Aleksei Dorkin PRO
adorkin
AI & ML interests
Computational Linguistics
Recent Activity
upvoted an article about 10 hours ago
Introducing BERTopic Integration with the Hugging Face Hub liked a dataset about 10 hours ago
jasperai/monet liked a model about 10 hours ago
nvidia/LocateAnything-3BOrganizations
-
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 51 • • 11 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 516 • • 7 -
nvidia/Qwen-3-Nemotron-32B-Reward
Text Classification • 32B • Updated • 91 • 20 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 24.4k • 45
-
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 • 86.1k • 96 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 30.4k • 164 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 1.87M • • 693 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 2.79M • 272
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 18.8k • • 221 -
nvidia/llama-3.1-nemoguard-8b-topic-control
Text Classification • Updated • 2.51k • 18 -
nvidia/llama-3.1-nemoguard-8b-content-safety
Text Classification • Updated • 2.33k • 35 -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 1.22M • 179
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 86.1k • 96 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 30.4k • 164 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 1.87M • • 693 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 2.79M • 272
-
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 51 • • 11 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 516 • • 7 -
nvidia/Qwen-3-Nemotron-32B-Reward
Text Classification • 32B • Updated • 91 • 20 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 24.4k • 45
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 18.8k • • 221 -
nvidia/llama-3.1-nemoguard-8b-topic-control
Text Classification • Updated • 2.51k • 18 -
nvidia/llama-3.1-nemoguard-8b-content-safety
Text Classification • Updated • 2.33k • 35 -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 1.22M • 179
-
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