CVPR 2025PastComputer vision
Second Workshop on Visual Concepts
VisCon 2025
- Submission deadline
- Apr 16, 2025, 08:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (34)
Fetched from OpenReview (v2) on 2026-06-10.
BAR: Probing Brain Encoders with Concept-Based Explanations
Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
Beyond Language Priors: Enhancing Visual Comprehension and Attention in MLLMs
Can generative models generate novel objects the same as familiar objects?
Can Visual Encoder Learn to See Arrows?
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Contrastive Mean-Shift Learning for Generalized Category Discovery
Coreset Selection via LLM-based Concept Bottlenecks
Dictionary-based Framework for Interpretable and Consistent Object Parsing
Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning
Emergence and Evolution of Interpretable Concepts in Diffusion Models Through the Lens of Sparse Autoencoders
GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution
HyperVLM: Hyperbolic Space Guided Vision Language Modeling for Hierarchical Multi-Modal Understanding
Learning Hierarchically using Formal Concepts
Learning reusable concepts across different video understanding tasks
Memory-Modular Classification: Novel-Class Generalization with Web-Crawled Memory
On Achieving Perfect Multimodal Alignment
PartComposer: Composing Part-Level Concepts from Single-Image Examples
Physical Rule-Guided Convolutional Neural Network
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
Pruning Visual Concepts for Efficient and Interpretable Transfer Learning
Quantifying Interpretability in CLIP Models with Concept Consistency
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
Sequentially Acquiring Concept Knowledge to Guide Continual Learning
SGBD: Sharpness-Aware Mirror Gradient with BLIP-Based Denoising for Robust Multimodal Product Recommendation
SSCA: SigLIP-2 Sonar Concept Alignment
Text Slider: Efficient and Precise Concept Control for Video Generation and Editing via LoRA Adapters
Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics
Unsupervised Training of Vision Transformers with Synthetic Negatives
Vision language models have difficulty recognizing virtual objects
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
Where Do Erased Concepts Go in Diffusion Models?