About
Research & Development
MoHoBench: A New Benchmark for Evaluating Honesty in Multimodal AI
TLDR: A new research paper introduces MoHoBench, the first systematic benchmark to assess the honesty of Multimodal Large Language Models (MLLMs) when faced with...
Research & Development
ST-GDance: Generating Realistic Group Choreography for Extended Music
TLDR: ST-GDance is a novel AI framework that generates long, collision-free group dance choreography from music. It achieves this by decoupling spatial and temporal...
Research & Development
Enhancing Teamwork: How Legible AI Agents Improve Collaboration
TLDR: This research explores "legibility" in AI, which is how clearly an agent communicates its intentions through its actions. It extends this concept to...
Research & Development
Self-Aware AI: Improving Safety in Vision-Language Models
TLDR: Large Vision-Language Models (LVLMs) are vulnerable to harmful inputs because their safety mechanisms operate in early layers, before the model fully develops semantic...
Research & Development
Assistax: A New Era for Reinforcement Learning in Assistive Robotics
TLDR: Assistax is a novel open-source, hardware-accelerated benchmark for training reinforcement learning algorithms in assistive robotics. Utilizing JAX and MuJoCo's MJX, it achieves significant...
Research & Development
DualSG: Enhancing Time Series Forecasting with Semantic Guidance from Language Models
TLDR: DualSG is a new framework for multivariate time series forecasting that uses Large Language Models (LLMs) as "semantic guides" rather than direct forecasters....