Picture for Beibin Li

Beibin Li

Alchemist: Towards the Design of Efficient Online Continual Learning System

Add code
Mar 03, 2025
Viaarxiv icon

PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathology

Add code
Feb 13, 2025
Viaarxiv icon

On the Emergence of Thinking in LLMs I: Searching for the Right Intuition

Add code
Feb 10, 2025
Figure 1 for On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Figure 2 for On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Figure 3 for On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Figure 4 for On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Viaarxiv icon

Towards Safer Heuristics With XPlain

Add code
Oct 19, 2024
Figure 1 for Towards Safer Heuristics With XPlain
Figure 2 for Towards Safer Heuristics With XPlain
Figure 3 for Towards Safer Heuristics With XPlain
Figure 4 for Towards Safer Heuristics With XPlain
Viaarxiv icon

Towards Foundation Models for Mixed Integer Linear Programming

Add code
Oct 10, 2024
Figure 1 for Towards Foundation Models for Mixed Integer Linear Programming
Figure 2 for Towards Foundation Models for Mixed Integer Linear Programming
Figure 3 for Towards Foundation Models for Mixed Integer Linear Programming
Figure 4 for Towards Foundation Models for Mixed Integer Linear Programming
Viaarxiv icon

Small Language Models for Application Interactions: A Case Study

Add code
May 23, 2024
Figure 1 for Small Language Models for Application Interactions: A Case Study
Figure 2 for Small Language Models for Application Interactions: A Case Study
Figure 3 for Small Language Models for Application Interactions: A Case Study
Figure 4 for Small Language Models for Application Interactions: A Case Study
Viaarxiv icon

Reflect-RL: Two-Player Online RL Fine-Tuning for LMs

Add code
Feb 20, 2024
Figure 1 for Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Figure 2 for Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Figure 3 for Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Figure 4 for Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Viaarxiv icon

Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native

Add code
Jan 17, 2024
Figure 1 for Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
Figure 2 for Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
Viaarxiv icon

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Add code
Aug 16, 2023
Viaarxiv icon

Large Language Models for Supply Chain Optimization

Add code
Jul 13, 2023
Viaarxiv icon