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
Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data
EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Eigen-Value: Efficient Domain-Robust Data Valuation Via Eigenvalue-Based Approach
EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift
Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios
Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
Entropy-Based Visual Re-Perception Inference for Multimodal Models
Environmental Understanding Vision-Language Model for Embodied Agent
Equivariant Unsupervised Object Detection with Learnable Riesz Transform and Composite Spatial Transformers
Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
EscherNet++: A Scalable Multi-View Framework for Amodal Completion, Novel View Synthesis and Feed-Forward 3D Reconstruction
Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
Evaluating Dataset Watermarking for Fine-Tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach
Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams
Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration
Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
Exploiting the Source-Asymmetry Confidence Gap for Generalizable AI-Generated Image Detection
Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors
Extending Segment Anything Model 2 to Multi-Object Tracking by Optimizing Hierarchical Trajectory Memory
Face Time Traveller : Travel Through Ages Without Losing Identity
FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting
FALCON: Fast Adaptive Lightweight Computation of Intensities and Events for Depth Estimation
Fast Autoregressive Video Generation with Diagonal Decoding
Fast Generative DeOcclusion for Vision and Robotics
Fast-HOI: Fast Human-Object Interaction Synthesis via Distilled Interaction Prior and Physical Constrains
Fast Kernel-Space Diffusion for Remote Sensing Pansharpening
FastMMoE: Accelerating Multimodal Large Language Models Through Dynamic Expert Activation and Routing-Aware Token Pruning
FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-Aware and Contrastive Learning
FedAR: Attribute-Guided Representation Learning for Heterogeneous Federated Learning
FedCVC: Federated Primal-Dual Learning with Client-Driven Virtual Compensation for Mitigating Dual Drift
FedErase: Personalized Federated Unlearning for Text-to-Image Diffusion Models
FedNPC: Stochastic Noise-Driven Post-hoc Classifier Calibration Method for Federated Long-Tailed Learning
FedOrtho: Efficient Federated Unlearning Via Orthogonal Convolution and Adaptive Soft Pruning
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
FF3R: Feedforward Feature 3D Reconstruction from Unconstrained Views
FineCog-Nav: Integrating Fine-Grained Cognitive Modules for Zero-Shot Multimodal UAV Navigation
Fine-Grained Visual Prompt and Region Self-Distillation for Retrieval-Augmented VQA
Finetune Like You Pretrain: Boosting Zero-Shot Adversarial Robustness in Vision-Language Models
FIRE-CIR: Fine-Grained Reasoning for Composed Fashion Image Retrieval
FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
FlowSteer: Conditioning Flow Field for Consistent Image Restoration
FLToM: Robust Federated Learning with Theory-of-Mind Structure
ForenDeX: Unlocking Forensic Insights for Explainable AI-Generated Image Detection
ForestPrune: High-Ratio Visual Token Compression for Video Multimodal Large Language Models Via Spatial-Temporal Forest Modeling
ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FraQAT: Quantization Aware Training with Fractional Bits

« prev Page 5/16 next »