OpenBMB

community

https://www.openbmb.cn

Activity Feed Request to join this org

AI & ML interests

Large Language Models

Recent Activity

tc-mb new activity about 4 hours ago

openbmb/MiniCPM-o-4_5:Fix audio placeholder length mismatch for merged audio inputs

tc-mb new activity 1 day ago

openbmb/MiniCPM-o-4_5:Update modeling_minicpmo.py

tc-mb new activity 6 days ago

openbmb/MiniCPM-V-4.6:fix: README fine-tuning links

View all activity

Papers

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

Rethinking the Role of Efficient Attention in Hybrid Architectures

View all Papers

in openbmb/MiniCPM-o-4_5 about 4 hours ago

Fix audio placeholder length mismatch for merged audio inputs

#19 opened about 22 hours ago by

in openbmb/MiniCPM-o-4_5 1 day ago

Update modeling_minicpmo.py

#18 opened 3 days ago by

in openbmb/MiniCPM-V-4.6 6 days ago

fix: README fine-tuning links

#10 opened 6 days ago by

authored a paper 6 days ago

Memory Shot for Long-Term Dialogue

Paper • 2606.28338 • Published May 30 • 2

updated a Space 6 days ago

VoxCPM Demo

VoxCPM2 Nano-vLLM Demo

submitted a paper to Daily Papers 13 days ago

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

Paper • 2606.18831 • Published 21 days ago • 7

in openbmb/MiniCPM5-1B 15 days ago

Base model link broken

#19 opened about 1 month ago by

authored a paper 20 days ago

Liberating LLM Capabilities in Full-Duplex Speech Models

Paper • 2606.07547 • Published May 4 • 8

submitted a paper to Daily Papers 20 days ago

Rethinking the Role of Efficient Attention in Hybrid Architectures

Paper • 2606.15378 • Published 25 days ago • 18

authored a paper 22 days ago

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Paper • 2604.27393 • Published Apr 30 • 81

authored a paper 22 days ago

MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis

Paper • 2606.13782 • Published 27 days ago • 2

in openbmb/MA-ProofBench 22 days ago

Update README

#1 opened 22 days ago by

published a dataset 22 days ago

openbmb/MA-ProofBench

Viewer • Updated 22 days ago • 200 • 603 • 6

updated a dataset 22 days ago

openbmb/MA-ProofBench

Viewer • Updated 22 days ago • 200 • 603 • 6

authored 3 papers about 1 month ago

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models

Paper • 2601.01373 • Published Jan 4 • 1

FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding

Paper • 2602.03417 • Published Feb 3

MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling

Paper • 2602.11761 • Published Feb 12 • 8

cyl

submitted a paper to Daily Papers about 2 months ago

The Unlearnability Phenomenon in RLVR for Language Models

Paper • 2605.16787 • Published May 16 • 6

cyl

authored a paper about 2 months ago

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

Paper • 2504.05419 • Published Apr 7, 2025 • 2

authored a paper about 2 months ago

LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?

Paper • 2605.08985 • Published May 9 • 23