The second version of omnimodal large model Uni-MoE
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
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.
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 15k • 100 -
KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
Feature Extraction • 0.5B • Updated • 5.43k • 68 -
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 19 -
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Paper • 2506.20923 • Published • 10
-
KaLM-Embedding/KaLM-Reranker-V1-Nano
Text Ranking • 0.8B • Updated • 689 • 6 -
KaLM-Embedding/KaLM-Reranker-V1-Small
Text Ranking • 2B • Updated • 465 • 4 -
KaLM-Embedding/KaLM-Reranker-V1-Large
Text Ranking • 8B • Updated • 176 • 2 -
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
Paper • 2606.22807 • Published • 49
The second version of omnimodal large model Uni-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
The first version of Uni-MoE
Data and filtering models of our financial open-source YiZhao Dataset.
Text and multimodal embedding & reranking models
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 15k • 100 -
KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
Feature Extraction • 0.5B • Updated • 5.43k • 68 -
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 19 -
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Paper • 2506.20923 • Published • 10
-
KaLM-Embedding/KaLM-Reranker-V1-Nano
Text Ranking • 0.8B • Updated • 689 • 6 -
KaLM-Embedding/KaLM-Reranker-V1-Small
Text Ranking • 2B • Updated • 465 • 4 -
KaLM-Embedding/KaLM-Reranker-V1-Large
Text Ranking • 8B • Updated • 176 • 2 -
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
Paper • 2606.22807 • Published • 49