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
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
A Simple Framework for Visual Navigation
Assessing the Reliability of Image Quality Metrics and Mitigating Quality Bias in Generative Models
Asymmetric Collaborative Distillation for Asymmetric Image Retrieval
Attention-Guided Energy Optimization for Label-Aligned Anomaly Generation
Attention Never Lie: Visual Attention Defocus Reveals and Rectifies Hallucinations in MLLMs
Attention-Space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
A Unified Privacy-Utility Framework for Collaborative Inference via Randomized Smoothing
AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
Autoregressive Universal Video Segmentation Model
Benchmarking Layout-Guided Diffusion Models Through Unified Semantic-Spatial Evaluation in Closed and Open Settings
Benchmarking Vision-Language Models Under Contradictory Virtual Content Attacks in Augmented Reality
Beyond 3D Geometry: M3FD, a Large-Scale Dataset and Benchmark for Multimodal 3D Perceptual Understanding
Beyond Accuracy: An Empirical Study of Perception Stability in Multimodal Large Language Models
Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
Beyond Pixel Loss: Video-INRs Prefer Perceptual Optimization
Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models
Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
Beyond Single Object: Learning 3D Relations with Large Language Models
Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
Beyond Syntax: Action Semantics Learning for App Agents
Beyond Voxel 3D Editing : Learning from 3D Masks and Self-Constructed Data
Bi-Level Optimization for Single Domain Generalization
Bind-Your-Avatar: Multi-Character-Talking Video Generation with Dynamic 3D-Mask-Based Embedding Router
BiomedHELIX : HiErarchical-Local Interaction eXploration for Biomedical Vision-Language Models
BitTP: The Lightweight Trajectory Prediction Model with BitLLM for Edge-Devices
BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis
Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting
BLMT-Stereo: Breaking the Local Minima Trap of Iterative Stereo Matching
Block Cascading: Training Free Acceleration of Block-Causal Video Models
Blockwise Divide-and-Aggregate for Image Restoration using Diffusion Priors
BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities
B-MoE: A Body-Part-Aware Mixture-of-Experts “All Parts Matter” Approach to Micro-Action Recognition
Bootstrap Your Own Classifier: Your Pretrained Vision Models are Secretly Strong Continual Learners
Brain-Inspired Multimodal Spike Neural Network for Image-Text Retrieval
BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language Decoding
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Breaking Degradation Coupling: A Structural Entropy–Guided Decoupled Framework and Benchmark for Infrared Enhancement
Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings
BridgeDiffusion: Latent Space Optimization for Independent Body-Part Generation with Motion Consistency Bridges in Interactive Dance
Bridge Your Fields: MeteoNet for Efficient Non-Uniform Meteorological Field Reconstruction
Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning
C^2T: Captioning-Structure and LLM-Aligned Common-Sense Reward Learning for Traffic–Vehicle Coordination
C3-Diff: Super-Resolving Spatial Transcriptomics via Cross-Modal Cross-Content Contrastive Diffusion Modelling
CADReasoner: Iterative Program Editing for CAD Reverse Engineering
CADRNet: Cognitively-Inspired Active Vision for 3D Reasoning Segmentation via Differentiable Rendering
Can Textual Reasoning Improve the Performance of MLLMs on Fine-Grained Visual Classification?
CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

« prev Page 2/16 next »