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
UnrealSpace: Analyzing Spatial Understanding and Reasoning in Controllable Simulation
Unsupervised Graph Partitioning Framework for Background Suppression in Multi-Query Vehicle Re-Identification
USV: Unified Sparsification for Accelerating Video Diffusion Models
VACoT: Rethinking Visual Data Augmentation with VLMs
VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal Reinforcement Learning
Value Bounds and Convergence Analysis for Averages of LRP Attributions
Variable-View Diffusion with Geometric Uncertainty Unlocks LiDAR Upsampling
VEBench: Benchmarking Large Multimodal Models for Real-World Video Editing
VeCoR — Velocity Contrastive Regularization for Flow Matching
VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
Verify Claimed Text-to-Image Models Via Boundary-Aware Prompt Optimization
VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
VHOI: Controllable Video Generation of Human–Object Interactions from Sparse Trajectories via Motion Densification
Vibra Verse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning
Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
Video Generation Models are Good Latent Reward Models
Video Inspector: An Agentic-RL Framework and Benchmark for Human-Aligned Generative Video Evaluation
VideoMatGen: PBR Materials Through Joint Generative Modeling
VIDEOP2R: Video Understanding from Perception to Reasoning
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
Video Reasoning Without Training
VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMs
VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
VirPro: Visual-Referred Probabilistic Prompt Learning for Weakly-Supervised Monocular 3D Detection
VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation
Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
Vision Language Models are Confused Tourists
Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning
Vision-Language Models for Automated 3D PET/CT Report Generation
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models
Visual Reasoning Through Tool-Supervised Reinforcement Learning
Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI
VoQA: Visual-only Question Answering
Vote-in-Context: VLMs as Explainable Zero-Shot Rank Fusers
VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-Based Deepfake Detection
VR-CLIP: Visual Refinement of CLIP for Zero-Shot Semantic Segmentation
VRSA: Jailbreaking Multimodal Large Language Models Through Visual Reasoning Sequential Attack
VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models
VSI: Visual–Subtitle Integration for Keyframe Selection to Enhance Long Video Understanding
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
Wake the Sleeping Weights: Sparsely-Activated Continual Test-Time Adaptation for Medical Image Segmentation
Watermarking Matters for Deepfake Detection: A Proactive Method for Detecting Forgeries Under Conventional Attacks
Weakly-Supervised Referring Video Object Segmentation Through Text Supervision
Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning
WGS: Watertight Geometry Standardization for Scalable 3D Generation

« prev Page 15/16 next »