MLDS 2019: Balaji Viswanathan of Invento Robotics at Machine Learning Developers Summit 2019
summary
Balaji Viswanathan discusses multimodal natural language processing that extends beyond speech recognition to handle multiple input types; he frames the problem of integrating modalities (such as speech plus other signals) for better language understanding. The talk focuses on approaches used at Invento Robotics for building multimodal NLP systems, likely including system design and practical considerations for deploying such models.
AI-written summary · about
related talks
30mRoblox's Journey to Supporting Multimodality on vLLM
15mMulti-Modal AI Optimization: Combining Text, Vision, and Speech Efficiently
27mThe Cutting Edge of AI: From LLMs to Multimodal Intelligence
40mKeynote: Open-source Multimodal AI in the Wild
19mLLM-Enhanced Multimodal AI: Revolutionizing Audio/Video Interaction
37mA Practical Guide to Robust Multi modal Machine Learning in Education
20mMultimodal language models
08mQ n A with Dr Ananth Sankar