OpenMOSS

university

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

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

CCCCyx updated a collection about 7 hours ago

CCCCyx updated a collection about 7 hours ago

CCCCyx updated a collection about 14 hours ago

View all activity

Papers

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

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

View all Papers

OpenMOSS-Team 's papers 25

Submitted by

Xiaoran Liu (SII)

AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts

OpenMOSS-Team

Submitted by

Haowei Zhang

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

OpenMOSS-Team

Submitted by

Fu Jinlan

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

OpenMOSS-Team

FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

OpenMOSS-Team

Submitted by

yangjie

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

OpenMOSS-Team

Submitted by

Zhaoye Fei

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

OpenMOSS-Team

Submitted by

Xiaoran Liu (SII)

DiRL: An Efficient Post-Training Framework for Diffusion Language Models

OpenMOSS-Team

Submitted by

Xiaoran Liu (SII)

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

OpenMOSS-Team

Submitted by

Siyin Wang (SII)

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

OpenMOSS-Team

Submitted by

Tony.Li

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

OpenMOSS-Team

Submitted by

Siyin Wang (SII)

RoboOmni: Proactive Robot Manipulation in Omni-modal Context

OpenMOSS-Team

Submitted by

Siyin Wang (SII)

LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

OpenMOSS-Team