OpenMOSS

university

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

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

kiiic updated a collection about 18 hours ago

kiiic published an article about 18 hours ago

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

zylin12 new activity 4 days ago

OpenMOSS-Team/MOSS-Transcribe-Diarize:Model enters a repetitive generation loop on music-only audio until the token limit is reached

View all activity

Papers

MOSS-Image Technical Report

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

View all Papers

Articles

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

about 18 hours ago

OpenMOSS-Team 's papers 29

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

Submitted by

Yuan-Li-FNLP

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

OpenMOSS-Team