Aleksei Dorkin PRO
adorkin
AI & ML interests
Computational Linguistics
Recent Activity
liked a model 1 day ago
Linkup-Platform/linkup-sparseup-embed-v1 liked a dataset 4 days ago
TurkuNLP/WebDocumentDescriptors liked a model 5 days ago
knowledgator/gliformer-large-v1Organizations
-
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 168 • • 11 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 1.98k • • 7 -
nvidia/Qwen-3-Nemotron-32B-Reward
Text Classification • 32B • Updated • 904 • 20 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 9.14k • 49
-
TartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages
Paper • 2404.12845 • Published -
TartuNLP at EvaLatin 2024: Emotion Polarity Detection
Paper • 2405.01159 • Published -
TartuNLP @ AXOLOTL-24: Leveraging Classifier Output for New Sense Detection in Lexical Semantics
Paper • 2407.03861 • Published -
TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
Paper • 2504.21547 • Published
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 18.7k • 103 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 30.7k • 171 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 2.58M • • 804 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 2.11M • • 325
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 43.5k • • 224 -
nvidia/llama-3.1-nemoguard-8b-topic-control
Text Classification • Updated • 255 • 20 -
nvidia/llama-3.1-nemoguard-8b-content-safety
Text Classification • Updated • 338 • 38 -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 86.3k • 181
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 18.7k • 103 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 30.7k • 171 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 2.58M • • 804 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 2.11M • • 325
-
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 168 • • 11 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 1.98k • • 7 -
nvidia/Qwen-3-Nemotron-32B-Reward
Text Classification • 32B • Updated • 904 • 20 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 9.14k • 49
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 43.5k • • 224 -
nvidia/llama-3.1-nemoguard-8b-topic-control
Text Classification • Updated • 255 • 20 -
nvidia/llama-3.1-nemoguard-8b-content-safety
Text Classification • Updated • 338 • 38 -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 86.3k • 181
-
TartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages
Paper • 2404.12845 • Published -
TartuNLP at EvaLatin 2024: Emotion Polarity Detection
Paper • 2405.01159 • Published -
TartuNLP @ AXOLOTL-24: Leveraging Classifier Output for New Sense Detection in Lexical Semantics
Paper • 2407.03861 • Published -
TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
Paper • 2504.21547 • Published