CVPR 2026PastComputer vision
Third Workshop on Visual Concepts
VisCon 2026
- Submission deadline
- Apr 2, 2026, 07:59 UTCOpenReview-synced 2026-04-02 07:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (27)
Fetched from OpenReview (v2) on 2026-06-10.
A Taxonomy-Aware Evaluation for Open-Vocabulary Wildlife Detection
CGEBench: Benchmarking Concept Generalization of Promptable Image Segmentation Models
ConceptOT: Fine-Grained Vision-Language Alignment via Low-Rank Unbalanced Optimal Transport
CTRL-STEER: Closed-Loop Neuron Activation Control in Vision-Language-Action Models
Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
Do VLMs Reason About Faces? Probing the Perception-Reasoning Gap in Identity Judgment
Entropy-based Patchification Creates Semantic Tokens
Forecasting Animal Motion in the Wild
From Comparison to Composition: Towards Understanding Machine Cognition of Unseen Categories
Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles
Improved Vision-Language Alignment via Text-Conditioned Image Embeddings using Sparse Autoencoders
INSID3: Training-Free In-Context Segmentation with DINOv3
LandCIS: Hierarchical Semantic Anchoring for Concept-Centric Continual Segmentation
Learning Sparse Visual Representations via Spatial-Semantic Factorization
MCSBench: Probing Multimodal Conceptual Structure of Multimodal LLMs
Most of This Video Is Boring
Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations
Seeing Only What Exists: Visibility-Aware Contrastive Learning for Concept-Level Hallucination in Vision–Language Models
Self-Consistency for LLM-Based Motion Trajectory Generation and Verification
Semantic Concept Conditioning for State Space Image Super-Resolution
SPOT: Structured Prompting with Object-centric Tokens for open-world scene graphs
Test-Time Visual Concept Anchoring via Entropic Optimal Transport
Toward Compact and Structured Visual Representations in VLMs: SSM-Based Vision Encoders as an Alternative to Transformers
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
VCode: A Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation