50 citations
- Adobe Systems (United States)US1 paper
- Apple (United States)US1 paper
- Aston UniversityGB1 paper
- Bar-Ilan UniversityIL1 paper
- Carnegie Mellon UniversityUS1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Georgia Institute of TechnologyUS1 paper
- Google (United States)US1 paper
- Honda (Japan)JP1 paper
- Italian Institute of TechnologyIT1 paper
- Max Planck Institute for Intelligent SystemsDE1 paper
13 papers
Charge Migration and Residual Non-Linearity in NIRSpec BOTS Observations
Munazza K. Alam, Leonardo Ubeda, Qinyan +3
We investigate the effect of charge migration and residual non-linearity on the JWST/NIRSpec G395H NRS1 and NRS2 detectors using Bright Object Time Series (BOTS) observations of th…
Primal-Dual iLQR for GPU-Accelerated Learning and Control in Legged Robots
Lorenzo Amatucci, João Sousa-Pinto, Giulio Turrisi +3
This paper introduces a novel Model Predictive Control (MPC) implementation for legged robot locomotion that leverages GPU parallelization. Our approach enables both temporal and s…
Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results
Andrea Santilli, Adam Golinski, Michael Kirchhof +5
Uncertainty Quantification (UQ) in Language Models (LMs) is key to improving their safety and reliability. Evaluations often use metrics like AUROC to assess how well UQ methods (e…
Towards a World-English Language Model for On-Device Virtual Assistants
Rricha Jalota, Lyan Verwimp, Markus Nussbaum-Thom +3
Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally language-, region-, and in some cases, device-dependent, which increases the effort to scale and m…
A Multimodal Approach to Device-Directed Speech Detection with Large Language Models
Dominik Wagner, Alexander Churchill, Siddharth Sigtia +4
Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explo…
Streaming Anchor Loss: Augmenting Supervision with Temporal Significance
Utkarsh Oggy Sarawgi, John Berkowitz, Vineet Garg +5
Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the lear…