About
Research & Development
HDSim: Crafting Human-like Traffic for Advanced Self-Driving Tests
TLDR: HDSim is a new simulation framework that uses cognitive theory and large language models (LLMs) to create highly realistic and diverse human-like traffic...
Research & Development
Enhancing Video Creation with Precise Spatial Control: Introducing SSG-DiT
TLDR: SSG-DiT is a new framework for controllable video generation that tackles "semantic drift" by using a two-stage process. It first generates a text-aware...
Research & Development
Unlocking Low-Resource Language Performance in LLMs Through Neuron Overlap
TLDR: A new method, BridgeX-ICL, improves cross-lingual performance in Large Language Models (LLMs) for low-resource languages without costly fine-tuning. It identifies 'overlap neurons' shared...
Research & Development
Evaluating Language Models on Logical Reasoning: The Challenge of Natural Language Satisfiability
TLDR: A research paper investigates how transformer-based language models (TLMs) perform on natural language satisfiability (NLS) problems, which involve determining if a set of...
Research & Development
Highway Safety Enhanced by AI: A Multi-Agent Approach to Scene Understanding
TLDR: This paper introduces a multi-agent AI framework for comprehensive highway scene understanding. It uses a large AI model (like GPT-4o) to generate detailed...
Research & Development
SSFO: A Self-Supervised Method for Improving LLM Faithfulness in RAG Systems
TLDR: SSFO (Self-Supervised Faithfulness Optimization) is a novel approach that enhances the faithfulness of Large Language Models (LLMs) in Retrieval-Augmented Generation (RAG) systems. It...