Scaling RL for Open-Ended Agents via Tournamentbased Relative Ranking
Alibaba-NLP
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
-
Alibaba-NLP/E2Rank-0.6B
Feature Extraction • 0.6B • Updated • 642 • 12 -
Alibaba-NLP/E2Rank-4B
Feature Extraction • 4B • Updated • 40 • 3 -
Alibaba-NLP/E2Rank-8B
Feature Extraction • 8B • Updated • 45 • 4 -
E^2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
Paper • 2510.22733 • Published • 31
GTE Models Based on ModernBERT
General Text Embedding Models Released by Tongyi Lab of Alibaba Group
-
Alibaba-NLP/gte-Qwen2-7B-instruct
Sentence Similarity • 8B • Updated • 78.1k • 477 -
Alibaba-NLP/gte-Qwen2-1.5B-instruct
Sentence Similarity • 2B • Updated • 109k • 225 -
Alibaba-NLP/gte-multilingual-base
Sentence Similarity • 0.3B • Updated • 1.44M • 341 -
Alibaba-NLP/gte-multilingual-reranker-base
Text Ranking • 0.3B • Updated • 301k • 172
Towards General Video Embeddings: Models and Benchmarks
-
Alibaba-NLP/GVE-3B
Sentence Similarity • 4B • Updated • 352 • 15 -
Alibaba-NLP/GVE-7B
Sentence Similarity • 8B • Updated • 1.95k • 17 -
Alibaba-NLP/UVRB
Updated • 1.59k • 4 -
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
Paper • 2510.27571 • Published • 17
A highly effective and efficient pointwise reranker built from a reasoning LLM, which excels across diverse relevance scenarios with low latency
General Multimodal Embedding Models Released by Tongyi Lab of Alibaba Group
Scaling RL for Open-Ended Agents via Tournamentbased Relative Ranking
Towards General Video Embeddings: Models and Benchmarks
-
Alibaba-NLP/GVE-3B
Sentence Similarity • 4B • Updated • 352 • 15 -
Alibaba-NLP/GVE-7B
Sentence Similarity • 8B • Updated • 1.95k • 17 -
Alibaba-NLP/UVRB
Updated • 1.59k • 4 -
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
Paper • 2510.27571 • Published • 17
Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
-
Alibaba-NLP/E2Rank-0.6B
Feature Extraction • 0.6B • Updated • 642 • 12 -
Alibaba-NLP/E2Rank-4B
Feature Extraction • 4B • Updated • 40 • 3 -
Alibaba-NLP/E2Rank-8B
Feature Extraction • 8B • Updated • 45 • 4 -
E^2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
Paper • 2510.22733 • Published • 31
A highly effective and efficient pointwise reranker built from a reasoning LLM, which excels across diverse relevance scenarios with low latency
GTE Models Based on ModernBERT
General Multimodal Embedding Models Released by Tongyi Lab of Alibaba Group
General Text Embedding Models Released by Tongyi Lab of Alibaba Group
-
Alibaba-NLP/gte-Qwen2-7B-instruct
Sentence Similarity • 8B • Updated • 78.1k • 477 -
Alibaba-NLP/gte-Qwen2-1.5B-instruct
Sentence Similarity • 2B • Updated • 109k • 225 -
Alibaba-NLP/gte-multilingual-base
Sentence Similarity • 0.3B • Updated • 1.44M • 341 -
Alibaba-NLP/gte-multilingual-reranker-base
Text Ranking • 0.3B • Updated • 301k • 172