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
CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering
CETCam: Camera-Controllable Video Generation via Consistent and Extensible Tokenization
ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking
CLASH: A Benchmark for Cross-Modal Contradiction Detection
Class-Aware Drift Compensation for Non-Uniform Semantic Shift in Continual Learning
CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models
CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
CLLAP: Contrastive Learning-Based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion
CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation
CogNet: Multi-Agent Collaborative Reasoning and Verification for Salient Object Ranking
Cognitive Attack Detection in Augmented Reality (CADAR): A Neuro-Symbolic Approach with Particle Filtering on Perception Graphs
CoherentHand: Temporally Consistent 3D Hand Trajectory Synthesis with Semantic Motion Priors
Concept Erasure via Attention Redirection
Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometric Problem Solving
Conformal Cross-Modal Active Learning
ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation
Consistent Video Editing as Flow-Driven Image-to-Video Generation
Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
Continual Adaptation of Vision Foundational Models for Semantic Segmentation in Adverse Weather
Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
Controllable Radar Simulation with Waveform Parameter Embedding
ControlPose: High-Fidelity Pose-Controlled Image Generation with Multi-Faceted Pose Disentanglement
CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
CoTFly: Making UAVs Think Where to Fly Next Through Visual Chain-of-Thought Reasoning
Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination
CoVCR: Bridging Visual Narrative Gaps via Context Generation for Robust Commonsense Reasoning
CP-IMoE: Collaborative Prompt-Guided Interactive Mixture-of-Experts for Incomplete Multimodal Learning
CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension
Cross-Dimensional Forgery Pattern Extraction for Generalizable Forgery Localization Framework
Cross-Resolution Diffusion Models Via Network Pruning
CrossWeaver: Towards Efficient Cross-Modal Interweaving and Decoupling for Weakly-Aligned Multispectral Object Detection
CrowdVerse: A Bidirectional Reality-Calibrated Benchmark for Crowd Understanding and Simulation
CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels
CtrlISP: Rescuing Low-Light RAW Images via Controllable Neural ISP
CurrMix: Curriculum-Enhanced MixUp for Long-Tailed Visual Recognition
D^2-STX: Decoupling Spatial-Temporal Cross-Attention for Dual-Branch Repetitive Action Counting
D4C: Data-Free Quantization for Contrastive Language-Image Pre-Training Models
DA-CLIP: Mitigating Granularity Mismatch in Zero-Shot Anomaly Detection via Decoupled Text-Visual Alignment
DaMN: Deleting and Migrating Normalization Layers from Transformers
DARTS: Distance-Aware Robust Training for Selective Classification
Debiased One-Shot NAS Via Density-Aware Sampling
Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction
Decoupled Scale-Wise Autoregressive Modeling for Visual Generation
DEED: Dual-Channel Enhanced Ensemble Distillation for Uncertainty-Aware Recognition
Deepfake-Agent: Aggregating Semantic Forgery Clues for Generalizable Detection
Deep Parameter Interpolation for Scalar Conditioning

« prev Page 3/16 next »