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
OminPSD: Layered PSD Generation with Diffusion Transformer
OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism
OmniHead: A Unified Model for Dynamic Nonverbal Facial Behaviors
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
Once for All: An End-to-End Paradigm for VLM-Based Domain-Generalized Object Detection
One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
One Model for All: Unified Try-On and Try-Off in Any Pose via LLM-Inspired Bidirectional Tweedie Diffusion
Online Interpretable Matrix Decomposition for Large-Scale Streaming Data
OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution
On the Feasibility and Opportunity of Autoregressive 3D Object Detection
On the Group Disparities Arising from Machine Unlearning
Open World Image Aesthetic Assessment
Optimizing Certified Radius of Zero-Shot Composed Image Retrieval via Text Guidance
Organizing Unstructured Image Collections using Natural Language
OTPrune: Distribution-Aligned Visual Token Pruning Via Optimal Transport
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Models
P^2CS: Parallel Point Cloud Pre-Training with Semantic Consistency
PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
PaM-MIL: Proliferation and Metastasis Enhanced Localization for Multiple Instance Learning on Pathology Images
Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers
Parallel In-Context Learning for Large Vision Language Models
PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views
PBSBench: A Multi-Level Vision-Language Framework and Benchmark for Hematopathology Whole Slide Image Interpretation
PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting
PEdit: Pareto-Guided Image Editing via Dynamic Latent Trajectory Control
PEPR: Privileged Event-Based Predictive Regularization for Domain Generalization
Personalized Functional Brain Network Modeling with Adaptive Auto-Weighted Learning for Automatic Brain Disorder Diagnosis
Perturb and Recover: Fine-Tuning for Effective Backdoor Removal from CLIP
PestVL-Net: Enabling Multimodal Pest Learning Via Fine-Grained Vision-Language Interaction
Phantasia: Context-Adaptive Backdoors in Vision Language Models
PhyFusion: Physics-Aware Infrared and Visible Image Fusion via Modality-Specific Physical Priors
PHYLOMAN: Generative Behavior Control via Fusing LLM Planning and Physics-Based Control
PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
Physics-Informed Reward Framework for Vision-Language Driven Safe Autonomous Driving
Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline
PlanGS: Active 3D Gaussian Reconstruction with Real-Time Planning
PLR-Gate: Real-Time Gradient Privacy Assessment and Gated Transmission for Secure Federated Learning
Plug-and-Play Dynamic In-Context Learning with Stochastic Regularization for Screen Content Image Super-Resolution
PolyReal: A Benchmark for Real-World Polymer Science Workflows
POMA-3D: The Point Map Way to 3D Scene Understanding
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
Pose-dIVE: Pose-Diversified Augmentation for Person Re-Identification
POS-ISP: Pipeline Optimization at the Sequence Level for Task-Aware ISP
Positive Divide and Negative Discrepancy: A New Perspective on Multi-Label Logit Distillation
PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation Via Multi-Agent LLMs

« prev Page 10/16 next »