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
PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation
PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
Pre-Trained Models Can Count (Almost): Exploring Quantitative Structure in Visual Representations
PrismPrune: Decoupling Saliency and Diversity in Attention for Efficient Visual Token Pruning in VLMs
ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction
ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
Prompt-Driven Small Object Instance Segmentation in Earth Observation
Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models
ProSM: Progressive Soft Masking for Fine-Grained Remote Image Segmentation
Proto-SaGa: Prototype-Based 3D Scene Segmentation with Semantic-Aware Gaussian Grouping
Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering
PSLIF: A Primary-Supplementary LIF Neuron for Spiking Neural Networks
PTF-CT: Polar-Aware Temporal-Frequential Iterative Reconstruction for Sparse-View CT
PureSpace: A Benchmark for Abstract Spatial Reasoning in Vision-Language Models
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution
QENN: A Quantum Entanglement-Inspired Neural Network for Interaction and Relationship Prediction in Story Videos
Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
Quantifying the Gap Between Understanding and Generation Within Unified Multimodal Models
QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery
R^2MoE: Representation and Expert Selection Dual-Regularized Mixture-of-Experts for Multimodal Clinical Data
RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes
RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation using Agglomerative Models
Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection
Re^2MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement
ReaAct: Bridging Robotic Reasoning and Action Generation Toward Real-World Spatial Generalization
RealDiffusion: Physics-Informed Attention for Multi-Character Storybook Generation
Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
ReCliFF: Adaptive Orthogonal Decoupling for Federated Fine-Tuning of Medical MLLMs
ReConText3D: Replay-Based Continual Text-to-3D Generation
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
Recursive Think-Answer Process for LLMs and VLMs
RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes
ReFoCUS: Reinforcement-Guided Frame Optimization for Contextual Understanding
Region-Aware Hierarchical Sub-Feature Alignment for Robust EEG-Based Visual Decoding
RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference
Reliable Test-Time Adaptation Via Evidential Uncertainty Modeling in Vision–Language Models
ReMem: A Dynamic Memory Evolution Detector for Zero-Shot Anomaly Detection
Res2SPDNet: Multi-Granularity SPD Matrix Residual Learning for Signal Classification
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
Rethinking Conditioning in Diffusion Models: Dynamic Token Scheduling for Efficient and Aligned Text-to-Image Generation
Rethinking Medical High-Modality Learning Under Missingness — A Long-Tailed Distribution Perspective
Rethinking Training Dynamics in Scale-Wise Autoregressive Generation
Rethinking VLMs for Image Forgery Detection and Localization
Rethinking Whole-Body CT Image Interpretation: An Abnormality-Centric Approach
Retrieval-VLA: Training-Free In-Context Adaptation for Vision-Language-Action Models
Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models
Revisiting Articulated Parts Perception in Robot Manipulation
Revisiting Image Manipulation Localization Under Realistic Manipulation Scenarios

« prev Page 11/16 next »