Debadeepta Dey

Latest

• What Makes Convolutional Models Great on Long Sequence Modeling?
• AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
• LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
• FEAR: Ranking Architectures by their Feature Extraction Capabilities
• A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
• Blind Spot Detection for Safe Sim-to-Real Transfer
• Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations
• Efficient forward architecture search
• Anytime neural networks via joint optimization of auxiliary losses
• Overcoming blind spots in the real world: Leveraging complementary abilities for joint execution
• Reparameterized Variational Divergence Minimization for Stable Imitation
• Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention
• Airsim-w: A simulation environment for wildlife conservation with uavs
• Data-driven planning via imitation learning
• Discovering blind spots in reinforcement learning
• Learn-to-score: Efficient 3d scene exploration by predicting view utility
• Near Real-Time Detection of Poachers from Drones in AirSim.
• Adaptive information gathering via imitation learning
• Airsim: High-fidelity visual and physical simulation for autonomous vehicles
• Flight dynamics-based recovery of a UAV trajectory using ground cameras
• Learning to gather information via imitation
• No-regret replanning under uncertainty
• Safety-aware algorithms for adversarial contextual bandit
• Submodular trajectory optimization for aerial 3d scanning
• Vision and learning for deliberative monocular cluttered flight
• Predicting Sets and Lists: Theory and Practice
• Predicting multiple structured visual interpretations
• Knapsack constrained contextual submodular list prediction with application to multi-document summarization
• Learning monocular reactive uav control in cluttered natural environments
• Classification of plant structures from uncalibrated image sequences
• Contextual Sequence Prediction with Application to Control Library Optimization
• A cascaded method to detect aircraft in video imagery
• Efficient Optimization of Control Libraries
• Passive, long-range detection of aircraft: towards a field deployable sense and avoid system
• Prototype sense-and-avoid system for UAVs