About
Research & Development
MultiTrust-X: A New Benchmark for Trustworthy Multimodal AI
TLDR: MultiTrust-X is a new benchmark and framework for evaluating, analyzing, and mitigating trustworthiness issues in Multimodal Large Language Models (MLLMs). It defines a...
Research & Development
Adaptive RAG: How Feedback Loops Enhance AI’s Knowledge Retrieval
TLDR: This research paper surveys advanced Retrieval-Augmented Generation (RAG) systems that integrate 'feedback' during test-time to move beyond static retrieval. It categorizes feedback into...
Research & Development
SRDrone: Autonomous Drone Planning with Self-Refining AI
TLDR: SRDrone is a new system that enables industrial drones to plan and execute complex tasks autonomously, without human intervention. It uses a continuous...
Research & Development
SurGE: A New Benchmark for Evaluating Automated Scientific Survey Generation
TLDR: SurGE (Survey Generation Evaluation) is a new benchmark introduced by researchers from Tsinghua University to evaluate automated scientific survey generation in computer science....
Research & Development
Kitchen-R: A New Benchmark for Integrated Robot Planning and Control in Simulated Kitchens
TLDR: Kitchen-R is a novel benchmark that unifies the evaluation of high-level task planning and low-level robot control in a simulated kitchen environment. It...
Research & Development
StreamMem: Efficient Memory Management for AI in Streaming Video Understanding
TLDR: StreamMem is a novel method that allows Multimodal Large Language Models (MLLMs) to efficiently process and understand long, streaming videos without running out...