🤝 Open to Collab
Marcus Gawronsky
marcusinthesky
AI & ML interests
Representation Learning
Recent Activity
liked a dataset about 20 hours ago
pangram/editlens_iclr updated a collection 3 days ago
PricingPerspectiveOrganizations
Probability-valued firm information is used to study asset co-movement, construct interaction fields, and certify portfolio diversification.
-
Systematic Covariance Envelopes from Wasserstein Geometry: Evidence from Language-Model Representations
Paper • 2410.23447 • Published • 1 -
Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
Paper • 2608.29669 • Published • 2 -
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Paper • 2608.29692 • Published • 2 -
Wasserstein Playground
🎯Watch wasserstein geometry impact returns co-movement.
-
Simple Open-Vocabulary Object Detection with Vision Transformers
Paper • 2205.06230 • Published • 4 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 148k • 159 -
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Paper • 2305.07011 • Published • 5 -
Multi-Modal Classifiers for Open-Vocabulary Object Detection
Paper • 2306.05493 • Published • 5
-
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Paper • 2410.10139 • Published • 51 -
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Paper • 2410.10563 • Published • 37 -
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
Paper • 2410.10783 • Published • 26 -
TVBench: Redesigning Video-Language Evaluation
Paper • 2410.07752 • Published • 5
-
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Paper • 2403.19651 • Published • 26 -
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Paper • 2404.04125 • Published • 29 -
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 30 -
Gecko: Versatile Text Embeddings Distilled from Large Language Models
Paper • 2403.20327 • Published • 47
Probability-valued firm information is used to study asset co-movement, construct interaction fields, and certify portfolio diversification.
-
Systematic Covariance Envelopes from Wasserstein Geometry: Evidence from Language-Model Representations
Paper • 2410.23447 • Published • 1 -
Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
Paper • 2608.29669 • Published • 2 -
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Paper • 2608.29692 • Published • 2 -
Wasserstein Playground
🎯Watch wasserstein geometry impact returns co-movement.
-
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Paper • 2410.10139 • Published • 51 -
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Paper • 2410.10563 • Published • 37 -
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
Paper • 2410.10783 • Published • 26 -
TVBench: Redesigning Video-Language Evaluation
Paper • 2410.07752 • Published • 5
-
Simple Open-Vocabulary Object Detection with Vision Transformers
Paper • 2205.06230 • Published • 4 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 148k • 159 -
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Paper • 2305.07011 • Published • 5 -
Multi-Modal Classifiers for Open-Vocabulary Object Detection
Paper • 2306.05493 • Published • 5
-
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Paper • 2403.19651 • Published • 26 -
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Paper • 2404.04125 • Published • 29 -
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 30 -
Gecko: Versatile Text Embeddings Distilled from Large Language Models
Paper • 2403.20327 • Published • 47