sabaridsnfuji/Qwen3-VL-4B-COMPASS-T-DINOv3
Updated
sabarinathan
sabaridsnfuji
AI & ML interests
Hi, I’m Sabarinathan, an AI Engineer and developer passionate about building robust and responsible multimodal models, including OCR and document understanding for English, Japanese, and Tamil.
My work spans speech recognition, image understanding, and transformer-based architectures.
Interests:
Vision-Language Models (VLM) and lightweight computer vision models
Natural Language Processing (NLP)
Automatic Speech Recognition (ASR)
Recent Activity
updated a model about 1 month ago
sabaridsnfuji/Qwen3-VL-4B-COMPASS-T-DINOv3 published a model about 1 month ago
sabaridsnfuji/Qwen3-VL-4B-COMPASS-T-DINOv3 commentedon an article about 1 month ago
What We Learned by Reproducing 2,200 papers from ICMLOrganizations
sabaridsnfuji/Qwen3-1.7B-tamil-16bit-Instruct
Text Generation • 2B • Updated • 236
sabaridsnfuji/Qwen3-VL-4B-COMPASS-T
Updated
sabaridsnfuji/SenseNova-SI-1.5-InternVL3-8B-spatial-analysis-stage2
Feature Extraction • 8B • Updated • 19
sabaridsnfuji/SenseNova-SI-1.5-InternVL3-8B-spatial-analysis
Feature Extraction • 8B • Updated • 14
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv8
Image-Text-to-Text • 4B • Updated • 5
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv6
Image-Text-to-Text • 4B • Updated • 6
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv5
Image-Text-to-Text • 4B • Updated • 5
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv4
Image-Text-to-Text • 4B • Updated • 5
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv3
Image-Text-to-Text • 4B • Updated • 4
sabaridsnfuji/Qwen3.5-4B-Spatial-Analysis
Image-Text-to-Text • 5B • Updated • 5
sabaridsnfuji/Qwen3-VL-8B-Spatial-Analysis
Image-Text-to-Text • 9B • Updated • 5
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv2
Image-Text-to-Text • 4B • Updated • 11 • 1
sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysis
Image-Text-to-Text • 4B • Updated • 32 • • 1
sabaridsnfuji/Qwen3-4B-Tamil-Classical-Poetry-merged
Text Generation • 4B • Updated • 8
sabaridsnfuji/Qwen3-4B-Tamil-Classical-Poetry-GRPO
Updated
sabaridsnfuji/Qwen3-8B-tamil-16bit-Instruct
Text Generation • 8B • Updated • 8 • 1
sabaridsnfuji/Qwen3-4B-tamil-16bit-Instruct
Text Generation • 4B • Updated • 18
sabaridsnfuji/Qwen3-0.6B-tamil-16bit-Instruct
Text Generation • 0.6B • Updated • 14
sabaridsnfuji/qwen2.5-3b-vl-RGB-Comb-new-spatial-prompt-16bit-instruct
Image-Text-to-Text • 4B • Updated • 8
sabaridsnfuji/gpt-oss-20b-tamil-16bit-Instruct
Text Generation • 21B • Updated • 11
sabaridsnfuji/doc-classifier-v2
Updated
sabaridsnfuji/doc-classifier
Updated
sabaridsnfuji/Qwen3-1.7B-Senthamizh-16bit
Text Generation • 2B • Updated • 10
sabaridsnfuji/Japanese-Receipt-VL-lfm2-450M-v2
0.5B • Updated • 16
sabaridsnfuji/lfm2-vl-450M-ja
0.5B • Updated • 4
sabaridsnfuji/Japanese-Receipt-VL-lfm2-450M
Image-Text-to-Text • 0.5B • Updated • 56 • 2
sabaridsnfuji/qwen2.5-3b_vl_RGB_Comb_newprompts-16bit-Instruct
Image-Text-to-Text • 4B • Updated • 7
sabaridsnfuji/Japanese-Receipt-VL-3B-JSON-v2
Image-Text-to-Text • 4B • Updated • 31 • 1
sabaridsnfuji/Japanese-floorplan_analysis-16bit
Image-Text-to-Text • 8B • Updated • 26