Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

[Arxiv 2024] Official Implementation of the paper: "Towards Robust Instruction Tuning on Multimodal Large Language Models"

KAIROS: An LLM Eval Technique to Evaluate Multi-Agent Social Interactions

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

Codebase for ProactiveAI in conversations

This repository contains the official implementation of Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned