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
HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching
HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal–Image Modeling and Understanding
HEDA: Hyperbolic-Euclidean Dual Adaptation for Robust Real-World Point Cloud Completion
Hi3Doc: Hierarchical Tri-Level Representations for Multimodal Long-Document Understanding
HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints
Hierarchical Textual Knowledge for Enhanced Image Clustering
HippoMM: Hippocampal-Inspired Multimodal Memory for Long Audiovisual Event Understanding
HiStream: Efficient High-Resolution Video Generation via Redundancy Eliminated Streaming
HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models
HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D
Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters
HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model
HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes
How far have we Gone in Generative Image Restoration? A Study on its Capability, Limitations and Evaluation Practices
How to Achieve Prototypical Birth and Death for OOD Detection?
Human-Intervention Segmentation via Federated Intent Embedding and Multi-Mask Recommendation
HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
HyperFM: A Efficient Hyperspectral Foundation Model with Spectral Grouping
HypHOI: Exploring Hierarchical Hyperbolic Embeddings for Human-Object Interaction Detection
IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
If you can Describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions
IM-Animation: An Implicit Motion Representation for Identity-Decoupled Character Animation
Improving Autoregressive Image Generation Through Coarse-to-Fine Token Prediction
Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering
Improving Synthesized Image Detection by Disentangling Generator-Shared and Generator-Specific Image Artifacts
Indexing Multimodal Language Models for Large-Scale Image Retrieval
InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models
Inference-Time Alignment of Diffusion Models via Evolutionary Algorithms
InstaDA: Augmenting Instance Segmentation Data with Dual-Agent System
Instant Colorization of Gaussian Splats
Instruction-Focus-Prompt-Semantics-Driven Structural Prompts for Universal SAM Segmentation
Intelligent Photo Retouching with Language Model-Based Artist Agents
IntentEdit: Multi-Agent Reasoning for Intent-Driven Complex Image Editing
INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
IRDINO: Adapting DINOv3 with Second-Order Motion Awareness for Moving Infrared Small Target Detection
Is Prompt Selection Necessary for Task-Free Online Continual Learning?
Is Your Text-to-Image Model Robust to Caption Noise?
iTCTSL: Interpretable Tropical Cyclone Track and Intensity Forecasting via Task Sensitive Learning
JACoP: Joint Alignment for Compliant Multi-Agent Prediction
Jailbreaking Frontier Foundation Models Through Intention Deception
Jano: Adaptive Diffusion Generation with Early-Stage Convergence Awareness
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
KGGAT: Knowledge-Guided Graph Attention Network for Multi-Label Image Classification
KnowMTP: A Knowledge-Guided Framework for Multi-Agent Trajectory Prediction in Autonomous Driving
Label-Agnostic Category Discovery
LangFlash: Feed-Forward 3D Language Gaussian Splatting from Sparse Unposed Images
Language-Augmented Semantic Priors for B-Spline Surface Fitting
Large Multimodal Models as General In-Context Classifiers

« prev Page 7/16 next »