About
Research & Development
Making Self-Driving Cars Smarter: A Low-Rank Solution to VLM Hallucinations
TLDR: A new low-rank method effectively reduces hallucinations in Vision Language Models (VLMs) used for autonomous driving. By analyzing multiple VLM-generated captions and identifying...
Research & Development
Large Language Models and Loop Invariants: A Performance Review
TLDR: This research paper evaluates the performance of Large Language Models (LLMs) in generating and fixing loop invariants, which are crucial for automated program...
Research & Development
CoFineLLM: Enhancing Robot Planning Reliability with Smarter Language Model Training
TLDR: CoFineLLM is a novel framework that fine-tunes Large Language Models (LLMs) for robot planning by integrating Conformal Prediction directly into the training process....
Research & Development
TabRAG: Better Information Extraction from Tables in RAG Systems
TLDR: TabRAG is a new parsing-based Retrieval-Augmented Generation (RAG) pipeline designed to improve how AI systems handle documents rich in tabular data. It addresses...
Research & Development
Enhancing Audio-Language Models with 3D Spatial Perception
TLDR: SPUR is a new framework that adds spatial audio understanding to existing Large Audio-Language Models (LALMs). It uses a First-Order Ambisonics (FOA) encoder...
Research & Development
Boosting Animal Re-Identification with Smart Data Sampling and Constraint-Aware Clustering
TLDR: A new active learning framework, Ambiguity-Aware Sampling (AAS), and a Non-Parametric, Plug-and-Play (NP3) algorithm have been developed to significantly improve animal re-identification (Re-ID)...