10 accepted papers
We study the problem of assigning operations in a dataflow graph to devices to minimize execution time in a work-conserving system, with emphasis on complex machine learning workloads. Prior learning-based approaches face three limitations: (1) reliance on bulk-synchronous frameworks that under-util…
Multilingual ASR offers training, deployment and overall performance benefits, but models trained via simple data pooling are known to suffer from cross-lingual interference. Oracle language information (exact-prior) and language-specific parameters are usually leveraged to overcome this, but such a…
Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker’s identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE that uses natural language descriptions of speaking style in…
Dormant tree pruning is laborintensive but essential to maintaining modern highly-productive fruit orchards. In this work we present a closed-loop visuomotor controller for robotic pruning. The controller guides the cutter through a cluttered tree environment to reach a specified cut point and ensur
Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances in offline IL, existing techniques find it challenging to learn policies for long-horizon tasks and require significant…
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM serv…
Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our k…
We address the problem of adapting robot trajectories to improve safety, comfort, and efficiency in humanrobot collaborative tasks. To this end, we propose CoMOTO, a trajectory optimization framework that utilizes stochastic motion prediction to anticipate the human's motion and adapt the robot's jo…
We propose a novel concept of Deep Part Embeddings (DPEs), which can be used to learn new Convolutional Neural Networks (CNNs) for different classes. We define DPE as a neuron of a trained CNN along with its network of filter activations that is interpretable as a part of a class that the neuron con…
In this paper, we propose the Radial Loss which utilizes category and sub-category labels to learn an order-preserving fine-grained video similarity metric. We propose an end-to-end quadlet-based Convolutional Neural Network (CNN) combined with Long Short-term Memory (LSTM) Unit to model video simil…