Serge Belongie

RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding

SuperF: Neural Implicit Fields for Multi-Image Super-Resolution

Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation

MADGen:Minority Attribute Discovery in Text-to-Image Generative Models

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers

Balancing Perception and Distortion in Super Resolution via Spatial–Semantic Guidance

Unlearning-based Neural Interpretations

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Do better language models have crisper vision?

Concept Denoising Score Matching for Responsible Text-to-Image Generation