-
Advancing Reference-free Evaluation of Video Captions with Factual Analysis
Paper • 2509.16538 • Published • 1 -
dipta007/VCInspector-7B
Image-Text-to-Text • 8B • Updated • 26 • 1 -
dipta007/VCInspector-3B
Image-Text-to-Text • 4B • Updated • 35 • 1 -
dipta007/ActivityNet-FG-It
Viewer • Updated • 242k • 41
Shubhashis Roy Dipta PRO
dipta007
AI & ML interests
Multimodal Understanding, Reasoning, Generation
Recent Activity
updated a model about 21 hours ago
dipta007/VCInspector-7B updated a model about 21 hours ago
dipta007/VCInspector-3B updated a dataset about 21 hours ago
dipta007/ActivityNet-FG-ItOrganizations
-
GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
Paper • 2601.06767 • Published -
dipta007/Ganit
Viewer • Updated • 32.3k • 57 -
dipta007/GanitLLM-4B_SFT_CGRPO
Text Generation • 196k • Updated • 1.74k -
dipta007/GanitLLM-4B_SFT_GRPO
Text Generation • 196k • Updated • 202 • 1
-
Advancing Reference-free Evaluation of Video Captions with Factual Analysis
Paper • 2509.16538 • Published • 1 -
dipta007/VCInspector-7B
Image-Text-to-Text • 8B • Updated • 26 • 1 -
dipta007/VCInspector-3B
Image-Text-to-Text • 4B • Updated • 35 • 1 -
dipta007/ActivityNet-FG-It
Viewer • Updated • 242k • 41
-
GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
Paper • 2601.06767 • Published -
dipta007/Ganit
Viewer • Updated • 32.3k • 57 -
dipta007/GanitLLM-4B_SFT_CGRPO
Text Generation • 196k • Updated • 1.74k -
dipta007/GanitLLM-4B_SFT_GRPO
Text Generation • 196k • Updated • 202 • 1
models 20
dipta007/VCInspector-7B
Image-Text-to-Text • 8B • Updated • 26 • 1
dipta007/VCInspector-3B
Image-Text-to-Text • 4B • Updated • 35 • 1
dipta007/GanitLLM-0.6B_CGRPO
Text Generation • 0.6B • Updated • 230
dipta007/GanitLLM-0.6B-SFT
Text Generation • 0.8B • Updated • 232
dipta007/GanitLLM-0.6B_SFT_GRPO
Text Generation • 0.8B • Updated • 227
dipta007/GanitLLM-0.6B_SFT_CGRPO
Text Generation • 0.8B • Updated • 230
dipta007/GanitLLM-1.7B_CGRPO
Text Generation • 2B • Updated • 228
dipta007/GanitLLM-1.7B-SFT
Text Generation • 2B • Updated • 226
dipta007/GanitLLM-1.7B_SFT_GRPO
Text Generation • 2B • Updated • 223
dipta007/GanitLLM-1.7B_SFT_CGRPO
Text Generation • 2B • Updated • 220
datasets 52
dipta007/ActivityNet-FG-It
Viewer • Updated • 242k • 41
dipta007/Ganit
Viewer • Updated • 32.3k • 57
dipta007/DistractMath-Bn
Viewer • Updated • 3.69k • 25
dipta007/dagger
Viewer • Updated • 6.48k • 27
dipta007/BanglaBias
Viewer • Updated • 200 • 35
dipta007/youcook2-retouch-prompts
Viewer • Updated • 3.18k • 16
dipta007/youcook2-retouch-videos
Viewer • Updated • 7 • 11
dipta007/APIGen-MT-5k-with-cot
Updated • 2
dipta007/APIGen-MT-5k-train-val
Viewer • Updated • 4.8k • 19
dipta007/APIGen-MT-5k-with-cot-v1-deepseek_deepseek
Viewer • Updated • 2.5k • 5