OpenMOSS

university

http://openmoss.sii.edu.cn/

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

ljbro submitted a paper about 6 hours ago

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

ljbro authored a paper about 24 hours ago

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

ljbro published a dataset 1 day ago

OpenMOSS-Team/GTAVBench

View all activity

Papers

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

MOSS-Image Technical Report

View all Papers

Articles

MOSS-Live: A Full-Duplex Real-Time Interaction System

OpenMOSS-Team 's papers 30

Submitted by

Jiajun Chen(SII)

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

OpenMOSS-Team

Submitted by

Xu Zhe

MOSS-Image Technical Report

OpenMOSS-Team

Submitted by

Xiaoran Liu (SII)

Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position

OpenMOSS-Team

Submitted by

yxzwang (SII)

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

OpenMOSS-Team

Submitted by

Pengyu Wang

MOSS-VL Technical Report

OpenMOSS-Team

Submitted by

FSY(SII)

WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning

OpenMOSS-Team

Submitted by

JunZhan

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

OpenMOSS-Team

Submitted by

Siyin Wang (SII)

In-Context World Modeling for Robotic Control

OpenMOSS-Team

2

Submitted by

Siyin Wang (SII)

World Action Models: The Next Frontier in Embodied AI

OpenMOSS-Team

Submitted by

zhiyuan zeng

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

OpenMOSS-Team

Submitted by

yitian gong

MOSS-TTS Technical Report

OpenMOSS-Team

Submitted by

Tony.Li

AI Can Learn Scientific Taste

OpenMOSS-Team