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
DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning
DEGround: An Effective Baseline for Ego-Centric 3D Visual Grounding With a Homogeneous Framework
DELRER: Disease Evolution-Informed Longitudinal Radiology Report Generation
DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
Detecting Precise Hand Touch Moments in Egocentric Video
Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
DGD: Density Gradient-Guided Diffusion for Long-Tailed Clustering
DIAMOND-SSS: Diffusion-Augmented Multi-View Optimization for Data-Efficient SubSurface Scattering
Diffusion^2: Turning 3D Environments into Radio Frequency Heatmaps
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
DINO-VO: Learning Where to Focus for Enhanced State Estimation
Direct Language Embedding Enables Gaussian Splatting for Large Scenes
Discovering Attention Head Interactions in Vision Transformers
Disentangle Once, Control All: A Unified and Efficient Framework for Disentangling Multi-Condition Control in Human Video Generation
Disrupting Positional Encoding for Effective Open Set Recognition
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
Distilling Counterfactual Reasoning from Language to Vision: Causal Graph-Guided Post-Training for Video Understanding
Distilling Out-of-Distribution Knowledge from Large Language Models for CLIP Generalization
DM^3T: Harmonizing Modalities via Diffusion for Multi-Object Tracking
DMin: Scalable Training Data Influence Estimation for Diffusion Models
Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Model
Do Audio-Visual Large Language Models Really See and Hear?
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
Do LLMs and VLMs Share Reasoning Neurons? Evidence and Mechanisms of Cross-Modal Transfer
Do MLLMs Exhibit Human-Like Perceptual Behaviors? HVSBench: A Benchmark for MLLM Alignment with Human Perceptual Behavior
Do Vision Models Perceive Illusory Motion in Static Images Like Humans?
DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
DRA: Structure-Preserving Backdoor Erasure via Diagnosing, Recalibrating, and Adapting
DR-DPO: Dual-Regularized DPO for Efficient Dataset Condensation
Drive-Cascade: Autoregressive Occupancy to LiDAR and Video Synthesis
DSAA: Dual-Stage Attribute Activation for Fine-Grained Open Vocabulary Detection
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly Detection
Dual-Modality Anchor-Guided Filtering for Test-Time Prompt Tuning
Dual Strategies for Test-Time Adaptation
DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual Reasoning
dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning
Dynamic Full-Body Motion Agent with Object Interaction via Blending Pre-Trained Modular Controllers
Dynamic Scene Decomposition Beyond Moving Objects for High-Fidelity 3D Reconstruction in Autonomous Driving
DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion
Earthquake-Bench: Video Generation Benchmark for Earthquake Simulation
EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration
ECOC-IL: Robust and Efficient Label LDP for Imbalanced Learning
Eevee: Towards Close-up High-Resolution Video-Based Virtual Try-on
Efficient3D : A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Efficient Discrete Diffusion Model for Scalable Multi-Objective Traveling Salesman Problem
Efficient Document Parsing via Parallel Token Prediction
Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention
Efficient Unlearning Through Maximizing Relearning Convergence Delay
EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting

« prev Page 4/16 next »