About
Research & Development
LEXPOL: A New Framework for Multi-Task Reinforcement Learning Using Language-Guided Skill Composition
TLDR: LEXPOL (Lexical Policy Networks) is a new multi-task reinforcement learning algorithm that uses natural language descriptions to guide an agent. It employs a...
Research & Development
Unlocking Future Hand Movements: A New AI System for 3D Hand Motion Forecasting
TLDR: ForeHand4D is a novel AI system that forecasts detailed 3D motion and articulation of both hands from a single everyday image. It overcomes...
Research & Development
Large Language Models Emerge as Adaptable Teammates for Human-AI Collaboration
TLDR: A new study explores how Large Language Models (LLMs) can act as 'policy-agnostic human proxies' to simulate human decision-making in heterogeneous AI teams,...
Research & Development
BanglaTalk: Bridging Communication Gaps for Bengali Dialects
TLDR: BanglaTalk is the first real-time speech assistant designed for diverse Bengali regional dialects. It uses a client-server architecture with Real-time Transport Protocol (RTP)...
Research & Development
Teaching Robots Complex Skills: A New Approach to Grounded Skill Discovery
TLDR: Reference-Grounded Skill Discovery (RGSD) is a novel algorithm that addresses the challenge of scaling unsupervised skill discovery to high-degree-of-freedom (DoF) agents. It achieves...
Research & Development
Unpacking AI’s Scientific Problem-Solving: The AInstein Framework
TLDR: AInstein is a new framework that tests if large language models (LLMs) can solve AI research problems using only their internal knowledge. It...