SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Paper • 2603.19028 • Published • 15
Niccolò Biondi
NiccoBiondi
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models upvoted a paper 1 day ago
TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation upvoted a paper 1 day ago
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language ModelsOrganizations
upvoted a paper about 3 hours ago
upvoted 2
papers 1 day ago
upvoted 5
papers 18 days ago
On Large Multimodal Models as Open-World Image Classifiers
Paper • 2503.21851 • Published • 8
Loomis Painter: Reconstructing the Painting Process
Paper • 2511.17344 • Published • 20
Specificity-aware reinforcement learning for fine-grained open-world classification
Paper • 2603.03197 • Published • 16
Large Multimodal Models as General In-Context Classifiers
Paper • 2602.23229 • Published • 26
Compositional Caching for Training-free Open-vocabulary Attribute Detection
Paper • 2503.19145 • Published • 3
upvoted 2
papers 3 months ago
upvoted 7
papers over 1 year ago
MUST-VQA: MUltilingual Scene-text VQA
Paper • 2209.06730 • Published • 2
CTE: A Dataset for Contextualized Table Extraction
Paper • 2302.01451 • Published • 2
Comics Datasets Framework: Mix of Comics datasets for detection benchmarking
Paper • 2407.03540 • Published • 3
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
Paper • 2407.03550 • Published • 2
One missing piece in Vision and Language: A Survey on Comics Understanding
Paper • 2409.09502 • Published • 24
Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements
Paper • 2405.02581 • Published • 2
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
Paper • 2407.09435 • Published • 23