cover

Detailing the Primary Methodology Implemented in Our Models: Octopus v2

3 Apr 2025

In this section, we detail the primary methodology implemented in our models, followed by the dataset collection process essential for fine-tuning these models.

cover

Efficient On-Device LLMs: Function Calling and Fine-Tuning Strategies

3 Apr 2025

Due to memory limitations and lower inference speeds, deploying larger models on edge devices like PCs or smartphones is challenging.

cover

Octopus v2: An On-Device Language Model for Super Agent

1 Apr 2025

Language models have shown effectiveness in a variety of software applications, particularly in tasks related to automatic workflow.

cover

Dangerous Diagnoses? GPT-4V’s Role in Medical Image Interpretation

1 Apr 2025

GPT-4V struggles with medical image interpretation, showing poor diagnostic accuracy and posing risks to patient care, highlighting the need for caution.

cover

Can GPT-4V Diagnose? A Deep Dive into AI’s Medical Imaging Capabilities

1 Apr 2025

GPT-4V shows potential in medical image interpretation but lacks diagnostic accuracy, highlighting risks and the need for caution in clinical applications.

cover

The Role of Human-in-the-Loop Preferences in Reward Function Learning for Humanoid Tasks

3 Dec 2024

Explore how human-in-the-loop preferences refine reward functions in tasks like humanoid running and jumping.

cover

Tracking Reward Function Improvement with Proxy Human Preferences in ICPL

3 Dec 2024

Explore how In-Context Preference Learning (ICPL) progressively refined reward functions in humanoid tasks using proxy human preferences.

cover

Few-shot In-Context Preference Learning Using Large Language Models: Environment Details

3 Dec 2024

Discover the key environment details, task descriptions, and metrics for 9 tasks in IsaacGym, as outlined in this paper.

cover

ICPL Baseline Methods: Disagreement Sampling and PrefPPO for Reward Learning

3 Dec 2024

Learn how disagreement sampling and PrefPPO optimize reward learning in reinforcement learning.