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
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
SLAD : Shared LoRA Adapters for Task Specific Distillation
SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance
Softmax-GS: Generalized Gaussians Learning When to Blend or Bound
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
SoREL: Soft-Label Refurbishment with Ensemble Learning for Noisy Long-Tailed Classification
SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery
Spatial Transcriptomics as Images for Large-Scale Pretraining
Speed3R: Sparse Feed-Forward 3D Reconstruction Models
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration
Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression
SPOT: Sparsification with Attention Dynamics via Token Relevance in Vision Transformers
Stability and Non-Local Modeling in Hybrid Convolution–Transformer Networks for Snapshot Hyperspectral Reconstruction
Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
Stochastic Perturbations Improve Distribution-to-Distribution Generative Models
STORM: End-to-End Referring Multi-Object Tracking in Videos
Stream3D: Streaming Zero-Shot 3D Instance Segmentation with Multi-View Noise Mask Filtering and Manifold Refining
StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
SuperGlasses: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses
SurfaceGS: Dynamic Surface Gaussian Splatting for Urban Driving Scenes
SurfelOcc: Self-Supervised Occupancy Prediction via 2D Surfel Splatting
Surgical Procedural Planning as 3D World Modelling: Towards Automated Pulmonary Resection
SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction
SwiftPie: Lightning-Fast Subject-Driven Image Personalization via One Step Diffusion
SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
Switch-JustDance: Benchmarking Whole-Body Motion Tracking Controllers using a Commercial Console Game
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization with Multi-Video 4D Gaussian Splatting
SyntheticManga: Training-Free Manga Generation with Phased Diffusion
TALENT: Target-Aware Efficient Tuning for Referring Image Segmentation
TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation
TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
TAPNext++: What’s Next for Tracking Any Point (TAP)?
Tap, Scan, Exploit: The Hidden Vulnerabilities of Everyday QR Codes
Task-Specific Knowledge Improves Generalization: A Logits-Based Framework for Continual Learning of Vision-Language Models
Teleoperation, Simulation, or Human Video? Data Utilization Law for Robot Manipulation
Temporally Consistent Long-Term Memory for 3D Single Object Tracking
Temporally-Smooth Global Bundle Adjustment for Real-Time Dense Visual SLAM
Test-Time Distillation for Continual Model Adaptation
TextBind: Your Vision-Language Models are Naturally Unified Multimodal Models
Text-Driven Reasoning Video Editing via Reinforcement Learning on Digital Twin Representations
Texture-Guided Multiscale Cross-Modal Fusion for AI-Generated Image Quality Assessment
The DeepSpeak Dataset
The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning
THEval. Evaluation Framework for Talking Head Video Generation

« prev Page 13/16 next »