Lagos
- Asia > Japan > Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.14)
- North America > Canada > Ontario > Toronto (0.14)
- Africa > Democratic Republic of the Congo > Kinshasa Province > Kinshasa (0.04)
- (17 more...)
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (0.92)
- Europe > United Kingdom (0.04)
- Africa > Côte d'Ivoire (0.04)
- North America (0.04)
- Africa > Nigeria > Lagos State > Lagos (0.04)
- Asia > British Indian Ocean Territory > Diego Garcia (0.04)
- North America > United States > New Mexico > Bernalillo County > Albuquerque (0.04)
- Europe > United Kingdom (0.04)
- (2 more...)
- Information Technology > Data Science (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.93)
- Information Technology > Artificial Intelligence > Natural Language (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Clustering (0.47)
- Europe > Iceland (0.05)
- North America > United States > Utah > Salt Lake County > Salt Lake City (0.04)
- North America > United States > Massachusetts > Middlesex County > Reading (0.04)
- (9 more...)
SLYKLatent: A Learning Framework for Gaze Estimation Using Deep Facial Feature Learning
Adebayo, Samuel, Dessing, Joost C., McLoone, Seán
In this research, we present SLYKLatent, a novel approach for enhancing gaze estimation by addressing appearance instability challenges in datasets due to aleatoric uncertainties, covariant shifts, and test domain generalization. SLYKLatent utilizes Self-Supervised Learning for initial training with facial expression datasets, followed by refinement with a patch-based tri-branch network and an inverse explained variance-weighted training loss function. Our evaluation on benchmark datasets achieves a 10.9% improvement on Gaze360, supersedes top MPIIFaceGaze results with 3.8%, and leads on a subset of ETH-XGaze by 11.6%, surpassing existing methods by significant margins. Adaptability tests on RAF-DB and Affectnet show 86.4% and 60.9% accuracies, respectively. Ablation studies confirm the effectiveness of SLYKLatent's novel components.
- Europe > Netherlands > North Holland > Amsterdam (0.04)
- North America > United States > Wisconsin > Dane County > Madison (0.04)
- North America > Canada > British Columbia > Vancouver (0.04)
- (7 more...)
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
Deng, Ruixuan, Hu, Xiaoyang, Gilberti, Miles, Storks, Shane, Taxali, Aman, Angstadt, Mike, Sripada, Chandra, Chai, Joyce
We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just a handful of prompts. Focusing on concept-relation prediction tasks, we show that ablating these components for concepts (e.g., countries and words) and relations (e.g., capital city and translation language) changes model outputs in predictable ways, while amplifying these components induces counterfactual responses. Notably, composing relation and concept components yields compound counterfactual outputs. Further analysis reveals that while most concept components emerge from the very first layer, more abstract relation components are concentrated in later layers. Lastly, we show that extracted components more comprehensively capture concepts and relations than individual features while maintaining specificity. Overall, our findings suggest a modular organization of knowledge accessed through compositional operations, and advance methods for efficient, targeted LLM manipulation.
- Africa > Nigeria > Federal Capital Territory > Abuja (0.05)
- Asia > China > Beijing > Beijing (0.05)
- South America > Peru (0.04)
- (21 more...)
- Asia > Japan > Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.14)
- North America > Canada > Ontario > Toronto (0.14)
- Africa > Democratic Republic of the Congo > Kinshasa Province > Kinshasa (0.04)
- (17 more...)
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (0.92)
- Europe > United Kingdom (0.04)
- Africa > Côte d'Ivoire (0.04)
- North America (0.04)
- Africa > Nigeria > Lagos State > Lagos (0.04)
- Asia > British Indian Ocean Territory > Diego Garcia (0.04)
- North America > United States > New Mexico > Bernalillo County > Albuquerque (0.04)
- Europe > United Kingdom (0.04)
- (2 more...)
- Information Technology > Data Science (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.93)
- Information Technology > Artificial Intelligence > Natural Language (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Clustering (0.47)
Reinforcement Learning for Autonomous Point-to-Point UAV Navigation
Oyinlola, Salim, Subedi, Nitesh, Sarkar, Soumik
Unmanned Aerial Vehicles (UAVs) are increasingly used in automated inspection, delivery, and navigation tasks that require reliable autonomy. This project develops a reinforcement learning (RL) approach to enable a single UAV to autonomously navigate between predefined points without manual intervention. The drone learns navigation policies through trial-and-error interaction, using a custom reward function that encourages goal-reaching efficiency while penalizing collisions and unsafe behavior. The control system integrates ROS with a Gym-compatible training environment, enabling flexible deployment and testing. After training, the learned policy is deployed on a real UAV platform and evaluated under practical conditions. Results show that the UAV can successfully perform autonomous navigation with minimal human oversight, demonstrating the viability of RL-based control for point-to-point drone operations in real-world scenarios.
- North America > United States > Iowa > Story County > Ames (0.05)
- Africa > Nigeria > Lagos State > Lagos (0.04)
- Africa > Nigeria > Lagos State > Akoka (0.04)