Picture for Boyang Li

Boyang Li

A Training Data Recipe to Accelerate A* Search with Language Models

Add code
Jul 13, 2024
Viaarxiv icon

Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines

Add code
Jun 20, 2024
Viaarxiv icon

Multilingual Synopses of Movie Narratives: A Dataset for Story Understanding

Add code
Jun 18, 2024
Figure 1 for Multilingual Synopses of Movie Narratives: A Dataset for Story Understanding
Figure 2 for Multilingual Synopses of Movie Narratives: A Dataset for Story Understanding
Figure 3 for Multilingual Synopses of Movie Narratives: A Dataset for Story Understanding
Figure 4 for Multilingual Synopses of Movie Narratives: A Dataset for Story Understanding
Viaarxiv icon

Rationale-based Ensemble of Multiple QA Strategies for Zero-shot Knowledge-based VQA

Add code
Jun 18, 2024
Viaarxiv icon

Concept-skill Transferability-based Data Selection for Large Vision-Language Models

Add code
Jun 16, 2024
Viaarxiv icon

GridPE: Unifying Positional Encoding in Transformers with a Grid Cell-Inspired Framework

Add code
Jun 11, 2024
Viaarxiv icon

Improving Generalization of Neural Vehicle Routing Problem Solvers Through the Lens of Model Architecture

Add code
Jun 10, 2024
Viaarxiv icon

Async Learned User Embeddings for Ads Delivery Optimization

Add code
Jun 09, 2024
Viaarxiv icon

Neuro-Symbolic Temporal Point Processes

Add code
Jun 06, 2024
Viaarxiv icon

FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors

Add code
May 21, 2024
Figure 1 for FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Figure 2 for FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Figure 3 for FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Figure 4 for FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Viaarxiv icon