Talks
All the talks so far.
End-to-end Object Detection with Transformers
Rucha Bhalchandra JoshiPublished: at 02:00 PMThis talk presents DETR, a new method for object detection that streamlines the pipeline by removing the need for components like non-maximum suppression and anchor generation.
You Only Look Once - Unified, Real-Time Object Detection
Aritra MukhopadhayaPublished: at 02:00 PMThis talk discusses YOLO, a groundbreaking method for object detection. YOLO revolutionizes object detection with real-time processing, using a single network for bounding box and class probability predictions, excelling in speed and domain generalization.
DT-Solver - Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function
Rahul VishwakarmaPublished: at 02:00 PMThis talk discusses DT-Solver, a novel approach to automated theorem proving that uses dynamic-tree Monte-Carlo search and a proof-level value function for improved state exploration.
End-to-end Object Detection with Transformers
Rucha Bhalchandra JoshiPublished: at 02:00 PMThis talk presents DETR, a new method for object detection that streamlines the pipeline by removing the need for components like non-maximum suppression and anchor generation.
Handling position and visibility discontinuities for physically-based differentiable rendering
Annada Prasad BeheraPublished: at 02:00 PMIn this talk, we discuss handling position and visibility discontinuities for physically-based differentiable rendering.
Physics Aware Training
Jyotirmaya ShivottamPublished: at 02:00 PMThis talk discusses physics-aware training, a novel approach to training deep physical neural networks using backpropagation. Physics-aware training combines the scalability of backpropagation with the automatic mitigation of imperfections and noise achievable with in situ algorithms, enabling the training of controllable physical systems for machine learning tasks.