Reverse-Engineered Reasoning
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
AutoMV: An Automatic Multi-Agent System for Music Video Generation
COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
-
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
m-a-p/TreePO-Qwen2.5-7B
Text Generation • 8B • Updated • 50 • 2 -
m-a-p/TreePO_data
Viewer • Updated • 3.12k • 75 -
m-a-p/TreePO-Qwen2.5-7B_fixed-div
8B • Updated • 49
All 1.3B & 340M hybrid linear-attention experiments.
This is the collections of COIG-P's models
-
m-a-p/Infinity-Instruct-3M-0625-Llama3-8B-COIG-P
Text Generation • 8B • Updated • 45 -
m-a-p/Qwen2.5-Instruct-7B-COIG-P
Text Generation • 8B • Updated • 51 -
m-a-p/Infinity-Instruct-3M-0625-Mistral-7B-COIG-P
Text Generation • 7B • Updated • 49 -
m-a-p/Qwen2-Instruct-7B-COIG-P
Text Generation • 8B • Updated • 50
YuE: Open Full-song Generation Foundation Model
The checkpoints for the MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training.
Dataset and Models of Chinese Open Instruction Generalist Series.
Datasets, Benchmark and Models of ChatMusician: Understanding and Generating Music Intrinsically with LLM
Neo
https://arxiv.org/abs/2406.13923
CriticLean
Data and model collection for MARBLE: https://github.com/a43992899/MARBLE/
This is the collection of COIG-P's datasets
MuPT
-
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Paper • 2306.00107 • Published • 4 -
MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Paper • 2309.08730 • Published • 2 -
ChatMusician: Understanding and Generating Music Intrinsically with LLM
Paper • 2402.16153 • Published • 58 -
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Paper • 2401.11944 • Published • 27
This is the checkpoints and datasets of MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Reverse-Engineered Reasoning
https://arxiv.org/abs/2406.13923
-
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
m-a-p/TreePO-Qwen2.5-7B
Text Generation • 8B • Updated • 50 • 2 -
m-a-p/TreePO_data
Viewer • Updated • 3.12k • 75 -
m-a-p/TreePO-Qwen2.5-7B_fixed-div
8B • Updated • 49
CriticLean
All 1.3B & 340M hybrid linear-attention experiments.
Data and model collection for MARBLE: https://github.com/a43992899/MARBLE/
This is the collections of COIG-P's models
-
m-a-p/Infinity-Instruct-3M-0625-Llama3-8B-COIG-P
Text Generation • 8B • Updated • 45 -
m-a-p/Qwen2.5-Instruct-7B-COIG-P
Text Generation • 8B • Updated • 51 -
m-a-p/Infinity-Instruct-3M-0625-Mistral-7B-COIG-P
Text Generation • 7B • Updated • 49 -
m-a-p/Qwen2-Instruct-7B-COIG-P
Text Generation • 8B • Updated • 50
This is the collection of COIG-P's datasets
YuE: Open Full-song Generation Foundation Model
The checkpoints for the MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training.
MuPT
Dataset and Models of Chinese Open Instruction Generalist Series.
Datasets, Benchmark and Models of ChatMusician: Understanding and Generating Music Intrinsically with LLM
-
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Paper • 2306.00107 • Published • 4 -
MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Paper • 2309.08730 • Published • 2 -
ChatMusician: Understanding and Generating Music Intrinsically with LLM
Paper • 2402.16153 • Published • 58 -
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Paper • 2401.11944 • Published • 27
This is the checkpoints and datasets of MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Neo