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
Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss
Revisiting Real-Time Detection Transformer with Efficient Encoder Design
Rich Feature Learning via Diversification
Riemannian Score-Based Diffusion for Language-Conditioned Grasp and Affordance Detection
RiGS: Rigid-Aware 4D Gaussian Splatting from a Single Monocular Video
RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
Robust Continual Unlearning Against Knowledge Erosion and Forgetting Reversal
Robust Image Self-Recovery Against Tampering using Watermark Generation with Pixel Shuffling
RodNet: Visual Pathway-Inspired Adaptive Sparse Network for Efficient Low-Light Image Enhancement
Rolling and Denoising: Rethinking Dynamic Modal Fusion for Multi-Modal Object Re-Identification
ROSE: Retrieval-Oriented Segmentation Enhancement
RU4D-SLAM: Reweighting Uncertainty in Gaussian Splatting SLAM for 4D Scene Reconstruction
RVLF: A Reinforcing Vision–Language Framework for Gloss-Free Sign Language Translation
S^2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
S³O: Selective Spatial-Spectral Operator for Cross-Scale Fusion
Safe Codebook: Token-Level Moderation for Safer Visual Autoregressive Generation
Safe-LLaVA: A Privacy-Preserving Vision Language Dataset and Benchmark for Biometric Safety
SafetyBPO: Bidirectional Preference Optimization for Safe Text-to-Image Generation
SAGA: Semantic Anchor-Guided Alignment for Multi-Source Domain Adaptive Object Detection
SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
SA-Matching DETR: A Lightweight Transformer Detector with Enhanced Scale Adaptive Matching
SAT: Selective Aggregation Transformer for Image Super-Resolution
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
Scaling Pre-Training to One Hundred Billion Data for Vision Language Models
Scaling Spatial Reasoning in MLLMs Through Programmatic Data Synthesis
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
SciPostGen: Bridging the Gap Between Scientific Papers and Poster Layouts
SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters
SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
SCOPE: Spatially Ordered Continual Learning for 3D Segmentation
SCP: Spatial Causal Prediction in Video
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Seeing Helps Reasoning in Language Models
Seeing the Abstract: A Benchmark for Visual-Only Metaphor Understanding in Multimodal Large Language Models
Seeing Through Fog: Towards Fog-Invariant Action Recognition
Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting
See Tomorrow, Act Today: Foresight-Driven Autonomous Driving
Self-Evolving 3D Scene Generation from a Single Image
Semantic Guided Feature Disentanglement and Reconstruction for Domain Adaptive Object Detection
SemanticMoments: Training-Free Motion Similarity via Third Moment Features
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
SFS-DETR: Spatial-Frequency Selection for UAV Object Detection
SGST-Transformer: A Spherical Geometry-Aware Spatio-Temporal Transformer for 360° Video Saliency Prediction
Shape and Texture Recognition in Large Vision-Language Models
ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-Based 3D Scene Understanding

« prev Page 12/16 next »