About
Research & Development
MASteer: Automating Trustworthiness Repair in Large Language Models
TLDR: MASteer is a novel end-to-end framework that enhances the trustworthiness of Large Language Models (LLMs) by automating the repair process. It uses a...
Research & Development
Building Better Benchmarks for Specialized AI Models
TLDR: The COMP-COMP framework offers a new approach to building benchmarks for domain-specific Large Language Models (LLMs). Moving beyond traditional 'scaling law' methods, it...
Research & Development
Enhancing AI Collaboration: How Language Models Learn to Navigate Complex Social Games
TLDR: This research introduces a framework for "multi-agentic LLMs" to improve decision-making and coordination in multi-agent systems. It integrates advanced prompt engineering, memory systems...
Research & Development
Benchmarking AI Agents: A New Standard for Evaluating Tool Use Capabilities
TLDR: MCPToolBench++ is a new large-scale benchmark for evaluating how well AI agents and Large Language Models (LLMs) use real-world tools via the Model...
Research & Development
Smart Privacy for Image Data: Optimizing Semantic Communication with Independent Jammers
TLDR: A new research paper introduces a novel covert semantic communication framework that secures the transmission of image meaning from a server to a...
Research & Development
THINK TUNING: A New Approach to Teaching LLMs How to Self-Reflect
TLDR: THINK TUNING is a novel interactive training framework that instills cognitive reflection and self-correction in Large Language Models (LLMs). Inspired by teacher-student feedback,...