising Generation for Multi-Agent Behavior Modeling in Traffic Environments
M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?

« prev Page 8/16 next »