The second version of omnimodal large model Uni-MoE
AI & ML interests
None defined yet.
Recent Activity
Papers
Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE
Large Models based Multimodal Agent for Long Video Generation: https://github.com/HITsz-TMG/Anim-Director; https://github.com/HITsz-TMG/FilmAgent
-
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Paper • 2408.09787 • Published • 10 -
AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation
Paper • 2506.10540 • Published • 37 -
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
Paper • 2501.12909 • Published • 74
A diverse video understanding and reasoning benchmark
Data and filtering models of our financial open-source YiZhao Dataset.
-
HIT-TMG/YiZhao
Viewer • Updated • 47.5M • 1.48k • 6 -
HIT-TMG/yizhao-risk-zh-scorer
Text Classification • 0.1B • Updated • 19 • 2 -
HIT-TMG/yizhao-risk-en-scorer
Text Classification • 22.7M • Updated • 13 • 4 -
HIT-TMG/yizhao-fin-en-scorer
Text Classification • 22.7M • Updated • 14 • 3
-
HIT-TMG/TruthReader_RAG_train
Viewer • Updated • 7.16k • 101 • 6 -
HIT-TMG/Qwen1.5-14B-Chat_RAG-Reader
Text Generation • 14B • Updated • 10 -
HIT-TMG/Mixtral_13B_Chat_RAG-Reader
Text Generation • 13B • Updated • 8 -
HIT-TMG/bge-m3_RAG-conversational-IR
Sentence Similarity • 0.6B • Updated • 20 • 1
Text and multimodal embedding & reranking models
-
vec-ai/lychee-embed
Sentence Similarity • 2B • Updated • 15 • 9 -
vec-ai/lychee-rerank
Text Ranking • 2B • Updated • 13 • 4 -
vec-ai/lychee-rerank-mm
8B • Updated • 33 -
Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
Paper • 2510.14824 • Published • 1
The first version of Uni-MoE
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 28.9k • 43 -
KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
Feature Extraction • 0.5B • Updated • 12.9k • 47 -
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 18 -
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Paper • 2506.20923 • Published • 6
The second version of omnimodal large model Uni-MoE
Text and multimodal embedding & reranking models
-
vec-ai/lychee-embed
Sentence Similarity • 2B • Updated • 15 • 9 -
vec-ai/lychee-rerank
Text Ranking • 2B • Updated • 13 • 4 -
vec-ai/lychee-rerank-mm
8B • Updated • 33 -
Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
Paper • 2510.14824 • Published • 1
Large Models based Multimodal Agent for Long Video Generation: https://github.com/HITsz-TMG/Anim-Director; https://github.com/HITsz-TMG/FilmAgent
-
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Paper • 2408.09787 • Published • 10 -
AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation
Paper • 2506.10540 • Published • 37 -
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
Paper • 2501.12909 • Published • 74
A diverse video understanding and reasoning benchmark
The first version of Uni-MoE
Data and filtering models of our financial open-source YiZhao Dataset.
-
HIT-TMG/YiZhao
Viewer • Updated • 47.5M • 1.48k • 6 -
HIT-TMG/yizhao-risk-zh-scorer
Text Classification • 0.1B • Updated • 19 • 2 -
HIT-TMG/yizhao-risk-en-scorer
Text Classification • 22.7M • Updated • 13 • 4 -
HIT-TMG/yizhao-fin-en-scorer
Text Classification • 22.7M • Updated • 14 • 3
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 28.9k • 43 -
KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
Feature Extraction • 0.5B • Updated • 12.9k • 47 -
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 18 -
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Paper • 2506.20923 • Published • 6
-
HIT-TMG/TruthReader_RAG_train
Viewer • Updated • 7.16k • 101 • 6 -
HIT-TMG/Qwen1.5-14B-Chat_RAG-Reader
Text Generation • 14B • Updated • 10 -
HIT-TMG/Mixtral_13B_Chat_RAG-Reader
Text Generation • 13B • Updated • 8 -
HIT-TMG/bge-m3_RAG-conversational-IR
Sentence Similarity • 0.6B • Updated • 20 • 1