-
Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs
Paper • 2503.16870 • Published • 5 -
Gemma 3 Technical Report
Paper • 2503.19786 • Published • 52 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 158 -
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
Paper • 2503.19855 • Published • 28
Souvik Mandal
Souvik3333
AI & ML interests
VLMs, LLMs, Confidence Score from VLMs
Recent Activity
new activity
about 6 hours ago
nanonets/Nanonets-OCR-s:License Clarification
updated
a model
about 6 hours ago
nanonets/Nanonets-OCR-s
published
a Space
1 day ago
Souvik3333/Nanonets-ocr-s
Organizations
Collections
1
datasets
0
None public yet