OpenMOSS

university

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

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

xpqiu authored a paper about 1 hour ago

AI Can Learn Scientific Taste

lkdhy updated a model about 1 hour ago

OpenMOSS-Team/SciThinker-30B

lkdhy updated a model about 1 hour ago

OpenMOSS-Team/SciThinker-4B

View all activity

Papers

AI Can Learn Scientific Taste

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

View all Papers

OpenMOSS-Team 's Papers 19

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

Submitted by

yitian gong

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models

OpenMOSS-Team

Submitted by

SII-liangtianyi

MOVA: Towards Scalable and Synchronized Video-Audio Generation

OpenMOSS-Team

Submitted by

XinghaoWang

Prism: Spectral-Aware Block-Sparse Attention

OpenMOSS-Team

Submitted by

Xiaoran Liu (SII)

FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation

OpenMOSS-Team

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

9

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

Submitted by

QinyuanCheng

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

OpenMOSS-Team